diff options
250 files changed, 16311 insertions, 4171 deletions
diff --git a/.gitattributes b/.gitattributes index 8ce9c6b888..1bdc91e282 100644 --- a/.gitattributes +++ b/.gitattributes @@ -1,8 +1,10 @@ * whitespace=!indent,trail,space *.[ch] whitespace=indent,trail,space diff=cpp *.sh whitespace=indent,trail,space eol=lf -*.perl eol=lf -*.pm eol=lf +*.perl eol=lf diff=perl +*.pl eof=lf diff=perl +*.pm eol=lf diff=perl +*.py eol=lf diff=python /Documentation/git-*.txt eol=lf /command-list.txt eol=lf /GIT-VERSION-GEN eol=lf diff --git a/.gitignore b/.gitignore index 833ef3b0b7..b2a1ae4a1d 100644 --- a/.gitignore +++ b/.gitignore @@ -3,6 +3,7 @@ /GIT-LDFLAGS /GIT-PREFIX /GIT-PERL-DEFINES +/GIT-PERL-HEADER /GIT-PYTHON-VARS /GIT-SCRIPT-DEFINES /GIT-USER-AGENT @@ -34,6 +35,7 @@ /git-clone /git-column /git-commit +/git-commit-graph /git-commit-tree /git-config /git-count-objects @@ -140,6 +142,7 @@ /git-rm /git-send-email /git-send-pack +/git-serve /git-sh-i18n /git-sh-i18n--envsubst /git-sh-setup @@ -25,8 +25,8 @@ Ben Walton <bdwalton@gmail.com> <bwalton@artsci.utoronto.ca> Benoit Sigoure <tsunanet@gmail.com> <tsuna@lrde.epita.fr> Bernt Hansen <bernt@norang.ca> <bernt@alumni.uwaterloo.ca> Brandon Casey <drafnel@gmail.com> <casey@nrlssc.navy.mil> -brian m. carlson <sandals@crustytoothpaste.ath.cx> Brian M. Carlson <sandals@crustytoothpaste.ath.cx> -brian m. carlson <sandals@crustytoothpaste.ath.cx> <sandals@crustytoothpaste.net> +brian m. carlson <sandals@crustytoothpaste.net> Brian M. Carlson <sandals@crustytoothpaste.ath.cx> +brian m. carlson <sandals@crustytoothpaste.net> <sandals@crustytoothpaste.ath.cx> Bryan Larsen <bryan@larsen.st> <bryan.larsen@gmail.com> Bryan Larsen <bryan@larsen.st> <bryanlarsen@yahoo.com> Cheng Renquan <crquan@gmail.com> diff --git a/Documentation/Makefile b/Documentation/Makefile index 6232143cb9..fa9e5c0acd 100644 --- a/Documentation/Makefile +++ b/Documentation/Makefile @@ -78,6 +78,7 @@ TECH_DOCS += technical/pack-heuristics TECH_DOCS += technical/pack-protocol TECH_DOCS += technical/protocol-capabilities TECH_DOCS += technical/protocol-common +TECH_DOCS += technical/protocol-v2 TECH_DOCS += technical/racy-git TECH_DOCS += technical/send-pack-pipeline TECH_DOCS += technical/shallow diff --git a/Documentation/RelNotes/2.18.0.txt b/Documentation/RelNotes/2.18.0.txt index 31c3f6d670..fccc2f34ef 100644 --- a/Documentation/RelNotes/2.18.0.txt +++ b/Documentation/RelNotes/2.18.0.txt @@ -44,6 +44,44 @@ UI, Workflows & Features * "git mergetools" learned talking to guiffy. + * The scripts in contrib/emacs/ have outlived their usefulness and + have been replaced with a stub that errors out and tells the user + there are replacements. + + * The new "checkout-encoding" attribute can ask Git to convert the + contents to the specified encoding when checking out to the working + tree (and the other way around when checking in). + + * The "git config" command uses separate options e.g. "--int", + "--bool", etc. to specify what type the caller wants the value to + be interpreted as. A new "--type=<typename>" option has been + introduced, which would make it cleaner to define new types. + + * "git config --get" learned the "--default" option, to help the + calling script. Building on top of the above changes, the + "git config" learns "--type=color" type. Taken together, you can + do things like "git config --get foo.color --default blue" and get + the ANSI color sequence for the color given to foo.color variable, + or "blue" if the variable does not exist. + + * "git ls-remote" learned an option to allow sorting its output based + on the refnames being shown. + + * The command line completion (in contrib/) has been taught that "git + stash save" has been deprecated ("git stash push" is the preferred + spelling in the new world) and does not offer it as a possible + completion candidate when "git stash push" can be. + + * "git gc --prune=nonsense" spent long time repacking and then + silently failed when underlying "git prune --expire=nonsense" + failed to parse its command line. This has been corrected. + + * Error messages from "git push" can be painted for more visibility. + + * "git http-fetch" (deprecated) had an optional and experimental + "feature" to fetch only commits and/or trees, which nobody used. + This has been removed. + Performance, Internal Implementation, Development Support etc. @@ -118,6 +156,30 @@ Performance, Internal Implementation, Development Support etc. fast-import.c, which in turn has become the first user of the mem-pool API. + * A build-time option has been added to allow Git to be told to refer + to its associated files relative to the main binary, in the same + way that has been possible on Windows for quite some time, for + Linux, BSDs and Darwin. + + * Precompute and store information necessary for ancestry traversal + in a separate file to optimize graph walking. + + * The effort to pass the repository in-core structure throughout the + API continues. This round deals with the code that implements the + refs/replace/ mechanism. + + * The build procedure "make DEVELOPER=YesPlease" learned to enable a + bit more warning options depending on the compiler used to help + developers more. There also is "make DEVOPTS=tokens" knob + available now, for those who want to help fixing warnings we + usually ignore, for example. + + * A new version of the transport protocol is being worked on. + + * The code to interface to GPG has been restructured somewhat to make + it cleaner to integrate with other types of signature systems later. + + Also contains various documentation updates and code clean-ups. @@ -183,6 +245,53 @@ Fixes since v2.17 attacker's control) buffer overflow. (merge d8579accfa bp/fsmonitor-bufsize-fix later to maint). + * Recent simplification of build procedure forgot a bit of tweak to + the build procedure of contrib/mw-to-git/ + (merge d8698987f3 ab/simplify-perl-makefile later to maint). + + * Moving a submodule that itself has submodule in it with "git mv" + forgot to make necessary adjustment to the nested sub-submodules; + now the codepath learned to recurse into the submodules. + + * "git config --unset a.b", when "a.b" is the last variable in an + otherwise empty section "a", left an empty section "a" behind, and + worse yet, a subsequent "git config a.c value" did not reuse that + empty shell and instead created a new one. These have been + (partially) corrected. + (merge c71d8bb38a js/empty-config-section-fix later to maint). + + * "git worktree remove" learned that "-f" is a shorthand for + "--force" option, just like for "git worktree add". + (merge d228eea514 sb/worktree-remove-opt-force later to maint). + + * The completion script (in contrib/) learned to clear cached list of + command line options upon dot-sourcing it again in a more efficient + way. + (merge 94408dc71c sg/completion-clear-cached later to maint). + + * "git svn" had a minor thinko/typo which has been fixed. + (merge 51db271587 ab/git-svn-get-record-typofix later to maint). + + * During a "rebase -i" session, the code could give older timestamp + to commits created by later "pick" than an earlier "reword", which + has been corrected. + (merge 12f7babd6b js/ident-date-fix later to maint). + + * "git submodule status" did not check the symbolic revision name it + computed for the submodule HEAD is not the NULL, and threw it at + printf routines, which has been corrected. + (merge 0b5e2ea7cf nd/submodule-status-fix later to maint). + + * When fed input that already has In-Reply-To: and/or References: + headers and told to add the same information, "git send-email" + added these headers separately, instead of appending to an existing + one, which is a violation of the RFC. This has been corrected. + (merge 256be1d3f0 sa/send-email-dedup-some-headers later to maint). + + * "git fast-export" had a regression in v2.15.0 era where it skipped + some merge commits in certain cases, which has been corrected. + (merge be011bbe00 ma/fast-export-skip-merge-fix later to maint). + * Other minor doc, test and build updates and code cleanups. (merge 248f66ed8e nd/trace-with-env later to maint). (merge 14ced5562c ys/bisect-object-id-missing-conversion-fix later to maint). @@ -198,3 +307,6 @@ Fixes since v2.17 (merge decf711fc1 ps/test-chmtime-get later to maint). (merge 22d11a6e8e es/worktree-docs later to maint). (merge 92a5dbbc22 tg/use-git-contacts later to maint). + (merge adc887221f tq/t1510 later to maint). + (merge bed21a8ad6 sg/doc-gc-quote-mismatch-fix later to maint). + (merge 73364e4f10 tz/doc-git-urls-reference later to maint). diff --git a/Documentation/config.txt b/Documentation/config.txt index d6bcb5dcb6..84e2891aed 100644 --- a/Documentation/config.txt +++ b/Documentation/config.txt @@ -530,6 +530,12 @@ core.autocrlf:: This variable can be set to 'input', in which case no output conversion is performed. +core.checkRoundtripEncoding:: + A comma and/or whitespace separated list of encodings that Git + performs UTF-8 round trip checks on if they are used in an + `working-tree-encoding` attribute (see linkgit:gitattributes[5]). + The default value is `SHIFT-JIS`. + core.symlinks:: If false, symbolic links are checked out as small plain files that contain the link text. linkgit:git-update-index[1] and @@ -898,6 +904,10 @@ core.notesRef:: This setting defaults to "refs/notes/commits", and it can be overridden by the `GIT_NOTES_REF` environment variable. See linkgit:git-notes[1]. +core.commitGraph:: + Enable git commit graph feature. Allows reading from the + commit-graph file. + core.sparseCheckout:: Enable "sparse checkout" feature. See section "Sparse checkout" in linkgit:git-read-tree[1] for more information. @@ -1092,6 +1102,16 @@ clean.requireForce:: A boolean to make git-clean do nothing unless given -f, -i or -n. Defaults to true. +color.advice:: + A boolean to enable/disable color in hints (e.g. when a push + failed, see `advice.*` for a list). May be set to `always`, + `false` (or `never`) or `auto` (or `true`), in which case colors + are used only when the error output goes to a terminal. If + unset, then the value of `color.ui` is used (`auto` by default). + +color.advice.hint:: + Use customized color for hints. + color.branch:: A boolean to enable/disable color in the output of linkgit:git-branch[1]. May be set to `always`, @@ -1194,6 +1214,15 @@ color.pager:: A boolean to enable/disable colored output when the pager is in use (default is true). +color.push:: + A boolean to enable/disable color in push errors. May be set to + `always`, `false` (or `never`) or `auto` (or `true`), in which + case colors are used only when the error output goes to a terminal. + If unset, then the value of `color.ui` is used (`auto` by default). + +color.push.error:: + Use customized color for push errors. + color.showBranch:: A boolean to enable/disable color in the output of linkgit:git-show-branch[1]. May be set to `always`, @@ -1222,6 +1251,15 @@ color.status.<slot>:: status short-format), or `unmerged` (files which have unmerged changes). +color.transport:: + A boolean to enable/disable color when pushes are rejected. May be + set to `always`, `false` (or `never`) or `auto` (or `true`), in which + case colors are used only when the error output goes to a terminal. + If unset, then the value of `color.ui` is used (`auto` by default). + +color.transport.rejected:: + Use customized color when a push was rejected. + color.ui:: This variable determines the default value for variables such as `color.diff` and `color.grep` that control the use of color @@ -1562,6 +1600,18 @@ gc.autoDetach:: Make `git gc --auto` return immediately and run in background if the system supports it. Default is true. +gc.bigPackThreshold:: + If non-zero, all packs larger than this limit are kept when + `git gc` is run. This is very similar to `--keep-base-pack` + except that all packs that meet the threshold are kept, not + just the base pack. Defaults to zero. Common unit suffixes of + 'k', 'm', or 'g' are supported. ++ +Note that if the number of kept packs is more than gc.autoPackLimit, +this configuration variable is ignored, all packs except the base pack +will be repacked. After this the number of packs should go below +gc.autoPackLimit and gc.bigPackThreshold should be respected again. + gc.logExpiry:: If the file gc.log exists, then `git gc --auto` won't run unless that file is more than 'gc.logExpiry' old. Default is @@ -2426,6 +2476,7 @@ pack.window:: pack.depth:: The maximum delta depth used by linkgit:git-pack-objects[1] when no maximum depth is given on the command line. Defaults to 50. + Maximum value is 4095. pack.windowMemory:: The maximum size of memory that is consumed by each thread @@ -2462,7 +2513,8 @@ pack.deltaCacheLimit:: The maximum size of a delta, that is cached in linkgit:git-pack-objects[1]. This cache is used to speed up the writing object phase by not having to recompute the final delta - result once the best match for all objects is found. Defaults to 1000. + result once the best match for all objects is found. + Defaults to 1000. Maximum value is 65535. pack.threads:: Specifies the number of threads to spawn when searching for best diff --git a/Documentation/fetch-options.txt b/Documentation/fetch-options.txt index 8631e365f4..97d3217df9 100644 --- a/Documentation/fetch-options.txt +++ b/Documentation/fetch-options.txt @@ -188,6 +188,14 @@ endif::git-pull[] is specified. This flag forces progress status even if the standard error stream is not directed to a terminal. +-o <option>:: +--server-option=<option>:: + Transmit the given string to the server when communicating using + protocol version 2. The given string must not contain a NUL or LF + character. + When multiple `--server-option=<option>` are given, they are all + sent to the other side in the order listed on the command line. + -4:: --ipv4:: Use IPv4 addresses only, ignoring IPv6 addresses. diff --git a/Documentation/git-apply.txt b/Documentation/git-apply.txt index 4ebc3d3271..c993fbf714 100644 --- a/Documentation/git-apply.txt +++ b/Documentation/git-apply.txt @@ -113,8 +113,10 @@ explained for the configuration variable `core.quotePath` (see linkgit:git-config[1]). -p<n>:: - Remove <n> leading slashes from traditional diff paths. The - default is 1. + Remove <n> leading path components (separated by slashes) from + traditional diff paths. E.g., with `-p2`, a patch against + `a/dir/file` will be applied directly to `file`. The default is + 1. -C<n>:: Ensure at least <n> lines of surrounding context match before diff --git a/Documentation/git-clone.txt b/Documentation/git-clone.txt index 42ca7b5095..b844b9957c 100644 --- a/Documentation/git-clone.txt +++ b/Documentation/git-clone.txt @@ -260,7 +260,7 @@ or `--mirror` is given) <repository>:: The (possibly remote) repository to clone from. See the - <<URLS,URLS>> section below for more information on specifying + <<URLS,GIT URLS>> section below for more information on specifying repositories. <directory>:: diff --git a/Documentation/git-commit-graph.txt b/Documentation/git-commit-graph.txt new file mode 100644 index 0000000000..4c97b555cc --- /dev/null +++ b/Documentation/git-commit-graph.txt @@ -0,0 +1,94 @@ +git-commit-graph(1) +=================== + +NAME +---- +git-commit-graph - Write and verify Git commit graph files + + +SYNOPSIS +-------- +[verse] +'git commit-graph read' [--object-dir <dir>] +'git commit-graph write' <options> [--object-dir <dir>] + + +DESCRIPTION +----------- + +Manage the serialized commit graph file. + + +OPTIONS +------- +--object-dir:: + Use given directory for the location of packfiles and commit graph + file. This parameter exists to specify the location of an alternate + that only has the objects directory, not a full .git directory. The + commit graph file is expected to be at <dir>/info/commit-graph and + the packfiles are expected to be in <dir>/pack. + + +COMMANDS +-------- +'write':: + +Write a commit graph file based on the commits found in packfiles. ++ +With the `--stdin-packs` option, generate the new commit graph by +walking objects only in the specified pack-indexes. (Cannot be combined +with --stdin-commits.) ++ +With the `--stdin-commits` option, generate the new commit graph by +walking commits starting at the commits specified in stdin as a list +of OIDs in hex, one OID per line. (Cannot be combined with +--stdin-packs.) ++ +With the `--append` option, include all commits that are present in the +existing commit-graph file. + +'read':: + +Read a graph file given by the commit-graph file and output basic +details about the graph file. Used for debugging purposes. + + +EXAMPLES +-------- + +* Write a commit graph file for the packed commits in your local .git folder. ++ +------------------------------------------------ +$ git commit-graph write +------------------------------------------------ + +* Write a graph file, extending the current graph file using commits +* in <pack-index>. ++ +------------------------------------------------ +$ echo <pack-index> | git commit-graph write --stdin-packs +------------------------------------------------ + +* Write a graph file containing all reachable commits. ++ +------------------------------------------------ +$ git show-ref -s | git commit-graph write --stdin-commits +------------------------------------------------ + +* Write a graph file containing all commits in the current +* commit-graph file along with those reachable from HEAD. ++ +------------------------------------------------ +$ git rev-parse HEAD | git commit-graph write --stdin-commits --append +------------------------------------------------ + +* Read basic information from the commit-graph file. ++ +------------------------------------------------ +$ git commit-graph read +------------------------------------------------ + + +GIT +--- +Part of the linkgit:git[1] suite diff --git a/Documentation/git-config.txt b/Documentation/git-config.txt index e09ed5d7d5..18ddc78f42 100644 --- a/Documentation/git-config.txt +++ b/Documentation/git-config.txt @@ -9,13 +9,13 @@ git-config - Get and set repository or global options SYNOPSIS -------- [verse] -'git config' [<file-option>] [type] [--show-origin] [-z|--null] name [value [value_regex]] -'git config' [<file-option>] [type] --add name value -'git config' [<file-option>] [type] --replace-all name value [value_regex] -'git config' [<file-option>] [type] [--show-origin] [-z|--null] --get name [value_regex] -'git config' [<file-option>] [type] [--show-origin] [-z|--null] --get-all name [value_regex] -'git config' [<file-option>] [type] [--show-origin] [-z|--null] [--name-only] --get-regexp name_regex [value_regex] -'git config' [<file-option>] [type] [-z|--null] --get-urlmatch name URL +'git config' [<file-option>] [--type=<type>] [--show-origin] [-z|--null] name [value [value_regex]] +'git config' [<file-option>] [--type=<type>] --add name value +'git config' [<file-option>] [--type=<type>] --replace-all name value [value_regex] +'git config' [<file-option>] [--type=<type>] [--show-origin] [-z|--null] --get name [value_regex] +'git config' [<file-option>] [--type=<type>] [--show-origin] [-z|--null] --get-all name [value_regex] +'git config' [<file-option>] [--type=<type>] [--show-origin] [-z|--null] [--name-only] --get-regexp name_regex [value_regex] +'git config' [<file-option>] [--type=<type>] [-z|--null] --get-urlmatch name URL 'git config' [<file-option>] --unset name [value_regex] 'git config' [<file-option>] --unset-all name [value_regex] 'git config' [<file-option>] --rename-section old_name new_name @@ -38,12 +38,10 @@ existing values that match the regexp are updated or unset. If you want to handle the lines that do *not* match the regex, just prepend a single exclamation mark in front (see also <<EXAMPLES>>). -The type specifier can be either `--int` or `--bool`, to make -'git config' ensure that the variable(s) are of the given type and -convert the value to the canonical form (simple decimal number for int, -a "true" or "false" string for bool), or `--path`, which does some -path expansion (see `--path` below). If no type specifier is passed, no -checks or transformations are performed on the value. +The `--type=<type>` option instructs 'git config' to ensure that incoming and +outgoing values are canonicalize-able under the given <type>. If no +`--type=<type>` is given, no canonicalization will be performed. Callers may +unset an existing `--type` specifier with `--no-type`. When reading, the values are read from the system, global and repository local configuration files by default, and options @@ -160,30 +158,43 @@ See also <<FILES>>. --list:: List all variables set in config file, along with their values. ---bool:: - 'git config' will ensure that the output is "true" or "false" +--type <type>:: + 'git config' will ensure that any input or output is valid under the given + type constraint(s), and will canonicalize outgoing values in `<type>`'s + canonical form. ++ +Valid `<type>`'s include: ++ +- 'bool': canonicalize values as either "true" or "false". +- 'int': canonicalize values as simple decimal numbers. An optional suffix of + 'k', 'm', or 'g' will cause the value to be multiplied by 1024, 1048576, or + 1073741824 upon input. +- 'bool-or-int': canonicalize according to either 'bool' or 'int', as described + above. +- 'path': canonicalize by adding a leading `~` to the value of `$HOME` and + `~user` to the home directory for the specified user. This specifier has no + effect when setting the value (but you can use `git config section.variable + ~/` from the command line to let your shell do the expansion.) +- 'expiry-date': canonicalize by converting from a fixed or relative date-string + to a timestamp. This specifier has no effect when setting the value. +- 'color': When getting a value, canonicalize by converting to an ANSI color + escape sequence. When setting a value, a sanity-check is performed to ensure + that the given value is canonicalize-able as an ANSI color, but it is written + as-is. ++ +--bool:: --int:: - 'git config' will ensure that the output is a simple - decimal number. An optional value suffix of 'k', 'm', or 'g' - in the config file will cause the value to be multiplied - by 1024, 1048576, or 1073741824 prior to output. - --bool-or-int:: - 'git config' will ensure that the output matches the format of - either --bool or --int, as described above. - --path:: - `git config` will expand a leading `~` to the value of - `$HOME`, and `~user` to the home directory for the - specified user. This option has no effect when setting the - value (but you can use `git config section.variable ~/` - from the command line to let your shell do the expansion). - --expiry-date:: - `git config` will ensure that the output is converted from - a fixed or relative date-string to a timestamp. This option - has no effect when setting the value. + Historical options for selecting a type specifier. Prefer instead `--type`, + (see: above). + +--no-type:: + Un-sets the previously set type specifier (if one was previously set). This + option requests that 'git config' not canonicalize the retrieved variable. + `--no-type` has no effect without `--type=<type>` or `--<type>`. -z:: --null:: @@ -221,6 +232,8 @@ See also <<FILES>>. output it as the ANSI color escape sequence to the standard output. The optional `default` parameter is used instead, if there is no color configured for `name`. ++ +`--type=color [--default=<default>]` is preferred over `--get-color`. -e:: --edit:: @@ -233,6 +246,10 @@ See also <<FILES>>. using `--file`, `--global`, etc) and `on` when searching all config files. +--default <value>:: + When using `--get`, and the requested variable is not found, behave as if + <value> were the value assigned to the that variable. + CONFIGURATION ------------- `pager.config` is only respected when listing configuration, i.e., when diff --git a/Documentation/git-filter-branch.txt b/Documentation/git-filter-branch.txt index b634043183..1d4d2f8604 100644 --- a/Documentation/git-filter-branch.txt +++ b/Documentation/git-filter-branch.txt @@ -288,7 +288,7 @@ git filter-branch --parent-filter \ or even simpler: ----------------------------------------------- -echo "$commit-id $graft-id" >> .git/info/grafts +git replace --graft $commit-id $graft-id git filter-branch $graft-id..HEAD ----------------------------------------------- diff --git a/Documentation/git-format-patch.txt b/Documentation/git-format-patch.txt index 6cbe462a77..b41e1329a7 100644 --- a/Documentation/git-format-patch.txt +++ b/Documentation/git-format-patch.txt @@ -47,7 +47,7 @@ There are two ways to specify which commits to operate on. The first rule takes precedence in the case of a single <commit>. To apply the second rule, i.e., format everything since the beginning of -history up until <commit>, use the '\--root' option: `git format-patch +history up until <commit>, use the `--root` option: `git format-patch --root <commit>`. If you want to format only <commit> itself, you can do this with `git format-patch -1 <commit>`. diff --git a/Documentation/git-gc.txt b/Documentation/git-gc.txt index 3126e0dd00..bb376ac584 100644 --- a/Documentation/git-gc.txt +++ b/Documentation/git-gc.txt @@ -9,7 +9,7 @@ git-gc - Cleanup unnecessary files and optimize the local repository SYNOPSIS -------- [verse] -'git gc' [--aggressive] [--auto] [--quiet] [--prune=<date> | --no-prune] [--force] +'git gc' [--aggressive] [--auto] [--quiet] [--prune=<date> | --no-prune] [--force] [--keep-largest-pack] DESCRIPTION ----------- @@ -56,10 +56,16 @@ single pack using `git repack -d -l`. Setting the value of `gc.auto` to 0 disables automatic packing of loose objects. + If the number of packs exceeds the value of `gc.autoPackLimit`, -then existing packs (except those marked with a `.keep` file) +then existing packs (except those marked with a `.keep` file +or over `gc.bigPackThreshold` limit) are consolidated into a single pack by using the `-A` option of -'git repack'. Setting `gc.autoPackLimit` to 0 disables -automatic consolidation of packs. +'git repack'. +If the amount of memory is estimated not enough for `git repack` to +run smoothly and `gc.bigPackThreshold` is not set, the largest +pack will also be excluded (this is the equivalent of running `git gc` +with `--keep-base-pack`). +Setting `gc.autoPackLimit` to 0 disables automatic consolidation of +packs. + If houskeeping is required due to many loose objects or packs, all other housekeeping tasks (e.g. rerere, working trees, reflog...) will @@ -84,6 +90,11 @@ be performed as well. Force `git gc` to run even if there may be another `git gc` instance running on this repository. +--keep-largest-pack:: + All packs except the largest pack and those marked with a + `.keep` files are consolidated into a single pack. When this + option is used, `gc.bigPackThreshold` is ignored. + Configuration ------------- @@ -129,7 +140,7 @@ The optional configuration variable `gc.aggressiveWindow` controls how much time is spent optimizing the delta compression of the objects in the repository when the --aggressive option is specified. The larger the value, the more time is spent optimizing the delta compression. See -the documentation for the --window' option in linkgit:git-repack[1] for +the documentation for the --window option in linkgit:git-repack[1] for more details. This defaults to 250. Similarly, the optional configuration variable `gc.aggressiveDepth` diff --git a/Documentation/git-http-fetch.txt b/Documentation/git-http-fetch.txt index 21a33d2c41..666b042679 100644 --- a/Documentation/git-http-fetch.txt +++ b/Documentation/git-http-fetch.txt @@ -15,8 +15,9 @@ DESCRIPTION ----------- Downloads a remote Git repository via HTTP. -*NOTE*: use of this command without -a is deprecated. The -a -behaviour will become the default in a future release. +This command always gets all objects. Historically, there were three options +`-a`, `-c` and `-t` for choosing which objects to download. They are now +silently ignored. OPTIONS ------- @@ -24,12 +25,8 @@ commit-id:: Either the hash or the filename under [URL]/refs/ to pull. --c:: - Get the commit objects. --t:: - Get trees associated with the commit objects. --a:: - Get all the objects. +-a, -c, -t:: + These options are ignored for historical reasons. -v:: Report what is downloaded. diff --git a/Documentation/git-log.txt b/Documentation/git-log.txt index 5437f8b0f0..90761f1694 100644 --- a/Documentation/git-log.txt +++ b/Documentation/git-log.txt @@ -9,7 +9,7 @@ git-log - Show commit logs SYNOPSIS -------- [verse] -'git log' [<options>] [<revision range>] [[\--] <path>...] +'git log' [<options>] [<revision range>] [[--] <path>...] DESCRIPTION ----------- @@ -90,13 +90,13 @@ include::line-range-format.txt[] ways to spell <revision range>, see the 'Specifying Ranges' section of linkgit:gitrevisions[7]. -[\--] <path>...:: +[--] <path>...:: Show only commits that are enough to explain how the files that match the specified paths came to be. See 'History Simplification' below for details and other simplification modes. + -Paths may need to be prefixed with ``\-- '' to separate them from +Paths may need to be prefixed with `--` to separate them from options or the revision range, when confusion arises. include::rev-list-options.txt[] @@ -125,7 +125,7 @@ EXAMPLES `git log --since="2 weeks ago" -- gitk`:: Show the changes during the last two weeks to the file 'gitk'. - The ``--'' is necessary to avoid confusion with the *branch* named + The `--` is necessary to avoid confusion with the *branch* named 'gitk' `git log --name-status release..test`:: diff --git a/Documentation/git-ls-remote.txt b/Documentation/git-ls-remote.txt index 5f2628c8f8..b9fd3770a6 100644 --- a/Documentation/git-ls-remote.txt +++ b/Documentation/git-ls-remote.txt @@ -10,7 +10,7 @@ SYNOPSIS -------- [verse] 'git ls-remote' [--heads] [--tags] [--refs] [--upload-pack=<exec>] - [-q | --quiet] [--exit-code] [--get-url] + [-q | --quiet] [--exit-code] [--get-url] [--sort=<key>] [--symref] [<repository> [<refs>...]] DESCRIPTION @@ -60,6 +60,24 @@ OPTIONS upload-pack only shows the symref HEAD, so it will be the only one shown by ls-remote. +--sort=<key>:: + Sort based on the key given. Prefix `-` to sort in descending order + of the value. Supports "version:refname" or "v:refname" (tag names + are treated as versions). The "version:refname" sort order can also + be affected by the "versionsort.suffix" configuration variable. + See linkgit:git-for-each-ref[1] for more sort options, but be aware + keys like `committerdate` that require access to the objects + themselves will not work for refs whose objects have not yet been + fetched from the remote, and will give a `missing object` error. + +-o <option>:: +--server-option=<option>:: + Transmit the given string to the server when communicating using + protocol version 2. The given string must not contain a NUL or LF + character. + When multiple `--server-option=<option>` are given, they are all + sent to the other side in the order listed on the command line. + <repository>:: The "remote" repository to query. This parameter can be either a URL or the name of a remote (see the GIT URLS and @@ -90,6 +108,10 @@ EXAMPLES c5db5456ae3b0873fc659c19fafdde22313cc441 refs/tags/v0.99.2 7ceca275d047c90c0c7d5afb13ab97efdf51bd6e refs/tags/v0.99.3 +SEE ALSO +-------- +linkgit:git-check-ref-format[1]. + GIT --- Part of the linkgit:git[1] suite diff --git a/Documentation/git-pack-objects.txt b/Documentation/git-pack-objects.txt index 81bc490ac5..6bfac6b7ff 100644 --- a/Documentation/git-pack-objects.txt +++ b/Documentation/git-pack-objects.txt @@ -12,7 +12,7 @@ SYNOPSIS 'git pack-objects' [-q | --progress | --all-progress] [--all-progress-implied] [--no-reuse-delta] [--delta-base-offset] [--non-empty] [--local] [--incremental] [--window=<n>] [--depth=<n>] - [--revs [--unpacked | --all]] + [--revs [--unpacked | --all]] [--keep-pack=<pack-name>] [--stdout [--filter=<filter-spec>] | base-name] [--shallow] [--keep-true-parents] < object-list @@ -96,7 +96,9 @@ base-name:: it too deep affects the performance on the unpacker side, because delta data needs to be applied that many times to get to the necessary object. - The default value for --window is 10 and --depth is 50. ++ +The default value for --window is 10 and --depth is 50. The maximum +depth is 4095. --window-memory=<n>:: This option provides an additional limit on top of `--window`; @@ -126,6 +128,13 @@ base-name:: has a .keep file to be ignored, even if it would have otherwise been packed. +--keep-pack=<pack-name>:: + This flag causes an object already in the given pack to be + ignored, even if it would have otherwise been + packed. `<pack-name>` is the the pack file name without + leading directory (e.g. `pack-123.pack`). The option could be + specified multiple times to keep multiple packs. + --incremental:: This flag causes an object already in a pack to be ignored even if it would have otherwise been packed. diff --git a/Documentation/git-push.txt b/Documentation/git-push.txt index 5b08302fc2..34410f9fca 100644 --- a/Documentation/git-push.txt +++ b/Documentation/git-push.txt @@ -300,7 +300,7 @@ origin +master` to force a push to the `master` branch). See the These options are passed to linkgit:git-send-pack[1]. A thin transfer significantly reduces the amount of sent data when the sender and receiver share many of the same objects in common. The default is - \--thin. + `--thin`. -q:: --quiet:: diff --git a/Documentation/git-repack.txt b/Documentation/git-repack.txt index ae750e9e11..d90e7907f4 100644 --- a/Documentation/git-repack.txt +++ b/Documentation/git-repack.txt @@ -9,7 +9,7 @@ git-repack - Pack unpacked objects in a repository SYNOPSIS -------- [verse] -'git repack' [-a] [-A] [-d] [-f] [-F] [-l] [-n] [-q] [-b] [--window=<n>] [--depth=<n>] [--threads=<n>] +'git repack' [-a] [-A] [-d] [-f] [-F] [-l] [-n] [-q] [-b] [--window=<n>] [--depth=<n>] [--threads=<n>] [--keep-pack=<pack-name>] DESCRIPTION ----------- @@ -90,7 +90,9 @@ other objects in that pack they already have locally. space. `--depth` limits the maximum delta depth; making it too deep affects the performance on the unpacker side, because delta data needs to be applied that many times to get to the necessary object. - The default value for --window is 10 and --depth is 50. ++ +The default value for --window is 10 and --depth is 50. The maximum +depth is 4095. --threads=<n>:: This option is passed through to `git pack-objects`. @@ -133,6 +135,13 @@ other objects in that pack they already have locally. with `-b` or `repack.writeBitmaps`, as it ensures that the bitmapped packfile has the necessary objects. +--keep-pack=<pack-name>:: + Exclude the given pack from repacking. This is the equivalent + of having `.keep` file on the pack. `<pack-name>` is the the + pack file name without leading directory (e.g. `pack-123.pack`). + The option could be specified multiple times to keep multiple + packs. + --unpack-unreachable=<when>:: When loosening unreachable objects, do not bother loosening any objects older than `<when>`. This can be used to optimize out diff --git a/Documentation/git-replace.txt b/Documentation/git-replace.txt index e5c57ae6ef..246dc9943c 100644 --- a/Documentation/git-replace.txt +++ b/Documentation/git-replace.txt @@ -11,6 +11,7 @@ SYNOPSIS 'git replace' [-f] <object> <replacement> 'git replace' [-f] --edit <object> 'git replace' [-f] --graft <commit> [<parent>...] +'git replace' [-f] --convert-graft-file 'git replace' -d <object>... 'git replace' [--format=<format>] [-l [<pattern>]] @@ -87,9 +88,13 @@ OPTIONS content as <commit> except that its parents will be [<parent>...] instead of <commit>'s parents. A replacement ref is then created to replace <commit> with the newly created - commit. See contrib/convert-grafts-to-replace-refs.sh for an - example script based on this option that can convert grafts to - replace refs. + commit. Use `--convert-graft-file` to convert a + `$GIT_DIR/info/grafts` file and use replace refs instead. + +--convert-graft-file:: + Creates graft commits for all entries in `$GIT_DIR/info/grafts` + and deletes that file upon success. The purpose is to help users + with transitioning off of the now-deprecated graft file. -l <pattern>:: --list <pattern>:: diff --git a/Documentation/git-shortlog.txt b/Documentation/git-shortlog.txt index 5e35ea18ac..bc80905a8a 100644 --- a/Documentation/git-shortlog.txt +++ b/Documentation/git-shortlog.txt @@ -8,7 +8,7 @@ git-shortlog - Summarize 'git log' output SYNOPSIS -------- [verse] -'git shortlog' [<options>] [<revision range>] [[\--] <path>...] +'git shortlog' [<options>] [<revision range>] [[--] <path>...] git log --pretty=short | 'git shortlog' [<options>] DESCRIPTION @@ -69,11 +69,11 @@ them. ways to spell <revision range>, see the "Specifying Ranges" section of linkgit:gitrevisions[7]. -[\--] <path>...:: +[--] <path>...:: Consider only commits that are enough to explain how the files that match the specified paths came to be. + -Paths may need to be prefixed with "\-- " to separate them from +Paths may need to be prefixed with `--` to separate them from options or the revision range, when confusion arises. MAPPING AUTHORS diff --git a/Documentation/git-submodule.txt b/Documentation/git-submodule.txt index 71c5618e82..630999f41a 100644 --- a/Documentation/git-submodule.txt +++ b/Documentation/git-submodule.txt @@ -213,8 +213,8 @@ sync [--recursive] [--] [<path>...]:: submodule URLs change upstream and you need to update your local repositories accordingly. + -"git submodule sync" synchronizes all submodules while -"git submodule sync \-- A" synchronizes submodule "A" only. +`git submodule sync` synchronizes all submodules while +`git submodule sync -- A` synchronizes submodule "A" only. + If `--recursive` is specified, this command will recurse into the registered submodules, and sync any nested submodules within. diff --git a/Documentation/git-worktree.txt b/Documentation/git-worktree.txt index 2755ca90e3..afc6576a14 100644 --- a/Documentation/git-worktree.txt +++ b/Documentation/git-worktree.txt @@ -14,7 +14,7 @@ SYNOPSIS 'git worktree lock' [--reason <string>] <worktree> 'git worktree move' <worktree> <new-path> 'git worktree prune' [-n] [-v] [--expire <expire>] -'git worktree remove' [--force] <worktree> +'git worktree remove' [-f] <worktree> 'git worktree unlock' <worktree> DESCRIPTION @@ -61,8 +61,13 @@ $ git worktree add --track -b <branch> <path> <remote>/<branch> ------------ + If `<commit-ish>` is omitted and neither `-b` nor `-B` nor `--detach` used, -then, as a convenience, a new branch based at HEAD is created automatically, -as if `-b $(basename <path>)` was specified. +then, as a convenience, the new worktree is associated with a branch +(call it `<branch>`) named after `$(basename <path>)`. If `<branch>` +doesn't exist, a new branch based on HEAD is automatically created as +if `-b <branch>` was given. If `<branch>` does exist, it will be +checked out in the new worktree, if it's not checked out anywhere +else, otherwise the command will refuse to create the worktree (unless +`--force` is used). list:: diff --git a/Documentation/git.txt b/Documentation/git.txt index 4767860e72..c662f41c1d 100644 --- a/Documentation/git.txt +++ b/Documentation/git.txt @@ -11,7 +11,7 @@ SYNOPSIS [verse] 'git' [--version] [--help] [-C <path>] [-c <name>=<value>] [--exec-path[=<path>]] [--html-path] [--man-path] [--info-path] - [-p|--paginate|--no-pager] [--no-replace-objects] [--bare] + [-p|--paginate|-P|--no-pager] [--no-replace-objects] [--bare] [--git-dir=<path>] [--work-tree=<path>] [--namespace=<name>] [--super-prefix=<path>] <command> [<args>] @@ -103,6 +103,7 @@ foo.bar= ...`) sets `foo.bar` to the empty string which `git config configuration options (see the "Configuration Mechanism" section below). +-P:: --no-pager:: Do not pipe Git output into a pager. diff --git a/Documentation/gitattributes.txt b/Documentation/gitattributes.txt index 1094fe2b5b..ee210be3ec 100644 --- a/Documentation/gitattributes.txt +++ b/Documentation/gitattributes.txt @@ -279,6 +279,94 @@ few exceptions. Even though... catch potential problems early, safety triggers. +`working-tree-encoding` +^^^^^^^^^^^^^^^^^^^^^^^ + +Git recognizes files encoded in ASCII or one of its supersets (e.g. +UTF-8, ISO-8859-1, ...) as text files. Files encoded in certain other +encodings (e.g. UTF-16) are interpreted as binary and consequently +built-in Git text processing tools (e.g. 'git diff') as well as most Git +web front ends do not visualize the contents of these files by default. + +In these cases you can tell Git the encoding of a file in the working +directory with the `working-tree-encoding` attribute. If a file with this +attribute is added to Git, then Git reencodes the content from the +specified encoding to UTF-8. Finally, Git stores the UTF-8 encoded +content in its internal data structure (called "the index"). On checkout +the content is reencoded back to the specified encoding. + +Please note that using the `working-tree-encoding` attribute may have a +number of pitfalls: + +- Alternative Git implementations (e.g. JGit or libgit2) and older Git + versions (as of March 2018) do not support the `working-tree-encoding` + attribute. If you decide to use the `working-tree-encoding` attribute + in your repository, then it is strongly recommended to ensure that all + clients working with the repository support it. + + For example, Microsoft Visual Studio resources files (`*.rc`) or + PowerShell script files (`*.ps1`) are sometimes encoded in UTF-16. + If you declare `*.ps1` as files as UTF-16 and you add `foo.ps1` with + a `working-tree-encoding` enabled Git client, then `foo.ps1` will be + stored as UTF-8 internally. A client without `working-tree-encoding` + support will checkout `foo.ps1` as UTF-8 encoded file. This will + typically cause trouble for the users of this file. + + If a Git client, that does not support the `working-tree-encoding` + attribute, adds a new file `bar.ps1`, then `bar.ps1` will be + stored "as-is" internally (in this example probably as UTF-16). + A client with `working-tree-encoding` support will interpret the + internal contents as UTF-8 and try to convert it to UTF-16 on checkout. + That operation will fail and cause an error. + +- Reencoding content to non-UTF encodings can cause errors as the + conversion might not be UTF-8 round trip safe. If you suspect your + encoding to not be round trip safe, then add it to + `core.checkRoundtripEncoding` to make Git check the round trip + encoding (see linkgit:git-config[1]). SHIFT-JIS (Japanese character + set) is known to have round trip issues with UTF-8 and is checked by + default. + +- Reencoding content requires resources that might slow down certain + Git operations (e.g 'git checkout' or 'git add'). + +Use the `working-tree-encoding` attribute only if you cannot store a file +in UTF-8 encoding and if you want Git to be able to process the content +as text. + +As an example, use the following attributes if your '*.ps1' files are +UTF-16 encoded with byte order mark (BOM) and you want Git to perform +automatic line ending conversion based on your platform. + +------------------------ +*.ps1 text working-tree-encoding=UTF-16 +------------------------ + +Use the following attributes if your '*.ps1' files are UTF-16 little +endian encoded without BOM and you want Git to use Windows line endings +in the working directory. Please note, it is highly recommended to +explicitly define the line endings with `eol` if the `working-tree-encoding` +attribute is used to avoid ambiguity. + +------------------------ +*.ps1 text working-tree-encoding=UTF-16LE eol=CRLF +------------------------ + +You can get a list of all available encodings on your platform with the +following command: + +------------------------ +iconv --list +------------------------ + +If you do not know the encoding of a file, then you can use the `file` +command to guess the encoding: + +------------------------ +file foo.ps1 +------------------------ + + `ident` ^^^^^^^ diff --git a/Documentation/gitk.txt b/Documentation/gitk.txt index ca96c281d1..244cd01493 100644 --- a/Documentation/gitk.txt +++ b/Documentation/gitk.txt @@ -8,7 +8,7 @@ gitk - The Git repository browser SYNOPSIS -------- [verse] -'gitk' [<options>] [<revision range>] [\--] [<path>...] +'gitk' [<options>] [<revision range>] [--] [<path>...] DESCRIPTION ----------- diff --git a/Documentation/gitremote-helpers.txt b/Documentation/gitremote-helpers.txt index 4b8c93ec59..9d1459aac6 100644 --- a/Documentation/gitremote-helpers.txt +++ b/Documentation/gitremote-helpers.txt @@ -102,6 +102,14 @@ Capabilities for Pushing + Supported commands: 'connect'. +'stateless-connect':: + Experimental; for internal use only. + Can attempt to connect to a remote server for communication + using git's wire-protocol version 2. See the documentation + for the stateless-connect command for more information. ++ +Supported commands: 'stateless-connect'. + 'push':: Can discover remote refs and push local commits and the history leading up to them to new or existing remote refs. @@ -136,6 +144,14 @@ Capabilities for Fetching + Supported commands: 'connect'. +'stateless-connect':: + Experimental; for internal use only. + Can attempt to connect to a remote server for communication + using git's wire-protocol version 2. See the documentation + for the stateless-connect command for more information. ++ +Supported commands: 'stateless-connect'. + 'fetch':: Can discover remote refs and transfer objects reachable from them to the local object store. @@ -375,6 +391,22 @@ Supported if the helper has the "export" capability. + Supported if the helper has the "connect" capability. +'stateless-connect' <service>:: + Experimental; for internal use only. + Connects to the given remote service for communication using + git's wire-protocol version 2. Valid replies to this command + are empty line (connection established), 'fallback' (no smart + transport support, fall back to dumb transports) and just + exiting with error message printed (can't connect, don't bother + trying to fall back). After line feed terminating the positive + (empty) response, the output of the service starts. Messages + (both request and response) must consist of zero or more + PKT-LINEs, terminating in a flush packet. The client must not + expect the server to store any state in between request-response + pairs. After the connection ends, the remote helper exits. ++ +Supported if the helper has the "stateless-connect" capability. + If a fatal error occurs, the program writes the error message to stderr and exits. The caller should expect that a suitable error message has been printed if the child closes the connection without diff --git a/Documentation/glossary-content.txt b/Documentation/glossary-content.txt index 6b8888d123..6c2d23dc48 100644 --- a/Documentation/glossary-content.txt +++ b/Documentation/glossary-content.txt @@ -463,7 +463,7 @@ exclude;; [[def_push]]push:: Pushing a <<def_branch,branch>> means to get the branch's <<def_head_ref,head ref>> from a remote <<def_repository,repository>>, - find out if it is a direct ancestor to the branch's local + find out if it is an ancestor to the branch's local head ref, and in that case, putting all objects, which are <<def_reachable,reachable>> from the local head ref, and which are missing from the remote diff --git a/Documentation/technical/api-config.txt b/Documentation/technical/api-config.txt index 9a778b0cad..fa39ac9d71 100644 --- a/Documentation/technical/api-config.txt +++ b/Documentation/technical/api-config.txt @@ -47,21 +47,23 @@ will first feed the user-wide one to the callback, and then the repo-specific one; by overwriting, the higher-priority repo-specific value is left at the end). -The `git_config_with_options` function lets the caller examine config +The `config_with_options` function lets the caller examine config while adjusting some of the default behavior of `git_config`. It should almost never be used by "regular" Git code that is looking up configuration variables. It is intended for advanced callers like `git-config`, which are intentionally tweaking the normal config-lookup process. It takes two extra parameters: -`filename`:: -If this parameter is non-NULL, it specifies the name of a file to -parse for configuration, rather than looking in the usual files. Regular -`git_config` defaults to `NULL`. +`config_source`:: +If this parameter is non-NULL, it specifies the source to parse for +configuration, rather than looking in the usual files. See `struct +git_config_source` in `config.h` for details. Regular `git_config` defaults +to `NULL`. -`respect_includes`:: -Specify whether include directives should be followed in parsed files. -Regular `git_config` defaults to `1`. +`opts`:: +Specify options to adjust the behavior of parsing config files. See `struct +config_options` in `config.h` for details. As an example: regular `git_config` +sets `opts.respect_includes` to `1` by default. Reading Specific Files ---------------------- diff --git a/Documentation/technical/api-submodule-config.txt b/Documentation/technical/api-submodule-config.txt index ee907c4a82..fb06089393 100644 --- a/Documentation/technical/api-submodule-config.txt +++ b/Documentation/technical/api-submodule-config.txt @@ -38,7 +38,7 @@ Data Structures Functions --------- -`void submodule_free()`:: +`void submodule_free(struct repository *r)`:: Use these to free the internally cached values. diff --git a/Documentation/technical/commit-graph-format.txt b/Documentation/technical/commit-graph-format.txt new file mode 100644 index 0000000000..ad6af8105c --- /dev/null +++ b/Documentation/technical/commit-graph-format.txt @@ -0,0 +1,97 @@ +Git commit graph format +======================= + +The Git commit graph stores a list of commit OIDs and some associated +metadata, including: + +- The generation number of the commit. Commits with no parents have + generation number 1; commits with parents have generation number + one more than the maximum generation number of its parents. We + reserve zero as special, and can be used to mark a generation + number invalid or as "not computed". + +- The root tree OID. + +- The commit date. + +- The parents of the commit, stored using positional references within + the graph file. + +These positional references are stored as unsigned 32-bit integers +corresponding to the array position withing the list of commit OIDs. We +use the most-significant bit for special purposes, so we can store at most +(1 << 31) - 1 (around 2 billion) commits. + +== Commit graph files have the following format: + +In order to allow extensions that add extra data to the graph, we organize +the body into "chunks" and provide a binary lookup table at the beginning +of the body. The header includes certain values, such as number of chunks +and hash type. + +All 4-byte numbers are in network order. + +HEADER: + + 4-byte signature: + The signature is: {'C', 'G', 'P', 'H'} + + 1-byte version number: + Currently, the only valid version is 1. + + 1-byte Hash Version (1 = SHA-1) + We infer the hash length (H) from this value. + + 1-byte number (C) of "chunks" + + 1-byte (reserved for later use) + Current clients should ignore this value. + +CHUNK LOOKUP: + + (C + 1) * 12 bytes listing the table of contents for the chunks: + First 4 bytes describe the chunk id. Value 0 is a terminating label. + Other 8 bytes provide the byte-offset in current file for chunk to + start. (Chunks are ordered contiguously in the file, so you can infer + the length using the next chunk position if necessary.) Each chunk + ID appears at most once. + + The remaining data in the body is described one chunk at a time, and + these chunks may be given in any order. Chunks are required unless + otherwise specified. + +CHUNK DATA: + + OID Fanout (ID: {'O', 'I', 'D', 'F'}) (256 * 4 bytes) + The ith entry, F[i], stores the number of OIDs with first + byte at most i. Thus F[255] stores the total + number of commits (N). + + OID Lookup (ID: {'O', 'I', 'D', 'L'}) (N * H bytes) + The OIDs for all commits in the graph, sorted in ascending order. + + Commit Data (ID: {'C', 'G', 'E', 'T' }) (N * (H + 16) bytes) + * The first H bytes are for the OID of the root tree. + * The next 8 bytes are for the positions of the first two parents + of the ith commit. Stores value 0xffffffff if no parent in that + position. If there are more than two parents, the second value + has its most-significant bit on and the other bits store an array + position into the Large Edge List chunk. + * The next 8 bytes store the generation number of the commit and + the commit time in seconds since EPOCH. The generation number + uses the higher 30 bits of the first 4 bytes, while the commit + time uses the 32 bits of the second 4 bytes, along with the lowest + 2 bits of the lowest byte, storing the 33rd and 34th bit of the + commit time. + + Large Edge List (ID: {'E', 'D', 'G', 'E'}) [Optional] + This list of 4-byte values store the second through nth parents for + all octopus merges. The second parent value in the commit data stores + an array position within this list along with the most-significant bit + on. Starting at that array position, iterate through this list of commit + positions for the parents until reaching a value with the most-significant + bit on. The other bits correspond to the position of the last parent. + +TRAILER: + + H-byte HASH-checksum of all of the above. diff --git a/Documentation/technical/commit-graph.txt b/Documentation/technical/commit-graph.txt new file mode 100644 index 0000000000..0550c6d0dc --- /dev/null +++ b/Documentation/technical/commit-graph.txt @@ -0,0 +1,163 @@ +Git Commit Graph Design Notes +============================= + +Git walks the commit graph for many reasons, including: + +1. Listing and filtering commit history. +2. Computing merge bases. + +These operations can become slow as the commit count grows. The merge +base calculation shows up in many user-facing commands, such as 'merge-base' +or 'status' and can take minutes to compute depending on history shape. + +There are two main costs here: + +1. Decompressing and parsing commits. +2. Walking the entire graph to satisfy topological order constraints. + +The commit graph file is a supplemental data structure that accelerates +commit graph walks. If a user downgrades or disables the 'core.commitGraph' +config setting, then the existing ODB is sufficient. The file is stored +as "commit-graph" either in the .git/objects/info directory or in the info +directory of an alternate. + +The commit graph file stores the commit graph structure along with some +extra metadata to speed up graph walks. By listing commit OIDs in lexi- +cographic order, we can identify an integer position for each commit and +refer to the parents of a commit using those integer positions. We use +binary search to find initial commits and then use the integer positions +for fast lookups during the walk. + +A consumer may load the following info for a commit from the graph: + +1. The commit OID. +2. The list of parents, along with their integer position. +3. The commit date. +4. The root tree OID. +5. The generation number (see definition below). + +Values 1-4 satisfy the requirements of parse_commit_gently(). + +Define the "generation number" of a commit recursively as follows: + + * A commit with no parents (a root commit) has generation number one. + + * A commit with at least one parent has generation number one more than + the largest generation number among its parents. + +Equivalently, the generation number of a commit A is one more than the +length of a longest path from A to a root commit. The recursive definition +is easier to use for computation and observing the following property: + + If A and B are commits with generation numbers N and M, respectively, + and N <= M, then A cannot reach B. That is, we know without searching + that B is not an ancestor of A because it is further from a root commit + than A. + + Conversely, when checking if A is an ancestor of B, then we only need + to walk commits until all commits on the walk boundary have generation + number at most N. If we walk commits using a priority queue seeded by + generation numbers, then we always expand the boundary commit with highest + generation number and can easily detect the stopping condition. + +This property can be used to significantly reduce the time it takes to +walk commits and determine topological relationships. Without generation +numbers, the general heuristic is the following: + + If A and B are commits with commit time X and Y, respectively, and + X < Y, then A _probably_ cannot reach B. + +This heuristic is currently used whenever the computation is allowed to +violate topological relationships due to clock skew (such as "git log" +with default order), but is not used when the topological order is +required (such as merge base calculations, "git log --graph"). + +In practice, we expect some commits to be created recently and not stored +in the commit graph. We can treat these commits as having "infinite" +generation number and walk until reaching commits with known generation +number. + +Design Details +-------------- + +- The commit graph file is stored in a file named 'commit-graph' in the + .git/objects/info directory. This could be stored in the info directory + of an alternate. + +- The core.commitGraph config setting must be on to consume graph files. + +- The file format includes parameters for the object ID hash function, + so a future change of hash algorithm does not require a change in format. + +Future Work +----------- + +- The commit graph feature currently does not honor commit grafts. This can + be remedied by duplicating or refactoring the current graft logic. + +- The 'commit-graph' subcommand does not have a "verify" mode that is + necessary for integration with fsck. + +- The file format includes room for precomputed generation numbers. These + are not currently computed, so all generation numbers will be marked as + 0 (or "uncomputed"). A later patch will include this calculation. + +- After computing and storing generation numbers, we must make graph + walks aware of generation numbers to gain the performance benefits they + enable. This will mostly be accomplished by swapping a commit-date-ordered + priority queue with one ordered by generation number. The following + operations are important candidates: + + - paint_down_to_common() + - 'log --topo-order' + +- Currently, parse_commit_gently() requires filling in the root tree + object for a commit. This passes through lookup_tree() and consequently + lookup_object(). Also, it calls lookup_commit() when loading the parents. + These method calls check the ODB for object existence, even if the + consumer does not need the content. For example, we do not need the + tree contents when computing merge bases. Now that commit parsing is + removed from the computation time, these lookup operations are the + slowest operations keeping graph walks from being fast. Consider + loading these objects without verifying their existence in the ODB and + only loading them fully when consumers need them. Consider a method + such as "ensure_tree_loaded(commit)" that fully loads a tree before + using commit->tree. + +- The current design uses the 'commit-graph' subcommand to generate the graph. + When this feature stabilizes enough to recommend to most users, we should + add automatic graph writes to common operations that create many commits. + For example, one could compute a graph on 'clone', 'fetch', or 'repack' + commands. + +- A server could provide a commit graph file as part of the network protocol + to avoid extra calculations by clients. This feature is only of benefit if + the user is willing to trust the file, because verifying the file is correct + is as hard as computing it from scratch. + +Related Links +------------- +[0] https://bugs.chromium.org/p/git/issues/detail?id=8 + Chromium work item for: Serialized Commit Graph + +[1] https://public-inbox.org/git/20110713070517.GC18566@sigill.intra.peff.net/ + An abandoned patch that introduced generation numbers. + +[2] https://public-inbox.org/git/20170908033403.q7e6dj7benasrjes@sigill.intra.peff.net/ + Discussion about generation numbers on commits and how they interact + with fsck. + +[3] https://public-inbox.org/git/20170908034739.4op3w4f2ma5s65ku@sigill.intra.peff.net/ + More discussion about generation numbers and not storing them inside + commit objects. A valuable quote: + + "I think we should be moving more in the direction of keeping + repo-local caches for optimizations. Reachability bitmaps have been + a big performance win. I think we should be doing the same with our + properties of commits. Not just generation numbers, but making it + cheap to access the graph structure without zlib-inflating whole + commit objects (i.e., packv4 or something like the "metapacks" I + proposed a few years ago)." + +[4] https://public-inbox.org/git/20180108154822.54829-1-git@jeffhostetler.com/T/#u + A patch to remove the ahead-behind calculation from 'status'. diff --git a/Documentation/technical/pack-format.txt b/Documentation/technical/pack-format.txt index 8e5bf60be3..70a99fd142 100644 --- a/Documentation/technical/pack-format.txt +++ b/Documentation/technical/pack-format.txt @@ -36,6 +36,98 @@ Git pack format - The trailer records 20-byte SHA-1 checksum of all of the above. +=== Object types + +Valid object types are: + +- OBJ_COMMIT (1) +- OBJ_TREE (2) +- OBJ_BLOB (3) +- OBJ_TAG (4) +- OBJ_OFS_DELTA (6) +- OBJ_REF_DELTA (7) + +Type 5 is reserved for future expansion. Type 0 is invalid. + +=== Deltified representation + +Conceptually there are only four object types: commit, tree, tag and +blob. However to save space, an object could be stored as a "delta" of +another "base" object. These representations are assigned new types +ofs-delta and ref-delta, which is only valid in a pack file. + +Both ofs-delta and ref-delta store the "delta" to be applied to +another object (called 'base object') to reconstruct the object. The +difference between them is, ref-delta directly encodes 20-byte base +object name. If the base object is in the same pack, ofs-delta encodes +the offset of the base object in the pack instead. + +The base object could also be deltified if it's in the same pack. +Ref-delta can also refer to an object outside the pack (i.e. the +so-called "thin pack"). When stored on disk however, the pack should +be self contained to avoid cyclic dependency. + +The delta data is a sequence of instructions to reconstruct an object +from the base object. If the base object is deltified, it must be +converted to canonical form first. Each instruction appends more and +more data to the target object until it's complete. There are two +supported instructions so far: one for copy a byte range from the +source object and one for inserting new data embedded in the +instruction itself. + +Each instruction has variable length. Instruction type is determined +by the seventh bit of the first octet. The following diagrams follow +the convention in RFC 1951 (Deflate compressed data format). + +==== Instruction to copy from base object + + +----------+---------+---------+---------+---------+-------+-------+-------+ + | 1xxxxxxx | offset1 | offset2 | offset3 | offset4 | size1 | size2 | size3 | + +----------+---------+---------+---------+---------+-------+-------+-------+ + +This is the instruction format to copy a byte range from the source +object. It encodes the offset to copy from and the number of bytes to +copy. Offset and size are in little-endian order. + +All offset and size bytes are optional. This is to reduce the +instruction size when encoding small offsets or sizes. The first seven +bits in the first octet determines which of the next seven octets is +present. If bit zero is set, offset1 is present. If bit one is set +offset2 is present and so on. + +Note that a more compact instruction does not change offset and size +encoding. For example, if only offset2 is omitted like below, offset3 +still contains bits 16-23. It does not become offset2 and contains +bits 8-15 even if it's right next to offset1. + + +----------+---------+---------+ + | 10000101 | offset1 | offset3 | + +----------+---------+---------+ + +In its most compact form, this instruction only takes up one byte +(0x80) with both offset and size omitted, which will have default +values zero. There is another exception: size zero is automatically +converted to 0x10000. + +==== Instruction to add new data + + +----------+============+ + | 0xxxxxxx | data | + +----------+============+ + +This is the instruction to construct target object without the base +object. The following data is appended to the target object. The first +seven bits of the first octet determines the size of data in +bytes. The size must be non-zero. + +==== Reserved instruction + + +----------+============ + | 00000000 | + +----------+============ + +This is the instruction reserved for future expansion. + == Original (version 1) pack-*.idx files have the following format: - The header consists of 256 4-byte network byte order diff --git a/Documentation/technical/protocol-v2.txt b/Documentation/technical/protocol-v2.txt new file mode 100644 index 0000000000..d7b6f38e0a --- /dev/null +++ b/Documentation/technical/protocol-v2.txt @@ -0,0 +1,405 @@ + Git Wire Protocol, Version 2 +============================== + +This document presents a specification for a version 2 of Git's wire +protocol. Protocol v2 will improve upon v1 in the following ways: + + * Instead of multiple service names, multiple commands will be + supported by a single service + * Easily extendable as capabilities are moved into their own section + of the protocol, no longer being hidden behind a NUL byte and + limited by the size of a pkt-line + * Separate out other information hidden behind NUL bytes (e.g. agent + string as a capability and symrefs can be requested using 'ls-refs') + * Reference advertisement will be omitted unless explicitly requested + * ls-refs command to explicitly request some refs + * Designed with http and stateless-rpc in mind. With clear flush + semantics the http remote helper can simply act as a proxy + +In protocol v2 communication is command oriented. When first contacting a +server a list of capabilities will advertised. Some of these capabilities +will be commands which a client can request be executed. Once a command +has completed, a client can reuse the connection and request that other +commands be executed. + + Packet-Line Framing +--------------------- + +All communication is done using packet-line framing, just as in v1. See +`Documentation/technical/pack-protocol.txt` and +`Documentation/technical/protocol-common.txt` for more information. + +In protocol v2 these special packets will have the following semantics: + + * '0000' Flush Packet (flush-pkt) - indicates the end of a message + * '0001' Delimiter Packet (delim-pkt) - separates sections of a message + + Initial Client Request +------------------------ + +In general a client can request to speak protocol v2 by sending +`version=2` through the respective side-channel for the transport being +used which inevitably sets `GIT_PROTOCOL`. More information can be +found in `pack-protocol.txt` and `http-protocol.txt`. In all cases the +response from the server is the capability advertisement. + + Git Transport +~~~~~~~~~~~~~~~ + +When using the git:// transport, you can request to use protocol v2 by +sending "version=2" as an extra parameter: + + 003egit-upload-pack /project.git\0host=myserver.com\0\0version=2\0 + + SSH and File Transport +~~~~~~~~~~~~~~~~~~~~~~~~ + +When using either the ssh:// or file:// transport, the GIT_PROTOCOL +environment variable must be set explicitly to include "version=2". + + HTTP Transport +~~~~~~~~~~~~~~~~ + +When using the http:// or https:// transport a client makes a "smart" +info/refs request as described in `http-protocol.txt` and requests that +v2 be used by supplying "version=2" in the `Git-Protocol` header. + + C: Git-Protocol: version=2 + C: + C: GET $GIT_URL/info/refs?service=git-upload-pack HTTP/1.0 + +A v2 server would reply: + + S: 200 OK + S: <Some headers> + S: ... + S: + S: 000eversion 2\n + S: <capability-advertisement> + +Subsequent requests are then made directly to the service +`$GIT_URL/git-upload-pack`. (This works the same for git-receive-pack). + + Capability Advertisement +-------------------------- + +A server which decides to communicate (based on a request from a client) +using protocol version 2, notifies the client by sending a version string +in its initial response followed by an advertisement of its capabilities. +Each capability is a key with an optional value. Clients must ignore all +unknown keys. Semantics of unknown values are left to the definition of +each key. Some capabilities will describe commands which can be requested +to be executed by the client. + + capability-advertisement = protocol-version + capability-list + flush-pkt + + protocol-version = PKT-LINE("version 2" LF) + capability-list = *capability + capability = PKT-LINE(key[=value] LF) + + key = 1*(ALPHA | DIGIT | "-_") + value = 1*(ALPHA | DIGIT | " -_.,?\/{}[]()<>!@#$%^&*+=:;") + + Command Request +----------------- + +After receiving the capability advertisement, a client can then issue a +request to select the command it wants with any particular capabilities +or arguments. There is then an optional section where the client can +provide any command specific parameters or queries. Only a single +command can be requested at a time. + + request = empty-request | command-request + empty-request = flush-pkt + command-request = command + capability-list + [command-args] + flush-pkt + command = PKT-LINE("command=" key LF) + command-args = delim-pkt + *command-specific-arg + + command-specific-args are packet line framed arguments defined by + each individual command. + +The server will then check to ensure that the client's request is +comprised of a valid command as well as valid capabilities which were +advertised. If the request is valid the server will then execute the +command. A server MUST wait till it has received the client's entire +request before issuing a response. The format of the response is +determined by the command being executed, but in all cases a flush-pkt +indicates the end of the response. + +When a command has finished, and the client has received the entire +response from the server, a client can either request that another +command be executed or can terminate the connection. A client may +optionally send an empty request consisting of just a flush-pkt to +indicate that no more requests will be made. + + Capabilities +-------------- + +There are two different types of capabilities: normal capabilities, +which can be used to to convey information or alter the behavior of a +request, and commands, which are the core actions that a client wants to +perform (fetch, push, etc). + +Protocol version 2 is stateless by default. This means that all commands +must only last a single round and be stateless from the perspective of the +server side, unless the client has requested a capability indicating that +state should be maintained by the server. Clients MUST NOT require state +management on the server side in order to function correctly. This +permits simple round-robin load-balancing on the server side, without +needing to worry about state management. + + agent +~~~~~~~ + +The server can advertise the `agent` capability with a value `X` (in the +form `agent=X`) to notify the client that the server is running version +`X`. The client may optionally send its own agent string by including +the `agent` capability with a value `Y` (in the form `agent=Y`) in its +request to the server (but it MUST NOT do so if the server did not +advertise the agent capability). The `X` and `Y` strings may contain any +printable ASCII characters except space (i.e., the byte range 32 < x < +127), and are typically of the form "package/version" (e.g., +"git/1.8.3.1"). The agent strings are purely informative for statistics +and debugging purposes, and MUST NOT be used to programmatically assume +the presence or absence of particular features. + + ls-refs +~~~~~~~~~ + +`ls-refs` is the command used to request a reference advertisement in v2. +Unlike the current reference advertisement, ls-refs takes in arguments +which can be used to limit the refs sent from the server. + +Additional features not supported in the base command will be advertised +as the value of the command in the capability advertisement in the form +of a space separated list of features: "<command>=<feature 1> <feature 2>" + +ls-refs takes in the following arguments: + + symrefs + In addition to the object pointed by it, show the underlying ref + pointed by it when showing a symbolic ref. + peel + Show peeled tags. + ref-prefix <prefix> + When specified, only references having a prefix matching one of + the provided prefixes are displayed. + +The output of ls-refs is as follows: + + output = *ref + flush-pkt + ref = PKT-LINE(obj-id SP refname *(SP ref-attribute) LF) + ref-attribute = (symref | peeled) + symref = "symref-target:" symref-target + peeled = "peeled:" obj-id + + fetch +~~~~~~~ + +`fetch` is the command used to fetch a packfile in v2. It can be looked +at as a modified version of the v1 fetch where the ref-advertisement is +stripped out (since the `ls-refs` command fills that role) and the +message format is tweaked to eliminate redundancies and permit easy +addition of future extensions. + +Additional features not supported in the base command will be advertised +as the value of the command in the capability advertisement in the form +of a space separated list of features: "<command>=<feature 1> <feature 2>" + +A `fetch` request can take the following arguments: + + want <oid> + Indicates to the server an object which the client wants to + retrieve. Wants can be anything and are not limited to + advertised objects. + + have <oid> + Indicates to the server an object which the client has locally. + This allows the server to make a packfile which only contains + the objects that the client needs. Multiple 'have' lines can be + supplied. + + done + Indicates to the server that negotiation should terminate (or + not even begin if performing a clone) and that the server should + use the information supplied in the request to construct the + packfile. + + thin-pack + Request that a thin pack be sent, which is a pack with deltas + which reference base objects not contained within the pack (but + are known to exist at the receiving end). This can reduce the + network traffic significantly, but it requires the receiving end + to know how to "thicken" these packs by adding the missing bases + to the pack. + + no-progress + Request that progress information that would normally be sent on + side-band channel 2, during the packfile transfer, should not be + sent. However, the side-band channel 3 is still used for error + responses. + + include-tag + Request that annotated tags should be sent if the objects they + point to are being sent. + + ofs-delta + Indicate that the client understands PACKv2 with delta referring + to its base by position in pack rather than by an oid. That is, + they can read OBJ_OFS_DELTA (ake type 6) in a packfile. + +If the 'shallow' feature is advertised the following arguments can be +included in the clients request as well as the potential addition of the +'shallow-info' section in the server's response as explained below. + + shallow <oid> + A client must notify the server of all commits for which it only + has shallow copies (meaning that it doesn't have the parents of + a commit) by supplying a 'shallow <oid>' line for each such + object so that the server is aware of the limitations of the + client's history. This is so that the server is aware that the + client may not have all objects reachable from such commits. + + deepen <depth> + Requests that the fetch/clone should be shallow having a commit + depth of <depth> relative to the remote side. + + deepen-relative + Requests that the semantics of the "deepen" command be changed + to indicate that the depth requested is relative to the client's + current shallow boundary, instead of relative to the requested + commits. + + deepen-since <timestamp> + Requests that the shallow clone/fetch should be cut at a + specific time, instead of depth. Internally it's equivalent to + doing "git rev-list --max-age=<timestamp>". Cannot be used with + "deepen". + + deepen-not <rev> + Requests that the shallow clone/fetch should be cut at a + specific revision specified by '<rev>', instead of a depth. + Internally it's equivalent of doing "git rev-list --not <rev>". + Cannot be used with "deepen", but can be used with + "deepen-since". + +The response of `fetch` is broken into a number of sections separated by +delimiter packets (0001), with each section beginning with its section +header. + + output = *section + section = (acknowledgments | shallow-info | packfile) + (flush-pkt | delim-pkt) + + acknowledgments = PKT-LINE("acknowledgments" LF) + (nak | *ack) + (ready) + ready = PKT-LINE("ready" LF) + nak = PKT-LINE("NAK" LF) + ack = PKT-LINE("ACK" SP obj-id LF) + + shallow-info = PKT-LINE("shallow-info" LF) + *PKT-LINE((shallow | unshallow) LF) + shallow = "shallow" SP obj-id + unshallow = "unshallow" SP obj-id + + packfile = PKT-LINE("packfile" LF) + *PKT-LINE(%x01-03 *%x00-ff) + + acknowledgments section + * If the client determines that it is finished with negotiations + by sending a "done" line, the acknowledgments sections MUST be + omitted from the server's response. + + * Always begins with the section header "acknowledgments" + + * The server will respond with "NAK" if none of the object ids sent + as have lines were common. + + * The server will respond with "ACK obj-id" for all of the + object ids sent as have lines which are common. + + * A response cannot have both "ACK" lines as well as a "NAK" + line. + + * The server will respond with a "ready" line indicating that + the server has found an acceptable common base and is ready to + make and send a packfile (which will be found in the packfile + section of the same response) + + * If the server has found a suitable cut point and has decided + to send a "ready" line, then the server can decide to (as an + optimization) omit any "ACK" lines it would have sent during + its response. This is because the server will have already + determined the objects it plans to send to the client and no + further negotiation is needed. + + shallow-info section + * If the client has requested a shallow fetch/clone, a shallow + client requests a fetch or the server is shallow then the + server's response may include a shallow-info section. The + shallow-info section will be included if (due to one of the + above conditions) the server needs to inform the client of any + shallow boundaries or adjustments to the clients already + existing shallow boundaries. + + * Always begins with the section header "shallow-info" + + * If a positive depth is requested, the server will compute the + set of commits which are no deeper than the desired depth. + + * The server sends a "shallow obj-id" line for each commit whose + parents will not be sent in the following packfile. + + * The server sends an "unshallow obj-id" line for each commit + which the client has indicated is shallow, but is no longer + shallow as a result of the fetch (due to its parents being + sent in the following packfile). + + * The server MUST NOT send any "unshallow" lines for anything + which the client has not indicated was shallow as a part of + its request. + + * This section is only included if a packfile section is also + included in the response. + + packfile section + * This section is only included if the client has sent 'want' + lines in its request and either requested that no more + negotiation be done by sending 'done' or if the server has + decided it has found a sufficient cut point to produce a + packfile. + + * Always begins with the section header "packfile" + + * The transmission of the packfile begins immediately after the + section header + + * The data transfer of the packfile is always multiplexed, using + the same semantics of the 'side-band-64k' capability from + protocol version 1. This means that each packet, during the + packfile data stream, is made up of a leading 4-byte pkt-line + length (typical of the pkt-line format), followed by a 1-byte + stream code, followed by the actual data. + + The stream code can be one of: + 1 - pack data + 2 - progress messages + 3 - fatal error message just before stream aborts + + server-option +~~~~~~~~~~~~~~~ + +If advertised, indicates that any number of server specific options can be +included in a request. This is done by sending each option as a +"server-option=<option>" capability line in the capability-list section of +a request. + +The provided options must not contain a NUL or LF character. diff --git a/Documentation/technical/shallow.txt b/Documentation/technical/shallow.txt index 5183b15422..01dedfe9ff 100644 --- a/Documentation/technical/shallow.txt +++ b/Documentation/technical/shallow.txt @@ -8,20 +8,22 @@ repo, and therefore grafts are introduced pretending that these commits have no parents. ********************************************************* -The basic idea is to write the SHA-1s of shallow commits into -$GIT_DIR/shallow, and handle its contents like the contents -of $GIT_DIR/info/grafts (with the difference that shallow -cannot contain parent information). - -This information is stored in a new file instead of grafts, or -even the config, since the user should not touch that file -at all (even throughout development of the shallow clone, it -was never manually edited!). +$GIT_DIR/shallow lists commit object names and tells Git to +pretend as if they are root commits (e.g. "git log" traversal +stops after showing them; "git fsck" does not complain saying +the commits listed on their "parent" lines do not exist). Each line contains exactly one SHA-1. When read, a commit_graft will be constructed, which has nr_parent < 0 to make it easier to discern from user provided grafts. +Note that the shallow feature could not be changed easily to +use replace refs: a commit containing a `mergetag` is not allowed +to be replaced, not even by a root commit. Such a commit can be +made shallow, though. Also, having a `shallow` file explicitly +listing all the commits made shallow makes it a *lot* easier to +do shallow-specific things such as to deepen the history. + Since fsck-objects relies on the library to read the objects, it honours shallow commits automatically. @@ -441,6 +441,49 @@ all:: # # When cross-compiling, define HOST_CPU as the canonical name of the CPU on # which the built Git will run (for instance "x86_64"). +# +# Define RUNTIME_PREFIX to configure Git to resolve its ancillary tooling and +# support files relative to the location of the runtime binary, rather than +# hard-coding them into the binary. Git installations built with RUNTIME_PREFIX +# can be moved to arbitrary filesystem locations. RUNTIME_PREFIX also causes +# Perl scripts to use a modified entry point header allowing them to resolve +# support files at runtime. +# +# When using RUNTIME_PREFIX, define HAVE_BSD_KERN_PROC_SYSCTL if your platform +# supports the KERN_PROC BSD sysctl function. +# +# When using RUNTIME_PREFIX, define PROCFS_EXECUTABLE_PATH if your platform +# mounts a "procfs" filesystem capable of resolving the path of the current +# executable. If defined, this must be the canonical path for the "procfs" +# current executable path. +# +# When using RUNTIME_PREFIX, define HAVE_NS_GET_EXECUTABLE_PATH if your platform +# supports calling _NSGetExecutablePath to retrieve the path of the running +# executable. +# +# When using RUNTIME_PREFIX, define HAVE_WPGMPTR if your platform offers +# the global variable _wpgmptr containing the absolute path of the current +# executable (this is the case on Windows). +# +# Define DEVELOPER to enable more compiler warnings. Compiler version +# and family are auto detected, but could be overridden by defining +# COMPILER_FEATURES (see config.mak.dev) +# +# When DEVELOPER is set, DEVOPTS can be used to control compiler +# options. This variable contains keywords separated by +# whitespace. The following keywords are are recognized: +# +# no-error: +# +# suppresses the -Werror that implicitly comes with +# DEVELOPER=1. Useful for getting the full set of errors +# without immediately dying, or for logging them. +# +# extra-all: +# +# The DEVELOPER mode enables -Wextra with a few exceptions. By +# setting this flag the exceptions are removed, and all of +# -Wextra is used. GIT-VERSION-FILE: FORCE @$(SHELL_PATH) ./GIT-VERSION-GEN @@ -449,15 +492,6 @@ GIT-VERSION-FILE: FORCE # CFLAGS and LDFLAGS are for the users to override from the command line. CFLAGS = -g -O2 -Wall -DEVELOPER_CFLAGS = -Werror \ - -Wdeclaration-after-statement \ - -Wno-format-zero-length \ - -Wold-style-definition \ - -Woverflow \ - -Wpointer-arith \ - -Wstrict-prototypes \ - -Wunused \ - -Wvla LDFLAGS = ALL_CFLAGS = $(CPPFLAGS) $(CFLAGS) ALL_LDFLAGS = $(LDFLAGS) @@ -478,6 +512,8 @@ ARFLAGS = rcs # mandir # infodir # htmldir +# localedir +# perllibdir # This can help installing the suite in a relocatable way. prefix = $(HOME) @@ -502,7 +538,9 @@ bindir_relative = $(patsubst $(prefix)/%,%,$(bindir)) mandir_relative = $(patsubst $(prefix)/%,%,$(mandir)) infodir_relative = $(patsubst $(prefix)/%,%,$(infodir)) gitexecdir_relative = $(patsubst $(prefix)/%,%,$(gitexecdir)) +localedir_relative = $(patsubst $(prefix)/%,%,$(localedir)) htmldir_relative = $(patsubst $(prefix)/%,%,$(htmldir)) +perllibdir_relative = $(patsubst $(prefix)/%,%,$(perllibdir)) export prefix bindir sharedir sysconfdir gitwebdir perllibdir localedir @@ -652,7 +690,6 @@ PROGRAM_OBJS += imap-send.o PROGRAM_OBJS += sh-i18n--envsubst.o PROGRAM_OBJS += shell.o PROGRAM_OBJS += show-index.o -PROGRAM_OBJS += upload-pack.o PROGRAM_OBJS += remote-testsvn.o # Binary suffix, set to .exe for Windows builds @@ -701,6 +738,7 @@ TEST_PROGRAMS_NEED_X += test-dump-untracked-cache TEST_PROGRAMS_NEED_X += test-fake-ssh TEST_PROGRAMS_NEED_X += test-line-buffer TEST_PROGRAMS_NEED_X += test-parse-options +TEST_PROGRAMS_NEED_X += test-pkt-line TEST_PROGRAMS_NEED_X += test-svn-fe TEST_PROGRAMS_NEED_X += test-tool @@ -789,6 +827,7 @@ LIB_OBJS += color.o LIB_OBJS += column.o LIB_OBJS += combine-diff.o LIB_OBJS += commit.o +LIB_OBJS += commit-graph.o LIB_OBJS += compat/obstack.o LIB_OBJS += compat/terminal.o LIB_OBJS += config.o @@ -842,6 +881,7 @@ LIB_OBJS += list-objects-filter-options.o LIB_OBJS += ll-merge.o LIB_OBJS += lockfile.o LIB_OBJS += log-tree.o +LIB_OBJS += ls-refs.o LIB_OBJS += mailinfo.o LIB_OBJS += mailmap.o LIB_OBJS += match-trees.o @@ -898,6 +938,7 @@ LIB_OBJS += revision.o LIB_OBJS += run-command.o LIB_OBJS += send-pack.o LIB_OBJS += sequencer.o +LIB_OBJS += serve.o LIB_OBJS += server-info.o LIB_OBJS += setup.o LIB_OBJS += sha1-array.o @@ -926,6 +967,7 @@ LIB_OBJS += tree-diff.o LIB_OBJS += tree.o LIB_OBJS += tree-walk.o LIB_OBJS += unpack-trees.o +LIB_OBJS += upload-pack.o LIB_OBJS += url.o LIB_OBJS += urlmatch.o LIB_OBJS += usage.o @@ -965,6 +1007,7 @@ BUILTIN_OBJS += builtin/clone.o BUILTIN_OBJS += builtin/column.o BUILTIN_OBJS += builtin/commit-tree.o BUILTIN_OBJS += builtin/commit.o +BUILTIN_OBJS += builtin/commit-graph.o BUILTIN_OBJS += builtin/config.o BUILTIN_OBJS += builtin/count-objects.o BUILTIN_OBJS += builtin/credential.o @@ -1030,6 +1073,7 @@ BUILTIN_OBJS += builtin/rev-parse.o BUILTIN_OBJS += builtin/revert.o BUILTIN_OBJS += builtin/rm.o BUILTIN_OBJS += builtin/send-pack.o +BUILTIN_OBJS += builtin/serve.o BUILTIN_OBJS += builtin/shortlog.o BUILTIN_OBJS += builtin/show-branch.o BUILTIN_OBJS += builtin/show-ref.o @@ -1043,6 +1087,7 @@ BUILTIN_OBJS += builtin/update-index.o BUILTIN_OBJS += builtin/update-ref.o BUILTIN_OBJS += builtin/update-server-info.o BUILTIN_OBJS += builtin/upload-archive.o +BUILTIN_OBJS += builtin/upload-pack.o BUILTIN_OBJS += builtin/var.o BUILTIN_OBJS += builtin/verify-commit.o BUILTIN_OBJS += builtin/verify-pack.o @@ -1064,7 +1109,7 @@ include config.mak.uname -include config.mak ifdef DEVELOPER -CFLAGS += $(DEVELOPER_CFLAGS) +include config.mak.dev endif comma := , @@ -1665,10 +1710,27 @@ ifdef HAVE_BSD_SYSCTL BASIC_CFLAGS += -DHAVE_BSD_SYSCTL endif +ifdef HAVE_BSD_KERN_PROC_SYSCTL + BASIC_CFLAGS += -DHAVE_BSD_KERN_PROC_SYSCTL +endif + ifdef HAVE_GETDELIM BASIC_CFLAGS += -DHAVE_GETDELIM endif +ifneq ($(PROCFS_EXECUTABLE_PATH),) + procfs_executable_path_SQ = $(subst ','\'',$(PROCFS_EXECUTABLE_PATH)) + BASIC_CFLAGS += '-DPROCFS_EXECUTABLE_PATH="$(procfs_executable_path_SQ)"' +endif + +ifdef HAVE_NS_GET_EXECUTABLE_PATH + BASIC_CFLAGS += -DHAVE_NS_GET_EXECUTABLE_PATH +endif + +ifdef HAVE_WPGMPTR + BASIC_CFLAGS += -DHAVE_WPGMPTR +endif + ifeq ($(TCLTK_PATH),) NO_TCLTK = NoThanks endif @@ -1753,11 +1815,13 @@ mandir_relative_SQ = $(subst ','\'',$(mandir_relative)) infodir_relative_SQ = $(subst ','\'',$(infodir_relative)) perllibdir_SQ = $(subst ','\'',$(perllibdir)) localedir_SQ = $(subst ','\'',$(localedir)) +localedir_relative_SQ = $(subst ','\'',$(localedir_relative)) gitexecdir_SQ = $(subst ','\'',$(gitexecdir)) gitexecdir_relative_SQ = $(subst ','\'',$(gitexecdir_relative)) template_dir_SQ = $(subst ','\'',$(template_dir)) htmldir_relative_SQ = $(subst ','\'',$(htmldir_relative)) prefix_SQ = $(subst ','\'',$(prefix)) +perllibdir_relative_SQ = $(subst ','\'',$(perllibdir_relative)) gitwebdir_SQ = $(subst ','\'',$(gitwebdir)) SHELL_PATH_SQ = $(subst ','\'',$(SHELL_PATH)) @@ -1768,6 +1832,31 @@ TCLTK_PATH_SQ = $(subst ','\'',$(TCLTK_PATH)) DIFF_SQ = $(subst ','\'',$(DIFF)) PERLLIB_EXTRA_SQ = $(subst ','\'',$(PERLLIB_EXTRA)) +# RUNTIME_PREFIX's resolution logic requires resource paths to be expressed +# relative to each other and share an installation path. +# +# This is a dependency in: +# - Git's binary RUNTIME_PREFIX logic in (see "exec_cmd.c"). +# - The runtime prefix Perl header (see +# "perl/header_templates/runtime_prefix.template.pl"). +ifdef RUNTIME_PREFIX + +ifneq ($(filter /%,$(firstword $(gitexecdir_relative))),) +$(error RUNTIME_PREFIX requires a relative gitexecdir, not: $(gitexecdir)) +endif + +ifneq ($(filter /%,$(firstword $(localedir_relative))),) +$(error RUNTIME_PREFIX requires a relative localedir, not: $(localedir)) +endif + +ifndef NO_PERL +ifneq ($(filter /%,$(firstword $(perllibdir_relative))),) +$(error RUNTIME_PREFIX requires a relative perllibdir, not: $(perllibdir)) +endif +endif + +endif + # We must filter out any object files from $(GITLIBS), # as it is typically used like: # @@ -1988,27 +2077,44 @@ git.res: git.rc GIT-VERSION-FILE # This makes sure we depend on the NO_PERL setting itself. $(SCRIPT_PERL_GEN): GIT-BUILD-OPTIONS -ifndef NO_PERL -$(SCRIPT_PERL_GEN): +# Used for substitution in Perl modules. Disabled when using RUNTIME_PREFIX +# since the locale directory is injected. +perl_localedir_SQ = $(localedir_SQ) +ifndef NO_PERL +PERL_HEADER_TEMPLATE = perl/header_templates/fixed_prefix.template.pl PERL_DEFINES = $(PERL_PATH_SQ):$(PERLLIB_EXTRA_SQ):$(perllibdir_SQ) -$(SCRIPT_PERL_GEN): % : %.perl GIT-PERL-DEFINES GIT-VERSION-FILE + +PERL_DEFINES := $(PERL_PATH_SQ) $(PERLLIB_EXTRA_SQ) $(perllibdir_SQ) +PERL_DEFINES += $(RUNTIME_PREFIX) + +# Support Perl runtime prefix. In this mode, a different header is installed +# into Perl scripts. +ifdef RUNTIME_PREFIX + +PERL_HEADER_TEMPLATE = perl/header_templates/runtime_prefix.template.pl + +# Don't export a fixed $(localedir) path; it will be resolved by the Perl header +# at runtime. +perl_localedir_SQ = + +endif + +PERL_DEFINES += $(gitexecdir) $(perllibdir) $(localedir) + +$(SCRIPT_PERL_GEN): % : %.perl GIT-PERL-DEFINES GIT-PERL-HEADER GIT-VERSION-FILE $(QUIET_GEN)$(RM) $@ $@+ && \ - INSTLIBDIR='$(perllibdir_SQ)' && \ - INSTLIBDIR_EXTRA='$(PERLLIB_EXTRA_SQ)' && \ - INSTLIBDIR="$$INSTLIBDIR$${INSTLIBDIR_EXTRA:+:$$INSTLIBDIR_EXTRA}" && \ sed -e '1{' \ -e ' s|#!.*perl|#!$(PERL_PATH_SQ)|' \ - -e ' h' \ - -e ' s=.*=use lib (split(/$(pathsep)/, $$ENV{GITPERLLIB} || "'"$$INSTLIBDIR"'"));=' \ - -e ' H' \ - -e ' x' \ + -e ' rGIT-PERL-HEADER' \ + -e ' G' \ -e '}' \ -e 's/@@GIT_VERSION@@/$(GIT_VERSION)/g' \ $< >$@+ && \ chmod +x $@+ && \ mv $@+ $@ +PERL_DEFINES := $(subst $(space),:,$(PERL_DEFINES)) GIT-PERL-DEFINES: FORCE @FLAGS='$(PERL_DEFINES)'; \ if test x"$$FLAGS" != x"`cat $@ 2>/dev/null`" ; then \ @@ -2016,6 +2122,22 @@ GIT-PERL-DEFINES: FORCE echo "$$FLAGS" >$@; \ fi +GIT-PERL-HEADER: $(PERL_HEADER_TEMPLATE) GIT-PERL-DEFINES Makefile + $(QUIET_GEN)$(RM) $@ && \ + INSTLIBDIR='$(perllibdir_SQ)' && \ + INSTLIBDIR_EXTRA='$(PERLLIB_EXTRA_SQ)' && \ + INSTLIBDIR="$$INSTLIBDIR$${INSTLIBDIR_EXTRA:+:$$INSTLIBDIR_EXTRA}" && \ + sed -e 's=@@PATHSEP@@=$(pathsep)=g' \ + -e "s=@@INSTLIBDIR@@=$$INSTLIBDIR=g" \ + -e 's=@@PERLLIBDIR_REL@@=$(perllibdir_relative_SQ)=g' \ + -e 's=@@GITEXECDIR_REL@@=$(gitexecdir_relative_SQ)=g' \ + -e 's=@@LOCALEDIR_REL@@=$(localedir_relative_SQ)=g' \ + $< >$@+ && \ + mv $@+ $@ + +.PHONY: perllibdir +perllibdir: + @echo '$(perllibdir_SQ)' .PHONY: gitweb gitweb: @@ -2160,8 +2282,9 @@ endif exec-cmd.sp exec-cmd.s exec-cmd.o: GIT-PREFIX exec-cmd.sp exec-cmd.s exec-cmd.o: EXTRA_CPPFLAGS = \ '-DGIT_EXEC_PATH="$(gitexecdir_SQ)"' \ + '-DGIT_LOCALE_PATH="$(localedir_relative_SQ)"' \ '-DBINDIR="$(bindir_relative_SQ)"' \ - '-DPREFIX="$(prefix_SQ)"' + '-DFALLBACK_RUNTIME_PREFIX="$(prefix_SQ)"' builtin/init-db.sp builtin/init-db.s builtin/init-db.o: GIT-PREFIX builtin/init-db.sp builtin/init-db.s builtin/init-db.o: EXTRA_CPPFLAGS = \ @@ -2177,7 +2300,7 @@ attr.sp attr.s attr.o: EXTRA_CPPFLAGS = \ gettext.sp gettext.s gettext.o: GIT-PREFIX gettext.sp gettext.s gettext.o: EXTRA_CPPFLAGS = \ - -DGIT_LOCALE_PATH='"$(localedir_SQ)"' + -DGIT_LOCALE_PATH='"$(localedir_relative_SQ)"' http-push.sp http.sp http-walker.sp remote-curl.sp imap-send.sp: SPARSE_FLAGS += \ -DCURL_DISABLE_TYPECHECK @@ -2337,7 +2460,7 @@ endif perl/build/lib/%.pm: perl/%.pm $(QUIET_GEN)mkdir -p $(dir $@) && \ - sed -e 's|@@LOCALEDIR@@|$(localedir_SQ)|g' \ + sed -e 's|@@LOCALEDIR@@|$(perl_localedir_SQ)|g' \ -e 's|@@NO_PERL_CPAN_FALLBACKS@@|$(NO_PERL_CPAN_FALLBACKS_SQ)|g' \ < $< > $@ @@ -2795,7 +2918,7 @@ ifndef NO_TCLTK endif $(RM) GIT-VERSION-FILE GIT-CFLAGS GIT-LDFLAGS GIT-BUILD-OPTIONS $(RM) GIT-USER-AGENT GIT-PREFIX - $(RM) GIT-SCRIPT-DEFINES GIT-PERL-DEFINES GIT-PYTHON-VARS + $(RM) GIT-SCRIPT-DEFINES GIT-PERL-DEFINES GIT-PERL-HEADER GIT-PYTHON-VARS .PHONY: all install profile-clean clean strip .PHONY: shell_compatibility_test please_set_SHELL_PATH_to_a_more_modern_shell @@ -1,5 +1,6 @@ #include "cache.h" #include "config.h" +#include "color.h" int advice_push_update_rejected = 1; int advice_push_non_ff_current = 1; @@ -19,6 +20,34 @@ int advice_rm_hints = 1; int advice_add_embedded_repo = 1; int advice_ignored_hook = 1; int advice_waiting_for_editor = 1; +int advice_graft_file_deprecated = 1; + +static int advice_use_color = -1; +static char advice_colors[][COLOR_MAXLEN] = { + GIT_COLOR_RESET, + GIT_COLOR_YELLOW, /* HINT */ +}; + +enum color_advice { + ADVICE_COLOR_RESET = 0, + ADVICE_COLOR_HINT = 1, +}; + +static int parse_advise_color_slot(const char *slot) +{ + if (!strcasecmp(slot, "reset")) + return ADVICE_COLOR_RESET; + if (!strcasecmp(slot, "hint")) + return ADVICE_COLOR_HINT; + return -1; +} + +static const char *advise_get_color(enum color_advice ix) +{ + if (want_color_stderr(advice_use_color)) + return advice_colors[ix]; + return ""; +} static struct { const char *name; @@ -42,6 +71,7 @@ static struct { { "addembeddedrepo", &advice_add_embedded_repo }, { "ignoredhook", &advice_ignored_hook }, { "waitingforeditor", &advice_waiting_for_editor }, + { "graftfiledeprecated", &advice_graft_file_deprecated }, /* make this an alias for backward compatibility */ { "pushnonfastforward", &advice_push_update_rejected } @@ -59,7 +89,10 @@ void advise(const char *advice, ...) for (cp = buf.buf; *cp; cp = np) { np = strchrnul(cp, '\n'); - fprintf(stderr, _("hint: %.*s\n"), (int)(np - cp), cp); + fprintf(stderr, _("%shint: %.*s%s\n"), + advise_get_color(ADVICE_COLOR_HINT), + (int)(np - cp), cp, + advise_get_color(ADVICE_COLOR_RESET)); if (*np) np++; } @@ -68,9 +101,23 @@ void advise(const char *advice, ...) int git_default_advice_config(const char *var, const char *value) { - const char *k; + const char *k, *slot_name; int i; + if (!strcmp(var, "color.advice")) { + advice_use_color = git_config_colorbool(var, value); + return 0; + } + + if (skip_prefix(var, "color.advice.", &slot_name)) { + int slot = parse_advise_color_slot(slot_name); + if (slot < 0) + return 0; + if (!value) + return config_error_nonbool(var); + return color_parse(value, advice_colors[slot]); + } + if (!skip_prefix(var, "advice.", &k)) return 0; @@ -21,6 +21,7 @@ extern int advice_rm_hints; extern int advice_add_embedded_repo; extern int advice_ignored_hook; extern int advice_waiting_for_editor; +extern int advice_graft_file_deprecated; int git_default_advice_config(const char *var, const char *value); __attribute__((format (printf, 1, 2))) @@ -93,6 +93,7 @@ void *alloc_commit_node(void) struct commit *c = alloc_node(&commit_state, sizeof(struct commit)); c->object.type = OBJ_COMMIT; c->index = alloc_commit_index(); + c->graph_pos = COMMIT_NOT_FROM_GRAPH; return c; } diff --git a/archive-tar.c b/archive-tar.c index 3563bcb9f2..f93409324f 100644 --- a/archive-tar.c +++ b/archive-tar.c @@ -276,7 +276,7 @@ static int write_tar_entry(struct archiver_args *args, memcpy(header.name, path, pathlen); if (S_ISREG(mode) && !args->convert && - oid_object_info(oid, &size) == OBJ_BLOB && + oid_object_info(the_repository, oid, &size) == OBJ_BLOB && size > big_file_threshold) buffer = NULL; else if (S_ISLNK(mode) || S_ISREG(mode)) { diff --git a/archive-zip.c b/archive-zip.c index 6b20bce4d1..74f3fe9103 100644 --- a/archive-zip.c +++ b/archive-zip.c @@ -325,7 +325,8 @@ static int write_zip_entry(struct archiver_args *args, compressed_size = 0; buffer = NULL; } else if (S_ISREG(mode) || S_ISLNK(mode)) { - enum object_type type = oid_object_info(oid, &size); + enum object_type type = oid_object_info(the_repository, oid, + &size); method = 0; attr2 = S_ISLNK(mode) ? ((mode | 0777) << 16) : diff --git a/argv-array.c b/argv-array.c index 5d370fa336..cb5bcd2c06 100644 --- a/argv-array.c +++ b/argv-array.c @@ -64,6 +64,26 @@ void argv_array_pop(struct argv_array *array) array->argc--; } +void argv_array_split(struct argv_array *array, const char *to_split) +{ + while (isspace(*to_split)) + to_split++; + for (;;) { + const char *p = to_split; + + if (!*p) + break; + + while (*p && !isspace(*p)) + p++; + argv_array_push_nodup(array, xstrndup(to_split, p - to_split)); + + while (isspace(*p)) + p++; + to_split = p; + } +} + void argv_array_clear(struct argv_array *array) { if (array->argv != empty_argv) { diff --git a/argv-array.h b/argv-array.h index 29056e49a1..750c30d2f2 100644 --- a/argv-array.h +++ b/argv-array.h @@ -19,6 +19,8 @@ LAST_ARG_MUST_BE_NULL void argv_array_pushl(struct argv_array *, ...); void argv_array_pushv(struct argv_array *, const char **); void argv_array_pop(struct argv_array *); +/* Splits by whitespace; does not handle quoted arguments! */ +void argv_array_split(struct argv_array *, const char *); void argv_array_clear(struct argv_array *); const char **argv_array_detach(struct argv_array *); @@ -81,7 +81,7 @@ static void verify_working_tree_path(struct commit *work_tree, const char *path) unsigned mode; if (!get_tree_entry(commit_oid, path, &blob_oid, &mode) && - oid_object_info(&blob_oid, NULL) == OBJ_BLOB) + oid_object_info(the_repository, &blob_oid, NULL) == OBJ_BLOB) return; } @@ -504,7 +504,7 @@ static int fill_blob_sha1_and_mode(struct blame_origin *origin) return 0; if (get_tree_entry(&origin->commit->object.oid, origin->path, &origin->blob_oid, &origin->mode)) goto error_out; - if (oid_object_info(&origin->blob_oid, NULL) != OBJ_BLOB) + if (oid_object_info(the_repository, &origin->blob_oid, NULL) != OBJ_BLOB) goto error_out; return 0; error_out: @@ -551,10 +551,10 @@ static struct blame_origin *find_origin(struct commit *parent, diff_setup_done(&diff_opts); if (is_null_oid(&origin->commit->object.oid)) - do_diff_cache(&parent->tree->object.oid, &diff_opts); + do_diff_cache(get_commit_tree_oid(parent), &diff_opts); else - diff_tree_oid(&parent->tree->object.oid, - &origin->commit->tree->object.oid, + diff_tree_oid(get_commit_tree_oid(parent), + get_commit_tree_oid(origin->commit), "", &diff_opts); diffcore_std(&diff_opts); @@ -620,10 +620,10 @@ static struct blame_origin *find_rename(struct commit *parent, diff_setup_done(&diff_opts); if (is_null_oid(&origin->commit->object.oid)) - do_diff_cache(&parent->tree->object.oid, &diff_opts); + do_diff_cache(get_commit_tree_oid(parent), &diff_opts); else - diff_tree_oid(&parent->tree->object.oid, - &origin->commit->tree->object.oid, + diff_tree_oid(get_commit_tree_oid(parent), + get_commit_tree_oid(origin->commit), "", &diff_opts); diffcore_std(&diff_opts); @@ -1255,10 +1255,10 @@ static void find_copy_in_parent(struct blame_scoreboard *sb, diff_opts.flags.find_copies_harder = 1; if (is_null_oid(&target->commit->object.oid)) - do_diff_cache(&parent->tree->object.oid, &diff_opts); + do_diff_cache(get_commit_tree_oid(parent), &diff_opts); else - diff_tree_oid(&parent->tree->object.oid, - &target->commit->tree->object.oid, + diff_tree_oid(get_commit_tree_oid(parent), + get_commit_tree_oid(target->commit), "", &diff_opts); if (!diff_opts.flags.find_copies_harder) @@ -149,6 +149,7 @@ extern int cmd_clone(int argc, const char **argv, const char *prefix); extern int cmd_clean(int argc, const char **argv, const char *prefix); extern int cmd_column(int argc, const char **argv, const char *prefix); extern int cmd_commit(int argc, const char **argv, const char *prefix); +extern int cmd_commit_graph(int argc, const char **argv, const char *prefix); extern int cmd_commit_tree(int argc, const char **argv, const char *prefix); extern int cmd_config(int argc, const char **argv, const char *prefix); extern int cmd_count_objects(int argc, const char **argv, const char *prefix); @@ -215,6 +216,7 @@ extern int cmd_rev_parse(int argc, const char **argv, const char *prefix); extern int cmd_revert(int argc, const char **argv, const char *prefix); extern int cmd_rm(int argc, const char **argv, const char *prefix); extern int cmd_send_pack(int argc, const char **argv, const char *prefix); +extern int cmd_serve(int argc, const char **argv, const char *prefix); extern int cmd_shortlog(int argc, const char **argv, const char *prefix); extern int cmd_show(int argc, const char **argv, const char *prefix); extern int cmd_show_branch(int argc, const char **argv, const char *prefix); @@ -231,6 +233,7 @@ extern int cmd_update_ref(int argc, const char **argv, const char *prefix); extern int cmd_update_server_info(int argc, const char **argv, const char *prefix); extern int cmd_upload_archive(int argc, const char **argv, const char *prefix); extern int cmd_upload_archive_writer(int argc, const char **argv, const char *prefix); +extern int cmd_upload_pack(int argc, const char **argv, const char *prefix); extern int cmd_var(int argc, const char **argv, const char *prefix); extern int cmd_verify_commit(int argc, const char **argv, const char *prefix); extern int cmd_verify_tag(int argc, const char **argv, const char *prefix); diff --git a/builtin/blame.c b/builtin/blame.c index db38c0b307..bfdf7cc132 100644 --- a/builtin/blame.c +++ b/builtin/blame.c @@ -655,7 +655,7 @@ static int is_a_rev(const char *name) if (get_oid(name, &oid)) return 0; - return OBJ_NONE < oid_object_info(&oid, NULL); + return OBJ_NONE < oid_object_info(the_repository, &oid, NULL); } int cmd_blame(int argc, const char **argv, const char *prefix) diff --git a/builtin/branch.c b/builtin/branch.c index 5bd2a0dd48..efc9ac1922 100644 --- a/builtin/branch.c +++ b/builtin/branch.c @@ -391,7 +391,6 @@ static void print_ref_list(struct ref_filter *filter, struct ref_sorting *sortin struct ref_array array; int maxwidth = 0; const char *remote_prefix = ""; - struct strbuf out = STRBUF_INIT; char *to_free = NULL; /* @@ -419,7 +418,10 @@ static void print_ref_list(struct ref_filter *filter, struct ref_sorting *sortin ref_array_sort(sorting, &array); for (i = 0; i < array.nr; i++) { - format_ref_array_item(array.items[i], format, &out); + struct strbuf out = STRBUF_INIT; + struct strbuf err = STRBUF_INIT; + if (format_ref_array_item(array.items[i], format, &out, &err)) + die("%s", err.buf); if (column_active(colopts)) { assert(!filter->verbose && "--column and --verbose are incompatible"); /* format to a string_list to let print_columns() do its job */ @@ -428,6 +430,7 @@ static void print_ref_list(struct ref_filter *filter, struct ref_sorting *sortin fwrite(out.buf, 1, out.len, stdout); putchar('\n'); } + strbuf_release(&err); strbuf_release(&out); } diff --git a/builtin/cat-file.c b/builtin/cat-file.c index 2c46d257cd..b8ecbea98e 100644 --- a/builtin/cat-file.c +++ b/builtin/cat-file.c @@ -77,7 +77,7 @@ static int cat_one_file(int opt, const char *exp_type, const char *obj_name, switch (opt) { case 't': oi.type_name = &sb; - if (oid_object_info_extended(&oid, &oi, flags) < 0) + if (oid_object_info_extended(the_repository, &oid, &oi, flags) < 0) die("git cat-file: could not get object info"); if (sb.len) { printf("%s\n", sb.buf); @@ -88,7 +88,7 @@ static int cat_one_file(int opt, const char *exp_type, const char *obj_name, case 's': oi.sizep = &size; - if (oid_object_info_extended(&oid, &oi, flags) < 0) + if (oid_object_info_extended(the_repository, &oid, &oi, flags) < 0) die("git cat-file: could not get object info"); printf("%lu\n", size); return 0; @@ -116,7 +116,7 @@ static int cat_one_file(int opt, const char *exp_type, const char *obj_name, /* else fallthrough */ case 'p': - type = oid_object_info(&oid, NULL); + type = oid_object_info(the_repository, &oid, NULL); if (type < 0) die("Not a valid object name %s", obj_name); @@ -140,7 +140,7 @@ static int cat_one_file(int opt, const char *exp_type, const char *obj_name, case 0: if (type_from_string(exp_type) == OBJ_BLOB) { struct object_id blob_oid; - if (oid_object_info(&oid, NULL) == OBJ_TAG) { + if (oid_object_info(the_repository, &oid, NULL) == OBJ_TAG) { char *buffer = read_object_file(&oid, &type, &size); const char *target; @@ -151,7 +151,7 @@ static int cat_one_file(int opt, const char *exp_type, const char *obj_name, } else oidcpy(&blob_oid, &oid); - if (oid_object_info(&blob_oid, NULL) == OBJ_BLOB) + if (oid_object_info(the_repository, &blob_oid, NULL) == OBJ_BLOB) return stream_blob_to_fd(1, &blob_oid, NULL, 0); /* * we attempted to dereference a tag to a blob @@ -342,7 +342,7 @@ static void batch_object_write(const char *obj_name, struct batch_options *opt, struct strbuf buf = STRBUF_INIT; if (!data->skip_object_info && - oid_object_info_extended(&data->oid, &data->info, + oid_object_info_extended(the_repository, &data->oid, &data->info, OBJECT_INFO_LOOKUP_REPLACE) < 0) { printf("%s missing\n", obj_name ? obj_name : oid_to_hex(&data->oid)); diff --git a/builtin/checkout.c b/builtin/checkout.c index b49b582071..2b3b768eff 100644 --- a/builtin/checkout.c +++ b/builtin/checkout.c @@ -484,7 +484,8 @@ static int merge_working_tree(const struct checkout_opts *opts, resolve_undo_clear(); if (opts->force) { - ret = reset_tree(new_branch_info->commit->tree, opts, 1, writeout_error); + ret = reset_tree(get_commit_tree(new_branch_info->commit), + opts, 1, writeout_error); if (ret) return ret; } else { @@ -570,18 +571,23 @@ static int merge_working_tree(const struct checkout_opts *opts, o.verbosity = 0; work = write_tree_from_memory(&o); - ret = reset_tree(new_branch_info->commit->tree, opts, 1, + ret = reset_tree(get_commit_tree(new_branch_info->commit), + opts, 1, writeout_error); if (ret) return ret; o.ancestor = old_branch_info->name; o.branch1 = new_branch_info->name; o.branch2 = "local"; - ret = merge_trees(&o, new_branch_info->commit->tree, work, - old_branch_info->commit->tree, &result); + ret = merge_trees(&o, + get_commit_tree(new_branch_info->commit), + work, + get_commit_tree(old_branch_info->commit), + &result); if (ret < 0) exit(128); - ret = reset_tree(new_branch_info->commit->tree, opts, 0, + ret = reset_tree(get_commit_tree(new_branch_info->commit), + opts, 0, writeout_error); strbuf_release(&o.obuf); if (ret) @@ -1002,7 +1008,7 @@ static int parse_branchname_arg(int argc, const char **argv, *source_tree = parse_tree_indirect(rev); } else { parse_commit_or_die(new_branch_info->commit); - *source_tree = new_branch_info->commit->tree; + *source_tree = get_commit_tree(new_branch_info->commit); } if (!*source_tree) /* case (1): want a tree */ diff --git a/builtin/clone.c b/builtin/clone.c index 7df5932b85..84f1473d19 100644 --- a/builtin/clone.c +++ b/builtin/clone.c @@ -1135,7 +1135,7 @@ int cmd_clone(int argc, const char **argv, const char *prefix) if (transport->smart_options && !deepen && !filter_options.choice) transport->smart_options->check_self_contained_and_connected = 1; - refs = transport_get_remote_refs(transport); + refs = transport_get_remote_refs(transport, NULL); if (refs) { mapped_refs = wanted_peer_refs(refs, refspec); diff --git a/builtin/column.c b/builtin/column.c index 0c3223d64b..5228ccf37a 100644 --- a/builtin/column.c +++ b/builtin/column.c @@ -42,7 +42,6 @@ int cmd_column(int argc, const char **argv, const char *prefix) git_config(column_config, NULL); memset(&copts, 0, sizeof(copts)); - copts.width = term_columns(); copts.padding = 1; argc = parse_options(argc, argv, "", options, builtin_column_usage, 0); if (argc) diff --git a/builtin/commit-graph.c b/builtin/commit-graph.c new file mode 100644 index 0000000000..37420ae0fd --- /dev/null +++ b/builtin/commit-graph.c @@ -0,0 +1,171 @@ +#include "builtin.h" +#include "config.h" +#include "dir.h" +#include "lockfile.h" +#include "parse-options.h" +#include "commit-graph.h" + +static char const * const builtin_commit_graph_usage[] = { + N_("git commit-graph [--object-dir <objdir>]"), + N_("git commit-graph read [--object-dir <objdir>]"), + N_("git commit-graph write [--object-dir <objdir>] [--append] [--stdin-packs|--stdin-commits]"), + NULL +}; + +static const char * const builtin_commit_graph_read_usage[] = { + N_("git commit-graph read [--object-dir <objdir>]"), + NULL +}; + +static const char * const builtin_commit_graph_write_usage[] = { + N_("git commit-graph write [--object-dir <objdir>] [--append] [--stdin-packs|--stdin-commits]"), + NULL +}; + +static struct opts_commit_graph { + const char *obj_dir; + int stdin_packs; + int stdin_commits; + int append; +} opts; + +static int graph_read(int argc, const char **argv) +{ + struct commit_graph *graph = NULL; + char *graph_name; + + static struct option builtin_commit_graph_read_options[] = { + OPT_STRING(0, "object-dir", &opts.obj_dir, + N_("dir"), + N_("The object directory to store the graph")), + OPT_END(), + }; + + argc = parse_options(argc, argv, NULL, + builtin_commit_graph_read_options, + builtin_commit_graph_read_usage, 0); + + if (!opts.obj_dir) + opts.obj_dir = get_object_directory(); + + graph_name = get_commit_graph_filename(opts.obj_dir); + graph = load_commit_graph_one(graph_name); + + if (!graph) + die("graph file %s does not exist", graph_name); + FREE_AND_NULL(graph_name); + + printf("header: %08x %d %d %d %d\n", + ntohl(*(uint32_t*)graph->data), + *(unsigned char*)(graph->data + 4), + *(unsigned char*)(graph->data + 5), + *(unsigned char*)(graph->data + 6), + *(unsigned char*)(graph->data + 7)); + printf("num_commits: %u\n", graph->num_commits); + printf("chunks:"); + + if (graph->chunk_oid_fanout) + printf(" oid_fanout"); + if (graph->chunk_oid_lookup) + printf(" oid_lookup"); + if (graph->chunk_commit_data) + printf(" commit_metadata"); + if (graph->chunk_large_edges) + printf(" large_edges"); + printf("\n"); + + return 0; +} + +static int graph_write(int argc, const char **argv) +{ + const char **pack_indexes = NULL; + int packs_nr = 0; + const char **commit_hex = NULL; + int commits_nr = 0; + const char **lines = NULL; + int lines_nr = 0; + int lines_alloc = 0; + + static struct option builtin_commit_graph_write_options[] = { + OPT_STRING(0, "object-dir", &opts.obj_dir, + N_("dir"), + N_("The object directory to store the graph")), + OPT_BOOL(0, "stdin-packs", &opts.stdin_packs, + N_("scan pack-indexes listed by stdin for commits")), + OPT_BOOL(0, "stdin-commits", &opts.stdin_commits, + N_("start walk at commits listed by stdin")), + OPT_BOOL(0, "append", &opts.append, + N_("include all commits already in the commit-graph file")), + OPT_END(), + }; + + argc = parse_options(argc, argv, NULL, + builtin_commit_graph_write_options, + builtin_commit_graph_write_usage, 0); + + if (opts.stdin_packs && opts.stdin_commits) + die(_("cannot use both --stdin-commits and --stdin-packs")); + if (!opts.obj_dir) + opts.obj_dir = get_object_directory(); + + if (opts.stdin_packs || opts.stdin_commits) { + struct strbuf buf = STRBUF_INIT; + lines_nr = 0; + lines_alloc = 128; + ALLOC_ARRAY(lines, lines_alloc); + + while (strbuf_getline(&buf, stdin) != EOF) { + ALLOC_GROW(lines, lines_nr + 1, lines_alloc); + lines[lines_nr++] = strbuf_detach(&buf, NULL); + } + + if (opts.stdin_packs) { + pack_indexes = lines; + packs_nr = lines_nr; + } + if (opts.stdin_commits) { + commit_hex = lines; + commits_nr = lines_nr; + } + } + + write_commit_graph(opts.obj_dir, + pack_indexes, + packs_nr, + commit_hex, + commits_nr, + opts.append); + + return 0; +} + +int cmd_commit_graph(int argc, const char **argv, const char *prefix) +{ + static struct option builtin_commit_graph_options[] = { + OPT_STRING(0, "object-dir", &opts.obj_dir, + N_("dir"), + N_("The object directory to store the graph")), + OPT_END(), + }; + + if (argc == 2 && !strcmp(argv[1], "-h")) + usage_with_options(builtin_commit_graph_usage, + builtin_commit_graph_options); + + git_config(git_default_config, NULL); + argc = parse_options(argc, argv, prefix, + builtin_commit_graph_options, + builtin_commit_graph_usage, + PARSE_OPT_STOP_AT_NON_OPTION); + + if (argc > 0) { + if (!strcmp(argv[0], "read")) + return graph_read(argc, argv); + if (!strcmp(argv[0], "write")) + return graph_write(argc, argv); + } + + usage_with_options(builtin_commit_graph_usage, + builtin_commit_graph_options); +} diff --git a/builtin/config.c b/builtin/config.c index 01169dd628..69e7270356 100644 --- a/builtin/config.c +++ b/builtin/config.c @@ -25,7 +25,8 @@ static char term = '\n'; static int use_global_config, use_system_config, use_local_config; static struct git_config_source given_config_source; -static int actions, types; +static int actions, type; +static char *default_value; static int end_null; static int respect_includes_opt = -1; static struct config_options config_options; @@ -55,11 +56,68 @@ static int show_origin; #define PAGING_ACTIONS (ACTION_LIST | ACTION_GET_ALL | \ ACTION_GET_REGEXP | ACTION_GET_URLMATCH) -#define TYPE_BOOL (1<<0) -#define TYPE_INT (1<<1) -#define TYPE_BOOL_OR_INT (1<<2) -#define TYPE_PATH (1<<3) -#define TYPE_EXPIRY_DATE (1<<4) +#define TYPE_BOOL 1 +#define TYPE_INT 2 +#define TYPE_BOOL_OR_INT 3 +#define TYPE_PATH 4 +#define TYPE_EXPIRY_DATE 5 +#define TYPE_COLOR 6 + +#define OPT_CALLBACK_VALUE(s, l, v, h, i) \ + { OPTION_CALLBACK, (s), (l), (v), NULL, (h), PARSE_OPT_NOARG | \ + PARSE_OPT_NONEG, option_parse_type, (i) } + +static struct option builtin_config_options[]; + +static int option_parse_type(const struct option *opt, const char *arg, + int unset) +{ + int new_type, *to_type; + + if (unset) { + *((int *) opt->value) = 0; + return 0; + } + + /* + * To support '--<type>' style flags, begin with new_type equal to + * opt->defval. + */ + new_type = opt->defval; + if (!new_type) { + if (!strcmp(arg, "bool")) + new_type = TYPE_BOOL; + else if (!strcmp(arg, "int")) + new_type = TYPE_INT; + else if (!strcmp(arg, "bool-or-int")) + new_type = TYPE_BOOL_OR_INT; + else if (!strcmp(arg, "path")) + new_type = TYPE_PATH; + else if (!strcmp(arg, "expiry-date")) + new_type = TYPE_EXPIRY_DATE; + else if (!strcmp(arg, "color")) + new_type = TYPE_COLOR; + else + die(_("unrecognized --type argument, %s"), arg); + } + + to_type = opt->value; + if (*to_type && *to_type != new_type) { + /* + * Complain when there is a new type not equal to the old type. + * This allows for combinations like '--int --type=int' and + * '--type=int --type=int', but disallows ones like '--type=bool + * --int' and '--type=bool + * --type=int'. + */ + error("only one type at a time."); + usage_with_options(builtin_config_usage, + builtin_config_options); + } + *to_type = new_type; + + return 0; +} static struct option builtin_config_options[] = { OPT_GROUP(N_("Config file location")), @@ -84,16 +142,18 @@ static struct option builtin_config_options[] = { OPT_BIT(0, "get-color", &actions, N_("find the color configured: slot [default]"), ACTION_GET_COLOR), OPT_BIT(0, "get-colorbool", &actions, N_("find the color setting: slot [stdout-is-tty]"), ACTION_GET_COLORBOOL), OPT_GROUP(N_("Type")), - OPT_BIT(0, "bool", &types, N_("value is \"true\" or \"false\""), TYPE_BOOL), - OPT_BIT(0, "int", &types, N_("value is decimal number"), TYPE_INT), - OPT_BIT(0, "bool-or-int", &types, N_("value is --bool or --int"), TYPE_BOOL_OR_INT), - OPT_BIT(0, "path", &types, N_("value is a path (file or directory name)"), TYPE_PATH), - OPT_BIT(0, "expiry-date", &types, N_("value is an expiry date"), TYPE_EXPIRY_DATE), + OPT_CALLBACK('t', "type", &type, "", N_("value is given this type"), option_parse_type), + OPT_CALLBACK_VALUE(0, "bool", &type, N_("value is \"true\" or \"false\""), TYPE_BOOL), + OPT_CALLBACK_VALUE(0, "int", &type, N_("value is decimal number"), TYPE_INT), + OPT_CALLBACK_VALUE(0, "bool-or-int", &type, N_("value is --bool or --int"), TYPE_BOOL_OR_INT), + OPT_CALLBACK_VALUE(0, "path", &type, N_("value is a path (file or directory name)"), TYPE_PATH), + OPT_CALLBACK_VALUE(0, "expiry-date", &type, N_("value is an expiry date"), TYPE_EXPIRY_DATE), OPT_GROUP(N_("Other")), OPT_BOOL('z', "null", &end_null, N_("terminate values with NUL byte")), OPT_BOOL(0, "name-only", &omit_values, N_("show variable names only")), OPT_BOOL(0, "includes", &respect_includes_opt, N_("respect include directives on lookup")), OPT_BOOL(0, "show-origin", &show_origin, N_("show origin of config (file, standard input, blob, command line)")), + OPT_STRING(0, "default", &default_value, N_("value"), N_("with --get, use default value when missing entry")), OPT_END(), }; @@ -149,30 +209,35 @@ static int format_config(struct strbuf *buf, const char *key_, const char *value if (show_keys) strbuf_addch(buf, key_delim); - if (types == TYPE_INT) + if (type == TYPE_INT) strbuf_addf(buf, "%"PRId64, git_config_int64(key_, value_ ? value_ : "")); - else if (types == TYPE_BOOL) + else if (type == TYPE_BOOL) strbuf_addstr(buf, git_config_bool(key_, value_) ? "true" : "false"); - else if (types == TYPE_BOOL_OR_INT) { + else if (type == TYPE_BOOL_OR_INT) { int is_bool, v; v = git_config_bool_or_int(key_, value_, &is_bool); if (is_bool) strbuf_addstr(buf, v ? "true" : "false"); else strbuf_addf(buf, "%d", v); - } else if (types == TYPE_PATH) { + } else if (type == TYPE_PATH) { const char *v; if (git_config_pathname(&v, key_, value_) < 0) return -1; strbuf_addstr(buf, v); free((char *)v); - } else if (types == TYPE_EXPIRY_DATE) { + } else if (type == TYPE_EXPIRY_DATE) { timestamp_t t; if (git_config_expiry_date(&t, key_, value_) < 0) return -1; strbuf_addf(buf, "%"PRItime, t); + } else if (type == TYPE_COLOR) { + char v[COLOR_MAXLEN]; + if (git_config_color(v, key_, value_) < 0) + return -1; + strbuf_addstr(buf, v); } else if (value_) { strbuf_addstr(buf, value_); } else { @@ -258,6 +323,16 @@ static int get_value(const char *key_, const char *regex_) config_with_options(collect_config, &values, &given_config_source, &config_options); + if (!values.nr && default_value) { + struct strbuf *item; + ALLOC_GROW(values.items, values.nr + 1, values.alloc); + item = &values.items[values.nr++]; + strbuf_init(item, 0); + if (format_config(item, key_, default_value) < 0) + die(_("failed to format default config value: %s"), + default_value); + } + ret = !values.nr; for (i = 0; i < values.nr; i++) { @@ -287,7 +362,7 @@ static char *normalize_value(const char *key, const char *value) if (!value) return NULL; - if (types == 0 || types == TYPE_PATH || types == TYPE_EXPIRY_DATE) + if (type == 0 || type == TYPE_PATH || type == TYPE_EXPIRY_DATE) /* * We don't do normalization for TYPE_PATH here: If * the path is like ~/foobar/, we prefer to store @@ -296,11 +371,11 @@ static char *normalize_value(const char *key, const char *value) * Also don't do normalization for expiry dates. */ return xstrdup(value); - if (types == TYPE_INT) + if (type == TYPE_INT) return xstrfmt("%"PRId64, git_config_int64(key, value)); - if (types == TYPE_BOOL) + if (type == TYPE_BOOL) return xstrdup(git_config_bool(key, value) ? "true" : "false"); - if (types == TYPE_BOOL_OR_INT) { + if (type == TYPE_BOOL_OR_INT) { int is_bool, v; v = git_config_bool_or_int(key, value, &is_bool); if (!is_bool) @@ -308,8 +383,22 @@ static char *normalize_value(const char *key, const char *value) else return xstrdup(v ? "true" : "false"); } + if (type == TYPE_COLOR) { + char v[COLOR_MAXLEN]; + if (git_config_color(v, key, value)) + die("cannot parse color '%s'", value); + + /* + * The contents of `v` now contain an ANSI escape + * sequence, not suitable for including within a + * configuration file. Treat the above as a + * "sanity-check", and return the given value, which we + * know is representable as valid color code. + */ + return xstrdup(value); + } - die("BUG: cannot normalize type %d", types); + die("BUG: cannot normalize type %d", type); } static int get_color_found; @@ -566,12 +655,7 @@ int cmd_config(int argc, const char **argv, const char *prefix) key_delim = '\n'; } - if (HAS_MULTI_BITS(types)) { - error("only one type at a time."); - usage_with_options(builtin_config_usage, builtin_config_options); - } - - if ((actions & (ACTION_GET_COLOR|ACTION_GET_COLORBOOL)) && types) { + if ((actions & (ACTION_GET_COLOR|ACTION_GET_COLORBOOL)) && type) { error("--get-color and variable type are incoherent"); usage_with_options(builtin_config_usage, builtin_config_options); } @@ -601,6 +685,12 @@ int cmd_config(int argc, const char **argv, const char *prefix) usage_with_options(builtin_config_usage, builtin_config_options); } + if (default_value && !(actions & ACTION_GET)) { + error("--default is only applicable to --get"); + usage_with_options(builtin_config_usage, + builtin_config_options); + } + if (actions & PAGING_ACTIONS) setup_auto_pager("config", 1); diff --git a/builtin/describe.c b/builtin/describe.c index b5afc45846..a4160e7f5d 100644 --- a/builtin/describe.c +++ b/builtin/describe.c @@ -502,7 +502,7 @@ static void describe(const char *arg, int last_one) if (cmit) describe_commit(&oid, &sb); - else if (oid_object_info(&oid, NULL) == OBJ_BLOB) + else if (oid_object_info(the_repository, &oid, NULL) == OBJ_BLOB) describe_blob(oid, &sb); else die(_("%s is neither a commit nor blob"), arg); diff --git a/builtin/diff.c b/builtin/diff.c index 16bfb22f73..bfefff3a84 100644 --- a/builtin/diff.c +++ b/builtin/diff.c @@ -398,7 +398,7 @@ int cmd_diff(int argc, const char **argv, const char *prefix) if (!obj) die(_("invalid object '%s' given."), name); if (obj->type == OBJ_COMMIT) - obj = &((struct commit *)obj)->tree->object; + obj = &get_commit_tree(((struct commit *)obj))->object; if (obj->type == OBJ_TREE) { obj->flags |= flags; diff --git a/builtin/fast-export.c b/builtin/fast-export.c index a15898d641..68a762fbea 100644 --- a/builtin/fast-export.c +++ b/builtin/fast-export.c @@ -578,11 +578,11 @@ static void handle_commit(struct commit *commit, struct rev_info *rev, get_object_mark(&commit->parents->item->object) != 0 && !full_tree) { parse_commit_or_die(commit->parents->item); - diff_tree_oid(&commit->parents->item->tree->object.oid, - &commit->tree->object.oid, "", &rev->diffopt); + diff_tree_oid(get_commit_tree_oid(commit->parents->item), + get_commit_tree_oid(commit), "", &rev->diffopt); } else - diff_root_tree_oid(&commit->tree->object.oid, + diff_root_tree_oid(get_commit_tree_oid(commit), "", &rev->diffopt); /* Export the referenced blobs, and remember the marks. */ @@ -651,8 +651,11 @@ static void handle_tail(struct object_array *commits, struct rev_info *revs, struct commit *commit; while (commits->nr) { commit = (struct commit *)object_array_pop(commits); - if (has_unshown_parent(commit)) + if (has_unshown_parent(commit)) { + /* Queue again, to be handled later */ + add_object_array(&commit->object, NULL, commits); return; + } handle_commit(commit, revs, paths_of_changed_objects); } } @@ -947,7 +950,7 @@ static void import_marks(char *input_file) if (last_idnum < mark) last_idnum = mark; - type = oid_object_info(&oid, NULL); + type = oid_object_info(the_repository, &oid, NULL); if (type < 0) die("object not found: %s", oid_to_hex(&oid)); diff --git a/builtin/fetch-pack.c b/builtin/fetch-pack.c index a7bc1366ab..1a1bc63566 100644 --- a/builtin/fetch-pack.c +++ b/builtin/fetch-pack.c @@ -4,6 +4,7 @@ #include "remote.h" #include "connect.h" #include "sha1-array.h" +#include "protocol.h" static const char fetch_pack_usage[] = "git fetch-pack [--all] [--stdin] [--quiet | -q] [--keep | -k] [--thin] " @@ -52,6 +53,7 @@ int cmd_fetch_pack(int argc, const char **argv, const char *prefix) struct fetch_pack_args args; struct oid_array shallow = OID_ARRAY_INIT; struct string_list deepen_not = STRING_LIST_INIT_DUP; + struct packet_reader reader; fetch_if_missing = 0; @@ -211,10 +213,24 @@ int cmd_fetch_pack(int argc, const char **argv, const char *prefix) if (!conn) return args.diag_url ? 0 : 1; } - get_remote_heads(fd[0], NULL, 0, &ref, 0, NULL, &shallow); + + packet_reader_init(&reader, fd[0], NULL, 0, + PACKET_READ_CHOMP_NEWLINE | + PACKET_READ_GENTLE_ON_EOF); + + switch (discover_version(&reader)) { + case protocol_v2: + die("support for protocol v2 not implemented yet"); + case protocol_v1: + case protocol_v0: + get_remote_heads(&reader, &ref, 0, NULL, &shallow); + break; + case protocol_unknown_version: + BUG("unknown protocol version"); + } ref = fetch_pack(&args, fd, conn, ref, dest, sought, nr_sought, - &shallow, pack_lockfile_ptr); + &shallow, pack_lockfile_ptr, protocol_v0); if (pack_lockfile) { printf("lock %s\n", pack_lockfile); fflush(stdout); diff --git a/builtin/fetch.c b/builtin/fetch.c index dcdfc66f09..1f037e8e4b 100644 --- a/builtin/fetch.c +++ b/builtin/fetch.c @@ -62,6 +62,7 @@ static int shown_url = 0; static int refmap_alloc, refmap_nr; static const char **refmap_array; static struct list_objects_filter_options filter_options; +static struct string_list server_options = STRING_LIST_INIT_DUP; static int git_fetch_config(const char *k, const char *v, void *cb) { @@ -170,6 +171,7 @@ static struct option builtin_fetch_options[] = { N_("accept refs that update .git/shallow")), { OPTION_CALLBACK, 0, "refmap", NULL, N_("refmap"), N_("specify fetch refmap"), PARSE_OPT_NONEG, parse_refmap_arg }, + OPT_STRING_LIST('o', "server-option", &server_options, N_("server-specific"), N_("option to transmit")), OPT_SET_INT('4', "ipv4", &family, N_("use IPv4 addresses only"), TRANSPORT_FAMILY_IPV4), OPT_SET_INT('6', "ipv6", &family, N_("use IPv6 addresses only"), @@ -264,7 +266,7 @@ static void find_non_local_tags(struct transport *transport, struct string_list_item *item = NULL; for_each_ref(add_existing, &existing_refs); - for (ref = transport_get_remote_refs(transport); ref; ref = ref->next) { + for (ref = transport_get_remote_refs(transport, NULL); ref; ref = ref->next) { if (!starts_with(ref->name, "refs/tags/")) continue; @@ -346,11 +348,28 @@ static struct ref *get_ref_map(struct transport *transport, struct ref *rm; struct ref *ref_map = NULL; struct ref **tail = &ref_map; + struct argv_array ref_prefixes = ARGV_ARRAY_INIT; /* opportunistically-updated references: */ struct ref *orefs = NULL, **oref_tail = &orefs; - const struct ref *remote_refs = transport_get_remote_refs(transport); + const struct ref *remote_refs; + + for (i = 0; i < refspec_count; i++) { + if (!refspecs[i].exact_sha1) { + const char *glob = strchr(refspecs[i].src, '*'); + if (glob) + argv_array_pushf(&ref_prefixes, "%.*s", + (int)(glob - refspecs[i].src), + refspecs[i].src); + else + expand_ref_prefix(&ref_prefixes, refspecs[i].src); + } + } + + remote_refs = transport_get_remote_refs(transport, &ref_prefixes); + + argv_array_clear(&ref_prefixes); if (refspec_count) { struct refspec *fetch_refspec; @@ -637,7 +656,7 @@ static int update_local_ref(struct ref *ref, struct branch *current_branch = branch_get(NULL); const char *pretty_ref = prettify_refname(ref->name); - type = oid_object_info(&ref->new_oid, NULL); + type = oid_object_info(the_repository, &ref->new_oid, NULL); if (type < 0) die(_("object %s not found"), oid_to_hex(&ref->new_oid)); @@ -1400,6 +1419,9 @@ static int fetch_one(struct remote *remote, int argc, const char **argv, int pru } } + if (server_options.nr) + gtransport->server_options = &server_options; + sigchain_push_common(unlock_pack_on_signal); atexit(unlock_pack); refspec = parse_fetch_refspec(ref_nr, refs); diff --git a/builtin/fsck.c b/builtin/fsck.c index 087360a675..9d59d7d5a2 100644 --- a/builtin/fsck.c +++ b/builtin/fsck.c @@ -67,7 +67,8 @@ static const char *printable_type(struct object *obj) const char *ret; if (obj->type == OBJ_NONE) { - enum object_type type = oid_object_info(&obj->oid, NULL); + enum object_type type = oid_object_info(the_repository, + &obj->oid, NULL); if (type > 0) object_as_type(obj, type, 0); } diff --git a/builtin/gc.c b/builtin/gc.c index 3e67124eaa..c4777b2449 100644 --- a/builtin/gc.c +++ b/builtin/gc.c @@ -22,6 +22,10 @@ #include "commit.h" #include "packfile.h" #include "object-store.h" +#include "pack.h" +#include "pack-objects.h" +#include "blob.h" +#include "tree.h" #define FAILED_RUN "failed to run %s" @@ -41,6 +45,8 @@ static timestamp_t gc_log_expire_time; static const char *gc_log_expire = "1.day.ago"; static const char *prune_expire = "2.weeks.ago"; static const char *prune_worktrees_expire = "3.months.ago"; +static unsigned long big_pack_threshold; +static unsigned long max_delta_cache_size = DEFAULT_DELTA_CACHE_SIZE; static struct argv_array pack_refs_cmd = ARGV_ARRAY_INIT; static struct argv_array reflog = ARGV_ARRAY_INIT; @@ -128,6 +134,9 @@ static void gc_config(void) git_config_get_expiry("gc.worktreepruneexpire", &prune_worktrees_expire); git_config_get_expiry("gc.logexpiry", &gc_log_expire); + git_config_get_ulong("gc.bigpackthreshold", &big_pack_threshold); + git_config_get_ulong("pack.deltacachesize", &max_delta_cache_size); + git_config(git_default_config, NULL); } @@ -166,6 +175,28 @@ static int too_many_loose_objects(void) return needed; } +static struct packed_git *find_base_packs(struct string_list *packs, + unsigned long limit) +{ + struct packed_git *p, *base = NULL; + + for (p = get_packed_git(the_repository); p; p = p->next) { + if (!p->pack_local) + continue; + if (limit) { + if (p->pack_size >= limit) + string_list_append(packs, p->pack_name); + } else if (!base || base->pack_size < p->pack_size) { + base = p; + } + } + + if (base) + string_list_append(packs, base->pack_name); + + return base; +} + static int too_many_packs(void) { struct packed_git *p; @@ -188,7 +219,86 @@ static int too_many_packs(void) return gc_auto_pack_limit < cnt; } -static void add_repack_all_option(void) +static uint64_t total_ram(void) +{ +#if defined(HAVE_SYSINFO) + struct sysinfo si; + + if (!sysinfo(&si)) + return si.totalram; +#elif defined(HAVE_BSD_SYSCTL) && (defined(HW_MEMSIZE) || defined(HW_PHYSMEM)) + int64_t physical_memory; + int mib[2]; + size_t length; + + mib[0] = CTL_HW; +# if defined(HW_MEMSIZE) + mib[1] = HW_MEMSIZE; +# else + mib[1] = HW_PHYSMEM; +# endif + length = sizeof(int64_t); + if (!sysctl(mib, 2, &physical_memory, &length, NULL, 0)) + return physical_memory; +#elif defined(GIT_WINDOWS_NATIVE) + MEMORYSTATUSEX memInfo; + + memInfo.dwLength = sizeof(MEMORYSTATUSEX); + if (GlobalMemoryStatusEx(&memInfo)) + return memInfo.ullTotalPhys; +#endif + return 0; +} + +static uint64_t estimate_repack_memory(struct packed_git *pack) +{ + unsigned long nr_objects = approximate_object_count(); + size_t os_cache, heap; + + if (!pack || !nr_objects) + return 0; + + /* + * First we have to scan through at least one pack. + * Assume enough room in OS file cache to keep the entire pack + * or we may accidentally evict data of other processes from + * the cache. + */ + os_cache = pack->pack_size + pack->index_size; + /* then pack-objects needs lots more for book keeping */ + heap = sizeof(struct object_entry) * nr_objects; + /* + * internal rev-list --all --objects takes up some memory too, + * let's say half of it is for blobs + */ + heap += sizeof(struct blob) * nr_objects / 2; + /* + * and the other half is for trees (commits and tags are + * usually insignificant) + */ + heap += sizeof(struct tree) * nr_objects / 2; + /* and then obj_hash[], underestimated in fact */ + heap += sizeof(struct object *) * nr_objects; + /* revindex is used also */ + heap += sizeof(struct revindex_entry) * nr_objects; + /* + * read_sha1_file() (either at delta calculation phase, or + * writing phase) also fills up the delta base cache + */ + heap += delta_base_cache_limit; + /* and of course pack-objects has its own delta cache */ + heap += max_delta_cache_size; + + return os_cache + heap; +} + +static int keep_one_pack(struct string_list_item *item, void *data) +{ + argv_array_pushf(&repack, "--keep-pack=%s", basename(item->string)); + return 0; +} + +static void add_repack_all_option(struct string_list *keep_pack) { if (prune_expire && !strcmp(prune_expire, "now")) argv_array_push(&repack, "-a"); @@ -197,6 +307,9 @@ static void add_repack_all_option(void) if (prune_expire) argv_array_pushf(&repack, "--unpack-unreachable=%s", prune_expire); } + + if (keep_pack) + for_each_string_list(keep_pack, keep_one_pack, NULL); } static void add_repack_incremental_option(void) @@ -219,9 +332,35 @@ static int need_to_gc(void) * we run "repack -A -d -l". Otherwise we tell the caller * there is no need. */ - if (too_many_packs()) - add_repack_all_option(); - else if (too_many_loose_objects()) + if (too_many_packs()) { + struct string_list keep_pack = STRING_LIST_INIT_NODUP; + + if (big_pack_threshold) { + find_base_packs(&keep_pack, big_pack_threshold); + if (keep_pack.nr >= gc_auto_pack_limit) { + big_pack_threshold = 0; + string_list_clear(&keep_pack, 0); + find_base_packs(&keep_pack, 0); + } + } else { + struct packed_git *p = find_base_packs(&keep_pack, 0); + uint64_t mem_have, mem_want; + + mem_have = total_ram(); + mem_want = estimate_repack_memory(p); + + /* + * Only allow 1/2 of memory for pack-objects, leave + * the rest for the OS and other processes in the + * system. + */ + if (!mem_have || mem_want < mem_have / 2) + string_list_clear(&keep_pack, 0); + } + + add_repack_all_option(&keep_pack); + string_list_clear(&keep_pack, 0); + } else if (too_many_loose_objects()) add_repack_incremental_option(); else return 0; @@ -354,6 +493,8 @@ int cmd_gc(int argc, const char **argv, const char *prefix) const char *name; pid_t pid; int daemonized = 0; + int keep_base_pack = -1; + timestamp_t dummy; struct option builtin_gc_options[] = { OPT__QUIET(&quiet, N_("suppress progress reporting")), @@ -366,6 +507,8 @@ int cmd_gc(int argc, const char **argv, const char *prefix) OPT_BOOL_F(0, "force", &force, N_("force running gc even if there may be another gc running"), PARSE_OPT_NOCOMPLETE), + OPT_BOOL(0, "keep-largest-pack", &keep_base_pack, + N_("repack all other packs except the largest pack")), OPT_END() }; @@ -382,7 +525,7 @@ int cmd_gc(int argc, const char **argv, const char *prefix) /* default expiry time, overwritten in gc_config */ gc_config(); if (parse_expiry_date(gc_log_expire, &gc_log_expire_time)) - die(_("Failed to parse gc.logexpiry value %s"), gc_log_expire); + die(_("failed to parse gc.logexpiry value %s"), gc_log_expire); if (pack_refs < 0) pack_refs = !is_bare_repository(); @@ -392,6 +535,9 @@ int cmd_gc(int argc, const char **argv, const char *prefix) if (argc > 0) usage_with_options(builtin_gc_usage, builtin_gc_options); + if (prune_expire && parse_expiry_date(prune_expire, &dummy)) + die(_("failed to parse prune expiry value %s"), prune_expire); + if (aggressive) { argv_array_push(&repack, "-f"); if (aggressive_depth > 0) @@ -431,8 +577,19 @@ int cmd_gc(int argc, const char **argv, const char *prefix) */ daemonized = !daemonize(); } - } else - add_repack_all_option(); + } else { + struct string_list keep_pack = STRING_LIST_INIT_NODUP; + + if (keep_base_pack != -1) { + if (keep_base_pack) + find_base_packs(&keep_pack, 0); + } else if (big_pack_threshold) { + find_base_packs(&keep_pack, big_pack_threshold); + } + + add_repack_all_option(&keep_pack); + string_list_clear(&keep_pack, 0); + } name = lock_repo_for_gc(force, &pid); if (name) { diff --git a/builtin/grep.c b/builtin/grep.c index 5f32d2ce84..6e7bc76785 100644 --- a/builtin/grep.c +++ b/builtin/grep.c @@ -602,8 +602,7 @@ static int grep_tree(struct grep_opt *opt, const struct pathspec *pathspec, } static int grep_object(struct grep_opt *opt, const struct pathspec *pathspec, - struct object *obj, const char *name, const char *path, - struct repository *repo) + struct object *obj, const char *name, const char *path) { if (obj->type == OBJ_BLOB) return grep_oid(opt, &obj->oid, name, 0, path); @@ -630,7 +629,7 @@ static int grep_object(struct grep_opt *opt, const struct pathspec *pathspec, } init_tree_desc(&tree, data, size); hit = grep_tree(opt, pathspec, &tree, &base, base.len, - obj->type == OBJ_COMMIT, repo); + obj->type == OBJ_COMMIT, the_repository); strbuf_release(&base); free(data); return hit; @@ -639,7 +638,6 @@ static int grep_object(struct grep_opt *opt, const struct pathspec *pathspec, } static int grep_objects(struct grep_opt *opt, const struct pathspec *pathspec, - struct repository *repo, const struct object_array *list) { unsigned int i; @@ -652,11 +650,11 @@ static int grep_objects(struct grep_opt *opt, const struct pathspec *pathspec, /* load the gitmodules file for this rev */ if (recurse_submodules) { - submodule_free(); + submodule_free(the_repository); gitmodules_config_oid(&real_obj->oid); } - if (grep_object(opt, pathspec, real_obj, list->objects[i].name, list->objects[i].path, - repo)) { + if (grep_object(opt, pathspec, real_obj, list->objects[i].name, + list->objects[i].path)) { hit = 1; if (opt->status_only) break; @@ -1108,7 +1106,7 @@ int cmd_grep(int argc, const char **argv, const char *prefix) if (cached) die(_("both --cached and trees are given.")); - hit = grep_objects(&opt, &pathspec, the_repository, &list); + hit = grep_objects(&opt, &pathspec, &list); } if (num_threads) diff --git a/builtin/index-pack.c b/builtin/index-pack.c index 78e66b9986..e2f670bef9 100644 --- a/builtin/index-pack.c +++ b/builtin/index-pack.c @@ -223,7 +223,7 @@ static unsigned check_object(struct object *obj) if (!(obj->flags & FLAG_CHECKED)) { unsigned long size; - int type = oid_object_info(&obj->oid, &size); + int type = oid_object_info(the_repository, &obj->oid, &size); if (type <= 0) die(_("did not receive expected object %s"), oid_to_hex(&obj->oid)); @@ -812,7 +812,7 @@ static void sha1_object(const void *data, struct object_entry *obj_entry, enum object_type has_type; unsigned long has_size; read_lock(); - has_type = oid_object_info(oid, &has_size); + has_type = oid_object_info(the_repository, oid, &has_size); if (has_type < 0) die(_("cannot read existing object info %s"), oid_to_hex(oid)); if (has_type != type || has_size != size) @@ -1271,7 +1271,7 @@ static void conclude_pack(int fix_thin_pack, const char *curr_pack, unsigned cha nr_objects - nr_objects_initial); stop_progress_msg(&progress, msg.buf); strbuf_release(&msg); - hashclose(f, tail_hash, 0); + finalize_hashfile(f, tail_hash, 0); hashcpy(read_hash, pack_hash); fixup_pack_header_footer(output_fd, pack_hash, curr_pack, nr_objects, diff --git a/builtin/log.c b/builtin/log.c index 71f68a3e4f..75f7ff0441 100644 --- a/builtin/log.c +++ b/builtin/log.c @@ -1067,8 +1067,8 @@ static void make_cover_letter(struct rev_info *rev, int use_stdout, diff_setup_done(&opts); - diff_tree_oid(&origin->tree->object.oid, - &head->tree->object.oid, + diff_tree_oid(get_commit_tree_oid(origin), + get_commit_tree_oid(head), "", &opts); diffcore_std(&opts); diff_flush(&opts); diff --git a/builtin/ls-remote.c b/builtin/ls-remote.c index 540d56429f..1a25df7ee1 100644 --- a/builtin/ls-remote.c +++ b/builtin/ls-remote.c @@ -1,7 +1,9 @@ #include "builtin.h" #include "cache.h" #include "transport.h" +#include "ref-filter.h" #include "remote.h" +#include "refs.h" static const char * const ls_remote_usage[] = { N_("git ls-remote [--heads] [--tags] [--refs] [--upload-pack=<exec>]\n" @@ -43,10 +45,15 @@ int cmd_ls_remote(int argc, const char **argv, const char *prefix) int show_symref_target = 0; const char *uploadpack = NULL; const char **pattern = NULL; + struct argv_array ref_prefixes = ARGV_ARRAY_INIT; + int i; + struct string_list server_options = STRING_LIST_INIT_DUP; struct remote *remote; struct transport *transport; const struct ref *ref; + struct ref_array ref_array; + static struct ref_sorting *sorting = NULL, **sorting_tail = &sorting; struct option options[] = { OPT__QUIET(&quiet, N_("do not print remote URL")), @@ -60,14 +67,19 @@ int cmd_ls_remote(int argc, const char **argv, const char *prefix) OPT_BIT(0, "refs", &flags, N_("do not show peeled tags"), REF_NORMAL), OPT_BOOL(0, "get-url", &get_url, N_("take url.<base>.insteadOf into account")), + OPT_CALLBACK(0 , "sort", sorting_tail, N_("key"), + N_("field name to sort on"), &parse_opt_ref_sorting), OPT_SET_INT_F(0, "exit-code", &status, N_("exit with exit code 2 if no matching refs are found"), 2, PARSE_OPT_NOCOMPLETE), OPT_BOOL(0, "symref", &show_symref_target, N_("show underlying ref in addition to the object pointed by it")), + OPT_STRING_LIST('o', "server-option", &server_options, N_("server-specific"), N_("option to transmit")), OPT_END() }; + memset(&ref_array, 0, sizeof(ref_array)); + argc = parse_options(argc, argv, prefix, options, ls_remote_usage, PARSE_OPT_STOP_AT_NON_OPTION); dest = argv[0]; @@ -75,8 +87,17 @@ int cmd_ls_remote(int argc, const char **argv, const char *prefix) if (argc > 1) { int i; pattern = xcalloc(argc, sizeof(const char *)); - for (i = 1; i < argc; i++) + for (i = 1; i < argc; i++) { + const char *glob; pattern[i - 1] = xstrfmt("*/%s", argv[i]); + + glob = strchr(argv[i], '*'); + if (glob) + argv_array_pushf(&ref_prefixes, "%.*s", + (int)(glob - argv[i]), argv[i]); + else + expand_ref_prefix(&ref_prefixes, argv[i]); + } } remote = remote_get(dest); @@ -90,28 +111,46 @@ int cmd_ls_remote(int argc, const char **argv, const char *prefix) if (get_url) { printf("%s\n", *remote->url); + UNLEAK(sorting); return 0; } transport = transport_get(remote, NULL); if (uploadpack != NULL) transport_set_option(transport, TRANS_OPT_UPLOADPACK, uploadpack); + if (server_options.nr) + transport->server_options = &server_options; - ref = transport_get_remote_refs(transport); - if (transport_disconnect(transport)) + ref = transport_get_remote_refs(transport, &ref_prefixes); + if (transport_disconnect(transport)) { + UNLEAK(sorting); return 1; + } if (!dest && !quiet) fprintf(stderr, "From %s\n", *remote->url); for ( ; ref; ref = ref->next) { + struct ref_array_item *item; if (!check_ref_type(ref, flags)) continue; if (!tail_match(pattern, ref->name)) continue; + item = ref_array_push(&ref_array, ref->name, &ref->old_oid); + item->symref = xstrdup_or_null(ref->symref); + } + + if (sorting) + ref_array_sort(sorting, &ref_array); + + for (i = 0; i < ref_array.nr; i++) { + const struct ref_array_item *ref = ref_array.items[i]; if (show_symref_target && ref->symref) - printf("ref: %s\t%s\n", ref->symref, ref->name); - printf("%s\t%s\n", oid_to_hex(&ref->old_oid), ref->name); + printf("ref: %s\t%s\n", ref->symref, ref->refname); + printf("%s\t%s\n", oid_to_hex(&ref->objectname), ref->refname); status = 0; /* we found something */ } + + UNLEAK(sorting); + UNLEAK(ref_array); return status; } diff --git a/builtin/ls-tree.c b/builtin/ls-tree.c index d44b4f9c27..409da4e835 100644 --- a/builtin/ls-tree.c +++ b/builtin/ls-tree.c @@ -94,7 +94,7 @@ static int show_tree(const struct object_id *oid, struct strbuf *base, char size_text[24]; if (!strcmp(type, blob_type)) { unsigned long size; - if (oid_object_info(oid, &size) == OBJ_BAD) + if (oid_object_info(the_repository, oid, &size) == OBJ_BAD) xsnprintf(size_text, sizeof(size_text), "BAD"); else diff --git a/builtin/mktag.c b/builtin/mktag.c index 9f5a50a8fd..82a6e86077 100644 --- a/builtin/mktag.c +++ b/builtin/mktag.c @@ -1,5 +1,6 @@ #include "builtin.h" #include "tag.h" +#include "replace-object.h" /* * A signature file has a very simple fixed format: four lines @@ -24,7 +25,7 @@ static int verify_object(const struct object_id *oid, const char *expected_type) enum object_type type; unsigned long size; void *buffer = read_object_file(oid, &type, &size); - const struct object_id *repl = lookup_replace_object(oid); + const struct object_id *repl = lookup_replace_object(the_repository, oid); if (buffer) { if (type == type_from_string(expected_type)) diff --git a/builtin/mktree.c b/builtin/mktree.c index 263c530315..bb76b469fd 100644 --- a/builtin/mktree.c +++ b/builtin/mktree.c @@ -116,7 +116,7 @@ static void mktree_line(char *buf, size_t len, int nul_term_line, int allow_miss } /* Check the type of object identified by sha1 */ - obj_type = oid_object_info(&oid, NULL); + obj_type = oid_object_info(the_repository, &oid, NULL); if (obj_type < 0) { if (allow_missing) { ; /* no problem - missing objects are presumed to be of the right type */ diff --git a/builtin/mv.c b/builtin/mv.c index 6d141f7a53..7a63667d64 100644 --- a/builtin/mv.c +++ b/builtin/mv.c @@ -276,10 +276,12 @@ int cmd_mv(int argc, const char **argv, const char *prefix) die_errno(_("renaming '%s' failed"), src); } if (submodule_gitfile[i]) { - if (submodule_gitfile[i] != SUBMODULE_WITH_GITDIR) - connect_work_tree_and_git_dir(dst, submodule_gitfile[i]); if (!update_path_in_gitmodules(src, dst)) gitmodules_modified = 1; + if (submodule_gitfile[i] != SUBMODULE_WITH_GITDIR) + connect_work_tree_and_git_dir(dst, + submodule_gitfile[i], + 1); } if (mode == WORKING_DIRECTORY) diff --git a/builtin/pack-objects.c b/builtin/pack-objects.c index 4bdae5a1d8..8552d7e42e 100644 --- a/builtin/pack-objects.c +++ b/builtin/pack-objects.c @@ -30,6 +30,19 @@ #include "list.h" #include "packfile.h" #include "object-store.h" +#include "dir.h" + +#define IN_PACK(obj) oe_in_pack(&to_pack, obj) +#define SIZE(obj) oe_size(&to_pack, obj) +#define SET_SIZE(obj,size) oe_set_size(&to_pack, obj, size) +#define DELTA_SIZE(obj) oe_delta_size(&to_pack, obj) +#define DELTA(obj) oe_delta(&to_pack, obj) +#define DELTA_CHILD(obj) oe_delta_child(&to_pack, obj) +#define DELTA_SIBLING(obj) oe_delta_sibling(&to_pack, obj) +#define SET_DELTA(obj, val) oe_set_delta(&to_pack, obj, val) +#define SET_DELTA_SIZE(obj, val) oe_set_delta_size(&to_pack, obj, val) +#define SET_DELTA_CHILD(obj, val) oe_set_delta_child(&to_pack, obj, val) +#define SET_DELTA_SIBLING(obj, val) oe_set_delta_sibling(&to_pack, obj, val) static const char *pack_usage[] = { N_("git pack-objects --stdout [<options>...] [< <ref-list> | < <object-list>]"), @@ -45,7 +58,7 @@ static const char *pack_usage[] = { static struct packing_data to_pack; static struct pack_idx_entry **written_list; -static uint32_t nr_result, nr_written; +static uint32_t nr_result, nr_written, nr_seen; static int non_empty; static int reuse_delta = 1, reuse_object = 1; @@ -55,7 +68,8 @@ static int pack_loose_unreachable; static int local; static int have_non_local_packs; static int incremental; -static int ignore_packed_keep; +static int ignore_packed_keep_on_disk; +static int ignore_packed_keep_in_core; static int allow_ofs_delta; static struct pack_idx_option pack_idx_opts; static const char *base_name; @@ -80,7 +94,7 @@ static uint16_t write_bitmap_options; static int exclude_promisor_objects; static unsigned long delta_cache_size = 0; -static unsigned long max_delta_cache_size = 256 * 1024 * 1024; +static unsigned long max_delta_cache_size = DEFAULT_DELTA_CACHE_SIZE; static unsigned long cache_max_small_delta_size = 1000; static unsigned long window_memory_limit = 0; @@ -127,13 +141,14 @@ static void *get_delta(struct object_entry *entry) buf = read_object_file(&entry->idx.oid, &type, &size); if (!buf) die("unable to read %s", oid_to_hex(&entry->idx.oid)); - base_buf = read_object_file(&entry->delta->idx.oid, &type, &base_size); + base_buf = read_object_file(&DELTA(entry)->idx.oid, &type, + &base_size); if (!base_buf) die("unable to read %s", - oid_to_hex(&entry->delta->idx.oid)); + oid_to_hex(&DELTA(entry)->idx.oid)); delta_buf = diff_delta(base_buf, base_size, buf, size, &delta_size, 0); - if (!delta_buf || delta_size != entry->delta_size) + if (!delta_buf || delta_size != DELTA_SIZE(entry)) die("delta size changed"); free(buf); free(base_buf); @@ -266,8 +281,8 @@ static unsigned long write_no_reuse_object(struct hashfile *f, struct object_ent struct git_istream *st = NULL; if (!usable_delta) { - if (entry->type == OBJ_BLOB && - entry->size > big_file_threshold && + if (oe_type(entry) == OBJ_BLOB && + oe_size_greater_than(&to_pack, entry, big_file_threshold) && (st = open_istream(&entry->idx.oid, &type, &size, NULL)) != NULL) buf = NULL; else { @@ -283,15 +298,15 @@ static unsigned long write_no_reuse_object(struct hashfile *f, struct object_ent FREE_AND_NULL(entry->delta_data); entry->z_delta_size = 0; } else if (entry->delta_data) { - size = entry->delta_size; + size = DELTA_SIZE(entry); buf = entry->delta_data; entry->delta_data = NULL; - type = (allow_ofs_delta && entry->delta->idx.offset) ? + type = (allow_ofs_delta && DELTA(entry)->idx.offset) ? OBJ_OFS_DELTA : OBJ_REF_DELTA; } else { buf = get_delta(entry); - size = entry->delta_size; - type = (allow_ofs_delta && entry->delta->idx.offset) ? + size = DELTA_SIZE(entry); + type = (allow_ofs_delta && DELTA(entry)->idx.offset) ? OBJ_OFS_DELTA : OBJ_REF_DELTA; } @@ -315,7 +330,7 @@ static unsigned long write_no_reuse_object(struct hashfile *f, struct object_ent * encoding of the relative offset for the delta * base from this object's position in the pack. */ - off_t ofs = entry->idx.offset - entry->delta->idx.offset; + off_t ofs = entry->idx.offset - DELTA(entry)->idx.offset; unsigned pos = sizeof(dheader) - 1; dheader[pos] = ofs & 127; while (ofs >>= 7) @@ -341,7 +356,7 @@ static unsigned long write_no_reuse_object(struct hashfile *f, struct object_ent return 0; } hashwrite(f, header, hdrlen); - hashwrite(f, entry->delta->idx.oid.hash, 20); + hashwrite(f, DELTA(entry)->idx.oid.hash, 20); hdrlen += 20; } else { if (limit && hdrlen + datalen + 20 >= limit) { @@ -367,21 +382,22 @@ static unsigned long write_no_reuse_object(struct hashfile *f, struct object_ent static off_t write_reuse_object(struct hashfile *f, struct object_entry *entry, unsigned long limit, int usable_delta) { - struct packed_git *p = entry->in_pack; + struct packed_git *p = IN_PACK(entry); struct pack_window *w_curs = NULL; struct revindex_entry *revidx; off_t offset; - enum object_type type = entry->type; + enum object_type type = oe_type(entry); off_t datalen; unsigned char header[MAX_PACK_OBJECT_HEADER], dheader[MAX_PACK_OBJECT_HEADER]; unsigned hdrlen; + unsigned long entry_size = SIZE(entry); - if (entry->delta) - type = (allow_ofs_delta && entry->delta->idx.offset) ? + if (DELTA(entry)) + type = (allow_ofs_delta && DELTA(entry)->idx.offset) ? OBJ_OFS_DELTA : OBJ_REF_DELTA; hdrlen = encode_in_pack_object_header(header, sizeof(header), - type, entry->size); + type, entry_size); offset = entry->in_pack_offset; revidx = find_pack_revindex(p, offset); @@ -398,7 +414,7 @@ static off_t write_reuse_object(struct hashfile *f, struct object_entry *entry, datalen -= entry->in_pack_header_size; if (!pack_to_stdout && p->index_version == 1 && - check_pack_inflate(p, &w_curs, offset, datalen, entry->size)) { + check_pack_inflate(p, &w_curs, offset, datalen, entry_size)) { error("corrupt packed object for %s", oid_to_hex(&entry->idx.oid)); unuse_pack(&w_curs); @@ -406,7 +422,7 @@ static off_t write_reuse_object(struct hashfile *f, struct object_entry *entry, } if (type == OBJ_OFS_DELTA) { - off_t ofs = entry->idx.offset - entry->delta->idx.offset; + off_t ofs = entry->idx.offset - DELTA(entry)->idx.offset; unsigned pos = sizeof(dheader) - 1; dheader[pos] = ofs & 127; while (ofs >>= 7) @@ -425,7 +441,7 @@ static off_t write_reuse_object(struct hashfile *f, struct object_entry *entry, return 0; } hashwrite(f, header, hdrlen); - hashwrite(f, entry->delta->idx.oid.hash, 20); + hashwrite(f, DELTA(entry)->idx.oid.hash, 20); hdrlen += 20; reused_delta++; } else { @@ -465,28 +481,29 @@ static off_t write_object(struct hashfile *f, else limit = pack_size_limit - write_offset; - if (!entry->delta) + if (!DELTA(entry)) usable_delta = 0; /* no delta */ else if (!pack_size_limit) usable_delta = 1; /* unlimited packfile */ - else if (entry->delta->idx.offset == (off_t)-1) + else if (DELTA(entry)->idx.offset == (off_t)-1) usable_delta = 0; /* base was written to another pack */ - else if (entry->delta->idx.offset) + else if (DELTA(entry)->idx.offset) usable_delta = 1; /* base already exists in this pack */ else usable_delta = 0; /* base could end up in another pack */ if (!reuse_object) to_reuse = 0; /* explicit */ - else if (!entry->in_pack) + else if (!IN_PACK(entry)) to_reuse = 0; /* can't reuse what we don't have */ - else if (entry->type == OBJ_REF_DELTA || entry->type == OBJ_OFS_DELTA) + else if (oe_type(entry) == OBJ_REF_DELTA || + oe_type(entry) == OBJ_OFS_DELTA) /* check_object() decided it for us ... */ to_reuse = usable_delta; /* ... but pack split may override that */ - else if (entry->type != entry->in_pack_type) + else if (oe_type(entry) != entry->in_pack_type) to_reuse = 0; /* pack has delta which is unusable */ - else if (entry->delta) + else if (DELTA(entry)) to_reuse = 0; /* we want to pack afresh */ else to_reuse = 1; /* we have it in-pack undeltified, @@ -538,12 +555,12 @@ static enum write_one_status write_one(struct hashfile *f, } /* if we are deltified, write out base object first. */ - if (e->delta) { + if (DELTA(e)) { e->idx.offset = 1; /* now recurse */ - switch (write_one(f, e->delta, offset)) { + switch (write_one(f, DELTA(e), offset)) { case WRITE_ONE_RECURSIVE: /* we cannot depend on this one */ - e->delta = NULL; + SET_DELTA(e, NULL); break; default: break; @@ -605,34 +622,34 @@ static void add_descendants_to_write_order(struct object_entry **wo, /* add this node... */ add_to_write_order(wo, endp, e); /* all its siblings... */ - for (s = e->delta_sibling; s; s = s->delta_sibling) { + for (s = DELTA_SIBLING(e); s; s = DELTA_SIBLING(s)) { add_to_write_order(wo, endp, s); } } /* drop down a level to add left subtree nodes if possible */ - if (e->delta_child) { + if (DELTA_CHILD(e)) { add_to_order = 1; - e = e->delta_child; + e = DELTA_CHILD(e); } else { add_to_order = 0; /* our sibling might have some children, it is next */ - if (e->delta_sibling) { - e = e->delta_sibling; + if (DELTA_SIBLING(e)) { + e = DELTA_SIBLING(e); continue; } /* go back to our parent node */ - e = e->delta; - while (e && !e->delta_sibling) { + e = DELTA(e); + while (e && !DELTA_SIBLING(e)) { /* we're on the right side of a subtree, keep * going up until we can go right again */ - e = e->delta; + e = DELTA(e); } if (!e) { /* done- we hit our original root node */ return; } /* pass it off to sibling at this level */ - e = e->delta_sibling; + e = DELTA_SIBLING(e); } }; } @@ -643,7 +660,7 @@ static void add_family_to_write_order(struct object_entry **wo, { struct object_entry *root; - for (root = e; root->delta; root = root->delta) + for (root = e; DELTA(root); root = DELTA(root)) ; /* nothing */ add_descendants_to_write_order(wo, endp, root); } @@ -658,8 +675,8 @@ static struct object_entry **compute_write_order(void) for (i = 0; i < to_pack.nr_objects; i++) { objects[i].tagged = 0; objects[i].filled = 0; - objects[i].delta_child = NULL; - objects[i].delta_sibling = NULL; + SET_DELTA_CHILD(&objects[i], NULL); + SET_DELTA_SIBLING(&objects[i], NULL); } /* @@ -669,11 +686,11 @@ static struct object_entry **compute_write_order(void) */ for (i = to_pack.nr_objects; i > 0;) { struct object_entry *e = &objects[--i]; - if (!e->delta) + if (!DELTA(e)) continue; /* Mark me as the first child */ - e->delta_sibling = e->delta->delta_child; - e->delta->delta_child = e; + e->delta_sibling_idx = DELTA(e)->delta_child_idx; + SET_DELTA_CHILD(DELTA(e), e); } /* @@ -705,8 +722,8 @@ static struct object_entry **compute_write_order(void) * And then all remaining commits and tags. */ for (i = last_untagged; i < to_pack.nr_objects; i++) { - if (objects[i].type != OBJ_COMMIT && - objects[i].type != OBJ_TAG) + if (oe_type(&objects[i]) != OBJ_COMMIT && + oe_type(&objects[i]) != OBJ_TAG) continue; add_to_write_order(wo, &wo_end, &objects[i]); } @@ -715,7 +732,7 @@ static struct object_entry **compute_write_order(void) * And then all the trees. */ for (i = last_untagged; i < to_pack.nr_objects; i++) { - if (objects[i].type != OBJ_TREE) + if (oe_type(&objects[i]) != OBJ_TREE) continue; add_to_write_order(wo, &wo_end, &objects[i]); } @@ -837,11 +854,11 @@ static void write_pack_file(void) * If so, rewrite it like in fast-import */ if (pack_to_stdout) { - hashclose(f, oid.hash, CSUM_CLOSE); + finalize_hashfile(f, oid.hash, CSUM_HASH_IN_STREAM | CSUM_CLOSE); } else if (nr_written == nr_remaining) { - hashclose(f, oid.hash, CSUM_FSYNC); + finalize_hashfile(f, oid.hash, CSUM_HASH_IN_STREAM | CSUM_FSYNC | CSUM_CLOSE); } else { - int fd = hashclose(f, oid.hash, 0); + int fd = finalize_hashfile(f, oid.hash, 0); fixup_pack_header_footer(fd, oid.hash, pack_tmp_name, nr_written, oid.hash, offset); close(fd); @@ -878,7 +895,8 @@ static void write_pack_file(void) if (write_bitmap_index) { bitmap_writer_set_checksum(oid.hash); - bitmap_writer_build_type_index(written_list, nr_written); + bitmap_writer_build_type_index( + &to_pack, written_list, nr_written); } finish_tmp_packfile(&tmpname, pack_tmp_name, @@ -982,13 +1000,16 @@ static int want_found_object(int exclude, struct packed_git *p) * Otherwise, we signal "-1" at the end to tell the caller that we do * not know either way, and it needs to check more packs. */ - if (!ignore_packed_keep && + if (!ignore_packed_keep_on_disk && + !ignore_packed_keep_in_core && (!local || !have_non_local_packs)) return 1; if (local && !p->pack_local) return 0; - if (ignore_packed_keep && p->pack_local && p->pack_keep) + if (p->pack_local && + ((ignore_packed_keep_on_disk && p->pack_keep) || + (ignore_packed_keep_in_core && p->pack_keep_in_core))) return 0; /* we don't know yet; keep looking for more packs */ @@ -1066,14 +1087,13 @@ static void create_object_entry(const struct object_id *oid, entry = packlist_alloc(&to_pack, oid->hash, index_pos); entry->hash = hash; - if (type) - entry->type = type; + oe_set_type(entry, type); if (exclude) entry->preferred_base = 1; else nr_result++; if (found_pack) { - entry->in_pack = found_pack; + oe_set_in_pack(&to_pack, entry, found_pack); entry->in_pack_offset = found_offset; } @@ -1091,6 +1111,8 @@ static int add_object_entry(const struct object_id *oid, enum object_type type, off_t found_offset = 0; uint32_t index_pos; + display_progress(progress_state, ++nr_seen); + if (have_duplicate_entry(oid, exclude, &index_pos)) return 0; @@ -1106,8 +1128,6 @@ static int add_object_entry(const struct object_id *oid, enum object_type type, create_object_entry(oid, type, pack_name_hash(name), exclude, name && no_try_delta(name), index_pos, found_pack, found_offset); - - display_progress(progress_state, nr_result); return 1; } @@ -1118,6 +1138,8 @@ static int add_object_entry_from_bitmap(const struct object_id *oid, { uint32_t index_pos; + display_progress(progress_state, ++nr_seen); + if (have_duplicate_entry(oid, 0, &index_pos)) return 0; @@ -1125,8 +1147,6 @@ static int add_object_entry_from_bitmap(const struct object_id *oid, return 0; create_object_entry(oid, type, name_hash, 0, 0, index_pos, pack, offset); - - display_progress(progress_state, nr_result); return 1; } @@ -1398,8 +1418,10 @@ static void cleanup_preferred_base(void) static void check_object(struct object_entry *entry) { - if (entry->in_pack) { - struct packed_git *p = entry->in_pack; + unsigned long canonical_size; + + if (IN_PACK(entry)) { + struct packed_git *p = IN_PACK(entry); struct pack_window *w_curs = NULL; const unsigned char *base_ref = NULL; struct object_entry *base_entry; @@ -1407,6 +1429,8 @@ static void check_object(struct object_entry *entry) unsigned long avail; off_t ofs; unsigned char *buf, c; + enum object_type type; + unsigned long in_pack_size; buf = use_pack(p, &w_curs, entry->in_pack_offset, &avail); @@ -1415,11 +1439,15 @@ static void check_object(struct object_entry *entry) * since non-delta representations could still be reused. */ used = unpack_object_header_buffer(buf, avail, - &entry->in_pack_type, - &entry->size); + &type, + &in_pack_size); if (used == 0) goto give_up; + if (type < 0) + BUG("invalid type %d", type); + entry->in_pack_type = type; + /* * Determine if this is a delta and if so whether we can * reuse it or not. Otherwise let's find out as cheaply as @@ -1428,9 +1456,10 @@ static void check_object(struct object_entry *entry) switch (entry->in_pack_type) { default: /* Not a delta hence we've already got all we need. */ - entry->type = entry->in_pack_type; + oe_set_type(entry, entry->in_pack_type); + SET_SIZE(entry, in_pack_size); entry->in_pack_header_size = used; - if (entry->type < OBJ_COMMIT || entry->type > OBJ_BLOB) + if (oe_type(entry) < OBJ_COMMIT || oe_type(entry) > OBJ_BLOB) goto give_up; unuse_pack(&w_curs); return; @@ -1484,25 +1513,29 @@ static void check_object(struct object_entry *entry) * deltify other objects against, in order to avoid * circular deltas. */ - entry->type = entry->in_pack_type; - entry->delta = base_entry; - entry->delta_size = entry->size; - entry->delta_sibling = base_entry->delta_child; - base_entry->delta_child = entry; + oe_set_type(entry, entry->in_pack_type); + SET_SIZE(entry, in_pack_size); /* delta size */ + SET_DELTA(entry, base_entry); + SET_DELTA_SIZE(entry, in_pack_size); + entry->delta_sibling_idx = base_entry->delta_child_idx; + SET_DELTA_CHILD(base_entry, entry); unuse_pack(&w_curs); return; } - if (entry->type) { + if (oe_type(entry)) { + off_t delta_pos; + /* * This must be a delta and we already know what the * final object type is. Let's extract the actual * object size from the delta header. */ - entry->size = get_size_from_delta(p, &w_curs, - entry->in_pack_offset + entry->in_pack_header_size); - if (entry->size == 0) + delta_pos = entry->in_pack_offset + entry->in_pack_header_size; + canonical_size = get_size_from_delta(p, &w_curs, delta_pos); + if (canonical_size == 0) goto give_up; + SET_SIZE(entry, canonical_size); unuse_pack(&w_curs); return; } @@ -1516,27 +1549,34 @@ static void check_object(struct object_entry *entry) unuse_pack(&w_curs); } - entry->type = oid_object_info(&entry->idx.oid, &entry->size); - /* - * The error condition is checked in prepare_pack(). This is - * to permit a missing preferred base object to be ignored - * as a preferred base. Doing so can result in a larger - * pack file, but the transfer will still take place. - */ + oe_set_type(entry, + oid_object_info(the_repository, &entry->idx.oid, &canonical_size)); + if (entry->type_valid) { + SET_SIZE(entry, canonical_size); + } else { + /* + * Bad object type is checked in prepare_pack(). This is + * to permit a missing preferred base object to be ignored + * as a preferred base. Doing so can result in a larger + * pack file, but the transfer will still take place. + */ + } } static int pack_offset_sort(const void *_a, const void *_b) { const struct object_entry *a = *(struct object_entry **)_a; const struct object_entry *b = *(struct object_entry **)_b; + const struct packed_git *a_in_pack = IN_PACK(a); + const struct packed_git *b_in_pack = IN_PACK(b); /* avoid filesystem trashing with loose objects */ - if (!a->in_pack && !b->in_pack) + if (!a_in_pack && !b_in_pack) return oidcmp(&a->idx.oid, &b->idx.oid); - if (a->in_pack < b->in_pack) + if (a_in_pack < b_in_pack) return -1; - if (a->in_pack > b->in_pack) + if (a_in_pack > b_in_pack) return 1; return a->in_pack_offset < b->in_pack_offset ? -1 : (a->in_pack_offset > b->in_pack_offset); @@ -1557,29 +1597,37 @@ static int pack_offset_sort(const void *_a, const void *_b) */ static void drop_reused_delta(struct object_entry *entry) { - struct object_entry **p = &entry->delta->delta_child; + unsigned *idx = &to_pack.objects[entry->delta_idx - 1].delta_child_idx; struct object_info oi = OBJECT_INFO_INIT; + enum object_type type; + unsigned long size; + + while (*idx) { + struct object_entry *oe = &to_pack.objects[*idx - 1]; - while (*p) { - if (*p == entry) - *p = (*p)->delta_sibling; + if (oe == entry) + *idx = oe->delta_sibling_idx; else - p = &(*p)->delta_sibling; + idx = &oe->delta_sibling_idx; } - entry->delta = NULL; + SET_DELTA(entry, NULL); entry->depth = 0; - oi.sizep = &entry->size; - oi.typep = &entry->type; - if (packed_object_info(entry->in_pack, entry->in_pack_offset, &oi) < 0) { + oi.sizep = &size; + oi.typep = &type; + if (packed_object_info(the_repository, IN_PACK(entry), entry->in_pack_offset, &oi) < 0) { /* * We failed to get the info from this pack for some reason; * fall back to sha1_object_info, which may find another copy. - * And if that fails, the error will be recorded in entry->type + * And if that fails, the error will be recorded in oe_type(entry) * and dealt with in prepare_pack(). */ - entry->type = oid_object_info(&entry->idx.oid, &entry->size); + oe_set_type(entry, + oid_object_info(the_repository, &entry->idx.oid, &size)); + } else { + oe_set_type(entry, type); } + SET_SIZE(entry, size); } /* @@ -1603,7 +1651,7 @@ static void break_delta_chains(struct object_entry *entry) for (cur = entry, total_depth = 0; cur; - cur = cur->delta, total_depth++) { + cur = DELTA(cur), total_depth++) { if (cur->dfs_state == DFS_DONE) { /* * We've already seen this object and know it isn't @@ -1628,7 +1676,7 @@ static void break_delta_chains(struct object_entry *entry) * it's not a delta, we're done traversing, but we'll mark it * done to save time on future traversals. */ - if (!cur->delta) { + if (!DELTA(cur)) { cur->dfs_state = DFS_DONE; break; } @@ -1651,7 +1699,7 @@ static void break_delta_chains(struct object_entry *entry) * We keep all commits in the chain that we examined. */ cur->dfs_state = DFS_ACTIVE; - if (cur->delta->dfs_state == DFS_ACTIVE) { + if (DELTA(cur)->dfs_state == DFS_ACTIVE) { drop_reused_delta(cur); cur->dfs_state = DFS_DONE; break; @@ -1666,7 +1714,7 @@ static void break_delta_chains(struct object_entry *entry) * an extra "next" pointer to keep going after we reset cur->delta. */ for (cur = entry; cur; cur = next) { - next = cur->delta; + next = DELTA(cur); /* * We should have a chain of zero or more ACTIVE states down to @@ -1711,6 +1759,10 @@ static void get_object_details(void) uint32_t i; struct object_entry **sorted_by_offset; + if (progress) + progress_state = start_progress(_("Counting objects"), + to_pack.nr_objects); + sorted_by_offset = xcalloc(to_pack.nr_objects, sizeof(struct object_entry *)); for (i = 0; i < to_pack.nr_objects; i++) sorted_by_offset[i] = to_pack.objects + i; @@ -1719,9 +1771,12 @@ static void get_object_details(void) for (i = 0; i < to_pack.nr_objects; i++) { struct object_entry *entry = sorted_by_offset[i]; check_object(entry); - if (big_file_threshold < entry->size) + if (entry->type_valid && + oe_size_greater_than(&to_pack, entry, big_file_threshold)) entry->no_try_delta = 1; + display_progress(progress_state, i + 1); } + stop_progress(&progress_state); /* * This must happen in a second pass, since we rely on the delta @@ -1746,10 +1801,14 @@ static int type_size_sort(const void *_a, const void *_b) { const struct object_entry *a = *(struct object_entry **)_a; const struct object_entry *b = *(struct object_entry **)_b; + enum object_type a_type = oe_type(a); + enum object_type b_type = oe_type(b); + unsigned long a_size = SIZE(a); + unsigned long b_size = SIZE(b); - if (a->type > b->type) + if (a_type > b_type) return -1; - if (a->type < b->type) + if (a_type < b_type) return 1; if (a->hash > b->hash) return -1; @@ -1759,9 +1818,9 @@ static int type_size_sort(const void *_a, const void *_b) return -1; if (a->preferred_base < b->preferred_base) return 1; - if (a->size > b->size) + if (a_size > b_size) return -1; - if (a->size < b->size) + if (a_size < b_size) return 1; return a < b ? -1 : (a > b); /* newest first */ } @@ -1814,6 +1873,46 @@ static pthread_mutex_t progress_mutex; #endif +/* + * Return the size of the object without doing any delta + * reconstruction (so non-deltas are true object sizes, but deltas + * return the size of the delta data). + */ +unsigned long oe_get_size_slow(struct packing_data *pack, + const struct object_entry *e) +{ + struct packed_git *p; + struct pack_window *w_curs; + unsigned char *buf; + enum object_type type; + unsigned long used, avail, size; + + if (e->type_ != OBJ_OFS_DELTA && e->type_ != OBJ_REF_DELTA) { + read_lock(); + if (oid_object_info(the_repository, &e->idx.oid, &size) < 0) + die(_("unable to get size of %s"), + oid_to_hex(&e->idx.oid)); + read_unlock(); + return size; + } + + p = oe_in_pack(pack, e); + if (!p) + BUG("when e->type is a delta, it must belong to a pack"); + + read_lock(); + w_curs = NULL; + buf = use_pack(p, &w_curs, e->in_pack_offset, &avail); + used = unpack_object_header_buffer(buf, avail, &type, &size); + if (used == 0) + die(_("unable to parse object header of %s"), + oid_to_hex(&e->idx.oid)); + + unuse_pack(&w_curs); + read_unlock(); + return size; +} + static int try_delta(struct unpacked *trg, struct unpacked *src, unsigned max_depth, unsigned long *mem_usage) { @@ -1825,7 +1924,7 @@ static int try_delta(struct unpacked *trg, struct unpacked *src, void *delta_buf; /* Don't bother doing diffs between different types */ - if (trg_entry->type != src_entry->type) + if (oe_type(trg_entry) != oe_type(src_entry)) return -1; /* @@ -1836,8 +1935,8 @@ static int try_delta(struct unpacked *trg, struct unpacked *src, * it, we will still save the transfer cost, as we already know * the other side has it and we won't send src_entry at all. */ - if (reuse_delta && trg_entry->in_pack && - trg_entry->in_pack == src_entry->in_pack && + if (reuse_delta && IN_PACK(trg_entry) && + IN_PACK(trg_entry) == IN_PACK(src_entry) && !src_entry->preferred_base && trg_entry->in_pack_type != OBJ_REF_DELTA && trg_entry->in_pack_type != OBJ_OFS_DELTA) @@ -1848,19 +1947,19 @@ static int try_delta(struct unpacked *trg, struct unpacked *src, return 0; /* Now some size filtering heuristics. */ - trg_size = trg_entry->size; - if (!trg_entry->delta) { + trg_size = SIZE(trg_entry); + if (!DELTA(trg_entry)) { max_size = trg_size/2 - 20; ref_depth = 1; } else { - max_size = trg_entry->delta_size; + max_size = DELTA_SIZE(trg_entry); ref_depth = trg->depth; } max_size = (uint64_t)max_size * (max_depth - src->depth) / (max_depth - ref_depth + 1); if (max_size == 0) return 0; - src_size = src_entry->size; + src_size = SIZE(src_entry); sizediff = src_size < trg_size ? trg_size - src_size : 0; if (sizediff >= max_size) return 0; @@ -1922,10 +2021,14 @@ static int try_delta(struct unpacked *trg, struct unpacked *src, delta_buf = create_delta(src->index, trg->data, trg_size, &delta_size, max_size); if (!delta_buf) return 0; + if (delta_size >= (1U << OE_DELTA_SIZE_BITS)) { + free(delta_buf); + return 0; + } - if (trg_entry->delta) { + if (DELTA(trg_entry)) { /* Prefer only shallower same-sized deltas. */ - if (delta_size == trg_entry->delta_size && + if (delta_size == DELTA_SIZE(trg_entry) && src->depth + 1 >= trg->depth) { free(delta_buf); return 0; @@ -1940,7 +2043,7 @@ static int try_delta(struct unpacked *trg, struct unpacked *src, free(trg_entry->delta_data); cache_lock(); if (trg_entry->delta_data) { - delta_cache_size -= trg_entry->delta_size; + delta_cache_size -= DELTA_SIZE(trg_entry); trg_entry->delta_data = NULL; } if (delta_cacheable(src_size, trg_size, delta_size)) { @@ -1952,8 +2055,8 @@ static int try_delta(struct unpacked *trg, struct unpacked *src, free(delta_buf); } - trg_entry->delta = src_entry; - trg_entry->delta_size = delta_size; + SET_DELTA(trg_entry, src_entry); + SET_DELTA_SIZE(trg_entry, delta_size); trg->depth = src->depth + 1; return 1; @@ -1961,13 +2064,13 @@ static int try_delta(struct unpacked *trg, struct unpacked *src, static unsigned int check_delta_limit(struct object_entry *me, unsigned int n) { - struct object_entry *child = me->delta_child; + struct object_entry *child = DELTA_CHILD(me); unsigned int m = n; while (child) { unsigned int c = check_delta_limit(child, n + 1); if (m < c) m = c; - child = child->delta_sibling; + child = DELTA_SIBLING(child); } return m; } @@ -1978,7 +2081,7 @@ static unsigned long free_unpacked(struct unpacked *n) free_delta_index(n->index); n->index = NULL; if (n->data) { - freed_mem += n->entry->size; + freed_mem += SIZE(n->entry); FREE_AND_NULL(n->data); } n->entry = NULL; @@ -2036,7 +2139,7 @@ static void find_deltas(struct object_entry **list, unsigned *list_size, * otherwise they would become too deep. */ max_depth = depth; - if (entry->delta_child) { + if (DELTA_CHILD(entry)) { max_depth -= check_delta_limit(entry, 0); if (max_depth <= 0) goto next; @@ -2074,19 +2177,26 @@ static void find_deltas(struct object_entry **list, unsigned *list_size, * between writes at that moment. */ if (entry->delta_data && !pack_to_stdout) { - entry->z_delta_size = do_compress(&entry->delta_data, - entry->delta_size); - cache_lock(); - delta_cache_size -= entry->delta_size; - delta_cache_size += entry->z_delta_size; - cache_unlock(); + unsigned long size; + + size = do_compress(&entry->delta_data, DELTA_SIZE(entry)); + if (size < (1U << OE_Z_DELTA_BITS)) { + entry->z_delta_size = size; + cache_lock(); + delta_cache_size -= DELTA_SIZE(entry); + delta_cache_size += entry->z_delta_size; + cache_unlock(); + } else { + FREE_AND_NULL(entry->delta_data); + entry->z_delta_size = 0; + } } /* if we made n a delta, and if n is already at max * depth, leaving it in the window is pointless. we * should evict it first. */ - if (entry->delta && max_depth <= n->depth) + if (DELTA(entry) && max_depth <= n->depth) continue; /* @@ -2094,7 +2204,7 @@ static void find_deltas(struct object_entry **list, unsigned *list_size, * currently deltified object, to keep it longer. It will * be the first base object to be attempted next. */ - if (entry->delta) { + if (DELTA(entry)) { struct unpacked swap = array[best_base]; int dist = (window + idx - best_base) % window; int dst = best_base; @@ -2415,13 +2525,14 @@ static void prepare_pack(int window, int depth) for (i = 0; i < to_pack.nr_objects; i++) { struct object_entry *entry = to_pack.objects + i; - if (entry->delta) + if (DELTA(entry)) /* This happens if we decided to reuse existing * delta from a pack. "reuse_delta &&" is implied. */ continue; - if (entry->size < 50) + if (!entry->type_valid || + oe_size_less_than(&to_pack, entry, 50)) continue; if (entry->no_try_delta) @@ -2429,11 +2540,11 @@ static void prepare_pack(int window, int depth) if (!entry->preferred_base) { nr_deltas++; - if (entry->type < 0) + if (oe_type(entry) < 0) die("unable to get type of object %s", oid_to_hex(&entry->idx.oid)); } else { - if (entry->type < 0) { + if (oe_type(entry) < 0) { /* * This object is not found, but we * don't have to include it anyway. @@ -2542,7 +2653,7 @@ static void read_object_list_from_stdin(void) die("expected object ID, got garbage:\n %s", line); add_preferred_base_object(p + 1); - add_object_entry(&oid, 0, p + 1, 0); + add_object_entry(&oid, OBJ_NONE, p + 1, 0); } } @@ -2675,7 +2786,7 @@ static void add_objects_in_unpacked_packs(struct rev_info *revs) struct object_id oid; struct object *o; - if (!p->pack_local || p->pack_keep) + if (!p->pack_local || p->pack_keep || p->pack_keep_in_core) continue; if (open_pack_index(p)) die("cannot open pack index"); @@ -2706,7 +2817,7 @@ static void add_objects_in_unpacked_packs(struct rev_info *revs) static int add_loose_object(const struct object_id *oid, const char *path, void *data) { - enum object_type type = oid_object_info(oid, NULL); + enum object_type type = oid_object_info(the_repository, oid, NULL); if (type < 0) { warning("loose object at %s could not be examined", path); @@ -2738,7 +2849,8 @@ static int has_sha1_pack_kept_or_nonlocal(const struct object_id *oid) get_packed_git(the_repository); while (p) { - if ((!p->pack_local || p->pack_keep) && + if ((!p->pack_local || p->pack_keep || + p->pack_keep_in_core) && find_pack_entry_one(oid->hash, p)) { last_found = p; return 1; @@ -2781,7 +2893,7 @@ static void loosen_unused_packed_objects(struct rev_info *revs) struct object_id oid; for (p = get_packed_git(the_repository); p; p = p->next) { - if (!p->pack_local || p->pack_keep) + if (!p->pack_local || p->pack_keep || p->pack_keep_in_core) continue; if (open_pack_index(p)) @@ -2807,7 +2919,8 @@ static int pack_options_allow_reuse(void) { return pack_to_stdout && allow_ofs_delta && - !ignore_packed_keep && + !ignore_packed_keep_on_disk && + !ignore_packed_keep_in_core && (!local || !have_non_local_packs) && !incremental; } @@ -2916,6 +3029,32 @@ static void get_object_list(int ac, const char **av) oid_array_clear(&recent_objects); } +static void add_extra_kept_packs(const struct string_list *names) +{ + struct packed_git *p; + + if (!names->nr) + return; + + for (p = get_packed_git(the_repository); p; p = p->next) { + const char *name = basename(p->pack_name); + int i; + + if (!p->pack_local) + continue; + + for (i = 0; i < names->nr; i++) + if (!fspathcmp(name, names->items[i].string)) + break; + + if (i < names->nr) { + p->pack_keep_in_core = 1; + ignore_packed_keep_in_core = 1; + continue; + } + } +} + static int option_parse_index_version(const struct option *opt, const char *arg, int unset) { @@ -2955,6 +3094,7 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix) struct argv_array rp = ARGV_ARRAY_INIT; int rev_list_unpacked = 0, rev_list_all = 0, rev_list_reflog = 0; int rev_list_index = 0; + struct string_list keep_pack_list = STRING_LIST_INIT_NODUP; struct option pack_objects_options[] = { OPT_SET_INT('q', "quiet", &progress, N_("do not show progress meter"), 0), @@ -3019,8 +3159,10 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix) N_("create thin packs")), OPT_BOOL(0, "shallow", &shallow, N_("create packs suitable for shallow fetches")), - OPT_BOOL(0, "honor-pack-keep", &ignore_packed_keep, + OPT_BOOL(0, "honor-pack-keep", &ignore_packed_keep_on_disk, N_("ignore packs that have companion .keep file")), + OPT_STRING_LIST(0, "keep-pack", &keep_pack_list, N_("name"), + N_("ignore this pack")), OPT_INTEGER(0, "compression", &pack_compression_level, N_("pack compression level")), OPT_SET_INT(0, "keep-true-parents", &grafts_replace_parents, @@ -3038,6 +3180,9 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix) OPT_END(), }; + if (DFS_NUM_STATES > (1 << OE_DFS_STATE_BITS)) + BUG("too many dfs states, increase OE_DFS_STATE_BITS"); + check_replace_refs = 0; reset_pack_idx_option(&pack_idx_opts); @@ -3054,6 +3199,17 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix) if (pack_to_stdout != !base_name || argc) usage_with_options(pack_usage, pack_objects_options); + if (depth >= (1 << OE_DEPTH_BITS)) { + warning(_("delta chain depth %d is too deep, forcing %d"), + depth, (1 << OE_DEPTH_BITS) - 1); + depth = (1 << OE_DEPTH_BITS) - 1; + } + if (cache_max_small_delta_size >= (1U << OE_Z_DELTA_BITS)) { + warning(_("pack.deltaCacheLimit is too high, forcing %d"), + (1U << OE_Z_DELTA_BITS) - 1); + cache_max_small_delta_size = (1U << OE_Z_DELTA_BITS) - 1; + } + argv_array_push(&rp, "pack-objects"); if (thin) { use_internal_rev_list = 1; @@ -3148,19 +3304,20 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix) if (progress && all_progress_implied) progress = 2; - if (ignore_packed_keep) { + add_extra_kept_packs(&keep_pack_list); + if (ignore_packed_keep_on_disk) { struct packed_git *p; for (p = get_packed_git(the_repository); p; p = p->next) if (p->pack_local && p->pack_keep) break; if (!p) /* no keep-able packs found */ - ignore_packed_keep = 0; + ignore_packed_keep_on_disk = 0; } if (local) { /* - * unlike ignore_packed_keep above, we do not want to - * unset "local" based on looking at packs, as it - * also covers non-local objects + * unlike ignore_packed_keep_on_disk above, we do not + * want to unset "local" based on looking at packs, as + * it also covers non-local objects */ struct packed_git *p; for (p = get_packed_git(the_repository); p; p = p->next) { @@ -3171,8 +3328,10 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix) } } + prepare_packing_data(&to_pack); + if (progress) - progress_state = start_progress(_("Counting objects"), 0); + progress_state = start_progress(_("Enumerating objects"), 0); if (!use_internal_rev_list) read_object_list_from_stdin(); else { diff --git a/builtin/pack-refs.c b/builtin/pack-refs.c index b106a392a4..f3353564f9 100644 --- a/builtin/pack-refs.c +++ b/builtin/pack-refs.c @@ -1,6 +1,7 @@ #include "builtin.h" #include "parse-options.h" #include "refs.h" +#include "repository.h" static char const * const pack_refs_usage[] = { N_("git pack-refs [<options>]"), @@ -17,5 +18,5 @@ int cmd_pack_refs(int argc, const char **argv, const char *prefix) }; if (parse_options(argc, argv, prefix, opts, pack_refs_usage, 0)) usage_with_options(pack_refs_usage, opts); - return refs_pack_refs(get_main_ref_store(), flags); + return refs_pack_refs(get_main_ref_store(the_repository), flags); } diff --git a/builtin/prune.c b/builtin/prune.c index 38ced18dad..518ffbea13 100644 --- a/builtin/prune.c +++ b/builtin/prune.c @@ -50,7 +50,8 @@ static int prune_object(const struct object_id *oid, const char *fullpath, if (st.st_mtime > expire) return 0; if (show_only || verbose) { - enum object_type type = oid_object_info(oid, NULL); + enum object_type type = oid_object_info(the_repository, oid, + NULL); printf("%s %s\n", oid_to_hex(oid), (type > 0) ? type_name(type) : "unknown"); } diff --git a/builtin/push.c b/builtin/push.c index 013c20d616..ac3705370e 100644 --- a/builtin/push.c +++ b/builtin/push.c @@ -12,12 +12,40 @@ #include "submodule.h" #include "submodule-config.h" #include "send-pack.h" +#include "color.h" static const char * const push_usage[] = { N_("git push [<options>] [<repository> [<refspec>...]]"), NULL, }; +static int push_use_color = -1; +static char push_colors[][COLOR_MAXLEN] = { + GIT_COLOR_RESET, + GIT_COLOR_RED, /* ERROR */ +}; + +enum color_push { + PUSH_COLOR_RESET = 0, + PUSH_COLOR_ERROR = 1 +}; + +static int parse_push_color_slot(const char *slot) +{ + if (!strcasecmp(slot, "reset")) + return PUSH_COLOR_RESET; + if (!strcasecmp(slot, "error")) + return PUSH_COLOR_ERROR; + return -1; +} + +static const char *push_get_color(enum color_push ix) +{ + if (want_color_stderr(push_use_color)) + return push_colors[ix]; + return ""; +} + static int thin = 1; static int deleterefs; static const char *receivepack; @@ -337,8 +365,11 @@ static int push_with_options(struct transport *transport, int flags) fprintf(stderr, _("Pushing to %s\n"), transport->url); err = transport_push(transport, refspec_nr, refspec, flags, &reject_reasons); - if (err != 0) + if (err != 0) { + fprintf(stderr, "%s", push_get_color(PUSH_COLOR_ERROR)); error(_("failed to push some refs to '%s'"), transport->url); + fprintf(stderr, "%s", push_get_color(PUSH_COLOR_RESET)); + } err |= transport_disconnect(transport); if (!err) @@ -467,6 +498,7 @@ static void set_push_cert_flags(int *flags, int v) static int git_push_config(const char *k, const char *v, void *cb) { + const char *slot_name; int *flags = cb; int status; @@ -514,6 +546,16 @@ static int git_push_config(const char *k, const char *v, void *cb) else string_list_append(&push_options_config, v); return 0; + } else if (!strcmp(k, "color.push")) { + push_use_color = git_config_colorbool(k, v); + return 0; + } else if (skip_prefix(k, "color.push.", &slot_name)) { + int slot = parse_push_color_slot(slot_name); + if (slot < 0) + return 0; + if (!v) + return config_error_nonbool(k); + return color_parse(v, push_colors[slot]); } return git_default_config(k, v, NULL); diff --git a/builtin/receive-pack.c b/builtin/receive-pack.c index 4b68a28e92..0dd163280d 100644 --- a/builtin/receive-pack.c +++ b/builtin/receive-pack.c @@ -1965,6 +1965,12 @@ int cmd_receive_pack(int argc, const char **argv, const char *prefix) unpack_limit = receive_unpack_limit; switch (determine_protocol_version_server()) { + case protocol_v2: + /* + * push support for protocol v2 has not been implemented yet, + * so ignore the request to use v2 and fallback to using v0. + */ + break; case protocol_v1: /* * v1 is just the original protocol with a version string, diff --git a/builtin/reflog.c b/builtin/reflog.c index a89bd1dd25..a48984d37e 100644 --- a/builtin/reflog.c +++ b/builtin/reflog.c @@ -154,7 +154,7 @@ static int commit_is_complete(struct commit *commit) for (i = 0; i < found.nr; i++) { struct commit *c = (struct commit *)found.objects[i].item; - if (!tree_is_complete(&c->tree->object.oid)) { + if (!tree_is_complete(get_commit_tree_oid(c))) { is_incomplete = 1; c->object.flags |= INCOMPLETE; } diff --git a/builtin/remote.c b/builtin/remote.c index 45c9219e07..0bbf9f4c9e 100644 --- a/builtin/remote.c +++ b/builtin/remote.c @@ -866,7 +866,7 @@ static int get_remote_ref_states(const char *name, if (query) { transport = transport_get(states->remote, states->remote->url_nr > 0 ? states->remote->url[0] : NULL); - remote_refs = transport_get_remote_refs(transport); + remote_refs = transport_get_remote_refs(transport, NULL); transport_disconnect(transport); states->queried = 1; diff --git a/builtin/repack.c b/builtin/repack.c index 7bdb40142f..6c636e159e 100644 --- a/builtin/repack.c +++ b/builtin/repack.c @@ -86,7 +86,8 @@ static void remove_pack_on_signal(int signo) * have a corresponding .keep or .promisor file. These packs are not to * be kept if we are going to pack everything into one file. */ -static void get_non_kept_pack_filenames(struct string_list *fname_list) +static void get_non_kept_pack_filenames(struct string_list *fname_list, + const struct string_list *extra_keep) { DIR *dir; struct dirent *e; @@ -97,6 +98,14 @@ static void get_non_kept_pack_filenames(struct string_list *fname_list) while ((e = readdir(dir)) != NULL) { size_t len; + int i; + + for (i = 0; i < extra_keep->nr; i++) + if (!fspathcmp(e->d_name, extra_keep->items[i].string)) + break; + if (extra_keep->nr > 0 && i < extra_keep->nr) + continue; + if (!strip_suffix(e->d_name, ".pack", &len)) continue; @@ -148,7 +157,7 @@ int cmd_repack(int argc, const char **argv, const char *prefix) struct string_list rollback = STRING_LIST_INIT_NODUP; struct string_list existing_packs = STRING_LIST_INIT_DUP; struct strbuf line = STRBUF_INIT; - int ext, ret, failed; + int i, ext, ret, failed; FILE *out; /* variables to be filled by option parsing */ @@ -160,6 +169,7 @@ int cmd_repack(int argc, const char **argv, const char *prefix) const char *depth = NULL; const char *threads = NULL; const char *max_pack_size = NULL; + struct string_list keep_pack_list = STRING_LIST_INIT_NODUP; int no_reuse_delta = 0, no_reuse_object = 0; int no_update_server_info = 0; int quiet = 0; @@ -200,6 +210,8 @@ int cmd_repack(int argc, const char **argv, const char *prefix) N_("maximum size of each packfile")), OPT_BOOL(0, "pack-kept-objects", &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")), OPT_END() }; @@ -230,6 +242,9 @@ int cmd_repack(int argc, const char **argv, const char *prefix) argv_array_push(&cmd.args, "--keep-true-parents"); if (!pack_kept_objects) argv_array_push(&cmd.args, "--honor-pack-keep"); + for (i = 0; i < keep_pack_list.nr; i++) + argv_array_pushf(&cmd.args, "--keep-pack=%s", + keep_pack_list.items[i].string); argv_array_push(&cmd.args, "--non-empty"); argv_array_push(&cmd.args, "--all"); argv_array_push(&cmd.args, "--reflog"); @@ -254,7 +269,7 @@ int cmd_repack(int argc, const char **argv, const char *prefix) argv_array_push(&cmd.args, "--write-bitmap-index"); if (pack_everything & ALL_INTO_ONE) { - get_non_kept_pack_filenames(&existing_packs); + get_non_kept_pack_filenames(&existing_packs, &keep_pack_list); if (existing_packs.nr && delete_redundant) { if (unpack_unreachable) { diff --git a/builtin/replace.c b/builtin/replace.c index 935647be6b..6da2411e14 100644 --- a/builtin/replace.c +++ b/builtin/replace.c @@ -14,12 +14,15 @@ #include "refs.h" #include "parse-options.h" #include "run-command.h" +#include "object-store.h" +#include "repository.h" #include "tag.h" static const char * const git_replace_usage[] = { N_("git replace [-f] <object> <replacement>"), N_("git replace [-f] --edit <object>"), N_("git replace [-f] --graft <commit> [<parent>...]"), + N_("git replace [-f] --convert-graft-file"), N_("git replace -d <object>..."), N_("git replace [--format=<format>] [-l [<pattern>]]"), NULL @@ -53,8 +56,9 @@ static int show_reference(const char *refname, const struct object_id *oid, if (get_oid(refname, &object)) return error("Failed to resolve '%s' as a valid ref.", refname); - obj_type = oid_object_info(&object, NULL); - repl_type = oid_object_info(oid, NULL); + obj_type = oid_object_info(the_repository, &object, + NULL); + repl_type = oid_object_info(the_repository, oid, NULL); printf("%s (%s) -> %s (%s)\n", refname, type_name(obj_type), oid_to_hex(oid), type_name(repl_type)); @@ -79,11 +83,11 @@ static int list_replace_refs(const char *pattern, const char *format) else if (!strcmp(format, "long")) data.format = REPLACE_FORMAT_LONG; else - die("invalid replace format '%s'\n" - "valid formats are 'short', 'medium' and 'long'\n", - format); + return error("invalid replace format '%s'\n" + "valid formats are 'short', 'medium' and 'long'\n", + format); - for_each_replace_ref(show_reference, (void *)&data); + for_each_replace_ref(the_repository, show_reference, (void *)&data); return 0; } @@ -134,7 +138,7 @@ static int delete_replace_ref(const char *name, const char *ref, return 0; } -static void check_ref_valid(struct object_id *object, +static int check_ref_valid(struct object_id *object, struct object_id *prev, struct strbuf *ref, int force) @@ -142,12 +146,13 @@ static void check_ref_valid(struct object_id *object, strbuf_reset(ref); strbuf_addf(ref, "%s%s", git_replace_ref_base, oid_to_hex(object)); if (check_refname_format(ref->buf, 0)) - die("'%s' is not a valid ref name.", ref->buf); + return error("'%s' is not a valid ref name.", ref->buf); if (read_ref(ref->buf, prev)) oidclr(prev); else if (!force) - die("replace ref '%s' already exists", ref->buf); + return error("replace ref '%s' already exists", ref->buf); + return 0; } static int replace_object_oid(const char *object_ref, @@ -161,28 +166,33 @@ static int replace_object_oid(const char *object_ref, struct strbuf ref = STRBUF_INIT; struct ref_transaction *transaction; struct strbuf err = STRBUF_INIT; + int res = 0; - obj_type = oid_object_info(object, NULL); - repl_type = oid_object_info(repl, NULL); + obj_type = oid_object_info(the_repository, object, NULL); + repl_type = oid_object_info(the_repository, repl, NULL); if (!force && obj_type != repl_type) - die("Objects must be of the same type.\n" - "'%s' points to a replaced object of type '%s'\n" - "while '%s' points to a replacement object of type '%s'.", - object_ref, type_name(obj_type), - replace_ref, type_name(repl_type)); - - check_ref_valid(object, &prev, &ref, force); + return error("Objects must be of the same type.\n" + "'%s' points to a replaced object of type '%s'\n" + "while '%s' points to a replacement object of " + "type '%s'.", + object_ref, type_name(obj_type), + replace_ref, type_name(repl_type)); + + if (check_ref_valid(object, &prev, &ref, force)) { + strbuf_release(&ref); + return -1; + } transaction = ref_transaction_begin(&err); if (!transaction || ref_transaction_update(transaction, ref.buf, repl, &prev, 0, NULL, &err) || ref_transaction_commit(transaction, &err)) - die("%s", err.buf); + res = error("%s", err.buf); ref_transaction_free(transaction); strbuf_release(&ref); - return 0; + return res; } static int replace_object(const char *object_ref, const char *replace_ref, int force) @@ -190,9 +200,11 @@ static int replace_object(const char *object_ref, const char *replace_ref, int f struct object_id object, repl; if (get_oid(object_ref, &object)) - die("Failed to resolve '%s' as a valid ref.", object_ref); + return error("Failed to resolve '%s' as a valid ref.", + object_ref); if (get_oid(replace_ref, &repl)) - die("Failed to resolve '%s' as a valid ref.", replace_ref); + return error("Failed to resolve '%s' as a valid ref.", + replace_ref); return replace_object_oid(object_ref, &object, replace_ref, &repl, force); } @@ -202,7 +214,7 @@ static int replace_object(const char *object_ref, const char *replace_ref, int f * If "raw" is true, then the object's raw contents are printed according to * "type". Otherwise, we pretty-print the contents for human editing. */ -static void export_object(const struct object_id *oid, enum object_type type, +static int export_object(const struct object_id *oid, enum object_type type, int raw, const char *filename) { struct child_process cmd = CHILD_PROCESS_INIT; @@ -210,7 +222,7 @@ static void export_object(const struct object_id *oid, enum object_type type, fd = open(filename, O_WRONLY | O_CREAT | O_TRUNC, 0666); if (fd < 0) - die_errno("unable to open %s for writing", filename); + return error_errno("unable to open %s for writing", filename); argv_array_push(&cmd.args, "--no-replace-objects"); argv_array_push(&cmd.args, "cat-file"); @@ -223,7 +235,8 @@ static void export_object(const struct object_id *oid, enum object_type type, cmd.out = fd; if (run_command(&cmd)) - die("cat-file reported failure"); + return error("cat-file reported failure"); + return 0; } /* @@ -231,14 +244,14 @@ static void export_object(const struct object_id *oid, enum object_type type, * interpreting it as "type", and writing the result to the object database. * The sha1 of the written object is returned via sha1. */ -static void import_object(struct object_id *oid, enum object_type type, +static int import_object(struct object_id *oid, enum object_type type, int raw, const char *filename) { int fd; fd = open(filename, O_RDONLY); if (fd < 0) - die_errno("unable to open %s for reading", filename); + return error_errno("unable to open %s for reading", filename); if (!raw && type == OBJ_TREE) { const char *argv[] = { "mktree", NULL }; @@ -250,27 +263,40 @@ static void import_object(struct object_id *oid, enum object_type type, cmd.in = fd; cmd.out = -1; - if (start_command(&cmd)) - die("unable to spawn mktree"); + if (start_command(&cmd)) { + close(fd); + return error("unable to spawn mktree"); + } - if (strbuf_read(&result, cmd.out, 41) < 0) - die_errno("unable to read from mktree"); + if (strbuf_read(&result, cmd.out, 41) < 0) { + error_errno("unable to read from mktree"); + close(fd); + close(cmd.out); + return -1; + } close(cmd.out); - if (finish_command(&cmd)) - die("mktree reported failure"); - if (get_oid_hex(result.buf, oid) < 0) - die("mktree did not return an object name"); + if (finish_command(&cmd)) { + strbuf_release(&result); + return error("mktree reported failure"); + } + if (get_oid_hex(result.buf, oid) < 0) { + strbuf_release(&result); + return error("mktree did not return an object name"); + } strbuf_release(&result); } else { struct stat st; int flags = HASH_FORMAT_CHECK | HASH_WRITE_OBJECT; - if (fstat(fd, &st) < 0) - die_errno("unable to fstat %s", filename); + if (fstat(fd, &st) < 0) { + error_errno("unable to fstat %s", filename); + close(fd); + return -1; + } if (index_fd(oid, fd, &st, type, NULL, flags) < 0) - die("unable to write object to database"); + return error("unable to write object to database"); /* index_fd close()s fd for us */ } @@ -278,30 +304,43 @@ static void import_object(struct object_id *oid, enum object_type type, * No need to close(fd) here; both run-command and index-fd * will have done it for us. */ + return 0; } static int edit_and_replace(const char *object_ref, int force, int raw) { - char *tmpfile = git_pathdup("REPLACE_EDITOBJ"); + char *tmpfile; enum object_type type; struct object_id old_oid, new_oid, prev; struct strbuf ref = STRBUF_INIT; if (get_oid(object_ref, &old_oid) < 0) - die("Not a valid object name: '%s'", object_ref); + return error("Not a valid object name: '%s'", object_ref); - type = oid_object_info(&old_oid, NULL); + type = oid_object_info(the_repository, &old_oid, NULL); if (type < 0) - die("unable to get object type for %s", oid_to_hex(&old_oid)); + return error("unable to get object type for %s", + oid_to_hex(&old_oid)); - check_ref_valid(&old_oid, &prev, &ref, force); + if (check_ref_valid(&old_oid, &prev, &ref, force)) { + strbuf_release(&ref); + return -1; + } strbuf_release(&ref); - export_object(&old_oid, type, raw, tmpfile); - if (launch_editor(tmpfile, NULL, NULL) < 0) - die("editing object file failed"); - import_object(&new_oid, type, raw, tmpfile); - + tmpfile = git_pathdup("REPLACE_EDITOBJ"); + if (export_object(&old_oid, type, raw, tmpfile)) { + free(tmpfile); + return -1; + } + if (launch_editor(tmpfile, NULL, NULL) < 0) { + free(tmpfile); + return error("editing object file failed"); + } + if (import_object(&new_oid, type, raw, tmpfile)) { + free(tmpfile); + return -1; + } free(tmpfile); if (!oidcmp(&old_oid, &new_oid)) @@ -310,7 +349,7 @@ static int edit_and_replace(const char *object_ref, int force, int raw) return replace_object_oid(object_ref, &old_oid, "replacement", &new_oid, force); } -static void replace_parents(struct strbuf *buf, int argc, const char **argv) +static int replace_parents(struct strbuf *buf, int argc, const char **argv) { struct strbuf new_parents = STRBUF_INIT; const char *parent_start, *parent_end; @@ -327,9 +366,15 @@ static void replace_parents(struct strbuf *buf, int argc, const char **argv) /* prepare new parents */ for (i = 0; i < argc; i++) { struct object_id oid; - if (get_oid(argv[i], &oid) < 0) - die(_("Not a valid object name: '%s'"), argv[i]); - lookup_commit_or_die(&oid, argv[i]); + if (get_oid(argv[i], &oid) < 0) { + strbuf_release(&new_parents); + return error(_("Not a valid object name: '%s'"), + argv[i]); + } + if (!lookup_commit_reference(&oid)) { + strbuf_release(&new_parents); + return error(_("could not parse %s"), argv[i]); + } strbuf_addf(&new_parents, "parent %s\n", oid_to_hex(&oid)); } @@ -338,6 +383,7 @@ static void replace_parents(struct strbuf *buf, int argc, const char **argv) new_parents.buf, new_parents.len); strbuf_release(&new_parents); + return 0; } struct check_mergetag_data { @@ -345,7 +391,7 @@ struct check_mergetag_data { const char **argv; }; -static void check_one_mergetag(struct commit *commit, +static int check_one_mergetag(struct commit *commit, struct commit_extra_header *extra, void *data) { @@ -358,33 +404,35 @@ static void check_one_mergetag(struct commit *commit, hash_object_file(extra->value, extra->len, type_name(OBJ_TAG), &tag_oid); tag = lookup_tag(&tag_oid); if (!tag) - die(_("bad mergetag in commit '%s'"), ref); + return error(_("bad mergetag in commit '%s'"), ref); if (parse_tag_buffer(tag, extra->value, extra->len)) - die(_("malformed mergetag in commit '%s'"), ref); + return error(_("malformed mergetag in commit '%s'"), ref); /* iterate over new parents */ for (i = 1; i < mergetag_data->argc; i++) { struct object_id oid; if (get_oid(mergetag_data->argv[i], &oid) < 0) - die(_("Not a valid object name: '%s'"), mergetag_data->argv[i]); + return error(_("Not a valid object name: '%s'"), + mergetag_data->argv[i]); if (!oidcmp(&tag->tagged->oid, &oid)) - return; /* found */ + return 0; /* found */ } - die(_("original commit '%s' contains mergetag '%s' that is discarded; " - "use --edit instead of --graft"), ref, oid_to_hex(&tag_oid)); + return error(_("original commit '%s' contains mergetag '%s' that is " + "discarded; use --edit instead of --graft"), ref, + oid_to_hex(&tag_oid)); } -static void check_mergetags(struct commit *commit, int argc, const char **argv) +static int check_mergetags(struct commit *commit, int argc, const char **argv) { struct check_mergetag_data mergetag_data; mergetag_data.argc = argc; mergetag_data.argv = argv; - for_each_mergetag(check_one_mergetag, commit, &mergetag_data); + return for_each_mergetag(check_one_mergetag, commit, &mergetag_data); } -static int create_graft(int argc, const char **argv, int force) +static int create_graft(int argc, const char **argv, int force, int gentle) { struct object_id old_oid, new_oid; const char *old_ref = argv[0]; @@ -394,33 +442,81 @@ static int create_graft(int argc, const char **argv, int force) unsigned long size; if (get_oid(old_ref, &old_oid) < 0) - die(_("Not a valid object name: '%s'"), old_ref); - commit = lookup_commit_or_die(&old_oid, old_ref); + return error(_("Not a valid object name: '%s'"), old_ref); + commit = lookup_commit_reference(&old_oid); + if (!commit) + return error(_("could not parse %s"), old_ref); buffer = get_commit_buffer(commit, &size); strbuf_add(&buf, buffer, size); unuse_commit_buffer(commit, buffer); - replace_parents(&buf, argc - 1, &argv[1]); + if (replace_parents(&buf, argc - 1, &argv[1]) < 0) { + strbuf_release(&buf); + return -1; + } if (remove_signature(&buf)) { warning(_("the original commit '%s' has a gpg signature."), old_ref); warning(_("the signature will be removed in the replacement commit!")); } - check_mergetags(commit, argc, argv); + if (check_mergetags(commit, argc, argv)) { + strbuf_release(&buf); + return -1; + } - if (write_object_file(buf.buf, buf.len, commit_type, &new_oid)) - die(_("could not write replacement commit for: '%s'"), old_ref); + if (write_object_file(buf.buf, buf.len, commit_type, &new_oid)) { + strbuf_release(&buf); + return error(_("could not write replacement commit for: '%s'"), + old_ref); + } strbuf_release(&buf); - if (!oidcmp(&old_oid, &new_oid)) + if (!oidcmp(&old_oid, &new_oid)) { + if (gentle) { + warning("graft for '%s' unnecessary", oid_to_hex(&old_oid)); + return 0; + } return error("new commit is the same as the old one: '%s'", oid_to_hex(&old_oid)); + } return replace_object_oid(old_ref, &old_oid, "replacement", &new_oid, force); } +static int convert_graft_file(int force) +{ + const char *graft_file = get_graft_file(); + FILE *fp = fopen_or_warn(graft_file, "r"); + struct strbuf buf = STRBUF_INIT, err = STRBUF_INIT; + struct argv_array args = ARGV_ARRAY_INIT; + + if (!fp) + return -1; + + while (strbuf_getline(&buf, fp) != EOF) { + if (*buf.buf == '#') + continue; + + argv_array_split(&args, buf.buf); + if (args.argc && create_graft(args.argc, args.argv, force, 1)) + strbuf_addf(&err, "\n\t%s", buf.buf); + argv_array_clear(&args); + } + fclose(fp); + + strbuf_release(&buf); + + if (!err.len) + return unlink_or_warn(graft_file); + + warning(_("could not convert the following graft(s):\n%s"), err.buf); + strbuf_release(&err); + + return -1; +} + int cmd_replace(int argc, const char **argv, const char *prefix) { int force = 0; @@ -432,6 +528,7 @@ int cmd_replace(int argc, const char **argv, const char *prefix) MODE_DELETE, MODE_EDIT, MODE_GRAFT, + MODE_CONVERT_GRAFT_FILE, MODE_REPLACE } cmdmode = MODE_UNSPECIFIED; struct option options[] = { @@ -439,6 +536,7 @@ int cmd_replace(int argc, const char **argv, const char *prefix) OPT_CMDMODE('d', "delete", &cmdmode, N_("delete replace refs"), MODE_DELETE), OPT_CMDMODE('e', "edit", &cmdmode, N_("edit existing object"), MODE_EDIT), OPT_CMDMODE('g', "graft", &cmdmode, N_("change a commit's parents"), MODE_GRAFT), + OPT_CMDMODE(0, "convert-graft-file", &cmdmode, N_("convert existing graft file"), MODE_CONVERT_GRAFT_FILE), OPT_BOOL_F('f', "force", &force, N_("replace the ref if it exists"), PARSE_OPT_NOCOMPLETE), OPT_BOOL(0, "raw", &raw, N_("do not pretty-print contents for --edit")), @@ -461,7 +559,8 @@ int cmd_replace(int argc, const char **argv, const char *prefix) if (force && cmdmode != MODE_REPLACE && cmdmode != MODE_EDIT && - cmdmode != MODE_GRAFT) + cmdmode != MODE_GRAFT && + cmdmode != MODE_CONVERT_GRAFT_FILE) usage_msg_opt("-f only makes sense when writing a replacement", git_replace_usage, options); @@ -492,7 +591,13 @@ int cmd_replace(int argc, const char **argv, const char *prefix) if (argc < 1) usage_msg_opt("-g needs at least one argument", git_replace_usage, options); - return create_graft(argc, argv, force); + return create_graft(argc, argv, force, 0); + + case MODE_CONVERT_GRAFT_FILE: + if (argc != 0) + usage_msg_opt("--convert-graft-file takes no argument", + git_replace_usage, options); + return !!convert_graft_file(force); case MODE_LIST: if (argc > 1) @@ -501,6 +606,6 @@ int cmd_replace(int argc, const char **argv, const char *prefix) return list_replace_refs(argv[0], format); default: - die("BUG: invalid cmdmode %d", (int)cmdmode); + BUG("invalid cmdmode %d", (int)cmdmode); } } diff --git a/builtin/send-pack.c b/builtin/send-pack.c index fc4f0bb5fb..b5427f75e3 100644 --- a/builtin/send-pack.c +++ b/builtin/send-pack.c @@ -14,6 +14,7 @@ #include "sha1-array.h" #include "gpg-interface.h" #include "gettext.h" +#include "protocol.h" static const char * const send_pack_usage[] = { N_("git send-pack [--all | --mirror] [--dry-run] [--force] " @@ -154,6 +155,7 @@ int cmd_send_pack(int argc, const char **argv, const char *prefix) int progress = -1; int from_stdin = 0; struct push_cas_option cas = {0}; + struct packet_reader reader; struct option options[] = { OPT__VERBOSITY(&verbose), @@ -256,8 +258,22 @@ int cmd_send_pack(int argc, const char **argv, const char *prefix) args.verbose ? CONNECT_VERBOSE : 0); } - get_remote_heads(fd[0], NULL, 0, &remote_refs, REF_NORMAL, - &extra_have, &shallow); + packet_reader_init(&reader, fd[0], NULL, 0, + PACKET_READ_CHOMP_NEWLINE | + PACKET_READ_GENTLE_ON_EOF); + + switch (discover_version(&reader)) { + case protocol_v2: + die("support for protocol v2 not implemented yet"); + break; + case protocol_v1: + case protocol_v0: + get_remote_heads(&reader, &remote_refs, REF_NORMAL, + &extra_have, &shallow); + break; + case protocol_unknown_version: + BUG("unknown protocol version"); + } transport_verify_remote_names(nr_refspecs, refspecs); diff --git a/builtin/serve.c b/builtin/serve.c new file mode 100644 index 0000000000..d3fd240bb3 --- /dev/null +++ b/builtin/serve.c @@ -0,0 +1,30 @@ +#include "cache.h" +#include "builtin.h" +#include "parse-options.h" +#include "serve.h" + +static char const * const serve_usage[] = { + N_("git serve [<options>]"), + NULL +}; + +int cmd_serve(int argc, const char **argv, const char *prefix) +{ + struct serve_options opts = SERVE_OPTIONS_INIT; + + struct option options[] = { + OPT_BOOL(0, "stateless-rpc", &opts.stateless_rpc, + N_("quit after a single request/response exchange")), + OPT_BOOL(0, "advertise-capabilities", &opts.advertise_capabilities, + N_("exit immediately after advertising capabilities")), + OPT_END() + }; + + /* ignore all unknown cmdline switches for now */ + argc = parse_options(argc, argv, prefix, options, serve_usage, + PARSE_OPT_KEEP_DASHDASH | + PARSE_OPT_KEEP_UNKNOWN); + serve(&opts); + + return 0; +} diff --git a/builtin/submodule--helper.c b/builtin/submodule--helper.c index a404df3ea4..c2403a915f 100644 --- a/builtin/submodule--helper.c +++ b/builtin/submodule--helper.c @@ -455,7 +455,7 @@ static void init_submodule(const char *path, const char *prefix, displaypath = get_submodule_displaypath(path, prefix); - sub = submodule_from_path(&null_oid, path); + sub = submodule_from_path(the_repository, &null_oid, path); if (!sub) die(_("No url found for submodule path '%s' in .gitmodules"), @@ -596,8 +596,12 @@ static void print_status(unsigned int flags, char state, const char *path, printf("%c%s %s", state, oid_to_hex(oid), displaypath); - if (state == ' ' || state == '+') - printf(" (%s)", compute_rev_name(path, oid_to_hex(oid))); + if (state == ' ' || state == '+') { + const char *name = compute_rev_name(path, oid_to_hex(oid)); + + if (name) + printf(" (%s)", name); + } printf("\n"); } @@ -622,7 +626,7 @@ static void status_submodule(const char *path, const struct object_id *ce_oid, struct rev_info rev; int diff_files_result; - if (!submodule_from_path(&null_oid, path)) + if (!submodule_from_path(the_repository, &null_oid, path)) die(_("no submodule mapping found in .gitmodules for path '%s'"), path); @@ -746,7 +750,7 @@ static int module_name(int argc, const char **argv, const char *prefix) if (argc != 2) usage(_("git submodule--helper name <path>")); - sub = submodule_from_path(&null_oid, argv[1]); + sub = submodule_from_path(the_repository, &null_oid, argv[1]); if (!sub) die(_("no submodule mapping found in .gitmodules for path '%s'"), @@ -777,7 +781,7 @@ static void sync_submodule(const char *path, const char *prefix, if (!is_submodule_active(the_repository, path)) return; - sub = submodule_from_path(&null_oid, path); + sub = submodule_from_path(the_repository, &null_oid, path); if (sub && sub->url) { if (starts_with_dot_dot_slash(sub->url) || @@ -930,7 +934,7 @@ static void deinit_submodule(const char *path, const char *prefix, struct strbuf sb_config = STRBUF_INIT; char *sub_git_dir = xstrfmt("%s/.git", path); - sub = submodule_from_path(&null_oid, path); + sub = submodule_from_path(the_repository, &null_oid, path); if (!sub || !sub->name) goto cleanup; @@ -1264,8 +1268,7 @@ static int module_clone(int argc, const char **argv, const char *prefix) strbuf_reset(&sb); } - /* Connect module worktree and git dir */ - connect_work_tree_and_git_dir(path, sm_gitdir); + connect_work_tree_and_git_dir(path, sm_gitdir, 0); p = git_pathdup_submodule(path, "config"); if (!p) @@ -1372,7 +1375,7 @@ static int prepare_to_clone_next_submodule(const struct cache_entry *ce, goto cleanup; } - sub = submodule_from_path(&null_oid, ce->name); + sub = submodule_from_path(the_repository, &null_oid, ce->name); if (suc->recursive_prefix) displaypath = relative_path(suc->recursive_prefix, @@ -1655,7 +1658,7 @@ static const char *remote_submodule_branch(const char *path) const char *branch = NULL; char *key; - sub = submodule_from_path(&null_oid, path); + sub = submodule_from_path(the_repository, &null_oid, path); if (!sub) return NULL; diff --git a/builtin/tag.c b/builtin/tag.c index 46a5c6a1da..5d0dd11240 100644 --- a/builtin/tag.c +++ b/builtin/tag.c @@ -212,7 +212,7 @@ static void create_tag(const struct object_id *object, const char *tag, struct strbuf header = STRBUF_INIT; char *path = NULL; - type = oid_object_info(object, NULL); + type = oid_object_info(the_repository, object, NULL); if (type <= OBJ_NONE) die(_("bad object type.")); @@ -298,7 +298,7 @@ static void create_reflog_msg(const struct object_id *oid, struct strbuf *sb) } strbuf_addstr(sb, " ("); - type = oid_object_info(oid, NULL); + type = oid_object_info(the_repository, oid, NULL); switch (type) { default: strbuf_addstr(sb, "object of unknown type"); diff --git a/builtin/unpack-objects.c b/builtin/unpack-objects.c index b7755c6cc5..cfe9019f80 100644 --- a/builtin/unpack-objects.c +++ b/builtin/unpack-objects.c @@ -199,7 +199,7 @@ static int check_object(struct object *obj, int type, void *data, struct fsck_op if (!(obj->flags & FLAG_OPEN)) { unsigned long size; - int type = oid_object_info(&obj->oid, &size); + int type = oid_object_info(the_repository, &obj->oid, &size); if (type != obj->type || type <= 0) die("object of unexpected type"); obj->flags |= FLAG_WRITTEN; diff --git a/builtin/upload-pack.c b/builtin/upload-pack.c new file mode 100644 index 0000000000..decde5a3b1 --- /dev/null +++ b/builtin/upload-pack.c @@ -0,0 +1,74 @@ +#include "cache.h" +#include "builtin.h" +#include "exec-cmd.h" +#include "pkt-line.h" +#include "parse-options.h" +#include "protocol.h" +#include "upload-pack.h" +#include "serve.h" + +static const char * const upload_pack_usage[] = { + N_("git upload-pack [<options>] <dir>"), + NULL +}; + +int cmd_upload_pack(int argc, const char **argv, const char *prefix) +{ + const char *dir; + int strict = 0; + struct upload_pack_options opts = { 0 }; + struct serve_options serve_opts = SERVE_OPTIONS_INIT; + struct option options[] = { + OPT_BOOL(0, "stateless-rpc", &opts.stateless_rpc, + N_("quit after a single request/response exchange")), + OPT_BOOL(0, "advertise-refs", &opts.advertise_refs, + N_("exit immediately after initial ref advertisement")), + OPT_BOOL(0, "strict", &strict, + N_("do not try <directory>/.git/ if <directory> is no Git directory")), + OPT_INTEGER(0, "timeout", &opts.timeout, + N_("interrupt transfer after <n> seconds of inactivity")), + OPT_END() + }; + + packet_trace_identity("upload-pack"); + check_replace_refs = 0; + + argc = parse_options(argc, argv, NULL, options, upload_pack_usage, 0); + + if (argc != 1) + usage_with_options(upload_pack_usage, options); + + if (opts.timeout) + opts.daemon_mode = 1; + + setup_path(); + + dir = argv[0]; + + if (!enter_repo(dir, strict)) + die("'%s' does not appear to be a git repository", dir); + + switch (determine_protocol_version_server()) { + case protocol_v2: + serve_opts.advertise_capabilities = opts.advertise_refs; + serve_opts.stateless_rpc = opts.stateless_rpc; + serve(&serve_opts); + break; + case protocol_v1: + /* + * v1 is just the original protocol with a version string, + * so just fall through after writing the version string. + */ + if (opts.advertise_refs || !opts.stateless_rpc) + packet_write_fmt(1, "version 1\n"); + + /* fallthrough */ + case protocol_v0: + upload_pack(&opts); + break; + case protocol_unknown_version: + BUG("unknown protocol version"); + } + + return 0; +} diff --git a/builtin/worktree.c b/builtin/worktree.c index 40a438ed6c..5c7d2bb180 100644 --- a/builtin/worktree.c +++ b/builtin/worktree.c @@ -29,8 +29,6 @@ struct add_opts { int detach; int checkout; int keep_locked; - const char *new_branch; - int force_new_branch; }; static int show_only; @@ -298,8 +296,6 @@ static int add_worktree(const char *path, const char *refname, strbuf_addf(&sb, "%s/commondir", sb_repo.buf); write_file(sb.buf, "../.."); - fprintf_ln(stderr, _("Preparing %s (identifier %s)"), path, name); - argv_array_pushf(&child_env, "%s=%s", GIT_DIR_ENVIRONMENT, sb_git.buf); argv_array_pushf(&child_env, "%s=%s", GIT_WORK_TREE_ENVIRONMENT, path); cp.git_cmd = 1; @@ -366,18 +362,75 @@ done: return ret; } +static void print_preparing_worktree_line(int detach, + const char *branch, + const char *new_branch, + int force_new_branch) +{ + if (force_new_branch) { + struct commit *commit = lookup_commit_reference_by_name(new_branch); + if (!commit) + printf_ln(_("Preparing worktree (new branch '%s')"), new_branch); + else + printf_ln(_("Preparing worktree (resetting branch '%s'; was at %s)"), + new_branch, + find_unique_abbrev(&commit->object.oid, DEFAULT_ABBREV)); + } else if (new_branch) { + printf_ln(_("Preparing worktree (new branch '%s')"), new_branch); + } else { + struct strbuf s = STRBUF_INIT; + if (!detach && !strbuf_check_branch_ref(&s, branch) && + ref_exists(s.buf)) + printf_ln(_("Preparing worktree (checking out '%s')"), + branch); + else { + struct commit *commit = lookup_commit_reference_by_name(branch); + if (!commit) + die(_("invalid reference: %s"), branch); + printf_ln(_("Preparing worktree (detached HEAD %s)"), + find_unique_abbrev(&commit->object.oid, DEFAULT_ABBREV)); + } + strbuf_release(&s); + } +} + +static const char *dwim_branch(const char *path, const char **new_branch) +{ + int n; + const char *s = worktree_basename(path, &n); + const char *branchname = xstrndup(s, n); + struct strbuf ref = STRBUF_INIT; + + UNLEAK(branchname); + if (!strbuf_check_branch_ref(&ref, branchname) && + ref_exists(ref.buf)) { + strbuf_release(&ref); + return branchname; + } + + *new_branch = branchname; + if (guess_remote) { + struct object_id oid; + const char *remote = + unique_tracking_name(*new_branch, &oid); + return remote; + } + return NULL; +} + static int add(int ac, const char **av, const char *prefix) { struct add_opts opts; const char *new_branch_force = NULL; char *path; const char *branch; + const char *new_branch = NULL; const char *opt_track = NULL; struct option options[] = { OPT__FORCE(&opts.force, N_("checkout <branch> even if already checked out in other worktree"), PARSE_OPT_NOCOMPLETE), - OPT_STRING('b', NULL, &opts.new_branch, N_("branch"), + OPT_STRING('b', NULL, &new_branch, N_("branch"), N_("create a new branch")), OPT_STRING('B', NULL, &new_branch_force, N_("branch"), N_("create or reset a branch")), @@ -395,7 +448,7 @@ static int add(int ac, const char **av, const char *prefix) memset(&opts, 0, sizeof(opts)); opts.checkout = 1; ac = parse_options(ac, av, prefix, options, worktree_usage, 0); - if (!!opts.detach + !!opts.new_branch + !!new_branch_force > 1) + if (!!opts.detach + !!new_branch + !!new_branch_force > 1) die(_("-b, -B, and --detach are mutually exclusive")); if (ac < 1 || ac > 2) usage_with_options(worktree_usage, options); @@ -406,33 +459,25 @@ static int add(int ac, const char **av, const char *prefix) if (!strcmp(branch, "-")) branch = "@{-1}"; - opts.force_new_branch = !!new_branch_force; - if (opts.force_new_branch) { + if (new_branch_force) { struct strbuf symref = STRBUF_INIT; - opts.new_branch = new_branch_force; + new_branch = new_branch_force; if (!opts.force && - !strbuf_check_branch_ref(&symref, opts.new_branch) && + !strbuf_check_branch_ref(&symref, new_branch) && ref_exists(symref.buf)) die_if_checked_out(symref.buf, 0); strbuf_release(&symref); } - if (ac < 2 && !opts.new_branch && !opts.detach) { - int n; - const char *s = worktree_basename(path, &n); - opts.new_branch = xstrndup(s, n); - if (guess_remote) { - struct object_id oid; - const char *remote = - unique_tracking_name(opts.new_branch, &oid); - if (remote) - branch = remote; - } + if (ac < 2 && !new_branch && !opts.detach) { + const char *s = dwim_branch(path, &new_branch); + if (s) + branch = s; } - if (ac == 2 && !opts.new_branch && !opts.detach) { + if (ac == 2 && !new_branch && !opts.detach) { struct object_id oid; struct commit *commit; const char *remote; @@ -441,25 +486,27 @@ static int add(int ac, const char **av, const char *prefix) if (!commit) { remote = unique_tracking_name(branch, &oid); if (remote) { - opts.new_branch = branch; + new_branch = branch; branch = remote; } } } - if (opts.new_branch) { + print_preparing_worktree_line(opts.detach, branch, new_branch, !!new_branch_force); + + if (new_branch) { struct child_process cp = CHILD_PROCESS_INIT; cp.git_cmd = 1; argv_array_push(&cp.args, "branch"); - if (opts.force_new_branch) + if (new_branch_force) argv_array_push(&cp.args, "--force"); - argv_array_push(&cp.args, opts.new_branch); + argv_array_push(&cp.args, new_branch); argv_array_push(&cp.args, branch); if (opt_track) argv_array_push(&cp.args, opt_track); if (run_command(&cp)) return -1; - branch = opts.new_branch; + branch = new_branch; } else if (opt_track) { die(_("--[no-]track can only be used if a new branch is created")); } @@ -783,8 +830,9 @@ static int remove_worktree(int ac, const char **av, const char *prefix) { int force = 0; struct option options[] = { - OPT_BOOL(0, "force", &force, - N_("force removing even if the worktree is dirty")), + OPT__FORCE(&force, + N_("force removing even if the worktree is dirty"), + PARSE_OPT_NOCOMPLETE), OPT_END() }; struct worktree **worktrees, *wt; diff --git a/bulk-checkin.c b/bulk-checkin.c index de1f4040c7..c0bc8de107 100644 --- a/bulk-checkin.c +++ b/bulk-checkin.c @@ -36,9 +36,9 @@ static void finish_bulk_checkin(struct bulk_checkin_state *state) unlink(state->pack_tmp_name); goto clear_exit; } else if (state->nr_written == 1) { - hashclose(state->f, oid.hash, CSUM_FSYNC); + finalize_hashfile(state->f, oid.hash, CSUM_HASH_IN_STREAM | CSUM_FSYNC | CSUM_CLOSE); } else { - int fd = hashclose(state->f, oid.hash, 0); + int fd = finalize_hashfile(state->f, oid.hash, 0); fixup_pack_header_footer(fd, oid.hash, state->pack_tmp_name, state->nr_written, oid.hash, state->offset); @@ -373,6 +373,13 @@ extern void free_name_hash(struct index_state *istate); #define read_blob_data_from_cache(path, sz) read_blob_data_from_index(&the_index, (path), (sz)) #endif +#define TYPE_BITS 3 + +/* + * Values in this enum (except those outside the 3 bit range) are part + * of pack file format. See Documentation/technical/pack-format.txt + * for more information. + */ enum object_type { OBJ_BAD = -1, OBJ_NONE = 0, @@ -428,6 +435,7 @@ static inline enum object_type object_type(unsigned int mode) #define GIT_ICASE_PATHSPECS_ENVIRONMENT "GIT_ICASE_PATHSPECS" #define GIT_QUARANTINE_ENVIRONMENT "GIT_QUARANTINE_PATH" #define GIT_OPTIONAL_LOCKS_ENVIRONMENT "GIT_OPTIONAL_LOCKS" +#define GIT_TEXT_DOMAIN_DIR_ENVIRONMENT "GIT_TEXTDOMAINDIR" /* * Environment variable used in handshaking the wire protocol. @@ -805,6 +813,7 @@ extern char *git_replace_ref_base; extern int fsync_object_files; extern int core_preload_index; +extern int core_commit_graph; extern int core_apply_sparse_checkout; extern int precomposed_unicode; extern int protect_hfs; @@ -1191,27 +1200,8 @@ static inline void *read_object_file(const struct object_id *oid, enum object_ty return read_object_file_extended(oid, type, size, 1); } -/* - * This internal function is only declared here for the benefit of - * lookup_replace_object(). Please do not call it directly. - */ -extern const struct object_id *do_lookup_replace_object(const struct object_id *oid); - -/* - * If object sha1 should be replaced, return the replacement object's - * name (replaced recursively, if necessary). The return value is - * either sha1 or a pointer to a permanently-allocated value. When - * object replacement is suppressed, always return sha1. - */ -static inline const struct object_id *lookup_replace_object(const struct object_id *oid) -{ - if (!check_replace_refs) - return oid; - return do_lookup_replace_object(oid); -} - /* Read and unpack an object file into memory, write memory to an object file */ -extern int oid_object_info(const struct object_id *, unsigned long *); +int oid_object_info(struct repository *r, const struct object_id *, unsigned long *); extern int hash_object_file(const void *buf, unsigned long len, const char *type, struct object_id *oid); @@ -1692,7 +1682,10 @@ struct object_info { #define OBJECT_INFO_QUICK 8 /* Do not check loose object */ #define OBJECT_INFO_IGNORE_LOOSE 16 -extern int oid_object_info_extended(const struct object_id *, struct object_info *, unsigned flags); + +int oid_object_info_extended(struct repository *r, + const struct object_id *, + struct object_info *, unsigned flags); /* * Set this to 0 to prevent sha1_object_info_extended() from fetching missing diff --git a/ci/run-build-and-tests.sh b/ci/run-build-and-tests.sh index 3735ce413f..4b04c75b7f 100755 --- a/ci/run-build-and-tests.sh +++ b/ci/run-build-and-tests.sh @@ -11,7 +11,10 @@ make --jobs=2 make --quiet test if test "$jobname" = "linux-gcc" then - GIT_TEST_SPLIT_INDEX=YesPlease make --quiet test + export GIT_TEST_SPLIT_INDEX=yes + export GIT_TEST_FULL_IN_PACK_ARRAY=true + export GIT_TEST_OE_SIZE=10 + make --quiet test fi check_unignored_build_artifacts @@ -319,18 +319,20 @@ int git_config_colorbool(const char *var, const char *value) return GIT_COLOR_AUTO; } -static int check_auto_color(void) +static int check_auto_color(int fd) { - if (color_stdout_is_tty < 0) - color_stdout_is_tty = isatty(1); - if (color_stdout_is_tty || (pager_in_use() && pager_use_color)) { + static int color_stderr_is_tty = -1; + int *is_tty_p = fd == 1 ? &color_stdout_is_tty : &color_stderr_is_tty; + if (*is_tty_p < 0) + *is_tty_p = isatty(fd); + if (*is_tty_p || (fd == 1 && pager_in_use() && pager_use_color)) { if (!is_terminal_dumb()) return 1; } return 0; } -int want_color(int var) +int want_color_fd(int fd, int var) { /* * NEEDSWORK: This function is sometimes used from multiple threads, and @@ -339,15 +341,15 @@ int want_color(int var) * is listed in .tsan-suppressions for the time being. */ - static int want_auto = -1; + static int want_auto[3] = { -1, -1, -1 }; if (var < 0) var = git_use_color_default; if (var == GIT_COLOR_AUTO) { - if (want_auto < 0) - want_auto = check_auto_color(); - return want_auto; + if (want_auto[fd] < 0) + want_auto[fd] = check_auto_color(fd); + return want_auto[fd]; } return var; } @@ -88,7 +88,9 @@ int git_config_colorbool(const char *var, const char *value); * Return a boolean whether to use color, where the argument 'var' is * one of GIT_COLOR_UNKNOWN, GIT_COLOR_NEVER, GIT_COLOR_ALWAYS, GIT_COLOR_AUTO. */ -int want_color(int var); +int want_color_fd(int fd, int var); +#define want_color(colorbool) want_color_fd(1, (colorbool)) +#define want_color_stderr(colorbool) want_color_fd(2, (colorbool)) /* * Translate a Git color from 'value' into a string that the terminal can diff --git a/command-list.txt b/command-list.txt index a1fad28fd8..835c5890be 100644 --- a/command-list.txt +++ b/command-list.txt @@ -34,6 +34,7 @@ git-clean mainporcelain git-clone mainporcelain init git-column purehelpers git-commit mainporcelain history +git-commit-graph plumbingmanipulators git-commit-tree plumbingmanipulators git-config ancillarymanipulators git-count-objects ancillaryinterrogators diff --git a/commit-graph.c b/commit-graph.c new file mode 100644 index 0000000000..4c6127088f --- /dev/null +++ b/commit-graph.c @@ -0,0 +1,761 @@ +#include "cache.h" +#include "config.h" +#include "git-compat-util.h" +#include "lockfile.h" +#include "pack.h" +#include "packfile.h" +#include "commit.h" +#include "object.h" +#include "revision.h" +#include "sha1-lookup.h" +#include "commit-graph.h" +#include "object-store.h" + +#define GRAPH_SIGNATURE 0x43475048 /* "CGPH" */ +#define GRAPH_CHUNKID_OIDFANOUT 0x4f494446 /* "OIDF" */ +#define GRAPH_CHUNKID_OIDLOOKUP 0x4f49444c /* "OIDL" */ +#define GRAPH_CHUNKID_DATA 0x43444154 /* "CDAT" */ +#define GRAPH_CHUNKID_LARGEEDGES 0x45444745 /* "EDGE" */ + +#define GRAPH_DATA_WIDTH 36 + +#define GRAPH_VERSION_1 0x1 +#define GRAPH_VERSION GRAPH_VERSION_1 + +#define GRAPH_OID_VERSION_SHA1 1 +#define GRAPH_OID_LEN_SHA1 GIT_SHA1_RAWSZ +#define GRAPH_OID_VERSION GRAPH_OID_VERSION_SHA1 +#define GRAPH_OID_LEN GRAPH_OID_LEN_SHA1 + +#define GRAPH_OCTOPUS_EDGES_NEEDED 0x80000000 +#define GRAPH_PARENT_MISSING 0x7fffffff +#define GRAPH_EDGE_LAST_MASK 0x7fffffff +#define GRAPH_PARENT_NONE 0x70000000 + +#define GRAPH_LAST_EDGE 0x80000000 + +#define GRAPH_FANOUT_SIZE (4 * 256) +#define GRAPH_CHUNKLOOKUP_WIDTH 12 +#define GRAPH_MIN_SIZE (5 * GRAPH_CHUNKLOOKUP_WIDTH + GRAPH_FANOUT_SIZE + \ + GRAPH_OID_LEN + 8) + +char *get_commit_graph_filename(const char *obj_dir) +{ + return xstrfmt("%s/info/commit-graph", obj_dir); +} + +static struct commit_graph *alloc_commit_graph(void) +{ + struct commit_graph *g = xcalloc(1, sizeof(*g)); + g->graph_fd = -1; + + return g; +} + +struct commit_graph *load_commit_graph_one(const char *graph_file) +{ + void *graph_map; + const unsigned char *data, *chunk_lookup; + size_t graph_size; + struct stat st; + uint32_t i; + struct commit_graph *graph; + int fd = git_open(graph_file); + uint64_t last_chunk_offset; + uint32_t last_chunk_id; + uint32_t graph_signature; + unsigned char graph_version, hash_version; + + if (fd < 0) + return NULL; + if (fstat(fd, &st)) { + close(fd); + return NULL; + } + graph_size = xsize_t(st.st_size); + + if (graph_size < GRAPH_MIN_SIZE) { + close(fd); + die("graph file %s is too small", graph_file); + } + graph_map = xmmap(NULL, graph_size, PROT_READ, MAP_PRIVATE, fd, 0); + data = (const unsigned char *)graph_map; + + graph_signature = get_be32(data); + if (graph_signature != GRAPH_SIGNATURE) { + error("graph signature %X does not match signature %X", + graph_signature, GRAPH_SIGNATURE); + goto cleanup_fail; + } + + graph_version = *(unsigned char*)(data + 4); + if (graph_version != GRAPH_VERSION) { + error("graph version %X does not match version %X", + graph_version, GRAPH_VERSION); + goto cleanup_fail; + } + + hash_version = *(unsigned char*)(data + 5); + if (hash_version != GRAPH_OID_VERSION) { + error("hash version %X does not match version %X", + hash_version, GRAPH_OID_VERSION); + goto cleanup_fail; + } + + graph = alloc_commit_graph(); + + graph->hash_len = GRAPH_OID_LEN; + graph->num_chunks = *(unsigned char*)(data + 6); + graph->graph_fd = fd; + graph->data = graph_map; + graph->data_len = graph_size; + + last_chunk_id = 0; + last_chunk_offset = 8; + chunk_lookup = data + 8; + for (i = 0; i < graph->num_chunks; i++) { + uint32_t chunk_id = get_be32(chunk_lookup + 0); + uint64_t chunk_offset = get_be64(chunk_lookup + 4); + int chunk_repeated = 0; + + chunk_lookup += GRAPH_CHUNKLOOKUP_WIDTH; + + if (chunk_offset > graph_size - GIT_MAX_RAWSZ) { + error("improper chunk offset %08x%08x", (uint32_t)(chunk_offset >> 32), + (uint32_t)chunk_offset); + goto cleanup_fail; + } + + switch (chunk_id) { + case GRAPH_CHUNKID_OIDFANOUT: + if (graph->chunk_oid_fanout) + chunk_repeated = 1; + else + graph->chunk_oid_fanout = (uint32_t*)(data + chunk_offset); + break; + + case GRAPH_CHUNKID_OIDLOOKUP: + if (graph->chunk_oid_lookup) + chunk_repeated = 1; + else + graph->chunk_oid_lookup = data + chunk_offset; + break; + + case GRAPH_CHUNKID_DATA: + if (graph->chunk_commit_data) + chunk_repeated = 1; + else + graph->chunk_commit_data = data + chunk_offset; + break; + + case GRAPH_CHUNKID_LARGEEDGES: + if (graph->chunk_large_edges) + chunk_repeated = 1; + else + graph->chunk_large_edges = data + chunk_offset; + break; + } + + if (chunk_repeated) { + error("chunk id %08x appears multiple times", chunk_id); + goto cleanup_fail; + } + + if (last_chunk_id == GRAPH_CHUNKID_OIDLOOKUP) + { + graph->num_commits = (chunk_offset - last_chunk_offset) + / graph->hash_len; + } + + last_chunk_id = chunk_id; + last_chunk_offset = chunk_offset; + } + + return graph; + +cleanup_fail: + munmap(graph_map, graph_size); + close(fd); + exit(1); +} + +/* global storage */ +static struct commit_graph *commit_graph = NULL; + +static void prepare_commit_graph_one(const char *obj_dir) +{ + char *graph_name; + + if (commit_graph) + return; + + graph_name = get_commit_graph_filename(obj_dir); + commit_graph = load_commit_graph_one(graph_name); + + FREE_AND_NULL(graph_name); +} + +static int prepare_commit_graph_run_once = 0; +static void prepare_commit_graph(void) +{ + struct alternate_object_database *alt; + char *obj_dir; + + if (prepare_commit_graph_run_once) + return; + prepare_commit_graph_run_once = 1; + + obj_dir = get_object_directory(); + prepare_commit_graph_one(obj_dir); + prepare_alt_odb(the_repository); + for (alt = the_repository->objects->alt_odb_list; + !commit_graph && alt; + alt = alt->next) + prepare_commit_graph_one(alt->path); +} + +static void close_commit_graph(void) +{ + if (!commit_graph) + return; + + if (commit_graph->graph_fd >= 0) { + munmap((void *)commit_graph->data, commit_graph->data_len); + commit_graph->data = NULL; + close(commit_graph->graph_fd); + } + + FREE_AND_NULL(commit_graph); +} + +static int bsearch_graph(struct commit_graph *g, struct object_id *oid, uint32_t *pos) +{ + return bsearch_hash(oid->hash, g->chunk_oid_fanout, + g->chunk_oid_lookup, g->hash_len, pos); +} + +static struct commit_list **insert_parent_or_die(struct commit_graph *g, + uint64_t pos, + struct commit_list **pptr) +{ + struct commit *c; + struct object_id oid; + hashcpy(oid.hash, g->chunk_oid_lookup + g->hash_len * pos); + c = lookup_commit(&oid); + if (!c) + die("could not find commit %s", oid_to_hex(&oid)); + c->graph_pos = pos; + return &commit_list_insert(c, pptr)->next; +} + +static int fill_commit_in_graph(struct commit *item, struct commit_graph *g, uint32_t pos) +{ + uint32_t edge_value; + uint32_t *parent_data_ptr; + uint64_t date_low, date_high; + struct commit_list **pptr; + const unsigned char *commit_data = g->chunk_commit_data + (g->hash_len + 16) * pos; + + item->object.parsed = 1; + item->graph_pos = pos; + + item->maybe_tree = NULL; + + date_high = get_be32(commit_data + g->hash_len + 8) & 0x3; + date_low = get_be32(commit_data + g->hash_len + 12); + item->date = (timestamp_t)((date_high << 32) | date_low); + + pptr = &item->parents; + + edge_value = get_be32(commit_data + g->hash_len); + if (edge_value == GRAPH_PARENT_NONE) + return 1; + pptr = insert_parent_or_die(g, edge_value, pptr); + + edge_value = get_be32(commit_data + g->hash_len + 4); + if (edge_value == GRAPH_PARENT_NONE) + return 1; + if (!(edge_value & GRAPH_OCTOPUS_EDGES_NEEDED)) { + pptr = insert_parent_or_die(g, edge_value, pptr); + return 1; + } + + parent_data_ptr = (uint32_t*)(g->chunk_large_edges + + 4 * (uint64_t)(edge_value & GRAPH_EDGE_LAST_MASK)); + do { + edge_value = get_be32(parent_data_ptr); + pptr = insert_parent_or_die(g, + edge_value & GRAPH_EDGE_LAST_MASK, + pptr); + parent_data_ptr++; + } while (!(edge_value & GRAPH_LAST_EDGE)); + + return 1; +} + +int parse_commit_in_graph(struct commit *item) +{ + if (!core_commit_graph) + return 0; + if (item->object.parsed) + return 1; + + prepare_commit_graph(); + if (commit_graph) { + uint32_t pos; + int found; + if (item->graph_pos != COMMIT_NOT_FROM_GRAPH) { + pos = item->graph_pos; + found = 1; + } else { + found = bsearch_graph(commit_graph, &(item->object.oid), &pos); + } + + if (found) + return fill_commit_in_graph(item, commit_graph, pos); + } + + return 0; +} + +static struct tree *load_tree_for_commit(struct commit_graph *g, struct commit *c) +{ + struct object_id oid; + const unsigned char *commit_data = g->chunk_commit_data + + GRAPH_DATA_WIDTH * (c->graph_pos); + + hashcpy(oid.hash, commit_data); + c->maybe_tree = lookup_tree(&oid); + + return c->maybe_tree; +} + +struct tree *get_commit_tree_in_graph(const struct commit *c) +{ + if (c->maybe_tree) + return c->maybe_tree; + if (c->graph_pos == COMMIT_NOT_FROM_GRAPH) + BUG("get_commit_tree_in_graph called from non-commit-graph commit"); + + return load_tree_for_commit(commit_graph, (struct commit *)c); +} + +static void write_graph_chunk_fanout(struct hashfile *f, + struct commit **commits, + int nr_commits) +{ + int i, count = 0; + struct commit **list = commits; + + /* + * Write the first-level table (the list is sorted, + * but we use a 256-entry lookup to be able to avoid + * having to do eight extra binary search iterations). + */ + for (i = 0; i < 256; i++) { + while (count < nr_commits) { + if ((*list)->object.oid.hash[0] != i) + break; + count++; + list++; + } + + hashwrite_be32(f, count); + } +} + +static void write_graph_chunk_oids(struct hashfile *f, int hash_len, + struct commit **commits, int nr_commits) +{ + struct commit **list = commits; + int count; + for (count = 0; count < nr_commits; count++, list++) + hashwrite(f, (*list)->object.oid.hash, (int)hash_len); +} + +static const unsigned char *commit_to_sha1(size_t index, void *table) +{ + struct commit **commits = table; + return commits[index]->object.oid.hash; +} + +static void write_graph_chunk_data(struct hashfile *f, int hash_len, + struct commit **commits, int nr_commits) +{ + struct commit **list = commits; + struct commit **last = commits + nr_commits; + uint32_t num_extra_edges = 0; + + while (list < last) { + struct commit_list *parent; + int edge_value; + uint32_t packedDate[2]; + + parse_commit(*list); + hashwrite(f, get_commit_tree_oid(*list)->hash, hash_len); + + parent = (*list)->parents; + + if (!parent) + edge_value = GRAPH_PARENT_NONE; + else { + edge_value = sha1_pos(parent->item->object.oid.hash, + commits, + nr_commits, + commit_to_sha1); + + if (edge_value < 0) + edge_value = GRAPH_PARENT_MISSING; + } + + hashwrite_be32(f, edge_value); + + if (parent) + parent = parent->next; + + if (!parent) + edge_value = GRAPH_PARENT_NONE; + else if (parent->next) + edge_value = GRAPH_OCTOPUS_EDGES_NEEDED | num_extra_edges; + else { + edge_value = sha1_pos(parent->item->object.oid.hash, + commits, + nr_commits, + commit_to_sha1); + if (edge_value < 0) + edge_value = GRAPH_PARENT_MISSING; + } + + hashwrite_be32(f, edge_value); + + if (edge_value & GRAPH_OCTOPUS_EDGES_NEEDED) { + do { + num_extra_edges++; + parent = parent->next; + } while (parent); + } + + if (sizeof((*list)->date) > 4) + packedDate[0] = htonl(((*list)->date >> 32) & 0x3); + else + packedDate[0] = 0; + + packedDate[1] = htonl((*list)->date); + hashwrite(f, packedDate, 8); + + list++; + } +} + +static void write_graph_chunk_large_edges(struct hashfile *f, + struct commit **commits, + int nr_commits) +{ + struct commit **list = commits; + struct commit **last = commits + nr_commits; + struct commit_list *parent; + + while (list < last) { + int num_parents = 0; + for (parent = (*list)->parents; num_parents < 3 && parent; + parent = parent->next) + num_parents++; + + if (num_parents <= 2) { + list++; + continue; + } + + /* Since num_parents > 2, this initializer is safe. */ + for (parent = (*list)->parents->next; parent; parent = parent->next) { + int edge_value = sha1_pos(parent->item->object.oid.hash, + commits, + nr_commits, + commit_to_sha1); + + if (edge_value < 0) + edge_value = GRAPH_PARENT_MISSING; + else if (!parent->next) + edge_value |= GRAPH_LAST_EDGE; + + hashwrite_be32(f, edge_value); + } + + list++; + } +} + +static int commit_compare(const void *_a, const void *_b) +{ + const struct object_id *a = (const struct object_id *)_a; + const struct object_id *b = (const struct object_id *)_b; + return oidcmp(a, b); +} + +struct packed_commit_list { + struct commit **list; + int nr; + int alloc; +}; + +struct packed_oid_list { + struct object_id *list; + int nr; + int alloc; +}; + +static int add_packed_commits(const struct object_id *oid, + struct packed_git *pack, + uint32_t pos, + void *data) +{ + struct packed_oid_list *list = (struct packed_oid_list*)data; + enum object_type type; + off_t offset = nth_packed_object_offset(pack, pos); + struct object_info oi = OBJECT_INFO_INIT; + + oi.typep = &type; + if (packed_object_info(the_repository, pack, offset, &oi) < 0) + die("unable to get type of object %s", oid_to_hex(oid)); + + if (type != OBJ_COMMIT) + return 0; + + ALLOC_GROW(list->list, list->nr + 1, list->alloc); + oidcpy(&(list->list[list->nr]), oid); + list->nr++; + + return 0; +} + +static void add_missing_parents(struct packed_oid_list *oids, struct commit *commit) +{ + struct commit_list *parent; + for (parent = commit->parents; parent; parent = parent->next) { + if (!(parent->item->object.flags & UNINTERESTING)) { + ALLOC_GROW(oids->list, oids->nr + 1, oids->alloc); + oidcpy(&oids->list[oids->nr], &(parent->item->object.oid)); + oids->nr++; + parent->item->object.flags |= UNINTERESTING; + } + } +} + +static void close_reachable(struct packed_oid_list *oids) +{ + int i; + struct commit *commit; + + for (i = 0; i < oids->nr; i++) { + commit = lookup_commit(&oids->list[i]); + if (commit) + commit->object.flags |= UNINTERESTING; + } + + /* + * As this loop runs, oids->nr may grow, but not more + * than the number of missing commits in the reachable + * closure. + */ + for (i = 0; i < oids->nr; i++) { + commit = lookup_commit(&oids->list[i]); + + if (commit && !parse_commit(commit)) + add_missing_parents(oids, commit); + } + + for (i = 0; i < oids->nr; i++) { + commit = lookup_commit(&oids->list[i]); + + if (commit) + commit->object.flags &= ~UNINTERESTING; + } +} + +void write_commit_graph(const char *obj_dir, + const char **pack_indexes, + int nr_packs, + const char **commit_hex, + int nr_commits, + int append) +{ + struct packed_oid_list oids; + struct packed_commit_list commits; + struct hashfile *f; + uint32_t i, count_distinct = 0; + char *graph_name; + int fd; + struct lock_file lk = LOCK_INIT; + uint32_t chunk_ids[5]; + uint64_t chunk_offsets[5]; + int num_chunks; + int num_extra_edges; + struct commit_list *parent; + + oids.nr = 0; + oids.alloc = approximate_object_count() / 4; + + if (append) { + prepare_commit_graph_one(obj_dir); + if (commit_graph) + oids.alloc += commit_graph->num_commits; + } + + if (oids.alloc < 1024) + oids.alloc = 1024; + ALLOC_ARRAY(oids.list, oids.alloc); + + if (append && commit_graph) { + for (i = 0; i < commit_graph->num_commits; i++) { + const unsigned char *hash = commit_graph->chunk_oid_lookup + + commit_graph->hash_len * i; + hashcpy(oids.list[oids.nr++].hash, hash); + } + } + + if (pack_indexes) { + struct strbuf packname = STRBUF_INIT; + int dirlen; + strbuf_addf(&packname, "%s/pack/", obj_dir); + dirlen = packname.len; + for (i = 0; i < nr_packs; i++) { + struct packed_git *p; + strbuf_setlen(&packname, dirlen); + strbuf_addstr(&packname, pack_indexes[i]); + p = add_packed_git(packname.buf, packname.len, 1); + if (!p) + die("error adding pack %s", packname.buf); + if (open_pack_index(p)) + die("error opening index for %s", packname.buf); + for_each_object_in_pack(p, add_packed_commits, &oids); + close_pack(p); + } + strbuf_release(&packname); + } + + if (commit_hex) { + for (i = 0; i < nr_commits; i++) { + const char *end; + struct object_id oid; + struct commit *result; + + if (commit_hex[i] && parse_oid_hex(commit_hex[i], &oid, &end)) + continue; + + result = lookup_commit_reference_gently(&oid, 1); + + if (result) { + ALLOC_GROW(oids.list, oids.nr + 1, oids.alloc); + oidcpy(&oids.list[oids.nr], &(result->object.oid)); + oids.nr++; + } + } + } + + if (!pack_indexes && !commit_hex) + for_each_packed_object(add_packed_commits, &oids, 0); + + close_reachable(&oids); + + QSORT(oids.list, oids.nr, commit_compare); + + count_distinct = 1; + for (i = 1; i < oids.nr; i++) { + if (oidcmp(&oids.list[i-1], &oids.list[i])) + count_distinct++; + } + + if (count_distinct >= GRAPH_PARENT_MISSING) + die(_("the commit graph format cannot write %d commits"), count_distinct); + + commits.nr = 0; + commits.alloc = count_distinct; + ALLOC_ARRAY(commits.list, commits.alloc); + + num_extra_edges = 0; + for (i = 0; i < oids.nr; i++) { + int num_parents = 0; + if (i > 0 && !oidcmp(&oids.list[i-1], &oids.list[i])) + continue; + + commits.list[commits.nr] = lookup_commit(&oids.list[i]); + parse_commit(commits.list[commits.nr]); + + for (parent = commits.list[commits.nr]->parents; + parent; parent = parent->next) + num_parents++; + + if (num_parents > 2) + num_extra_edges += num_parents - 1; + + commits.nr++; + } + num_chunks = num_extra_edges ? 4 : 3; + + if (commits.nr >= GRAPH_PARENT_MISSING) + die(_("too many commits to write graph")); + + graph_name = get_commit_graph_filename(obj_dir); + fd = hold_lock_file_for_update(&lk, graph_name, 0); + + if (fd < 0) { + struct strbuf folder = STRBUF_INIT; + strbuf_addstr(&folder, graph_name); + strbuf_setlen(&folder, strrchr(folder.buf, '/') - folder.buf); + + if (mkdir(folder.buf, 0777) < 0) + die_errno(_("cannot mkdir %s"), folder.buf); + strbuf_release(&folder); + + fd = hold_lock_file_for_update(&lk, graph_name, LOCK_DIE_ON_ERROR); + + if (fd < 0) + die_errno("unable to create '%s'", graph_name); + } + + f = hashfd(lk.tempfile->fd, lk.tempfile->filename.buf); + + hashwrite_be32(f, GRAPH_SIGNATURE); + + hashwrite_u8(f, GRAPH_VERSION); + hashwrite_u8(f, GRAPH_OID_VERSION); + hashwrite_u8(f, num_chunks); + hashwrite_u8(f, 0); /* unused padding byte */ + + chunk_ids[0] = GRAPH_CHUNKID_OIDFANOUT; + chunk_ids[1] = GRAPH_CHUNKID_OIDLOOKUP; + chunk_ids[2] = GRAPH_CHUNKID_DATA; + if (num_extra_edges) + chunk_ids[3] = GRAPH_CHUNKID_LARGEEDGES; + else + chunk_ids[3] = 0; + chunk_ids[4] = 0; + + chunk_offsets[0] = 8 + (num_chunks + 1) * GRAPH_CHUNKLOOKUP_WIDTH; + chunk_offsets[1] = chunk_offsets[0] + GRAPH_FANOUT_SIZE; + chunk_offsets[2] = chunk_offsets[1] + GRAPH_OID_LEN * commits.nr; + chunk_offsets[3] = chunk_offsets[2] + (GRAPH_OID_LEN + 16) * commits.nr; + chunk_offsets[4] = chunk_offsets[3] + 4 * num_extra_edges; + + for (i = 0; i <= num_chunks; i++) { + uint32_t chunk_write[3]; + + chunk_write[0] = htonl(chunk_ids[i]); + chunk_write[1] = htonl(chunk_offsets[i] >> 32); + chunk_write[2] = htonl(chunk_offsets[i] & 0xffffffff); + hashwrite(f, chunk_write, 12); + } + + write_graph_chunk_fanout(f, commits.list, commits.nr); + write_graph_chunk_oids(f, GRAPH_OID_LEN, commits.list, commits.nr); + write_graph_chunk_data(f, GRAPH_OID_LEN, commits.list, commits.nr); + write_graph_chunk_large_edges(f, commits.list, commits.nr); + + close_commit_graph(); + finalize_hashfile(f, NULL, CSUM_HASH_IN_STREAM | CSUM_FSYNC); + commit_lock_file(&lk); + + free(oids.list); + oids.alloc = 0; + oids.nr = 0; +} diff --git a/commit-graph.h b/commit-graph.h new file mode 100644 index 0000000000..260a468e73 --- /dev/null +++ b/commit-graph.h @@ -0,0 +1,48 @@ +#ifndef COMMIT_GRAPH_H +#define COMMIT_GRAPH_H + +#include "git-compat-util.h" + +char *get_commit_graph_filename(const char *obj_dir); + +/* + * Given a commit struct, try to fill the commit struct info, including: + * 1. tree object + * 2. date + * 3. parents. + * + * Returns 1 if and only if the commit was found in the packed graph. + * + * See parse_commit_buffer() for the fallback after this call. + */ +int parse_commit_in_graph(struct commit *item); + +struct tree *get_commit_tree_in_graph(const struct commit *c); + +struct commit_graph { + int graph_fd; + + const unsigned char *data; + size_t data_len; + + unsigned char hash_len; + unsigned char num_chunks; + uint32_t num_commits; + struct object_id oid; + + const uint32_t *chunk_oid_fanout; + const unsigned char *chunk_oid_lookup; + const unsigned char *chunk_commit_data; + const unsigned char *chunk_large_edges; +}; + +struct commit_graph *load_commit_graph_one(const char *graph_file); + +void write_commit_graph(const char *obj_dir, + const char **pack_indexes, + int nr_packs, + const char **commit_hex, + int nr_commits, + int append); + +#endif @@ -1,6 +1,7 @@ #include "cache.h" #include "tag.h" #include "commit.h" +#include "commit-graph.h" #include "pkt-line.h" #include "utf8.h" #include "diff.h" @@ -12,6 +13,7 @@ #include "prio-queue.h" #include "sha1-lookup.h" #include "wt-status.h" +#include "advice.h" static struct commit_extra_header *read_commit_extra_header_lines(const char *buf, size_t len, const char **); @@ -176,6 +178,15 @@ static int read_graft_file(const char *graft_file) struct strbuf buf = STRBUF_INIT; if (!fp) return -1; + if (advice_graft_file_deprecated) + advise(_("Support for <GIT_DIR>/info/grafts is deprecated\n" + "and will be removed in a future Git version.\n" + "\n" + "Please use \"git replace --convert-graft-file\"\n" + "to convert the grafts into replace refs.\n" + "\n" + "Turn this message off by running\n" + "\"git config advice.graftFileDeprecated false\"")); while (!strbuf_getwholeline(&buf, fp, '\n')) { /* The format is just "Commit Parent1 Parent2 ...\n" */ struct commit_graft *graft = read_graft_line(&buf); @@ -295,6 +306,22 @@ void free_commit_buffer(struct commit *commit) } } +struct tree *get_commit_tree(const struct commit *commit) +{ + if (commit->maybe_tree || !commit->object.parsed) + return commit->maybe_tree; + + if (commit->graph_pos == COMMIT_NOT_FROM_GRAPH) + BUG("commit has NULL tree, but was not loaded from commit-graph"); + + return get_commit_tree_in_graph(commit); +} + +struct object_id *get_commit_tree_oid(const struct commit *commit) +{ + return &get_commit_tree(commit)->object.oid; +} + const void *detach_commit_buffer(struct commit *commit, unsigned long *sizep) { struct commit_buffer *v = buffer_slab_peek(&buffer_slab, commit); @@ -334,7 +361,7 @@ int parse_commit_buffer(struct commit *item, const void *buffer, unsigned long s if (get_sha1_hex(bufptr + 5, parent.hash) < 0) return error("bad tree pointer in commit %s", oid_to_hex(&item->object.oid)); - item->tree = lookup_tree(&parent); + item->maybe_tree = lookup_tree(&parent); bufptr += tree_entry_len + 1; /* "tree " + "hex sha1" + "\n" */ pptr = &item->parents; @@ -383,6 +410,8 @@ int parse_commit_gently(struct commit *item, int quiet_on_missing) return -1; if (item->object.parsed) return 0; + if (parse_commit_in_graph(item)) + return 0; buffer = read_object_file(&item->object.oid, &type, &size); if (!buffer) return quiet_on_missing ? -1 : @@ -1288,17 +1317,19 @@ struct commit_extra_header *read_commit_extra_headers(struct commit *commit, return extra; } -void for_each_mergetag(each_mergetag_fn fn, struct commit *commit, void *data) +int for_each_mergetag(each_mergetag_fn fn, struct commit *commit, void *data) { struct commit_extra_header *extra, *to_free; + int res = 0; to_free = read_commit_extra_headers(commit, NULL); - for (extra = to_free; extra; extra = extra->next) { + for (extra = to_free; !res && extra; extra = extra->next) { if (strcmp(extra->key, "mergetag")) continue; /* not a merge tag */ - fn(commit, extra, data); + res = fn(commit, extra, data); } free_commit_extra_headers(to_free); + return res; } static inline int standard_header_field(const char *field, size_t len) @@ -9,6 +9,8 @@ #include "string-list.h" #include "pretty.h" +#define COMMIT_NOT_FROM_GRAPH 0xFFFFFFFF + struct commit_list { struct commit *item; struct commit_list *next; @@ -20,7 +22,14 @@ struct commit { unsigned int index; timestamp_t date; struct commit_list *parents; - struct tree *tree; + + /* + * If the commit is loaded from the commit-graph file, then this + * member may be NULL. Only access it through get_commit_tree() + * or get_commit_tree_oid(). + */ + struct tree *maybe_tree; + uint32_t graph_pos; }; extern int save_commit_buffer; @@ -99,6 +108,9 @@ void unuse_commit_buffer(const struct commit *, const void *buffer); */ void free_commit_buffer(struct commit *); +struct tree *get_commit_tree(const struct commit *); +struct object_id *get_commit_tree_oid(const struct commit *); + /* * Disassociate any cached object buffer from the commit, but do not free it. * The buffer (or NULL, if none) is returned. @@ -291,10 +303,10 @@ extern const char *find_commit_header(const char *msg, const char *key, /* Find the end of the log message, the right place for a new trailer. */ extern int ignore_non_trailer(const char *buf, size_t len); -typedef void (*each_mergetag_fn)(struct commit *commit, struct commit_extra_header *extra, +typedef int (*each_mergetag_fn)(struct commit *commit, struct commit_extra_header *extra, void *cb_data); -extern void for_each_mergetag(each_mergetag_fn fn, struct commit *commit, void *data); +extern int for_each_mergetag(each_mergetag_fn fn, struct commit *commit, void *data); struct merge_remote_desc { struct object *obj; /* the named object, could be a tag */ diff --git a/common-main.c b/common-main.c index b989e136b5..3728f66b4c 100644 --- a/common-main.c +++ b/common-main.c @@ -32,14 +32,14 @@ int main(int argc, const char **argv) */ sanitize_stdfds(); + git_resolve_executable_dir(argv[0]); + git_setup_gettext(); initialize_the_repository(); attr_start(); - git_extract_argv0_path(argv[0]); - restore_sigpipe_to_default(); return cmd_main(argc, argv); diff --git a/compat/mingw.c b/compat/mingw.c index a67872babf..6ded1c859f 100644 --- a/compat/mingw.c +++ b/compat/mingw.c @@ -2221,7 +2221,7 @@ void mingw_startup(void) die_startup(); /* determine size of argv and environ conversion buffer */ - maxlen = wcslen(_wpgmptr); + maxlen = wcslen(wargv[0]); for (i = 1; i < argc; i++) maxlen = max(maxlen, wcslen(wargv[i])); for (i = 0; wenv[i]; i++) @@ -2241,8 +2241,7 @@ void mingw_startup(void) buffer = malloc_startup(maxlen); /* convert command line arguments and environment to UTF-8 */ - __argv[0] = wcstoutfdup_startup(buffer, _wpgmptr, maxlen); - for (i = 1; i < argc; i++) + for (i = 0; i < argc; i++) __argv[i] = wcstoutfdup_startup(buffer, wargv[i], maxlen); for (i = 0; wenv[i]; i++) environ[i] = wcstoutfdup_startup(buffer, wenv[i], maxlen); @@ -16,6 +16,7 @@ #include "string-list.h" #include "utf8.h" #include "dir.h" +#include "color.h" struct config_source { struct config_source *prev; @@ -653,7 +654,45 @@ static int get_base_var(struct strbuf *name) } } -static int git_parse_source(config_fn_t fn, void *data) +struct parse_event_data { + enum config_event_t previous_type; + size_t previous_offset; + const struct config_options *opts; +}; + +static int do_event(enum config_event_t type, struct parse_event_data *data) +{ + size_t offset; + + if (!data->opts || !data->opts->event_fn) + return 0; + + if (type == CONFIG_EVENT_WHITESPACE && + data->previous_type == type) + return 0; + + offset = cf->do_ftell(cf); + /* + * At EOF, the parser always "inserts" an extra '\n', therefore + * the end offset of the event is the current file position, otherwise + * we will already have advanced to the next event. + */ + if (type != CONFIG_EVENT_EOF) + offset--; + + if (data->previous_type != CONFIG_EVENT_EOF && + data->opts->event_fn(data->previous_type, data->previous_offset, + offset, data->opts->event_fn_data) < 0) + return -1; + + data->previous_type = type; + data->previous_offset = offset; + + return 0; +} + +static int git_parse_source(config_fn_t fn, void *data, + const struct config_options *opts) { int comment = 0; int baselen = 0; @@ -664,8 +703,15 @@ static int git_parse_source(config_fn_t fn, void *data) /* U+FEFF Byte Order Mark in UTF8 */ const char *bomptr = utf8_bom; + /* For the parser event callback */ + struct parse_event_data event_data = { + CONFIG_EVENT_EOF, 0, opts + }; + for (;;) { - int c = get_next_char(); + int c; + + c = get_next_char(); if (bomptr && *bomptr) { /* We are at the file beginning; skip UTF8-encoded BOM * if present. Sane editors won't put this in on their @@ -682,18 +728,33 @@ static int git_parse_source(config_fn_t fn, void *data) } } if (c == '\n') { - if (cf->eof) + if (cf->eof) { + if (do_event(CONFIG_EVENT_EOF, &event_data) < 0) + return -1; return 0; + } + if (do_event(CONFIG_EVENT_WHITESPACE, &event_data) < 0) + return -1; comment = 0; continue; } - if (comment || isspace(c)) + if (comment) continue; + if (isspace(c)) { + if (do_event(CONFIG_EVENT_WHITESPACE, &event_data) < 0) + return -1; + continue; + } if (c == '#' || c == ';') { + if (do_event(CONFIG_EVENT_COMMENT, &event_data) < 0) + return -1; comment = 1; continue; } if (c == '[') { + if (do_event(CONFIG_EVENT_SECTION, &event_data) < 0) + return -1; + /* Reset prior to determining a new stem */ strbuf_reset(var); if (get_base_var(var) < 0 || var->len < 1) @@ -704,6 +765,10 @@ static int git_parse_source(config_fn_t fn, void *data) } if (!isalpha(c)) break; + + if (do_event(CONFIG_EVENT_ENTRY, &event_data) < 0) + return -1; + /* * Truncate the var name back to the section header * stem prior to grabbing the suffix part of the name @@ -715,6 +780,9 @@ static int git_parse_source(config_fn_t fn, void *data) break; } + if (do_event(CONFIG_EVENT_ERROR, &event_data) < 0) + return -1; + switch (cf->origin_type) { case CONFIG_ORIGIN_BLOB: error_msg = xstrfmt(_("bad config line %d in blob %s"), @@ -1000,6 +1068,15 @@ int git_config_expiry_date(timestamp_t *timestamp, const char *var, const char * return 0; } +int git_config_color(char *dest, const char *var, const char *value) +{ + if (!value) + return config_error_nonbool(var); + if (color_parse(value, dest) < 0) + return -1; + return 0; +} + static int git_default_core_config(const char *var, const char *value) { /* This needs a better name */ @@ -1172,6 +1249,11 @@ static int git_default_core_config(const char *var, const char *value) return 0; } + if (!strcmp(var, "core.checkroundtripencoding")) { + check_roundtrip_encoding = xstrdup(value); + return 0; + } + if (!strcmp(var, "core.notesref")) { notes_ref_name = xstrdup(value); return 0; @@ -1226,6 +1308,11 @@ static int git_default_core_config(const char *var, const char *value) return 0; } + if (!strcmp(var, "core.commitgraph")) { + core_commit_graph = git_config_bool(var, value); + return 0; + } + if (!strcmp(var, "core.sparsecheckout")) { core_apply_sparse_checkout = git_config_bool(var, value); return 0; @@ -1365,7 +1452,7 @@ int git_default_config(const char *var, const char *value, void *dummy) if (starts_with(var, "mailmap.")) return git_default_mailmap_config(var, value); - if (starts_with(var, "advice.")) + if (starts_with(var, "advice.") || starts_with(var, "color.advice")) return git_default_advice_config(var, value); if (!strcmp(var, "pager.color") || !strcmp(var, "color.pager")) { @@ -1398,7 +1485,8 @@ int git_default_config(const char *var, const char *value, void *dummy) * fgetc, ungetc, ftell of top need to be initialized before calling * this function. */ -static int do_config_from(struct config_source *top, config_fn_t fn, void *data) +static int do_config_from(struct config_source *top, config_fn_t fn, void *data, + const struct config_options *opts) { int ret; @@ -1410,7 +1498,7 @@ static int do_config_from(struct config_source *top, config_fn_t fn, void *data) strbuf_init(&top->var, 1024); cf = top; - ret = git_parse_source(fn, data); + ret = git_parse_source(fn, data, opts); /* pop config-file parsing state stack */ strbuf_release(&top->value); @@ -1423,7 +1511,7 @@ static int do_config_from(struct config_source *top, config_fn_t fn, void *data) static int do_config_from_file(config_fn_t fn, const enum config_origin_type origin_type, const char *name, const char *path, FILE *f, - void *data) + void *data, const struct config_options *opts) { struct config_source top; int ret; @@ -1438,29 +1526,38 @@ static int do_config_from_file(config_fn_t fn, top.do_ftell = config_file_ftell; flockfile(f); - ret = do_config_from(&top, fn, data); + ret = do_config_from(&top, fn, data, opts); funlockfile(f); return ret; } static int git_config_from_stdin(config_fn_t fn, void *data) { - return do_config_from_file(fn, CONFIG_ORIGIN_STDIN, "", NULL, stdin, data); + return do_config_from_file(fn, CONFIG_ORIGIN_STDIN, "", NULL, stdin, + data, NULL); } -int git_config_from_file(config_fn_t fn, const char *filename, void *data) +int git_config_from_file_with_options(config_fn_t fn, const char *filename, + void *data, + const struct config_options *opts) { int ret = -1; FILE *f; f = fopen_or_warn(filename, "r"); if (f) { - ret = do_config_from_file(fn, CONFIG_ORIGIN_FILE, filename, filename, f, data); + ret = do_config_from_file(fn, CONFIG_ORIGIN_FILE, filename, + filename, f, data, opts); fclose(f); } return ret; } +int git_config_from_file(config_fn_t fn, const char *filename, void *data) +{ + return git_config_from_file_with_options(fn, filename, data, NULL); +} + int git_config_from_mem(config_fn_t fn, const enum config_origin_type origin_type, const char *name, const char *buf, size_t len, void *data) { @@ -1477,7 +1574,7 @@ int git_config_from_mem(config_fn_t fn, const enum config_origin_type origin_typ top.do_ungetc = config_buf_ungetc; top.do_ftell = config_buf_ftell; - return do_config_from(&top, fn, data); + return do_config_from(&top, fn, data, NULL); } int git_config_from_blob_oid(config_fn_t fn, @@ -2221,96 +2318,98 @@ void git_die_config(const char *key, const char *err, ...) * Find all the stuff for git_config_set() below. */ -static struct { +struct config_store_data { int baselen; char *key; int do_not_match; regex_t *value_regex; int multi_replace; - size_t *offset; - unsigned int offset_alloc; - enum { START, SECTION_SEEN, SECTION_END_SEEN, KEY_SEEN } state; - unsigned int seen; -} store; + struct { + size_t begin, end; + enum config_event_t type; + int is_keys_section; + } *parsed; + unsigned int parsed_nr, parsed_alloc, *seen, seen_nr, seen_alloc; + unsigned int key_seen:1, section_seen:1, is_keys_section:1; +}; -static int matches(const char *key, const char *value) +static int matches(const char *key, const char *value, + const struct config_store_data *store) { - if (strcmp(key, store.key)) + if (strcmp(key, store->key)) return 0; /* not ours */ - if (!store.value_regex) + if (!store->value_regex) return 1; /* always matches */ - if (store.value_regex == CONFIG_REGEX_NONE) + if (store->value_regex == CONFIG_REGEX_NONE) return 0; /* never matches */ - return store.do_not_match ^ - (value && !regexec(store.value_regex, value, 0, NULL, 0)); + return store->do_not_match ^ + (value && !regexec(store->value_regex, value, 0, NULL, 0)); +} + +static int store_aux_event(enum config_event_t type, + size_t begin, size_t end, void *data) +{ + struct config_store_data *store = data; + + ALLOC_GROW(store->parsed, store->parsed_nr + 1, store->parsed_alloc); + store->parsed[store->parsed_nr].begin = begin; + store->parsed[store->parsed_nr].end = end; + store->parsed[store->parsed_nr].type = type; + + if (type == CONFIG_EVENT_SECTION) { + if (cf->var.len < 2 || cf->var.buf[cf->var.len - 1] != '.') + BUG("Invalid section name '%s'", cf->var.buf); + + /* Is this the section we were looking for? */ + store->is_keys_section = + store->parsed[store->parsed_nr].is_keys_section = + cf->var.len - 1 == store->baselen && + !strncasecmp(cf->var.buf, store->key, store->baselen); + if (store->is_keys_section) { + store->section_seen = 1; + ALLOC_GROW(store->seen, store->seen_nr + 1, + store->seen_alloc); + store->seen[store->seen_nr] = store->parsed_nr; + } + } + + store->parsed_nr++; + + return 0; } static int store_aux(const char *key, const char *value, void *cb) { - const char *ep; - size_t section_len; + struct config_store_data *store = cb; - switch (store.state) { - case KEY_SEEN: - if (matches(key, value)) { - if (store.seen == 1 && store.multi_replace == 0) { + if (store->key_seen) { + if (matches(key, value, store)) { + if (store->seen_nr == 1 && store->multi_replace == 0) { warning(_("%s has multiple values"), key); } - ALLOC_GROW(store.offset, store.seen + 1, - store.offset_alloc); + ALLOC_GROW(store->seen, store->seen_nr + 1, + store->seen_alloc); - store.offset[store.seen] = cf->do_ftell(cf); - store.seen++; + store->seen[store->seen_nr] = store->parsed_nr; + store->seen_nr++; } - break; - case SECTION_SEEN: + } else if (store->is_keys_section) { /* - * What we are looking for is in store.key (both - * section and var), and its section part is baselen - * long. We found key (again, both section and var). - * We would want to know if this key is in the same - * section as what we are looking for. We already - * know we are in the same section as what should - * hold store.key. + * Do not increment matches yet: this may not be a match, but we + * are in the desired section. */ - ep = strrchr(key, '.'); - section_len = ep - key; + ALLOC_GROW(store->seen, store->seen_nr + 1, store->seen_alloc); + store->seen[store->seen_nr] = store->parsed_nr; + store->section_seen = 1; - if ((section_len != store.baselen) || - memcmp(key, store.key, section_len+1)) { - store.state = SECTION_END_SEEN; - break; - } - - /* - * Do not increment matches: this is no match, but we - * just made sure we are in the desired section. - */ - ALLOC_GROW(store.offset, store.seen + 1, - store.offset_alloc); - store.offset[store.seen] = cf->do_ftell(cf); - /* fallthru */ - case SECTION_END_SEEN: - case START: - if (matches(key, value)) { - ALLOC_GROW(store.offset, store.seen + 1, - store.offset_alloc); - store.offset[store.seen] = cf->do_ftell(cf); - store.state = KEY_SEEN; - store.seen++; - } else { - if (strrchr(key, '.') - key == store.baselen && - !strncmp(key, store.key, store.baselen)) { - store.state = SECTION_SEEN; - ALLOC_GROW(store.offset, - store.seen + 1, - store.offset_alloc); - store.offset[store.seen] = cf->do_ftell(cf); - } + if (matches(key, value, store)) { + store->seen_nr++; + store->key_seen = 1; } } + return 0; } @@ -2322,31 +2421,33 @@ static int write_error(const char *filename) return 4; } -static struct strbuf store_create_section(const char *key) +static struct strbuf store_create_section(const char *key, + const struct config_store_data *store) { const char *dot; int i; struct strbuf sb = STRBUF_INIT; - dot = memchr(key, '.', store.baselen); + dot = memchr(key, '.', store->baselen); if (dot) { strbuf_addf(&sb, "[%.*s \"", (int)(dot - key), key); - for (i = dot - key + 1; i < store.baselen; i++) { + for (i = dot - key + 1; i < store->baselen; i++) { if (key[i] == '"' || key[i] == '\\') strbuf_addch(&sb, '\\'); strbuf_addch(&sb, key[i]); } strbuf_addstr(&sb, "\"]\n"); } else { - strbuf_addf(&sb, "[%.*s]\n", store.baselen, key); + strbuf_addf(&sb, "[%.*s]\n", store->baselen, key); } return sb; } -static ssize_t write_section(int fd, const char *key) +static ssize_t write_section(int fd, const char *key, + const struct config_store_data *store) { - struct strbuf sb = store_create_section(key); + struct strbuf sb = store_create_section(key, store); ssize_t ret; ret = write_in_full(fd, sb.buf, sb.len); @@ -2355,11 +2456,12 @@ static ssize_t write_section(int fd, const char *key) return ret; } -static ssize_t write_pair(int fd, const char *key, const char *value) +static ssize_t write_pair(int fd, const char *key, const char *value, + const struct config_store_data *store) { int i; ssize_t ret; - int length = strlen(key + store.baselen + 1); + int length = strlen(key + store->baselen + 1); const char *quote = ""; struct strbuf sb = STRBUF_INIT; @@ -2379,7 +2481,7 @@ static ssize_t write_pair(int fd, const char *key, const char *value) quote = "\""; strbuf_addf(&sb, "\t%.*s = %s", - length, key + store.baselen + 1, quote); + length, key + store->baselen + 1, quote); for (i = 0; value[i]; i++) switch (value[i]) { @@ -2405,30 +2507,85 @@ static ssize_t write_pair(int fd, const char *key, const char *value) return ret; } -static ssize_t find_beginning_of_line(const char *contents, size_t size, - size_t offset_, int *found_bracket) +/* + * If we are about to unset the last key(s) in a section, and if there are + * no comments surrounding (or included in) the section, we will want to + * extend begin/end to remove the entire section. + * + * Note: the parameter `seen_ptr` points to the index into the store.seen + * array. * This index may be incremented if a section has more than one + * entry (which all are to be removed). + */ +static void maybe_remove_section(struct config_store_data *store, + const char *contents, + size_t *begin_offset, size_t *end_offset, + int *seen_ptr) { - size_t equal_offset = size, bracket_offset = size; - ssize_t offset; + size_t begin; + int i, seen, section_seen = 0; + + /* + * First, ensure that this is the first key, and that there are no + * comments before the entry nor before the section header. + */ + seen = *seen_ptr; + for (i = store->seen[seen]; i > 0; i--) { + enum config_event_t type = store->parsed[i - 1].type; + + if (type == CONFIG_EVENT_COMMENT) + /* There is a comment before this entry or section */ + return; + if (type == CONFIG_EVENT_ENTRY) { + if (!section_seen) + /* This is not the section's first entry. */ + return; + /* We encountered no comment before the section. */ + break; + } + if (type == CONFIG_EVENT_SECTION) { + if (!store->parsed[i - 1].is_keys_section) + break; + section_seen = 1; + } + } + begin = store->parsed[i].begin; + + /* + * Next, make sure that we are removing he last key(s) in the section, + * and that there are no comments that are possibly about the current + * section. + */ + for (i = store->seen[seen] + 1; i < store->parsed_nr; i++) { + enum config_event_t type = store->parsed[i].type; -contline: - for (offset = offset_-2; offset > 0 - && contents[offset] != '\n'; offset--) - switch (contents[offset]) { - case '=': equal_offset = offset; break; - case ']': bracket_offset = offset; break; + if (type == CONFIG_EVENT_COMMENT) + return; + if (type == CONFIG_EVENT_SECTION) { + if (store->parsed[i].is_keys_section) + continue; + break; + } + if (type == CONFIG_EVENT_ENTRY) { + if (++seen < store->seen_nr && + i == store->seen[seen]) + /* We want to remove this entry, too */ + continue; + /* There is another entry in this section. */ + return; } - if (offset > 0 && contents[offset-1] == '\\') { - offset_ = offset; - goto contline; } - if (bracket_offset < equal_offset) { - *found_bracket = 1; - offset = bracket_offset+1; - } else - offset++; - return offset; + /* + * We are really removing the last entry/entries from this section, and + * there are no enclosed or surrounding comments. Remove the entire, + * now-empty section. + */ + *seen_ptr = seen; + *begin_offset = begin; + if (i < store->parsed_nr) + *end_offset = store->parsed[i].begin; + else + *end_offset = store->parsed[store->parsed_nr - 1].end; } int git_config_set_in_file_gently(const char *config_filename, @@ -2489,6 +2646,9 @@ int git_config_set_multivar_in_file_gently(const char *config_filename, char *filename_buf = NULL; char *contents = NULL; size_t contents_sz; + struct config_store_data store; + + memset(&store, 0, sizeof(store)); /* parse-key returns negative; flip the sign to feed exit(3) */ ret = 0 - git_config_parse_key(key, &store.key, &store.baselen); @@ -2531,13 +2691,14 @@ int git_config_set_multivar_in_file_gently(const char *config_filename, } store.key = (char *)key; - if (write_section(fd, key) < 0 || - write_pair(fd, key, value) < 0) + if (write_section(fd, key, &store) < 0 || + write_pair(fd, key, value, &store) < 0) goto write_err_out; } else { struct stat st; size_t copy_begin, copy_end; int i, new_line = 0; + struct config_options opts; if (value_regex == NULL) store.value_regex = NULL; @@ -2560,18 +2721,24 @@ int git_config_set_multivar_in_file_gently(const char *config_filename, } } - ALLOC_GROW(store.offset, 1, store.offset_alloc); - store.offset[0] = 0; - store.state = START; - store.seen = 0; + ALLOC_GROW(store.parsed, 1, store.parsed_alloc); + store.parsed[0].end = 0; + + memset(&opts, 0, sizeof(opts)); + opts.event_fn = store_aux_event; + opts.event_fn_data = &store; /* - * After this, store.offset will contain the *end* offset - * of the last match, or remain at 0 if no match was found. + * After this, store.parsed will contain offsets of all the + * parsed elements, and store.seen will contain a list of + * matches, as indices into store.parsed. + * * As a side effect, we make sure to transform only a valid * existing config file. */ - if (git_config_from_file(store_aux, config_filename, NULL)) { + if (git_config_from_file_with_options(store_aux, + config_filename, + &store, &opts)) { error("invalid config file %s", config_filename); free(store.key); if (store.value_regex != NULL && @@ -2591,8 +2758,8 @@ int git_config_set_multivar_in_file_gently(const char *config_filename, } /* if nothing to unset, or too many matches, error out */ - if ((store.seen == 0 && value == NULL) || - (store.seen > 1 && multi_replace == 0)) { + if ((store.seen_nr == 0 && value == NULL) || + (store.seen_nr > 1 && multi_replace == 0)) { ret = CONFIG_NOTHING_SET; goto out_free; } @@ -2623,18 +2790,49 @@ int git_config_set_multivar_in_file_gently(const char *config_filename, goto out_free; } - if (store.seen == 0) - store.seen = 1; + if (store.seen_nr == 0) { + if (!store.seen_alloc) { + /* Did not see key nor section */ + ALLOC_GROW(store.seen, 1, store.seen_alloc); + store.seen[0] = store.parsed_nr + - !!store.parsed_nr; + } + store.seen_nr = 1; + } - for (i = 0, copy_begin = 0; i < store.seen; i++) { - if (store.offset[i] == 0) { - store.offset[i] = copy_end = contents_sz; - } else if (store.state != KEY_SEEN) { - copy_end = store.offset[i]; - } else - copy_end = find_beginning_of_line( - contents, contents_sz, - store.offset[i]-2, &new_line); + for (i = 0, copy_begin = 0; i < store.seen_nr; i++) { + size_t replace_end; + int j = store.seen[i]; + + new_line = 0; + if (!store.key_seen) { + copy_end = store.parsed[j].end; + /* include '\n' when copying section header */ + if (copy_end > 0 && copy_end < contents_sz && + contents[copy_end - 1] != '\n' && + contents[copy_end] == '\n') + copy_end++; + replace_end = copy_end; + } else { + replace_end = store.parsed[j].end; + copy_end = store.parsed[j].begin; + if (!value) + maybe_remove_section(&store, contents, + ©_end, + &replace_end, &i); + /* + * Swallow preceding white-space on the same + * line. + */ + while (copy_end > 0 ) { + char c = contents[copy_end - 1]; + + if (isspace(c) && c != '\n') + copy_end--; + else + break; + } + } if (copy_end > 0 && contents[copy_end-1] != '\n') new_line = 1; @@ -2648,16 +2846,16 @@ int git_config_set_multivar_in_file_gently(const char *config_filename, write_str_in_full(fd, "\n") < 0) goto write_err_out; } - copy_begin = store.offset[i]; + copy_begin = replace_end; } /* write the pair (value == NULL means unset) */ if (value != NULL) { - if (store.state == START) { - if (write_section(fd, key) < 0) + if (!store.section_seen) { + if (write_section(fd, key, &store) < 0) goto write_err_out; } - if (write_pair(fd, key, value) < 0) + if (write_pair(fd, key, value, &store) < 0) goto write_err_out; } @@ -2781,7 +2979,8 @@ static int section_name_is_ok(const char *name) /* if new_name == NULL, the section is removed instead */ static int git_config_copy_or_rename_section_in_file(const char *config_filename, - const char *old_name, const char *new_name, int copy) + const char *old_name, + const char *new_name, int copy) { int ret = 0, remove = 0; char *filename_buf = NULL; @@ -2791,6 +2990,9 @@ static int git_config_copy_or_rename_section_in_file(const char *config_filename FILE *config_file = NULL; struct stat st; struct strbuf copystr = STRBUF_INIT; + struct config_store_data store; + + memset(&store, 0, sizeof(store)); if (new_name && !section_name_is_ok(new_name)) { ret = error("invalid section name: %s", new_name); @@ -2860,7 +3062,7 @@ static int git_config_copy_or_rename_section_in_file(const char *config_filename } store.baselen = strlen(new_name); if (!copy) { - if (write_section(out_fd, new_name) < 0) { + if (write_section(out_fd, new_name, &store) < 0) { ret = write_error(get_lock_file_path(&lock)); goto out; } @@ -2881,7 +3083,7 @@ static int git_config_copy_or_rename_section_in_file(const char *config_filename output[0] = '\t'; } } else { - copystr = store_create_section(new_name); + copystr = store_create_section(new_name, &store); } } remove = 0; @@ -28,15 +28,40 @@ enum config_origin_type { CONFIG_ORIGIN_CMDLINE }; +enum config_event_t { + CONFIG_EVENT_SECTION, + CONFIG_EVENT_ENTRY, + CONFIG_EVENT_WHITESPACE, + CONFIG_EVENT_COMMENT, + CONFIG_EVENT_EOF, + CONFIG_EVENT_ERROR +}; + +/* + * The parser event function (if not NULL) is called with the event type and + * the begin/end offsets of the parsed elements. + * + * Note: for CONFIG_EVENT_ENTRY (i.e. config variables), the trailing newline + * character is considered part of the element. + */ +typedef int (*config_parser_event_fn_t)(enum config_event_t type, + size_t begin_offset, size_t end_offset, + void *event_fn_data); + struct config_options { unsigned int respect_includes : 1; const char *commondir; const char *git_dir; + config_parser_event_fn_t event_fn; + void *event_fn_data; }; typedef int (*config_fn_t)(const char *, const char *, void *); extern int git_default_config(const char *, const char *, void *); extern int git_config_from_file(config_fn_t fn, const char *, void *); +extern int git_config_from_file_with_options(config_fn_t fn, const char *, + void *, + const struct config_options *); extern int git_config_from_mem(config_fn_t fn, const enum config_origin_type, const char *name, const char *buf, size_t len, void *data); extern int git_config_from_blob_oid(config_fn_t fn, const char *name, @@ -59,6 +84,7 @@ extern int git_config_bool(const char *, const char *); extern int git_config_string(const char **, const char *, const char *); extern int git_config_pathname(const char **, const char *, const char *); extern int git_config_expiry_date(timestamp_t *, const char *, const char *); +extern int git_config_color(char *, const char *, const char *); extern int git_config_set_in_file_gently(const char *, const char *, const char *); extern void git_config_set_in_file(const char *, const char *, const char *); extern int git_config_set_gently(const char *, const char *); diff --git a/config.mak.dev b/config.mak.dev new file mode 100644 index 0000000000..2d244ca470 --- /dev/null +++ b/config.mak.dev @@ -0,0 +1,42 @@ +ifeq ($(filter no-error,$(DEVOPTS)),) +CFLAGS += -Werror +endif +CFLAGS += -Wdeclaration-after-statement +CFLAGS += -Wno-format-zero-length +CFLAGS += -Wold-style-definition +CFLAGS += -Woverflow +CFLAGS += -Wpointer-arith +CFLAGS += -Wstrict-prototypes +CFLAGS += -Wunused +CFLAGS += -Wvla + +ifndef COMPILER_FEATURES +COMPILER_FEATURES := $(shell ./detect-compiler $(CC)) +endif + +ifneq ($(filter clang4,$(COMPILER_FEATURES)),) +CFLAGS += -Wtautological-constant-out-of-range-compare +endif + +ifneq ($(or $(filter gcc6,$(COMPILER_FEATURES)),$(filter clang4,$(COMPILER_FEATURES))),) +CFLAGS += -Wextra +# if a function is public, there should be a prototype and the right +# header file should be included. If not, it should be static. +CFLAGS += -Wmissing-prototypes +ifeq ($(filter extra-all,$(DEVOPTS)),) +# These are disabled because we have these all over the place. +CFLAGS += -Wno-empty-body +CFLAGS += -Wno-missing-field-initializers +CFLAGS += -Wno-sign-compare +CFLAGS += -Wno-unused-function +CFLAGS += -Wno-unused-parameter +endif +endif + +# uninitialized warnings on gcc 4.9.2 in xdiff/xdiffi.c and config.c +# not worth fixing since newer compilers correctly stop complaining +ifneq ($(filter gcc4,$(COMPILER_FEATURES)),) +ifeq ($(filter gcc5,$(COMPILER_FEATURES)),) +CFLAGS += -Wno-uninitialized +endif +endif diff --git a/config.mak.uname b/config.mak.uname index 6a1d0de0cc..684fc5bf02 100644 --- a/config.mak.uname +++ b/config.mak.uname @@ -37,6 +37,8 @@ ifeq ($(uname_S),Linux) HAVE_GETDELIM = YesPlease SANE_TEXT_GREP=-a FREAD_READS_DIRECTORIES = UnfortunatelyYes + BASIC_CFLAGS += -DHAVE_SYSINFO + PROCFS_EXECUTABLE_PATH = /proc/self/exe endif ifeq ($(uname_S),GNU/kFreeBSD) HAVE_ALLOCA_H = YesPlease @@ -111,6 +113,7 @@ ifeq ($(uname_S),Darwin) BASIC_CFLAGS += -DPROTECT_HFS_DEFAULT=1 HAVE_BSD_SYSCTL = YesPlease FREAD_READS_DIRECTORIES = UnfortunatelyYes + HAVE_NS_GET_EXECUTABLE_PATH = YesPlease endif ifeq ($(uname_S),SunOS) NEEDS_SOCKET = YesPlease @@ -205,6 +208,7 @@ ifeq ($(uname_S),FreeBSD) HAVE_PATHS_H = YesPlease GMTIME_UNRELIABLE_ERRORS = UnfortunatelyYes HAVE_BSD_SYSCTL = YesPlease + HAVE_BSD_KERN_PROC_SYSCTL = YesPlease PAGER_ENV = LESS=FRX LV=-c MORE=FRX FREAD_READS_DIRECTORIES = UnfortunatelyYes endif @@ -217,6 +221,8 @@ ifeq ($(uname_S),OpenBSD) BASIC_LDFLAGS += -L/usr/local/lib HAVE_PATHS_H = YesPlease HAVE_BSD_SYSCTL = YesPlease + HAVE_BSD_KERN_PROC_SYSCTL = YesPlease + PROCFS_EXECUTABLE_PATH = /proc/curproc/file endif ifeq ($(uname_S),MirBSD) NO_STRCASESTR = YesPlease @@ -235,6 +241,8 @@ ifeq ($(uname_S),NetBSD) USE_ST_TIMESPEC = YesPlease HAVE_PATHS_H = YesPlease HAVE_BSD_SYSCTL = YesPlease + HAVE_BSD_KERN_PROC_SYSCTL = YesPlease + PROCFS_EXECUTABLE_PATH = /proc/curproc/exe endif ifeq ($(uname_S),AIX) DEFAULT_PAGER = more @@ -350,6 +358,7 @@ ifeq ($(uname_S),Windows) SNPRINTF_RETURNS_BOGUS = YesPlease NO_SVN_TESTS = YesPlease RUNTIME_PREFIX = YesPlease + HAVE_WPGMPTR = YesWeDo NO_ST_BLOCKS_IN_STRUCT_STAT = YesPlease NO_NSEC = YesPlease USE_WIN32_MMAP = YesPlease @@ -499,6 +508,7 @@ ifneq (,$(findstring MINGW,$(uname_S))) NO_SVN_TESTS = YesPlease NO_PERL_MAKEMAKER = YesPlease RUNTIME_PREFIX = YesPlease + HAVE_WPGMPTR = YesWeDo NO_ST_BLOCKS_IN_STRUCT_STAT = YesPlease NO_NSEC = YesPlease USE_WIN32_MMAP = YesPlease @@ -12,9 +12,11 @@ #include "sha1-array.h" #include "transport.h" #include "strbuf.h" +#include "version.h" #include "protocol.h" -static char *server_capabilities; +static char *server_capabilities_v1; +static struct argv_array server_capabilities_v2 = ARGV_ARRAY_INIT; static const char *parse_feature_value(const char *, const char *, int *); static int check_ref(const char *name, unsigned int flags) @@ -46,8 +48,14 @@ int check_ref_type(const struct ref *ref, int flags) return check_ref(ref->name, flags); } -static void die_initial_contact(int unexpected) +static NORETURN void die_initial_contact(int unexpected) { + /* + * A hang-up after seeing some response from the other end + * means that it is unexpected, as we know the other end is + * willing to talk to us. A hang-up before seeing any + * response does not necessarily mean an ACL problem, though. + */ if (unexpected) die(_("The remote end hung up upon initial contact")); else @@ -56,6 +64,92 @@ static void die_initial_contact(int unexpected) "and the repository exists.")); } +/* Checks if the server supports the capability 'c' */ +int server_supports_v2(const char *c, int die_on_error) +{ + int i; + + for (i = 0; i < server_capabilities_v2.argc; i++) { + const char *out; + if (skip_prefix(server_capabilities_v2.argv[i], c, &out) && + (!*out || *out == '=')) + return 1; + } + + if (die_on_error) + die("server doesn't support '%s'", c); + + return 0; +} + +int server_supports_feature(const char *c, const char *feature, + int die_on_error) +{ + int i; + + for (i = 0; i < server_capabilities_v2.argc; i++) { + const char *out; + if (skip_prefix(server_capabilities_v2.argv[i], c, &out) && + (!*out || *(out++) == '=')) { + if (parse_feature_request(out, feature)) + return 1; + else + break; + } + } + + if (die_on_error) + die("server doesn't support feature '%s'", feature); + + return 0; +} + +static void process_capabilities_v2(struct packet_reader *reader) +{ + while (packet_reader_read(reader) == PACKET_READ_NORMAL) + argv_array_push(&server_capabilities_v2, reader->line); + + if (reader->status != PACKET_READ_FLUSH) + die("expected flush after capabilities"); +} + +enum protocol_version discover_version(struct packet_reader *reader) +{ + enum protocol_version version = protocol_unknown_version; + + /* + * Peek the first line of the server's response to + * determine the protocol version the server is speaking. + */ + switch (packet_reader_peek(reader)) { + case PACKET_READ_EOF: + die_initial_contact(0); + case PACKET_READ_FLUSH: + case PACKET_READ_DELIM: + version = protocol_v0; + break; + case PACKET_READ_NORMAL: + version = determine_protocol_version_client(reader->line); + break; + } + + switch (version) { + case protocol_v2: + process_capabilities_v2(reader); + break; + case protocol_v1: + /* Read the peeked version line */ + packet_reader_read(reader); + break; + case protocol_v0: + break; + case protocol_unknown_version: + BUG("unknown protocol version"); + } + + return version; +} + static void parse_one_symref_info(struct string_list *symref, const char *val, int len) { char *sym, *target; @@ -85,7 +179,7 @@ reject: static void annotate_refs_with_symref_info(struct ref *ref) { struct string_list symref = STRING_LIST_INIT_DUP; - const char *feature_list = server_capabilities; + const char *feature_list = server_capabilities_v1; while (feature_list) { int len; @@ -109,60 +203,21 @@ static void annotate_refs_with_symref_info(struct ref *ref) string_list_clear(&symref, 0); } -/* - * Read one line of a server's ref advertisement into packet_buffer. - */ -static int read_remote_ref(int in, char **src_buf, size_t *src_len, - int *responded) -{ - int len = packet_read(in, src_buf, src_len, - packet_buffer, sizeof(packet_buffer), - PACKET_READ_GENTLE_ON_EOF | - PACKET_READ_CHOMP_NEWLINE); - const char *arg; - if (len < 0) - die_initial_contact(*responded); - if (len > 4 && skip_prefix(packet_buffer, "ERR ", &arg)) - die("remote error: %s", arg); - - *responded = 1; - - return len; -} - -#define EXPECTING_PROTOCOL_VERSION 0 -#define EXPECTING_FIRST_REF 1 -#define EXPECTING_REF 2 -#define EXPECTING_SHALLOW 3 - -/* Returns 1 if packet_buffer is a protocol version pkt-line, 0 otherwise. */ -static int process_protocol_version(void) +static void process_capabilities(const char *line, int *len) { - switch (determine_protocol_version_client(packet_buffer)) { - case protocol_v1: - return 1; - case protocol_v0: - return 0; - default: - die("server is speaking an unknown protocol"); - } -} - -static void process_capabilities(int *len) -{ - int nul_location = strlen(packet_buffer); + int nul_location = strlen(line); if (nul_location == *len) return; - server_capabilities = xstrdup(packet_buffer + nul_location + 1); + server_capabilities_v1 = xstrdup(line + nul_location + 1); *len = nul_location; } -static int process_dummy_ref(void) +static int process_dummy_ref(const char *line) { struct object_id oid; const char *name; - if (parse_oid_hex(packet_buffer, &oid, &name)) + if (parse_oid_hex(line, &oid, &name)) return 0; if (*name != ' ') return 0; @@ -171,20 +226,20 @@ static int process_dummy_ref(void) return !oidcmp(&null_oid, &oid) && !strcmp(name, "capabilities^{}"); } -static void check_no_capabilities(int len) +static void check_no_capabilities(const char *line, int len) { - if (strlen(packet_buffer) != len) + if (strlen(line) != len) warning("Ignoring capabilities after first line '%s'", - packet_buffer + strlen(packet_buffer)); + line + strlen(line)); } -static int process_ref(int len, struct ref ***list, unsigned int flags, - struct oid_array *extra_have) +static int process_ref(const char *line, int len, struct ref ***list, + unsigned int flags, struct oid_array *extra_have) { struct object_id old_oid; const char *name; - if (parse_oid_hex(packet_buffer, &old_oid, &name)) + if (parse_oid_hex(line, &old_oid, &name)) return 0; if (*name != ' ') return 0; @@ -200,16 +255,17 @@ static int process_ref(int len, struct ref ***list, unsigned int flags, **list = ref; *list = &ref->next; } - check_no_capabilities(len); + check_no_capabilities(line, len); return 1; } -static int process_shallow(int len, struct oid_array *shallow_points) +static int process_shallow(const char *line, int len, + struct oid_array *shallow_points) { const char *arg; struct object_id old_oid; - if (!skip_prefix(packet_buffer, "shallow ", &arg)) + if (!skip_prefix(line, "shallow ", &arg)) return 0; if (get_oid_hex(arg, &old_oid)) @@ -217,60 +273,68 @@ static int process_shallow(int len, struct oid_array *shallow_points) if (!shallow_points) die("repository on the other end cannot be shallow"); oid_array_append(shallow_points, &old_oid); - check_no_capabilities(len); + check_no_capabilities(line, len); return 1; } +enum get_remote_heads_state { + EXPECTING_FIRST_REF = 0, + EXPECTING_REF, + EXPECTING_SHALLOW, + EXPECTING_DONE, +}; + /* * Read all the refs from the other end */ -struct ref **get_remote_heads(int in, char *src_buf, size_t src_len, +struct ref **get_remote_heads(struct packet_reader *reader, struct ref **list, unsigned int flags, struct oid_array *extra_have, struct oid_array *shallow_points) { struct ref **orig_list = list; - - /* - * A hang-up after seeing some response from the other end - * means that it is unexpected, as we know the other end is - * willing to talk to us. A hang-up before seeing any - * response does not necessarily mean an ACL problem, though. - */ - int responded = 0; - int len; - int state = EXPECTING_PROTOCOL_VERSION; + int len = 0; + enum get_remote_heads_state state = EXPECTING_FIRST_REF; + const char *arg; *list = NULL; - while ((len = read_remote_ref(in, &src_buf, &src_len, &responded))) { + while (state != EXPECTING_DONE) { + switch (packet_reader_read(reader)) { + case PACKET_READ_EOF: + die_initial_contact(1); + case PACKET_READ_NORMAL: + len = reader->pktlen; + if (len > 4 && skip_prefix(reader->line, "ERR ", &arg)) + die("remote error: %s", arg); + break; + case PACKET_READ_FLUSH: + state = EXPECTING_DONE; + break; + case PACKET_READ_DELIM: + die("invalid packet"); + } + switch (state) { - case EXPECTING_PROTOCOL_VERSION: - if (process_protocol_version()) { - state = EXPECTING_FIRST_REF; - break; - } - state = EXPECTING_FIRST_REF; - /* fallthrough */ case EXPECTING_FIRST_REF: - process_capabilities(&len); - if (process_dummy_ref()) { + process_capabilities(reader->line, &len); + if (process_dummy_ref(reader->line)) { state = EXPECTING_SHALLOW; break; } state = EXPECTING_REF; /* fallthrough */ case EXPECTING_REF: - if (process_ref(len, &list, flags, extra_have)) + if (process_ref(reader->line, len, &list, flags, extra_have)) break; state = EXPECTING_SHALLOW; /* fallthrough */ case EXPECTING_SHALLOW: - if (process_shallow(len, shallow_points)) + if (process_shallow(reader->line, len, shallow_points)) break; - die("protocol error: unexpected '%s'", packet_buffer); - default: - die("unexpected state %d", state); + die("protocol error: unexpected '%s'", reader->line); + case EXPECTING_DONE: + break; } } @@ -279,6 +343,112 @@ struct ref **get_remote_heads(int in, char *src_buf, size_t src_len, return list; } +/* Returns 1 when a valid ref has been added to `list`, 0 otherwise */ +static int process_ref_v2(const char *line, struct ref ***list) +{ + int ret = 1; + int i = 0; + struct object_id old_oid; + struct ref *ref; + struct string_list line_sections = STRING_LIST_INIT_DUP; + const char *end; + + /* + * Ref lines have a number of fields which are space deliminated. The + * first field is the OID of the ref. The second field is the ref + * name. Subsequent fields (symref-target and peeled) are optional and + * don't have a particular order. + */ + if (string_list_split(&line_sections, line, ' ', -1) < 2) { + ret = 0; + goto out; + } + + if (parse_oid_hex(line_sections.items[i++].string, &old_oid, &end) || + *end) { + ret = 0; + goto out; + } + + ref = alloc_ref(line_sections.items[i++].string); + + oidcpy(&ref->old_oid, &old_oid); + **list = ref; + *list = &ref->next; + + for (; i < line_sections.nr; i++) { + const char *arg = line_sections.items[i].string; + if (skip_prefix(arg, "symref-target:", &arg)) + ref->symref = xstrdup(arg); + + if (skip_prefix(arg, "peeled:", &arg)) { + struct object_id peeled_oid; + char *peeled_name; + struct ref *peeled; + if (parse_oid_hex(arg, &peeled_oid, &end) || *end) { + ret = 0; + goto out; + } + + peeled_name = xstrfmt("%s^{}", ref->name); + peeled = alloc_ref(peeled_name); + + oidcpy(&peeled->old_oid, &peeled_oid); + **list = peeled; + *list = &peeled->next; + + free(peeled_name); + } + } + +out: + string_list_clear(&line_sections, 0); + return ret; +} + +struct ref **get_remote_refs(int fd_out, struct packet_reader *reader, + struct ref **list, int for_push, + const struct argv_array *ref_prefixes, + const struct string_list *server_options) +{ + int i; + *list = NULL; + + if (server_supports_v2("ls-refs", 1)) + packet_write_fmt(fd_out, "command=ls-refs\n"); + + if (server_supports_v2("agent", 0)) + packet_write_fmt(fd_out, "agent=%s", git_user_agent_sanitized()); + + if (server_options && server_options->nr && + server_supports_v2("server-option", 1)) + for (i = 0; i < server_options->nr; i++) + packet_write_fmt(fd_out, "server-option=%s", + server_options->items[i].string); + + packet_delim(fd_out); + /* When pushing we don't want to request the peeled tags */ + if (!for_push) + packet_write_fmt(fd_out, "peel\n"); + packet_write_fmt(fd_out, "symrefs\n"); + for (i = 0; ref_prefixes && i < ref_prefixes->argc; i++) { + packet_write_fmt(fd_out, "ref-prefix %s\n", + ref_prefixes->argv[i]); + } + packet_flush(fd_out); + + /* Process response from server */ + while (packet_reader_read(reader) == PACKET_READ_NORMAL) { + if (!process_ref_v2(reader->line, &list)) + die("invalid ls-refs response: %s", reader->line); + } + + if (reader->status != PACKET_READ_FLUSH) + die("expected flush after ref listing"); + + return list; +} + static const char *parse_feature_value(const char *feature_list, const char *feature, int *lenp) { int len; @@ -323,7 +493,7 @@ int parse_feature_request(const char *feature_list, const char *feature) const char *server_feature_value(const char *feature, int *len) { - return parse_feature_value(server_capabilities, feature, len); + return parse_feature_value(server_capabilities_v1, feature, len); } int server_supports(const char *feature) @@ -872,6 +1042,7 @@ static enum ssh_variant determine_ssh_variant(const char *ssh_command, */ static struct child_process *git_connect_git(int fd[2], char *hostandport, const char *path, const char *prog, + enum protocol_version version, int flags) { struct child_process *conn; @@ -910,10 +1081,10 @@ static struct child_process *git_connect_git(int fd[2], char *hostandport, target_host, 0); /* If using a new version put that stuff here after a second null byte */ - if (get_protocol_version_config() > 0) { + if (version > 0) { strbuf_addch(&request, '\0'); strbuf_addf(&request, "version=%d%c", - get_protocol_version_config(), '\0'); + version, '\0'); } packet_write(fd[1], request.buf, request.len); @@ -929,14 +1100,14 @@ static struct child_process *git_connect_git(int fd[2], char *hostandport, */ static void push_ssh_options(struct argv_array *args, struct argv_array *env, enum ssh_variant variant, const char *port, - int flags) + enum protocol_version version, int flags) { if (variant == VARIANT_SSH && - get_protocol_version_config() > 0) { + version > 0) { argv_array_push(args, "-o"); argv_array_push(args, "SendEnv=" GIT_PROTOCOL_ENVIRONMENT); argv_array_pushf(env, GIT_PROTOCOL_ENVIRONMENT "=version=%d", - get_protocol_version_config()); + version); } if (flags & CONNECT_IPV4) { @@ -989,7 +1160,8 @@ static void push_ssh_options(struct argv_array *args, struct argv_array *env, /* Prepare a child_process for use by Git's SSH-tunneled transport. */ static void fill_ssh_args(struct child_process *conn, const char *ssh_host, - const char *port, int flags) + const char *port, enum protocol_version version, + int flags) { const char *ssh; enum ssh_variant variant; @@ -1023,14 +1195,14 @@ static void fill_ssh_args(struct child_process *conn, const char *ssh_host, argv_array_push(&detect.args, ssh); argv_array_push(&detect.args, "-G"); push_ssh_options(&detect.args, &detect.env_array, - VARIANT_SSH, port, flags); + VARIANT_SSH, port, version, flags); argv_array_push(&detect.args, ssh_host); variant = run_command(&detect) ? VARIANT_SIMPLE : VARIANT_SSH; } argv_array_push(&conn->args, ssh); - push_ssh_options(&conn->args, &conn->env_array, variant, port, flags); + push_ssh_options(&conn->args, &conn->env_array, variant, port, version, flags); argv_array_push(&conn->args, ssh_host); } @@ -1051,6 +1223,15 @@ struct child_process *git_connect(int fd[2], const char *url, char *hostandport, *path; struct child_process *conn; enum protocol protocol; + enum protocol_version version = get_protocol_version_config(); + + /* + * NEEDSWORK: If we are trying to use protocol v2 and we are planning + * to perform a push, then fallback to v0 since the client doesn't know + * how to push yet using v2. + */ + if (version == protocol_v2 && !strcmp("git-receive-pack", prog)) + version = protocol_v0; /* Without this we cannot rely on waitpid() to tell * what happened to our children. @@ -1065,7 +1246,7 @@ struct child_process *git_connect(int fd[2], const char *url, printf("Diag: path=%s\n", path ? path : "NULL"); conn = NULL; } else if (protocol == PROTO_GIT) { - conn = git_connect_git(fd, hostandport, path, prog, flags); + conn = git_connect_git(fd, hostandport, path, prog, version, flags); } else { struct strbuf cmd = STRBUF_INIT; const char *const *var; @@ -1108,12 +1289,12 @@ struct child_process *git_connect(int fd[2], const char *url, strbuf_release(&cmd); return NULL; } - fill_ssh_args(conn, ssh_host, port, flags); + fill_ssh_args(conn, ssh_host, port, version, flags); } else { transport_check_allowed("file"); - if (get_protocol_version_config() > 0) { + if (version > 0) { argv_array_pushf(&conn->env_array, GIT_PROTOCOL_ENVIRONMENT "=version=%d", - get_protocol_version_config()); + version); } } argv_array_push(&conn->args, cmd.buf); @@ -13,4 +13,11 @@ extern int parse_feature_request(const char *features, const char *feature); extern const char *server_feature_value(const char *feature, int *len_ret); extern int url_is_local_not_ssh(const char *url); +struct packet_reader; +extern enum protocol_version discover_version(struct packet_reader *reader); + +extern int server_supports_v2(const char *c, int die_on_error); +extern int server_supports_feature(const char *c, const char *feature, + int die_on_error); + #endif diff --git a/contrib/coccinelle/commit.cocci b/contrib/coccinelle/commit.cocci new file mode 100644 index 0000000000..a7e9215ffc --- /dev/null +++ b/contrib/coccinelle/commit.cocci @@ -0,0 +1,28 @@ +@@ +expression c; +@@ +- &c->maybe_tree->object.oid ++ get_commit_tree_oid(c) + +@@ +expression c; +@@ +- c->maybe_tree->object.oid.hash ++ get_commit_tree_oid(c)->hash + +// These excluded functions must access c->maybe_tree direcly. +@@ +identifier f !~ "^(get_commit_tree|get_commit_tree_in_graph|load_tree_for_commit)$"; +expression c; +@@ + f(...) {... +- c->maybe_tree ++ get_commit_tree(c) + ...} + +@@ +expression c; +expression s; +@@ +- get_commit_tree(c) = s ++ c->maybe_tree = s diff --git a/contrib/completion/git-completion.bash b/contrib/completion/git-completion.bash index 7fe2e213d1..52ece3a6cf 100644 --- a/contrib/completion/git-completion.bash +++ b/contrib/completion/git-completion.bash @@ -284,7 +284,11 @@ __gitcomp () # Clear the variables caching builtins' options when (re-)sourcing # the completion script. -unset $(set |sed -ne 's/^\(__gitcomp_builtin_[a-zA-Z0-9_][a-zA-Z0-9_]*\)=.*/\1/p') 2>/dev/null +if [[ -n ${ZSH_VERSION-} ]]; then + unset $(set |sed -ne 's/^\(__gitcomp_builtin_[a-zA-Z0-9_][a-zA-Z0-9_]*\)=.*/\1/p') 2>/dev/null +else + unset $(compgen -v __gitcomp_builtin_) +fi # This function is equivalent to # @@ -875,6 +879,7 @@ __git_list_porcelain_commands () check-ref-format) : plumbing;; checkout-index) : plumbing;; column) : internal helper;; + commit-graph) : plumbing;; commit-tree) : plumbing;; count-objects) : infrequent;; credential) : credentials;; @@ -2345,6 +2350,7 @@ _git_config () core.bigFileThreshold core.checkStat core.commentChar + core.commitGraph core.compression core.createObject core.deltaBaseCacheLimit @@ -2769,13 +2775,21 @@ _git_show_branch () _git_stash () { local save_opts='--all --keep-index --no-keep-index --quiet --patch --include-untracked' - local subcommands='push save list show apply clear drop pop create branch' - local subcommand="$(__git_find_on_cmdline "$subcommands")" + local subcommands='push list show apply clear drop pop create branch' + local subcommand="$(__git_find_on_cmdline "$subcommands save")" + if [ -n "$(__git_find_on_cmdline "-p")" ]; then + subcommand="push" + fi if [ -z "$subcommand" ]; then case "$cur" in --*) __gitcomp "$save_opts" ;; + sa*) + if [ -z "$(__git_find_on_cmdline "$save_opts")" ]; then + __gitcomp "save" + fi + ;; *) if [ -z "$(__git_find_on_cmdline "$save_opts")" ]; then __gitcomp "$subcommands" diff --git a/contrib/convert-grafts-to-replace-refs.sh b/contrib/convert-grafts-to-replace-refs.sh deleted file mode 100755 index 0cbc917b8c..0000000000 --- a/contrib/convert-grafts-to-replace-refs.sh +++ /dev/null @@ -1,28 +0,0 @@ -#!/bin/sh - -# You should execute this script in the repository where you -# want to convert grafts to replace refs. - -GRAFTS_FILE="${GIT_DIR:-.git}/info/grafts" - -. $(git --exec-path)/git-sh-setup - -test -f "$GRAFTS_FILE" || die "Could not find graft file: '$GRAFTS_FILE'" - -grep '^[^# ]' "$GRAFTS_FILE" | -while read definition -do - if test -n "$definition" - then - echo "Converting: $definition" - git replace --graft $definition || - die "Conversion failed for: $definition" - fi -done - -mv "$GRAFTS_FILE" "$GRAFTS_FILE.bak" || - die "Could not rename '$GRAFTS_FILE' to '$GRAFTS_FILE.bak'" - -echo "Success!" -echo "All the grafts in '$GRAFTS_FILE' have been converted to replace refs!" -echo "The grafts file '$GRAFTS_FILE' has been renamed: '$GRAFTS_FILE.bak'" diff --git a/contrib/emacs/.gitignore b/contrib/emacs/.gitignore deleted file mode 100644 index c531d9867f..0000000000 --- a/contrib/emacs/.gitignore +++ /dev/null @@ -1 +0,0 @@ -*.elc diff --git a/contrib/emacs/Makefile b/contrib/emacs/Makefile deleted file mode 100644 index 24d9312941..0000000000 --- a/contrib/emacs/Makefile +++ /dev/null @@ -1,21 +0,0 @@ -## Build and install stuff - -EMACS = emacs - -ELC = git.elc git-blame.elc -INSTALL ?= install -INSTALL_ELC = $(INSTALL) -m 644 -prefix ?= $(HOME) -emacsdir = $(prefix)/share/emacs/site-lisp -RM ?= rm -f - -all: $(ELC) - -install: all - $(INSTALL) -d $(DESTDIR)$(emacsdir) - $(INSTALL_ELC) $(ELC:.elc=.el) $(ELC) $(DESTDIR)$(emacsdir) - -%.elc: %.el - $(EMACS) -batch -f batch-byte-compile $< - -clean:; $(RM) $(ELC) diff --git a/contrib/emacs/README b/contrib/emacs/README index 82368bdbff..977a16f1e3 100644 --- a/contrib/emacs/README +++ b/contrib/emacs/README @@ -1,30 +1,24 @@ -This directory contains various modules for Emacs support. +This directory used to contain various modules for Emacs support. -To make the modules available to Emacs, you should add this directory -to your load-path, and then require the modules you want. This can be -done by adding to your .emacs something like this: +These were added shortly after Git was first released. Since then +Emacs's own support for Git got better than what was offered by these +modes. There are also popular 3rd-party Git modes such as Magit which +offer replacements for these. - (add-to-list 'load-path ".../git/contrib/emacs") - (require 'git) - (require 'git-blame) - - -The following modules are available: +The following modules were available, and can be dug up from the Git +history: * git.el: - Status manager that displays the state of all the files of the - project, and provides easy access to the most frequently used git - commands. The user interface is as far as possible compatible with - the pcl-cvs mode. It can be started with `M-x git-status'. + Wrapper for "git status" that provided access to other git commands. + + Modern alternatives to this include Magit, and VC mode that ships + with Emacs. * git-blame.el: - Emacs implementation of incremental git-blame. When you turn it on - while viewing a file, the editor buffer will be updated by setting - the background of individual lines to a color that reflects which - commit it comes from. And when you move around the buffer, a - one-line summary will be shown in the echo area. + A wrapper for "git blame" written before Emacs's own vc-annotate + mode learned to invoke git-blame, which can be done via C-x v g. * vc-git.el: diff --git a/contrib/emacs/git-blame.el b/contrib/emacs/git-blame.el index 510e0f7103..6a8a2b8ff1 100644 --- a/contrib/emacs/git-blame.el +++ b/contrib/emacs/git-blame.el @@ -1,483 +1,6 @@ -;;; git-blame.el --- Minor mode for incremental blame for Git -*- coding: utf-8 -*- -;; -;; Copyright (C) 2007 David KÃ¥gedal -;; -;; Authors: David KÃ¥gedal <davidk@lysator.liu.se> -;; Created: 31 Jan 2007 -;; Message-ID: <87iren2vqx.fsf@morpheus.local> -;; License: GPL -;; Keywords: git, version control, release management -;; -;; Compatibility: Emacs21, Emacs22 and EmacsCVS -;; Git 1.5 and up - -;; This file is *NOT* part of GNU Emacs. -;; This file is distributed under the same terms as GNU Emacs. - -;; This program is free software; you can redistribute it and/or -;; modify it under the terms of the GNU General Public License as -;; published by the Free Software Foundation; either version 2 of -;; the License, or (at your option) any later version. - -;; This program is distributed in the hope that it will be -;; useful, but WITHOUT ANY WARRANTY; without even the implied -;; warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR -;; PURPOSE. See the GNU General Public License for more details. - -;; You should have received a copy of the GNU General Public -;; License along with this program; if not, see -;; <http://www.gnu.org/licenses/>. - -;; http://www.fsf.org/copyleft/gpl.html - - -;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;; -;; -;;; Commentary: -;; -;; Here is an Emacs implementation of incremental git-blame. When you -;; turn it on while viewing a file, the editor buffer will be updated by -;; setting the background of individual lines to a color that reflects -;; which commit it comes from. And when you move around the buffer, a -;; one-line summary will be shown in the echo area. - -;;; Installation: -;; -;; To use this package, put it somewhere in `load-path' (or add -;; directory with git-blame.el to `load-path'), and add the following -;; line to your .emacs: -;; -;; (require 'git-blame) -;; -;; If you do not want to load this package before it is necessary, you -;; can make use of the `autoload' feature, e.g. by adding to your .emacs -;; the following lines -;; -;; (autoload 'git-blame-mode "git-blame" -;; "Minor mode for incremental blame for Git." t) -;; -;; Then first use of `M-x git-blame-mode' would load the package. - -;;; Compatibility: -;; -;; It requires GNU Emacs 21 or later and Git 1.5.0 and up -;; -;; If you'are using Emacs 20, try changing this: -;; -;; (overlay-put ovl 'face (list :background -;; (cdr (assq 'color (cddddr info))))) -;; -;; to -;; -;; (overlay-put ovl 'face (cons 'background-color -;; (cdr (assq 'color (cddddr info))))) - - -;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;; -;; -;;; Code: - -(eval-when-compile (require 'cl)) ; to use `push', `pop' -(require 'format-spec) - -(defface git-blame-prefix-face - '((((background dark)) (:foreground "gray" - :background "black")) - (((background light)) (:foreground "gray" - :background "white")) - (t (:weight bold))) - "The face used for the hash prefix." - :group 'git-blame) - -(defgroup git-blame nil - "A minor mode showing Git blame information." - :group 'git - :link '(function-link git-blame-mode)) - - -(defcustom git-blame-use-colors t - "Use colors to indicate commits in `git-blame-mode'." - :type 'boolean - :group 'git-blame) - -(defcustom git-blame-prefix-format - "%h %20A:" - "The format of the prefix added to each line in `git-blame' -mode. The format is passed to `format-spec' with the following format keys: - - %h - the abbreviated hash - %H - the full hash - %a - the author name - %A - the author email - %c - the committer name - %C - the committer email - %s - the commit summary -" - :group 'git-blame) - -(defcustom git-blame-mouseover-format - "%h %a %A: %s" - "The format of the description shown when pointing at a line in -`git-blame' mode. The format string is passed to `format-spec' -with the following format keys: - - %h - the abbreviated hash - %H - the full hash - %a - the author name - %A - the author email - %c - the committer name - %C - the committer email - %s - the commit summary -" - :group 'git-blame) - - -(defun git-blame-color-scale (&rest elements) - "Given a list, returns a list of triples formed with each -elements of the list. - -a b => bbb bba bab baa abb aba aaa aab" - (let (result) - (dolist (a elements) - (dolist (b elements) - (dolist (c elements) - (setq result (cons (format "#%s%s%s" a b c) result))))) - result)) - -;; (git-blame-color-scale "0c" "04" "24" "1c" "2c" "34" "14" "3c") => -;; ("#3c3c3c" "#3c3c14" "#3c3c34" "#3c3c2c" "#3c3c1c" "#3c3c24" -;; "#3c3c04" "#3c3c0c" "#3c143c" "#3c1414" "#3c1434" "#3c142c" ...) - -(defmacro git-blame-random-pop (l) - "Select a random element from L and returns it. Also remove -selected element from l." - ;; only works on lists with unique elements - `(let ((e (elt ,l (random (length ,l))))) - (setq ,l (remove e ,l)) - e)) - -(defvar git-blame-log-oneline-format - "format:[%cr] %cn: %s" - "*Formatting option used for describing current line in the minibuffer. - -This option is used to pass to git log --pretty= command-line option, -and describe which commit the current line was made.") - -(defvar git-blame-dark-colors - (git-blame-color-scale "0c" "04" "24" "1c" "2c" "34" "14" "3c") - "*List of colors (format #RGB) to use in a dark environment. - -To check out the list, evaluate (list-colors-display git-blame-dark-colors).") - -(defvar git-blame-light-colors - (git-blame-color-scale "c4" "d4" "cc" "dc" "f4" "e4" "fc" "ec") - "*List of colors (format #RGB) to use in a light environment. - -To check out the list, evaluate (list-colors-display git-blame-light-colors).") - -(defvar git-blame-colors '() - "Colors used by git-blame. The list is built once when activating git-blame -minor mode.") - -(defvar git-blame-ancient-color "dark green" - "*Color to be used for ancient commit.") - -(defvar git-blame-autoupdate t - "*Automatically update the blame display while editing") - -(defvar git-blame-proc nil - "The running git-blame process") -(make-variable-buffer-local 'git-blame-proc) - -(defvar git-blame-overlays nil - "The git-blame overlays used in the current buffer.") -(make-variable-buffer-local 'git-blame-overlays) - -(defvar git-blame-cache nil - "A cache of git-blame information for the current buffer") -(make-variable-buffer-local 'git-blame-cache) - -(defvar git-blame-idle-timer nil - "An idle timer that updates the blame") -(make-variable-buffer-local 'git-blame-cache) - -(defvar git-blame-update-queue nil - "A queue of update requests") -(make-variable-buffer-local 'git-blame-update-queue) - -;; FIXME: docstrings -(defvar git-blame-file nil) -(defvar git-blame-current nil) - -(defvar git-blame-mode nil) -(make-variable-buffer-local 'git-blame-mode) - -(defvar git-blame-mode-line-string " blame" - "String to display on the mode line when git-blame is active.") - -(or (assq 'git-blame-mode minor-mode-alist) - (setq minor-mode-alist - (cons '(git-blame-mode git-blame-mode-line-string) minor-mode-alist))) - -;;;###autoload -(defun git-blame-mode (&optional arg) - "Toggle minor mode for displaying Git blame - -With prefix ARG, turn the mode on if ARG is positive." - (interactive "P") - (cond - ((null arg) - (if git-blame-mode (git-blame-mode-off) (git-blame-mode-on))) - ((> (prefix-numeric-value arg) 0) (git-blame-mode-on)) - (t (git-blame-mode-off)))) - -(defun git-blame-mode-on () - "Turn on git-blame mode. - -See also function `git-blame-mode'." - (make-local-variable 'git-blame-colors) - (if git-blame-autoupdate - (add-hook 'after-change-functions 'git-blame-after-change nil t) - (remove-hook 'after-change-functions 'git-blame-after-change t)) - (git-blame-cleanup) - (let ((bgmode (cdr (assoc 'background-mode (frame-parameters))))) - (if (eq bgmode 'dark) - (setq git-blame-colors git-blame-dark-colors) - (setq git-blame-colors git-blame-light-colors))) - (setq git-blame-cache (make-hash-table :test 'equal)) - (setq git-blame-mode t) - (git-blame-run)) - -(defun git-blame-mode-off () - "Turn off git-blame mode. - -See also function `git-blame-mode'." - (git-blame-cleanup) - (if git-blame-idle-timer (cancel-timer git-blame-idle-timer)) - (setq git-blame-mode nil)) - -;;;###autoload -(defun git-reblame () - "Recalculate all blame information in the current buffer" - (interactive) - (unless git-blame-mode - (error "Git-blame is not active")) - - (git-blame-cleanup) - (git-blame-run)) - -(defun git-blame-run (&optional startline endline) - (if git-blame-proc - ;; Should maybe queue up a new run here - (message "Already running git blame") - (let ((display-buf (current-buffer)) - (blame-buf (get-buffer-create - (concat " git blame for " (buffer-name)))) - (args '("--incremental" "--contents" "-"))) - (if startline - (setq args (append args - (list "-L" (format "%d,%d" startline endline))))) - (setq args (append args - (list (file-name-nondirectory buffer-file-name)))) - (setq git-blame-proc - (apply 'start-process - "git-blame" blame-buf - "git" "blame" - args)) - (with-current-buffer blame-buf - (erase-buffer) - (make-local-variable 'git-blame-file) - (make-local-variable 'git-blame-current) - (setq git-blame-file display-buf) - (setq git-blame-current nil)) - (set-process-filter git-blame-proc 'git-blame-filter) - (set-process-sentinel git-blame-proc 'git-blame-sentinel) - (process-send-region git-blame-proc (point-min) (point-max)) - (process-send-eof git-blame-proc)))) - -(defun remove-git-blame-text-properties (start end) - (let ((modified (buffer-modified-p)) - (inhibit-read-only t)) - (remove-text-properties start end '(point-entered nil)) - (set-buffer-modified-p modified))) - -(defun git-blame-cleanup () - "Remove all blame properties" - (mapc 'delete-overlay git-blame-overlays) - (setq git-blame-overlays nil) - (remove-git-blame-text-properties (point-min) (point-max))) - -(defun git-blame-update-region (start end) - "Rerun blame to get updates between START and END" - (let ((overlays (overlays-in start end))) - (while overlays - (let ((overlay (pop overlays))) - (if (< (overlay-start overlay) start) - (setq start (overlay-start overlay))) - (if (> (overlay-end overlay) end) - (setq end (overlay-end overlay))) - (setq git-blame-overlays (delete overlay git-blame-overlays)) - (delete-overlay overlay)))) - (remove-git-blame-text-properties start end) - ;; We can be sure that start and end are at line breaks - (git-blame-run (1+ (count-lines (point-min) start)) - (count-lines (point-min) end))) - -(defun git-blame-sentinel (proc status) - (with-current-buffer (process-buffer proc) - (with-current-buffer git-blame-file - (setq git-blame-proc nil) - (if git-blame-update-queue - (git-blame-delayed-update)))) - ;;(kill-buffer (process-buffer proc)) - ;;(message "git blame finished") - ) - -(defvar in-blame-filter nil) - -(defun git-blame-filter (proc str) - (with-current-buffer (process-buffer proc) - (save-excursion - (goto-char (process-mark proc)) - (insert-before-markers str) - (goto-char (point-min)) - (unless in-blame-filter - (let ((more t) - (in-blame-filter t)) - (while more - (setq more (git-blame-parse)))))))) - -(defun git-blame-parse () - (cond ((looking-at "\\([0-9a-f]\\{40\\}\\) \\([0-9]+\\) \\([0-9]+\\) \\([0-9]+\\)\n") - (let ((hash (match-string 1)) - (src-line (string-to-number (match-string 2))) - (res-line (string-to-number (match-string 3))) - (num-lines (string-to-number (match-string 4)))) - (delete-region (point) (match-end 0)) - (setq git-blame-current (list (git-blame-new-commit hash) - src-line res-line num-lines))) - t) - ((looking-at "\\([a-z-]+\\) \\(.+\\)\n") - (let ((key (match-string 1)) - (value (match-string 2))) - (delete-region (point) (match-end 0)) - (git-blame-add-info (car git-blame-current) key value) - (when (string= key "filename") - (git-blame-create-overlay (car git-blame-current) - (caddr git-blame-current) - (cadddr git-blame-current)) - (setq git-blame-current nil))) - t) - (t - nil))) - -(defun git-blame-new-commit (hash) - (with-current-buffer git-blame-file - (or (gethash hash git-blame-cache) - ;; Assign a random color to each new commit info - ;; Take care not to select the same color multiple times - (let* ((color (if git-blame-colors - (git-blame-random-pop git-blame-colors) - git-blame-ancient-color)) - (info `(,hash (color . ,color)))) - (puthash hash info git-blame-cache) - info)))) - -(defun git-blame-create-overlay (info start-line num-lines) - (with-current-buffer git-blame-file - (save-excursion - (let ((inhibit-point-motion-hooks t) - (inhibit-modification-hooks t)) - (goto-char (point-min)) - (forward-line (1- start-line)) - (let* ((start (point)) - (end (progn (forward-line num-lines) (point))) - (ovl (make-overlay start end)) - (hash (car info)) - (spec `((?h . ,(substring hash 0 6)) - (?H . ,hash) - (?a . ,(git-blame-get-info info 'author)) - (?A . ,(git-blame-get-info info 'author-mail)) - (?c . ,(git-blame-get-info info 'committer)) - (?C . ,(git-blame-get-info info 'committer-mail)) - (?s . ,(git-blame-get-info info 'summary))))) - (push ovl git-blame-overlays) - (overlay-put ovl 'git-blame info) - (overlay-put ovl 'help-echo - (format-spec git-blame-mouseover-format spec)) - (if git-blame-use-colors - (overlay-put ovl 'face (list :background - (cdr (assq 'color (cdr info)))))) - (overlay-put ovl 'line-prefix - (propertize (format-spec git-blame-prefix-format spec) - 'face 'git-blame-prefix-face))))))) - -(defun git-blame-add-info (info key value) - (nconc info (list (cons (intern key) value)))) - -(defun git-blame-get-info (info key) - (cdr (assq key (cdr info)))) - -(defun git-blame-current-commit () - (let ((info (get-char-property (point) 'git-blame))) - (if info - (car info) - (error "No commit info")))) - -(defun git-describe-commit (hash) - (with-temp-buffer - (call-process "git" nil t nil - "log" "-1" - (concat "--pretty=" git-blame-log-oneline-format) - hash) - (buffer-substring (point-min) (point-max)))) - -(defvar git-blame-last-identification nil) -(make-variable-buffer-local 'git-blame-last-identification) -(defun git-blame-identify (&optional hash) - (interactive) - (let ((info (gethash (or hash (git-blame-current-commit)) git-blame-cache))) - (when (and info (not (eq info git-blame-last-identification))) - (message "%s" (nth 4 info)) - (setq git-blame-last-identification info)))) - -;; (defun git-blame-after-save () -;; (when git-blame-mode -;; (git-blame-cleanup) -;; (git-blame-run))) -;; (add-hook 'after-save-hook 'git-blame-after-save) - -(defun git-blame-after-change (start end length) - (when git-blame-mode - (git-blame-enq-update start end))) - -(defvar git-blame-last-update nil) -(make-variable-buffer-local 'git-blame-last-update) -(defun git-blame-enq-update (start end) - "Mark the region between START and END as needing blame update" - ;; Try to be smart and avoid multiple callouts for sequential - ;; editing - (cond ((and git-blame-last-update - (= start (cdr git-blame-last-update))) - (setcdr git-blame-last-update end)) - ((and git-blame-last-update - (= end (car git-blame-last-update))) - (setcar git-blame-last-update start)) - (t - (setq git-blame-last-update (cons start end)) - (setq git-blame-update-queue (nconc git-blame-update-queue - (list git-blame-last-update))))) - (unless (or git-blame-proc git-blame-idle-timer) - (setq git-blame-idle-timer - (run-with-idle-timer 0.5 nil 'git-blame-delayed-update)))) - -(defun git-blame-delayed-update () - (setq git-blame-idle-timer nil) - (if git-blame-update-queue - (let ((first (pop git-blame-update-queue)) - (inhibit-point-motion-hooks t)) - (git-blame-update-region (car first) (cdr first))))) - -(provide 'git-blame) - -;;; git-blame.el ends here +(error "git-blame.el no longer ships with git. It's recommended +to replace its use with Emacs's own vc-annotate. See +contrib/emacs/README in git's +sources (https://github.com/git/git/blob/master/contrib/emacs/README) +for more info on suggested alternatives and for why this +happened.") diff --git a/contrib/emacs/git.el b/contrib/emacs/git.el index 97919f2d73..03f926281f 100644 --- a/contrib/emacs/git.el +++ b/contrib/emacs/git.el @@ -1,1704 +1,6 @@ -;;; git.el --- A user interface for git - -;; Copyright (C) 2005, 2006, 2007, 2008, 2009 Alexandre Julliard <julliard@winehq.org> - -;; Version: 1.0 - -;; This program is free software; you can redistribute it and/or -;; modify it under the terms of the GNU General Public License as -;; published by the Free Software Foundation; either version 2 of -;; the License, or (at your option) any later version. -;; -;; This program is distributed in the hope that it will be -;; useful, but WITHOUT ANY WARRANTY; without even the implied -;; warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR -;; PURPOSE. See the GNU General Public License for more details. -;; -;; You should have received a copy of the GNU General Public -;; License along with this program; if not, see -;; <http://www.gnu.org/licenses/>. - -;;; Commentary: - -;; This file contains an interface for the git version control -;; system. It provides easy access to the most frequently used git -;; commands. The user interface is as far as possible identical to -;; that of the PCL-CVS mode. -;; -;; To install: put this file on the load-path and place the following -;; in your .emacs file: -;; -;; (require 'git) -;; -;; To start: `M-x git-status' -;; -;; TODO -;; - diff against other branch -;; - renaming files from the status buffer -;; - creating tags -;; - fetch/pull -;; - revlist browser -;; - git-show-branch browser -;; - -;;; Compatibility: -;; -;; This file works on GNU Emacs 21 or later. It may work on older -;; versions but this is not guaranteed. -;; -;; It may work on XEmacs 21, provided that you first install the ewoc -;; and log-edit packages. -;; - -(eval-when-compile (require 'cl)) -(require 'ewoc) -(require 'log-edit) -(require 'easymenu) - - -;;;; Customizations -;;;; ------------------------------------------------------------ - -(defgroup git nil - "A user interface for the git versioning system." - :group 'tools) - -(defcustom git-committer-name nil - "User name to use for commits. -The default is to fall back to the repository config, -then to `add-log-full-name' and then to `user-full-name'." - :group 'git - :type '(choice (const :tag "Default" nil) - (string :tag "Name"))) - -(defcustom git-committer-email nil - "Email address to use for commits. -The default is to fall back to the git repository config, -then to `add-log-mailing-address' and then to `user-mail-address'." - :group 'git - :type '(choice (const :tag "Default" nil) - (string :tag "Email"))) - -(defcustom git-commits-coding-system nil - "Default coding system for the log message of git commits." - :group 'git - :type '(choice (const :tag "From repository config" nil) - (coding-system))) - -(defcustom git-append-signed-off-by nil - "Whether to append a Signed-off-by line to the commit message before editing." - :group 'git - :type 'boolean) - -(defcustom git-reuse-status-buffer t - "Whether `git-status' should try to reuse an existing buffer -if there is already one that displays the same directory." - :group 'git - :type 'boolean) - -(defcustom git-per-dir-ignore-file ".gitignore" - "Name of the per-directory ignore file." - :group 'git - :type 'string) - -(defcustom git-show-uptodate nil - "Whether to display up-to-date files." - :group 'git - :type 'boolean) - -(defcustom git-show-ignored nil - "Whether to display ignored files." - :group 'git - :type 'boolean) - -(defcustom git-show-unknown t - "Whether to display unknown files." - :group 'git - :type 'boolean) - - -(defface git-status-face - '((((class color) (background light)) (:foreground "purple")) - (((class color) (background dark)) (:foreground "salmon"))) - "Git mode face used to highlight added and modified files." - :group 'git) - -(defface git-unmerged-face - '((((class color) (background light)) (:foreground "red" :bold t)) - (((class color) (background dark)) (:foreground "red" :bold t))) - "Git mode face used to highlight unmerged files." - :group 'git) - -(defface git-unknown-face - '((((class color) (background light)) (:foreground "goldenrod" :bold t)) - (((class color) (background dark)) (:foreground "goldenrod" :bold t))) - "Git mode face used to highlight unknown files." - :group 'git) - -(defface git-uptodate-face - '((((class color) (background light)) (:foreground "grey60")) - (((class color) (background dark)) (:foreground "grey40"))) - "Git mode face used to highlight up-to-date files." - :group 'git) - -(defface git-ignored-face - '((((class color) (background light)) (:foreground "grey60")) - (((class color) (background dark)) (:foreground "grey40"))) - "Git mode face used to highlight ignored files." - :group 'git) - -(defface git-mark-face - '((((class color) (background light)) (:foreground "red" :bold t)) - (((class color) (background dark)) (:foreground "tomato" :bold t))) - "Git mode face used for the file marks." - :group 'git) - -(defface git-header-face - '((((class color) (background light)) (:foreground "blue")) - (((class color) (background dark)) (:foreground "blue"))) - "Git mode face used for commit headers." - :group 'git) - -(defface git-separator-face - '((((class color) (background light)) (:foreground "brown")) - (((class color) (background dark)) (:foreground "brown"))) - "Git mode face used for commit separator." - :group 'git) - -(defface git-permission-face - '((((class color) (background light)) (:foreground "green" :bold t)) - (((class color) (background dark)) (:foreground "green" :bold t))) - "Git mode face used for permission changes." - :group 'git) - - -;;;; Utilities -;;;; ------------------------------------------------------------ - -(defconst git-log-msg-separator "--- log message follows this line ---") - -(defvar git-log-edit-font-lock-keywords - `(("^\\(Author:\\|Date:\\|Merge:\\|Signed-off-by:\\)\\(.*\\)$" - (1 font-lock-keyword-face) - (2 font-lock-function-name-face)) - (,(concat "^\\(" (regexp-quote git-log-msg-separator) "\\)$") - (1 font-lock-comment-face)))) - -(defun git-get-env-strings (env) - "Build a list of NAME=VALUE strings from a list of environment strings." - (mapcar (lambda (entry) (concat (car entry) "=" (cdr entry))) env)) - -(defun git-call-process (buffer &rest args) - "Wrapper for call-process that sets environment strings." - (apply #'call-process "git" nil buffer nil args)) - -(defun git-call-process-display-error (&rest args) - "Wrapper for call-process that displays error messages." - (let* ((dir default-directory) - (buffer (get-buffer-create "*Git Command Output*")) - (ok (with-current-buffer buffer - (let ((default-directory dir) - (buffer-read-only nil)) - (erase-buffer) - (eq 0 (apply #'git-call-process (list buffer t) args)))))) - (unless ok (display-message-or-buffer buffer)) - ok)) - -(defun git-call-process-string (&rest args) - "Wrapper for call-process that returns the process output as a string, -or nil if the git command failed." - (with-temp-buffer - (and (eq 0 (apply #'git-call-process t args)) - (buffer-string)))) - -(defun git-call-process-string-display-error (&rest args) - "Wrapper for call-process that displays error message and returns -the process output as a string, or nil if the git command failed." - (with-temp-buffer - (if (eq 0 (apply #'git-call-process (list t t) args)) - (buffer-string) - (display-message-or-buffer (current-buffer)) - nil))) - -(defun git-run-process-region (buffer start end program args) - "Run a git process with a buffer region as input." - (let ((output-buffer (current-buffer)) - (dir default-directory)) - (with-current-buffer buffer - (cd dir) - (apply #'call-process-region start end program - nil (list output-buffer t) nil args)))) - -(defun git-run-command-buffer (buffer-name &rest args) - "Run a git command, sending the output to a buffer named BUFFER-NAME." - (let ((dir default-directory) - (buffer (get-buffer-create buffer-name))) - (message "Running git %s..." (car args)) - (with-current-buffer buffer - (let ((default-directory dir) - (buffer-read-only nil)) - (erase-buffer) - (apply #'git-call-process buffer args))) - (message "Running git %s...done" (car args)) - buffer)) - -(defun git-run-command-region (buffer start end env &rest args) - "Run a git command with specified buffer region as input." - (with-temp-buffer - (if (eq 0 (if env - (git-run-process-region - buffer start end "env" - (append (git-get-env-strings env) (list "git") args)) - (git-run-process-region buffer start end "git" args))) - (buffer-string) - (display-message-or-buffer (current-buffer)) - nil))) - -(defun git-run-hook (hook env &rest args) - "Run a git hook and display its output if any." - (let ((dir default-directory) - (hook-name (expand-file-name (concat ".git/hooks/" hook)))) - (or (not (file-executable-p hook-name)) - (let (status (buffer (get-buffer-create "*Git Hook Output*"))) - (with-current-buffer buffer - (erase-buffer) - (cd dir) - (setq status - (if env - (apply #'call-process "env" nil (list buffer t) nil - (append (git-get-env-strings env) (list hook-name) args)) - (apply #'call-process hook-name nil (list buffer t) nil args)))) - (display-message-or-buffer buffer) - (eq 0 status))))) - -(defun git-get-string-sha1 (string) - "Read a SHA1 from the specified string." - (and string - (string-match "[0-9a-f]\\{40\\}" string) - (match-string 0 string))) - -(defun git-get-committer-name () - "Return the name to use as GIT_COMMITTER_NAME." - ; copied from log-edit - (or git-committer-name - (git-config "user.name") - (and (boundp 'add-log-full-name) add-log-full-name) - (and (fboundp 'user-full-name) (user-full-name)) - (and (boundp 'user-full-name) user-full-name))) - -(defun git-get-committer-email () - "Return the email address to use as GIT_COMMITTER_EMAIL." - ; copied from log-edit - (or git-committer-email - (git-config "user.email") - (and (boundp 'add-log-mailing-address) add-log-mailing-address) - (and (fboundp 'user-mail-address) (user-mail-address)) - (and (boundp 'user-mail-address) user-mail-address))) - -(defun git-get-commits-coding-system () - "Return the coding system to use for commits." - (let ((repo-config (git-config "i18n.commitencoding"))) - (or git-commits-coding-system - (and repo-config - (fboundp 'locale-charset-to-coding-system) - (locale-charset-to-coding-system repo-config)) - 'utf-8))) - -(defun git-get-logoutput-coding-system () - "Return the coding system used for git-log output." - (let ((repo-config (or (git-config "i18n.logoutputencoding") - (git-config "i18n.commitencoding")))) - (or git-commits-coding-system - (and repo-config - (fboundp 'locale-charset-to-coding-system) - (locale-charset-to-coding-system repo-config)) - 'utf-8))) - -(defun git-escape-file-name (name) - "Escape a file name if necessary." - (if (string-match "[\n\t\"\\]" name) - (concat "\"" - (mapconcat (lambda (c) - (case c - (?\n "\\n") - (?\t "\\t") - (?\\ "\\\\") - (?\" "\\\"") - (t (char-to-string c)))) - name "") - "\"") - name)) - -(defun git-success-message (text files) - "Print a success message after having handled FILES." - (let ((n (length files))) - (if (equal n 1) - (message "%s %s" text (car files)) - (message "%s %d files" text n)))) - -(defun git-get-top-dir (dir) - "Retrieve the top-level directory of a git tree." - (let ((cdup (with-output-to-string - (with-current-buffer standard-output - (cd dir) - (unless (eq 0 (git-call-process t "rev-parse" "--show-cdup")) - (error "cannot find top-level git tree for %s." dir)))))) - (expand-file-name (concat (file-name-as-directory dir) - (car (split-string cdup "\n")))))) - -;stolen from pcl-cvs -(defun git-append-to-ignore (file) - "Add a file name to the ignore file in its directory." - (let* ((fullname (expand-file-name file)) - (dir (file-name-directory fullname)) - (name (file-name-nondirectory fullname)) - (ignore-name (expand-file-name git-per-dir-ignore-file dir)) - (created (not (file-exists-p ignore-name)))) - (save-window-excursion - (set-buffer (find-file-noselect ignore-name)) - (goto-char (point-max)) - (unless (zerop (current-column)) (insert "\n")) - (insert "/" name "\n") - (sort-lines nil (point-min) (point-max)) - (save-buffer)) - (when created - (git-call-process nil "update-index" "--add" "--" (file-relative-name ignore-name))) - (git-update-status-files (list (file-relative-name ignore-name))))) - -; propertize definition for XEmacs, stolen from erc-compat -(eval-when-compile - (unless (fboundp 'propertize) - (defun propertize (string &rest props) - (let ((string (copy-sequence string))) - (while props - (put-text-property 0 (length string) (nth 0 props) (nth 1 props) string) - (setq props (cddr props))) - string)))) - -;;;; Wrappers for basic git commands -;;;; ------------------------------------------------------------ - -(defun git-rev-parse (rev) - "Parse a revision name and return its SHA1." - (git-get-string-sha1 - (git-call-process-string "rev-parse" rev))) - -(defun git-config (key) - "Retrieve the value associated to KEY in the git repository config file." - (let ((str (git-call-process-string "config" key))) - (and str (car (split-string str "\n"))))) - -(defun git-symbolic-ref (ref) - "Wrapper for the git-symbolic-ref command." - (let ((str (git-call-process-string "symbolic-ref" ref))) - (and str (car (split-string str "\n"))))) - -(defun git-update-ref (ref newval &optional oldval reason) - "Update a reference by calling git-update-ref." - (let ((args (and oldval (list oldval)))) - (when newval (push newval args)) - (push ref args) - (when reason - (push reason args) - (push "-m" args)) - (unless newval (push "-d" args)) - (apply 'git-call-process-display-error "update-ref" args))) - -(defun git-for-each-ref (&rest specs) - "Return a list of refs using git-for-each-ref. -Each entry is a cons of (SHORT-NAME . FULL-NAME)." - (let (refs) - (with-temp-buffer - (apply #'git-call-process t "for-each-ref" "--format=%(refname)" specs) - (goto-char (point-min)) - (while (re-search-forward "^[^/\n]+/[^/\n]+/\\(.+\\)$" nil t) - (push (cons (match-string 1) (match-string 0)) refs))) - (nreverse refs))) - -(defun git-read-tree (tree &optional index-file) - "Read a tree into the index file." - (let ((process-environment - (append (and index-file (list (concat "GIT_INDEX_FILE=" index-file))) process-environment))) - (apply 'git-call-process-display-error "read-tree" (if tree (list tree))))) - -(defun git-write-tree (&optional index-file) - "Call git-write-tree and return the resulting tree SHA1 as a string." - (let ((process-environment - (append (and index-file (list (concat "GIT_INDEX_FILE=" index-file))) process-environment))) - (git-get-string-sha1 - (git-call-process-string-display-error "write-tree")))) - -(defun git-commit-tree (buffer tree parent) - "Create a commit and possibly update HEAD. -Create a commit with the message in BUFFER using the tree with hash TREE. -Use PARENT as the parent of the new commit. If PARENT is the current \"HEAD\", -update the \"HEAD\" reference to the new commit." - (let ((author-name (git-get-committer-name)) - (author-email (git-get-committer-email)) - (subject "commit (initial): ") - author-date log-start log-end args coding-system-for-write) - (when parent - (setq subject "commit: ") - (push "-p" args) - (push parent args)) - (with-current-buffer buffer - (goto-char (point-min)) - (if - (setq log-start (re-search-forward (concat "^" (regexp-quote git-log-msg-separator) "\n") nil t)) - (save-restriction - (narrow-to-region (point-min) log-start) - (goto-char (point-min)) - (when (re-search-forward "^Author: +\\(.*?\\) *<\\(.*\\)> *$" nil t) - (setq author-name (match-string 1) - author-email (match-string 2))) - (goto-char (point-min)) - (when (re-search-forward "^Date: +\\(.*\\)$" nil t) - (setq author-date (match-string 1))) - (goto-char (point-min)) - (when (re-search-forward "^Merge: +\\(.*\\)" nil t) - (setq subject "commit (merge): ") - (dolist (parent (split-string (match-string 1) " +" t)) - (push "-p" args) - (push parent args)))) - (setq log-start (point-min))) - (setq log-end (point-max)) - (goto-char log-start) - (when (re-search-forward ".*$" nil t) - (setq subject (concat subject (match-string 0)))) - (setq coding-system-for-write buffer-file-coding-system)) - (let ((commit - (git-get-string-sha1 - (let ((env `(("GIT_AUTHOR_NAME" . ,author-name) - ("GIT_AUTHOR_EMAIL" . ,author-email) - ("GIT_COMMITTER_NAME" . ,(git-get-committer-name)) - ("GIT_COMMITTER_EMAIL" . ,(git-get-committer-email))))) - (when author-date (push `("GIT_AUTHOR_DATE" . ,author-date) env)) - (apply #'git-run-command-region - buffer log-start log-end env - "commit-tree" tree (nreverse args)))))) - (when commit (git-update-ref "HEAD" commit parent subject)) - commit))) - -(defun git-empty-db-p () - "Check if the git db is empty (no commit done yet)." - (not (eq 0 (git-call-process nil "rev-parse" "--verify" "HEAD")))) - -(defun git-get-merge-heads () - "Retrieve the merge heads from the MERGE_HEAD file if present." - (let (heads) - (when (file-readable-p ".git/MERGE_HEAD") - (with-temp-buffer - (insert-file-contents ".git/MERGE_HEAD" nil nil nil t) - (goto-char (point-min)) - (while (re-search-forward "[0-9a-f]\\{40\\}" nil t) - (push (match-string 0) heads)))) - (nreverse heads))) - -(defun git-get-commit-description (commit) - "Get a one-line description of COMMIT." - (let ((coding-system-for-read (git-get-logoutput-coding-system))) - (let ((descr (git-call-process-string "log" "--max-count=1" "--pretty=oneline" commit))) - (if (and descr (string-match "\\`\\([0-9a-f]\\{40\\}\\) *\\(.*\\)$" descr)) - (concat (substring (match-string 1 descr) 0 10) " - " (match-string 2 descr)) - descr)))) - -;;;; File info structure -;;;; ------------------------------------------------------------ - -; fileinfo structure stolen from pcl-cvs -(defstruct (git-fileinfo - (:copier nil) - (:constructor git-create-fileinfo (state name &optional old-perm new-perm rename-state orig-name marked)) - (:conc-name git-fileinfo->)) - marked ;; t/nil - state ;; current state - name ;; file name - old-perm new-perm ;; permission flags - rename-state ;; rename or copy state - orig-name ;; original name for renames or copies - needs-update ;; whether file needs to be updated - needs-refresh) ;; whether file needs to be refreshed - -(defvar git-status nil) - -(defun git-set-fileinfo-state (info state) - "Set the state of a file info." - (unless (eq (git-fileinfo->state info) state) - (setf (git-fileinfo->state info) state - (git-fileinfo->new-perm info) (git-fileinfo->old-perm info) - (git-fileinfo->rename-state info) nil - (git-fileinfo->orig-name info) nil - (git-fileinfo->needs-update info) nil - (git-fileinfo->needs-refresh info) t))) - -(defun git-status-filenames-map (status func files &rest args) - "Apply FUNC to the status files names in the FILES list. -The list must be sorted." - (when files - (let ((file (pop files)) - (node (ewoc-nth status 0))) - (while (and file node) - (let* ((info (ewoc-data node)) - (name (git-fileinfo->name info))) - (if (string-lessp name file) - (setq node (ewoc-next status node)) - (if (string-equal name file) - (apply func info args)) - (setq file (pop files)))))))) - -(defun git-set-filenames-state (status files state) - "Set the state of a list of named files. The list must be sorted" - (when files - (git-status-filenames-map status #'git-set-fileinfo-state files state) - (unless state ;; delete files whose state has been set to nil - (ewoc-filter status (lambda (info) (git-fileinfo->state info)))))) - -(defun git-state-code (code) - "Convert from a string to a added/deleted/modified state." - (case (string-to-char code) - (?M 'modified) - (?? 'unknown) - (?A 'added) - (?D 'deleted) - (?U 'unmerged) - (?T 'modified) - (t nil))) - -(defun git-status-code-as-string (code) - "Format a git status code as string." - (case code - ('modified (propertize "Modified" 'face 'git-status-face)) - ('unknown (propertize "Unknown " 'face 'git-unknown-face)) - ('added (propertize "Added " 'face 'git-status-face)) - ('deleted (propertize "Deleted " 'face 'git-status-face)) - ('unmerged (propertize "Unmerged" 'face 'git-unmerged-face)) - ('uptodate (propertize "Uptodate" 'face 'git-uptodate-face)) - ('ignored (propertize "Ignored " 'face 'git-ignored-face)) - (t "? "))) - -(defun git-file-type-as-string (old-perm new-perm) - "Return a string describing the file type based on its permissions." - (let* ((old-type (lsh (or old-perm 0) -9)) - (new-type (lsh (or new-perm 0) -9)) - (str (case new-type - (64 ;; file - (case old-type - (64 nil) - (80 " (type change symlink -> file)") - (112 " (type change subproject -> file)"))) - (80 ;; symlink - (case old-type - (64 " (type change file -> symlink)") - (112 " (type change subproject -> symlink)") - (t " (symlink)"))) - (112 ;; subproject - (case old-type - (64 " (type change file -> subproject)") - (80 " (type change symlink -> subproject)") - (t " (subproject)"))) - (72 nil) ;; directory (internal, not a real git state) - (0 ;; deleted or unknown - (case old-type - (80 " (symlink)") - (112 " (subproject)"))) - (t (format " (unknown type %o)" new-type))))) - (cond (str (propertize str 'face 'git-status-face)) - ((eq new-type 72) "/") - (t "")))) - -(defun git-rename-as-string (info) - "Return a string describing the copy or rename associated with INFO, or an empty string if none." - (let ((state (git-fileinfo->rename-state info))) - (if state - (propertize - (concat " (" - (if (eq state 'copy) "copied from " - (if (eq (git-fileinfo->state info) 'added) "renamed from " - "renamed to ")) - (git-escape-file-name (git-fileinfo->orig-name info)) - ")") 'face 'git-status-face) - ""))) - -(defun git-permissions-as-string (old-perm new-perm) - "Format a permission change as string." - (propertize - (if (or (not old-perm) - (not new-perm) - (eq 0 (logand ?\111 (logxor old-perm new-perm)))) - " " - (if (eq 0 (logand ?\111 old-perm)) "+x" "-x")) - 'face 'git-permission-face)) - -(defun git-fileinfo-prettyprint (info) - "Pretty-printer for the git-fileinfo structure." - (let ((old-perm (git-fileinfo->old-perm info)) - (new-perm (git-fileinfo->new-perm info))) - (insert (concat " " (if (git-fileinfo->marked info) (propertize "*" 'face 'git-mark-face) " ") - " " (git-status-code-as-string (git-fileinfo->state info)) - " " (git-permissions-as-string old-perm new-perm) - " " (git-escape-file-name (git-fileinfo->name info)) - (git-file-type-as-string old-perm new-perm) - (git-rename-as-string info))))) - -(defun git-update-node-fileinfo (node info) - "Update the fileinfo of the specified node. The names are assumed to match already." - (let ((data (ewoc-data node))) - (setf - ;; preserve the marked flag - (git-fileinfo->marked info) (git-fileinfo->marked data) - (git-fileinfo->needs-update data) nil) - (when (not (equal info data)) - (setf (git-fileinfo->needs-refresh info) t - (ewoc-data node) info)))) - -(defun git-insert-info-list (status infolist files) - "Insert a sorted list of file infos in the status buffer, replacing existing ones if any." - (let* ((info (pop infolist)) - (node (ewoc-nth status 0)) - (name (and info (git-fileinfo->name info))) - remaining) - (while info - (let ((nodename (and node (git-fileinfo->name (ewoc-data node))))) - (while (and files (string-lessp (car files) name)) - (push (pop files) remaining)) - (when (and files (string-equal (car files) name)) - (setq files (cdr files))) - (cond ((not nodename) - (setq node (ewoc-enter-last status info)) - (setq info (pop infolist)) - (setq name (and info (git-fileinfo->name info)))) - ((string-lessp nodename name) - (setq node (ewoc-next status node))) - ((string-equal nodename name) - ;; preserve the marked flag - (git-update-node-fileinfo node info) - (setq info (pop infolist)) - (setq name (and info (git-fileinfo->name info)))) - (t - (setq node (ewoc-enter-before status node info)) - (setq info (pop infolist)) - (setq name (and info (git-fileinfo->name info))))))) - (nconc (nreverse remaining) files))) - -(defun git-run-diff-index (status files) - "Run git-diff-index on FILES and parse the results into STATUS. -Return the list of files that haven't been handled." - (let (infolist) - (with-temp-buffer - (apply #'git-call-process t "diff-index" "-z" "-M" "HEAD" "--" files) - (goto-char (point-min)) - (while (re-search-forward - ":\\([0-7]\\{6\\}\\) \\([0-7]\\{6\\}\\) [0-9a-f]\\{40\\} [0-9a-f]\\{40\\} \\(\\([ADMUT]\\)\0\\([^\0]+\\)\\|\\([CR]\\)[0-9]*\0\\([^\0]+\\)\0\\([^\0]+\\)\\)\0" - nil t 1) - (let ((old-perm (string-to-number (match-string 1) 8)) - (new-perm (string-to-number (match-string 2) 8)) - (state (or (match-string 4) (match-string 6))) - (name (or (match-string 5) (match-string 7))) - (new-name (match-string 8))) - (if new-name ; copy or rename - (if (eq ?C (string-to-char state)) - (push (git-create-fileinfo 'added new-name old-perm new-perm 'copy name) infolist) - (push (git-create-fileinfo 'deleted name 0 0 'rename new-name) infolist) - (push (git-create-fileinfo 'added new-name old-perm new-perm 'rename name) infolist)) - (push (git-create-fileinfo (git-state-code state) name old-perm new-perm) infolist))))) - (setq infolist (sort (nreverse infolist) - (lambda (info1 info2) - (string-lessp (git-fileinfo->name info1) - (git-fileinfo->name info2))))) - (git-insert-info-list status infolist files))) - -(defun git-find-status-file (status file) - "Find a given file in the status ewoc and return its node." - (let ((node (ewoc-nth status 0))) - (while (and node (not (string= file (git-fileinfo->name (ewoc-data node))))) - (setq node (ewoc-next status node))) - node)) - -(defun git-run-ls-files (status files default-state &rest options) - "Run git-ls-files on FILES and parse the results into STATUS. -Return the list of files that haven't been handled." - (let (infolist) - (with-temp-buffer - (apply #'git-call-process t "ls-files" "-z" (append options (list "--") files)) - (goto-char (point-min)) - (while (re-search-forward "\\([^\0]*?\\)\\(/?\\)\0" nil t 1) - (let ((name (match-string 1))) - (push (git-create-fileinfo default-state name 0 - (if (string-equal "/" (match-string 2)) (lsh ?\110 9) 0)) - infolist)))) - (setq infolist (nreverse infolist)) ;; assume it is sorted already - (git-insert-info-list status infolist files))) - -(defun git-run-ls-files-cached (status files default-state) - "Run git-ls-files -c on FILES and parse the results into STATUS. -Return the list of files that haven't been handled." - (let (infolist) - (with-temp-buffer - (apply #'git-call-process t "ls-files" "-z" "-s" "-c" "--" files) - (goto-char (point-min)) - (while (re-search-forward "\\([0-7]\\{6\\}\\) [0-9a-f]\\{40\\} 0\t\\([^\0]+\\)\0" nil t) - (let* ((new-perm (string-to-number (match-string 1) 8)) - (old-perm (if (eq default-state 'added) 0 new-perm)) - (name (match-string 2))) - (push (git-create-fileinfo default-state name old-perm new-perm) infolist)))) - (setq infolist (nreverse infolist)) ;; assume it is sorted already - (git-insert-info-list status infolist files))) - -(defun git-run-ls-unmerged (status files) - "Run git-ls-files -u on FILES and parse the results into STATUS." - (with-temp-buffer - (apply #'git-call-process t "ls-files" "-z" "-u" "--" files) - (goto-char (point-min)) - (let (unmerged-files) - (while (re-search-forward "[0-7]\\{6\\} [0-9a-f]\\{40\\} [123]\t\\([^\0]+\\)\0" nil t) - (push (match-string 1) unmerged-files)) - (setq unmerged-files (nreverse unmerged-files)) ;; assume it is sorted already - (git-set-filenames-state status unmerged-files 'unmerged)))) - -(defun git-get-exclude-files () - "Get the list of exclude files to pass to git-ls-files." - (let (files - (config (git-config "core.excludesfile"))) - (when (file-readable-p ".git/info/exclude") - (push ".git/info/exclude" files)) - (when (and config (file-readable-p config)) - (push config files)) - files)) - -(defun git-run-ls-files-with-excludes (status files default-state &rest options) - "Run git-ls-files on FILES with appropriate --exclude-from options." - (let ((exclude-files (git-get-exclude-files))) - (apply #'git-run-ls-files status files default-state "--directory" "--no-empty-directory" - (concat "--exclude-per-directory=" git-per-dir-ignore-file) - (append options (mapcar (lambda (f) (concat "--exclude-from=" f)) exclude-files))))) - -(defun git-update-status-files (&optional files mark-files) - "Update the status of FILES from the index. -The FILES list must be sorted." - (unless git-status (error "Not in git-status buffer.")) - ;; set the needs-update flag on existing files - (if files - (git-status-filenames-map - git-status (lambda (info) (setf (git-fileinfo->needs-update info) t)) files) - (ewoc-map (lambda (info) (setf (git-fileinfo->needs-update info) t) nil) git-status) - (git-call-process nil "update-index" "--refresh") - (when git-show-uptodate - (git-run-ls-files-cached git-status nil 'uptodate))) - (let ((remaining-files - (if (git-empty-db-p) ; we need some special handling for an empty db - (git-run-ls-files-cached git-status files 'added) - (git-run-diff-index git-status files)))) - (git-run-ls-unmerged git-status files) - (when (or remaining-files (and git-show-unknown (not files))) - (setq remaining-files (git-run-ls-files-with-excludes git-status remaining-files 'unknown "-o"))) - (when (or remaining-files (and git-show-ignored (not files))) - (setq remaining-files (git-run-ls-files-with-excludes git-status remaining-files 'ignored "-o" "-i"))) - (unless files - (setq remaining-files (git-get-filenames (ewoc-collect git-status #'git-fileinfo->needs-update)))) - (when remaining-files - (setq remaining-files (git-run-ls-files-cached git-status remaining-files 'uptodate))) - (git-set-filenames-state git-status remaining-files nil) - (when mark-files (git-mark-files git-status files)) - (git-refresh-files) - (git-refresh-ewoc-hf git-status))) - -(defun git-mark-files (status files) - "Mark all the specified FILES, and unmark the others." - (let ((file (and files (pop files))) - (node (ewoc-nth status 0))) - (while node - (let ((info (ewoc-data node))) - (if (and file (string-equal (git-fileinfo->name info) file)) - (progn - (unless (git-fileinfo->marked info) - (setf (git-fileinfo->marked info) t) - (setf (git-fileinfo->needs-refresh info) t)) - (setq file (pop files)) - (setq node (ewoc-next status node))) - (when (git-fileinfo->marked info) - (setf (git-fileinfo->marked info) nil) - (setf (git-fileinfo->needs-refresh info) t)) - (if (and file (string-lessp file (git-fileinfo->name info))) - (setq file (pop files)) - (setq node (ewoc-next status node)))))))) - -(defun git-marked-files () - "Return a list of all marked files, or if none a list containing just the file at cursor position." - (unless git-status (error "Not in git-status buffer.")) - (or (ewoc-collect git-status (lambda (info) (git-fileinfo->marked info))) - (list (ewoc-data (ewoc-locate git-status))))) - -(defun git-marked-files-state (&rest states) - "Return a sorted list of marked files that are in the specified states." - (let ((files (git-marked-files)) - result) - (dolist (info files) - (when (memq (git-fileinfo->state info) states) - (push info result))) - (nreverse result))) - -(defun git-refresh-files () - "Refresh all files that need it and clear the needs-refresh flag." - (unless git-status (error "Not in git-status buffer.")) - (ewoc-map - (lambda (info) - (let ((refresh (git-fileinfo->needs-refresh info))) - (setf (git-fileinfo->needs-refresh info) nil) - refresh)) - git-status) - ; move back to goal column - (when goal-column (move-to-column goal-column))) - -(defun git-refresh-ewoc-hf (status) - "Refresh the ewoc header and footer." - (let ((branch (git-symbolic-ref "HEAD")) - (head (if (git-empty-db-p) "Nothing committed yet" - (git-get-commit-description "HEAD"))) - (merge-heads (git-get-merge-heads))) - (ewoc-set-hf status - (format "Directory: %s\nBranch: %s\nHead: %s%s\n" - default-directory - (if branch - (if (string-match "^refs/heads/" branch) - (substring branch (match-end 0)) - branch) - "none (detached HEAD)") - head - (if merge-heads - (concat "\nMerging: " - (mapconcat (lambda (str) (git-get-commit-description str)) merge-heads "\n ")) - "")) - (if (ewoc-nth status 0) "" " No changes.")))) - -(defun git-get-filenames (files) - (mapcar (lambda (info) (git-fileinfo->name info)) files)) - -(defun git-update-index (index-file files) - "Run git-update-index on a list of files." - (let ((process-environment (append (and index-file (list (concat "GIT_INDEX_FILE=" index-file))) - process-environment)) - added deleted modified) - (dolist (info files) - (case (git-fileinfo->state info) - ('added (push info added)) - ('deleted (push info deleted)) - ('modified (push info modified)))) - (and - (or (not added) (apply #'git-call-process-display-error "update-index" "--add" "--" (git-get-filenames added))) - (or (not deleted) (apply #'git-call-process-display-error "update-index" "--remove" "--" (git-get-filenames deleted))) - (or (not modified) (apply #'git-call-process-display-error "update-index" "--" (git-get-filenames modified)))))) - -(defun git-run-pre-commit-hook () - "Run the pre-commit hook if any." - (unless git-status (error "Not in git-status buffer.")) - (let ((files (git-marked-files-state 'added 'deleted 'modified))) - (or (not files) - (not (file-executable-p ".git/hooks/pre-commit")) - (let ((index-file (make-temp-file "gitidx"))) - (unwind-protect - (let ((head-tree (unless (git-empty-db-p) (git-rev-parse "HEAD^{tree}")))) - (git-read-tree head-tree index-file) - (git-update-index index-file files) - (git-run-hook "pre-commit" `(("GIT_INDEX_FILE" . ,index-file)))) - (delete-file index-file)))))) - -(defun git-do-commit () - "Perform the actual commit using the current buffer as log message." - (interactive) - (let ((buffer (current-buffer)) - (index-file (make-temp-file "gitidx"))) - (with-current-buffer log-edit-parent-buffer - (if (git-marked-files-state 'unmerged) - (message "You cannot commit unmerged files, resolve them first.") - (unwind-protect - (let ((files (git-marked-files-state 'added 'deleted 'modified)) - head tree head-tree) - (unless (git-empty-db-p) - (setq head (git-rev-parse "HEAD") - head-tree (git-rev-parse "HEAD^{tree}"))) - (message "Running git commit...") - (when - (and - (git-read-tree head-tree index-file) - (git-update-index nil files) ;update both the default index - (git-update-index index-file files) ;and the temporary one - (setq tree (git-write-tree index-file))) - (if (or (not (string-equal tree head-tree)) - (yes-or-no-p "The tree was not modified, do you really want to perform an empty commit? ")) - (let ((commit (git-commit-tree buffer tree head))) - (when commit - (condition-case nil (delete-file ".git/MERGE_HEAD") (error nil)) - (condition-case nil (delete-file ".git/MERGE_MSG") (error nil)) - (with-current-buffer buffer (erase-buffer)) - (git-update-status-files (git-get-filenames files)) - (git-call-process nil "rerere") - (git-call-process nil "gc" "--auto") - (message "Committed %s." commit) - (git-run-hook "post-commit" nil))) - (message "Commit aborted.")))) - (delete-file index-file)))))) - - -;;;; Interactive functions -;;;; ------------------------------------------------------------ - -(defun git-mark-file () - "Mark the file that the cursor is on and move to the next one." - (interactive) - (unless git-status (error "Not in git-status buffer.")) - (let* ((pos (ewoc-locate git-status)) - (info (ewoc-data pos))) - (setf (git-fileinfo->marked info) t) - (ewoc-invalidate git-status pos) - (ewoc-goto-next git-status 1))) - -(defun git-unmark-file () - "Unmark the file that the cursor is on and move to the next one." - (interactive) - (unless git-status (error "Not in git-status buffer.")) - (let* ((pos (ewoc-locate git-status)) - (info (ewoc-data pos))) - (setf (git-fileinfo->marked info) nil) - (ewoc-invalidate git-status pos) - (ewoc-goto-next git-status 1))) - -(defun git-unmark-file-up () - "Unmark the file that the cursor is on and move to the previous one." - (interactive) - (unless git-status (error "Not in git-status buffer.")) - (let* ((pos (ewoc-locate git-status)) - (info (ewoc-data pos))) - (setf (git-fileinfo->marked info) nil) - (ewoc-invalidate git-status pos) - (ewoc-goto-prev git-status 1))) - -(defun git-mark-all () - "Mark all files." - (interactive) - (unless git-status (error "Not in git-status buffer.")) - (ewoc-map (lambda (info) (unless (git-fileinfo->marked info) - (setf (git-fileinfo->marked info) t))) git-status) - ; move back to goal column after invalidate - (when goal-column (move-to-column goal-column))) - -(defun git-unmark-all () - "Unmark all files." - (interactive) - (unless git-status (error "Not in git-status buffer.")) - (ewoc-map (lambda (info) (when (git-fileinfo->marked info) - (setf (git-fileinfo->marked info) nil) - t)) git-status) - ; move back to goal column after invalidate - (when goal-column (move-to-column goal-column))) - -(defun git-toggle-all-marks () - "Toggle all file marks." - (interactive) - (unless git-status (error "Not in git-status buffer.")) - (ewoc-map (lambda (info) (setf (git-fileinfo->marked info) (not (git-fileinfo->marked info))) t) git-status) - ; move back to goal column after invalidate - (when goal-column (move-to-column goal-column))) - -(defun git-next-file (&optional n) - "Move the selection down N files." - (interactive "p") - (unless git-status (error "Not in git-status buffer.")) - (ewoc-goto-next git-status n)) - -(defun git-prev-file (&optional n) - "Move the selection up N files." - (interactive "p") - (unless git-status (error "Not in git-status buffer.")) - (ewoc-goto-prev git-status n)) - -(defun git-next-unmerged-file (&optional n) - "Move the selection down N unmerged files." - (interactive "p") - (unless git-status (error "Not in git-status buffer.")) - (let* ((last (ewoc-locate git-status)) - (node (ewoc-next git-status last))) - (while (and node (> n 0)) - (when (eq 'unmerged (git-fileinfo->state (ewoc-data node))) - (setq n (1- n)) - (setq last node)) - (setq node (ewoc-next git-status node))) - (ewoc-goto-node git-status last))) - -(defun git-prev-unmerged-file (&optional n) - "Move the selection up N unmerged files." - (interactive "p") - (unless git-status (error "Not in git-status buffer.")) - (let* ((last (ewoc-locate git-status)) - (node (ewoc-prev git-status last))) - (while (and node (> n 0)) - (when (eq 'unmerged (git-fileinfo->state (ewoc-data node))) - (setq n (1- n)) - (setq last node)) - (setq node (ewoc-prev git-status node))) - (ewoc-goto-node git-status last))) - -(defun git-insert-file (file) - "Insert file(s) into the git-status buffer." - (interactive "fInsert file: ") - (git-update-status-files (list (file-relative-name file)))) - -(defun git-add-file () - "Add marked file(s) to the index cache." - (interactive) - (let ((files (git-get-filenames (git-marked-files-state 'unknown 'ignored 'unmerged)))) - ;; FIXME: add support for directories - (unless files - (push (file-relative-name (read-file-name "File to add: " nil nil t)) files)) - (when (apply 'git-call-process-display-error "update-index" "--add" "--" files) - (git-update-status-files files) - (git-success-message "Added" files)))) - -(defun git-ignore-file () - "Add marked file(s) to the ignore list." - (interactive) - (let ((files (git-get-filenames (git-marked-files-state 'unknown)))) - (unless files - (push (file-relative-name (read-file-name "File to ignore: " nil nil t)) files)) - (dolist (f files) (git-append-to-ignore f)) - (git-update-status-files files) - (git-success-message "Ignored" files))) - -(defun git-remove-file () - "Remove the marked file(s)." - (interactive) - (let ((files (git-get-filenames (git-marked-files-state 'added 'modified 'unknown 'uptodate 'ignored)))) - (unless files - (push (file-relative-name (read-file-name "File to remove: " nil nil t)) files)) - (if (yes-or-no-p - (if (cdr files) - (format "Remove %d files? " (length files)) - (format "Remove %s? " (car files)))) - (progn - (dolist (name files) - (ignore-errors - (if (file-directory-p name) - (delete-directory name) - (delete-file name)))) - (when (apply 'git-call-process-display-error "update-index" "--remove" "--" files) - (git-update-status-files files) - (git-success-message "Removed" files))) - (message "Aborting")))) - -(defun git-revert-file () - "Revert changes to the marked file(s)." - (interactive) - (let ((files (git-marked-files-state 'added 'deleted 'modified 'unmerged)) - added modified) - (when (and files - (yes-or-no-p - (if (cdr files) - (format "Revert %d files? " (length files)) - (format "Revert %s? " (git-fileinfo->name (car files)))))) - (dolist (info files) - (case (git-fileinfo->state info) - ('added (push (git-fileinfo->name info) added)) - ('deleted (push (git-fileinfo->name info) modified)) - ('unmerged (push (git-fileinfo->name info) modified)) - ('modified (push (git-fileinfo->name info) modified)))) - ;; check if a buffer contains one of the files and isn't saved - (dolist (file modified) - (let ((buffer (get-file-buffer file))) - (when (and buffer (buffer-modified-p buffer)) - (error "Buffer %s is modified. Please kill or save modified buffers before reverting." (buffer-name buffer))))) - (let ((ok (and - (or (not added) - (apply 'git-call-process-display-error "update-index" "--force-remove" "--" added)) - (or (not modified) - (apply 'git-call-process-display-error "checkout" "HEAD" modified)))) - (names (git-get-filenames files))) - (git-update-status-files names) - (when ok - (dolist (file modified) - (let ((buffer (get-file-buffer file))) - (when buffer (with-current-buffer buffer (revert-buffer t t t))))) - (git-success-message "Reverted" names)))))) - -(defun git-remove-handled () - "Remove handled files from the status list." - (interactive) - (ewoc-filter git-status - (lambda (info) - (case (git-fileinfo->state info) - ('ignored git-show-ignored) - ('uptodate git-show-uptodate) - ('unknown git-show-unknown) - (t t)))) - (unless (ewoc-nth git-status 0) ; refresh header if list is empty - (git-refresh-ewoc-hf git-status))) - -(defun git-toggle-show-uptodate () - "Toogle the option for showing up-to-date files." - (interactive) - (if (setq git-show-uptodate (not git-show-uptodate)) - (git-refresh-status) - (git-remove-handled))) - -(defun git-toggle-show-ignored () - "Toogle the option for showing ignored files." - (interactive) - (if (setq git-show-ignored (not git-show-ignored)) - (progn - (message "Inserting ignored files...") - (git-run-ls-files-with-excludes git-status nil 'ignored "-o" "-i") - (git-refresh-files) - (git-refresh-ewoc-hf git-status) - (message "Inserting ignored files...done")) - (git-remove-handled))) - -(defun git-toggle-show-unknown () - "Toogle the option for showing unknown files." - (interactive) - (if (setq git-show-unknown (not git-show-unknown)) - (progn - (message "Inserting unknown files...") - (git-run-ls-files-with-excludes git-status nil 'unknown "-o") - (git-refresh-files) - (git-refresh-ewoc-hf git-status) - (message "Inserting unknown files...done")) - (git-remove-handled))) - -(defun git-expand-directory (info) - "Expand the directory represented by INFO to list its files." - (when (eq (lsh (git-fileinfo->new-perm info) -9) ?\110) - (let ((dir (git-fileinfo->name info))) - (git-set-filenames-state git-status (list dir) nil) - (git-run-ls-files-with-excludes git-status (list (concat dir "/")) 'unknown "-o") - (git-refresh-files) - (git-refresh-ewoc-hf git-status) - t))) - -(defun git-setup-diff-buffer (buffer) - "Setup a buffer for displaying a diff." - (let ((dir default-directory)) - (with-current-buffer buffer - (diff-mode) - (goto-char (point-min)) - (setq default-directory dir) - (setq buffer-read-only t))) - (display-buffer buffer) - ; shrink window only if it displays the status buffer - (when (eq (window-buffer) (current-buffer)) - (shrink-window-if-larger-than-buffer))) - -(defun git-diff-file () - "Diff the marked file(s) against HEAD." - (interactive) - (let ((files (git-marked-files))) - (git-setup-diff-buffer - (apply #'git-run-command-buffer "*git-diff*" "diff-index" "-p" "-M" "HEAD" "--" (git-get-filenames files))))) - -(defun git-diff-file-merge-head (arg) - "Diff the marked file(s) against the first merge head (or the nth one with a numeric prefix)." - (interactive "p") - (let ((files (git-marked-files)) - (merge-heads (git-get-merge-heads))) - (unless merge-heads (error "No merge in progress")) - (git-setup-diff-buffer - (apply #'git-run-command-buffer "*git-diff*" "diff-index" "-p" "-M" - (or (nth (1- arg) merge-heads) "HEAD") "--" (git-get-filenames files))))) - -(defun git-diff-unmerged-file (stage) - "Diff the marked unmerged file(s) against the specified stage." - (let ((files (git-marked-files))) - (git-setup-diff-buffer - (apply #'git-run-command-buffer "*git-diff*" "diff-files" "-p" stage "--" (git-get-filenames files))))) - -(defun git-diff-file-base () - "Diff the marked unmerged file(s) against the common base file." - (interactive) - (git-diff-unmerged-file "-1")) - -(defun git-diff-file-mine () - "Diff the marked unmerged file(s) against my pre-merge version." - (interactive) - (git-diff-unmerged-file "-2")) - -(defun git-diff-file-other () - "Diff the marked unmerged file(s) against the other's pre-merge version." - (interactive) - (git-diff-unmerged-file "-3")) - -(defun git-diff-file-combined () - "Do a combined diff of the marked unmerged file(s)." - (interactive) - (git-diff-unmerged-file "-c")) - -(defun git-diff-file-idiff () - "Perform an interactive diff on the current file." - (interactive) - (let ((files (git-marked-files-state 'added 'deleted 'modified))) - (unless (eq 1 (length files)) - (error "Cannot perform an interactive diff on multiple files.")) - (let* ((filename (car (git-get-filenames files))) - (buff1 (find-file-noselect filename)) - (buff2 (git-run-command-buffer (concat filename ".~HEAD~") "cat-file" "blob" (concat "HEAD:" filename)))) - (ediff-buffers buff1 buff2)))) - -(defun git-log-file () - "Display a log of changes to the marked file(s)." - (interactive) - (let* ((files (git-marked-files)) - (coding-system-for-read git-commits-coding-system) - (buffer (apply #'git-run-command-buffer "*git-log*" "rev-list" "--pretty" "HEAD" "--" (git-get-filenames files)))) - (with-current-buffer buffer - ; (git-log-mode) FIXME: implement log mode - (goto-char (point-min)) - (setq buffer-read-only t)) - (display-buffer buffer))) - -(defun git-log-edit-files () - "Return a list of marked files for use in the log-edit buffer." - (with-current-buffer log-edit-parent-buffer - (git-get-filenames (git-marked-files-state 'added 'deleted 'modified)))) - -(defun git-log-edit-diff () - "Run a diff of the current files being committed from a log-edit buffer." - (with-current-buffer log-edit-parent-buffer - (git-diff-file))) - -(defun git-append-sign-off (name email) - "Append a Signed-off-by entry to the current buffer, avoiding duplicates." - (let ((sign-off (format "Signed-off-by: %s <%s>" name email)) - (case-fold-search t)) - (goto-char (point-min)) - (unless (re-search-forward (concat "^" (regexp-quote sign-off)) nil t) - (goto-char (point-min)) - (unless (re-search-forward "^Signed-off-by: " nil t) - (setq sign-off (concat "\n" sign-off))) - (goto-char (point-max)) - (insert sign-off "\n")))) - -(defun git-setup-log-buffer (buffer &optional merge-heads author-name author-email subject date msg) - "Setup the log buffer for a commit." - (unless git-status (error "Not in git-status buffer.")) - (let ((dir default-directory) - (committer-name (git-get-committer-name)) - (committer-email (git-get-committer-email)) - (sign-off git-append-signed-off-by)) - (with-current-buffer buffer - (cd dir) - (erase-buffer) - (insert - (propertize - (format "Author: %s <%s>\n%s%s" - (or author-name committer-name) - (or author-email committer-email) - (if date (format "Date: %s\n" date) "") - (if merge-heads - (format "Merge: %s\n" - (mapconcat 'identity merge-heads " ")) - "")) - 'face 'git-header-face) - (propertize git-log-msg-separator 'face 'git-separator-face) - "\n") - (when subject (insert subject "\n\n")) - (cond (msg (insert msg "\n")) - ((file-readable-p ".git/rebase-apply/msg") - (insert-file-contents ".git/rebase-apply/msg")) - ((file-readable-p ".git/MERGE_MSG") - (insert-file-contents ".git/MERGE_MSG"))) - ; delete empty lines at end - (goto-char (point-min)) - (when (re-search-forward "\n+\\'" nil t) - (replace-match "\n" t t)) - (when sign-off (git-append-sign-off committer-name committer-email))) - buffer)) - -(define-derived-mode git-log-edit-mode log-edit-mode "Git-Log-Edit" - "Major mode for editing git log messages. - -Set up git-specific `font-lock-keywords' for `log-edit-mode'." - (set (make-local-variable 'font-lock-defaults) - '(git-log-edit-font-lock-keywords t t))) - -(defun git-commit-file () - "Commit the marked file(s), asking for a commit message." - (interactive) - (unless git-status (error "Not in git-status buffer.")) - (when (git-run-pre-commit-hook) - (let ((buffer (get-buffer-create "*git-commit*")) - (coding-system (git-get-commits-coding-system)) - author-name author-email subject date) - (when (eq 0 (buffer-size buffer)) - (when (file-readable-p ".git/rebase-apply/info") - (with-temp-buffer - (insert-file-contents ".git/rebase-apply/info") - (goto-char (point-min)) - (when (re-search-forward "^Author: \\(.*\\)\nEmail: \\(.*\\)$" nil t) - (setq author-name (match-string 1)) - (setq author-email (match-string 2))) - (goto-char (point-min)) - (when (re-search-forward "^Subject: \\(.*\\)$" nil t) - (setq subject (match-string 1))) - (goto-char (point-min)) - (when (re-search-forward "^Date: \\(.*\\)$" nil t) - (setq date (match-string 1))))) - (git-setup-log-buffer buffer (git-get-merge-heads) author-name author-email subject date)) - (if (boundp 'log-edit-diff-function) - (log-edit 'git-do-commit nil '((log-edit-listfun . git-log-edit-files) - (log-edit-diff-function . git-log-edit-diff)) buffer 'git-log-edit-mode) - (log-edit 'git-do-commit nil 'git-log-edit-files buffer - 'git-log-edit-mode)) - (setq paragraph-separate (concat (regexp-quote git-log-msg-separator) "$\\|Author: \\|Date: \\|Merge: \\|Signed-off-by: \\|\f\\|[ ]*$")) - (setq buffer-file-coding-system coding-system) - (re-search-forward (regexp-quote (concat git-log-msg-separator "\n")) nil t)))) - -(defun git-setup-commit-buffer (commit) - "Setup the commit buffer with the contents of COMMIT." - (let (parents author-name author-email subject date msg) - (with-temp-buffer - (let ((coding-system (git-get-logoutput-coding-system))) - (git-call-process t "log" "-1" "--pretty=medium" "--abbrev=40" commit) - (goto-char (point-min)) - (when (re-search-forward "^Merge: *\\(.*\\)$" nil t) - (setq parents (cdr (split-string (match-string 1) " +")))) - (when (re-search-forward "^Author: *\\(.*\\) <\\(.*\\)>$" nil t) - (setq author-name (match-string 1)) - (setq author-email (match-string 2))) - (when (re-search-forward "^Date: *\\(.*\\)$" nil t) - (setq date (match-string 1))) - (while (re-search-forward "^ \\(.*\\)$" nil t) - (push (match-string 1) msg)) - (setq msg (nreverse msg)) - (setq subject (pop msg)) - (while (and msg (zerop (length (car msg))) (pop msg))))) - (git-setup-log-buffer (get-buffer-create "*git-commit*") - parents author-name author-email subject date - (mapconcat #'identity msg "\n")))) - -(defun git-get-commit-files (commit) - "Retrieve a sorted list of files modified by COMMIT." - (let (files) - (with-temp-buffer - (git-call-process t "diff-tree" "-m" "-r" "-z" "--name-only" "--no-commit-id" "--root" commit) - (goto-char (point-min)) - (while (re-search-forward "\\([^\0]*\\)\0" nil t 1) - (push (match-string 1) files))) - (sort files #'string-lessp))) - -(defun git-read-commit-name (prompt &optional default) - "Ask for a commit name, with completion for local branch, remote branch and tag." - (completing-read prompt - (list* "HEAD" "ORIG_HEAD" "FETCH_HEAD" (mapcar #'car (git-for-each-ref))) - nil nil nil nil default)) - -(defun git-checkout (branch &optional merge) - "Checkout a branch, tag, or any commit. -Use a prefix arg if git should merge while checking out." - (interactive - (list (git-read-commit-name "Checkout: ") - current-prefix-arg)) - (unless git-status (error "Not in git-status buffer.")) - (let ((args (list branch "--"))) - (when merge (push "-m" args)) - (when (apply #'git-call-process-display-error "checkout" args) - (git-update-status-files)))) - -(defun git-branch (branch) - "Create a branch from the current HEAD and switch to it." - (interactive (list (git-read-commit-name "Branch: "))) - (unless git-status (error "Not in git-status buffer.")) - (if (git-rev-parse (concat "refs/heads/" branch)) - (if (yes-or-no-p (format "Branch %s already exists, replace it? " branch)) - (and (git-call-process-display-error "branch" "-f" branch) - (git-call-process-display-error "checkout" branch)) - (message "Canceled.")) - (git-call-process-display-error "checkout" "-b" branch)) - (git-refresh-ewoc-hf git-status)) - -(defun git-amend-commit () - "Undo the last commit on HEAD, and set things up to commit an -amended version of it." - (interactive) - (unless git-status (error "Not in git-status buffer.")) - (when (git-empty-db-p) (error "No commit to amend.")) - (let* ((commit (git-rev-parse "HEAD")) - (files (git-get-commit-files commit))) - (when (if (git-rev-parse "HEAD^") - (git-call-process-display-error "reset" "--soft" "HEAD^") - (and (git-update-ref "ORIG_HEAD" commit) - (git-update-ref "HEAD" nil commit))) - (git-update-status-files files t) - (git-setup-commit-buffer commit) - (git-commit-file)))) - -(defun git-cherry-pick-commit (arg) - "Cherry-pick a commit." - (interactive (list (git-read-commit-name "Cherry-pick commit: "))) - (unless git-status (error "Not in git-status buffer.")) - (let ((commit (git-rev-parse (concat arg "^0")))) - (unless commit (error "Not a valid commit '%s'." arg)) - (when (git-rev-parse (concat commit "^2")) - (error "Cannot cherry-pick a merge commit.")) - (let ((files (git-get-commit-files commit)) - (ok (git-call-process-display-error "cherry-pick" "-n" commit))) - (git-update-status-files files ok) - (with-current-buffer (git-setup-commit-buffer commit) - (goto-char (point-min)) - (if (re-search-forward "^\n*Signed-off-by:" nil t 1) - (goto-char (match-beginning 0)) - (goto-char (point-max))) - (insert "(cherry picked from commit " commit ")\n")) - (when ok (git-commit-file))))) - -(defun git-revert-commit (arg) - "Revert a commit." - (interactive (list (git-read-commit-name "Revert commit: "))) - (unless git-status (error "Not in git-status buffer.")) - (let ((commit (git-rev-parse (concat arg "^0")))) - (unless commit (error "Not a valid commit '%s'." arg)) - (when (git-rev-parse (concat commit "^2")) - (error "Cannot revert a merge commit.")) - (let ((files (git-get-commit-files commit)) - (subject (git-get-commit-description commit)) - (ok (git-call-process-display-error "revert" "-n" commit))) - (git-update-status-files files ok) - (when (string-match "^[0-9a-f]+ - \\(.*\\)$" subject) - (setq subject (match-string 1 subject))) - (git-setup-log-buffer (get-buffer-create "*git-commit*") - (git-get-merge-heads) nil nil (format "Revert \"%s\"" subject) nil - (format "This reverts commit %s.\n" commit)) - (when ok (git-commit-file))))) - -(defun git-find-file () - "Visit the current file in its own buffer." - (interactive) - (unless git-status (error "Not in git-status buffer.")) - (let ((info (ewoc-data (ewoc-locate git-status)))) - (unless (git-expand-directory info) - (find-file (git-fileinfo->name info)) - (when (eq 'unmerged (git-fileinfo->state info)) - (smerge-mode 1))))) - -(defun git-find-file-other-window () - "Visit the current file in its own buffer in another window." - (interactive) - (unless git-status (error "Not in git-status buffer.")) - (let ((info (ewoc-data (ewoc-locate git-status)))) - (find-file-other-window (git-fileinfo->name info)) - (when (eq 'unmerged (git-fileinfo->state info)) - (smerge-mode)))) - -(defun git-find-file-imerge () - "Visit the current file in interactive merge mode." - (interactive) - (unless git-status (error "Not in git-status buffer.")) - (let ((info (ewoc-data (ewoc-locate git-status)))) - (find-file (git-fileinfo->name info)) - (smerge-ediff))) - -(defun git-view-file () - "View the current file in its own buffer." - (interactive) - (unless git-status (error "Not in git-status buffer.")) - (let ((info (ewoc-data (ewoc-locate git-status)))) - (view-file (git-fileinfo->name info)))) - -(defun git-refresh-status () - "Refresh the git status buffer." - (interactive) - (unless git-status (error "Not in git-status buffer.")) - (message "Refreshing git status...") - (git-update-status-files) - (message "Refreshing git status...done")) - -(defun git-status-quit () - "Quit git-status mode." - (interactive) - (bury-buffer)) - -;;;; Major Mode -;;;; ------------------------------------------------------------ - -(defvar git-status-mode-hook nil - "Run after `git-status-mode' is setup.") - -(defvar git-status-mode-map nil - "Keymap for git major mode.") - -(defvar git-status nil - "List of all files managed by the git-status mode.") - -(unless git-status-mode-map - (let ((map (make-keymap)) - (commit-map (make-sparse-keymap)) - (diff-map (make-sparse-keymap)) - (toggle-map (make-sparse-keymap))) - (suppress-keymap map) - (define-key map "?" 'git-help) - (define-key map "h" 'git-help) - (define-key map " " 'git-next-file) - (define-key map "a" 'git-add-file) - (define-key map "c" 'git-commit-file) - (define-key map "\C-c" commit-map) - (define-key map "d" diff-map) - (define-key map "=" 'git-diff-file) - (define-key map "f" 'git-find-file) - (define-key map "\r" 'git-find-file) - (define-key map "g" 'git-refresh-status) - (define-key map "i" 'git-ignore-file) - (define-key map "I" 'git-insert-file) - (define-key map "l" 'git-log-file) - (define-key map "m" 'git-mark-file) - (define-key map "M" 'git-mark-all) - (define-key map "n" 'git-next-file) - (define-key map "N" 'git-next-unmerged-file) - (define-key map "o" 'git-find-file-other-window) - (define-key map "p" 'git-prev-file) - (define-key map "P" 'git-prev-unmerged-file) - (define-key map "q" 'git-status-quit) - (define-key map "r" 'git-remove-file) - (define-key map "t" toggle-map) - (define-key map "T" 'git-toggle-all-marks) - (define-key map "u" 'git-unmark-file) - (define-key map "U" 'git-revert-file) - (define-key map "v" 'git-view-file) - (define-key map "x" 'git-remove-handled) - (define-key map "\C-?" 'git-unmark-file-up) - (define-key map "\M-\C-?" 'git-unmark-all) - ; the commit submap - (define-key commit-map "\C-a" 'git-amend-commit) - (define-key commit-map "\C-b" 'git-branch) - (define-key commit-map "\C-o" 'git-checkout) - (define-key commit-map "\C-p" 'git-cherry-pick-commit) - (define-key commit-map "\C-v" 'git-revert-commit) - ; the diff submap - (define-key diff-map "b" 'git-diff-file-base) - (define-key diff-map "c" 'git-diff-file-combined) - (define-key diff-map "=" 'git-diff-file) - (define-key diff-map "e" 'git-diff-file-idiff) - (define-key diff-map "E" 'git-find-file-imerge) - (define-key diff-map "h" 'git-diff-file-merge-head) - (define-key diff-map "m" 'git-diff-file-mine) - (define-key diff-map "o" 'git-diff-file-other) - ; the toggle submap - (define-key toggle-map "u" 'git-toggle-show-uptodate) - (define-key toggle-map "i" 'git-toggle-show-ignored) - (define-key toggle-map "k" 'git-toggle-show-unknown) - (define-key toggle-map "m" 'git-toggle-all-marks) - (setq git-status-mode-map map)) - (easy-menu-define git-menu git-status-mode-map - "Git Menu" - `("Git" - ["Refresh" git-refresh-status t] - ["Commit" git-commit-file t] - ["Checkout..." git-checkout t] - ["New Branch..." git-branch t] - ["Cherry-pick Commit..." git-cherry-pick-commit t] - ["Revert Commit..." git-revert-commit t] - ("Merge" - ["Next Unmerged File" git-next-unmerged-file t] - ["Prev Unmerged File" git-prev-unmerged-file t] - ["Interactive Merge File" git-find-file-imerge t] - ["Diff Against Common Base File" git-diff-file-base t] - ["Diff Combined" git-diff-file-combined t] - ["Diff Against Merge Head" git-diff-file-merge-head t] - ["Diff Against Mine" git-diff-file-mine t] - ["Diff Against Other" git-diff-file-other t]) - "--------" - ["Add File" git-add-file t] - ["Revert File" git-revert-file t] - ["Ignore File" git-ignore-file t] - ["Remove File" git-remove-file t] - ["Insert File" git-insert-file t] - "--------" - ["Find File" git-find-file t] - ["View File" git-view-file t] - ["Diff File" git-diff-file t] - ["Interactive Diff File" git-diff-file-idiff t] - ["Log" git-log-file t] - "--------" - ["Mark" git-mark-file t] - ["Mark All" git-mark-all t] - ["Unmark" git-unmark-file t] - ["Unmark All" git-unmark-all t] - ["Toggle All Marks" git-toggle-all-marks t] - ["Hide Handled Files" git-remove-handled t] - "--------" - ["Show Uptodate Files" git-toggle-show-uptodate :style toggle :selected git-show-uptodate] - ["Show Ignored Files" git-toggle-show-ignored :style toggle :selected git-show-ignored] - ["Show Unknown Files" git-toggle-show-unknown :style toggle :selected git-show-unknown] - "--------" - ["Quit" git-status-quit t]))) - - -;; git mode should only run in the *git status* buffer -(put 'git-status-mode 'mode-class 'special) - -(defun git-status-mode () - "Major mode for interacting with Git. -Commands: -\\{git-status-mode-map}" - (kill-all-local-variables) - (buffer-disable-undo) - (setq mode-name "git status" - major-mode 'git-status-mode - goal-column 17 - buffer-read-only t) - (use-local-map git-status-mode-map) - (let ((buffer-read-only nil)) - (erase-buffer) - (let ((status (ewoc-create 'git-fileinfo-prettyprint "" ""))) - (set (make-local-variable 'git-status) status)) - (set (make-local-variable 'list-buffers-directory) default-directory) - (make-local-variable 'git-show-uptodate) - (make-local-variable 'git-show-ignored) - (make-local-variable 'git-show-unknown) - (run-hooks 'git-status-mode-hook))) - -(defun git-find-status-buffer (dir) - "Find the git status buffer handling a specified directory." - (let ((list (buffer-list)) - (fulldir (expand-file-name dir)) - found) - (while (and list (not found)) - (let ((buffer (car list))) - (with-current-buffer buffer - (when (and list-buffers-directory - (string-equal fulldir (expand-file-name list-buffers-directory)) - (eq major-mode 'git-status-mode)) - (setq found buffer)))) - (setq list (cdr list))) - found)) - -(defun git-status (dir) - "Entry point into git-status mode." - (interactive "DSelect directory: ") - (setq dir (git-get-top-dir dir)) - (if (file-exists-p (concat (file-name-as-directory dir) ".git")) - (let ((buffer (or (and git-reuse-status-buffer (git-find-status-buffer dir)) - (create-file-buffer (expand-file-name "*git-status*" dir))))) - (switch-to-buffer buffer) - (cd dir) - (git-status-mode) - (git-refresh-status) - (goto-char (point-min)) - (add-hook 'after-save-hook 'git-update-saved-file)) - (message "%s is not a git working tree." dir))) - -(defun git-update-saved-file () - "Update the corresponding git-status buffer when a file is saved. -Meant to be used in `after-save-hook'." - (let* ((file (expand-file-name buffer-file-name)) - (dir (condition-case nil (git-get-top-dir (file-name-directory file)) (error nil))) - (buffer (and dir (git-find-status-buffer dir)))) - (when buffer - (with-current-buffer buffer - (let ((filename (file-relative-name file dir))) - ; skip files located inside the .git directory - (unless (string-match "^\\.git/" filename) - (git-call-process nil "add" "--refresh" "--" filename) - (git-update-status-files (list filename)))))))) - -(defun git-help () - "Display help for Git mode." - (interactive) - (describe-function 'git-status-mode)) - -(provide 'git) -;;; git.el ends here +(error "git.el no longer ships with git. It's recommended to +replace its use with Magit, or simply delete references to git.el +in your initialization file(s). See contrib/emacs/README in git's +sources (https://github.com/git/git/blob/master/contrib/emacs/README) +for suggested alternatives and for why this happened. Emacs's own +VC mode and Magit are viable alternatives.") diff --git a/contrib/mw-to-git/Makefile b/contrib/mw-to-git/Makefile index a4b6f7a2cd..4e603512a3 100644 --- a/contrib/mw-to-git/Makefile +++ b/contrib/mw-to-git/Makefile @@ -21,8 +21,9 @@ HERE=contrib/mw-to-git/ INSTALL = install SCRIPT_PERL_FULL=$(patsubst %,$(HERE)/%,$(SCRIPT_PERL)) -INSTLIBDIR=$(shell $(MAKE) -C $(GIT_ROOT_DIR)/perl \ - -s --no-print-directory instlibdir) +INSTLIBDIR=$(shell $(MAKE) -C $(GIT_ROOT_DIR)/ \ + -s --no-print-directory prefix=$(prefix) \ + perllibdir=$(perllibdir) perllibdir) DESTDIR_SQ = $(subst ','\'',$(DESTDIR)) INSTLIBDIR_SQ = $(subst ','\'',$(INSTLIBDIR)) @@ -7,6 +7,7 @@ #include "sigchain.h" #include "pkt-line.h" #include "sub-process.h" +#include "utf8.h" /* * convert.c - convert a file when checking it out and checking it in. @@ -265,6 +266,241 @@ static int will_convert_lf_to_crlf(size_t len, struct text_stat *stats, } +static int validate_encoding(const char *path, const char *enc, + const char *data, size_t len, int die_on_error) +{ + /* We only check for UTF here as UTF?? can be an alias for UTF-?? */ + if (istarts_with(enc, "UTF")) { + /* + * Check for detectable errors in UTF encodings + */ + if (has_prohibited_utf_bom(enc, data, len)) { + const char *error_msg = _( + "BOM is prohibited in '%s' if encoded as %s"); + /* + * This advice is shown for UTF-??BE and UTF-??LE encodings. + * We cut off the last two characters of the encoding name + * to generate the encoding name suitable for BOMs. + */ + const char *advise_msg = _( + "The file '%s' contains a byte order " + "mark (BOM). Please use UTF-%s as " + "working-tree-encoding."); + const char *stripped = NULL; + char *upper = xstrdup_toupper(enc); + upper[strlen(upper)-2] = '\0'; + if (!skip_prefix(upper, "UTF-", &stripped)) + skip_prefix(stripped, "UTF", &stripped); + advise(advise_msg, path, stripped); + free(upper); + if (die_on_error) + die(error_msg, path, enc); + else { + return error(error_msg, path, enc); + } + + } else if (is_missing_required_utf_bom(enc, data, len)) { + const char *error_msg = _( + "BOM is required in '%s' if encoded as %s"); + const char *advise_msg = _( + "The file '%s' is missing a byte order " + "mark (BOM). Please use UTF-%sBE or UTF-%sLE " + "(depending on the byte order) as " + "working-tree-encoding."); + const char *stripped = NULL; + char *upper = xstrdup_toupper(enc); + if (!skip_prefix(upper, "UTF-", &stripped)) + skip_prefix(stripped, "UTF", &stripped); + advise(advise_msg, path, stripped, stripped); + free(upper); + if (die_on_error) + die(error_msg, path, enc); + else { + return error(error_msg, path, enc); + } + } + + } + return 0; +} + +static void trace_encoding(const char *context, const char *path, + const char *encoding, const char *buf, size_t len) +{ + static struct trace_key coe = TRACE_KEY_INIT(WORKING_TREE_ENCODING); + struct strbuf trace = STRBUF_INIT; + int i; + + strbuf_addf(&trace, "%s (%s, considered %s):\n", context, path, encoding); + for (i = 0; i < len && buf; ++i) { + strbuf_addf( + &trace,"| \e[2m%2i:\e[0m %2x \e[2m%c\e[0m%c", + i, + (unsigned char) buf[i], + (buf[i] > 32 && buf[i] < 127 ? buf[i] : ' '), + ((i+1) % 8 && (i+1) < len ? ' ' : '\n') + ); + } + strbuf_addchars(&trace, '\n', 1); + + trace_strbuf(&coe, &trace); + strbuf_release(&trace); +} + +static int check_roundtrip(const char *enc_name) +{ + /* + * check_roundtrip_encoding contains a string of comma and/or + * space separated encodings (eg. "UTF-16, ASCII, CP1125"). + * Search for the given encoding in that string. + */ + const char *found = strcasestr(check_roundtrip_encoding, enc_name); + const char *next; + int len; + if (!found) + return 0; + next = found + strlen(enc_name); + len = strlen(check_roundtrip_encoding); + return (found && ( + /* + * check that the found encoding is at the + * beginning of check_roundtrip_encoding or + * that it is prefixed with a space or comma + */ + found == check_roundtrip_encoding || ( + (isspace(found[-1]) || found[-1] == ',') + ) + ) && ( + /* + * check that the found encoding is at the + * end of check_roundtrip_encoding or + * that it is suffixed with a space or comma + */ + next == check_roundtrip_encoding + len || ( + next < check_roundtrip_encoding + len && + (isspace(next[0]) || next[0] == ',') + ) + )); +} + +static const char *default_encoding = "UTF-8"; + +static int encode_to_git(const char *path, const char *src, size_t src_len, + struct strbuf *buf, const char *enc, int conv_flags) +{ + char *dst; + int dst_len; + int die_on_error = conv_flags & CONV_WRITE_OBJECT; + + /* + * No encoding is specified or there is nothing to encode. + * Tell the caller that the content was not modified. + */ + if (!enc || (src && !src_len)) + return 0; + + /* + * Looks like we got called from "would_convert_to_git()". + * This means Git wants to know if it would encode (= modify!) + * the content. Let's answer with "yes", since an encoding was + * specified. + */ + if (!buf && !src) + return 1; + + if (validate_encoding(path, enc, src, src_len, die_on_error)) + return 0; + + trace_encoding("source", path, enc, src, src_len); + dst = reencode_string_len(src, src_len, default_encoding, enc, + &dst_len); + if (!dst) { + /* + * We could add the blob "as-is" to Git. However, on checkout + * we would try to reencode to the original encoding. This + * would fail and we would leave the user with a messed-up + * working tree. Let's try to avoid this by screaming loud. + */ + const char* msg = _("failed to encode '%s' from %s to %s"); + if (die_on_error) + die(msg, path, enc, default_encoding); + else { + error(msg, path, enc, default_encoding); + return 0; + } + } + trace_encoding("destination", path, default_encoding, dst, dst_len); + + /* + * UTF supports lossless conversion round tripping [1] and conversions + * between UTF and other encodings are mostly round trip safe as + * Unicode aims to be a superset of all other character encodings. + * However, certain encodings (e.g. SHIFT-JIS) are known to have round + * trip issues [2]. Check the round trip conversion for all encodings + * listed in core.checkRoundtripEncoding. + * + * The round trip check is only performed if content is written to Git. + * This ensures that no information is lost during conversion to/from + * the internal UTF-8 representation. + * + * Please note, the code below is not tested because I was not able to + * generate a faulty round trip without an iconv error. Iconv errors + * are already caught above. + * + * [1] http://unicode.org/faq/utf_bom.html#gen2 + * [2] https://support.microsoft.com/en-us/help/170559/prb-conversion-problem-between-shift-jis-and-unicode + */ + if (die_on_error && check_roundtrip(enc)) { + char *re_src; + int re_src_len; + + re_src = reencode_string_len(dst, dst_len, + enc, default_encoding, + &re_src_len); + + trace_printf("Checking roundtrip encoding for %s...\n", enc); + trace_encoding("reencoded source", path, enc, + re_src, re_src_len); + + if (!re_src || src_len != re_src_len || + memcmp(src, re_src, src_len)) { + const char* msg = _("encoding '%s' from %s to %s and " + "back is not the same"); + die(msg, path, enc, default_encoding); + } + + free(re_src); + } + + strbuf_attach(buf, dst, dst_len, dst_len + 1); + return 1; +} + +static int encode_to_worktree(const char *path, const char *src, size_t src_len, + struct strbuf *buf, const char *enc) +{ + char *dst; + int dst_len; + + /* + * No encoding is specified or there is nothing to encode. + * Tell the caller that the content was not modified. + */ + if (!enc || (src && !src_len)) + return 0; + + dst = reencode_string_len(src, src_len, enc, default_encoding, + &dst_len); + if (!dst) { + error("failed to encode '%s' from %s to %s", + path, default_encoding, enc); + return 0; + } + + strbuf_attach(buf, dst, dst_len, dst_len + 1); + return 1; +} + static int crlf_to_git(const struct index_state *istate, const char *path, const char *src, size_t len, struct strbuf *buf, @@ -978,6 +1214,24 @@ static int ident_to_worktree(const char *path, const char *src, size_t len, return 1; } +static const char *git_path_check_encoding(struct attr_check_item *check) +{ + const char *value = check->value; + + if (ATTR_UNSET(value) || !strlen(value)) + return NULL; + + if (ATTR_TRUE(value) || ATTR_FALSE(value)) { + die(_("true/false are no valid working-tree-encodings")); + } + + /* Don't encode to the default encoding */ + if (same_encoding(value, default_encoding)) + return NULL; + + return value; +} + static enum crlf_action git_path_check_crlf(struct attr_check_item *check) { const char *value = check->value; @@ -1033,6 +1287,7 @@ struct conv_attrs { enum crlf_action attr_action; /* What attr says */ enum crlf_action crlf_action; /* When no attr is set, use core.autocrlf */ int ident; + const char *working_tree_encoding; /* Supported encoding or default encoding if NULL */ }; static void convert_attrs(struct conv_attrs *ca, const char *path) @@ -1041,7 +1296,8 @@ static void convert_attrs(struct conv_attrs *ca, const char *path) if (!check) { check = attr_check_initl("crlf", "ident", "filter", - "eol", "text", NULL); + "eol", "text", "working-tree-encoding", + NULL); user_convert_tail = &user_convert; git_config(read_convert_config, NULL); } @@ -1064,6 +1320,7 @@ static void convert_attrs(struct conv_attrs *ca, const char *path) else if (eol_attr == EOL_CRLF) ca->crlf_action = CRLF_TEXT_CRLF; } + ca->working_tree_encoding = git_path_check_encoding(ccheck + 5); } else { ca->drv = NULL; ca->crlf_action = CRLF_UNDEFINED; @@ -1144,6 +1401,13 @@ int convert_to_git(const struct index_state *istate, src = dst->buf; len = dst->len; } + + ret |= encode_to_git(path, src, len, dst, ca.working_tree_encoding, conv_flags); + if (ret && dst) { + src = dst->buf; + len = dst->len; + } + if (!(conv_flags & CONV_EOL_KEEP_CRLF)) { ret |= crlf_to_git(istate, path, src, len, dst, ca.crlf_action, conv_flags); if (ret && dst) { @@ -1167,6 +1431,7 @@ void convert_to_git_filter_fd(const struct index_state *istate, if (!apply_filter(path, NULL, 0, fd, dst, ca.drv, CAP_CLEAN, NULL)) die("%s: clean filter '%s' failed", path, ca.drv->name); + encode_to_git(path, dst->buf, dst->len, dst, ca.working_tree_encoding, conv_flags); crlf_to_git(istate, path, dst->buf, dst->len, dst, ca.crlf_action, conv_flags); ident_to_git(path, dst->buf, dst->len, dst, ca.ident); } @@ -1198,6 +1463,12 @@ static int convert_to_working_tree_internal(const char *path, const char *src, } } + ret |= encode_to_worktree(path, src, len, dst, ca.working_tree_encoding); + if (ret) { + src = dst->buf; + len = dst->len; + } + ret_filter = apply_filter( path, src, len, -1, dst, ca.drv, CAP_SMUDGE, dco); if (!ret_filter && ca.drv && ca.drv->required) @@ -1664,6 +1935,9 @@ struct stream_filter *get_stream_filter(const char *path, const struct object_id if (ca.drv && (ca.drv->process || ca.drv->smudge || ca.drv->clean)) return NULL; + if (ca.working_tree_encoding) + return NULL; + if (ca.crlf_action == CRLF_AUTO || ca.crlf_action == CRLF_AUTO_CRLF) return NULL; @@ -12,6 +12,7 @@ struct index_state; #define CONV_EOL_RNDTRP_WARN (1<<1) /* Warn if CRLF to LF to CRLF is different */ #define CONV_EOL_RENORMALIZE (1<<2) /* Convert CRLF to LF */ #define CONV_EOL_KEEP_CRLF (1<<3) /* Keep CRLF line endings as is */ +#define CONV_WRITE_OBJECT (1<<4) /* Content is written to the index */ extern int global_conv_flags_eol; @@ -55,6 +56,7 @@ struct delayed_checkout { }; extern enum eol core_eol; +extern char *check_roundtrip_encoding; extern const char *get_cached_convert_stats_ascii(const struct index_state *istate, const char *path); extern const char *get_wt_convert_stats_ascii(const char *path); diff --git a/csum-file.c b/csum-file.c index 5eda7fb6af..53ce37f7ca 100644 --- a/csum-file.c +++ b/csum-file.c @@ -53,7 +53,7 @@ void hashflush(struct hashfile *f) } } -int hashclose(struct hashfile *f, unsigned char *result, unsigned int flags) +int finalize_hashfile(struct hashfile *f, unsigned char *result, unsigned int flags) { int fd; @@ -61,11 +61,11 @@ int hashclose(struct hashfile *f, unsigned char *result, unsigned int flags) the_hash_algo->final_fn(f->buffer, &f->ctx); if (result) hashcpy(result, f->buffer); - if (flags & (CSUM_CLOSE | CSUM_FSYNC)) { - /* write checksum and close fd */ + if (flags & CSUM_HASH_IN_STREAM) flush(f, f->buffer, the_hash_algo->rawsz); - if (flags & CSUM_FSYNC) - fsync_or_die(f->fd, f->name); + if (flags & CSUM_FSYNC) + fsync_or_die(f->fd, f->name); + if (flags & CSUM_CLOSE) { if (close(f->fd)) die_errno("%s: sha1 file error on close", f->name); fd = 0; diff --git a/csum-file.h b/csum-file.h index 992e5c0141..c5a2e335e7 100644 --- a/csum-file.h +++ b/csum-file.h @@ -26,14 +26,15 @@ struct hashfile_checkpoint { extern void hashfile_checkpoint(struct hashfile *, struct hashfile_checkpoint *); extern int hashfile_truncate(struct hashfile *, struct hashfile_checkpoint *); -/* hashclose flags */ -#define CSUM_CLOSE 1 -#define CSUM_FSYNC 2 +/* finalize_hashfile flags */ +#define CSUM_CLOSE 1 +#define CSUM_FSYNC 2 +#define CSUM_HASH_IN_STREAM 4 extern struct hashfile *hashfd(int fd, const char *name); extern struct hashfile *hashfd_check(const char *name); extern struct hashfile *hashfd_throughput(int fd, const char *name, struct progress *tp); -extern int hashclose(struct hashfile *, unsigned char *, unsigned int); +extern int finalize_hashfile(struct hashfile *, unsigned char *, unsigned int); extern void hashwrite(struct hashfile *, const void *, unsigned int); extern void hashflush(struct hashfile *f); extern void crc32_begin(struct hashfile *); diff --git a/detect-compiler b/detect-compiler new file mode 100755 index 0000000000..70b754481c --- /dev/null +++ b/detect-compiler @@ -0,0 +1,53 @@ +#!/bin/sh +# +# Probe the compiler for vintage, version, etc. This is used for setting +# optional make knobs under the DEVELOPER knob. + +CC="$*" + +# we get something like (this is at least true for gcc and clang) +# +# FreeBSD clang version 3.4.1 (tags/RELEASE...) +get_version_line() { + $CC -v 2>&1 | grep ' version ' +} + +get_family() { + get_version_line | sed 's/^\(.*\) version [0-9][^ ]* .*/\1/' +} + +get_version() { + get_version_line | sed 's/^.* version \([0-9][^ ]*\) .*/\1/' +} + +print_flags() { + family=$1 + version=$(get_version | cut -f 1 -d .) + + # Print a feature flag not only for the current version, but also + # for any prior versions we encompass. This avoids needing to do + # numeric comparisons in make, which are awkward. + while test "$version" -gt 0 + do + echo $family$version + version=$((version - 1)) + done +} + +case "$(get_family)" in +gcc) + print_flags gcc + ;; +clang) + print_flags clang + ;; +"FreeBSD clang") + print_flags clang + ;; +"Apple LLVM") + print_flags clang + ;; +*) + : unknown compiler family + ;; +esac @@ -3638,7 +3638,8 @@ int diff_populate_filespec(struct diff_filespec *s, unsigned int flags) else { enum object_type type; if (size_only || (flags & CHECK_BINARY)) { - type = oid_object_info(&s->oid, &s->size); + type = oid_object_info(the_repository, &s->oid, + &s->size); if (type < 0) die("unable to read %s", oid_to_hex(&s->oid)); @@ -19,6 +19,7 @@ #include "varint.h" #include "ewah/ewok.h" #include "fsmonitor.h" +#include "submodule-config.h" /* * Tells read_directory_recursive how a file or directory should be treated. @@ -3010,8 +3011,57 @@ void untracked_cache_add_to_index(struct index_state *istate, untracked_cache_invalidate_path(istate, path, 1); } -/* Update gitfile and core.worktree setting to connect work tree and git dir */ -void connect_work_tree_and_git_dir(const char *work_tree_, const char *git_dir_) +static void connect_wt_gitdir_in_nested(const char *sub_worktree, + const char *sub_gitdir) +{ + int i; + struct repository subrepo; + struct strbuf sub_wt = STRBUF_INIT; + struct strbuf sub_gd = STRBUF_INIT; + + const struct submodule *sub; + + /* If the submodule has no working tree, we can ignore it. */ + if (repo_init(&subrepo, sub_gitdir, sub_worktree)) + return; + + if (repo_read_index(&subrepo) < 0) + die("index file corrupt in repo %s", subrepo.gitdir); + + for (i = 0; i < subrepo.index->cache_nr; i++) { + const struct cache_entry *ce = subrepo.index->cache[i]; + + if (!S_ISGITLINK(ce->ce_mode)) + continue; + + while (i + 1 < subrepo.index->cache_nr && + !strcmp(ce->name, subrepo.index->cache[i + 1]->name)) + /* + * Skip entries with the same name in different stages + * to make sure an entry is returned only once. + */ + i++; + + sub = submodule_from_path(&subrepo, &null_oid, ce->name); + if (!sub || !is_submodule_active(&subrepo, ce->name)) + /* .gitmodules broken or inactive sub */ + continue; + + strbuf_reset(&sub_wt); + strbuf_reset(&sub_gd); + strbuf_addf(&sub_wt, "%s/%s", sub_worktree, sub->path); + strbuf_addf(&sub_gd, "%s/modules/%s", sub_gitdir, sub->name); + + connect_work_tree_and_git_dir(sub_wt.buf, sub_gd.buf, 1); + } + strbuf_release(&sub_wt); + strbuf_release(&sub_gd); + repo_clear(&subrepo); +} + +void connect_work_tree_and_git_dir(const char *work_tree_, + const char *git_dir_, + int recurse_into_nested) { struct strbuf gitfile_sb = STRBUF_INIT; struct strbuf cfg_sb = STRBUF_INIT; @@ -3041,6 +3091,10 @@ void connect_work_tree_and_git_dir(const char *work_tree_, const char *git_dir_) strbuf_release(&gitfile_sb); strbuf_release(&cfg_sb); strbuf_release(&rel_path); + + if (recurse_into_nested) + connect_wt_gitdir_in_nested(work_tree, git_dir); + free(work_tree); free(git_dir); } @@ -3054,5 +3108,5 @@ void relocate_gitdir(const char *path, const char *old_git_dir, const char *new_ die_errno(_("could not migrate git directory from '%s' to '%s'"), old_git_dir, new_git_dir); - connect_work_tree_and_git_dir(path, new_git_dir); + connect_work_tree_and_git_dir(path, new_git_dir, 0); } @@ -359,7 +359,17 @@ struct untracked_cache *read_untracked_extension(const void *data, unsigned long void write_untracked_extension(struct strbuf *out, struct untracked_cache *untracked); void add_untracked_cache(struct index_state *istate); void remove_untracked_cache(struct index_state *istate); -extern void connect_work_tree_and_git_dir(const char *work_tree, const char *git_dir); + +/* + * Connect a worktree to a git directory by creating (or overwriting) a + * '.git' file containing the location of the git directory. In the git + * directory set the core.worktree setting to indicate where the worktree is. + * When `recurse_into_nested` is set, recurse into any nested submodules, + * connecting them as well. + */ +extern void connect_work_tree_and_git_dir(const char *work_tree, + const char *git_dir, + int recurse_into_nested); extern void relocate_gitdir(const char *path, const char *old_git_dir, const char *new_git_dir); diff --git a/environment.c b/environment.c index fd970b81bd..2a6de2330b 100644 --- a/environment.c +++ b/environment.c @@ -51,10 +51,11 @@ const char *editor_program; const char *askpass_program; const char *excludes_file; enum auto_crlf auto_crlf = AUTO_CRLF_FALSE; -int check_replace_refs = 1; +int check_replace_refs = 1; /* NEEDSWORK: rename to read_replace_refs */ char *git_replace_ref_base; enum eol core_eol = EOL_UNSET; int global_conv_flags_eol = CONV_EOL_RNDTRP_WARN; +char *check_roundtrip_encoding = "SHIFT-JIS"; unsigned whitespace_rule_cfg = WS_DEFAULT_RULE; enum branch_track git_branch_track = BRANCH_TRACK_REMOTE; enum rebase_setup_type autorebase = AUTOREBASE_NEVER; @@ -65,6 +66,7 @@ enum push_default_type push_default = PUSH_DEFAULT_UNSPECIFIED; enum object_creation_mode object_creation_mode = OBJECT_CREATION_MODE; char *notes_ref_name; int grafts_replace_parents = 1; +int core_commit_graph; int core_apply_sparse_checkout; int merge_log_config = -1; int precomposed_unicode = -1; /* see probe_utf8_pathname_composition() */ diff --git a/exec-cmd.c b/exec-cmd.c index 8a8261746a..02d31ee897 100644 --- a/exec-cmd.c +++ b/exec-cmd.c @@ -2,25 +2,53 @@ #include "exec-cmd.h" #include "quote.h" #include "argv-array.h" -#define MAX_ARGS 32 -static const char *argv_exec_path; +#if defined(RUNTIME_PREFIX) + +#if defined(HAVE_NS_GET_EXECUTABLE_PATH) +#include <mach-o/dyld.h> +#endif + +#if defined(HAVE_BSD_KERN_PROC_SYSCTL) +#include <sys/param.h> +#include <sys/types.h> +#include <sys/sysctl.h> +#endif + +#endif /* RUNTIME_PREFIX */ + +#define MAX_ARGS 32 + +static const char *system_prefix(void); #ifdef RUNTIME_PREFIX -static const char *argv0_path; + +/** + * When using a runtime prefix, Git dynamically resolves paths relative to its + * executable. + * + * The method for determining the path of the executable is highly + * platform-specific. + */ + +/** + * Path to the current Git executable. Resolved on startup by + * 'git_resolve_executable_dir'. + */ +static const char *executable_dirname; static const char *system_prefix(void) { static const char *prefix; - assert(argv0_path); - assert(is_absolute_path(argv0_path)); + assert(executable_dirname); + assert(is_absolute_path(executable_dirname)); if (!prefix && - !(prefix = strip_path_suffix(argv0_path, GIT_EXEC_PATH)) && - !(prefix = strip_path_suffix(argv0_path, BINDIR)) && - !(prefix = strip_path_suffix(argv0_path, "git"))) { - prefix = PREFIX; + !(prefix = strip_path_suffix(executable_dirname, GIT_EXEC_PATH)) && + !(prefix = strip_path_suffix(executable_dirname, BINDIR)) && + !(prefix = strip_path_suffix(executable_dirname, "git"))) { + prefix = FALLBACK_RUNTIME_PREFIX; trace_printf("RUNTIME_PREFIX requested, " "but prefix computation failed. " "Using static fallback '%s'.\n", prefix); @@ -28,27 +56,201 @@ static const char *system_prefix(void) return prefix; } -void git_extract_argv0_path(const char *argv0) +/* + * Resolves the executable path from argv[0], only if it is absolute. + * + * Returns 0 on success, -1 on failure. + */ +static int git_get_exec_path_from_argv0(struct strbuf *buf, const char *argv0) { const char *slash; if (!argv0 || !*argv0) - return; + return -1; slash = find_last_dir_sep(argv0); + if (slash) { + trace_printf("trace: resolved executable path from argv0: %s\n", + argv0); + strbuf_add_absolute_path(buf, argv0); + return 0; + } + return -1; +} + +#ifdef PROCFS_EXECUTABLE_PATH +/* + * Resolves the executable path by examining a procfs symlink. + * + * Returns 0 on success, -1 on failure. + */ +static int git_get_exec_path_procfs(struct strbuf *buf) +{ + if (strbuf_realpath(buf, PROCFS_EXECUTABLE_PATH, 0)) { + trace_printf( + "trace: resolved executable path from procfs: %s\n", + buf->buf); + return 0; + } + return -1; +} +#endif /* PROCFS_EXECUTABLE_PATH */ + +#ifdef HAVE_BSD_KERN_PROC_SYSCTL +/* + * Resolves the executable path using KERN_PROC_PATHNAME BSD sysctl. + * + * Returns 0 on success, -1 on failure. + */ +static int git_get_exec_path_bsd_sysctl(struct strbuf *buf) +{ + int mib[4]; + char path[MAXPATHLEN]; + size_t cb = sizeof(path); + + mib[0] = CTL_KERN; + mib[1] = KERN_PROC; + mib[2] = KERN_PROC_PATHNAME; + mib[3] = -1; + if (!sysctl(mib, 4, path, &cb, NULL, 0)) { + trace_printf( + "trace: resolved executable path from sysctl: %s\n", + path); + strbuf_addstr(buf, path); + return 0; + } + return -1; +} +#endif /* HAVE_BSD_KERN_PROC_SYSCTL */ + +#ifdef HAVE_NS_GET_EXECUTABLE_PATH +/* + * Resolves the executable path by querying Darwin application stack. + * + * Returns 0 on success, -1 on failure. + */ +static int git_get_exec_path_darwin(struct strbuf *buf) +{ + char path[PATH_MAX]; + uint32_t size = sizeof(path); + if (!_NSGetExecutablePath(path, &size)) { + trace_printf( + "trace: resolved executable path from Darwin stack: %s\n", + path); + strbuf_addstr(buf, path); + return 0; + } + return -1; +} +#endif /* HAVE_NS_GET_EXECUTABLE_PATH */ + +#ifdef HAVE_WPGMPTR +/* + * Resolves the executable path by using the global variable _wpgmptr. + * + * Returns 0 on success, -1 on failure. + */ +static int git_get_exec_path_wpgmptr(struct strbuf *buf) +{ + int len = wcslen(_wpgmptr) * 3 + 1; + strbuf_grow(buf, len); + len = xwcstoutf(buf->buf, _wpgmptr, len); + if (len < 0) + return -1; + buf->len += len; + return 0; +} +#endif /* HAVE_WPGMPTR */ + +/* + * Resolves the absolute path of the current executable. + * + * Returns 0 on success, -1 on failure. + */ +static int git_get_exec_path(struct strbuf *buf, const char *argv0) +{ + /* + * Identifying the executable path is operating system specific. + * Selectively employ all available methods in order of preference, + * preferring highly-available authoritative methods over + * selectively-available or non-authoritative methods. + * + * All cases fall back on resolving against argv[0] if there isn't a + * better functional method. However, note that argv[0] can be + * used-supplied on many operating systems, and is not authoritative + * in those cases. + * + * Each of these functions returns 0 on success, so evaluation will stop + * after the first successful method. + */ + if ( +#ifdef HAVE_BSD_KERN_PROC_SYSCTL + git_get_exec_path_bsd_sysctl(buf) && +#endif /* HAVE_BSD_KERN_PROC_SYSCTL */ + +#ifdef HAVE_NS_GET_EXECUTABLE_PATH + git_get_exec_path_darwin(buf) && +#endif /* HAVE_NS_GET_EXECUTABLE_PATH */ + +#ifdef PROCFS_EXECUTABLE_PATH + git_get_exec_path_procfs(buf) && +#endif /* PROCFS_EXECUTABLE_PATH */ + +#ifdef HAVE_WPGMPTR + git_get_exec_path_wpgmptr(buf) && +#endif /* HAVE_WPGMPTR */ + + git_get_exec_path_from_argv0(buf, argv0)) { + return -1; + } + + if (strbuf_normalize_path(buf)) { + trace_printf("trace: could not normalize path: %s\n", buf->buf); + return -1; + } + + return 0; +} +void git_resolve_executable_dir(const char *argv0) +{ + struct strbuf buf = STRBUF_INIT; + char *resolved; + const char *slash; + + if (git_get_exec_path(&buf, argv0)) { + trace_printf( + "trace: could not determine executable path from: %s\n", + argv0); + strbuf_release(&buf); + return; + } + + resolved = strbuf_detach(&buf, NULL); + slash = find_last_dir_sep(resolved); if (slash) - argv0_path = xstrndup(argv0, slash - argv0); + resolved[slash - resolved] = '\0'; + + executable_dirname = resolved; + trace_printf("trace: resolved executable dir: %s\n", + executable_dirname); } #else +/* + * When not using a runtime prefix, Git uses a hard-coded path. + */ static const char *system_prefix(void) { - return PREFIX; + return FALLBACK_RUNTIME_PREFIX; } -void git_extract_argv0_path(const char *argv0) +/* + * This is called during initialization, but No work needs to be done here when + * runtime prefix is not being used. + */ +void git_resolve_executable_dir(const char *argv0) { } @@ -65,32 +267,28 @@ char *system_path(const char *path) return strbuf_detach(&d, NULL); } -void git_set_argv_exec_path(const char *exec_path) +static const char *exec_path_value; + +void git_set_exec_path(const char *exec_path) { - argv_exec_path = exec_path; + exec_path_value = exec_path; /* * Propagate this setting to external programs. */ setenv(EXEC_PATH_ENVIRONMENT, exec_path, 1); } - -/* Returns the highest-priority, location to look for git programs. */ +/* Returns the highest-priority location to look for git programs. */ const char *git_exec_path(void) { - static char *cached_exec_path; - - if (argv_exec_path) - return argv_exec_path; - - if (!cached_exec_path) { + if (!exec_path_value) { const char *env = getenv(EXEC_PATH_ENVIRONMENT); if (env && *env) - cached_exec_path = xstrdup(env); + exec_path_value = xstrdup(env); else - cached_exec_path = system_path(GIT_EXEC_PATH); + exec_path_value = system_path(GIT_EXEC_PATH); } - return cached_exec_path; + return exec_path_value; } static void add_path(struct strbuf *out, const char *path) @@ -103,10 +301,12 @@ static void add_path(struct strbuf *out, const char *path) void setup_path(void) { + const char *exec_path = git_exec_path(); const char *old_path = getenv("PATH"); struct strbuf new_path = STRBUF_INIT; - add_path(&new_path, git_exec_path()); + git_set_exec_path(exec_path); + add_path(&new_path, exec_path); if (old_path) strbuf_addstr(&new_path, old_path); @@ -125,7 +325,8 @@ const char **prepare_git_cmd(struct argv_array *out, const char **argv) return out->argv; } -int execv_git_cmd(const char **argv) { +int execv_git_cmd(const char **argv) +{ struct argv_array nargv = ARGV_ARRAY_INIT; prepare_git_cmd(&nargv, argv); @@ -140,8 +341,7 @@ int execv_git_cmd(const char **argv) { return -1; } - -int execl_git_cmd(const char *cmd,...) +int execl_git_cmd(const char *cmd, ...) { int argc; const char *argv[MAX_ARGS + 1]; diff --git a/exec-cmd.h b/exec-cmd.h index ff0b48048a..2522453cda 100644 --- a/exec-cmd.h +++ b/exec-cmd.h @@ -3,8 +3,8 @@ struct argv_array; -extern void git_set_argv_exec_path(const char *exec_path); -extern void git_extract_argv0_path(const char *path); +extern void git_set_exec_path(const char *exec_path); +extern void git_resolve_executable_dir(const char *path); extern const char *git_exec_path(void); extern void setup_path(void); extern const char **prepare_git_cmd(struct argv_array *out, const char **argv); diff --git a/fast-import.c b/fast-import.c index 05d1079d23..b2338fa8eb 100644 --- a/fast-import.c +++ b/fast-import.c @@ -973,7 +973,7 @@ static void end_packfile(void) struct tag *t; close_pack_windows(pack_data); - hashclose(pack_file, cur_pack_oid.hash, 0); + finalize_hashfile(pack_file, cur_pack_oid.hash, 0); fixup_pack_header_footer(pack_data->pack_fd, pack_data->sha1, pack_data->pack_name, object_count, cur_pack_oid.hash, pack_size); @@ -1331,7 +1331,7 @@ static void *gfi_unpack_entry( */ p->pack_size = pack_size + the_hash_algo->rawsz; } - return unpack_entry(p, oe->idx.offset, &type, sizep); + return unpack_entry(the_repository, p, oe->idx.offset, &type, sizep); } static const char *get_mode(const char *str, uint16_t *modep) @@ -1872,7 +1872,8 @@ static void read_marks(void) die("corrupt mark line: %s", line); e = find_object(&oid); if (!e) { - enum object_type type = oid_object_info(&oid, NULL); + enum object_type type = oid_object_info(the_repository, + &oid, NULL); if (type < 0) die("object not found: %s", oid_to_hex(&oid)); e = insert_object(&oid); @@ -2402,7 +2403,8 @@ static void file_change_m(const char *p, struct branch *b) enum object_type expected = S_ISDIR(mode) ? OBJ_TREE: OBJ_BLOB; enum object_type type = oe ? oe->type : - oid_object_info(&oid, NULL); + oid_object_info(the_repository, &oid, + NULL); if (type < 0) die("%s not found: %s", S_ISDIR(mode) ? "Tree" : "Blob", @@ -2563,7 +2565,8 @@ static void note_change_n(const char *p, struct branch *b, unsigned char *old_fa die("Not a blob (actually a %s): %s", type_name(oe->type), command_buf.buf); } else if (!is_null_oid(&oid)) { - enum object_type type = oid_object_info(&oid, NULL); + enum object_type type = oid_object_info(the_repository, &oid, + NULL); if (type < 0) die("Blob not found: %s", command_buf.buf); if (type != OBJ_BLOB) @@ -2850,7 +2853,7 @@ static void parse_new_tag(const char *arg) } else if (!get_oid(from, &oid)) { struct object_entry *oe = find_object(&oid); if (!oe) { - type = oid_object_info(&oid, NULL); + type = oid_object_info(the_repository, &oid, NULL); if (type < 0) die("Not a valid object: %s", from); } else @@ -3008,7 +3011,8 @@ static struct object_entry *dereference(struct object_entry *oe, unsigned long size; char *buf = NULL; if (!oe) { - enum object_type type = oid_object_info(oid, NULL); + enum object_type type = oid_object_info(the_repository, oid, + NULL); if (type < 0) die("object not found: %s", oid_to_hex(oid)); /* cache it! */ diff --git a/fetch-pack.c b/fetch-pack.c index 4a8bad8487..490c38f833 100644 --- a/fetch-pack.c +++ b/fetch-pack.c @@ -305,9 +305,9 @@ static void insert_one_alternate_object(struct object *obj) #define PIPESAFE_FLUSH 32 #define LARGE_FLUSH 16384 -static int next_flush(struct fetch_pack_args *args, int count) +static int next_flush(int stateless_rpc, int count) { - if (args->stateless_rpc) { + if (stateless_rpc) { if (count < LARGE_FLUSH) count <<= 1; else @@ -470,7 +470,7 @@ static int find_common(struct fetch_pack_args *args, send_request(args, fd[1], &req_buf); strbuf_setlen(&req_buf, state_len); flushes++; - flush_at = next_flush(args, count); + flush_at = next_flush(args->stateless_rpc, count); /* * We keep one window "ahead" of the other side, and @@ -1080,6 +1080,335 @@ static struct ref *do_fetch_pack(struct fetch_pack_args *args, return ref; } +static void add_shallow_requests(struct strbuf *req_buf, + const struct fetch_pack_args *args) +{ + if (is_repository_shallow()) + write_shallow_commits(req_buf, 1, NULL); + if (args->depth > 0) + packet_buf_write(req_buf, "deepen %d", args->depth); + if (args->deepen_since) { + timestamp_t max_age = approxidate(args->deepen_since); + packet_buf_write(req_buf, "deepen-since %"PRItime, max_age); + } + if (args->deepen_not) { + int i; + for (i = 0; i < args->deepen_not->nr; i++) { + struct string_list_item *s = args->deepen_not->items + i; + packet_buf_write(req_buf, "deepen-not %s", s->string); + } + } +} + +static void add_wants(const struct ref *wants, struct strbuf *req_buf) +{ + for ( ; wants ; wants = wants->next) { + const struct object_id *remote = &wants->old_oid; + const char *remote_hex; + struct object *o; + + /* + * If that object is complete (i.e. it is an ancestor of a + * local ref), we tell them we have it but do not have to + * tell them about its ancestors, which they already know + * about. + * + * We use lookup_object here because we are only + * interested in the case we *know* the object is + * reachable and we have already scanned it. + */ + if (((o = lookup_object(remote->hash)) != NULL) && + (o->flags & COMPLETE)) { + continue; + } + + remote_hex = oid_to_hex(remote); + packet_buf_write(req_buf, "want %s\n", remote_hex); + } +} + +static void add_common(struct strbuf *req_buf, struct oidset *common) +{ + struct oidset_iter iter; + const struct object_id *oid; + oidset_iter_init(common, &iter); + + while ((oid = oidset_iter_next(&iter))) { + packet_buf_write(req_buf, "have %s\n", oid_to_hex(oid)); + } +} + +static int add_haves(struct strbuf *req_buf, int *haves_to_send, int *in_vain) +{ + int ret = 0; + int haves_added = 0; + const struct object_id *oid; + + while ((oid = get_rev())) { + packet_buf_write(req_buf, "have %s\n", oid_to_hex(oid)); + if (++haves_added >= *haves_to_send) + break; + } + + *in_vain += haves_added; + if (!haves_added || *in_vain >= MAX_IN_VAIN) { + /* Send Done */ + packet_buf_write(req_buf, "done\n"); + ret = 1; + } + + /* Increase haves to send on next round */ + *haves_to_send = next_flush(1, *haves_to_send); + + return ret; +} + +static int send_fetch_request(int fd_out, const struct fetch_pack_args *args, + const struct ref *wants, struct oidset *common, + int *haves_to_send, int *in_vain) +{ + int ret = 0; + struct strbuf req_buf = STRBUF_INIT; + + if (server_supports_v2("fetch", 1)) + packet_buf_write(&req_buf, "command=fetch"); + if (server_supports_v2("agent", 0)) + packet_buf_write(&req_buf, "agent=%s", git_user_agent_sanitized()); + if (args->server_options && args->server_options->nr && + server_supports_v2("server-option", 1)) { + int i; + for (i = 0; i < args->server_options->nr; i++) + packet_write_fmt(fd_out, "server-option=%s", + args->server_options->items[i].string); + } + + packet_buf_delim(&req_buf); + if (args->use_thin_pack) + packet_buf_write(&req_buf, "thin-pack"); + if (args->no_progress) + packet_buf_write(&req_buf, "no-progress"); + if (args->include_tag) + packet_buf_write(&req_buf, "include-tag"); + if (prefer_ofs_delta) + packet_buf_write(&req_buf, "ofs-delta"); + + /* Add shallow-info and deepen request */ + if (server_supports_feature("fetch", "shallow", 0)) + add_shallow_requests(&req_buf, args); + else if (is_repository_shallow() || args->deepen) + die(_("Server does not support shallow requests")); + + /* add wants */ + add_wants(wants, &req_buf); + + /* Add all of the common commits we've found in previous rounds */ + add_common(&req_buf, common); + + /* Add initial haves */ + ret = add_haves(&req_buf, haves_to_send, in_vain); + + /* Send request */ + packet_buf_flush(&req_buf); + write_or_die(fd_out, req_buf.buf, req_buf.len); + + strbuf_release(&req_buf); + return ret; +} + +/* + * Processes a section header in a server's response and checks if it matches + * `section`. If the value of `peek` is 1, the header line will be peeked (and + * not consumed); if 0, the line will be consumed and the function will die if + * the section header doesn't match what was expected. + */ +static int process_section_header(struct packet_reader *reader, + const char *section, int peek) +{ + int ret; + + if (packet_reader_peek(reader) != PACKET_READ_NORMAL) + die("error reading section header '%s'", section); + + ret = !strcmp(reader->line, section); + + if (!peek) { + if (!ret) + die("expected '%s', received '%s'", + section, reader->line); + packet_reader_read(reader); + } + + return ret; +} + +static int process_acks(struct packet_reader *reader, struct oidset *common) +{ + /* received */ + int received_ready = 0; + int received_ack = 0; + + process_section_header(reader, "acknowledgments", 0); + while (packet_reader_read(reader) == PACKET_READ_NORMAL) { + const char *arg; + + if (!strcmp(reader->line, "NAK")) + continue; + + if (skip_prefix(reader->line, "ACK ", &arg)) { + struct object_id oid; + if (!get_oid_hex(arg, &oid)) { + struct commit *commit; + oidset_insert(common, &oid); + commit = lookup_commit(&oid); + mark_common(commit, 0, 1); + } + continue; + } + + if (!strcmp(reader->line, "ready")) { + clear_prio_queue(&rev_list); + received_ready = 1; + continue; + } + + die("unexpected acknowledgment line: '%s'", reader->line); + } + + if (reader->status != PACKET_READ_FLUSH && + reader->status != PACKET_READ_DELIM) + die("error processing acks: %d", reader->status); + + /* return 0 if no common, 1 if there are common, or 2 if ready */ + return received_ready ? 2 : (received_ack ? 1 : 0); +} + +static void receive_shallow_info(struct fetch_pack_args *args, + struct packet_reader *reader) +{ + process_section_header(reader, "shallow-info", 0); + while (packet_reader_read(reader) == PACKET_READ_NORMAL) { + const char *arg; + struct object_id oid; + + if (skip_prefix(reader->line, "shallow ", &arg)) { + if (get_oid_hex(arg, &oid)) + die(_("invalid shallow line: %s"), reader->line); + register_shallow(&oid); + continue; + } + if (skip_prefix(reader->line, "unshallow ", &arg)) { + if (get_oid_hex(arg, &oid)) + die(_("invalid unshallow line: %s"), reader->line); + if (!lookup_object(oid.hash)) + die(_("object not found: %s"), reader->line); + /* make sure that it is parsed as shallow */ + if (!parse_object(&oid)) + die(_("error in object: %s"), reader->line); + if (unregister_shallow(&oid)) + die(_("no shallow found: %s"), reader->line); + continue; + } + die(_("expected shallow/unshallow, got %s"), reader->line); + } + + if (reader->status != PACKET_READ_FLUSH && + reader->status != PACKET_READ_DELIM) + die("error processing shallow info: %d", reader->status); + + setup_alternate_shallow(&shallow_lock, &alternate_shallow_file, NULL); + args->deepen = 1; +} + +enum fetch_state { + FETCH_CHECK_LOCAL = 0, + FETCH_SEND_REQUEST, + FETCH_PROCESS_ACKS, + FETCH_GET_PACK, + FETCH_DONE, +}; + +static struct ref *do_fetch_pack_v2(struct fetch_pack_args *args, + int fd[2], + const struct ref *orig_ref, + struct ref **sought, int nr_sought, + char **pack_lockfile) +{ + struct ref *ref = copy_ref_list(orig_ref); + enum fetch_state state = FETCH_CHECK_LOCAL; + struct oidset common = OIDSET_INIT; + struct packet_reader reader; + int in_vain = 0; + int haves_to_send = INITIAL_FLUSH; + packet_reader_init(&reader, fd[0], NULL, 0, + PACKET_READ_CHOMP_NEWLINE); + + while (state != FETCH_DONE) { + switch (state) { + case FETCH_CHECK_LOCAL: + sort_ref_list(&ref, ref_compare_name); + QSORT(sought, nr_sought, cmp_ref_by_name); + + /* v2 supports these by default */ + allow_unadvertised_object_request |= ALLOW_REACHABLE_SHA1; + use_sideband = 2; + if (args->depth > 0 || args->deepen_since || args->deepen_not) + args->deepen = 1; + + if (marked) + for_each_ref(clear_marks, NULL); + marked = 1; + + for_each_ref(rev_list_insert_ref_oid, NULL); + for_each_cached_alternate(insert_one_alternate_object); + + /* Filter 'ref' by 'sought' and those that aren't local */ + if (everything_local(args, &ref, sought, nr_sought)) + state = FETCH_DONE; + else + state = FETCH_SEND_REQUEST; + break; + case FETCH_SEND_REQUEST: + if (send_fetch_request(fd[1], args, ref, &common, + &haves_to_send, &in_vain)) + state = FETCH_GET_PACK; + else + state = FETCH_PROCESS_ACKS; + break; + case FETCH_PROCESS_ACKS: + /* Process ACKs/NAKs */ + switch (process_acks(&reader, &common)) { + case 2: + state = FETCH_GET_PACK; + break; + case 1: + in_vain = 0; + /* fallthrough */ + default: + state = FETCH_SEND_REQUEST; + break; + } + break; + case FETCH_GET_PACK: + /* Check for shallow-info section */ + if (process_section_header(&reader, "shallow-info", 1)) + receive_shallow_info(args, &reader); + + /* get the pack */ + process_section_header(&reader, "packfile", 0); + if (get_pack(args, fd, pack_lockfile)) + die(_("git fetch-pack: fetch failed.")); + + state = FETCH_DONE; + break; + case FETCH_DONE: + continue; + } + } + + oidset_clear(&common); + return ref; +} + static void fetch_pack_config(void) { git_config_get_int("fetch.unpacklimit", &fetch_unpack_limit); @@ -1225,7 +1554,8 @@ struct ref *fetch_pack(struct fetch_pack_args *args, const char *dest, struct ref **sought, int nr_sought, struct oid_array *shallow, - char **pack_lockfile) + char **pack_lockfile, + enum protocol_version version) { struct ref *ref_cpy; struct shallow_info si; @@ -1239,8 +1569,12 @@ struct ref *fetch_pack(struct fetch_pack_args *args, die(_("no matching remote head")); } prepare_shallow_info(&si, shallow); - ref_cpy = do_fetch_pack(args, fd, ref, sought, nr_sought, - &si, pack_lockfile); + if (version == protocol_v2) + ref_cpy = do_fetch_pack_v2(args, fd, ref, sought, nr_sought, + pack_lockfile); + else + ref_cpy = do_fetch_pack(args, fd, ref, sought, nr_sought, + &si, pack_lockfile); reprepare_packed_git(the_repository); update_shallow(args, sought, nr_sought, &si); clear_shallow_info(&si); diff --git a/fetch-pack.h b/fetch-pack.h index 3e224a1822..bb45a366a8 100644 --- a/fetch-pack.h +++ b/fetch-pack.h @@ -3,6 +3,7 @@ #include "string-list.h" #include "run-command.h" +#include "protocol.h" #include "list-objects-filter-options.h" struct oid_array; @@ -14,6 +15,7 @@ struct fetch_pack_args { const char *deepen_since; const struct string_list *deepen_not; struct list_objects_filter_options filter_options; + const struct string_list *server_options; unsigned deepen_relative:1; unsigned quiet:1; unsigned keep_pack:1; @@ -53,7 +55,8 @@ struct ref *fetch_pack(struct fetch_pack_args *args, struct ref **sought, int nr_sought, struct oid_array *shallow, - char **pack_lockfile); + char **pack_lockfile, + enum protocol_version version); /* * Print an appropriate error message for each sought ref that wasn't @@ -396,9 +396,11 @@ static int fsck_walk_commit(struct commit *commit, void *data, struct fsck_optio name = get_object_name(options, &commit->object); if (name) - put_object_name(options, &commit->tree->object, "%s:", name); + put_object_name(options, &get_commit_tree(commit)->object, + "%s:", name); - result = options->walk((struct object *)commit->tree, OBJ_TREE, data, options); + result = options->walk((struct object *)get_commit_tree(commit), + OBJ_TREE, data, options); if (result < 0) return result; res = result; @@ -772,7 +774,7 @@ static int fsck_commit_buffer(struct commit *commit, const char *buffer, err = fsck_ident(&buffer, &commit->object, options); if (err) return err; - if (!commit->tree) { + if (!get_commit_tree(commit)) { err = report(options, &commit->object, FSCK_MSG_BAD_TREE, "could not load commit's tree %s", sha1_to_hex(tree_sha1)); if (err) return err; @@ -2,7 +2,8 @@ * Copyright (c) 2010 Ævar Arnfjörð Bjarmason */ -#include "git-compat-util.h" +#include "cache.h" +#include "exec-cmd.h" #include "gettext.h" #include "strbuf.h" #include "utf8.h" @@ -157,15 +158,24 @@ static void init_gettext_charset(const char *domain) void git_setup_gettext(void) { - const char *podir = getenv("GIT_TEXTDOMAINDIR"); + const char *podir = getenv(GIT_TEXT_DOMAIN_DIR_ENVIRONMENT); + char *p = NULL; if (!podir) - podir = GIT_LOCALE_PATH; + podir = p = system_path(GIT_LOCALE_PATH); + + if (!is_directory(podir)) { + free(p); + return; + } + bindtextdomain("git", podir); setlocale(LC_MESSAGES, ""); setlocale(LC_TIME, ""); init_gettext_charset("git"); textdomain("git"); + + free(p); } /* return the number of columns of string 's' in current locale */ diff --git a/git-compat-util.h b/git-compat-util.h index 07e383257b..f9e4c5f9bc 100644 --- a/git-compat-util.h +++ b/git-compat-util.h @@ -284,6 +284,10 @@ extern char *gitdirname(char *); #include <openssl/err.h> #endif +#ifdef HAVE_SYSINFO +# include <sys/sysinfo.h> +#endif + /* On most systems <netdb.h> would have given us this, but * not on some systems (e.g. z/OS). */ @@ -455,6 +459,7 @@ extern void (*get_warn_routine(void))(const char *warn, va_list params); extern void set_die_is_recursing_routine(int (*routine)(void)); extern int starts_with(const char *str, const char *prefix); +extern int istarts_with(const char *str, const char *prefix); /* * If the string "str" begins with the string found in "prefix", return 1. diff --git a/git-send-email.perl b/git-send-email.perl index 2fa7818ca9..7157397fd0 100755 --- a/git-send-email.perl +++ b/git-send-email.perl @@ -1642,10 +1642,15 @@ foreach my $t (@files) { elsif (/^Content-Transfer-Encoding: (.*)/i) { $xfer_encoding = $1 if not defined $xfer_encoding; } + elsif (/^In-Reply-To: (.*)/i) { + $in_reply_to = $1; + } + elsif (/^References: (.*)/i) { + $references = $1; + } elsif (!/^Date:\s/i && /^[-A-Za-z]+:\s+\S/) { push @xh, $_; } - } else { # In the traditional # "send lots of email" format, @@ -25,7 +25,7 @@ struct cmd_struct { const char git_usage_string[] = N_("git [--version] [--help] [-C <path>] [-c <name>=<value>]\n" " [--exec-path[=<path>]] [--html-path] [--man-path] [--info-path]\n" - " [-p | --paginate | --no-pager] [--no-replace-objects] [--bare]\n" + " [-p | --paginate | -P | --no-pager] [--no-replace-objects] [--bare]\n" " [--git-dir=<path>] [--work-tree=<path>] [--namespace=<name>]\n" " <command> [<args>]"); @@ -83,7 +83,7 @@ static int handle_options(const char ***argv, int *argc, int *envchanged) */ if (skip_prefix(cmd, "--exec-path", &cmd)) { if (*cmd == '=') - git_set_argv_exec_path(cmd + 1); + git_set_exec_path(cmd + 1); else { puts(git_exec_path()); exit(0); @@ -99,7 +99,7 @@ static int handle_options(const char ***argv, int *argc, int *envchanged) exit(0); } else if (!strcmp(cmd, "-p") || !strcmp(cmd, "--paginate")) { use_pager = 1; - } else if (!strcmp(cmd, "--no-pager")) { + } else if (!strcmp(cmd, "-P") || !strcmp(cmd, "--no-pager")) { use_pager = 0; if (envchanged) *envchanged = 1; @@ -392,6 +392,7 @@ static struct cmd_struct commands[] = { { "clone", cmd_clone }, { "column", cmd_column, RUN_SETUP_GENTLY }, { "commit", cmd_commit, RUN_SETUP | NEED_WORK_TREE }, + { "commit-graph", cmd_commit_graph, RUN_SETUP }, { "commit-tree", cmd_commit_tree, RUN_SETUP | NO_PARSEOPT }, { "config", cmd_config, RUN_SETUP_GENTLY | DELAY_PAGER_CONFIG }, { "count-objects", cmd_count_objects, RUN_SETUP }, @@ -465,6 +466,7 @@ static struct cmd_struct commands[] = { { "revert", cmd_revert, RUN_SETUP | NEED_WORK_TREE }, { "rm", cmd_rm, RUN_SETUP }, { "send-pack", cmd_send_pack, RUN_SETUP }, + { "serve", cmd_serve, RUN_SETUP }, { "shortlog", cmd_shortlog, RUN_SETUP_GENTLY | USE_PAGER }, { "show", cmd_show, RUN_SETUP }, { "show-branch", cmd_show_branch, RUN_SETUP }, @@ -482,6 +484,7 @@ static struct cmd_struct commands[] = { { "update-server-info", cmd_update_server_info, RUN_SETUP }, { "upload-archive", cmd_upload_archive, NO_PARSEOPT }, { "upload-archive--writer", cmd_upload_archive_writer, NO_PARSEOPT }, + { "upload-pack", cmd_upload_pack }, { "var", cmd_var, RUN_SETUP_GENTLY | NO_PARSEOPT }, { "verify-commit", cmd_verify_commit, RUN_SETUP }, { "verify-pack", cmd_verify_pack }, diff --git a/gpg-interface.c b/gpg-interface.c index 4feacf16e5..0647bd6348 100644 --- a/gpg-interface.c +++ b/gpg-interface.c @@ -101,22 +101,26 @@ void print_signature_buffer(const struct signature_check *sigc, unsigned flags) fputs(output, stderr); } -/* - * Look at GPG signed content (e.g. a signed tag object), whose - * payload is followed by a detached signature on it. Return the - * offset where the embedded detached signature begins, or the end of - * the data when there is no such signature. - */ -size_t parse_signature(const char *buf, unsigned long size) +static int is_gpg_start(const char *line) +{ + return starts_with(line, PGP_SIGNATURE) || + starts_with(line, PGP_MESSAGE); +} + +size_t parse_signature(const char *buf, size_t size) { - char *eol; size_t len = 0; - while (len < size && !starts_with(buf + len, PGP_SIGNATURE) && - !starts_with(buf + len, PGP_MESSAGE)) { + size_t match = size; + while (len < size) { + const char *eol; + + if (is_gpg_start(buf + len)) + match = len; + eol = memchr(buf + len, '\n', size - len); len += eol ? eol - (buf + len) + 1 : size - len; } - return len; + return match; } void set_signing_key(const char *key) @@ -128,13 +132,19 @@ void set_signing_key(const char *key) int git_gpg_config(const char *var, const char *value, void *cb) { if (!strcmp(var, "user.signingkey")) { + if (!value) + return config_error_nonbool(var); set_signing_key(value); + return 0; } + if (!strcmp(var, "gpg.program")) { if (!value) return config_error_nonbool(var); gpg_program = xstrdup(value); + return 0; } + return 0; } @@ -145,12 +155,6 @@ const char *get_signing_key(void) return git_committer_info(IDENT_STRICT|IDENT_NO_DATE); } -/* - * Create a detached signature for the contents of "buffer" and append - * it after "signature"; "buffer" and "signature" can be the same - * strbuf instance, which would cause the detached signature appended - * at the end. - */ int sign_buffer(struct strbuf *buffer, struct strbuf *signature, const char *signing_key) { struct child_process gpg = CHILD_PROCESS_INIT; @@ -192,11 +196,6 @@ int sign_buffer(struct strbuf *buffer, struct strbuf *signature, const char *sig return 0; } -/* - * Run "gpg" to see if the payload matches the detached signature. - * gpg_output, when set, receives the diagnostic output from GPG. - * gpg_status, when set, receives the status output from GPG. - */ int verify_signed_buffer(const char *payload, size_t payload_size, const char *signature, size_t signature_size, struct strbuf *gpg_output, struct strbuf *gpg_status) diff --git a/gpg-interface.h b/gpg-interface.h index d2d4fd3a65..a5e6517ae6 100644 --- a/gpg-interface.h +++ b/gpg-interface.h @@ -23,16 +23,43 @@ struct signature_check { char *key; }; -extern void signature_check_clear(struct signature_check *sigc); -extern size_t parse_signature(const char *buf, unsigned long size); -extern void parse_gpg_output(struct signature_check *); -extern int sign_buffer(struct strbuf *buffer, struct strbuf *signature, const char *signing_key); -extern int verify_signed_buffer(const char *payload, size_t payload_size, const char *signature, size_t signature_size, struct strbuf *gpg_output, struct strbuf *gpg_status); -extern int git_gpg_config(const char *, const char *, void *); -extern void set_signing_key(const char *); -extern const char *get_signing_key(void); -extern int check_signature(const char *payload, size_t plen, - const char *signature, size_t slen, struct signature_check *sigc); -void print_signature_buffer(const struct signature_check *sigc, unsigned flags); +void signature_check_clear(struct signature_check *sigc); + +/* + * Look at GPG signed content (e.g. a signed tag object), whose + * payload is followed by a detached signature on it. Return the + * offset where the embedded detached signature begins, or the end of + * the data when there is no such signature. + */ +size_t parse_signature(const char *buf, size_t size); + +void parse_gpg_output(struct signature_check *); + +/* + * Create a detached signature for the contents of "buffer" and append + * it after "signature"; "buffer" and "signature" can be the same + * strbuf instance, which would cause the detached signature appended + * at the end. + */ +int sign_buffer(struct strbuf *buffer, struct strbuf *signature, + const char *signing_key); + +/* + * Run "gpg" to see if the payload matches the detached signature. + * gpg_output, when set, receives the diagnostic output from GPG. + * gpg_status, when set, receives the status output from GPG. + */ +int verify_signed_buffer(const char *payload, size_t payload_size, + const char *signature, size_t signature_size, + struct strbuf *gpg_output, struct strbuf *gpg_status); + +int git_gpg_config(const char *, const char *, void *); +void set_signing_key(const char *); +const char *get_signing_key(void); +int check_signature(const char *payload, size_t plen, + const char *signature, size_t slen, + struct signature_check *sigc); +void print_signature_buffer(const struct signature_check *sigc, + unsigned flags); #endif diff --git a/http-backend.c b/http-backend.c index cc16cd04ad..adaef16fad 100644 --- a/http-backend.c +++ b/http-backend.c @@ -12,6 +12,7 @@ #include "argv-array.h" #include "packfile.h" #include "object-store.h" +#include "protocol.h" static const char content_type[] = "Content-Type"; static const char content_length[] = "Content-Length"; @@ -468,8 +469,11 @@ static void get_info_refs(struct strbuf *hdr, char *arg) hdr_str(hdr, content_type, buf.buf); end_headers(hdr); - packet_write_fmt(1, "# service=git-%s\n", svc->name); - packet_flush(1); + + if (determine_protocol_version_server() != protocol_v2) { + packet_write_fmt(1, "# service=git-%s\n", svc->name); + packet_flush(1); + } argv[0] = svc->name; run_service(argv, 0); diff --git a/http-fetch.c b/http-fetch.c index 885e471501..a32ac118d9 100644 --- a/http-fetch.c +++ b/http-fetch.c @@ -17,21 +17,13 @@ int cmd_main(int argc, const char **argv) char *url = NULL; int arg = 1; int rc = 0; - int get_tree = 0; - int get_history = 0; - int get_all = 0; int get_verbosely = 0; int get_recover = 0; while (arg < argc && argv[arg][0] == '-') { if (argv[arg][1] == 't') { - get_tree = 1; } else if (argv[arg][1] == 'c') { - get_history = 1; } else if (argv[arg][1] == 'a') { - get_all = 1; - get_tree = 1; - get_history = 1; } else if (argv[arg][1] == 'v') { get_verbosely = 1; } else if (argv[arg][1] == 'w') { @@ -55,10 +47,6 @@ int cmd_main(int argc, const char **argv) commits = 1; } - if (get_all == 0) - warning("http-fetch: use without -a is deprecated.\n" - "In a future release, -a will become the default."); - if (argv[arg]) str_end_url_with_slash(argv[arg], &url); @@ -68,9 +56,6 @@ int cmd_main(int argc, const char **argv) http_init(NULL, url, 0); walker = get_http_walker(url); - walker->get_tree = get_tree; - walker->get_history = get_history; - walker->get_all = get_all; walker->get_verbosely = get_verbosely; walker->get_recover = get_recover; diff --git a/http-push.c b/http-push.c index f308ce0195..2669f4bfa1 100644 --- a/http-push.c +++ b/http-push.c @@ -1331,7 +1331,7 @@ static int get_delta(struct rev_info *revs, struct remote_lock *lock) int count = 0; while ((commit = get_revision(revs)) != NULL) { - p = process_tree(commit->tree, p); + p = process_tree(get_commit_tree(commit), p); commit->object.flags |= LOCAL; if (!(commit->object.flags & UNINTERESTING)) count += add_send_request(&commit->object, lock); @@ -976,21 +976,6 @@ static void set_from_env(const char **var, const char *envname) *var = val; } -static void protocol_http_header(void) -{ - if (get_protocol_version_config() > 0) { - struct strbuf protocol_header = STRBUF_INIT; - - strbuf_addf(&protocol_header, GIT_PROTOCOL_HEADER ": version=%d", - get_protocol_version_config()); - - - extra_http_headers = curl_slist_append(extra_http_headers, - protocol_header.buf); - strbuf_release(&protocol_header); - } -} - void http_init(struct remote *remote, const char *url, int proactive_auth) { char *low_speed_limit; @@ -1021,8 +1006,6 @@ void http_init(struct remote *remote, const char *url, int proactive_auth) if (remote) var_override(&http_proxy_authmethod, remote->http_proxy_authmethod); - protocol_http_header(); - pragma_header = curl_slist_append(http_copy_default_headers(), "Pragma: no-cache"); no_pragma_header = curl_slist_append(http_copy_default_headers(), @@ -1795,6 +1778,14 @@ static int http_request(const char *url, headers = curl_slist_append(headers, buf.buf); + /* Add additional headers here */ + if (options && options->extra_headers) { + const struct string_list_item *item; + for_each_string_list_item(item, options->extra_headers) { + headers = curl_slist_append(headers, item->string); + } + } + curl_easy_setopt(slot->curl, CURLOPT_URL, url); curl_easy_setopt(slot->curl, CURLOPT_HTTPHEADER, headers); curl_easy_setopt(slot->curl, CURLOPT_ENCODING, "gzip"); @@ -172,6 +172,13 @@ struct http_get_options { * for details. */ struct strbuf *base_url; + + /* + * If not NULL, contains additional HTTP headers to be sent with the + * request. The strings in the list must not be freed until after the + * request has completed. + */ + struct string_list *extra_headers; }; /* Return values for http_get_*() */ diff --git a/line-log.c b/line-log.c index ecdce08c4b..fa9cfd5bdb 100644 --- a/line-log.c +++ b/line-log.c @@ -816,8 +816,8 @@ static void queue_diffs(struct line_log_data *range, assert(commit); DIFF_QUEUE_CLEAR(&diff_queued_diff); - diff_tree_oid(parent ? &parent->tree->object.oid : NULL, - &commit->tree->object.oid, "", opt); + diff_tree_oid(parent ? get_commit_tree_oid(parent) : NULL, + get_commit_tree_oid(commit), "", opt); if (opt->detect_rename) { filter_diffs_for_paths(range, 1); if (diff_might_be_rename()) diff --git a/list-objects-filter.c b/list-objects-filter.c index 247717561f..5b14d2711a 100644 --- a/list-objects-filter.c +++ b/list-objects-filter.c @@ -117,7 +117,7 @@ static enum list_objects_filter_result filter_blobs_limit( assert(obj->type == OBJ_BLOB); assert((obj->flags & SEEN) == 0); - t = oid_object_info(&obj->oid, &object_length); + t = oid_object_info(the_repository, &obj->oid, &object_length); if (t != OBJ_BLOB) { /* probably OBJ_NONE */ /* * We DO NOT have the blob locally, so we cannot diff --git a/list-objects.c b/list-objects.c index 168bef688a..3eec510357 100644 --- a/list-objects.c +++ b/list-objects.c @@ -195,7 +195,7 @@ static void mark_edge_parents_uninteresting(struct commit *commit, struct commit *parent = parents->item; if (!(parent->object.flags & UNINTERESTING)) continue; - mark_tree_uninteresting(parent->tree); + mark_tree_uninteresting(get_commit_tree(parent)); if (revs->edge_hint && !(parent->object.flags & SHOWN)) { parent->object.flags |= SHOWN; show_edge(parent); @@ -212,7 +212,7 @@ void mark_edges_uninteresting(struct rev_info *revs, show_edge_fn show_edge) struct commit *commit = list->item; if (commit->object.flags & UNINTERESTING) { - mark_tree_uninteresting(commit->tree); + mark_tree_uninteresting(get_commit_tree(commit)); if (revs->edge_hint_aggressive && !(commit->object.flags & SHOWN)) { commit->object.flags |= SHOWN; show_edge(commit); @@ -227,7 +227,7 @@ void mark_edges_uninteresting(struct rev_info *revs, show_edge_fn show_edge) struct commit *commit = (struct commit *)obj; if (obj->type != OBJ_COMMIT || !(obj->flags & UNINTERESTING)) continue; - mark_tree_uninteresting(commit->tree); + mark_tree_uninteresting(get_commit_tree(commit)); if (!(obj->flags & SHOWN)) { obj->flags |= SHOWN; show_edge(commit); @@ -300,8 +300,8 @@ static void do_traverse(struct rev_info *revs, * an uninteresting boundary commit may not have its tree * parsed yet, but we are not going to show them anyway */ - if (commit->tree) - add_pending_tree(revs, commit->tree); + if (get_commit_tree(commit)) + add_pending_tree(revs, get_commit_tree(commit)); show_commit(commit, show_data); if (revs->tree_blobs_in_commit_order) diff --git a/log-tree.c b/log-tree.c index d1c0bedf24..66329d089d 100644 --- a/log-tree.c +++ b/log-tree.c @@ -488,9 +488,9 @@ static int is_common_merge(const struct commit *commit) && !commit->parents->next->next); } -static void show_one_mergetag(struct commit *commit, - struct commit_extra_header *extra, - void *data) +static int show_one_mergetag(struct commit *commit, + struct commit_extra_header *extra, + void *data) { struct rev_info *opt = (struct rev_info *)data; struct object_id oid; @@ -502,7 +502,7 @@ static void show_one_mergetag(struct commit *commit, hash_object_file(extra->value, extra->len, type_name(OBJ_TAG), &oid); tag = lookup_tag(&oid); if (!tag) - return; /* error message already given */ + return -1; /* error message already given */ strbuf_init(&verify_message, 256); if (parse_tag_buffer(tag, extra->value, extra->len)) @@ -536,11 +536,12 @@ static void show_one_mergetag(struct commit *commit, show_sig_lines(opt, status, verify_message.buf); strbuf_release(&verify_message); + return 0; } -static void show_mergetag(struct rev_info *opt, struct commit *commit) +static int show_mergetag(struct rev_info *opt, struct commit *commit) { - for_each_mergetag(show_one_mergetag, commit, opt); + return for_each_mergetag(show_one_mergetag, commit, opt); } void show_log(struct rev_info *opt) @@ -806,7 +807,7 @@ static int log_tree_diff(struct rev_info *opt, struct commit *commit, struct log return 0; parse_commit_or_die(commit); - oid = &commit->tree->object.oid; + oid = get_commit_tree_oid(commit); /* Root commit? */ parents = get_saved_parents(opt, commit); @@ -831,7 +832,7 @@ static int log_tree_diff(struct rev_info *opt, struct commit *commit, struct log * we merged _in_. */ parse_commit_or_die(parents->item); - diff_tree_oid(&parents->item->tree->object.oid, + diff_tree_oid(get_commit_tree_oid(parents->item), oid, "", &opt->diffopt); log_tree_diff_flush(opt); return !opt->loginfo; @@ -846,7 +847,7 @@ static int log_tree_diff(struct rev_info *opt, struct commit *commit, struct log struct commit *parent = parents->item; parse_commit_or_die(parent); - diff_tree_oid(&parent->tree->object.oid, + diff_tree_oid(get_commit_tree_oid(parent), oid, "", &opt->diffopt); log_tree_diff_flush(opt); diff --git a/ls-refs.c b/ls-refs.c new file mode 100644 index 0000000000..a06f12eca8 --- /dev/null +++ b/ls-refs.c @@ -0,0 +1,96 @@ +#include "cache.h" +#include "repository.h" +#include "refs.h" +#include "remote.h" +#include "argv-array.h" +#include "ls-refs.h" +#include "pkt-line.h" + +/* + * Check if one of the prefixes is a prefix of the ref. + * If no prefixes were provided, all refs match. + */ +static int ref_match(const struct argv_array *prefixes, const char *refname) +{ + int i; + + if (!prefixes->argc) + return 1; /* no restriction */ + + for (i = 0; i < prefixes->argc; i++) { + const char *prefix = prefixes->argv[i]; + + if (starts_with(refname, prefix)) + return 1; + } + + return 0; +} + +struct ls_refs_data { + unsigned peel; + unsigned symrefs; + struct argv_array prefixes; +}; + +static int send_ref(const char *refname, const struct object_id *oid, + int flag, void *cb_data) +{ + struct ls_refs_data *data = cb_data; + const char *refname_nons = strip_namespace(refname); + struct strbuf refline = STRBUF_INIT; + + if (!ref_match(&data->prefixes, refname)) + return 0; + + strbuf_addf(&refline, "%s %s", oid_to_hex(oid), refname_nons); + if (data->symrefs && flag & REF_ISSYMREF) { + struct object_id unused; + const char *symref_target = resolve_ref_unsafe(refname, 0, + &unused, + &flag); + + if (!symref_target) + die("'%s' is a symref but it is not?", refname); + + strbuf_addf(&refline, " symref-target:%s", symref_target); + } + + if (data->peel) { + struct object_id peeled; + if (!peel_ref(refname, &peeled)) + strbuf_addf(&refline, " peeled:%s", oid_to_hex(&peeled)); + } + + strbuf_addch(&refline, '\n'); + packet_write(1, refline.buf, refline.len); + + strbuf_release(&refline); + return 0; +} + +int ls_refs(struct repository *r, struct argv_array *keys, + struct packet_reader *request) +{ + struct ls_refs_data data; + + memset(&data, 0, sizeof(data)); + + while (packet_reader_read(request) != PACKET_READ_FLUSH) { + const char *arg = request->line; + const char *out; + + if (!strcmp("peel", arg)) + data.peel = 1; + else if (!strcmp("symrefs", arg)) + data.symrefs = 1; + else if (skip_prefix(arg, "ref-prefix ", &out)) + argv_array_push(&data.prefixes, out); + } + + head_ref_namespaced(send_ref, &data); + for_each_namespaced_ref(send_ref, &data); + packet_flush(1); + argv_array_clear(&data.prefixes); + return 0; +} diff --git a/ls-refs.h b/ls-refs.h new file mode 100644 index 0000000000..b62877e8da --- /dev/null +++ b/ls-refs.h @@ -0,0 +1,10 @@ +#ifndef LS_REFS_H +#define LS_REFS_H + +struct repository; +struct argv_array; +struct packet_reader; +extern int ls_refs(struct repository *r, struct argv_array *keys, + struct packet_reader *request); + +#endif /* LS_REFS_H */ diff --git a/merge-recursive.c b/merge-recursive.c index 0c0d48624d..35df695fa4 100644 --- a/merge-recursive.c +++ b/merge-recursive.c @@ -49,6 +49,67 @@ static unsigned int path_hash(const char *path) return ignore_case ? strihash(path) : strhash(path); } +static struct dir_rename_entry *dir_rename_find_entry(struct hashmap *hashmap, + char *dir) +{ + struct dir_rename_entry key; + + if (dir == NULL) + return NULL; + hashmap_entry_init(&key, strhash(dir)); + key.dir = dir; + return hashmap_get(hashmap, &key, NULL); +} + +static int dir_rename_cmp(const void *unused_cmp_data, + const void *entry, + const void *entry_or_key, + const void *unused_keydata) +{ + const struct dir_rename_entry *e1 = entry; + const struct dir_rename_entry *e2 = entry_or_key; + + return strcmp(e1->dir, e2->dir); +} + +static void dir_rename_init(struct hashmap *map) +{ + hashmap_init(map, dir_rename_cmp, NULL, 0); +} + +static void dir_rename_entry_init(struct dir_rename_entry *entry, + char *directory) +{ + hashmap_entry_init(entry, strhash(directory)); + entry->dir = directory; + entry->non_unique_new_dir = 0; + strbuf_init(&entry->new_dir, 0); + string_list_init(&entry->possible_new_dirs, 0); +} + +static struct collision_entry *collision_find_entry(struct hashmap *hashmap, + char *target_file) +{ + struct collision_entry key; + + hashmap_entry_init(&key, strhash(target_file)); + key.target_file = target_file; + return hashmap_get(hashmap, &key, NULL); +} + +static int collision_cmp(void *unused_cmp_data, + const struct collision_entry *e1, + const struct collision_entry *e2, + const void *unused_keydata) +{ + return strcmp(e1->target_file, e2->target_file); +} + +static void collision_init(struct hashmap *map) +{ + hashmap_init(map, (hashmap_cmp_fn) collision_cmp, NULL, 0); +} + static void flush_output(struct merge_options *o) { if (o->buffer_output < 2 && o->obuf.len) { @@ -101,7 +162,7 @@ static struct commit *make_virtual_commit(struct tree *tree, const char *comment struct commit *commit = alloc_commit_node(); set_merge_remote_desc(commit, comment, (struct object *)commit); - commit->tree = tree; + commit->maybe_tree = tree; commit->object.parsed = 1; return commit; } @@ -119,6 +180,7 @@ static int oid_eq(const struct object_id *a, const struct object_id *b) enum rename_type { RENAME_NORMAL = 0, + RENAME_DIR, RENAME_DELETE, RENAME_ONE_FILE_TO_ONE, RENAME_ONE_FILE_TO_TWO, @@ -254,7 +316,7 @@ static int add_cacheinfo(struct merge_options *o, ce = make_cache_entry(mode, oid ? oid->hash : null_sha1, path, stage, 0); if (!ce) - return err(o, _("addinfo_cache failed for path '%s'"), path); + return err(o, _("add_cacheinfo failed for path '%s'; merge aborting."), path); ret = add_cache_entry(ce, options); if (refresh) { @@ -262,7 +324,7 @@ static int add_cacheinfo(struct merge_options *o, nce = refresh_cache_entry(ce, CE_MATCH_REFRESH | CE_MATCH_IGNORE_MISSING); if (!nce) - return err(o, _("addinfo_cache failed for path '%s'"), path); + return err(o, _("add_cacheinfo failed to refresh for path '%s'; merge aborting."), path); if (nce != ce) ret = add_cache_entry(nce, options); } @@ -275,33 +337,44 @@ static void init_tree_desc_from_tree(struct tree_desc *desc, struct tree *tree) init_tree_desc(desc, tree->buffer, tree->size); } -static int git_merge_trees(int index_only, +static int git_merge_trees(struct merge_options *o, struct tree *common, struct tree *head, struct tree *merge) { int rc; struct tree_desc t[3]; - struct unpack_trees_options opts; + struct index_state tmp_index = { NULL }; - memset(&opts, 0, sizeof(opts)); - if (index_only) - opts.index_only = 1; + memset(&o->unpack_opts, 0, sizeof(o->unpack_opts)); + if (o->call_depth) + o->unpack_opts.index_only = 1; else - opts.update = 1; - opts.merge = 1; - opts.head_idx = 2; - opts.fn = threeway_merge; - opts.src_index = &the_index; - opts.dst_index = &the_index; - setup_unpack_trees_porcelain(&opts, "merge"); + o->unpack_opts.update = 1; + o->unpack_opts.merge = 1; + o->unpack_opts.head_idx = 2; + o->unpack_opts.fn = threeway_merge; + o->unpack_opts.src_index = &the_index; + o->unpack_opts.dst_index = &tmp_index; + setup_unpack_trees_porcelain(&o->unpack_opts, "merge"); init_tree_desc_from_tree(t+0, common); init_tree_desc_from_tree(t+1, head); init_tree_desc_from_tree(t+2, merge); - rc = unpack_trees(3, t, &opts); + rc = unpack_trees(3, t, &o->unpack_opts); cache_tree_free(&active_cache_tree); + + /* + * Update the_index to match the new results, AFTER saving a copy + * in o->orig_index. Update src_index to point to the saved copy. + * (verify_uptodate() checks src_index, and the original index is + * the one that had the necessary modification timestamps.) + */ + o->orig_index = the_index; + the_index = tmp_index; + o->unpack_opts.src_index = &o->orig_index; + return rc; } @@ -360,6 +433,21 @@ static void get_files_dirs(struct merge_options *o, struct tree *tree) read_tree_recursive(tree, "", 0, 0, &match_all, save_files_dirs, o); } +static int get_tree_entry_if_blob(const struct object_id *tree, + const char *path, + struct object_id *hashy, + unsigned int *mode_o) +{ + int ret; + + ret = get_tree_entry(tree, path, hashy, mode_o); + if (S_ISDIR(*mode_o)) { + oidcpy(hashy, &null_oid); + *mode_o = 0; + } + return ret; +} + /* * Returns an index_entry instance which doesn't have to correspond to * a real cache entry in Git's index. @@ -370,12 +458,12 @@ static struct stage_data *insert_stage_data(const char *path, { struct string_list_item *item; struct stage_data *e = xcalloc(1, sizeof(struct stage_data)); - get_tree_entry(&o->object.oid, path, - &e->stages[1].oid, &e->stages[1].mode); - get_tree_entry(&a->object.oid, path, - &e->stages[2].oid, &e->stages[2].mode); - get_tree_entry(&b->object.oid, path, - &e->stages[3].oid, &e->stages[3].mode); + get_tree_entry_if_blob(&o->object.oid, path, + &e->stages[1].oid, &e->stages[1].mode); + get_tree_entry_if_blob(&a->object.oid, path, + &e->stages[2].oid, &e->stages[2].mode); + get_tree_entry_if_blob(&b->object.oid, path, + &e->stages[3].oid, &e->stages[3].mode); item = string_list_insert(entries, path); item->util = e; return e; @@ -534,78 +622,10 @@ struct rename { */ struct stage_data *src_entry; struct stage_data *dst_entry; + unsigned add_turned_into_rename:1; unsigned processed:1; }; -/* - * Get information of all renames which occurred between 'o_tree' and - * 'tree'. We need the three trees in the merge ('o_tree', 'a_tree' and - * 'b_tree') to be able to associate the correct cache entries with - * the rename information. 'tree' is always equal to either a_tree or b_tree. - */ -static struct string_list *get_renames(struct merge_options *o, - struct tree *tree, - struct tree *o_tree, - struct tree *a_tree, - struct tree *b_tree, - struct string_list *entries) -{ - int i; - struct string_list *renames; - struct diff_options opts; - - renames = xcalloc(1, sizeof(struct string_list)); - if (!o->detect_rename) - return renames; - - diff_setup(&opts); - opts.flags.recursive = 1; - opts.flags.rename_empty = 0; - opts.detect_rename = DIFF_DETECT_RENAME; - opts.rename_limit = o->merge_rename_limit >= 0 ? o->merge_rename_limit : - o->diff_rename_limit >= 0 ? o->diff_rename_limit : - 1000; - opts.rename_score = o->rename_score; - opts.show_rename_progress = o->show_rename_progress; - opts.output_format = DIFF_FORMAT_NO_OUTPUT; - diff_setup_done(&opts); - diff_tree_oid(&o_tree->object.oid, &tree->object.oid, "", &opts); - diffcore_std(&opts); - if (opts.needed_rename_limit > o->needed_rename_limit) - o->needed_rename_limit = opts.needed_rename_limit; - for (i = 0; i < diff_queued_diff.nr; ++i) { - struct string_list_item *item; - struct rename *re; - struct diff_filepair *pair = diff_queued_diff.queue[i]; - if (pair->status != 'R') { - diff_free_filepair(pair); - continue; - } - re = xmalloc(sizeof(*re)); - re->processed = 0; - re->pair = pair; - item = string_list_lookup(entries, re->pair->one->path); - if (!item) - re->src_entry = insert_stage_data(re->pair->one->path, - o_tree, a_tree, b_tree, entries); - else - re->src_entry = item->util; - - item = string_list_lookup(entries, re->pair->two->path); - if (!item) - re->dst_entry = insert_stage_data(re->pair->two->path, - o_tree, a_tree, b_tree, entries); - else - re->dst_entry = item->util; - item = string_list_insert(renames, pair->one->path); - item->util = re; - } - opts.output_format = DIFF_FORMAT_NO_OUTPUT; - diff_queued_diff.nr = 0; - diff_flush(&opts); - return renames; -} - static int update_stages(struct merge_options *opt, const char *path, const struct diff_filespec *o, const struct diff_filespec *a, @@ -637,6 +657,27 @@ static int update_stages(struct merge_options *opt, const char *path, return 0; } +static int update_stages_for_stage_data(struct merge_options *opt, + const char *path, + const struct stage_data *stage_data) +{ + struct diff_filespec o, a, b; + + o.mode = stage_data->stages[1].mode; + oidcpy(&o.oid, &stage_data->stages[1].oid); + + a.mode = stage_data->stages[2].mode; + oidcpy(&a.oid, &stage_data->stages[2].oid); + + b.mode = stage_data->stages[3].mode; + oidcpy(&b.oid, &stage_data->stages[3].oid); + + return update_stages(opt, path, + is_null_oid(&o.oid) ? NULL : &o, + is_null_oid(&a.oid) ? NULL : &a, + is_null_oid(&b.oid) ? NULL : &b); +} + static void update_entry(struct stage_data *entry, struct diff_filespec *o, struct diff_filespec *a, @@ -738,31 +779,92 @@ static int dir_in_way(const char *path, int check_working_copy, int empty_ok) !(empty_ok && is_empty_dir(path)); } -static int was_tracked(const char *path) +/* + * Returns whether path was tracked in the index before the merge started, + * and its oid and mode match the specified values + */ +static int was_tracked_and_matches(struct merge_options *o, const char *path, + const struct object_id *oid, unsigned mode) { - int pos = cache_name_pos(path, strlen(path)); + int pos = index_name_pos(&o->orig_index, path, strlen(path)); + struct cache_entry *ce; + + if (0 > pos) + /* we were not tracking this path before the merge */ + return 0; + + /* See if the file we were tracking before matches */ + ce = o->orig_index.cache[pos]; + return (oid_eq(&ce->oid, oid) && ce->ce_mode == mode); +} + +/* + * Returns whether path was tracked in the index before the merge started + */ +static int was_tracked(struct merge_options *o, const char *path) +{ + int pos = index_name_pos(&o->orig_index, path, strlen(path)); if (0 <= pos) - /* we have been tracking this path */ + /* we were tracking this path before the merge */ return 1; - /* - * Look for an unmerged entry for the path, - * specifically stage #2, which would indicate - * that "our" side before the merge started - * had the path tracked (and resulted in a conflict). - */ - for (pos = -1 - pos; - pos < active_nr && !strcmp(path, active_cache[pos]->name); - pos++) - if (ce_stage(active_cache[pos]) == 2) - return 1; return 0; } static int would_lose_untracked(const char *path) { - return !was_tracked(path) && file_exists(path); + /* + * This may look like it can be simplified to: + * return !was_tracked(o, path) && file_exists(path) + * but it can't. This function needs to know whether path was in + * the working tree due to EITHER having been tracked in the index + * before the merge OR having been put into the working copy and + * index by unpack_trees(). Due to that either-or requirement, we + * check the current index instead of the original one. + * + * Note that we do not need to worry about merge-recursive itself + * updating the index after unpack_trees() and before calling this + * function, because we strictly require all code paths in + * merge-recursive to update the working tree first and the index + * second. Doing otherwise would break + * update_file()/would_lose_untracked(); see every comment in this + * file which mentions "update_stages". + */ + int pos = cache_name_pos(path, strlen(path)); + + if (pos < 0) + pos = -1 - pos; + while (pos < active_nr && + !strcmp(path, active_cache[pos]->name)) { + /* + * If stage #0, it is definitely tracked. + * If it has stage #2 then it was tracked + * before this merge started. All other + * cases the path was not tracked. + */ + switch (ce_stage(active_cache[pos])) { + case 0: + case 2: + return 0; + } + pos++; + } + return file_exists(path); +} + +static int was_dirty(struct merge_options *o, const char *path) +{ + struct cache_entry *ce; + int dirty = 1; + + if (o->call_depth || !was_tracked(o, path)) + return !dirty; + + ce = index_file_exists(o->unpack_opts.src_index, + path, strlen(path), ignore_case); + dirty = verify_uptodate(ce, &o->unpack_opts) != 0; + return dirty; } static int make_room_for_path(struct merge_options *o, const char *path) @@ -893,7 +995,9 @@ static int update_file_flags(struct merge_options *o, } update_index: if (!ret && update_cache) - add_cacheinfo(o, mode, oid, path, 0, update_wd, ADD_CACHE_OK_TO_ADD); + if (add_cacheinfo(o, mode, oid, path, 0, update_wd, + ADD_CACHE_OK_TO_ADD)) + return -1; return ret; } @@ -978,12 +1082,13 @@ static int merge_3way(struct merge_options *o, } static int merge_file_1(struct merge_options *o, - const struct diff_filespec *one, - const struct diff_filespec *a, - const struct diff_filespec *b, - const char *branch1, - const char *branch2, - struct merge_file_info *result) + const struct diff_filespec *one, + const struct diff_filespec *a, + const struct diff_filespec *b, + const char *filename, + const char *branch1, + const char *branch2, + struct merge_file_info *result) { result->merge = 0; result->clean = 1; @@ -1063,18 +1168,22 @@ static int merge_file_1(struct merge_options *o, die("BUG: unsupported object type in the tree"); } + if (result->merge) + output(o, 2, _("Auto-merging %s"), filename); + return 0; } static int merge_file_special_markers(struct merge_options *o, - const struct diff_filespec *one, - const struct diff_filespec *a, - const struct diff_filespec *b, - const char *branch1, - const char *filename1, - const char *branch2, - const char *filename2, - struct merge_file_info *mfi) + const struct diff_filespec *one, + const struct diff_filespec *a, + const struct diff_filespec *b, + const char *target_filename, + const char *branch1, + const char *filename1, + const char *branch2, + const char *filename2, + struct merge_file_info *mfi) { char *side1 = NULL; char *side2 = NULL; @@ -1085,22 +1194,23 @@ static int merge_file_special_markers(struct merge_options *o, if (filename2) side2 = xstrfmt("%s:%s", branch2, filename2); - ret = merge_file_1(o, one, a, b, + ret = merge_file_1(o, one, a, b, target_filename, side1 ? side1 : branch1, side2 ? side2 : branch2, mfi); + free(side1); free(side2); return ret; } static int merge_file_one(struct merge_options *o, - const char *path, - const struct object_id *o_oid, int o_mode, - const struct object_id *a_oid, int a_mode, - const struct object_id *b_oid, int b_mode, - const char *branch1, - const char *branch2, - struct merge_file_info *mfi) + const char *path, + const struct object_id *o_oid, int o_mode, + const struct object_id *a_oid, int a_mode, + const struct object_id *b_oid, int b_mode, + const char *branch1, + const char *branch2, + struct merge_file_info *mfi) { struct diff_filespec one, a, b; @@ -1111,7 +1221,39 @@ static int merge_file_one(struct merge_options *o, a.mode = a_mode; oidcpy(&b.oid, b_oid); b.mode = b_mode; - return merge_file_1(o, &one, &a, &b, branch1, branch2, mfi); + return merge_file_1(o, &one, &a, &b, path, branch1, branch2, mfi); +} + +static int conflict_rename_dir(struct merge_options *o, + struct diff_filepair *pair, + const char *rename_branch, + const char *other_branch) +{ + const struct diff_filespec *dest = pair->two; + + if (!o->call_depth && would_lose_untracked(dest->path)) { + char *alt_path = unique_path(o, dest->path, rename_branch); + + output(o, 1, _("Error: Refusing to lose untracked file at %s; " + "writing to %s instead."), + dest->path, alt_path); + /* + * Write the file in worktree at alt_path, but not in the + * index. Instead, write to dest->path for the index but + * only at the higher appropriate stage. + */ + if (update_file(o, 0, &dest->oid, dest->mode, alt_path)) + return -1; + free(alt_path); + return update_stages(o, dest->path, NULL, + rename_branch == o->branch1 ? dest : NULL, + rename_branch == o->branch1 ? NULL : dest); + } + + /* Update dest->path both in index and in worktree */ + if (update_file(o, 1, &dest->oid, dest->mode, dest->path)) + return -1; + return 0; } static int handle_change_delete(struct merge_options *o, @@ -1127,7 +1269,8 @@ static int handle_change_delete(struct merge_options *o, const char *update_path = path; int ret = 0; - if (dir_in_way(path, !o->call_depth, 0)) { + if (dir_in_way(path, !o->call_depth, 0) || + (!o->call_depth && would_lose_untracked(path))) { update_path = alt_path = unique_path(o, path, change_branch); } @@ -1242,17 +1385,34 @@ static int handle_file(struct merge_options *o, add = filespec_from_entry(&other, dst_entry, stage ^ 1); if (add) { + int ren_src_was_dirty = was_dirty(o, rename->path); char *add_name = unique_path(o, rename->path, other_branch); if (update_file(o, 0, &add->oid, add->mode, add_name)) return -1; - remove_file(o, 0, rename->path, 0); + if (ren_src_was_dirty) { + output(o, 1, _("Refusing to lose dirty file at %s"), + rename->path); + } + /* + * Because the double negatives somehow keep confusing me... + * 1) update_wd iff !ren_src_was_dirty. + * 2) no_wd iff !update_wd + * 3) so, no_wd == !!ren_src_was_dirty == ren_src_was_dirty + */ + remove_file(o, 0, rename->path, ren_src_was_dirty); dst_name = unique_path(o, rename->path, cur_branch); } else { if (dir_in_way(rename->path, !o->call_depth, 0)) { dst_name = unique_path(o, rename->path, cur_branch); output(o, 1, _("%s is a directory in %s adding as %s instead"), rename->path, other_branch, dst_name); + } else if (!o->call_depth && + would_lose_untracked(rename->path)) { + dst_name = unique_path(o, rename->path, cur_branch); + output(o, 1, _("Refusing to lose untracked file at %s; " + "adding as %s instead"), + rename->path, dst_name); } } if ((ret = update_file(o, 0, &rename->oid, rename->mode, dst_name))) @@ -1339,6 +1499,8 @@ static int conflict_rename_rename_2to1(struct merge_options *o, struct diff_filespec *c1 = ci->pair1->two; struct diff_filespec *c2 = ci->pair2->two; char *path = c1->path; /* == c2->path */ + char *path_side_1_desc; + char *path_side_2_desc; struct merge_file_info mfi_c1; struct merge_file_info mfi_c2; int ret; @@ -1352,13 +1514,19 @@ static int conflict_rename_rename_2to1(struct merge_options *o, remove_file(o, 1, a->path, o->call_depth || would_lose_untracked(a->path)); remove_file(o, 1, b->path, o->call_depth || would_lose_untracked(b->path)); + path_side_1_desc = xstrfmt("%s (was %s)", path, a->path); + path_side_2_desc = xstrfmt("%s (was %s)", path, b->path); if (merge_file_special_markers(o, a, c1, &ci->ren1_other, + path_side_1_desc, o->branch1, c1->path, o->branch2, ci->ren1_other.path, &mfi_c1) || merge_file_special_markers(o, b, &ci->ren2_other, c2, + path_side_2_desc, o->branch1, ci->ren2_other.path, o->branch2, c2->path, &mfi_c2)) return -1; + free(path_side_1_desc); + free(path_side_2_desc); if (o->call_depth) { /* @@ -1378,11 +1546,43 @@ static int conflict_rename_rename_2to1(struct merge_options *o, char *new_path2 = unique_path(o, path, ci->branch2); output(o, 1, _("Renaming %s to %s and %s to %s instead"), a->path, new_path1, b->path, new_path2); - remove_file(o, 0, path, 0); + if (was_dirty(o, path)) + output(o, 1, _("Refusing to lose dirty file at %s"), + path); + else if (would_lose_untracked(path)) + /* + * Only way we get here is if both renames were from + * a directory rename AND user had an untracked file + * at the location where both files end up after the + * two directory renames. See testcase 10d of t6043. + */ + output(o, 1, _("Refusing to lose untracked file at " + "%s, even though it's in the way."), + path); + else + remove_file(o, 0, path, 0); ret = update_file(o, 0, &mfi_c1.oid, mfi_c1.mode, new_path1); if (!ret) ret = update_file(o, 0, &mfi_c2.oid, mfi_c2.mode, new_path2); + /* + * unpack_trees() actually populates the index for us for + * "normal" rename/rename(2to1) situtations so that the + * correct entries are at the higher stages, which would + * make the call below to update_stages_for_stage_data + * unnecessary. However, if either of the renames came + * from a directory rename, then unpack_trees() will not + * have gotten the right data loaded into the index, so we + * need to do so now. (While it'd be tempting to move this + * call to update_stages_for_stage_data() to + * apply_directory_rename_modifications(), that would break + * our intermediate calls to would_lose_untracked() since + * those rely on the current in-memory index. See also the + * big "NOTE" in update_stages()). + */ + if (update_stages_for_stage_data(o, path, ci->dst_entry1)) + ret = -1; + free(new_path2); free(new_path1); } @@ -1390,6 +1590,754 @@ static int conflict_rename_rename_2to1(struct merge_options *o, return ret; } +/* + * Get the diff_filepairs changed between o_tree and tree. + */ +static struct diff_queue_struct *get_diffpairs(struct merge_options *o, + struct tree *o_tree, + struct tree *tree) +{ + struct diff_queue_struct *ret; + struct diff_options opts; + + diff_setup(&opts); + opts.flags.recursive = 1; + opts.flags.rename_empty = 0; + opts.detect_rename = DIFF_DETECT_RENAME; + opts.rename_limit = o->merge_rename_limit >= 0 ? o->merge_rename_limit : + o->diff_rename_limit >= 0 ? o->diff_rename_limit : + 1000; + opts.rename_score = o->rename_score; + opts.show_rename_progress = o->show_rename_progress; + opts.output_format = DIFF_FORMAT_NO_OUTPUT; + diff_setup_done(&opts); + diff_tree_oid(&o_tree->object.oid, &tree->object.oid, "", &opts); + diffcore_std(&opts); + if (opts.needed_rename_limit > o->needed_rename_limit) + o->needed_rename_limit = opts.needed_rename_limit; + + ret = xmalloc(sizeof(*ret)); + *ret = diff_queued_diff; + + opts.output_format = DIFF_FORMAT_NO_OUTPUT; + diff_queued_diff.nr = 0; + diff_queued_diff.queue = NULL; + diff_flush(&opts); + return ret; +} + +static int tree_has_path(struct tree *tree, const char *path) +{ + struct object_id hashy; + unsigned int mode_o; + + return !get_tree_entry(&tree->object.oid, path, + &hashy, &mode_o); +} + +/* + * Return a new string that replaces the beginning portion (which matches + * entry->dir), with entry->new_dir. In perl-speak: + * new_path_name = (old_path =~ s/entry->dir/entry->new_dir/); + * NOTE: + * Caller must ensure that old_path starts with entry->dir + '/'. + */ +static char *apply_dir_rename(struct dir_rename_entry *entry, + const char *old_path) +{ + struct strbuf new_path = STRBUF_INIT; + int oldlen, newlen; + + if (entry->non_unique_new_dir) + return NULL; + + oldlen = strlen(entry->dir); + newlen = entry->new_dir.len + (strlen(old_path) - oldlen) + 1; + strbuf_grow(&new_path, newlen); + strbuf_addbuf(&new_path, &entry->new_dir); + strbuf_addstr(&new_path, &old_path[oldlen]); + + return strbuf_detach(&new_path, NULL); +} + +static void get_renamed_dir_portion(const char *old_path, const char *new_path, + char **old_dir, char **new_dir) +{ + char *end_of_old, *end_of_new; + int old_len, new_len; + + *old_dir = NULL; + *new_dir = NULL; + + /* + * For + * "a/b/c/d/e/foo.c" -> "a/b/some/thing/else/e/foo.c" + * the "e/foo.c" part is the same, we just want to know that + * "a/b/c/d" was renamed to "a/b/some/thing/else" + * so, for this example, this function returns "a/b/c/d" in + * *old_dir and "a/b/some/thing/else" in *new_dir. + * + * Also, if the basename of the file changed, we don't care. We + * want to know which portion of the directory, if any, changed. + */ + end_of_old = strrchr(old_path, '/'); + end_of_new = strrchr(new_path, '/'); + + if (end_of_old == NULL || end_of_new == NULL) + return; + while (*--end_of_new == *--end_of_old && + end_of_old != old_path && + end_of_new != new_path) + ; /* Do nothing; all in the while loop */ + /* + * We've found the first non-matching character in the directory + * paths. That means the current directory we were comparing + * represents the rename. Move end_of_old and end_of_new back + * to the full directory name. + */ + if (*end_of_old == '/') + end_of_old++; + if (*end_of_old != '/') + end_of_new++; + end_of_old = strchr(end_of_old, '/'); + end_of_new = strchr(end_of_new, '/'); + + /* + * It may have been the case that old_path and new_path were the same + * directory all along. Don't claim a rename if they're the same. + */ + old_len = end_of_old - old_path; + new_len = end_of_new - new_path; + + if (old_len != new_len || strncmp(old_path, new_path, old_len)) { + *old_dir = xstrndup(old_path, old_len); + *new_dir = xstrndup(new_path, new_len); + } +} + +static void remove_hashmap_entries(struct hashmap *dir_renames, + struct string_list *items_to_remove) +{ + int i; + struct dir_rename_entry *entry; + + for (i = 0; i < items_to_remove->nr; i++) { + entry = items_to_remove->items[i].util; + hashmap_remove(dir_renames, entry, NULL); + } + string_list_clear(items_to_remove, 0); +} + +/* + * See if there is a directory rename for path, and if there are any file + * level conflicts for the renamed location. If there is a rename and + * there are no conflicts, return the new name. Otherwise, return NULL. + */ +static char *handle_path_level_conflicts(struct merge_options *o, + const char *path, + struct dir_rename_entry *entry, + struct hashmap *collisions, + struct tree *tree) +{ + char *new_path = NULL; + struct collision_entry *collision_ent; + int clean = 1; + struct strbuf collision_paths = STRBUF_INIT; + + /* + * entry has the mapping of old directory name to new directory name + * that we want to apply to path. + */ + new_path = apply_dir_rename(entry, path); + + if (!new_path) { + /* This should only happen when entry->non_unique_new_dir set */ + if (!entry->non_unique_new_dir) + BUG("entry->non_unqiue_dir not set and !new_path"); + output(o, 1, _("CONFLICT (directory rename split): " + "Unclear where to place %s because directory " + "%s was renamed to multiple other directories, " + "with no destination getting a majority of the " + "files."), + path, entry->dir); + clean = 0; + return NULL; + } + + /* + * The caller needs to have ensured that it has pre-populated + * collisions with all paths that map to new_path. Do a quick check + * to ensure that's the case. + */ + collision_ent = collision_find_entry(collisions, new_path); + if (collision_ent == NULL) + BUG("collision_ent is NULL"); + + /* + * Check for one-sided add/add/.../add conflicts, i.e. + * where implicit renames from the other side doing + * directory rename(s) can affect this side of history + * to put multiple paths into the same location. Warn + * and bail on directory renames for such paths. + */ + if (collision_ent->reported_already) { + clean = 0; + } else if (tree_has_path(tree, new_path)) { + collision_ent->reported_already = 1; + strbuf_add_separated_string_list(&collision_paths, ", ", + &collision_ent->source_files); + output(o, 1, _("CONFLICT (implicit dir rename): Existing " + "file/dir at %s in the way of implicit " + "directory rename(s) putting the following " + "path(s) there: %s."), + new_path, collision_paths.buf); + clean = 0; + } else if (collision_ent->source_files.nr > 1) { + collision_ent->reported_already = 1; + strbuf_add_separated_string_list(&collision_paths, ", ", + &collision_ent->source_files); + output(o, 1, _("CONFLICT (implicit dir rename): Cannot map " + "more than one path to %s; implicit directory " + "renames tried to put these paths there: %s"), + new_path, collision_paths.buf); + clean = 0; + } + + /* Free memory we no longer need */ + strbuf_release(&collision_paths); + if (!clean && new_path) { + free(new_path); + return NULL; + } + + return new_path; +} + +/* + * There are a couple things we want to do at the directory level: + * 1. Check for both sides renaming to the same thing, in order to avoid + * implicit renaming of files that should be left in place. (See + * testcase 6b in t6043 for details.) + * 2. Prune directory renames if there are still files left in the + * the original directory. These represent a partial directory rename, + * i.e. a rename where only some of the files within the directory + * were renamed elsewhere. (Technically, this could be done earlier + * in get_directory_renames(), except that would prevent us from + * doing the previous check and thus failing testcase 6b.) + * 3. Check for rename/rename(1to2) conflicts (at the directory level). + * In the future, we could potentially record this info as well and + * omit reporting rename/rename(1to2) conflicts for each path within + * the affected directories, thus cleaning up the merge output. + * NOTE: We do NOT check for rename/rename(2to1) conflicts at the + * directory level, because merging directories is fine. If it + * causes conflicts for files within those merged directories, then + * that should be detected at the individual path level. + */ +static void handle_directory_level_conflicts(struct merge_options *o, + struct hashmap *dir_re_head, + struct tree *head, + struct hashmap *dir_re_merge, + struct tree *merge) +{ + struct hashmap_iter iter; + struct dir_rename_entry *head_ent; + struct dir_rename_entry *merge_ent; + + struct string_list remove_from_head = STRING_LIST_INIT_NODUP; + struct string_list remove_from_merge = STRING_LIST_INIT_NODUP; + + hashmap_iter_init(dir_re_head, &iter); + while ((head_ent = hashmap_iter_next(&iter))) { + merge_ent = dir_rename_find_entry(dir_re_merge, head_ent->dir); + if (merge_ent && + !head_ent->non_unique_new_dir && + !merge_ent->non_unique_new_dir && + !strbuf_cmp(&head_ent->new_dir, &merge_ent->new_dir)) { + /* 1. Renamed identically; remove it from both sides */ + string_list_append(&remove_from_head, + head_ent->dir)->util = head_ent; + strbuf_release(&head_ent->new_dir); + string_list_append(&remove_from_merge, + merge_ent->dir)->util = merge_ent; + strbuf_release(&merge_ent->new_dir); + } else if (tree_has_path(head, head_ent->dir)) { + /* 2. This wasn't a directory rename after all */ + string_list_append(&remove_from_head, + head_ent->dir)->util = head_ent; + strbuf_release(&head_ent->new_dir); + } + } + + remove_hashmap_entries(dir_re_head, &remove_from_head); + remove_hashmap_entries(dir_re_merge, &remove_from_merge); + + hashmap_iter_init(dir_re_merge, &iter); + while ((merge_ent = hashmap_iter_next(&iter))) { + head_ent = dir_rename_find_entry(dir_re_head, merge_ent->dir); + if (tree_has_path(merge, merge_ent->dir)) { + /* 2. This wasn't a directory rename after all */ + string_list_append(&remove_from_merge, + merge_ent->dir)->util = merge_ent; + } else if (head_ent && + !head_ent->non_unique_new_dir && + !merge_ent->non_unique_new_dir) { + /* 3. rename/rename(1to2) */ + /* + * We can assume it's not rename/rename(1to1) because + * that was case (1), already checked above. So we + * know that head_ent->new_dir and merge_ent->new_dir + * are different strings. + */ + output(o, 1, _("CONFLICT (rename/rename): " + "Rename directory %s->%s in %s. " + "Rename directory %s->%s in %s"), + head_ent->dir, head_ent->new_dir.buf, o->branch1, + head_ent->dir, merge_ent->new_dir.buf, o->branch2); + string_list_append(&remove_from_head, + head_ent->dir)->util = head_ent; + strbuf_release(&head_ent->new_dir); + string_list_append(&remove_from_merge, + merge_ent->dir)->util = merge_ent; + strbuf_release(&merge_ent->new_dir); + } + } + + remove_hashmap_entries(dir_re_head, &remove_from_head); + remove_hashmap_entries(dir_re_merge, &remove_from_merge); +} + +static struct hashmap *get_directory_renames(struct diff_queue_struct *pairs, + struct tree *tree) +{ + struct hashmap *dir_renames; + struct hashmap_iter iter; + struct dir_rename_entry *entry; + int i; + + /* + * Typically, we think of a directory rename as all files from a + * certain directory being moved to a target directory. However, + * what if someone first moved two files from the original + * directory in one commit, and then renamed the directory + * somewhere else in a later commit? At merge time, we just know + * that files from the original directory went to two different + * places, and that the bulk of them ended up in the same place. + * We want each directory rename to represent where the bulk of the + * files from that directory end up; this function exists to find + * where the bulk of the files went. + * + * The first loop below simply iterates through the list of file + * renames, finding out how often each directory rename pair + * possibility occurs. + */ + dir_renames = xmalloc(sizeof(*dir_renames)); + dir_rename_init(dir_renames); + for (i = 0; i < pairs->nr; ++i) { + struct string_list_item *item; + int *count; + struct diff_filepair *pair = pairs->queue[i]; + char *old_dir, *new_dir; + + /* File not part of directory rename if it wasn't renamed */ + if (pair->status != 'R') + continue; + + get_renamed_dir_portion(pair->one->path, pair->two->path, + &old_dir, &new_dir); + if (!old_dir) + /* Directory didn't change at all; ignore this one. */ + continue; + + entry = dir_rename_find_entry(dir_renames, old_dir); + if (!entry) { + entry = xmalloc(sizeof(*entry)); + dir_rename_entry_init(entry, old_dir); + hashmap_put(dir_renames, entry); + } else { + free(old_dir); + } + item = string_list_lookup(&entry->possible_new_dirs, new_dir); + if (!item) { + item = string_list_insert(&entry->possible_new_dirs, + new_dir); + item->util = xcalloc(1, sizeof(int)); + } else { + free(new_dir); + } + count = item->util; + *count += 1; + } + + /* + * For each directory with files moved out of it, we find out which + * target directory received the most files so we can declare it to + * be the "winning" target location for the directory rename. This + * winner gets recorded in new_dir. If there is no winner + * (multiple target directories received the same number of files), + * we set non_unique_new_dir. Once we've determined the winner (or + * that there is no winner), we no longer need possible_new_dirs. + */ + hashmap_iter_init(dir_renames, &iter); + while ((entry = hashmap_iter_next(&iter))) { + int max = 0; + int bad_max = 0; + char *best = NULL; + + for (i = 0; i < entry->possible_new_dirs.nr; i++) { + int *count = entry->possible_new_dirs.items[i].util; + + if (*count == max) + bad_max = max; + else if (*count > max) { + max = *count; + best = entry->possible_new_dirs.items[i].string; + } + } + if (bad_max == max) + entry->non_unique_new_dir = 1; + else { + assert(entry->new_dir.len == 0); + strbuf_addstr(&entry->new_dir, best); + } + /* + * The relevant directory sub-portion of the original full + * filepaths were xstrndup'ed before inserting into + * possible_new_dirs, and instead of manually iterating the + * list and free'ing each, just lie and tell + * possible_new_dirs that it did the strdup'ing so that it + * will free them for us. + */ + entry->possible_new_dirs.strdup_strings = 1; + string_list_clear(&entry->possible_new_dirs, 1); + } + + return dir_renames; +} + +static struct dir_rename_entry *check_dir_renamed(const char *path, + struct hashmap *dir_renames) +{ + char temp[PATH_MAX]; + char *end; + struct dir_rename_entry *entry; + + strcpy(temp, path); + while ((end = strrchr(temp, '/'))) { + *end = '\0'; + entry = dir_rename_find_entry(dir_renames, temp); + if (entry) + return entry; + } + return NULL; +} + +static void compute_collisions(struct hashmap *collisions, + struct hashmap *dir_renames, + struct diff_queue_struct *pairs) +{ + int i; + + /* + * Multiple files can be mapped to the same path due to directory + * renames done by the other side of history. Since that other + * side of history could have merged multiple directories into one, + * if our side of history added the same file basename to each of + * those directories, then all N of them would get implicitly + * renamed by the directory rename detection into the same path, + * and we'd get an add/add/.../add conflict, and all those adds + * from *this* side of history. This is not representable in the + * index, and users aren't going to easily be able to make sense of + * it. So we need to provide a good warning about what's + * happening, and fall back to no-directory-rename detection + * behavior for those paths. + * + * See testcases 9e and all of section 5 from t6043 for examples. + */ + collision_init(collisions); + + for (i = 0; i < pairs->nr; ++i) { + struct dir_rename_entry *dir_rename_ent; + struct collision_entry *collision_ent; + char *new_path; + struct diff_filepair *pair = pairs->queue[i]; + + if (pair->status != 'A' && pair->status != 'R') + continue; + dir_rename_ent = check_dir_renamed(pair->two->path, + dir_renames); + if (!dir_rename_ent) + continue; + + new_path = apply_dir_rename(dir_rename_ent, pair->two->path); + if (!new_path) + /* + * dir_rename_ent->non_unique_new_path is true, which + * means there is no directory rename for us to use, + * which means it won't cause us any additional + * collisions. + */ + continue; + collision_ent = collision_find_entry(collisions, new_path); + if (!collision_ent) { + collision_ent = xcalloc(1, + sizeof(struct collision_entry)); + hashmap_entry_init(collision_ent, strhash(new_path)); + hashmap_put(collisions, collision_ent); + collision_ent->target_file = new_path; + } else { + free(new_path); + } + string_list_insert(&collision_ent->source_files, + pair->two->path); + } +} + +static char *check_for_directory_rename(struct merge_options *o, + const char *path, + struct tree *tree, + struct hashmap *dir_renames, + struct hashmap *dir_rename_exclusions, + struct hashmap *collisions, + int *clean_merge) +{ + char *new_path = NULL; + struct dir_rename_entry *entry = check_dir_renamed(path, dir_renames); + struct dir_rename_entry *oentry = NULL; + + if (!entry) + return new_path; + + /* + * This next part is a little weird. We do not want to do an + * implicit rename into a directory we renamed on our side, because + * that will result in a spurious rename/rename(1to2) conflict. An + * example: + * Base commit: dumbdir/afile, otherdir/bfile + * Side 1: smrtdir/afile, otherdir/bfile + * Side 2: dumbdir/afile, dumbdir/bfile + * Here, while working on Side 1, we could notice that otherdir was + * renamed/merged to dumbdir, and change the diff_filepair for + * otherdir/bfile into a rename into dumbdir/bfile. However, Side + * 2 will notice the rename from dumbdir to smrtdir, and do the + * transitive rename to move it from dumbdir/bfile to + * smrtdir/bfile. That gives us bfile in dumbdir vs being in + * smrtdir, a rename/rename(1to2) conflict. We really just want + * the file to end up in smrtdir. And the way to achieve that is + * to not let Side1 do the rename to dumbdir, since we know that is + * the source of one of our directory renames. + * + * That's why oentry and dir_rename_exclusions is here. + * + * As it turns out, this also prevents N-way transient rename + * confusion; See testcases 9c and 9d of t6043. + */ + oentry = dir_rename_find_entry(dir_rename_exclusions, entry->new_dir.buf); + if (oentry) { + output(o, 1, _("WARNING: Avoiding applying %s -> %s rename " + "to %s, because %s itself was renamed."), + entry->dir, entry->new_dir.buf, path, entry->new_dir.buf); + } else { + new_path = handle_path_level_conflicts(o, path, entry, + collisions, tree); + *clean_merge &= (new_path != NULL); + } + + return new_path; +} + +static void apply_directory_rename_modifications(struct merge_options *o, + struct diff_filepair *pair, + char *new_path, + struct rename *re, + struct tree *tree, + struct tree *o_tree, + struct tree *a_tree, + struct tree *b_tree, + struct string_list *entries, + int *clean) +{ + struct string_list_item *item; + int stage = (tree == a_tree ? 2 : 3); + int update_wd; + + /* + * In all cases where we can do directory rename detection, + * unpack_trees() will have read pair->two->path into the + * index and the working copy. We need to remove it so that + * we can instead place it at new_path. It is guaranteed to + * not be untracked (unpack_trees() would have errored out + * saying the file would have been overwritten), but it might + * be dirty, though. + */ + update_wd = !was_dirty(o, pair->two->path); + if (!update_wd) + output(o, 1, _("Refusing to lose dirty file at %s"), + pair->two->path); + remove_file(o, 1, pair->two->path, !update_wd); + + /* Find or create a new re->dst_entry */ + item = string_list_lookup(entries, new_path); + if (item) { + /* + * Since we're renaming on this side of history, and it's + * due to a directory rename on the other side of history + * (which we only allow when the directory in question no + * longer exists on the other side of history), the + * original entry for re->dst_entry is no longer + * necessary... + */ + re->dst_entry->processed = 1; + + /* + * ...because we'll be using this new one. + */ + re->dst_entry = item->util; + } else { + /* + * re->dst_entry is for the before-dir-rename path, and we + * need it to hold information for the after-dir-rename + * path. Before creating a new entry, we need to mark the + * old one as unnecessary (...unless it is shared by + * src_entry, i.e. this didn't use to be a rename, in which + * case we can just allow the normal processing to happen + * for it). + */ + if (pair->status == 'R') + re->dst_entry->processed = 1; + + re->dst_entry = insert_stage_data(new_path, + o_tree, a_tree, b_tree, + entries); + item = string_list_insert(entries, new_path); + item->util = re->dst_entry; + } + + /* + * Update the stage_data with the information about the path we are + * moving into place. That slot will be empty and available for us + * to write to because of the collision checks in + * handle_path_level_conflicts(). In other words, + * re->dst_entry->stages[stage].oid will be the null_oid, so it's + * open for us to write to. + * + * It may be tempting to actually update the index at this point as + * well, using update_stages_for_stage_data(), but as per the big + * "NOTE" in update_stages(), doing so will modify the current + * in-memory index which will break calls to would_lose_untracked() + * that we need to make. Instead, we need to just make sure that + * the various conflict_rename_*() functions update the index + * explicitly rather than relying on unpack_trees() to have done it. + */ + get_tree_entry(&tree->object.oid, + pair->two->path, + &re->dst_entry->stages[stage].oid, + &re->dst_entry->stages[stage].mode); + + /* Update pair status */ + if (pair->status == 'A') { + /* + * Recording rename information for this add makes it look + * like a rename/delete conflict. Make sure we can + * correctly handle this as an add that was moved to a new + * directory instead of reporting a rename/delete conflict. + */ + re->add_turned_into_rename = 1; + } + /* + * We don't actually look at pair->status again, but it seems + * pedagogically correct to adjust it. + */ + pair->status = 'R'; + + /* + * Finally, record the new location. + */ + pair->two->path = new_path; +} + +/* + * Get information of all renames which occurred in 'pairs', making use of + * any implicit directory renames inferred from the other side of history. + * We need the three trees in the merge ('o_tree', 'a_tree' and 'b_tree') + * to be able to associate the correct cache entries with the rename + * information; tree is always equal to either a_tree or b_tree. + */ +static struct string_list *get_renames(struct merge_options *o, + struct diff_queue_struct *pairs, + struct hashmap *dir_renames, + struct hashmap *dir_rename_exclusions, + struct tree *tree, + struct tree *o_tree, + struct tree *a_tree, + struct tree *b_tree, + struct string_list *entries, + int *clean_merge) +{ + int i; + struct hashmap collisions; + struct hashmap_iter iter; + struct collision_entry *e; + struct string_list *renames; + + compute_collisions(&collisions, dir_renames, pairs); + renames = xcalloc(1, sizeof(struct string_list)); + + for (i = 0; i < pairs->nr; ++i) { + struct string_list_item *item; + struct rename *re; + struct diff_filepair *pair = pairs->queue[i]; + char *new_path; /* non-NULL only with directory renames */ + + if (pair->status != 'A' && pair->status != 'R') { + diff_free_filepair(pair); + continue; + } + new_path = check_for_directory_rename(o, pair->two->path, tree, + dir_renames, + dir_rename_exclusions, + &collisions, + clean_merge); + if (pair->status != 'R' && !new_path) { + diff_free_filepair(pair); + continue; + } + + re = xmalloc(sizeof(*re)); + re->processed = 0; + re->add_turned_into_rename = 0; + re->pair = pair; + item = string_list_lookup(entries, re->pair->one->path); + if (!item) + re->src_entry = insert_stage_data(re->pair->one->path, + o_tree, a_tree, b_tree, entries); + else + re->src_entry = item->util; + + item = string_list_lookup(entries, re->pair->two->path); + if (!item) + re->dst_entry = insert_stage_data(re->pair->two->path, + o_tree, a_tree, b_tree, entries); + else + re->dst_entry = item->util; + item = string_list_insert(renames, pair->one->path); + item->util = re; + if (new_path) + apply_directory_rename_modifications(o, pair, new_path, + re, tree, o_tree, + a_tree, b_tree, + entries, + clean_merge); + } + + hashmap_iter_init(&collisions, &iter); + while ((e = hashmap_iter_next(&iter))) { + free(e->target_file); + string_list_clear(&e->source_files, 0); + } + hashmap_free(&collisions, 1); + return renames; +} + static int process_renames(struct merge_options *o, struct string_list *a_renames, struct string_list *b_renames) @@ -1538,7 +2486,7 @@ static int process_renames(struct merge_options *o, * add-source case). */ remove_file(o, 1, ren1_src, - renamed_stage == 2 || !was_tracked(ren1_src)); + renamed_stage == 2 || !was_tracked(o, ren1_src)); oidcpy(&src_other.oid, &ren1->src_entry->stages[other_stage].oid); @@ -1548,7 +2496,19 @@ static int process_renames(struct merge_options *o, dst_other.mode = ren1->dst_entry->stages[other_stage].mode; try_merge = 0; - if (oid_eq(&src_other.oid, &null_oid)) { + if (oid_eq(&src_other.oid, &null_oid) && + ren1->add_turned_into_rename) { + setup_rename_conflict_info(RENAME_DIR, + ren1->pair, + NULL, + branch1, + branch2, + ren1->dst_entry, + NULL, + o, + NULL, + NULL); + } else if (oid_eq(&src_other.oid, &null_oid)) { setup_rename_conflict_info(RENAME_DELETE, ren1->pair, NULL, @@ -1645,6 +2605,105 @@ cleanup_and_return: return clean_merge; } +struct rename_info { + struct string_list *head_renames; + struct string_list *merge_renames; +}; + +static void initial_cleanup_rename(struct diff_queue_struct *pairs, + struct hashmap *dir_renames) +{ + struct hashmap_iter iter; + struct dir_rename_entry *e; + + hashmap_iter_init(dir_renames, &iter); + while ((e = hashmap_iter_next(&iter))) { + free(e->dir); + strbuf_release(&e->new_dir); + /* possible_new_dirs already cleared in get_directory_renames */ + } + hashmap_free(dir_renames, 1); + free(dir_renames); + + free(pairs->queue); + free(pairs); +} + +static int handle_renames(struct merge_options *o, + struct tree *common, + struct tree *head, + struct tree *merge, + struct string_list *entries, + struct rename_info *ri) +{ + struct diff_queue_struct *head_pairs, *merge_pairs; + struct hashmap *dir_re_head, *dir_re_merge; + int clean = 1; + + ri->head_renames = NULL; + ri->merge_renames = NULL; + + if (!o->detect_rename) + return 1; + + head_pairs = get_diffpairs(o, common, head); + merge_pairs = get_diffpairs(o, common, merge); + + dir_re_head = get_directory_renames(head_pairs, head); + dir_re_merge = get_directory_renames(merge_pairs, merge); + + handle_directory_level_conflicts(o, + dir_re_head, head, + dir_re_merge, merge); + + ri->head_renames = get_renames(o, head_pairs, + dir_re_merge, dir_re_head, head, + common, head, merge, entries, + &clean); + if (clean < 0) + goto cleanup; + ri->merge_renames = get_renames(o, merge_pairs, + dir_re_head, dir_re_merge, merge, + common, head, merge, entries, + &clean); + if (clean < 0) + goto cleanup; + clean &= process_renames(o, ri->head_renames, ri->merge_renames); + +cleanup: + /* + * Some cleanup is deferred until cleanup_renames() because the + * data structures are still needed and referenced in + * process_entry(). But there are a few things we can free now. + */ + initial_cleanup_rename(head_pairs, dir_re_head); + initial_cleanup_rename(merge_pairs, dir_re_merge); + + return clean; +} + +static void final_cleanup_rename(struct string_list *rename) +{ + const struct rename *re; + int i; + + if (rename == NULL) + return; + + for (i = 0; i < rename->nr; i++) { + re = rename->items[i].util; + diff_free_filepair(re->pair); + } + string_list_clear(rename, 1); + free(rename); +} + +static void final_cleanup_renames(struct rename_info *re_info) +{ + final_cleanup_rename(re_info->head_renames); + final_cleanup_rename(re_info->merge_renames); +} + static struct object_id *stage_oid(const struct object_id *oid, unsigned mode) { return (is_null_oid(oid) || mode == 0) ? NULL: (struct object_id *)oid; @@ -1735,6 +2794,7 @@ static int handle_modify_delete(struct merge_options *o, static int merge_content(struct merge_options *o, const char *path, + int is_dirty, struct object_id *o_oid, int o_mode, struct object_id *a_oid, int a_mode, struct object_id *b_oid, int b_mode, @@ -1775,29 +2835,26 @@ static int merge_content(struct merge_options *o, S_ISGITLINK(pair1->two->mode))) df_conflict_remains = 1; } - if (merge_file_special_markers(o, &one, &a, &b, + if (merge_file_special_markers(o, &one, &a, &b, path, o->branch1, path1, o->branch2, path2, &mfi)) return -1; - if (mfi.clean && !df_conflict_remains && - oid_eq(&mfi.oid, a_oid) && mfi.mode == a_mode) { - int path_renamed_outside_HEAD; + /* + * We can skip updating the working tree file iff: + * a) The merge is clean + * b) The merge matches what was in HEAD (content, mode, pathname) + * c) The target path is usable (i.e. not involved in D/F conflict) + */ + if (mfi.clean && + was_tracked_and_matches(o, path, &mfi.oid, mfi.mode) && + !df_conflict_remains) { output(o, 3, _("Skipped %s (merged same as existing)"), path); - /* - * The content merge resulted in the same file contents we - * already had. We can return early if those file contents - * are recorded at the correct path (which may not be true - * if the merge involves a rename). - */ - path_renamed_outside_HEAD = !path2 || !strcmp(path, path2); - if (!path_renamed_outside_HEAD) { - add_cacheinfo(o, mfi.mode, &mfi.oid, path, - 0, (!o->call_depth), 0); - return mfi.clean; - } - } else - output(o, 2, _("Auto-merging %s"), path); + if (add_cacheinfo(o, mfi.mode, &mfi.oid, path, + 0, (!o->call_depth && !is_dirty), 0)) + return -1; + return mfi.clean; + } if (!mfi.clean) { if (S_ISGITLINK(mfi.mode)) @@ -1809,7 +2866,7 @@ static int merge_content(struct merge_options *o, return -1; } - if (df_conflict_remains) { + if (df_conflict_remains || is_dirty) { char *new_path; if (o->call_depth) { remove_file_from_cache(path); @@ -1818,7 +2875,7 @@ static int merge_content(struct merge_options *o, if (update_stages(o, path, &one, &a, &b)) return -1; } else { - int file_from_stage2 = was_tracked(path); + int file_from_stage2 = was_tracked(o, path); struct diff_filespec merged; oidcpy(&merged.oid, &mfi.oid); merged.mode = mfi.mode; @@ -1831,6 +2888,10 @@ static int merge_content(struct merge_options *o, } new_path = unique_path(o, path, rename_conflict_info->branch1); + if (is_dirty) { + output(o, 1, _("Refusing to lose dirty file at %s"), + path); + } output(o, 1, _("Adding as %s instead"), new_path); if (update_file(o, 0, &mfi.oid, mfi.mode, new_path)) { free(new_path); @@ -1840,7 +2901,20 @@ static int merge_content(struct merge_options *o, mfi.clean = 0; } else if (update_file(o, mfi.clean, &mfi.oid, mfi.mode, path)) return -1; - return mfi.clean; + return !is_dirty && mfi.clean; +} + +static int conflict_rename_normal(struct merge_options *o, + const char *path, + struct object_id *o_oid, unsigned int o_mode, + struct object_id *a_oid, unsigned int a_mode, + struct object_id *b_oid, unsigned int b_mode, + struct rename_conflict_info *ci) +{ + /* Merge the content and write it out */ + return merge_content(o, path, was_dirty(o, path), + o_oid, o_mode, a_oid, a_mode, b_oid, b_mode, + ci); } /* Per entry merge function */ @@ -1862,9 +2936,20 @@ static int process_entry(struct merge_options *o, switch (conflict_info->rename_type) { case RENAME_NORMAL: case RENAME_ONE_FILE_TO_ONE: - clean_merge = merge_content(o, path, - o_oid, o_mode, a_oid, a_mode, b_oid, b_mode, - conflict_info); + clean_merge = conflict_rename_normal(o, + path, + o_oid, o_mode, + a_oid, a_mode, + b_oid, b_mode, + conflict_info); + break; + case RENAME_DIR: + clean_merge = 1; + if (conflict_rename_dir(o, + conflict_info->pair1, + conflict_info->branch1, + conflict_info->branch2)) + clean_merge = -1; break; case RENAME_DELETE: clean_merge = 0; @@ -1952,7 +3037,8 @@ static int process_entry(struct merge_options *o, } else if (a_oid && b_oid) { /* Case C: Added in both (check for same permissions) and */ /* case D: Modified in both, but differently. */ - clean_merge = merge_content(o, path, + int is_dirty = 0; /* unpack_trees would have bailed if dirty */ + clean_merge = merge_content(o, path, is_dirty, o_oid, o_mode, a_oid, a_mode, b_oid, b_mode, NULL); } else if (!o_oid && !a_oid && !b_oid) { @@ -1993,7 +3079,7 @@ int merge_trees(struct merge_options *o, return 1; } - code = git_merge_trees(o->call_depth, common, head, merge); + code = git_merge_trees(o, common, head, merge); if (code != 0) { if (show(o, 4) || o->call_depth) @@ -2004,7 +3090,8 @@ int merge_trees(struct merge_options *o, } if (unmerged_cache()) { - struct string_list *entries, *re_head, *re_merge; + struct string_list *entries; + struct rename_info re_info; int i; /* * Only need the hashmap while processing entries, so @@ -2018,9 +3105,8 @@ int merge_trees(struct merge_options *o, get_files_dirs(o, merge); entries = get_unmerged(); - re_head = get_renames(o, head, common, head, merge, entries); - re_merge = get_renames(o, merge, common, head, merge, entries); - clean = process_renames(o, re_head, re_merge); + clean = handle_renames(o, common, head, merge, entries, + &re_info); record_df_conflict_files(o, entries); if (clean < 0) goto cleanup; @@ -2045,22 +3131,28 @@ int merge_trees(struct merge_options *o, } cleanup: - string_list_clear(re_merge, 0); - string_list_clear(re_head, 0); + final_cleanup_renames(&re_info); + string_list_clear(entries, 1); + free(entries); hashmap_free(&o->current_file_dir_set, 1); - free(re_merge); - free(re_head); - free(entries); - if (clean < 0) return clean; } else clean = 1; + /* Free the extra index left from git_merge_trees() */ + /* + * FIXME: Need to also free data allocated by + * setup_unpack_trees_porcelain() tucked away in o->unpack_opts.msgs, + * but the problem is that only half of it refers to dynamically + * allocated data, while the other half points at static strings. + */ + discard_index(&o->orig_index); + if (o->call_depth && !(*result = write_tree_from_memory(o))) return -1; @@ -2154,7 +3246,8 @@ int merge_recursive(struct merge_options *o, read_cache(); o->ancestor = "merged common ancestors"; - clean = merge_trees(o, h1->tree, h2->tree, merged_common_ancestors->tree, + clean = merge_trees(o, get_commit_tree(h1), get_commit_tree(h2), + get_commit_tree(merged_common_ancestors), &mrtree); if (clean < 0) { flush_output(o); diff --git a/merge-recursive.h b/merge-recursive.h index 80d69d1401..248093e407 100644 --- a/merge-recursive.h +++ b/merge-recursive.h @@ -1,6 +1,7 @@ #ifndef MERGE_RECURSIVE_H #define MERGE_RECURSIVE_H +#include "unpack-trees.h" #include "string-list.h" struct merge_options { @@ -27,6 +28,33 @@ struct merge_options { struct strbuf obuf; struct hashmap current_file_dir_set; struct string_list df_conflict_file_set; + struct unpack_trees_options unpack_opts; + struct index_state orig_index; +}; + +/* + * For dir_rename_entry, directory names are stored as a full path from the + * toplevel of the repository and do not include a trailing '/'. Also: + * + * dir: original name of directory being renamed + * non_unique_new_dir: if true, could not determine new_dir + * new_dir: final name of directory being renamed + * possible_new_dirs: temporary used to help determine new_dir; see comments + * in get_directory_renames() for details + */ +struct dir_rename_entry { + struct hashmap_entry ent; /* must be the first member! */ + char *dir; + unsigned non_unique_new_dir:1; + struct strbuf new_dir; + struct string_list possible_new_dirs; +}; + +struct collision_entry { + struct hashmap_entry ent; /* must be the first member! */ + char *target_file; + struct string_list source_files; + unsigned reported_already:1; }; /* merge_trees() but with recursive ancestor consolidation */ diff --git a/notes-merge.c b/notes-merge.c index 8e0726a941..e06d71ea47 100644 --- a/notes-merge.c +++ b/notes-merge.c @@ -600,14 +600,14 @@ int notes_merge(struct notes_merge_options *o, printf("No merge base found; doing history-less merge\n"); } else if (!bases->next) { base_oid = &bases->item->object.oid; - base_tree_oid = &bases->item->tree->object.oid; + base_tree_oid = get_commit_tree_oid(bases->item); if (o->verbosity >= 4) printf("One merge base found (%.7s)\n", oid_to_hex(base_oid)); } else { /* TODO: How to handle multiple merge-bases? */ base_oid = &bases->item->object.oid; - base_tree_oid = &bases->item->tree->object.oid; + base_tree_oid = get_commit_tree_oid(bases->item); if (o->verbosity >= 3) printf("Multiple merge bases found. Using the first " "(%.7s)\n", oid_to_hex(base_oid)); @@ -634,8 +634,9 @@ int notes_merge(struct notes_merge_options *o, goto found_result; } - result = merge_from_diffs(o, base_tree_oid, &local->tree->object.oid, - &remote->tree->object.oid, local_tree); + result = merge_from_diffs(o, base_tree_oid, + get_commit_tree_oid(local), + get_commit_tree_oid(remote), local_tree); if (result != 0) { /* non-trivial merge (with or without conflicts) */ /* Commit (partial) result */ diff --git a/object-store.h b/object-store.h index fef33f345f..d683112fd7 100644 --- a/object-store.h +++ b/object-store.h @@ -1,6 +1,8 @@ #ifndef OBJECT_STORE_H #define OBJECT_STORE_H +#include "oidmap.h" + struct alternate_object_database { struct alternate_object_database *next; @@ -69,8 +71,10 @@ struct packed_git { int index_version; time_t mtime; int pack_fd; + int index; /* for builtin/pack-objects.c */ unsigned pack_local:1, pack_keep:1, + pack_keep_in_core:1, freshened:1, do_not_close:1, pack_promisor:1; @@ -94,6 +98,12 @@ struct raw_object_store { struct alternate_object_database **alt_odb_tail; /* + * Objects that should be substituted by other objects + * (see git-replace(1)). + */ + struct oidmap *replace_map; + + /* * private data * * should only be accessed directly by packfile.c @@ -1,5 +1,6 @@ #include "cache.h" #include "object.h" +#include "replace-object.h" #include "blob.h" #include "tree.h" #include "commit.h" @@ -246,7 +247,7 @@ struct object *parse_object(const struct object_id *oid) unsigned long size; enum object_type type; int eaten; - const struct object_id *repl = lookup_replace_object(oid); + const struct object_id *repl = lookup_replace_object(the_repository, oid); void *buffer; struct object *obj; @@ -256,7 +257,7 @@ struct object *parse_object(const struct object_id *oid) if ((obj && obj->type == OBJ_BLOB && has_object_file(oid)) || (!obj && has_object_file(oid) && - oid_object_info(oid, NULL) == OBJ_BLOB)) { + oid_object_info(the_repository, oid, NULL) == OBJ_BLOB)) { if (check_object_signature(repl, NULL, 0, NULL) < 0) { error("sha1 mismatch %s", oid_to_hex(oid)); return NULL; @@ -480,6 +481,9 @@ void raw_object_store_clear(struct raw_object_store *o) FREE_AND_NULL(o->objectdir); FREE_AND_NULL(o->alternate_db); + oidmap_free(o->replace_map, 1); + FREE_AND_NULL(o->replace_map); + free_alt_odbs(o); o->alt_odb_tail = NULL; @@ -25,7 +25,6 @@ struct object_array { #define OBJECT_ARRAY_INIT { 0, 0, NULL } -#define TYPE_BITS 3 /* * object flag allocation: * revision.h: 0---------10 26 diff --git a/pack-bitmap-write.c b/pack-bitmap-write.c index 41ae27fb19..72d9daec7e 100644 --- a/pack-bitmap-write.c +++ b/pack-bitmap-write.c @@ -48,7 +48,8 @@ void bitmap_writer_show_progress(int show) /** * Build the initial type index for the packfile */ -void bitmap_writer_build_type_index(struct pack_idx_entry **index, +void bitmap_writer_build_type_index(struct packing_data *to_pack, + struct pack_idx_entry **index, uint32_t index_nr) { uint32_t i; @@ -57,23 +58,25 @@ void bitmap_writer_build_type_index(struct pack_idx_entry **index, writer.trees = ewah_new(); writer.blobs = ewah_new(); writer.tags = ewah_new(); + ALLOC_ARRAY(to_pack->in_pack_pos, to_pack->nr_objects); for (i = 0; i < index_nr; ++i) { struct object_entry *entry = (struct object_entry *)index[i]; enum object_type real_type; - entry->in_pack_pos = i; + oe_set_in_pack_pos(to_pack, entry, i); - switch (entry->type) { + switch (oe_type(entry)) { case OBJ_COMMIT: case OBJ_TREE: case OBJ_BLOB: case OBJ_TAG: - real_type = entry->type; + real_type = oe_type(entry); break; default: - real_type = oid_object_info(&entry->idx.oid, NULL); + real_type = oid_object_info(the_repository, + &entry->idx.oid, NULL); break; } @@ -97,7 +100,7 @@ void bitmap_writer_build_type_index(struct pack_idx_entry **index, default: die("Missing type information for %s (%d/%d)", oid_to_hex(&entry->idx.oid), real_type, - entry->type); + oe_type(entry)); } } } @@ -146,7 +149,7 @@ static uint32_t find_object_pos(const unsigned char *sha1) "(object %s is missing)", sha1_to_hex(sha1)); } - return entry->in_pack_pos; + return oe_in_pack_pos(writer.to_pack, entry); } static void show_object(struct object *object, const char *name, void *data) @@ -534,7 +537,7 @@ void bitmap_writer_finish(struct pack_idx_entry **index, if (options & BITMAP_OPT_HASH_CACHE) write_hash_cache(f, index, index_nr); - hashclose(f, NULL, CSUM_FSYNC); + finalize_hashfile(f, NULL, CSUM_HASH_IN_STREAM | CSUM_FSYNC | CSUM_CLOSE); if (adjust_shared_perm(tmp_file.buf)) die_errno("unable to make temporary bitmap file readable"); diff --git a/pack-bitmap.c b/pack-bitmap.c index 3f2dab340f..c9e90d1bb5 100644 --- a/pack-bitmap.c +++ b/pack-bitmap.c @@ -1033,7 +1033,7 @@ int rebuild_existing_bitmaps(struct packing_data *mapping, oe = packlist_find(mapping, sha1, NULL); if (oe) - reposition[i] = oe->in_pack_pos + 1; + reposition[i] = oe_in_pack_pos(mapping, oe) + 1; } rebuild = bitmap_new(); diff --git a/pack-bitmap.h b/pack-bitmap.h index 3742a00e14..5ded2f139a 100644 --- a/pack-bitmap.h +++ b/pack-bitmap.h @@ -44,7 +44,9 @@ int rebuild_existing_bitmaps(struct packing_data *mapping, khash_sha1 *reused_bi void bitmap_writer_show_progress(int show); void bitmap_writer_set_checksum(unsigned char *sha1); -void bitmap_writer_build_type_index(struct pack_idx_entry **index, uint32_t index_nr); +void bitmap_writer_build_type_index(struct packing_data *to_pack, + struct pack_idx_entry **index, + uint32_t index_nr); void bitmap_writer_reuse_bitmaps(struct packing_data *to_pack); void bitmap_writer_select_commits(struct commit **indexed_commits, unsigned int indexed_commits_nr, int max_bitmaps); diff --git a/pack-check.c b/pack-check.c index 385d964bdd..d3a57df34f 100644 --- a/pack-check.c +++ b/pack-check.c @@ -1,4 +1,5 @@ #include "cache.h" +#include "repository.h" #include "pack.h" #include "pack-revindex.h" #include "progress.h" @@ -134,7 +135,7 @@ static int verify_packfile(struct packed_git *p, data = NULL; data_valid = 0; } else { - data = unpack_entry(p, entries[i].offset, &type, &size); + data = unpack_entry(the_repository, p, entries[i].offset, &type, &size); data_valid = 1; } diff --git a/pack-objects.c b/pack-objects.c index 9558d13834..e0c4600568 100644 --- a/pack-objects.c +++ b/pack-objects.c @@ -2,6 +2,8 @@ #include "object.h" #include "pack.h" #include "pack-objects.h" +#include "packfile.h" +#include "config.h" static uint32_t locate_object_entry_hash(struct packing_data *pdata, const unsigned char *sha1, @@ -86,6 +88,66 @@ struct object_entry *packlist_find(struct packing_data *pdata, return &pdata->objects[pdata->index[i] - 1]; } +static void prepare_in_pack_by_idx(struct packing_data *pdata) +{ + struct packed_git **mapping, *p; + int cnt = 0, nr = 1U << OE_IN_PACK_BITS; + + ALLOC_ARRAY(mapping, nr); + /* + * oe_in_pack() on an all-zero'd object_entry + * (i.e. in_pack_idx also zero) should return NULL. + */ + mapping[cnt++] = NULL; + for (p = get_packed_git(the_repository); p; p = p->next, cnt++) { + if (cnt == nr) { + free(mapping); + return; + } + p->index = cnt; + mapping[cnt] = p; + } + pdata->in_pack_by_idx = mapping; +} + +/* + * A new pack appears after prepare_in_pack_by_idx() has been + * run. This is likely a race. + * + * We could map this new pack to in_pack_by_idx[] array, but then we + * have to deal with full array anyway. And since it's hard to test + * this fall back code, just stay simple and fall back to using + * in_pack[] array. + */ +void oe_map_new_pack(struct packing_data *pack, + struct packed_git *p) +{ + uint32_t i; + + REALLOC_ARRAY(pack->in_pack, pack->nr_alloc); + + for (i = 0; i < pack->nr_objects; i++) + pack->in_pack[i] = oe_in_pack(pack, pack->objects + i); + + FREE_AND_NULL(pack->in_pack_by_idx); +} + +/* assume pdata is already zero'd by caller */ +void prepare_packing_data(struct packing_data *pdata) +{ + if (git_env_bool("GIT_TEST_FULL_IN_PACK_ARRAY", 0)) { + /* + * do not initialize in_pack_by_idx[] to force the + * slow path in oe_in_pack() + */ + } else { + prepare_in_pack_by_idx(pdata); + } + + pdata->oe_size_limit = git_env_ulong("GIT_TEST_OE_SIZE", + 1U << OE_SIZE_BITS); +} + struct object_entry *packlist_alloc(struct packing_data *pdata, const unsigned char *sha1, uint32_t index_pos) @@ -95,6 +157,9 @@ struct object_entry *packlist_alloc(struct packing_data *pdata, if (pdata->nr_objects >= pdata->nr_alloc) { pdata->nr_alloc = (pdata->nr_alloc + 1024) * 3 / 2; REALLOC_ARRAY(pdata->objects, pdata->nr_alloc); + + if (!pdata->in_pack_by_idx) + REALLOC_ARRAY(pdata->in_pack, pdata->nr_alloc); } new_entry = pdata->objects + pdata->nr_objects++; @@ -107,5 +172,8 @@ struct object_entry *packlist_alloc(struct packing_data *pdata, else pdata->index[index_pos] = pdata->nr_objects; + if (pdata->in_pack) + pdata->in_pack[pdata->nr_objects - 1] = NULL; + return new_entry; } diff --git a/pack-objects.h b/pack-objects.h index 03f1191659..edf74dabdd 100644 --- a/pack-objects.h +++ b/pack-objects.h @@ -1,45 +1,125 @@ #ifndef PACK_OBJECTS_H #define PACK_OBJECTS_H +#include "object-store.h" + +#define DEFAULT_DELTA_CACHE_SIZE (256 * 1024 * 1024) + +#define OE_DFS_STATE_BITS 2 +#define OE_DEPTH_BITS 12 +#define OE_IN_PACK_BITS 10 +#define OE_Z_DELTA_BITS 20 +/* + * Note that oe_set_size() becomes expensive when the given size is + * above this limit. Don't lower it too much. + */ +#define OE_SIZE_BITS 31 +#define OE_DELTA_SIZE_BITS 20 + +/* + * State flags for depth-first search used for analyzing delta cycles. + * + * The depth is measured in delta-links to the base (so if A is a delta + * against B, then A has a depth of 1, and B a depth of 0). + */ +enum dfs_state { + DFS_NONE = 0, + DFS_ACTIVE, + DFS_DONE, + DFS_NUM_STATES +}; + +/* + * The size of struct nearly determines pack-objects's memory + * consumption. This struct is packed tight for that reason. When you + * add or reorder something in this struct, think a bit about this. + * + * basic object info + * ----------------- + * idx.oid is filled up before delta searching starts. idx.crc32 is + * only valid after the object is written out and will be used for + * generating the index. idx.offset will be both gradually set and + * used in writing phase (base objects get offset first, then deltas + * refer to them) + * + * "size" is the uncompressed object size. Compressed size of the raw + * data for an object in a pack is not stored anywhere but is computed + * and made available when reverse .idx is made. Note that when a + * delta is reused, "size" is the uncompressed _delta_ size, not the + * canonical one after the delta has been applied. + * + * "hash" contains a path name hash which is used for sorting the + * delta list and also during delta searching. Once prepare_pack() + * returns it's no longer needed. + * + * source pack info + * ---------------- + * The (in_pack, in_pack_offset) tuple contains the location of the + * object in the source pack. in_pack_header_size allows quickly + * skipping the header and going straight to the zlib stream. + * + * "type" and "in_pack_type" both describe object type. in_pack_type + * may contain a delta type, while type is always the canonical type. + * + * deltas + * ------ + * Delta links (delta, delta_child and delta_sibling) are created to + * reflect that delta graph from the source pack then updated or added + * during delta searching phase when we find better deltas. + * + * delta_child and delta_sibling are last needed in + * compute_write_order(). "delta" and "delta_size" must remain valid + * at object writing phase in case the delta is not cached. + * + * If a delta is cached in memory and is compressed, delta_data points + * to the data and z_delta_size contains the compressed size. If it's + * uncompressed [1], z_delta_size must be zero. delta_size is always + * the uncompressed size and must be valid even if the delta is not + * cached. + * + * [1] during try_delta phase we don't bother with compressing because + * the delta could be quickly replaced with a better one. + */ struct object_entry { struct pack_idx_entry idx; - unsigned long size; /* uncompressed size */ - struct packed_git *in_pack; /* already in pack */ - off_t in_pack_offset; - struct object_entry *delta; /* delta base object */ - struct object_entry *delta_child; /* deltified objects who bases me */ - struct object_entry *delta_sibling; /* other deltified objects who - * uses the same base as me - */ void *delta_data; /* cached delta (uncompressed) */ - unsigned long delta_size; /* delta data size (uncompressed) */ - unsigned long z_delta_size; /* delta data size (compressed) */ - enum object_type type; - enum object_type in_pack_type; /* could be delta */ + off_t in_pack_offset; uint32_t hash; /* name hint hash */ - unsigned int in_pack_pos; - unsigned char in_pack_header_size; + unsigned size_:OE_SIZE_BITS; + unsigned size_valid:1; + uint32_t delta_idx; /* delta base object */ + uint32_t delta_child_idx; /* deltified objects who bases me */ + uint32_t delta_sibling_idx; /* other deltified objects who + * uses the same base as me + */ + unsigned delta_size_:OE_DELTA_SIZE_BITS; /* delta data size (uncompressed) */ + unsigned delta_size_valid:1; + unsigned in_pack_idx:OE_IN_PACK_BITS; /* already in pack */ + unsigned z_delta_size:OE_Z_DELTA_BITS; + unsigned type_valid:1; + unsigned type_:TYPE_BITS; + unsigned no_try_delta:1; + unsigned in_pack_type:TYPE_BITS; /* could be delta */ unsigned preferred_base:1; /* * we do not pack this, but is available * to be used as the base object to delta * objects against. */ - unsigned no_try_delta:1; unsigned tagged:1; /* near the very tip of refs */ unsigned filled:1; /* assigned write-order */ + unsigned dfs_state:OE_DFS_STATE_BITS; + unsigned char in_pack_header_size; + unsigned depth:OE_DEPTH_BITS; /* - * State flags for depth-first search used for analyzing delta cycles. + * pahole results on 64-bit linux (gcc and clang) + * + * size: 80, bit_padding: 20 bits, holes: 8 bits + * + * and on 32-bit (gcc) * - * The depth is measured in delta-links to the base (so if A is a delta - * against B, then A has a depth of 1, and B a depth of 0). + * size: 76, bit_padding: 20 bits, holes: 8 bits */ - enum { - DFS_NONE = 0, - DFS_ACTIVE, - DFS_DONE - } dfs_state; - int depth; }; struct packing_data { @@ -48,8 +128,22 @@ struct packing_data { int32_t *index; uint32_t index_size; + + unsigned int *in_pack_pos; + + /* + * Only one of these can be non-NULL and they have different + * sizes. if in_pack_by_idx is allocated, oe_in_pack() returns + * the pack of an object using in_pack_idx field. If not, + * in_pack[] array is used the same way as in_pack_pos[] + */ + struct packed_git **in_pack_by_idx; + struct packed_git **in_pack; + + uintmax_t oe_size_limit; }; +void prepare_packing_data(struct packing_data *pdata); struct object_entry *packlist_alloc(struct packing_data *pdata, const unsigned char *sha1, uint32_t index_pos); @@ -78,4 +172,178 @@ static inline uint32_t pack_name_hash(const char *name) return hash; } +static inline enum object_type oe_type(const struct object_entry *e) +{ + return e->type_valid ? e->type_ : OBJ_BAD; +} + +static inline void oe_set_type(struct object_entry *e, + enum object_type type) +{ + if (type >= OBJ_ANY) + BUG("OBJ_ANY cannot be set in pack-objects code"); + + e->type_valid = type >= OBJ_NONE; + e->type_ = (unsigned)type; +} + +static inline unsigned int oe_in_pack_pos(const struct packing_data *pack, + const struct object_entry *e) +{ + return pack->in_pack_pos[e - pack->objects]; +} + +static inline void oe_set_in_pack_pos(const struct packing_data *pack, + const struct object_entry *e, + unsigned int pos) +{ + pack->in_pack_pos[e - pack->objects] = pos; +} + +static inline struct packed_git *oe_in_pack(const struct packing_data *pack, + const struct object_entry *e) +{ + if (pack->in_pack_by_idx) + return pack->in_pack_by_idx[e->in_pack_idx]; + else + return pack->in_pack[e - pack->objects]; +} + +void oe_map_new_pack(struct packing_data *pack, + struct packed_git *p); +static inline void oe_set_in_pack(struct packing_data *pack, + struct object_entry *e, + struct packed_git *p) +{ + if (!p->index) + oe_map_new_pack(pack, p); + if (pack->in_pack_by_idx) + e->in_pack_idx = p->index; + else + pack->in_pack[e - pack->objects] = p; +} + +static inline struct object_entry *oe_delta( + const struct packing_data *pack, + const struct object_entry *e) +{ + if (e->delta_idx) + return &pack->objects[e->delta_idx - 1]; + return NULL; +} + +static inline void oe_set_delta(struct packing_data *pack, + struct object_entry *e, + struct object_entry *delta) +{ + if (delta) + e->delta_idx = (delta - pack->objects) + 1; + else + e->delta_idx = 0; +} + +static inline struct object_entry *oe_delta_child( + const struct packing_data *pack, + const struct object_entry *e) +{ + if (e->delta_child_idx) + return &pack->objects[e->delta_child_idx - 1]; + return NULL; +} + +static inline void oe_set_delta_child(struct packing_data *pack, + struct object_entry *e, + struct object_entry *delta) +{ + if (delta) + e->delta_child_idx = (delta - pack->objects) + 1; + else + e->delta_child_idx = 0; +} + +static inline struct object_entry *oe_delta_sibling( + const struct packing_data *pack, + const struct object_entry *e) +{ + if (e->delta_sibling_idx) + return &pack->objects[e->delta_sibling_idx - 1]; + return NULL; +} + +static inline void oe_set_delta_sibling(struct packing_data *pack, + struct object_entry *e, + struct object_entry *delta) +{ + if (delta) + e->delta_sibling_idx = (delta - pack->objects) + 1; + else + e->delta_sibling_idx = 0; +} + +unsigned long oe_get_size_slow(struct packing_data *pack, + const struct object_entry *e); +static inline unsigned long oe_size(struct packing_data *pack, + const struct object_entry *e) +{ + if (e->size_valid) + return e->size_; + + return oe_get_size_slow(pack, e); +} + +static inline int oe_size_less_than(struct packing_data *pack, + const struct object_entry *lhs, + unsigned long rhs) +{ + if (lhs->size_valid) + return lhs->size_ < rhs; + if (rhs < pack->oe_size_limit) /* rhs < 2^x <= lhs ? */ + return 0; + return oe_get_size_slow(pack, lhs) < rhs; +} + +static inline int oe_size_greater_than(struct packing_data *pack, + const struct object_entry *lhs, + unsigned long rhs) +{ + if (lhs->size_valid) + return lhs->size_ > rhs; + if (rhs < pack->oe_size_limit) /* rhs < 2^x <= lhs ? */ + return 1; + return oe_get_size_slow(pack, lhs) > rhs; +} + +static inline void oe_set_size(struct packing_data *pack, + struct object_entry *e, + unsigned long size) +{ + if (size < pack->oe_size_limit) { + e->size_ = size; + e->size_valid = 1; + } else { + e->size_valid = 0; + if (oe_get_size_slow(pack, e) != size) + BUG("'size' is supposed to be the object size!"); + } +} + +static inline unsigned long oe_delta_size(struct packing_data *pack, + const struct object_entry *e) +{ + if (e->delta_size_valid) + return e->delta_size_; + return oe_size(pack, e); +} + +static inline void oe_set_delta_size(struct packing_data *pack, + struct object_entry *e, + unsigned long size) +{ + e->delta_size_ = size; + e->delta_size_valid = e->delta_size_ == size; + if (!e->delta_size_valid && size != oe_size(pack, e)) + BUG("this can only happen in check_object() " + "where delta size is the same as entry size"); +} + #endif diff --git a/pack-write.c b/pack-write.c index d775c7406d..a9d46bc03f 100644 --- a/pack-write.c +++ b/pack-write.c @@ -170,8 +170,9 @@ const char *write_idx_file(const char *index_name, struct pack_idx_entry **objec } hashwrite(f, sha1, the_hash_algo->rawsz); - hashclose(f, NULL, ((opts->flags & WRITE_IDX_VERIFY) - ? CSUM_CLOSE : CSUM_FSYNC)); + finalize_hashfile(f, NULL, CSUM_HASH_IN_STREAM | CSUM_CLOSE | + ((opts->flags & WRITE_IDX_VERIFY) + ? 0 : CSUM_FSYNC)); return index_name; } diff --git a/packfile.c b/packfile.c index 0bc67d0e00..9e7e693fb5 100644 --- a/packfile.c +++ b/packfile.c @@ -304,7 +304,7 @@ void close_pack_index(struct packed_git *p) } } -static void close_pack(struct packed_git *p) +void close_pack(struct packed_git *p) { close_pack_windows(p); close_pack_fd(p); @@ -1104,7 +1104,9 @@ static const unsigned char *get_delta_base_sha1(struct packed_git *p, return NULL; } -static int retry_bad_packed_offset(struct packed_git *p, off_t obj_offset) +static int retry_bad_packed_offset(struct repository *r, + struct packed_git *p, + off_t obj_offset) { int type; struct revindex_entry *revidx; @@ -1114,7 +1116,7 @@ static int retry_bad_packed_offset(struct packed_git *p, off_t obj_offset) return OBJ_BAD; nth_packed_object_oid(&oid, p, revidx->nr); mark_bad_packed_object(p, oid.hash); - type = oid_object_info(&oid, NULL); + type = oid_object_info(r, &oid, NULL); if (type <= OBJ_NONE) return OBJ_BAD; return type; @@ -1122,7 +1124,8 @@ static int retry_bad_packed_offset(struct packed_git *p, off_t obj_offset) #define POI_STACK_PREALLOC 64 -static enum object_type packed_to_object_type(struct packed_git *p, +static enum object_type packed_to_object_type(struct repository *r, + struct packed_git *p, off_t obj_offset, enum object_type type, struct pack_window **w_curs, @@ -1153,7 +1156,7 @@ static enum object_type packed_to_object_type(struct packed_git *p, if (type <= OBJ_NONE) { /* If getting the base itself fails, we first * retry the base, otherwise unwind */ - type = retry_bad_packed_offset(p, base_offset); + type = retry_bad_packed_offset(r, p, base_offset); if (type > OBJ_NONE) goto out; goto unwind; @@ -1181,7 +1184,7 @@ out: unwind: while (poi_stack_nr) { obj_offset = poi_stack[--poi_stack_nr]; - type = retry_bad_packed_offset(p, obj_offset); + type = retry_bad_packed_offset(r, p, obj_offset); if (type > OBJ_NONE) goto out; } @@ -1268,14 +1271,15 @@ static void detach_delta_base_cache_entry(struct delta_base_cache_entry *ent) free(ent); } -static void *cache_or_unpack_entry(struct packed_git *p, off_t base_offset, - unsigned long *base_size, enum object_type *type) +static void *cache_or_unpack_entry(struct repository *r, struct packed_git *p, + off_t base_offset, unsigned long *base_size, + enum object_type *type) { struct delta_base_cache_entry *ent; ent = get_delta_base_cache_entry(p, base_offset); if (!ent) - return unpack_entry(p, base_offset, type, base_size); + return unpack_entry(r, p, base_offset, type, base_size); if (type) *type = ent->type; @@ -1329,8 +1333,8 @@ static void add_delta_base_cache(struct packed_git *p, off_t base_offset, hashmap_add(&delta_base_cache, ent); } -int packed_object_info(struct packed_git *p, off_t obj_offset, - struct object_info *oi) +int packed_object_info(struct repository *r, struct packed_git *p, + off_t obj_offset, struct object_info *oi) { struct pack_window *w_curs = NULL; unsigned long size; @@ -1342,7 +1346,7 @@ int packed_object_info(struct packed_git *p, off_t obj_offset, * a "real" type later if the caller is interested. */ if (oi->contentp) { - *oi->contentp = cache_or_unpack_entry(p, obj_offset, oi->sizep, + *oi->contentp = cache_or_unpack_entry(r, p, obj_offset, oi->sizep, &type); if (!*oi->contentp) type = OBJ_BAD; @@ -1376,8 +1380,8 @@ int packed_object_info(struct packed_git *p, off_t obj_offset, if (oi->typep || oi->type_name) { enum object_type ptot; - ptot = packed_to_object_type(p, obj_offset, type, &w_curs, - curpos); + ptot = packed_to_object_type(r, p, obj_offset, + type, &w_curs, curpos); if (oi->typep) *oi->typep = ptot; if (oi->type_name) { @@ -1465,7 +1469,9 @@ struct unpack_entry_stack_ent { unsigned long size; }; -static void *read_object(const struct object_id *oid, enum object_type *type, +static void *read_object(struct repository *r, + const struct object_id *oid, + enum object_type *type, unsigned long *size) { struct object_info oi = OBJECT_INFO_INIT; @@ -1474,12 +1480,12 @@ static void *read_object(const struct object_id *oid, enum object_type *type, oi.sizep = size; oi.contentp = &content; - if (oid_object_info_extended(oid, &oi, 0) < 0) + if (oid_object_info_extended(r, oid, &oi, 0) < 0) return NULL; return content; } -void *unpack_entry(struct packed_git *p, off_t obj_offset, +void *unpack_entry(struct repository *r, struct packed_git *p, off_t obj_offset, enum object_type *final_type, unsigned long *final_size) { struct pack_window *w_curs = NULL; @@ -1610,7 +1616,7 @@ void *unpack_entry(struct packed_git *p, off_t obj_offset, oid_to_hex(&base_oid), (uintmax_t)obj_offset, p->pack_name); mark_bad_packed_object(p, base_oid.hash); - base = read_object(&base_oid, &type, &base_size); + base = read_object(r, &base_oid, &type, &base_size); external_base = base; } } @@ -1869,7 +1875,7 @@ int has_pack_index(const unsigned char *sha1) return 1; } -static int for_each_object_in_pack(struct packed_git *p, each_packed_object_fn cb, void *data) +int for_each_object_in_pack(struct packed_git *p, each_packed_object_fn cb, void *data) { uint32_t i; int r = 0; @@ -1944,7 +1950,7 @@ static int add_promisor_object(const struct object_id *oid, struct commit *commit = (struct commit *) obj; struct commit_list *parents = commit->parents; - oidset_insert(set, &commit->tree->object.oid); + oidset_insert(set, get_commit_tree_oid(commit)); for (; parents; parents = parents->next) oidset_insert(set, &parents->item->object.oid); } else if (obj->type == OBJ_TAG) { diff --git a/packfile.h b/packfile.h index a92c0b241c..bfd0b5399d 100644 --- a/packfile.h +++ b/packfile.h @@ -65,6 +65,7 @@ extern void close_pack_index(struct packed_git *); extern unsigned char *use_pack(struct packed_git *, struct pack_window **, off_t, unsigned long *); extern void close_pack_windows(struct packed_git *); +extern void close_pack(struct packed_git *); extern void close_all_packs(struct raw_object_store *o); extern void unuse_pack(struct pack_window **); extern void clear_delta_base_cache(void); @@ -115,7 +116,7 @@ extern off_t nth_packed_object_offset(const struct packed_git *, uint32_t n); extern off_t find_pack_entry_one(const unsigned char *sha1, struct packed_git *); extern int is_pack_valid(struct packed_git *); -extern void *unpack_entry(struct packed_git *, off_t, enum object_type *, unsigned long *); +extern void *unpack_entry(struct repository *r, struct packed_git *, off_t, enum object_type *, unsigned long *); extern unsigned long unpack_object_header_buffer(const unsigned char *buf, unsigned long len, enum object_type *type, unsigned long *sizep); extern unsigned long get_size_from_delta(struct packed_git *, struct pack_window **, off_t); extern int unpack_object_header(struct packed_git *, struct pack_window **, off_t *, unsigned long *); @@ -125,7 +126,9 @@ extern void release_pack_memory(size_t); /* global flag to enable extra checks when accessing packed objects */ extern int do_check_packed_object_crc; -extern int packed_object_info(struct packed_git *pack, off_t offset, struct object_info *); +extern int packed_object_info(struct repository *r, + struct packed_git *pack, + off_t offset, struct object_info *); extern void mark_bad_packed_object(struct packed_git *p, const unsigned char *sha1); extern const struct packed_git *has_packed_and_bad(const unsigned char *sha1); @@ -154,6 +157,7 @@ typedef int each_packed_object_fn(const struct object_id *oid, struct packed_git *pack, uint32_t pos, void *data); +extern int for_each_object_in_pack(struct packed_git *p, each_packed_object_fn, void *data); extern int for_each_packed_object(each_packed_object_fn, void *, unsigned flags); /* @@ -109,10 +109,15 @@ void setup_pager(void) return; /* - * force computing the width of the terminal before we redirect - * the standard output to the pager. + * After we redirect standard output, we won't be able to use an ioctl + * to get the terminal size. Let's grab it now, and then set $COLUMNS + * to communicate it to any sub-processes. */ - (void) term_columns(); + { + char buf[64]; + xsnprintf(buf, sizeof(buf), "%d", term_columns()); + setenv("COLUMNS", buf, 0); + } setenv("GIT_PAGER_IN_USE", "true", 1); diff --git a/parse-options-cb.c b/parse-options-cb.c index c6679cb2cd..0f9f311a7a 100644 --- a/parse-options-cb.c +++ b/parse-options-cb.c @@ -38,7 +38,11 @@ int parse_opt_approxidate_cb(const struct option *opt, const char *arg, int parse_opt_expiry_date_cb(const struct option *opt, const char *arg, int unset) { - return parse_expiry_date(arg, (timestamp_t *)opt->value); + if (unset) + arg = "never"; + if (parse_expiry_date(arg, (timestamp_t *)opt->value)) + die(_("malformed expiration date '%s'"), arg); + return 0; } int parse_opt_color_flag_cb(const struct option *opt, const char *arg, diff --git a/perl/Git.pm b/perl/Git.pm index 16ebcc612c..d856930b2e 100644 --- a/perl/Git.pm +++ b/perl/Git.pm @@ -554,7 +554,7 @@ sub get_record { my ($fh, $rs) = @_; local $/ = $rs; my $rec = <$fh>; - chomp $rec if defined $rs; + chomp $rec if defined $rec; $rec; } diff --git a/perl/Git/I18N.pm b/perl/Git/I18N.pm index dba96fff0a..bfb4fb67a1 100644 --- a/perl/Git/I18N.pm +++ b/perl/Git/I18N.pm @@ -18,7 +18,7 @@ our @EXPORT_OK = @EXPORT; sub __bootstrap_locale_messages { our $TEXTDOMAIN = 'git'; - our $TEXTDOMAINDIR = $ENV{GIT_TEXTDOMAINDIR} || '@@LOCALEDIR@@'; + our $TEXTDOMAINDIR ||= $ENV{GIT_TEXTDOMAINDIR} || '@@LOCALEDIR@@'; require POSIX; POSIX->import(qw(setlocale)); diff --git a/perl/header_templates/fixed_prefix.template.pl b/perl/header_templates/fixed_prefix.template.pl new file mode 100644 index 0000000000..857b4391a4 --- /dev/null +++ b/perl/header_templates/fixed_prefix.template.pl @@ -0,0 +1 @@ +use lib (split(/@@PATHSEP@@/, $ENV{GITPERLLIB} || '@@INSTLIBDIR@@')); diff --git a/perl/header_templates/runtime_prefix.template.pl b/perl/header_templates/runtime_prefix.template.pl new file mode 100644 index 0000000000..9d28b3d863 --- /dev/null +++ b/perl/header_templates/runtime_prefix.template.pl @@ -0,0 +1,42 @@ +# BEGIN RUNTIME_PREFIX generated code. +# +# This finds our Git::* libraries relative to the script's runtime path. +sub __git_system_path { + my ($relpath) = @_; + my $gitexecdir_relative = '@@GITEXECDIR_REL@@'; + + # GIT_EXEC_PATH is supplied by `git` or the test suite. + my $exec_path; + if (exists $ENV{GIT_EXEC_PATH}) { + $exec_path = $ENV{GIT_EXEC_PATH}; + } else { + # This can happen if this script is being directly invoked instead of run + # by "git". + require FindBin; + $exec_path = $FindBin::Bin; + } + + # Trim off the relative gitexecdir path to get the system path. + (my $prefix = $exec_path) =~ s/\Q$gitexecdir_relative\E$//; + + require File::Spec; + return File::Spec->catdir($prefix, $relpath); +} + +BEGIN { + use lib split /@@PATHSEP@@/, + ( + $ENV{GITPERLLIB} || + do { + my $perllibdir = __git_system_path('@@PERLLIBDIR_REL@@'); + (-e $perllibdir) || die("Invalid system path ($relpath): $path"); + $perllibdir; + } + ); + + # Export the system locale directory to the I18N module. The locale directory + # is only installed if NO_GETTEXT is set. + $Git::I18N::TEXTDOMAINDIR = __git_system_path('@@LOCALEDIR_REL@@'); +} + +# END RUNTIME_PREFIX generated code. diff --git a/pkt-line.c b/pkt-line.c index 2827ca772a..555eb2a507 100644 --- a/pkt-line.c +++ b/pkt-line.c @@ -91,6 +91,12 @@ void packet_flush(int fd) write_or_die(fd, "0000", 4); } +void packet_delim(int fd) +{ + packet_trace("0001", 4, 1); + write_or_die(fd, "0001", 4); +} + int packet_flush_gently(int fd) { packet_trace("0000", 4, 1); @@ -105,6 +111,12 @@ void packet_buf_flush(struct strbuf *buf) strbuf_add(buf, "0000", 4); } +void packet_buf_delim(struct strbuf *buf) +{ + packet_trace("0001", 4, 1); + strbuf_add(buf, "0001", 4); +} + static void set_packet_header(char *buf, const int size) { static char hexchar[] = "0123456789abcdef"; @@ -203,6 +215,22 @@ void packet_buf_write(struct strbuf *buf, const char *fmt, ...) va_end(args); } +void packet_buf_write_len(struct strbuf *buf, const char *data, size_t len) +{ + size_t orig_len, n; + + orig_len = buf->len; + strbuf_addstr(buf, "0000"); + strbuf_add(buf, data, len); + n = buf->len - orig_len; + + if (n > LARGE_PACKET_MAX) + die("protocol error: impossibly long line"); + + set_packet_header(&buf->buf[orig_len], n); + packet_trace(data, len, 1); +} + int write_packetized_from_fd(int fd_in, int fd_out) { static char buf[LARGE_PACKET_DATA_MAX]; @@ -280,28 +308,43 @@ static int packet_length(const char *linelen) return (val < 0) ? val : (val << 8) | hex2chr(linelen + 2); } -int packet_read(int fd, char **src_buf, size_t *src_len, - char *buffer, unsigned size, int options) +enum packet_read_status packet_read_with_status(int fd, char **src_buffer, + size_t *src_len, char *buffer, + unsigned size, int *pktlen, + int options) { - int len, ret; + int len; char linelen[4]; - ret = get_packet_data(fd, src_buf, src_len, linelen, 4, options); - if (ret < 0) - return ret; + if (get_packet_data(fd, src_buffer, src_len, linelen, 4, options) < 0) { + *pktlen = -1; + return PACKET_READ_EOF; + } + len = packet_length(linelen); - if (len < 0) + + if (len < 0) { die("protocol error: bad line length character: %.4s", linelen); - if (!len) { + } else if (!len) { packet_trace("0000", 4, 0); - return 0; + *pktlen = 0; + return PACKET_READ_FLUSH; + } else if (len == 1) { + packet_trace("0001", 4, 0); + *pktlen = 0; + return PACKET_READ_DELIM; + } else if (len < 4) { + die("protocol error: bad line length %d", len); } + len -= 4; - if (len >= size) + if ((unsigned)len >= size) die("protocol error: bad line length %d", len); - ret = get_packet_data(fd, src_buf, src_len, buffer, len, options); - if (ret < 0) - return ret; + + if (get_packet_data(fd, src_buffer, src_len, buffer, len, options) < 0) { + *pktlen = -1; + return PACKET_READ_EOF; + } if ((options & PACKET_READ_CHOMP_NEWLINE) && len && buffer[len-1] == '\n') @@ -309,7 +352,19 @@ int packet_read(int fd, char **src_buf, size_t *src_len, buffer[len] = 0; packet_trace(buffer, len, 0); - return len; + *pktlen = len; + return PACKET_READ_NORMAL; +} + +int packet_read(int fd, char **src_buffer, size_t *src_len, + char *buffer, unsigned size, int options) +{ + int pktlen = -1; + + packet_read_with_status(fd, src_buffer, src_len, buffer, size, + &pktlen, options); + + return pktlen; } static char *packet_read_line_generic(int fd, @@ -377,3 +432,53 @@ ssize_t read_packetized_to_strbuf(int fd_in, struct strbuf *sb_out) } return sb_out->len - orig_len; } + +/* Packet Reader Functions */ +void packet_reader_init(struct packet_reader *reader, int fd, + char *src_buffer, size_t src_len, + int options) +{ + memset(reader, 0, sizeof(*reader)); + + reader->fd = fd; + reader->src_buffer = src_buffer; + reader->src_len = src_len; + reader->buffer = packet_buffer; + reader->buffer_size = sizeof(packet_buffer); + reader->options = options; +} + +enum packet_read_status packet_reader_read(struct packet_reader *reader) +{ + if (reader->line_peeked) { + reader->line_peeked = 0; + return reader->status; + } + + reader->status = packet_read_with_status(reader->fd, + &reader->src_buffer, + &reader->src_len, + reader->buffer, + reader->buffer_size, + &reader->pktlen, + reader->options); + + if (reader->status == PACKET_READ_NORMAL) + reader->line = reader->buffer; + else + reader->line = NULL; + + return reader->status; +} + +enum packet_read_status packet_reader_peek(struct packet_reader *reader) +{ + /* Only allow peeking a single line */ + if (reader->line_peeked) + return reader->status; + + /* Peek a line by reading it and setting peeked flag */ + packet_reader_read(reader); + reader->line_peeked = 1; + return reader->status; +} diff --git a/pkt-line.h b/pkt-line.h index 3dad583e2d..5b28d43472 100644 --- a/pkt-line.h +++ b/pkt-line.h @@ -20,10 +20,13 @@ * side can't, we stay with pure read/write interfaces. */ void packet_flush(int fd); +void packet_delim(int fd); void packet_write_fmt(int fd, const char *fmt, ...) __attribute__((format (printf, 2, 3))); void packet_buf_flush(struct strbuf *buf); +void packet_buf_delim(struct strbuf *buf); void packet_write(int fd_out, const char *buf, size_t size); void packet_buf_write(struct strbuf *buf, const char *fmt, ...) __attribute__((format (printf, 2, 3))); +void packet_buf_write_len(struct strbuf *buf, const char *data, size_t len); int packet_flush_gently(int fd); int packet_write_fmt_gently(int fd, const char *fmt, ...) __attribute__((format (printf, 2, 3))); int write_packetized_from_fd(int fd_in, int fd_out); @@ -66,6 +69,23 @@ int packet_read(int fd, char **src_buffer, size_t *src_len, char *buffer, unsigned size, int options); /* + * Read a packetized line into a buffer like the 'packet_read()' function but + * returns an 'enum packet_read_status' which indicates the status of the read. + * The number of bytes read will be assigined to *pktlen if the status of the + * read was 'PACKET_READ_NORMAL'. + */ +enum packet_read_status { + PACKET_READ_EOF, + PACKET_READ_NORMAL, + PACKET_READ_FLUSH, + PACKET_READ_DELIM, +}; +enum packet_read_status packet_read_with_status(int fd, char **src_buffer, + size_t *src_len, char *buffer, + unsigned size, int *pktlen, + int options); + +/* * Convenience wrapper for packet_read that is not gentle, and sets the * CHOMP_NEWLINE option. The return value is NULL for a flush packet, * and otherwise points to a static buffer (that may be overwritten by @@ -96,6 +116,64 @@ char *packet_read_line_buf(char **src_buf, size_t *src_len, int *size); */ ssize_t read_packetized_to_strbuf(int fd_in, struct strbuf *sb_out); +struct packet_reader { + /* source file descriptor */ + int fd; + + /* source buffer and its size */ + char *src_buffer; + size_t src_len; + + /* buffer that pkt-lines are read into and its size */ + char *buffer; + unsigned buffer_size; + + /* options to be used during reads */ + int options; + + /* status of the last read */ + enum packet_read_status status; + + /* length of data read during the last read */ + int pktlen; + + /* the last line read */ + const char *line; + + /* indicates if a line has been peeked */ + int line_peeked; +}; + +/* + * Initialize a 'struct packet_reader' object which is an + * abstraction around the 'packet_read_with_status()' function. + */ +extern void packet_reader_init(struct packet_reader *reader, int fd, + char *src_buffer, size_t src_len, + int options); + +/* + * Perform a packet read and return the status of the read. + * The values of 'pktlen' and 'line' are updated based on the status of the + * read as follows: + * + * PACKET_READ_ERROR: 'pktlen' is set to '-1' and 'line' is set to NULL + * PACKET_READ_NORMAL: 'pktlen' is set to the number of bytes read + * 'line' is set to point at the read line + * PACKET_READ_FLUSH: 'pktlen' is set to '0' and 'line' is set to NULL + */ +extern enum packet_read_status packet_reader_read(struct packet_reader *reader); + +/* + * Peek the next packet line without consuming it and return the status. + * The next call to 'packet_reader_read()' will perform a read of the same line + * that was peeked, consuming the line. + * + * Peeking multiple times without calling 'packet_reader_read()' will return + * the same result. + */ +extern enum packet_read_status packet_reader_peek(struct packet_reader *reader); + #define DEFAULT_PACKET_MAX 1000 #define LARGE_PACKET_MAX 65520 #define LARGE_PACKET_DATA_MAX (LARGE_PACKET_MAX - 4) @@ -1161,10 +1161,11 @@ static size_t format_commit_one(struct strbuf *sb, /* in UTF-8 */ strbuf_addstr(sb, diff_get_color(c->auto_color, DIFF_RESET)); return 1; case 'T': /* tree hash */ - strbuf_addstr(sb, oid_to_hex(&commit->tree->object.oid)); + strbuf_addstr(sb, oid_to_hex(get_commit_tree_oid(commit))); return 1; case 't': /* abbreviated tree hash */ - strbuf_add_unique_abbrev(sb, &commit->tree->object.oid, + strbuf_add_unique_abbrev(sb, + get_commit_tree_oid(commit), c->pretty_ctx->abbrev); return 1; case 'P': /* parent hashes */ diff --git a/protocol.c b/protocol.c index 43012b7eb6..5e636785d1 100644 --- a/protocol.c +++ b/protocol.c @@ -8,6 +8,8 @@ static enum protocol_version parse_protocol_version(const char *value) return protocol_v0; else if (!strcmp(value, "1")) return protocol_v1; + else if (!strcmp(value, "2")) + return protocol_v2; else return protocol_unknown_version; } diff --git a/protocol.h b/protocol.h index 1b2bc94a8d..2ad35e433c 100644 --- a/protocol.h +++ b/protocol.h @@ -5,6 +5,7 @@ enum protocol_version { protocol_unknown_version = -1, protocol_v0 = 0, protocol_v1 = 1, + protocol_v2 = 2, }; /* diff --git a/reachable.c b/reachable.c index a6ea33a5db..ffb976c33c 100644 --- a/reachable.c +++ b/reachable.c @@ -78,7 +78,7 @@ static void add_recent_object(const struct object_id *oid, * later processing, and the revision machinery expects * commits and tags to have been parsed. */ - type = oid_object_info(oid, NULL); + type = oid_object_info(the_repository, oid, NULL); if (type < 0) die("unable to get object info for %s", oid_to_hex(oid)); diff --git a/read-cache.c b/read-cache.c index 10f1c6bb8a..fa3df2e72e 100644 --- a/read-cache.c +++ b/read-cache.c @@ -2268,7 +2268,7 @@ static int do_write_index(struct index_state *istate, struct tempfile *tempfile, if (!istate->version) { istate->version = get_index_format_default(); - if (getenv("GIT_TEST_SPLIT_INDEX")) + if (git_env_bool("GIT_TEST_SPLIT_INDEX", 0)) init_split_index(istate); } @@ -2559,7 +2559,7 @@ int write_locked_index(struct index_state *istate, struct lock_file *lock, goto out; } - if (getenv("GIT_TEST_SPLIT_INDEX")) { + if (git_env_bool("GIT_TEST_SPLIT_INDEX", 0)) { int v = si->base_sha1[0]; if ((v & 15) < 6) istate->cache_changed |= SPLIT_INDEX_ORDERED; diff --git a/ref-filter.c b/ref-filter.c index ac82f9f21e..dba826e718 100644 --- a/ref-filter.c +++ b/ref-filter.c @@ -101,22 +101,38 @@ static struct used_atom { } *used_atom; static int used_atom_cnt, need_tagged, need_symref; -static void color_atom_parser(const struct ref_format *format, struct used_atom *atom, const char *color_value) +/* + * Expand string, append it to strbuf *sb, then return error code ret. + * Allow to save few lines of code. + */ +static int strbuf_addf_ret(struct strbuf *sb, int ret, const char *fmt, ...) +{ + va_list ap; + va_start(ap, fmt); + strbuf_vaddf(sb, fmt, ap); + va_end(ap); + return ret; +} + +static int color_atom_parser(const struct ref_format *format, struct used_atom *atom, + const char *color_value, struct strbuf *err) { if (!color_value) - die(_("expected format: %%(color:<color>)")); + return strbuf_addf_ret(err, -1, _("expected format: %%(color:<color>)")); if (color_parse(color_value, atom->u.color) < 0) - die(_("unrecognized color: %%(color:%s)"), color_value); + return strbuf_addf_ret(err, -1, _("unrecognized color: %%(color:%s)"), + color_value); /* * We check this after we've parsed the color, which lets us complain * about syntactically bogus color names even if they won't be used. */ if (!want_color(format->use_color)) color_parse("", atom->u.color); + return 0; } -static void refname_atom_parser_internal(struct refname_atom *atom, - const char *arg, const char *name) +static int refname_atom_parser_internal(struct refname_atom *atom, const char *arg, + const char *name, struct strbuf *err) { if (!arg) atom->option = R_NORMAL; @@ -126,16 +142,18 @@ static void refname_atom_parser_internal(struct refname_atom *atom, skip_prefix(arg, "strip=", &arg)) { atom->option = R_LSTRIP; if (strtol_i(arg, 10, &atom->lstrip)) - die(_("Integer value expected refname:lstrip=%s"), arg); + return strbuf_addf_ret(err, -1, _("Integer value expected refname:lstrip=%s"), arg); } else if (skip_prefix(arg, "rstrip=", &arg)) { atom->option = R_RSTRIP; if (strtol_i(arg, 10, &atom->rstrip)) - die(_("Integer value expected refname:rstrip=%s"), arg); + return strbuf_addf_ret(err, -1, _("Integer value expected refname:rstrip=%s"), arg); } else - die(_("unrecognized %%(%s) argument: %s"), name, arg); + return strbuf_addf_ret(err, -1, _("unrecognized %%(%s) argument: %s"), name, arg); + return 0; } -static void remote_ref_atom_parser(const struct ref_format *format, struct used_atom *atom, const char *arg) +static int remote_ref_atom_parser(const struct ref_format *format, struct used_atom *atom, + const char *arg, struct strbuf *err) { struct string_list params = STRING_LIST_INIT_DUP; int i; @@ -145,9 +163,8 @@ static void remote_ref_atom_parser(const struct ref_format *format, struct used_ if (!arg) { atom->u.remote_ref.option = RR_REF; - refname_atom_parser_internal(&atom->u.remote_ref.refname, - arg, atom->name); - return; + return refname_atom_parser_internal(&atom->u.remote_ref.refname, + arg, atom->name, err); } atom->u.remote_ref.nobracket = 0; @@ -170,29 +187,38 @@ static void remote_ref_atom_parser(const struct ref_format *format, struct used_ atom->u.remote_ref.push_remote = 1; } else { atom->u.remote_ref.option = RR_REF; - refname_atom_parser_internal(&atom->u.remote_ref.refname, - arg, atom->name); + if (refname_atom_parser_internal(&atom->u.remote_ref.refname, + arg, atom->name, err)) { + string_list_clear(¶ms, 0); + return -1; + } } } string_list_clear(¶ms, 0); + return 0; } -static void body_atom_parser(const struct ref_format *format, struct used_atom *atom, const char *arg) +static int body_atom_parser(const struct ref_format *format, struct used_atom *atom, + const char *arg, struct strbuf *err) { if (arg) - die(_("%%(body) does not take arguments")); + return strbuf_addf_ret(err, -1, _("%%(body) does not take arguments")); atom->u.contents.option = C_BODY_DEP; + return 0; } -static void subject_atom_parser(const struct ref_format *format, struct used_atom *atom, const char *arg) +static int subject_atom_parser(const struct ref_format *format, struct used_atom *atom, + const char *arg, struct strbuf *err) { if (arg) - die(_("%%(subject) does not take arguments")); + return strbuf_addf_ret(err, -1, _("%%(subject) does not take arguments")); atom->u.contents.option = C_SUB; + return 0; } -static void trailers_atom_parser(const struct ref_format *format, struct used_atom *atom, const char *arg) +static int trailers_atom_parser(const struct ref_format *format, struct used_atom *atom, + const char *arg, struct strbuf *err) { struct string_list params = STRING_LIST_INIT_DUP; int i; @@ -205,15 +231,20 @@ static void trailers_atom_parser(const struct ref_format *format, struct used_at atom->u.contents.trailer_opts.unfold = 1; else if (!strcmp(s, "only")) atom->u.contents.trailer_opts.only_trailers = 1; - else - die(_("unknown %%(trailers) argument: %s"), s); + else { + strbuf_addf(err, _("unknown %%(trailers) argument: %s"), s); + string_list_clear(¶ms, 0); + return -1; + } } } atom->u.contents.option = C_TRAILERS; string_list_clear(¶ms, 0); + return 0; } -static void contents_atom_parser(const struct ref_format *format, struct used_atom *atom, const char *arg) +static int contents_atom_parser(const struct ref_format *format, struct used_atom *atom, + const char *arg, struct strbuf *err) { if (!arg) atom->u.contents.option = C_BARE; @@ -225,16 +256,19 @@ static void contents_atom_parser(const struct ref_format *format, struct used_at atom->u.contents.option = C_SUB; else if (skip_prefix(arg, "trailers", &arg)) { skip_prefix(arg, ":", &arg); - trailers_atom_parser(format, atom, *arg ? arg : NULL); + if (trailers_atom_parser(format, atom, *arg ? arg : NULL, err)) + return -1; } else if (skip_prefix(arg, "lines=", &arg)) { atom->u.contents.option = C_LINES; if (strtoul_ui(arg, 10, &atom->u.contents.nlines)) - die(_("positive value expected contents:lines=%s"), arg); + return strbuf_addf_ret(err, -1, _("positive value expected contents:lines=%s"), arg); } else - die(_("unrecognized %%(contents) argument: %s"), arg); + return strbuf_addf_ret(err, -1, _("unrecognized %%(contents) argument: %s"), arg); + return 0; } -static void objectname_atom_parser(const struct ref_format *format, struct used_atom *atom, const char *arg) +static int objectname_atom_parser(const struct ref_format *format, struct used_atom *atom, + const char *arg, struct strbuf *err) { if (!arg) atom->u.objectname.option = O_FULL; @@ -244,16 +278,18 @@ static void objectname_atom_parser(const struct ref_format *format, struct used_ atom->u.objectname.option = O_LENGTH; if (strtoul_ui(arg, 10, &atom->u.objectname.length) || atom->u.objectname.length == 0) - die(_("positive value expected objectname:short=%s"), arg); + return strbuf_addf_ret(err, -1, _("positive value expected objectname:short=%s"), arg); if (atom->u.objectname.length < MINIMUM_ABBREV) atom->u.objectname.length = MINIMUM_ABBREV; } else - die(_("unrecognized %%(objectname) argument: %s"), arg); + return strbuf_addf_ret(err, -1, _("unrecognized %%(objectname) argument: %s"), arg); + return 0; } -static void refname_atom_parser(const struct ref_format *format, struct used_atom *atom, const char *arg) +static int refname_atom_parser(const struct ref_format *format, struct used_atom *atom, + const char *arg, struct strbuf *err) { - refname_atom_parser_internal(&atom->u.refname, arg, atom->name); + return refname_atom_parser_internal(&atom->u.refname, arg, atom->name, err); } static align_type parse_align_position(const char *s) @@ -267,7 +303,8 @@ static align_type parse_align_position(const char *s) return -1; } -static void align_atom_parser(const struct ref_format *format, struct used_atom *atom, const char *arg) +static int align_atom_parser(const struct ref_format *format, struct used_atom *atom, + const char *arg, struct strbuf *err) { struct align *align = &atom->u.align; struct string_list params = STRING_LIST_INIT_DUP; @@ -275,7 +312,7 @@ static void align_atom_parser(const struct ref_format *format, struct used_atom unsigned int width = ~0U; if (!arg) - die(_("expected format: %%(align:<width>,<position>)")); + return strbuf_addf_ret(err, -1, _("expected format: %%(align:<width>,<position>)")); align->position = ALIGN_LEFT; @@ -286,49 +323,65 @@ static void align_atom_parser(const struct ref_format *format, struct used_atom if (skip_prefix(s, "position=", &s)) { position = parse_align_position(s); - if (position < 0) - die(_("unrecognized position:%s"), s); + if (position < 0) { + strbuf_addf(err, _("unrecognized position:%s"), s); + string_list_clear(¶ms, 0); + return -1; + } align->position = position; } else if (skip_prefix(s, "width=", &s)) { - if (strtoul_ui(s, 10, &width)) - die(_("unrecognized width:%s"), s); + if (strtoul_ui(s, 10, &width)) { + strbuf_addf(err, _("unrecognized width:%s"), s); + string_list_clear(¶ms, 0); + return -1; + } } else if (!strtoul_ui(s, 10, &width)) ; else if ((position = parse_align_position(s)) >= 0) align->position = position; - else - die(_("unrecognized %%(align) argument: %s"), s); + else { + strbuf_addf(err, _("unrecognized %%(align) argument: %s"), s); + string_list_clear(¶ms, 0); + return -1; + } } - if (width == ~0U) - die(_("positive width expected with the %%(align) atom")); + if (width == ~0U) { + string_list_clear(¶ms, 0); + return strbuf_addf_ret(err, -1, _("positive width expected with the %%(align) atom")); + } align->width = width; string_list_clear(¶ms, 0); + return 0; } -static void if_atom_parser(const struct ref_format *format, struct used_atom *atom, const char *arg) +static int if_atom_parser(const struct ref_format *format, struct used_atom *atom, + const char *arg, struct strbuf *err) { if (!arg) { atom->u.if_then_else.cmp_status = COMPARE_NONE; - return; + return 0; } else if (skip_prefix(arg, "equals=", &atom->u.if_then_else.str)) { atom->u.if_then_else.cmp_status = COMPARE_EQUAL; } else if (skip_prefix(arg, "notequals=", &atom->u.if_then_else.str)) { atom->u.if_then_else.cmp_status = COMPARE_UNEQUAL; - } else { - die(_("unrecognized %%(if) argument: %s"), arg); - } + } else + return strbuf_addf_ret(err, -1, _("unrecognized %%(if) argument: %s"), arg); + return 0; } -static void head_atom_parser(const struct ref_format *format, struct used_atom *atom, const char *arg) +static int head_atom_parser(const struct ref_format *format, struct used_atom *atom, + const char *arg, struct strbuf *unused_err) { atom->u.head = resolve_refdup("HEAD", RESOLVE_REF_READING, NULL, NULL); + return 0; } static struct { const char *name; cmp_type cmp_type; - void (*parser)(const struct ref_format *format, struct used_atom *atom, const char *arg); + int (*parser)(const struct ref_format *format, struct used_atom *atom, + const char *arg, struct strbuf *err); } valid_atom[] = { { "refname" , FIELD_STR, refname_atom_parser }, { "objecttype" }, @@ -387,7 +440,8 @@ struct ref_formatting_state { struct atom_value { const char *s; - void (*handler)(struct atom_value *atomv, struct ref_formatting_state *state); + int (*handler)(struct atom_value *atomv, struct ref_formatting_state *state, + struct strbuf *err); uintmax_t value; /* used for sorting when not FIELD_STR */ struct used_atom *atom; }; @@ -396,7 +450,8 @@ struct atom_value { * Used to parse format string and sort specifiers */ static int parse_ref_filter_atom(const struct ref_format *format, - const char *atom, const char *ep) + const char *atom, const char *ep, + struct strbuf *err) { const char *sp; const char *arg; @@ -406,7 +461,8 @@ static int parse_ref_filter_atom(const struct ref_format *format, if (*sp == '*' && sp < ep) sp++; /* deref */ if (ep <= sp) - die(_("malformed field name: %.*s"), (int)(ep-atom), atom); + return strbuf_addf_ret(err, -1, _("malformed field name: %.*s"), + (int)(ep-atom), atom); /* Do we have the atom already used elsewhere? */ for (i = 0; i < used_atom_cnt; i++) { @@ -432,7 +488,8 @@ static int parse_ref_filter_atom(const struct ref_format *format, } if (ARRAY_SIZE(valid_atom) <= i) - die(_("unknown field name: %.*s"), (int)(ep-atom), atom); + return strbuf_addf_ret(err, -1, _("unknown field name: %.*s"), + (int)(ep-atom), atom); /* Add it in, including the deref prefix */ at = used_atom_cnt; @@ -451,8 +508,8 @@ static int parse_ref_filter_atom(const struct ref_format *format, } } memset(&used_atom[at].u, 0, sizeof(used_atom[at].u)); - if (valid_atom[i].parser) - valid_atom[i].parser(format, &used_atom[at], arg); + if (valid_atom[i].parser && valid_atom[i].parser(format, &used_atom[at], arg, err)) + return -1; if (*atom == '*') need_tagged = 1; if (!strcmp(valid_atom[i].name, "symref")) @@ -481,7 +538,8 @@ static void quote_formatting(struct strbuf *s, const char *str, int quote_style) } } -static void append_atom(struct atom_value *v, struct ref_formatting_state *state) +static int append_atom(struct atom_value *v, struct ref_formatting_state *state, + struct strbuf *unused_err) { /* * Quote formatting is only done when the stack has a single @@ -493,6 +551,7 @@ static void append_atom(struct atom_value *v, struct ref_formatting_state *state quote_formatting(&state->stack->output, v->s, state->quote_style); else strbuf_addstr(&state->stack->output, v->s); + return 0; } static void push_stack_element(struct ref_formatting_stack **stack) @@ -527,7 +586,8 @@ static void end_align_handler(struct ref_formatting_stack **stack) strbuf_release(&s); } -static void align_atom_handler(struct atom_value *atomv, struct ref_formatting_state *state) +static int align_atom_handler(struct atom_value *atomv, struct ref_formatting_state *state, + struct strbuf *unused_err) { struct ref_formatting_stack *new_stack; @@ -535,6 +595,7 @@ static void align_atom_handler(struct atom_value *atomv, struct ref_formatting_s new_stack = state->stack; new_stack->at_end = end_align_handler; new_stack->at_end_data = &atomv->atom->u.align; + return 0; } static void if_then_else_handler(struct ref_formatting_stack **stack) @@ -572,7 +633,8 @@ static void if_then_else_handler(struct ref_formatting_stack **stack) free(if_then_else); } -static void if_atom_handler(struct atom_value *atomv, struct ref_formatting_state *state) +static int if_atom_handler(struct atom_value *atomv, struct ref_formatting_state *state, + struct strbuf *unused_err) { struct ref_formatting_stack *new_stack; struct if_then_else *if_then_else = xcalloc(sizeof(struct if_then_else), 1); @@ -584,6 +646,7 @@ static void if_atom_handler(struct atom_value *atomv, struct ref_formatting_stat new_stack = state->stack; new_stack->at_end = if_then_else_handler; new_stack->at_end_data = if_then_else; + return 0; } static int is_empty(const char *s) @@ -596,7 +659,8 @@ static int is_empty(const char *s) return 1; } -static void then_atom_handler(struct atom_value *atomv, struct ref_formatting_state *state) +static int then_atom_handler(struct atom_value *atomv, struct ref_formatting_state *state, + struct strbuf *err) { struct ref_formatting_stack *cur = state->stack; struct if_then_else *if_then_else = NULL; @@ -604,11 +668,11 @@ static void then_atom_handler(struct atom_value *atomv, struct ref_formatting_st if (cur->at_end == if_then_else_handler) if_then_else = (struct if_then_else *)cur->at_end_data; if (!if_then_else) - die(_("format: %%(then) atom used without an %%(if) atom")); + return strbuf_addf_ret(err, -1, _("format: %%(then) atom used without an %%(if) atom")); if (if_then_else->then_atom_seen) - die(_("format: %%(then) atom used more than once")); + return strbuf_addf_ret(err, -1, _("format: %%(then) atom used more than once")); if (if_then_else->else_atom_seen) - die(_("format: %%(then) atom used after %%(else)")); + return strbuf_addf_ret(err, -1, _("format: %%(then) atom used after %%(else)")); if_then_else->then_atom_seen = 1; /* * If the 'equals' or 'notequals' attribute is used then @@ -624,9 +688,11 @@ static void then_atom_handler(struct atom_value *atomv, struct ref_formatting_st } else if (cur->output.len && !is_empty(cur->output.buf)) if_then_else->condition_satisfied = 1; strbuf_reset(&cur->output); + return 0; } -static void else_atom_handler(struct atom_value *atomv, struct ref_formatting_state *state) +static int else_atom_handler(struct atom_value *atomv, struct ref_formatting_state *state, + struct strbuf *err) { struct ref_formatting_stack *prev = state->stack; struct if_then_else *if_then_else = NULL; @@ -634,24 +700,26 @@ static void else_atom_handler(struct atom_value *atomv, struct ref_formatting_st if (prev->at_end == if_then_else_handler) if_then_else = (struct if_then_else *)prev->at_end_data; if (!if_then_else) - die(_("format: %%(else) atom used without an %%(if) atom")); + return strbuf_addf_ret(err, -1, _("format: %%(else) atom used without an %%(if) atom")); if (!if_then_else->then_atom_seen) - die(_("format: %%(else) atom used without a %%(then) atom")); + return strbuf_addf_ret(err, -1, _("format: %%(else) atom used without a %%(then) atom")); if (if_then_else->else_atom_seen) - die(_("format: %%(else) atom used more than once")); + return strbuf_addf_ret(err, -1, _("format: %%(else) atom used more than once")); if_then_else->else_atom_seen = 1; push_stack_element(&state->stack); state->stack->at_end_data = prev->at_end_data; state->stack->at_end = prev->at_end; + return 0; } -static void end_atom_handler(struct atom_value *atomv, struct ref_formatting_state *state) +static int end_atom_handler(struct atom_value *atomv, struct ref_formatting_state *state, + struct strbuf *err) { struct ref_formatting_stack *current = state->stack; struct strbuf s = STRBUF_INIT; if (!current->at_end) - die(_("format: %%(end) atom used without corresponding atom")); + return strbuf_addf_ret(err, -1, _("format: %%(end) atom used without corresponding atom")); current->at_end(&state->stack); /* Stack may have been popped within at_end(), hence reset the current pointer */ @@ -668,6 +736,7 @@ static void end_atom_handler(struct atom_value *atomv, struct ref_formatting_sta } strbuf_release(&s); pop_stack_element(&state->stack); + return 0; } /* @@ -702,17 +771,21 @@ int verify_ref_format(struct ref_format *format) format->need_color_reset_at_eol = 0; for (cp = format->format; *cp && (sp = find_next(cp)); ) { + struct strbuf err = STRBUF_INIT; const char *color, *ep = strchr(sp, ')'); int at; if (!ep) return error(_("malformed format string %s"), sp); /* sp points at "%(" and ep points at the closing ")" */ - at = parse_ref_filter_atom(format, sp + 2, ep); + at = parse_ref_filter_atom(format, sp + 2, ep, &err); + if (at < 0) + die("%s", err.buf); cp = ep + 1; if (skip_prefix(used_atom[at].name, "color:", &color)) format->need_color_reset_at_eol = !!strcmp(color, "reset"); + strbuf_release(&err); } if (format->need_color_reset_at_eol && !want_color(format->use_color)) format->need_color_reset_at_eol = 0; @@ -815,7 +888,7 @@ static void grab_commit_values(struct atom_value *val, int deref, struct object if (deref) name++; if (!strcmp(name, "tree")) { - v->s = xstrdup(oid_to_hex(&commit->tree->object.oid)); + v->s = xstrdup(oid_to_hex(get_commit_tree_oid(commit))); } else if (!strcmp(name, "numparent")) { v->value = commit_list_count(commit->parents); @@ -1358,28 +1431,30 @@ static const char *get_refname(struct used_atom *atom, struct ref_array_item *re return show_ref(&atom->u.refname, ref->refname); } -static void get_object(struct ref_array_item *ref, const struct object_id *oid, - int deref, struct object **obj) +static int get_object(struct ref_array_item *ref, const struct object_id *oid, + int deref, struct object **obj, struct strbuf *err) { int eaten; + int ret = 0; unsigned long size; void *buf = get_obj(oid, obj, &size, &eaten); if (!buf) - die(_("missing object %s for %s"), - oid_to_hex(oid), ref->refname); - if (!*obj) - die(_("parse_object_buffer failed on %s for %s"), - oid_to_hex(oid), ref->refname); - - grab_values(ref->value, deref, *obj, buf, size); + ret = strbuf_addf_ret(err, -1, _("missing object %s for %s"), + oid_to_hex(oid), ref->refname); + else if (!*obj) + ret = strbuf_addf_ret(err, -1, _("parse_object_buffer failed on %s for %s"), + oid_to_hex(oid), ref->refname); + else + grab_values(ref->value, deref, *obj, buf, size); if (!eaten) free(buf); + return ret; } /* * Parse the object referred by ref, and grab needed value. */ -static void populate_value(struct ref_array_item *ref) +static int populate_value(struct ref_array_item *ref, struct strbuf *err) { struct object *obj; int i; @@ -1501,16 +1576,17 @@ static void populate_value(struct ref_array_item *ref) break; } if (used_atom_cnt <= i) - return; + return 0; - get_object(ref, &ref->objectname, 0, &obj); + if (get_object(ref, &ref->objectname, 0, &obj, err)) + return -1; /* * If there is no atom that wants to know about tagged * object, we are done. */ if (!need_tagged || (obj->type != OBJ_TAG)) - return; + return 0; /* * If it is a tag object, see if we use a value that derefs @@ -1524,20 +1600,23 @@ static void populate_value(struct ref_array_item *ref) * is not consistent with what deref_tag() does * which peels the onion to the core. */ - get_object(ref, tagged, 1, &obj); + return get_object(ref, tagged, 1, &obj, err); } /* * Given a ref, return the value for the atom. This lazily gets value * out of the object by calling populate value. */ -static void get_ref_atom_value(struct ref_array_item *ref, int atom, struct atom_value **v) +static int get_ref_atom_value(struct ref_array_item *ref, int atom, + struct atom_value **v, struct strbuf *err) { if (!ref->value) { - populate_value(ref); + if (populate_value(ref, err)) + return -1; fill_missing_values(ref->value); } *v = &ref->value[atom]; + return 0; } /* @@ -2075,9 +2154,13 @@ static int cmp_ref_sorting(struct ref_sorting *s, struct ref_array_item *a, stru int cmp; cmp_type cmp_type = used_atom[s->atom].type; int (*cmp_fn)(const char *, const char *); + struct strbuf err = STRBUF_INIT; - get_ref_atom_value(a, s->atom, &va); - get_ref_atom_value(b, s->atom, &vb); + if (get_ref_atom_value(a, s->atom, &va, &err)) + die("%s", err.buf); + if (get_ref_atom_value(b, s->atom, &vb, &err)) + die("%s", err.buf); + strbuf_release(&err); cmp_fn = s->ignore_case ? strcasecmp : strcmp; if (s->version) cmp = versioncmp(va->s, vb->s); @@ -2136,9 +2219,10 @@ static void append_literal(const char *cp, const char *ep, struct ref_formatting } } -void format_ref_array_item(struct ref_array_item *info, +int format_ref_array_item(struct ref_array_item *info, const struct ref_format *format, - struct strbuf *final_buf) + struct strbuf *final_buf, + struct strbuf *error_buf) { const char *cp, *sp, *ep; struct ref_formatting_state state = REF_FORMATTING_STATE_INIT; @@ -2148,14 +2232,17 @@ void format_ref_array_item(struct ref_array_item *info, for (cp = format->format; *cp && (sp = find_next(cp)); cp = ep + 1) { struct atom_value *atomv; + int pos; ep = strchr(sp, ')'); if (cp < sp) append_literal(cp, sp, &state); - get_ref_atom_value(info, - parse_ref_filter_atom(format, sp + 2, ep), - &atomv); - atomv->handler(atomv, &state); + pos = parse_ref_filter_atom(format, sp + 2, ep, error_buf); + if (pos < 0 || get_ref_atom_value(info, pos, &atomv, error_buf) || + atomv->handler(atomv, &state, error_buf)) { + pop_stack_element(&state.stack); + return -1; + } } if (*cp) { sp = cp + strlen(cp); @@ -2164,21 +2251,30 @@ void format_ref_array_item(struct ref_array_item *info, if (format->need_color_reset_at_eol) { struct atom_value resetv; resetv.s = GIT_COLOR_RESET; - append_atom(&resetv, &state); + if (append_atom(&resetv, &state, error_buf)) { + pop_stack_element(&state.stack); + return -1; + } + } + if (state.stack->prev) { + pop_stack_element(&state.stack); + return strbuf_addf_ret(error_buf, -1, _("format: %%(end) atom missing")); } - if (state.stack->prev) - die(_("format: %%(end) atom missing")); strbuf_addbuf(final_buf, &state.stack->output); pop_stack_element(&state.stack); + return 0; } void show_ref_array_item(struct ref_array_item *info, const struct ref_format *format) { struct strbuf final_buf = STRBUF_INIT; + struct strbuf error_buf = STRBUF_INIT; - format_ref_array_item(info, format, &final_buf); + if (format_ref_array_item(info, format, &final_buf, &error_buf)) + die("%s", error_buf.buf); fwrite(final_buf.buf, 1, final_buf.len, stdout); + strbuf_release(&error_buf); strbuf_release(&final_buf); putchar('\n'); } @@ -2201,7 +2297,12 @@ static int parse_sorting_atom(const char *atom) */ struct ref_format dummy = REF_FORMAT_INIT; const char *end = atom + strlen(atom); - return parse_ref_filter_atom(&dummy, atom, end); + struct strbuf err = STRBUF_INIT; + int res = parse_ref_filter_atom(&dummy, atom, end, &err); + if (res < 0) + die("%s", err.buf); + strbuf_release(&err); + return res; } /* If no sorting option is given, use refname to sort as default */ diff --git a/ref-filter.h b/ref-filter.h index 76cf87cb6c..85c8ebc3b9 100644 --- a/ref-filter.h +++ b/ref-filter.h @@ -110,9 +110,10 @@ int verify_ref_format(struct ref_format *format); /* Sort the given ref_array as per the ref_sorting provided */ void ref_array_sort(struct ref_sorting *sort, struct ref_array *array); /* Based on the given format and quote_style, fill the strbuf */ -void format_ref_array_item(struct ref_array_item *info, - const struct ref_format *format, - struct strbuf *final_buf); +int format_ref_array_item(struct ref_array_item *info, + const struct ref_format *format, + struct strbuf *final_buf, + struct strbuf *error_buf); /* Print the ref using the given format and quote_style */ void show_ref_array_item(struct ref_array_item *info, const struct ref_format *format); /* Parse a single sort specifier and add it to the list */ @@ -13,6 +13,8 @@ #include "tag.h" #include "submodule.h" #include "worktree.h" +#include "argv-array.h" +#include "repository.h" /* * List of all available backends @@ -206,7 +208,7 @@ char *refs_resolve_refdup(struct ref_store *refs, char *resolve_refdup(const char *refname, int resolve_flags, struct object_id *oid, int *flags) { - return refs_resolve_refdup(get_main_ref_store(), + return refs_resolve_refdup(get_main_ref_store(the_repository), refname, resolve_flags, oid, flags); } @@ -228,7 +230,7 @@ int refs_read_ref_full(struct ref_store *refs, const char *refname, int read_ref_full(const char *refname, int resolve_flags, struct object_id *oid, int *flags) { - return refs_read_ref_full(get_main_ref_store(), refname, + return refs_read_ref_full(get_main_ref_store(the_repository), refname, resolve_flags, oid, flags); } @@ -301,7 +303,7 @@ enum peel_status peel_object(const struct object_id *name, struct object_id *oid struct object *o = lookup_unknown_object(name->hash); if (o->type == OBJ_NONE) { - int type = oid_object_info(name, NULL); + int type = oid_object_info(the_repository, name, NULL); if (type < 0 || !object_as_type(o, type, 0)) return PEEL_INVALID; } @@ -375,7 +377,7 @@ int refs_for_each_tag_ref(struct ref_store *refs, each_ref_fn fn, void *cb_data) int for_each_tag_ref(each_ref_fn fn, void *cb_data) { - return refs_for_each_tag_ref(get_main_ref_store(), fn, cb_data); + return refs_for_each_tag_ref(get_main_ref_store(the_repository), fn, cb_data); } int refs_for_each_branch_ref(struct ref_store *refs, each_ref_fn fn, void *cb_data) @@ -385,7 +387,7 @@ int refs_for_each_branch_ref(struct ref_store *refs, each_ref_fn fn, void *cb_da int for_each_branch_ref(each_ref_fn fn, void *cb_data) { - return refs_for_each_branch_ref(get_main_ref_store(), fn, cb_data); + return refs_for_each_branch_ref(get_main_ref_store(the_repository), fn, cb_data); } int refs_for_each_remote_ref(struct ref_store *refs, each_ref_fn fn, void *cb_data) @@ -395,7 +397,7 @@ int refs_for_each_remote_ref(struct ref_store *refs, each_ref_fn fn, void *cb_da int for_each_remote_ref(each_ref_fn fn, void *cb_data) { - return refs_for_each_remote_ref(get_main_ref_store(), fn, cb_data); + return refs_for_each_remote_ref(get_main_ref_store(the_repository), fn, cb_data); } int head_ref_namespaced(each_ref_fn fn, void *cb_data) @@ -502,6 +504,19 @@ int refname_match(const char *abbrev_name, const char *full_name) } /* + * Given a 'prefix' expand it by the rules in 'ref_rev_parse_rules' and add + * the results to 'prefixes' + */ +void expand_ref_prefix(struct argv_array *prefixes, const char *prefix) +{ + const char **p; + int len = strlen(prefix); + + for (p = ref_rev_parse_rules; *p; p++) + argv_array_pushf(prefixes, *p, len, prefix); +} + +/* * *string and *len will only be substituted, and *string returned (for * later free()ing) if the string passed in is a magic short-hand form * to name a branch. @@ -731,7 +746,7 @@ int refs_delete_ref(struct ref_store *refs, const char *msg, struct strbuf err = STRBUF_INIT; if (ref_type(refname) == REF_TYPE_PSEUDOREF) { - assert(refs == get_main_ref_store()); + assert(refs == get_main_ref_store(the_repository)); return delete_pseudoref(refname, old_oid); } @@ -753,7 +768,7 @@ int refs_delete_ref(struct ref_store *refs, const char *msg, int delete_ref(const char *msg, const char *refname, const struct object_id *old_oid, unsigned int flags) { - return refs_delete_ref(get_main_ref_store(), msg, refname, + return refs_delete_ref(get_main_ref_store(the_repository), msg, refname, old_oid, flags); } @@ -929,7 +944,7 @@ struct ref_transaction *ref_store_transaction_begin(struct ref_store *refs, struct ref_transaction *ref_transaction_begin(struct strbuf *err) { - return ref_store_transaction_begin(get_main_ref_store(), err); + return ref_store_transaction_begin(get_main_ref_store(the_repository), err); } void ref_transaction_free(struct ref_transaction *transaction) @@ -1061,7 +1076,7 @@ int refs_update_ref(struct ref_store *refs, const char *msg, int ret = 0; if (ref_type(refname) == REF_TYPE_PSEUDOREF) { - assert(refs == get_main_ref_store()); + assert(refs == get_main_ref_store(the_repository)); ret = write_pseudoref(refname, new_oid, old_oid, &err); } else { t = ref_store_transaction_begin(refs, &err); @@ -1100,7 +1115,7 @@ int update_ref(const char *msg, const char *refname, const struct object_id *old_oid, unsigned int flags, enum action_on_err onerr) { - return refs_update_ref(get_main_ref_store(), msg, refname, new_oid, + return refs_update_ref(get_main_ref_store(the_repository), msg, refname, new_oid, old_oid, flags, onerr); } @@ -1321,7 +1336,7 @@ int refs_head_ref(struct ref_store *refs, each_ref_fn fn, void *cb_data) int head_ref(each_ref_fn fn, void *cb_data) { - return refs_head_ref(get_main_ref_store(), fn, cb_data); + return refs_head_ref(get_main_ref_store(the_repository), fn, cb_data); } struct ref_iterator *refs_ref_iterator_begin( @@ -1380,7 +1395,7 @@ int refs_for_each_ref(struct ref_store *refs, each_ref_fn fn, void *cb_data) int for_each_ref(each_ref_fn fn, void *cb_data) { - return refs_for_each_ref(get_main_ref_store(), fn, cb_data); + return refs_for_each_ref(get_main_ref_store(the_repository), fn, cb_data); } int refs_for_each_ref_in(struct ref_store *refs, const char *prefix, @@ -1391,7 +1406,7 @@ int refs_for_each_ref_in(struct ref_store *refs, const char *prefix, int for_each_ref_in(const char *prefix, each_ref_fn fn, void *cb_data) { - return refs_for_each_ref_in(get_main_ref_store(), prefix, fn, cb_data); + return refs_for_each_ref_in(get_main_ref_store(the_repository), prefix, fn, cb_data); } int for_each_fullref_in(const char *prefix, each_ref_fn fn, void *cb_data, unsigned int broken) @@ -1400,7 +1415,7 @@ int for_each_fullref_in(const char *prefix, each_ref_fn fn, void *cb_data, unsig if (broken) flag = DO_FOR_EACH_INCLUDE_BROKEN; - return do_for_each_ref(get_main_ref_store(), + return do_for_each_ref(get_main_ref_store(the_repository), prefix, fn, 0, flag, cb_data); } @@ -1415,9 +1430,9 @@ int refs_for_each_fullref_in(struct ref_store *refs, const char *prefix, return do_for_each_ref(refs, prefix, fn, 0, flag, cb_data); } -int for_each_replace_ref(each_ref_fn fn, void *cb_data) +int for_each_replace_ref(struct repository *r, each_ref_fn fn, void *cb_data) { - return do_for_each_ref(get_main_ref_store(), + return do_for_each_ref(get_main_ref_store(r), git_replace_ref_base, fn, strlen(git_replace_ref_base), DO_FOR_EACH_INCLUDE_BROKEN, cb_data); @@ -1428,7 +1443,7 @@ int for_each_namespaced_ref(each_ref_fn fn, void *cb_data) struct strbuf buf = STRBUF_INIT; int ret; strbuf_addf(&buf, "%srefs/", get_git_namespace()); - ret = do_for_each_ref(get_main_ref_store(), + ret = do_for_each_ref(get_main_ref_store(the_repository), buf.buf, fn, 0, 0, cb_data); strbuf_release(&buf); return ret; @@ -1442,7 +1457,7 @@ int refs_for_each_rawref(struct ref_store *refs, each_ref_fn fn, void *cb_data) int for_each_rawref(each_ref_fn fn, void *cb_data) { - return refs_for_each_rawref(get_main_ref_store(), fn, cb_data); + return refs_for_each_rawref(get_main_ref_store(the_repository), fn, cb_data); } int refs_read_raw_ref(struct ref_store *ref_store, @@ -1548,7 +1563,7 @@ const char *refs_resolve_ref_unsafe(struct ref_store *refs, /* backend functions */ int refs_init_db(struct strbuf *err) { - struct ref_store *refs = get_main_ref_store(); + struct ref_store *refs = get_main_ref_store(the_repository); return refs->be->init_db(refs, err); } @@ -1556,7 +1571,7 @@ int refs_init_db(struct strbuf *err) const char *resolve_ref_unsafe(const char *refname, int resolve_flags, struct object_id *oid, int *flags) { - return refs_resolve_ref_unsafe(get_main_ref_store(), refname, + return refs_resolve_ref_unsafe(get_main_ref_store(the_repository), refname, resolve_flags, oid, flags); } @@ -1608,9 +1623,6 @@ static struct ref_store_hash_entry *alloc_ref_store_hash_entry( return entry; } -/* A pointer to the ref_store for the main repository: */ -static struct ref_store *main_ref_store; - /* A hashmap of ref_stores, stored by submodule name: */ static struct hashmap submodule_ref_stores; @@ -1652,13 +1664,16 @@ static struct ref_store *ref_store_init(const char *gitdir, return refs; } -struct ref_store *get_main_ref_store(void) +struct ref_store *get_main_ref_store(struct repository *r) { - if (main_ref_store) - return main_ref_store; + if (r->refs) + return r->refs; + + if (!r->gitdir) + BUG("attempting to get main_ref_store outside of repository"); - main_ref_store = ref_store_init(get_git_dir(), REF_STORE_ALL_CAPS); - return main_ref_store; + r->refs = ref_store_init(r->gitdir, REF_STORE_ALL_CAPS); + return r->refs; } /* @@ -1727,7 +1742,7 @@ struct ref_store *get_worktree_ref_store(const struct worktree *wt) const char *id; if (wt->is_current) - return get_main_ref_store(); + return get_main_ref_store(the_repository); id = wt->id ? wt->id : "/"; refs = lookup_ref_store_map(&worktree_ref_stores, id); @@ -1783,7 +1798,7 @@ int refs_peel_ref(struct ref_store *refs, const char *refname, int peel_ref(const char *refname, struct object_id *oid) { - return refs_peel_ref(get_main_ref_store(), refname, oid); + return refs_peel_ref(get_main_ref_store(the_repository), refname, oid); } int refs_create_symref(struct ref_store *refs, @@ -1799,7 +1814,7 @@ int refs_create_symref(struct ref_store *refs, int create_symref(const char *ref_target, const char *refs_heads_master, const char *logmsg) { - return refs_create_symref(get_main_ref_store(), ref_target, + return refs_create_symref(get_main_ref_store(the_repository), ref_target, refs_heads_master, logmsg); } @@ -2007,7 +2022,7 @@ int refs_for_each_reflog(struct ref_store *refs, each_ref_fn fn, void *cb_data) int for_each_reflog(each_ref_fn fn, void *cb_data) { - return refs_for_each_reflog(get_main_ref_store(), fn, cb_data); + return refs_for_each_reflog(get_main_ref_store(the_repository), fn, cb_data); } int refs_for_each_reflog_ent_reverse(struct ref_store *refs, @@ -2022,7 +2037,7 @@ int refs_for_each_reflog_ent_reverse(struct ref_store *refs, int for_each_reflog_ent_reverse(const char *refname, each_reflog_ent_fn fn, void *cb_data) { - return refs_for_each_reflog_ent_reverse(get_main_ref_store(), + return refs_for_each_reflog_ent_reverse(get_main_ref_store(the_repository), refname, fn, cb_data); } @@ -2035,7 +2050,7 @@ int refs_for_each_reflog_ent(struct ref_store *refs, const char *refname, int for_each_reflog_ent(const char *refname, each_reflog_ent_fn fn, void *cb_data) { - return refs_for_each_reflog_ent(get_main_ref_store(), refname, + return refs_for_each_reflog_ent(get_main_ref_store(the_repository), refname, fn, cb_data); } @@ -2046,7 +2061,7 @@ int refs_reflog_exists(struct ref_store *refs, const char *refname) int reflog_exists(const char *refname) { - return refs_reflog_exists(get_main_ref_store(), refname); + return refs_reflog_exists(get_main_ref_store(the_repository), refname); } int refs_create_reflog(struct ref_store *refs, const char *refname, @@ -2058,7 +2073,7 @@ int refs_create_reflog(struct ref_store *refs, const char *refname, int safe_create_reflog(const char *refname, int force_create, struct strbuf *err) { - return refs_create_reflog(get_main_ref_store(), refname, + return refs_create_reflog(get_main_ref_store(the_repository), refname, force_create, err); } @@ -2069,7 +2084,7 @@ int refs_delete_reflog(struct ref_store *refs, const char *refname) int delete_reflog(const char *refname) { - return refs_delete_reflog(get_main_ref_store(), refname); + return refs_delete_reflog(get_main_ref_store(the_repository), refname); } int refs_reflog_expire(struct ref_store *refs, @@ -2092,7 +2107,7 @@ int reflog_expire(const char *refname, const struct object_id *oid, reflog_expiry_cleanup_fn cleanup_fn, void *policy_cb_data) { - return refs_reflog_expire(get_main_ref_store(), + return refs_reflog_expire(get_main_ref_store(the_repository), refname, oid, flags, prepare_fn, should_prune_fn, cleanup_fn, policy_cb_data); @@ -2115,7 +2130,7 @@ int refs_delete_refs(struct ref_store *refs, const char *msg, int delete_refs(const char *msg, struct string_list *refnames, unsigned int flags) { - return refs_delete_refs(get_main_ref_store(), msg, refnames, flags); + return refs_delete_refs(get_main_ref_store(the_repository), msg, refnames, flags); } int refs_rename_ref(struct ref_store *refs, const char *oldref, @@ -2126,7 +2141,7 @@ int refs_rename_ref(struct ref_store *refs, const char *oldref, int rename_ref(const char *oldref, const char *newref, const char *logmsg) { - return refs_rename_ref(get_main_ref_store(), oldref, newref, logmsg); + return refs_rename_ref(get_main_ref_store(the_repository), oldref, newref, logmsg); } int refs_copy_existing_ref(struct ref_store *refs, const char *oldref, @@ -2137,5 +2152,5 @@ int refs_copy_existing_ref(struct ref_store *refs, const char *oldref, int copy_existing_ref(const char *oldref, const char *newref, const char *logmsg) { - return refs_copy_existing_ref(get_main_ref_store(), oldref, newref, logmsg); + return refs_copy_existing_ref(get_main_ref_store(the_repository), oldref, newref, logmsg); } @@ -139,6 +139,13 @@ int resolve_gitlink_ref(const char *submodule, const char *refname, */ int refname_match(const char *abbrev_name, const char *full_name); +/* + * Given a 'prefix' expand it by the rules in 'ref_rev_parse_rules' and add + * the results to 'prefixes' + */ +struct argv_array; +void expand_ref_prefix(struct argv_array *prefixes, const char *prefix); + int expand_ref(const char *str, int len, struct object_id *oid, char **ref); int dwim_ref(const char *str, int len, struct object_id *oid, char **ref); int dwim_log(const char *str, int len, struct object_id *oid, char **ref); @@ -300,7 +307,7 @@ int for_each_fullref_in(const char *prefix, each_ref_fn fn, void *cb_data, int for_each_tag_ref(each_ref_fn fn, void *cb_data); int for_each_branch_ref(each_ref_fn fn, void *cb_data); int for_each_remote_ref(each_ref_fn fn, void *cb_data); -int for_each_replace_ref(each_ref_fn fn, void *cb_data); +int for_each_replace_ref(struct repository *r, each_ref_fn fn, void *cb_data); int for_each_glob_ref(each_ref_fn fn, const char *pattern, void *cb_data); int for_each_glob_ref_in(each_ref_fn fn, const char *pattern, const char *prefix, void *cb_data); @@ -758,7 +765,7 @@ int reflog_expire(const char *refname, const struct object_id *oid, int ref_storage_backend_exists(const char *name); -struct ref_store *get_main_ref_store(void); +struct ref_store *get_main_ref_store(struct repository *r); /* * Return the ref_store instance for the specified submodule. For the * main repository, use submodule==NULL; such a call cannot fail. For diff --git a/refs/files-backend.c b/refs/files-backend.c index a92a2aa821..49d8f67bf1 100644 --- a/refs/files-backend.c +++ b/refs/files-backend.c @@ -62,10 +62,6 @@ struct ref_lock { struct object_id old_oid; }; -/* - * Future: need to be in "struct repository" - * when doing a full libification. - */ struct files_ref_store { struct ref_store base; unsigned int store_flags; diff --git a/remote-curl.c b/remote-curl.c index 8d2ffaf8de..ceb05347bd 100644 --- a/remote-curl.c +++ b/remote-curl.c @@ -1,6 +1,7 @@ #include "cache.h" #include "config.h" #include "remote.h" +#include "connect.h" #include "strbuf.h" #include "walker.h" #include "http.h" @@ -13,6 +14,7 @@ #include "credential.h" #include "sha1-array.h" #include "send-pack.h" +#include "protocol.h" #include "quote.h" static struct remote *remote; @@ -184,12 +186,13 @@ static int set_option(const char *name, const char *value) } struct discovery { - const char *service; + char *service; char *buf_alloc; char *buf; size_t len; struct ref *refs; struct oid_array shallow; + enum protocol_version version; unsigned proto_git : 1; }; static struct discovery *last_discovery; @@ -197,8 +200,31 @@ static struct discovery *last_discovery; static struct ref *parse_git_refs(struct discovery *heads, int for_push) { struct ref *list = NULL; - get_remote_heads(-1, heads->buf, heads->len, &list, - for_push ? REF_NORMAL : 0, NULL, &heads->shallow); + struct packet_reader reader; + + packet_reader_init(&reader, -1, heads->buf, heads->len, + PACKET_READ_CHOMP_NEWLINE | + PACKET_READ_GENTLE_ON_EOF); + + heads->version = discover_version(&reader); + switch (heads->version) { + case protocol_v2: + /* + * Do nothing. This isn't a list of refs but rather a + * capability advertisement. Client would have run + * 'stateless-connect' so we'll dump this capability listing + * and let them request the refs themselves. + */ + break; + case protocol_v1: + case protocol_v0: + get_remote_heads(&reader, &list, for_push ? REF_NORMAL : 0, + NULL, &heads->shallow); + break; + case protocol_unknown_version: + BUG("unknown protocol version"); + } + return list; } @@ -259,6 +285,7 @@ static void free_discovery(struct discovery *d) free(d->shallow.oid); free(d->buf_alloc); free_refs(d->refs); + free(d->service); free(d); } } @@ -290,6 +317,19 @@ static int show_http_message(struct strbuf *type, struct strbuf *charset, return 0; } +static int get_protocol_http_header(enum protocol_version version, + struct strbuf *header) +{ + if (version > 0) { + strbuf_addf(header, GIT_PROTOCOL_HEADER ": version=%d", + version); + + return 1; + } + + return 0; +} + static struct discovery *discover_refs(const char *service, int for_push) { struct strbuf exp = STRBUF_INIT; @@ -298,9 +338,12 @@ static struct discovery *discover_refs(const char *service, int for_push) struct strbuf buffer = STRBUF_INIT; struct strbuf refs_url = STRBUF_INIT; struct strbuf effective_url = STRBUF_INIT; + struct strbuf protocol_header = STRBUF_INIT; + struct string_list extra_headers = STRING_LIST_INIT_DUP; struct discovery *last = last_discovery; int http_ret, maybe_smart = 0; struct http_get_options http_options; + enum protocol_version version = get_protocol_version_config(); if (last && !strcmp(service, last->service)) return last; @@ -317,11 +360,24 @@ static struct discovery *discover_refs(const char *service, int for_push) strbuf_addf(&refs_url, "service=%s", service); } + /* + * NEEDSWORK: If we are trying to use protocol v2 and we are planning + * to perform a push, then fallback to v0 since the client doesn't know + * how to push yet using v2. + */ + if (version == protocol_v2 && !strcmp("git-receive-pack", service)) + version = protocol_v0; + + /* Add the extra Git-Protocol header */ + if (get_protocol_http_header(version, &protocol_header)) + string_list_append(&extra_headers, protocol_header.buf); + memset(&http_options, 0, sizeof(http_options)); http_options.content_type = &type; http_options.charset = &charset; http_options.effective_url = &effective_url; http_options.base_url = &url; + http_options.extra_headers = &extra_headers; http_options.initial_request = 1; http_options.no_cache = 1; http_options.keep_error = 1; @@ -345,7 +401,7 @@ static struct discovery *discover_refs(const char *service, int for_push) warning(_("redirecting to %s"), url.buf); last= xcalloc(1, sizeof(*last_discovery)); - last->service = service; + last->service = xstrdup(service); last->buf_alloc = strbuf_detach(&buffer, &last->len); last->buf = last->buf_alloc; @@ -377,6 +433,9 @@ static struct discovery *discover_refs(const char *service, int for_push) ; last->proto_git = 1; + } else if (maybe_smart && + last->len > 5 && starts_with(last->buf + 4, "version 2")) { + last->proto_git = 1; } if (last->proto_git) @@ -390,6 +449,8 @@ static struct discovery *discover_refs(const char *service, int for_push) strbuf_release(&charset); strbuf_release(&effective_url); strbuf_release(&buffer); + strbuf_release(&protocol_header); + string_list_clear(&extra_headers, 0); last_discovery = last; return last; } @@ -426,6 +487,7 @@ struct rpc_state { char *service_url; char *hdr_content_type; char *hdr_accept; + char *protocol_header; char *buf; size_t alloc; size_t len; @@ -612,6 +674,10 @@ static int post_rpc(struct rpc_state *rpc) headers = curl_slist_append(headers, needs_100_continue ? "Expect: 100-continue" : "Expect:"); + /* Add the extra Git-Protocol header */ + if (rpc->protocol_header) + headers = curl_slist_append(headers, rpc->protocol_header); + retry: slot = get_active_slot(); @@ -752,6 +818,11 @@ static int rpc_service(struct rpc_state *rpc, struct discovery *heads) strbuf_addf(&buf, "Accept: application/x-%s-result", svc); rpc->hdr_accept = strbuf_detach(&buf, NULL); + if (get_protocol_http_header(heads->version, &buf)) + rpc->protocol_header = strbuf_detach(&buf, NULL); + else + rpc->protocol_header = NULL; + while (!err) { int n = packet_read(rpc->out, NULL, NULL, rpc->buf, rpc->alloc, 0); if (!n) @@ -779,6 +850,7 @@ static int rpc_service(struct rpc_state *rpc, struct discovery *heads) free(rpc->service_url); free(rpc->hdr_content_type); free(rpc->hdr_accept); + free(rpc->protocol_header); free(rpc->buf); strbuf_release(&buf); return err; @@ -797,9 +869,6 @@ static int fetch_dumb(int nr_heads, struct ref **to_fetch) targets[i] = xstrdup(oid_to_hex(&to_fetch[i]->old_oid)); walker = get_http_walker(url.buf); - walker->get_all = 1; - walker->get_tree = 1; - walker->get_history = 1; walker->get_verbosely = options.verbosity >= 3; walker->get_recover = 0; ret = walker_fetch(walker, nr_heads, targets, NULL, NULL); @@ -1056,6 +1125,202 @@ static void parse_push(struct strbuf *buf) free(specs); } +/* + * Used to represent the state of a connection to an HTTP server when + * communicating using git's wire-protocol version 2. + */ +struct proxy_state { + char *service_name; + char *service_url; + struct curl_slist *headers; + struct strbuf request_buffer; + int in; + int out; + struct packet_reader reader; + size_t pos; + int seen_flush; +}; + +static void proxy_state_init(struct proxy_state *p, const char *service_name, + enum protocol_version version) +{ + struct strbuf buf = STRBUF_INIT; + + memset(p, 0, sizeof(*p)); + p->service_name = xstrdup(service_name); + + p->in = 0; + p->out = 1; + strbuf_init(&p->request_buffer, 0); + + strbuf_addf(&buf, "%s%s", url.buf, p->service_name); + p->service_url = strbuf_detach(&buf, NULL); + + p->headers = http_copy_default_headers(); + + strbuf_addf(&buf, "Content-Type: application/x-%s-request", p->service_name); + p->headers = curl_slist_append(p->headers, buf.buf); + strbuf_reset(&buf); + + strbuf_addf(&buf, "Accept: application/x-%s-result", p->service_name); + p->headers = curl_slist_append(p->headers, buf.buf); + strbuf_reset(&buf); + + p->headers = curl_slist_append(p->headers, "Transfer-Encoding: chunked"); + + /* Add the Git-Protocol header */ + if (get_protocol_http_header(version, &buf)) + p->headers = curl_slist_append(p->headers, buf.buf); + + packet_reader_init(&p->reader, p->in, NULL, 0, + PACKET_READ_GENTLE_ON_EOF); + + strbuf_release(&buf); +} + +static void proxy_state_clear(struct proxy_state *p) +{ + free(p->service_name); + free(p->service_url); + curl_slist_free_all(p->headers); + strbuf_release(&p->request_buffer); +} + +/* + * CURLOPT_READFUNCTION callback function. + * Attempts to copy over a single packet-line at a time into the + * curl provided buffer. + */ +static size_t proxy_in(char *buffer, size_t eltsize, + size_t nmemb, void *userdata) +{ + size_t max; + struct proxy_state *p = userdata; + size_t avail = p->request_buffer.len - p->pos; + + + if (eltsize != 1) + BUG("curl read callback called with size = %"PRIuMAX" != 1", + (uintmax_t)eltsize); + max = nmemb; + + if (!avail) { + if (p->seen_flush) { + p->seen_flush = 0; + return 0; + } + + strbuf_reset(&p->request_buffer); + switch (packet_reader_read(&p->reader)) { + case PACKET_READ_EOF: + die("unexpected EOF when reading from parent process"); + case PACKET_READ_NORMAL: + packet_buf_write_len(&p->request_buffer, p->reader.line, + p->reader.pktlen); + break; + case PACKET_READ_DELIM: + packet_buf_delim(&p->request_buffer); + break; + case PACKET_READ_FLUSH: + packet_buf_flush(&p->request_buffer); + p->seen_flush = 1; + break; + } + p->pos = 0; + avail = p->request_buffer.len; + } + + if (max < avail) + avail = max; + memcpy(buffer, p->request_buffer.buf + p->pos, avail); + p->pos += avail; + return avail; +} + +static size_t proxy_out(char *buffer, size_t eltsize, + size_t nmemb, void *userdata) +{ + size_t size; + struct proxy_state *p = userdata; + + if (eltsize != 1) + BUG("curl read callback called with size = %"PRIuMAX" != 1", + (uintmax_t)eltsize); + size = nmemb; + + write_or_die(p->out, buffer, size); + return size; +} + +/* Issues a request to the HTTP server configured in `p` */ +static int proxy_request(struct proxy_state *p) +{ + struct active_request_slot *slot; + + slot = get_active_slot(); + + curl_easy_setopt(slot->curl, CURLOPT_NOBODY, 0); + curl_easy_setopt(slot->curl, CURLOPT_POST, 1); + curl_easy_setopt(slot->curl, CURLOPT_URL, p->service_url); + curl_easy_setopt(slot->curl, CURLOPT_HTTPHEADER, p->headers); + + /* Setup function to read request from client */ + curl_easy_setopt(slot->curl, CURLOPT_READFUNCTION, proxy_in); + curl_easy_setopt(slot->curl, CURLOPT_READDATA, p); + + /* Setup function to write server response to client */ + curl_easy_setopt(slot->curl, CURLOPT_WRITEFUNCTION, proxy_out); + curl_easy_setopt(slot->curl, CURLOPT_WRITEDATA, p); + + if (run_slot(slot, NULL) != HTTP_OK) + return -1; + + return 0; +} + +static int stateless_connect(const char *service_name) +{ + struct discovery *discover; + struct proxy_state p; + + /* + * Run the info/refs request and see if the server supports protocol + * v2. If and only if the server supports v2 can we successfully + * establish a stateless connection, otherwise we need to tell the + * client to fallback to using other transport helper functions to + * complete their request. + */ + discover = discover_refs(service_name, 0); + if (discover->version != protocol_v2) { + printf("fallback\n"); + fflush(stdout); + return -1; + } else { + /* Stateless Connection established */ + printf("\n"); + fflush(stdout); + } + + proxy_state_init(&p, service_name, discover->version); + + /* + * Dump the capability listing that we got from the server earlier + * during the info/refs request. + */ + write_or_die(p.out, discover->buf, discover->len); + + /* Peek the next packet line. Until we see EOF keep sending POSTs */ + while (packet_reader_peek(&p.reader) != PACKET_READ_EOF) { + if (proxy_request(&p)) { + /* We would have an err here */ + break; + } + } + + proxy_state_clear(&p); + return 0; +} + int cmd_main(int argc, const char **argv) { struct strbuf buf = STRBUF_INIT; @@ -1124,12 +1389,16 @@ int cmd_main(int argc, const char **argv) fflush(stdout); } else if (!strcmp(buf.buf, "capabilities")) { + printf("stateless-connect\n"); printf("fetch\n"); printf("option\n"); printf("push\n"); printf("check-connectivity\n"); printf("\n"); fflush(stdout); + } else if (skip_prefix(buf.buf, "stateless-connect ", &arg)) { + if (!stateless_connect(arg)) + break; } else { error("remote-curl: unknown command '%s' from git", buf.buf); return 1; @@ -1376,7 +1376,7 @@ static void add_missing_tags(struct ref *src, struct ref **dst, struct ref ***ds continue; /* not a tag */ if (string_list_has_string(&dst_tag, ref->name)) continue; /* they already have it */ - if (oid_object_info(&ref->new_oid, NULL) != OBJ_TAG) + if (oid_object_info(the_repository, &ref->new_oid, NULL) != OBJ_TAG) continue; /* be conservative */ item = string_list_append(&src_tag, ref->name); item->util = ref; @@ -151,10 +151,19 @@ int check_ref_type(const struct ref *ref, int flags); void free_refs(struct ref *ref); struct oid_array; -extern struct ref **get_remote_heads(int in, char *src_buf, size_t src_len, +struct packet_reader; +struct argv_array; +struct string_list; +extern struct ref **get_remote_heads(struct packet_reader *reader, struct ref **list, unsigned int flags, struct oid_array *extra_have, - struct oid_array *shallow); + struct oid_array *shallow_points); + +/* Used for protocol v2 in order to retrieve refs from a remote */ +extern struct ref **get_remote_refs(int fd_out, struct packet_reader *reader, + struct ref **list, int for_push, + const struct argv_array *ref_prefixes, + const struct string_list *server_options); int resolve_remote_symref(struct ref *ref, struct ref *list); int ref_newer(const struct object_id *new_oid, const struct object_id *old_oid); diff --git a/replace-object.c b/replace-object.c index 336357394d..801b5c1678 100644 --- a/replace-object.c +++ b/replace-object.c @@ -1,55 +1,11 @@ #include "cache.h" -#include "sha1-lookup.h" +#include "oidmap.h" +#include "object-store.h" +#include "replace-object.h" #include "refs.h" +#include "repository.h" #include "commit.h" -/* - * An array of replacements. The array is kept sorted by the original - * sha1. - */ -static struct replace_object { - struct object_id original; - struct object_id replacement; -} **replace_object; - -static int replace_object_alloc, replace_object_nr; - -static const unsigned char *replace_sha1_access(size_t index, void *table) -{ - struct replace_object **replace = table; - return replace[index]->original.hash; -} - -static int replace_object_pos(const unsigned char *sha1) -{ - return sha1_pos(sha1, replace_object, replace_object_nr, - replace_sha1_access); -} - -static int register_replace_object(struct replace_object *replace, - int ignore_dups) -{ - int pos = replace_object_pos(replace->original.hash); - - if (0 <= pos) { - if (ignore_dups) - free(replace); - else { - free(replace_object[pos]); - replace_object[pos] = replace; - } - return 1; - } - pos = -pos - 1; - ALLOC_GROW(replace_object, replace_object_nr + 1, replace_object_alloc); - replace_object_nr++; - if (pos < replace_object_nr) - MOVE_ARRAY(replace_object + pos + 1, replace_object + pos, - replace_object_nr - pos - 1); - replace_object[pos] = replace; - return 0; -} - static int register_replace_ref(const char *refname, const struct object_id *oid, int flag, void *cb_data) @@ -59,7 +15,7 @@ static int register_replace_ref(const char *refname, const char *hash = slash ? slash + 1 : refname; struct replace_object *repl_obj = xmalloc(sizeof(*repl_obj)); - if (get_oid_hex(hash, &repl_obj->original)) { + if (get_oid_hex(hash, &repl_obj->original.oid)) { free(repl_obj); warning("bad replace ref name: %s", refname); return 0; @@ -69,23 +25,22 @@ static int register_replace_ref(const char *refname, oidcpy(&repl_obj->replacement, oid); /* Register new object */ - if (register_replace_object(repl_obj, 1)) + if (oidmap_put(the_repository->objects->replace_map, repl_obj)) die("duplicate replace ref: %s", refname); return 0; } -static void prepare_replace_object(void) +static void prepare_replace_object(struct repository *r) { - static int replace_object_prepared; - - if (replace_object_prepared) + if (r->objects->replace_map) return; - for_each_replace_ref(register_replace_ref, NULL); - replace_object_prepared = 1; - if (!replace_object_nr) - check_replace_refs = 0; + r->objects->replace_map = + xmalloc(sizeof(*r->objects->replace_map)); + oidmap_init(r->objects->replace_map, 0); + + for_each_replace_ref(r, register_replace_ref, NULL); } /* We allow "recursive" replacement. Only within reason, though */ @@ -98,23 +53,21 @@ static void prepare_replace_object(void) * permanently-allocated value. This function always respects replace * references, regardless of the value of check_replace_refs. */ -const struct object_id *do_lookup_replace_object(const struct object_id *oid) +const struct object_id *do_lookup_replace_object(struct repository *r, + const struct object_id *oid) { - int pos, depth = MAXREPLACEDEPTH; + int depth = MAXREPLACEDEPTH; const struct object_id *cur = oid; - prepare_replace_object(); + prepare_replace_object(r); /* Try to recursively replace the object */ - do { - if (--depth < 0) - die("replace depth too high for object %s", - oid_to_hex(oid)); - - pos = replace_object_pos(cur->hash); - if (0 <= pos) - cur = &replace_object[pos]->replacement; - } while (0 <= pos); - - return cur; + while (depth-- > 0) { + struct replace_object *repl_obj = + oidmap_get(r->objects->replace_map, cur); + if (!repl_obj) + return cur; + cur = &repl_obj->replacement; + } + die("replace depth too high for object %s", oid_to_hex(oid)); } diff --git a/replace-object.h b/replace-object.h new file mode 100644 index 0000000000..f996de3d62 --- /dev/null +++ b/replace-object.h @@ -0,0 +1,36 @@ +#ifndef REPLACE_OBJECT_H +#define REPLACE_OBJECT_H + +#include "oidmap.h" +#include "repository.h" +#include "object-store.h" + +struct replace_object { + struct oidmap_entry original; + struct object_id replacement; +}; + +/* + * This internal function is only declared here for the benefit of + * lookup_replace_object(). Please do not call it directly. + */ +extern const struct object_id *do_lookup_replace_object(struct repository *r, + const struct object_id *oid); + +/* + * If object sha1 should be replaced, return the replacement object's + * name (replaced recursively, if necessary). The return value is + * either sha1 or a pointer to a permanently-allocated value. When + * object replacement is suppressed, always return sha1. + */ +static inline const struct object_id *lookup_replace_object(struct repository *r, + const struct object_id *oid) +{ + if (!check_replace_refs || + (r->objects->replace_map && + r->objects->replace_map->map.tablesize == 0)) + return oid; + return do_lookup_replace_object(r, oid); +} + +#endif /* REPLACE_OBJECT_H */ diff --git a/repository.c b/repository.c index a4848c1bd0..beff3caa9e 100644 --- a/repository.c +++ b/repository.c @@ -135,9 +135,9 @@ static int read_and_verify_repository_format(struct repository_format *format, * Initialize 'repo' based on the provided 'gitdir'. * Return 0 upon success and a non-zero value upon failure. */ -static int repo_init(struct repository *repo, - const char *gitdir, - const char *worktree) +int repo_init(struct repository *repo, + const char *gitdir, + const char *worktree) { struct repository_format format; memset(repo, 0, sizeof(*repo)); @@ -176,7 +176,7 @@ int repo_submodule_init(struct repository *submodule, struct strbuf worktree = STRBUF_INIT; int ret = 0; - sub = submodule_from_cache(superproject, &null_oid, path); + sub = submodule_from_path(superproject, &null_oid, path); if (!sub) { ret = -1; goto out; diff --git a/repository.h b/repository.h index 09df94a472..f2646f0c52 100644 --- a/repository.h +++ b/repository.h @@ -26,6 +26,9 @@ struct repository { */ struct raw_object_store *objects; + /* The store in which the refs are held. */ + struct ref_store *refs; + /* * Path to the repository's graft file. * Cannot be NULL after initialization. @@ -97,6 +100,9 @@ extern void repo_set_gitdir(struct repository *repo, extern void repo_set_worktree(struct repository *repo, const char *path); extern void repo_set_hash_algo(struct repository *repo, int algo); extern void initialize_the_repository(void); +extern int repo_init(struct repository *r, + const char *gitdir, + const char *worktree); extern int repo_submodule_init(struct repository *submodule, struct repository *superproject, const char *path); diff --git a/revision.c b/revision.c index b42c836d7a..4e0e193e57 100644 --- a/revision.c +++ b/revision.c @@ -6,6 +6,7 @@ #include "diff.h" #include "refs.h" #include "revision.h" +#include "repository.h" #include "graph.h" #include "grep.h" #include "reflog-walk.h" @@ -440,8 +441,8 @@ static void file_change(struct diff_options *options, static int rev_compare_tree(struct rev_info *revs, struct commit *parent, struct commit *commit) { - struct tree *t1 = parent->tree; - struct tree *t2 = commit->tree; + struct tree *t1 = get_commit_tree(parent); + struct tree *t2 = get_commit_tree(commit); if (!t1) return REV_TREE_NEW; @@ -477,7 +478,7 @@ static int rev_compare_tree(struct rev_info *revs, static int rev_same_tree_as_empty(struct rev_info *revs, struct commit *commit) { int retval; - struct tree *t1 = commit->tree; + struct tree *t1 = get_commit_tree(commit); if (!t1) return 0; @@ -615,7 +616,7 @@ static void try_to_simplify_commit(struct rev_info *revs, struct commit *commit) if (!revs->prune) return; - if (!commit->tree) + if (!get_commit_tree(commit)) return; if (!commit->parents) { @@ -1285,7 +1286,7 @@ void add_reflogs_to_pending(struct rev_info *revs, unsigned flags) cb.all_revs = revs; cb.all_flags = flags; - cb.refs = get_main_ref_store(); + cb.refs = get_main_ref_store(the_repository); for_each_reflog(handle_one_reflog, &cb); if (!revs->single_worktree) @@ -2176,7 +2177,7 @@ static int handle_revision_pseudo_opt(const char *submodule, die("BUG: --single-worktree cannot be used together with submodule"); refs = get_submodule_ref_store(submodule); } else - refs = get_main_ref_store(); + refs = get_main_ref_store(the_repository); /* * NOTE! diff --git a/sequencer.c b/sequencer.c index e2f8394284..1ce63261a3 100644 --- a/sequencer.c +++ b/sequencer.c @@ -78,13 +78,6 @@ static GIT_PATH_FUNC(rebase_path_message, "rebase-merge/message") * previous commit and from the first squash/fixup commit are written * to it. The commit message for each subsequent squash/fixup commit * is appended to the file as it is processed. - * - * The first line of the file is of the form - * # This is a combination of $count commits. - * where $count is the number of commits whose messages have been - * written to the file so far (including the initial "pick" commit). - * Each time that a commit message is processed, this line is read and - * updated. It is deleted just before the combined commit is made. */ static GIT_PATH_FUNC(rebase_path_squash_msg, "rebase-merge/message-squash") /* @@ -96,6 +89,11 @@ static GIT_PATH_FUNC(rebase_path_squash_msg, "rebase-merge/message-squash") */ static GIT_PATH_FUNC(rebase_path_fixup_msg, "rebase-merge/message-fixup") /* + * This file contains the list fixup/squash commands that have been + * accumulated into message-fixup or message-squash so far. + */ +static GIT_PATH_FUNC(rebase_path_current_fixups, "rebase-merge/current-fixups") +/* * A script to set the GIT_AUTHOR_NAME, GIT_AUTHOR_EMAIL, and * GIT_AUTHOR_DATE that will be used for the commit that is currently * being rebased. @@ -279,6 +277,7 @@ int sequencer_remove_state(struct replay_opts *opts) for (i = 0; i < opts->xopts_nr; i++) free(opts->xopts[i]); free(opts->xopts); + strbuf_release(&opts->current_fixups); strbuf_reset(&buf); strbuf_addstr(&buf, get_dir(opts)); @@ -529,8 +528,8 @@ static int do_recursive_merge(struct commit *base, struct commit *next, o.show_rename_progress = 1; head_tree = parse_tree_indirect(head); - next_tree = next ? next->tree : empty_tree(); - base_tree = base ? base->tree : empty_tree(); + next_tree = next ? get_commit_tree(next) : empty_tree(); + base_tree = base ? get_commit_tree(base) : empty_tree(); for (xopt = opts->xopts; xopt != opts->xopts + opts->xopts_nr; xopt++) parse_merge_opt(&o, *xopt); @@ -591,7 +590,7 @@ static int is_index_unchanged(void) return error(_("unable to update cache tree")); return !oidcmp(&active_cache_tree->oid, - &head_commit->tree->object.oid); + get_commit_tree_oid(head_commit)); } static int write_author_script(const char *message) @@ -747,6 +746,8 @@ static int run_git_commit(const char *defmsg, struct replay_opts *opts, argv_array_pushf(&cmd.args, "-S%s", opts->gpg_sign); if (defmsg) argv_array_pushl(&cmd.args, "-F", defmsg, NULL); + else if (!(flags & EDIT_MSG)) + argv_array_pushl(&cmd.args, "-C", "HEAD", NULL); if ((flags & CLEANUP_MSG)) argv_array_push(&cmd.args, "--cleanup=strip"); if ((flags & EDIT_MSG)) @@ -1148,7 +1149,7 @@ static int try_to_commit(struct strbuf *msg, const char *author, } if (!(flags & ALLOW_EMPTY) && !oidcmp(current_head ? - ¤t_head->tree->object.oid : + get_commit_tree_oid(current_head) : &empty_tree_oid, &tree)) { res = 1; /* run 'git commit' to display error message */ goto out; @@ -1178,6 +1179,8 @@ static int try_to_commit(struct strbuf *msg, const char *author, goto out; } + reset_ident_date(); + if (commit_tree_extended(msg->buf, msg->len, &tree, parents, oid, author, opts->gpg_sign, extra)) { res = error(_("failed to write commit object")); @@ -1246,12 +1249,12 @@ static int is_original_commit_empty(struct commit *commit) if (parse_commit(parent)) return error(_("could not parse parent commit %s"), oid_to_hex(&parent->object.oid)); - ptree_oid = &parent->tree->object.oid; + ptree_oid = get_commit_tree_oid(parent); } else { ptree_oid = the_hash_algo->empty_tree; /* commit is root */ } - return !oidcmp(ptree_oid, &commit->tree->object.oid); + return !oidcmp(ptree_oid, get_commit_tree_oid(commit)); } /* @@ -1364,34 +1367,23 @@ static int update_squash_messages(enum todo_command command, struct commit *commit, struct replay_opts *opts) { struct strbuf buf = STRBUF_INIT; - int count, res; + int res; const char *message, *body; - if (file_exists(rebase_path_squash_msg())) { + if (opts->current_fixup_count > 0) { struct strbuf header = STRBUF_INIT; - char *eol, *p; + char *eol; - if (strbuf_read_file(&buf, rebase_path_squash_msg(), 2048) <= 0) + if (strbuf_read_file(&buf, rebase_path_squash_msg(), 9) <= 0) return error(_("could not read '%s'"), rebase_path_squash_msg()); - p = buf.buf + 1; - eol = strchrnul(buf.buf, '\n'); - if (buf.buf[0] != comment_line_char || - (p += strcspn(p, "0123456789\n")) == eol) - return error(_("unexpected 1st line of squash message:" - "\n\n\t%.*s"), - (int)(eol - buf.buf), buf.buf); - count = strtol(p, NULL, 10); - - if (count < 1) - return error(_("invalid 1st line of squash message:\n" - "\n\t%.*s"), - (int)(eol - buf.buf), buf.buf); + eol = buf.buf[0] != comment_line_char ? + buf.buf : strchrnul(buf.buf, '\n'); strbuf_addf(&header, "%c ", comment_line_char); - strbuf_addf(&header, - _("This is a combination of %d commits."), ++count); + strbuf_addf(&header, _("This is a combination of %d commits."), + opts->current_fixup_count + 2); strbuf_splice(&buf, 0, eol - buf.buf, header.buf, header.len); strbuf_release(&header); } else { @@ -1414,10 +1406,8 @@ static int update_squash_messages(enum todo_command command, rebase_path_fixup_msg()); } - count = 2; strbuf_addf(&buf, "%c ", comment_line_char); - strbuf_addf(&buf, _("This is a combination of %d commits."), - count); + strbuf_addf(&buf, _("This is a combination of %d commits."), 2); strbuf_addf(&buf, "\n%c ", comment_line_char); strbuf_addstr(&buf, _("This is the 1st commit message:")); strbuf_addstr(&buf, "\n\n"); @@ -1434,13 +1424,14 @@ static int update_squash_messages(enum todo_command command, if (command == TODO_SQUASH) { unlink(rebase_path_fixup_msg()); strbuf_addf(&buf, "\n%c ", comment_line_char); - strbuf_addf(&buf, _("This is the commit message #%d:"), count); + strbuf_addf(&buf, _("This is the commit message #%d:"), + ++opts->current_fixup_count); strbuf_addstr(&buf, "\n\n"); strbuf_addstr(&buf, body); } else if (command == TODO_FIXUP) { strbuf_addf(&buf, "\n%c ", comment_line_char); strbuf_addf(&buf, _("The commit message #%d will be skipped:"), - count); + ++opts->current_fixup_count); strbuf_addstr(&buf, "\n\n"); strbuf_add_commented_lines(&buf, body, strlen(body)); } else @@ -1449,6 +1440,17 @@ static int update_squash_messages(enum todo_command command, res = write_message(buf.buf, buf.len, rebase_path_squash_msg(), 0); strbuf_release(&buf); + + if (!res) { + strbuf_addf(&opts->current_fixups, "%s%s %s", + opts->current_fixups.len ? "\n" : "", + command_to_string(command), + oid_to_hex(&commit->object.oid)); + res = write_message(opts->current_fixups.buf, + opts->current_fixups.len, + rebase_path_current_fixups(), 0); + } + return res; } @@ -1711,6 +1713,9 @@ fast_forward_edit: if (!res && final_fixup) { unlink(rebase_path_fixup_msg()); unlink(rebase_path_squash_msg()); + unlink(rebase_path_current_fixups()); + strbuf_reset(&opts->current_fixups); + opts->current_fixup_count = 0; } leave: @@ -2127,6 +2132,16 @@ static int read_populate_opts(struct replay_opts *opts) read_strategy_opts(opts, &buf); strbuf_release(&buf); + if (read_oneliner(&opts->current_fixups, + rebase_path_current_fixups(), 1)) { + const char *p = opts->current_fixups.buf; + opts->current_fixup_count = 1; + while ((p = strchr(p, '\n'))) { + opts->current_fixup_count++; + p++; + } + } + return 0; } @@ -2471,10 +2486,9 @@ static int error_with_patch(struct commit *commit, static int error_failed_squash(struct commit *commit, struct replay_opts *opts, int subject_len, const char *subject) { - if (rename(rebase_path_squash_msg(), rebase_path_message())) - return error(_("could not rename '%s' to '%s'"), + if (copy_file(rebase_path_message(), rebase_path_squash_msg(), 0666)) + return error(_("could not copy '%s' to '%s'"), rebase_path_squash_msg(), rebase_path_message()); - unlink(rebase_path_fixup_msg()); unlink(git_path_merge_msg()); if (copy_file(git_path_merge_msg(), rebase_path_message(), 0666)) return error(_("could not copy '%s' to '%s'"), @@ -2566,7 +2580,7 @@ static int safe_append(const char *filename, const char *fmt, ...) static int do_label(const char *name, int len) { - struct ref_store *refs = get_main_ref_store(); + struct ref_store *refs = get_main_ref_store(the_repository); struct ref_transaction *transaction; struct strbuf ref_name = STRBUF_INIT, err = STRBUF_INIT; struct strbuf msg = STRBUF_INIT; @@ -3234,19 +3248,16 @@ static int continue_single_pick(void) return run_command_v_opt(argv, RUN_GIT_CMD); } -static int commit_staged_changes(struct replay_opts *opts) +static int commit_staged_changes(struct replay_opts *opts, + struct todo_list *todo_list) { unsigned int flags = ALLOW_EMPTY | EDIT_MSG; + unsigned int final_fixup = 0, is_clean; if (has_unstaged_changes(1)) return error(_("cannot rebase: You have unstaged changes.")); - if (!has_uncommitted_changes(0)) { - const char *cherry_pick_head = git_path_cherry_pick_head(); - if (file_exists(cherry_pick_head) && unlink(cherry_pick_head)) - return error(_("could not remove CHERRY_PICK_HEAD")); - return 0; - } + is_clean = !has_uncommitted_changes(0); if (file_exists(rebase_path_amend())) { struct strbuf rev = STRBUF_INIT; @@ -3259,19 +3270,107 @@ static int commit_staged_changes(struct replay_opts *opts) if (get_oid_hex(rev.buf, &to_amend)) return error(_("invalid contents: '%s'"), rebase_path_amend()); - if (oidcmp(&head, &to_amend)) + if (!is_clean && oidcmp(&head, &to_amend)) return error(_("\nYou have uncommitted changes in your " "working tree. Please, commit them\n" "first and then run 'git rebase " "--continue' again.")); + /* + * When skipping a failed fixup/squash, we need to edit the + * commit message, the current fixup list and count, and if it + * was the last fixup/squash in the chain, we need to clean up + * the commit message and if there was a squash, let the user + * edit it. + */ + if (is_clean && !oidcmp(&head, &to_amend) && + opts->current_fixup_count > 0 && + file_exists(rebase_path_stopped_sha())) { + const char *p = opts->current_fixups.buf; + int len = opts->current_fixups.len; + + opts->current_fixup_count--; + if (!len) + BUG("Incorrect current_fixups:\n%s", p); + while (len && p[len - 1] != '\n') + len--; + strbuf_setlen(&opts->current_fixups, len); + if (write_message(p, len, rebase_path_current_fixups(), + 0) < 0) + return error(_("could not write file: '%s'"), + rebase_path_current_fixups()); + + /* + * If a fixup/squash in a fixup/squash chain failed, the + * commit message is already correct, no need to commit + * it again. + * + * Only if it is the final command in the fixup/squash + * chain, and only if the chain is longer than a single + * fixup/squash command (which was just skipped), do we + * actually need to re-commit with a cleaned up commit + * message. + */ + if (opts->current_fixup_count > 0 && + !is_fixup(peek_command(todo_list, 0))) { + final_fixup = 1; + /* + * If there was not a single "squash" in the + * chain, we only need to clean up the commit + * message, no need to bother the user with + * opening the commit message in the editor. + */ + if (!starts_with(p, "squash ") && + !strstr(p, "\nsquash ")) + flags = (flags & ~EDIT_MSG) | CLEANUP_MSG; + } else if (is_fixup(peek_command(todo_list, 0))) { + /* + * We need to update the squash message to skip + * the latest commit message. + */ + struct commit *commit; + const char *path = rebase_path_squash_msg(); + + if (parse_head(&commit) || + !(p = get_commit_buffer(commit, NULL)) || + write_message(p, strlen(p), path, 0)) { + unuse_commit_buffer(commit, p); + return error(_("could not write file: " + "'%s'"), path); + } + unuse_commit_buffer(commit, p); + } + } strbuf_release(&rev); flags |= AMEND_MSG; } - if (run_git_commit(rebase_path_message(), opts, flags)) + if (is_clean) { + const char *cherry_pick_head = git_path_cherry_pick_head(); + + if (file_exists(cherry_pick_head) && unlink(cherry_pick_head)) + return error(_("could not remove CHERRY_PICK_HEAD")); + if (!final_fixup) + return 0; + } + + if (run_git_commit(final_fixup ? NULL : rebase_path_message(), + opts, flags)) return error(_("could not commit staged changes.")); unlink(rebase_path_amend()); + if (final_fixup) { + unlink(rebase_path_fixup_msg()); + unlink(rebase_path_squash_msg()); + } + if (opts->current_fixup_count > 0) { + /* + * Whether final fixup or not, we just cleaned up the commit + * message... + */ + unlink(rebase_path_current_fixups()); + strbuf_reset(&opts->current_fixups); + opts->current_fixup_count = 0; + } return 0; } @@ -3283,14 +3382,16 @@ int sequencer_continue(struct replay_opts *opts) if (read_and_refresh_cache(opts)) return -1; + if (read_populate_opts(opts)) + return -1; if (is_rebase_i(opts)) { - if (commit_staged_changes(opts)) + if ((res = read_populate_todo(&todo_list, opts))) + goto release_todo_list; + if (commit_staged_changes(opts, &todo_list)) return -1; } else if (!file_exists(get_todo_path(opts))) return continue_single_pick(); - if (read_populate_opts(opts)) - return -1; - if ((res = read_populate_todo(&todo_list, opts))) + else if ((res = read_populate_todo(&todo_list, opts))) goto release_todo_list; if (!is_rebase_i(opts)) { @@ -3349,7 +3450,8 @@ int sequencer_pick_revisions(struct replay_opts *opts) if (!get_oid(name, &oid)) { if (!lookup_commit_reference_gently(&oid, 1)) { - enum object_type type = oid_object_info(&oid, + enum object_type type = oid_object_info(the_repository, + &oid, NULL); return error(_("%s: can't cherry-pick a %s"), name, type_name(type)); diff --git a/sequencer.h b/sequencer.h index d9570d92b1..a800cb5755 100644 --- a/sequencer.h +++ b/sequencer.h @@ -44,10 +44,14 @@ struct replay_opts { char **xopts; size_t xopts_nr, xopts_alloc; + /* Used by fixup/squash */ + struct strbuf current_fixups; + int current_fixup_count; + /* Only used by REPLAY_NONE */ struct rev_info *revs; }; -#define REPLAY_OPTS_INIT { -1 } +#define REPLAY_OPTS_INIT { .action = -1, .current_fixups = STRBUF_INIT } /* Call this to setup defaults before parsing command line options */ void sequencer_init_config(struct replay_opts *opts); diff --git a/serve.c b/serve.c new file mode 100644 index 0000000000..bda085f09c --- /dev/null +++ b/serve.c @@ -0,0 +1,258 @@ +#include "cache.h" +#include "repository.h" +#include "config.h" +#include "pkt-line.h" +#include "version.h" +#include "argv-array.h" +#include "ls-refs.h" +#include "serve.h" +#include "upload-pack.h" + +static int always_advertise(struct repository *r, + struct strbuf *value) +{ + return 1; +} + +static int agent_advertise(struct repository *r, + struct strbuf *value) +{ + if (value) + strbuf_addstr(value, git_user_agent_sanitized()); + return 1; +} + +struct protocol_capability { + /* + * The name of the capability. The server uses this name when + * advertising this capability, and the client uses this name to + * specify this capability. + */ + const char *name; + + /* + * Function queried to see if a capability should be advertised. + * Optionally a value can be specified by adding it to 'value'. + * If a value is added to 'value', the server will advertise this + * capability as "<name>=<value>" instead of "<name>". + */ + int (*advertise)(struct repository *r, struct strbuf *value); + + /* + * Function called when a client requests the capability as a command. + * The function will be provided the capabilities requested via 'keys' + * as well as a struct packet_reader 'request' which the command should + * use to read the command specific part of the request. Every command + * MUST read until a flush packet is seen before sending a response. + * + * This field should be NULL for capabilities which are not commands. + */ + int (*command)(struct repository *r, + struct argv_array *keys, + struct packet_reader *request); +}; + +static struct protocol_capability capabilities[] = { + { "agent", agent_advertise, NULL }, + { "ls-refs", always_advertise, ls_refs }, + { "fetch", upload_pack_advertise, upload_pack_v2 }, + { "server-option", always_advertise, NULL }, +}; + +static void advertise_capabilities(void) +{ + struct strbuf capability = STRBUF_INIT; + struct strbuf value = STRBUF_INIT; + int i; + + for (i = 0; i < ARRAY_SIZE(capabilities); i++) { + struct protocol_capability *c = &capabilities[i]; + + if (c->advertise(the_repository, &value)) { + strbuf_addstr(&capability, c->name); + + if (value.len) { + strbuf_addch(&capability, '='); + strbuf_addbuf(&capability, &value); + } + + strbuf_addch(&capability, '\n'); + packet_write(1, capability.buf, capability.len); + } + + strbuf_reset(&capability); + strbuf_reset(&value); + } + + packet_flush(1); + strbuf_release(&capability); + strbuf_release(&value); +} + +static struct protocol_capability *get_capability(const char *key) +{ + int i; + + if (!key) + return NULL; + + for (i = 0; i < ARRAY_SIZE(capabilities); i++) { + struct protocol_capability *c = &capabilities[i]; + const char *out; + if (skip_prefix(key, c->name, &out) && (!*out || *out == '=')) + return c; + } + + return NULL; +} + +static int is_valid_capability(const char *key) +{ + const struct protocol_capability *c = get_capability(key); + + return c && c->advertise(the_repository, NULL); +} + +static int is_command(const char *key, struct protocol_capability **command) +{ + const char *out; + + if (skip_prefix(key, "command=", &out)) { + struct protocol_capability *cmd = get_capability(out); + + if (*command) + die("command '%s' requested after already requesting command '%s'", + out, (*command)->name); + if (!cmd || !cmd->advertise(the_repository, NULL) || !cmd->command) + die("invalid command '%s'", out); + + *command = cmd; + return 1; + } + + return 0; +} + +int has_capability(const struct argv_array *keys, const char *capability, + const char **value) +{ + int i; + for (i = 0; i < keys->argc; i++) { + const char *out; + if (skip_prefix(keys->argv[i], capability, &out) && + (!*out || *out == '=')) { + if (value) { + if (*out == '=') + out++; + *value = out; + } + return 1; + } + } + + return 0; +} + +enum request_state { + PROCESS_REQUEST_KEYS, + PROCESS_REQUEST_DONE, +}; + +static int process_request(void) +{ + enum request_state state = PROCESS_REQUEST_KEYS; + struct packet_reader reader; + struct argv_array keys = ARGV_ARRAY_INIT; + struct protocol_capability *command = NULL; + + packet_reader_init(&reader, 0, NULL, 0, + PACKET_READ_CHOMP_NEWLINE | + PACKET_READ_GENTLE_ON_EOF); + + /* + * Check to see if the client closed their end before sending another + * request. If so we can terminate the connection. + */ + if (packet_reader_peek(&reader) == PACKET_READ_EOF) + return 1; + reader.options = PACKET_READ_CHOMP_NEWLINE; + + while (state != PROCESS_REQUEST_DONE) { + switch (packet_reader_peek(&reader)) { + case PACKET_READ_EOF: + BUG("Should have already died when seeing EOF"); + case PACKET_READ_NORMAL: + /* collect request; a sequence of keys and values */ + if (is_command(reader.line, &command) || + is_valid_capability(reader.line)) + argv_array_push(&keys, reader.line); + else + die("unknown capability '%s'", reader.line); + + /* Consume the peeked line */ + packet_reader_read(&reader); + break; + case PACKET_READ_FLUSH: + /* + * If no command and no keys were given then the client + * wanted to terminate the connection. + */ + if (!keys.argc) + return 1; + + /* + * The flush packet isn't consume here like it is in + * the other parts of this switch statement. This is + * so that the command can read the flush packet and + * see the end of the request in the same way it would + * if command specific arguments were provided after a + * delim packet. + */ + state = PROCESS_REQUEST_DONE; + break; + case PACKET_READ_DELIM: + /* Consume the peeked line */ + packet_reader_read(&reader); + + state = PROCESS_REQUEST_DONE; + break; + } + } + + if (!command) + die("no command requested"); + + command->command(the_repository, &keys, &reader); + + argv_array_clear(&keys); + return 0; +} + +/* Main serve loop for protocol version 2 */ +void serve(struct serve_options *options) +{ + if (options->advertise_capabilities || !options->stateless_rpc) { + /* serve by default supports v2 */ + packet_write_fmt(1, "version 2\n"); + + advertise_capabilities(); + /* + * If only the list of capabilities was requested exit + * immediately after advertising capabilities + */ + if (options->advertise_capabilities) + return; + } + + /* + * If stateless-rpc was requested then exit after + * a single request/response exchange + */ + if (options->stateless_rpc) { + process_request(); + } else { + for (;;) + if (process_request()) + break; + } +} diff --git a/serve.h b/serve.h new file mode 100644 index 0000000000..fe65ba9f46 --- /dev/null +++ b/serve.h @@ -0,0 +1,15 @@ +#ifndef SERVE_H +#define SERVE_H + +struct argv_array; +extern int has_capability(const struct argv_array *keys, const char *capability, + const char **value); + +struct serve_options { + unsigned advertise_capabilities; + unsigned stateless_rpc; +}; +#define SERVE_OPTIONS_INIT { 0 } +extern void serve(struct serve_options *options); + +#endif /* SERVE_H */ diff --git a/sha1-file.c b/sha1-file.c index 77ccaab928..f66059ed7d 100644 --- a/sha1-file.c +++ b/sha1-file.c @@ -23,6 +23,7 @@ #include "sha1-lookup.h" #include "bulk-checkin.h" #include "repository.h" +#include "replace-object.h" #include "streaming.h" #include "dir.h" #include "list.h" @@ -141,7 +142,7 @@ static int get_conv_flags(unsigned flags) if (flags & HASH_RENORMALIZE) return CONV_EOL_RENORMALIZE; else if (flags & HASH_WRITE_OBJECT) - return global_conv_flags_eol; + return global_conv_flags_eol | CONV_WRITE_OBJECT; else return 0; } @@ -1230,7 +1231,8 @@ static int sha1_loose_object_info(struct repository *r, int fetch_if_missing = 1; -int oid_object_info_extended(const struct object_id *oid, struct object_info *oi, unsigned flags) +int oid_object_info_extended(struct repository *r, const struct object_id *oid, + struct object_info *oi, unsigned flags) { static struct object_info blank_oi = OBJECT_INFO_INIT; struct pack_entry e; @@ -1239,7 +1241,7 @@ int oid_object_info_extended(const struct object_id *oid, struct object_info *oi int already_retried = 0; if (flags & OBJECT_INFO_LOOKUP_REPLACE) - real = lookup_replace_object(oid); + real = lookup_replace_object(r, oid); if (is_null_oid(real)) return -1; @@ -1268,29 +1270,31 @@ int oid_object_info_extended(const struct object_id *oid, struct object_info *oi } while (1) { - if (find_pack_entry(the_repository, real->hash, &e)) + if (find_pack_entry(r, real->hash, &e)) break; if (flags & OBJECT_INFO_IGNORE_LOOSE) return -1; /* Most likely it's a loose object. */ - if (!sha1_loose_object_info(the_repository, real->hash, oi, flags)) + if (!sha1_loose_object_info(r, real->hash, oi, flags)) return 0; /* Not a loose object; someone else may have just packed it. */ if (!(flags & OBJECT_INFO_QUICK)) { - reprepare_packed_git(the_repository); - if (find_pack_entry(the_repository, real->hash, &e)) + reprepare_packed_git(r); + if (find_pack_entry(r, real->hash, &e)) break; } /* Check if it is a missing object */ if (fetch_if_missing && repository_format_partial_clone && - !already_retried) { + !already_retried && r == the_repository) { /* - * TODO Investigate haveing fetch_object() return + * TODO Investigate having fetch_object() return * TODO error/success and stopping the music here. + * TODO Pass a repository struct through fetch_object, + * such that arbitrary repositories work. */ fetch_object(repository_format_partial_clone, real->hash); already_retried = 1; @@ -1306,10 +1310,10 @@ int oid_object_info_extended(const struct object_id *oid, struct object_info *oi * information below, so return early. */ return 0; - rtype = packed_object_info(e.p, e.offset, oi); + rtype = packed_object_info(r, e.p, e.offset, oi); if (rtype < 0) { mark_bad_packed_object(e.p, real->hash); - return oid_object_info_extended(real, oi, 0); + return oid_object_info_extended(r, real, oi, 0); } else if (oi->whence == OI_PACKED) { oi->u.packed.offset = e.offset; oi->u.packed.pack = e.p; @@ -1321,15 +1325,17 @@ int oid_object_info_extended(const struct object_id *oid, struct object_info *oi } /* returns enum object_type or negative */ -int oid_object_info(const struct object_id *oid, unsigned long *sizep) +int oid_object_info(struct repository *r, + const struct object_id *oid, + unsigned long *sizep) { enum object_type type; struct object_info oi = OBJECT_INFO_INIT; oi.typep = &type; oi.sizep = sizep; - if (oid_object_info_extended(oid, &oi, - OBJECT_INFO_LOOKUP_REPLACE) < 0) + if (oid_object_info_extended(r, oid, &oi, + OBJECT_INFO_LOOKUP_REPLACE) < 0) return -1; return type; } @@ -1346,7 +1352,7 @@ static void *read_object(const unsigned char *sha1, enum object_type *type, hashcpy(oid.hash, sha1); - if (oid_object_info_extended(&oid, &oi, 0) < 0) + if (oid_object_info_extended(the_repository, &oid, &oi, 0) < 0) return NULL; return content; } @@ -1383,8 +1389,8 @@ void *read_object_file_extended(const struct object_id *oid, const struct packed_git *p; const char *path; struct stat st; - const struct object_id *repl = lookup_replace ? lookup_replace_object(oid) - : oid; + const struct object_id *repl = lookup_replace ? + lookup_replace_object(the_repository, oid) : oid; errno = 0; data = read_object(repl->hash, type, size); @@ -1744,7 +1750,7 @@ int has_sha1_file_with_flags(const unsigned char *sha1, int flags) if (!startup_info->have_repository) return 0; hashcpy(oid.hash, sha1); - return oid_object_info_extended(&oid, NULL, + return oid_object_info_extended(the_repository, &oid, NULL, flags | OBJECT_INFO_SKIP_CACHED) >= 0; } @@ -1987,7 +1993,7 @@ int read_pack_header(int fd, struct pack_header *header) void assert_oid_type(const struct object_id *oid, enum object_type expect) { - enum object_type type = oid_object_info(oid, NULL); + enum object_type type = oid_object_info(the_repository, oid, NULL); if (type < 0) die("%s is not a valid object", oid_to_hex(oid)); if (type != expect) diff --git a/sha1-name.c b/sha1-name.c index 5b93bf8da3..80030b159a 100644 --- a/sha1-name.c +++ b/sha1-name.c @@ -223,7 +223,7 @@ static int finish_object_disambiguation(struct disambiguate_state *ds, static int disambiguate_commit_only(const struct object_id *oid, void *cb_data_unused) { - int kind = oid_object_info(oid, NULL); + int kind = oid_object_info(the_repository, oid, NULL); return kind == OBJ_COMMIT; } @@ -232,7 +232,7 @@ static int disambiguate_committish_only(const struct object_id *oid, void *cb_da struct object *obj; int kind; - kind = oid_object_info(oid, NULL); + kind = oid_object_info(the_repository, oid, NULL); if (kind == OBJ_COMMIT) return 1; if (kind != OBJ_TAG) @@ -247,7 +247,7 @@ static int disambiguate_committish_only(const struct object_id *oid, void *cb_da static int disambiguate_tree_only(const struct object_id *oid, void *cb_data_unused) { - int kind = oid_object_info(oid, NULL); + int kind = oid_object_info(the_repository, oid, NULL); return kind == OBJ_TREE; } @@ -256,7 +256,7 @@ static int disambiguate_treeish_only(const struct object_id *oid, void *cb_data_ struct object *obj; int kind; - kind = oid_object_info(oid, NULL); + kind = oid_object_info(the_repository, oid, NULL); if (kind == OBJ_TREE || kind == OBJ_COMMIT) return 1; if (kind != OBJ_TAG) @@ -271,7 +271,7 @@ static int disambiguate_treeish_only(const struct object_id *oid, void *cb_data_ static int disambiguate_blob_only(const struct object_id *oid, void *cb_data_unused) { - int kind = oid_object_info(oid, NULL); + int kind = oid_object_info(the_repository, oid, NULL); return kind == OBJ_BLOB; } @@ -350,7 +350,7 @@ static int show_ambiguous_object(const struct object_id *oid, void *data) if (ds->fn && !ds->fn(oid, ds->cb_data)) return 0; - type = oid_object_info(oid, NULL); + type = oid_object_info(the_repository, oid, NULL); if (type == OBJ_COMMIT) { struct commit *commit = lookup_commit(oid); if (commit) { @@ -864,7 +864,7 @@ struct object *peel_to_type(const char *name, int namelen, if (o->type == OBJ_TAG) o = ((struct tag*) o)->tagged; else if (o->type == OBJ_COMMIT) - o = &(((struct commit *) o)->tree->object); + o = &(get_commit_tree(((struct commit *)o))->object); else { if (name) error("%.*s: expected %s type, but the object " diff --git a/sideband.c b/sideband.c index 6d7f943e43..325bf0e974 100644 --- a/sideband.c +++ b/sideband.c @@ -13,7 +13,7 @@ * the remote died unexpectedly. A flush() concludes the stream. */ -#define PREFIX "remote: " +#define DISPLAY_PREFIX "remote: " #define ANSI_SUFFIX "\033[K" #define DUMB_SUFFIX " " @@ -49,7 +49,7 @@ int recv_sideband(const char *me, int in_stream, int out) switch (band) { case 3: strbuf_addf(&outbuf, "%s%s%s", outbuf.len ? "\n" : "", - PREFIX, buf + 1); + DISPLAY_PREFIX, buf + 1); retval = SIDEBAND_REMOTE_ERROR; break; case 2: @@ -67,7 +67,7 @@ int recv_sideband(const char *me, int in_stream, int out) int linelen = brk - b; if (!outbuf.len) - strbuf_addstr(&outbuf, PREFIX); + strbuf_addstr(&outbuf, DISPLAY_PREFIX); if (linelen > 0) { strbuf_addf(&outbuf, "%.*s%s%c", linelen, b, suffix, *brk); @@ -81,8 +81,8 @@ int recv_sideband(const char *me, int in_stream, int out) } if (*b) - strbuf_addf(&outbuf, "%s%s", - outbuf.len ? "" : PREFIX, b); + strbuf_addf(&outbuf, "%s%s", outbuf.len ? + "" : DISPLAY_PREFIX, b); break; case 1: write_or_die(out, buf + 1, len); @@ -1,5 +1,6 @@ #include "cache.h" #include "refs.h" +#include "string-list.h" #include "utf8.h" int starts_with(const char *str, const char *prefix) @@ -11,6 +12,15 @@ int starts_with(const char *str, const char *prefix) return 0; } +int istarts_with(const char *str, const char *prefix) +{ + for (; ; str++, prefix++) + if (!*prefix) + return 1; + else if (tolower(*str) != tolower(*prefix)) + return 0; +} + int skip_to_optional_arg_default(const char *str, const char *prefix, const char **arg, const char *def) { @@ -171,6 +181,21 @@ struct strbuf **strbuf_split_buf(const char *str, size_t slen, return ret; } +void strbuf_add_separated_string_list(struct strbuf *str, + const char *sep, + struct string_list *slist) +{ + struct string_list_item *item; + int sep_needed = 0; + + for_each_string_list_item(item, slist) { + if (sep_needed) + strbuf_addstr(str, sep); + strbuf_addstr(str, item->string); + sep_needed = 1; + } +} + void strbuf_list_free(struct strbuf **sbs) { struct strbuf **s = sbs; @@ -793,7 +818,18 @@ char *xstrdup_tolower(const char *string) result = xmallocz(len); for (i = 0; i < len; i++) result[i] = tolower(string[i]); - result[i] = '\0'; + return result; +} + +char *xstrdup_toupper(const char *string) +{ + char *result; + size_t len, i; + + len = strlen(string); + result = xmallocz(len); + for (i = 0; i < len; i++) + result[i] = toupper(string[i]); return result; } @@ -1,6 +1,8 @@ #ifndef STRBUF_H #define STRBUF_H +struct string_list; + /** * strbuf's are meant to be used with all the usual C string and memory * APIs. Given that the length of the buffer is known, it's often better to @@ -537,6 +539,20 @@ static inline struct strbuf **strbuf_split(const struct strbuf *sb, return strbuf_split_max(sb, terminator, 0); } +/* + * Adds all strings of a string list to the strbuf, separated by the given + * separator. For example, if sep is + * ', ' + * and slist contains + * ['element1', 'element2', ..., 'elementN'], + * then write: + * 'element1, element2, ..., elementN' + * to str. If only one element, just write "element1" to str. + */ +extern void strbuf_add_separated_string_list(struct strbuf *str, + const char *sep, + struct string_list *slist); + /** * Free a NULL-terminated list of strbufs (for example, the return * values of the strbuf_split*() functions). @@ -616,6 +632,7 @@ __attribute__((format (printf,2,3))) extern int fprintf_ln(FILE *fp, const char *fmt, ...); char *xstrdup_tolower(const char *); +char *xstrdup_toupper(const char *); /** * Create a newly allocated string using printf format. You can do this easily diff --git a/streaming.c b/streaming.c index 7d55ba64c7..d1e6b2dce6 100644 --- a/streaming.c +++ b/streaming.c @@ -5,6 +5,7 @@ #include "streaming.h" #include "repository.h" #include "object-store.h" +#include "replace-object.h" #include "packfile.h" enum input_source { @@ -116,7 +117,7 @@ static enum input_source istream_source(const struct object_id *oid, oi->typep = type; oi->sizep = &size; - status = oid_object_info_extended(oid, oi, 0); + status = oid_object_info_extended(the_repository, oid, oi, 0); if (status < 0) return stream_error; @@ -139,7 +140,7 @@ struct git_istream *open_istream(const struct object_id *oid, { struct git_istream *st; struct object_info oi = OBJECT_INFO_INIT; - const struct object_id *real = lookup_replace_object(oid); + const struct object_id *real = lookup_replace_object(the_repository, oid); enum input_source src = istream_source(real, type, &oi); if (src < 0) diff --git a/submodule-config.c b/submodule-config.c index 3f2075764f..d87c3ff63a 100644 --- a/submodule-config.c +++ b/submodule-config.c @@ -619,31 +619,24 @@ static void gitmodules_read_check(struct repository *repo) repo_read_gitmodules(repo); } -const struct submodule *submodule_from_name(const struct object_id *treeish_name, +const struct submodule *submodule_from_name(struct repository *r, + const struct object_id *treeish_name, const char *name) { - gitmodules_read_check(the_repository); - return config_from(the_repository->submodule_cache, treeish_name, name, lookup_name); + gitmodules_read_check(r); + return config_from(r->submodule_cache, treeish_name, name, lookup_name); } -const struct submodule *submodule_from_path(const struct object_id *treeish_name, +const struct submodule *submodule_from_path(struct repository *r, + const struct object_id *treeish_name, const char *path) { - gitmodules_read_check(the_repository); - return config_from(the_repository->submodule_cache, treeish_name, path, lookup_path); + gitmodules_read_check(r); + return config_from(r->submodule_cache, treeish_name, path, lookup_path); } -const struct submodule *submodule_from_cache(struct repository *repo, - const struct object_id *treeish_name, - const char *key) +void submodule_free(struct repository *r) { - gitmodules_read_check(repo); - return config_from(repo->submodule_cache, treeish_name, - key, lookup_path); -} - -void submodule_free(void) -{ - if (the_repository->submodule_cache) - submodule_cache_clear(the_repository->submodule_cache); + if (r->submodule_cache) + submodule_cache_clear(r->submodule_cache); } diff --git a/submodule-config.h b/submodule-config.h index a5503a5d17..6f686184e8 100644 --- a/submodule-config.h +++ b/submodule-config.h @@ -39,13 +39,12 @@ extern int parse_update_recurse_submodules_arg(const char *opt, const char *arg) extern int parse_push_recurse_submodules_arg(const char *opt, const char *arg); extern void repo_read_gitmodules(struct repository *repo); extern void gitmodules_config_oid(const struct object_id *commit_oid); -extern const struct submodule *submodule_from_name( - const struct object_id *commit_or_tree, const char *name); -extern const struct submodule *submodule_from_path( - const struct object_id *commit_or_tree, const char *path); -extern const struct submodule *submodule_from_cache(struct repository *repo, - const struct object_id *treeish_name, - const char *key); -extern void submodule_free(void); +const struct submodule *submodule_from_name(struct repository *r, + const struct object_id *commit_or_tree, + const char *name); +const struct submodule *submodule_from_path(struct repository *r, + const struct object_id *commit_or_tree, + const char *path); +void submodule_free(struct repository *r); #endif /* SUBMODULE_CONFIG_H */ diff --git a/submodule.c b/submodule.c index 9a50168b23..8fd8e5d178 100644 --- a/submodule.c +++ b/submodule.c @@ -96,7 +96,7 @@ int update_path_in_gitmodules(const char *oldpath, const char *newpath) if (is_gitmodules_unmerged(&the_index)) die(_("Cannot change unmerged .gitmodules, resolve merge conflicts first")); - submodule = submodule_from_path(&null_oid, oldpath); + submodule = submodule_from_path(the_repository, &null_oid, oldpath); if (!submodule || !submodule->name) { warning(_("Could not find section in .gitmodules where path=%s"), oldpath); return -1; @@ -130,7 +130,7 @@ int remove_path_from_gitmodules(const char *path) if (is_gitmodules_unmerged(&the_index)) die(_("Cannot change unmerged .gitmodules, resolve merge conflicts first")); - submodule = submodule_from_path(&null_oid, path); + submodule = submodule_from_path(the_repository, &null_oid, path); if (!submodule || !submodule->name) { warning(_("Could not find section in .gitmodules where path=%s"), path); return -1; @@ -174,7 +174,8 @@ done: void set_diffopt_flags_from_submodule_config(struct diff_options *diffopt, const char *path) { - const struct submodule *submodule = submodule_from_path(&null_oid, path); + const struct submodule *submodule = submodule_from_path(the_repository, + &null_oid, path); if (submodule) { const char *ignore; char *key; @@ -230,7 +231,7 @@ int is_submodule_active(struct repository *repo, const char *path) const struct string_list *sl; const struct submodule *module; - module = submodule_from_cache(repo, &null_oid, path); + module = submodule_from_path(repo, &null_oid, path); /* early return if there isn't a path->module mapping */ if (!module) @@ -674,7 +675,7 @@ const struct submodule *submodule_from_ce(const struct cache_entry *ce) if (!should_update_submodules()) return NULL; - return submodule_from_path(&null_oid, ce->name); + return submodule_from_path(the_repository, &null_oid, ce->name); } static struct oid_array *submodule_commits(struct string_list *submodules, @@ -731,13 +732,14 @@ static void collect_changed_submodules_cb(struct diff_queue_struct *q, if (!S_ISGITLINK(p->two->mode)) continue; - submodule = submodule_from_path(commit_oid, p->two->path); + submodule = submodule_from_path(the_repository, + commit_oid, p->two->path); if (submodule) name = submodule->name; else { name = default_name_or_path(p->two->path); /* make sure name does not collide with existing one */ - submodule = submodule_from_name(commit_oid, name); + submodule = submodule_from_name(the_repository, commit_oid, name); if (submodule) { warning("Submodule in commit %s at path: " "'%s' collides with a submodule named " @@ -818,7 +820,7 @@ static int check_has_commit(const struct object_id *oid, void *data) { struct has_commit_data *cb = data; - enum object_type type = oid_object_info(oid, NULL); + enum object_type type = oid_object_info(the_repository, oid, NULL); switch (type) { case OBJ_COMMIT: @@ -945,7 +947,7 @@ int find_unpushed_submodules(struct oid_array *commits, const struct submodule *submodule; const char *path = NULL; - submodule = submodule_from_name(&null_oid, name->string); + submodule = submodule_from_name(the_repository, &null_oid, name->string); if (submodule) path = submodule->path; else @@ -1113,7 +1115,7 @@ static void calculate_changed_submodule_paths(void) const struct string_list_item *name; /* No need to check if there are no submodules configured */ - if (!submodule_from_path(NULL, NULL)) + if (!submodule_from_path(the_repository, NULL, NULL)) return; argv_array_push(&argv, "--"); /* argv[0] program name */ @@ -1134,7 +1136,7 @@ static void calculate_changed_submodule_paths(void) const struct submodule *submodule; const char *path = NULL; - submodule = submodule_from_name(&null_oid, name->string); + submodule = submodule_from_name(the_repository, &null_oid, name->string); if (submodule) path = submodule->path; else @@ -1162,7 +1164,7 @@ int submodule_touches_in_range(struct object_id *excl_oid, int ret; /* No need to check if there are no submodules configured */ - if (!submodule_from_path(NULL, NULL)) + if (!submodule_from_path(the_repository, NULL, NULL)) return 0; argv_array_push(&args, "--"); /* args[0] program name */ @@ -1234,7 +1236,7 @@ static int get_next_submodule(struct child_process *cp, if (!S_ISGITLINK(ce->ce_mode)) continue; - submodule = submodule_from_cache(spf->r, &null_oid, ce->name); + submodule = submodule_from_path(spf->r, &null_oid, ce->name); if (!submodule) { const char *name = default_name_or_path(ce->name); if (name) { @@ -1604,7 +1606,7 @@ int submodule_move_head(const char *path, if (old_head && !is_submodule_populated_gently(path, error_code_ptr)) return 0; - sub = submodule_from_path(&null_oid, path); + sub = submodule_from_path(the_repository, &null_oid, path); if (!sub) die("BUG: could not get submodule information for '%s'", path); @@ -1623,7 +1625,7 @@ int submodule_move_head(const char *path, } else { char *gitdir = xstrfmt("%s/modules/%s", get_git_common_dir(), sub->name); - connect_work_tree_and_git_dir(path, gitdir); + connect_work_tree_and_git_dir(path, gitdir, 0); free(gitdir); /* make sure the index is clean as well */ @@ -1633,7 +1635,7 @@ int submodule_move_head(const char *path, if (old_head && (flags & SUBMODULE_MOVE_HEAD_FORCE)) { char *gitdir = xstrfmt("%s/modules/%s", get_git_common_dir(), sub->name); - connect_work_tree_and_git_dir(path, gitdir); + connect_work_tree_and_git_dir(path, gitdir, 1); free(gitdir); } } @@ -1886,7 +1888,7 @@ static void relocate_single_git_dir_into_superproject(const char *prefix, real_old_git_dir = real_pathdup(old_git_dir, 1); - sub = submodule_from_path(&null_oid, path); + sub = submodule_from_path(the_repository, &null_oid, path); if (!sub) die(_("could not lookup name for submodule '%s'"), path); @@ -1942,11 +1944,11 @@ void absorb_git_dir_into_superproject(const char *prefix, * superproject did not rewrite the git file links yet, * fix it now. */ - sub = submodule_from_path(&null_oid, path); + sub = submodule_from_path(the_repository, &null_oid, path); if (!sub) die(_("could not lookup name for submodule '%s'"), path); connect_work_tree_and_git_dir(path, - git_path("modules/%s", sub->name)); + git_path("modules/%s", sub->name), 0); } else { /* Is it already absorbed into the superprojects git dir? */ char *real_sub_git_dir = real_pathdup(sub_git_dir, 1); @@ -2088,7 +2090,7 @@ int submodule_to_gitdir(struct strbuf *buf, const char *submodule) strbuf_addstr(buf, git_dir); } if (!is_git_directory(buf->buf)) { - sub = submodule_from_path(&null_oid, submodule); + sub = submodule_from_path(the_repository, &null_oid, submodule); if (!sub) { ret = -1; goto cleanup; diff --git a/submodule.h b/submodule.h index 9589f13127..e5526f6aaa 100644 --- a/submodule.h +++ b/submodule.h @@ -105,7 +105,6 @@ extern int push_unpushed_submodules(struct oid_array *commits, const char **refspec, int refspec_nr, const struct string_list *push_options, int dry_run); -extern void connect_work_tree_and_git_dir(const char *work_tree, const char *git_dir); /* * Given a submodule path (as in the index), return the repository * path of that submodule in 'buf'. Return -1 on error or when the @@ -293,6 +293,28 @@ and know what setup is needed for it. Or when you want to run everything up to a certain test. +Running tests with special setups +--------------------------------- + +The whole test suite could be run to test some special features +that cannot be easily covered by a few specific test cases. These +could be enabled by running the test suite with correct GIT_TEST_ +environment set. + +GIT_TEST_SPLIT_INDEX=<boolean> forces split-index mode on the whole +test suite. Accept any boolean values that are accepted by git-config. + +GIT_TEST_FULL_IN_PACK_ARRAY=<boolean> exercises the uncommon +pack-objects code path where there are more than 1024 packs even if +the actual number of packs in repository is below this limit. Accept +any boolean values that are accepted by git-config. + +GIT_TEST_OE_SIZE=<n> exercises the uncommon pack-objects code path +where we do not cache object size in memory and read it from existing +packs on demand. This normally only happens when the object size is +over 2GB. This variable forces the code path on any object larger than +<n> bytes. + Naming Tests ------------ diff --git a/t/helper/test-pkt-line.c b/t/helper/test-pkt-line.c new file mode 100644 index 0000000000..0f19e53c75 --- /dev/null +++ b/t/helper/test-pkt-line.c @@ -0,0 +1,64 @@ +#include "pkt-line.h" + +static void pack_line(const char *line) +{ + if (!strcmp(line, "0000") || !strcmp(line, "0000\n")) + packet_flush(1); + else if (!strcmp(line, "0001") || !strcmp(line, "0001\n")) + packet_delim(1); + else + packet_write_fmt(1, "%s", line); +} + +static void pack(int argc, const char **argv) +{ + if (argc) { /* read from argv */ + int i; + for (i = 0; i < argc; i++) + pack_line(argv[i]); + } else { /* read from stdin */ + char line[LARGE_PACKET_MAX]; + while (fgets(line, sizeof(line), stdin)) { + pack_line(line); + } + } +} + +static void unpack(void) +{ + struct packet_reader reader; + packet_reader_init(&reader, 0, NULL, 0, + PACKET_READ_GENTLE_ON_EOF | + PACKET_READ_CHOMP_NEWLINE); + + while (packet_reader_read(&reader) != PACKET_READ_EOF) { + switch (reader.status) { + case PACKET_READ_EOF: + break; + case PACKET_READ_NORMAL: + printf("%s\n", reader.line); + break; + case PACKET_READ_FLUSH: + printf("0000\n"); + break; + case PACKET_READ_DELIM: + printf("0001\n"); + break; + } + } +} + +int cmd_main(int argc, const char **argv) +{ + if (argc < 2) + die("too few arguments"); + + if (!strcmp(argv[1], "pack")) + pack(argc - 2, argv + 2); + else if (!strcmp(argv[1], "unpack")) + unpack(); + else + die("invalid argument '%s'", argv[1]); + + return 0; +} diff --git a/t/helper/test-ref-store.c b/t/helper/test-ref-store.c index 7c4f43746e..e9e0541276 100644 --- a/t/helper/test-ref-store.c +++ b/t/helper/test-ref-store.c @@ -3,6 +3,7 @@ #include "refs.h" #include "worktree.h" #include "object-store.h" +#include "repository.h" static const char *notnull(const char *arg, const char *name) { @@ -23,7 +24,7 @@ static const char **get_store(const char **argv, struct ref_store **refs) if (!argv[0]) { die("ref store required"); } else if (!strcmp(argv[0], "main")) { - *refs = get_main_ref_store(); + *refs = get_main_ref_store(the_repository); } else if (skip_prefix(argv[0], "submodule:", &gitdir)) { struct strbuf sb = STRBUF_INIT; int ret; diff --git a/t/helper/test-submodule-config.c b/t/helper/test-submodule-config.c index 5c6e4b010d..e2692746df 100644 --- a/t/helper/test-submodule-config.c +++ b/t/helper/test-submodule-config.c @@ -49,9 +49,11 @@ int cmd__submodule_config(int argc, const char **argv) die_usage(argc, argv, "Commit not found."); if (lookup_name) { - submodule = submodule_from_name(&commit_oid, path_or_name); + submodule = submodule_from_name(the_repository, + &commit_oid, path_or_name); } else - submodule = submodule_from_path(&commit_oid, path_or_name); + submodule = submodule_from_path(the_repository, + &commit_oid, path_or_name); if (!submodule) die_usage(argc, argv, "Submodule not found."); @@ -65,7 +67,7 @@ int cmd__submodule_config(int argc, const char **argv) arg += 2; } - submodule_free(); + submodule_free(the_repository); return 0; } diff --git a/t/perf/aggregate.perl b/t/perf/aggregate.perl index 48637ef64b..bc865160e7 100755 --- a/t/perf/aggregate.perl +++ b/t/perf/aggregate.perl @@ -4,6 +4,7 @@ use lib '../../perl/build/lib'; use strict; use warnings; use JSON; +use Getopt::Long; use Git; sub get_times { @@ -36,46 +37,34 @@ sub format_times { return $out; } +sub usage { + print <<EOT; +./aggregate.perl [options] [--] [<dir_or_rev>...] [--] [<test_script>...] > + + Options: + --codespeed * Format output for Codespeed + --reponame <str> * Send given reponame to codespeed + --sort-by <str> * Sort output (only "regression" criteria is supported) + --subsection <str> * Use results from given subsection + +EOT + exit(1); +} + my (@dirs, %dirnames, %dirabbrevs, %prefixes, @tests, $codespeed, $sortby, $subsection, $reponame); + +Getopt::Long::Configure qw/ require_order /; + +my $rc = GetOptions("codespeed" => \$codespeed, + "reponame=s" => \$reponame, + "sort-by=s" => \$sortby, + "subsection=s" => \$subsection); +usage() unless $rc; + while (scalar @ARGV) { my $arg = $ARGV[0]; my $dir; - if ($arg eq "--codespeed") { - $codespeed = 1; - shift @ARGV; - next; - } - if ($arg =~ /--sort-by(?:=(.*))?/) { - shift @ARGV; - if (defined $1) { - $sortby = $1; - } else { - $sortby = shift @ARGV; - if (! defined $sortby) { - die "'--sort-by' requires an argument"; - } - } - next; - } - if ($arg eq "--subsection") { - shift @ARGV; - $subsection = $ARGV[0]; - shift @ARGV; - if (! $subsection) { - die "empty subsection"; - } - next; - } - if ($arg eq "--reponame") { - shift @ARGV; - $reponame = $ARGV[0]; - shift @ARGV; - if (! $reponame) { - die "empty reponame"; - } - next; - } last if -f $arg or $arg eq "--"; if (! -d $arg) { my $rev = Git::command_oneline(qw(rev-parse --verify), $arg); @@ -225,7 +214,8 @@ sub print_sorted_results { my ($sortby) = @_; if ($sortby ne "regression") { - die "only 'regression' is supported as '--sort-by' argument"; + print "Only 'regression' is supported as '--sort-by' argument\n"; + usage(); } my @evolutions; diff --git a/t/t0028-working-tree-encoding.sh b/t/t0028-working-tree-encoding.sh new file mode 100755 index 0000000000..12b8eb963a --- /dev/null +++ b/t/t0028-working-tree-encoding.sh @@ -0,0 +1,245 @@ +#!/bin/sh + +test_description='working-tree-encoding conversion via gitattributes' + +. ./test-lib.sh + +GIT_TRACE_WORKING_TREE_ENCODING=1 && export GIT_TRACE_WORKING_TREE_ENCODING + +test_expect_success 'setup test files' ' + git config core.eol lf && + + text="hallo there!\ncan you read me?" && + echo "*.utf16 text working-tree-encoding=utf-16" >.gitattributes && + printf "$text" >test.utf8.raw && + printf "$text" | iconv -f UTF-8 -t UTF-16 >test.utf16.raw && + printf "$text" | iconv -f UTF-8 -t UTF-32 >test.utf32.raw && + + # Line ending tests + printf "one\ntwo\nthree\n" >lf.utf8.raw && + printf "one\r\ntwo\r\nthree\r\n" >crlf.utf8.raw && + + # BOM tests + printf "\0a\0b\0c" >nobom.utf16be.raw && + printf "a\0b\0c\0" >nobom.utf16le.raw && + printf "\376\777\0a\0b\0c" >bebom.utf16be.raw && + printf "\777\376a\0b\0c\0" >lebom.utf16le.raw && + printf "\0\0\0a\0\0\0b\0\0\0c" >nobom.utf32be.raw && + printf "a\0\0\0b\0\0\0c\0\0\0" >nobom.utf32le.raw && + printf "\0\0\376\777\0\0\0a\0\0\0b\0\0\0c" >bebom.utf32be.raw && + printf "\777\376\0\0a\0\0\0b\0\0\0c\0\0\0" >lebom.utf32le.raw && + + # Add only UTF-16 file, we will add the UTF-32 file later + cp test.utf16.raw test.utf16 && + cp test.utf32.raw test.utf32 && + git add .gitattributes test.utf16 && + git commit -m initial +' + +test_expect_success 'ensure UTF-8 is stored in Git' ' + test_when_finished "rm -f test.utf16.git" && + + git cat-file -p :test.utf16 >test.utf16.git && + test_cmp_bin test.utf8.raw test.utf16.git +' + +test_expect_success 're-encode to UTF-16 on checkout' ' + test_when_finished "rm -f test.utf16.raw" && + + rm test.utf16 && + git checkout test.utf16 && + test_cmp_bin test.utf16.raw test.utf16 +' + +test_expect_success 'check $GIT_DIR/info/attributes support' ' + test_when_finished "rm -f test.utf32.git" && + test_when_finished "git reset --hard HEAD" && + + echo "*.utf32 text working-tree-encoding=utf-32" >.git/info/attributes && + git add test.utf32 && + + git cat-file -p :test.utf32 >test.utf32.git && + test_cmp_bin test.utf8.raw test.utf32.git +' + +for i in 16 32 +do + test_expect_success "check prohibited UTF-${i} BOM" ' + test_when_finished "git reset --hard HEAD" && + + echo "*.utf${i}be text working-tree-encoding=utf-${i}be" >>.gitattributes && + echo "*.utf${i}le text working-tree-encoding=utf-${i}LE" >>.gitattributes && + + # Here we add a UTF-16 (resp. UTF-32) files with BOM (big/little-endian) + # but we tell Git to treat it as UTF-16BE/UTF-16LE (resp. UTF-32). + # In these cases the BOM is prohibited. + cp bebom.utf${i}be.raw bebom.utf${i}be && + test_must_fail git add bebom.utf${i}be 2>err.out && + test_i18ngrep "fatal: BOM is prohibited .* utf-${i}be" err.out && + test_i18ngrep "use UTF-${i} as working-tree-encoding" err.out && + + cp lebom.utf${i}le.raw lebom.utf${i}be && + test_must_fail git add lebom.utf${i}be 2>err.out && + test_i18ngrep "fatal: BOM is prohibited .* utf-${i}be" err.out && + test_i18ngrep "use UTF-${i} as working-tree-encoding" err.out && + + cp bebom.utf${i}be.raw bebom.utf${i}le && + test_must_fail git add bebom.utf${i}le 2>err.out && + test_i18ngrep "fatal: BOM is prohibited .* utf-${i}LE" err.out && + test_i18ngrep "use UTF-${i} as working-tree-encoding" err.out && + + cp lebom.utf${i}le.raw lebom.utf${i}le && + test_must_fail git add lebom.utf${i}le 2>err.out && + test_i18ngrep "fatal: BOM is prohibited .* utf-${i}LE" err.out && + test_i18ngrep "use UTF-${i} as working-tree-encoding" err.out + ' + + test_expect_success "check required UTF-${i} BOM" ' + test_when_finished "git reset --hard HEAD" && + + echo "*.utf${i} text working-tree-encoding=utf-${i}" >>.gitattributes && + + cp nobom.utf${i}be.raw nobom.utf${i} && + test_must_fail git add nobom.utf${i} 2>err.out && + test_i18ngrep "fatal: BOM is required .* utf-${i}" err.out && + test_i18ngrep "use UTF-${i}BE or UTF-${i}LE" err.out && + + cp nobom.utf${i}le.raw nobom.utf${i} && + test_must_fail git add nobom.utf${i} 2>err.out && + test_i18ngrep "fatal: BOM is required .* utf-${i}" err.out && + test_i18ngrep "use UTF-${i}BE or UTF-${i}LE" err.out + ' + + test_expect_success "eol conversion for UTF-${i} encoded files on checkout" ' + test_when_finished "rm -f crlf.utf${i}.raw lf.utf${i}.raw" && + test_when_finished "git reset --hard HEAD^" && + + cat lf.utf8.raw | iconv -f UTF-8 -t UTF-${i} >lf.utf${i}.raw && + cat crlf.utf8.raw | iconv -f UTF-8 -t UTF-${i} >crlf.utf${i}.raw && + cp crlf.utf${i}.raw eol.utf${i} && + + cat >expectIndexLF <<-EOF && + i/lf w/-text attr/text eol.utf${i} + EOF + + git add eol.utf${i} && + git commit -m eol && + + # UTF-${i} with CRLF (Windows line endings) + rm eol.utf${i} && + git -c core.eol=crlf checkout eol.utf${i} && + test_cmp_bin crlf.utf${i}.raw eol.utf${i} && + + # Although the file has CRLF in the working tree, + # ensure LF in the index + git ls-files --eol eol.utf${i} >actual && + test_cmp expectIndexLF actual && + + # UTF-${i} with LF (Unix line endings) + rm eol.utf${i} && + git -c core.eol=lf checkout eol.utf${i} && + test_cmp_bin lf.utf${i}.raw eol.utf${i} && + + # The file LF in the working tree, ensure LF in the index + git ls-files --eol eol.utf${i} >actual && + test_cmp expectIndexLF actual + ' +done + +test_expect_success 'check unsupported encodings' ' + test_when_finished "git reset --hard HEAD" && + + echo "*.set text working-tree-encoding" >.gitattributes && + printf "set" >t.set && + test_must_fail git add t.set 2>err.out && + test_i18ngrep "true/false are no valid working-tree-encodings" err.out && + + echo "*.unset text -working-tree-encoding" >.gitattributes && + printf "unset" >t.unset && + git add t.unset && + + echo "*.empty text working-tree-encoding=" >.gitattributes && + printf "empty" >t.empty && + git add t.empty && + + echo "*.garbage text working-tree-encoding=garbage" >.gitattributes && + printf "garbage" >t.garbage && + test_must_fail git add t.garbage 2>err.out && + test_i18ngrep "failed to encode" err.out +' + +test_expect_success 'error if encoding round trip is not the same during refresh' ' + BEFORE_STATE=$(git rev-parse HEAD) && + test_when_finished "git reset --hard $BEFORE_STATE" && + + # Add and commit a UTF-16 file but skip the "working-tree-encoding" + # filter. Consequently, the in-repo representation is UTF-16 and not + # UTF-8. This simulates a Git version that has no working tree encoding + # support. + echo "*.utf16le text working-tree-encoding=utf-16le" >.gitattributes && + echo "hallo" >nonsense.utf16le && + TEST_HASH=$(git hash-object --no-filters -w nonsense.utf16le) && + git update-index --add --cacheinfo 100644 $TEST_HASH nonsense.utf16le && + COMMIT=$(git commit-tree -p $(git rev-parse HEAD) -m "plain commit" $(git write-tree)) && + git update-ref refs/heads/master $COMMIT && + + test_must_fail git checkout HEAD^ 2>err.out && + test_i18ngrep "error: .* overwritten by checkout:" err.out +' + +test_expect_success 'error if encoding garbage is already in Git' ' + BEFORE_STATE=$(git rev-parse HEAD) && + test_when_finished "git reset --hard $BEFORE_STATE" && + + # Skip the UTF-16 filter for the added file + # This simulates a Git version that has no checkoutEncoding support + cp nobom.utf16be.raw nonsense.utf16 && + TEST_HASH=$(git hash-object --no-filters -w nonsense.utf16) && + git update-index --add --cacheinfo 100644 $TEST_HASH nonsense.utf16 && + COMMIT=$(git commit-tree -p $(git rev-parse HEAD) -m "plain commit" $(git write-tree)) && + git update-ref refs/heads/master $COMMIT && + + git diff 2>err.out && + test_i18ngrep "error: BOM is required" err.out +' + +test_expect_success 'check roundtrip encoding' ' + test_when_finished "rm -f roundtrip.shift roundtrip.utf16" && + test_when_finished "git reset --hard HEAD" && + + text="hallo there!\nroundtrip test here!" && + printf "$text" | iconv -f UTF-8 -t SHIFT-JIS >roundtrip.shift && + printf "$text" | iconv -f UTF-8 -t UTF-16 >roundtrip.utf16 && + echo "*.shift text working-tree-encoding=SHIFT-JIS" >>.gitattributes && + + # SHIFT-JIS encoded files are round-trip checked by default... + GIT_TRACE=1 git add .gitattributes roundtrip.shift 2>&1 | + grep "Checking roundtrip encoding for SHIFT-JIS" && + git reset && + + # ... unless we overwrite the Git config! + ! GIT_TRACE=1 git -c core.checkRoundtripEncoding=garbage \ + add .gitattributes roundtrip.shift 2>&1 | + grep "Checking roundtrip encoding for SHIFT-JIS" && + git reset && + + # UTF-16 encoded files should not be round-trip checked by default... + ! GIT_TRACE=1 git add roundtrip.utf16 2>&1 | + grep "Checking roundtrip encoding for UTF-16" && + git reset && + + # ... unless we tell Git to check it! + GIT_TRACE=1 git -c core.checkRoundtripEncoding="UTF-16, UTF-32" \ + add roundtrip.utf16 2>&1 | + grep "Checking roundtrip encoding for utf-16" && + git reset && + + # ... unless we tell Git to check it! + # (here we also check that the casing of the encoding is irrelevant) + GIT_TRACE=1 git -c core.checkRoundtripEncoding="UTF-32, utf-16" \ + add roundtrip.utf16 2>&1 | + grep "Checking roundtrip encoding for utf-16" && + git reset +' + +test_done diff --git a/t/t0061-run-command.sh b/t/t0061-run-command.sh index d03149be9f..c887ed5b45 100755 --- a/t/t0061-run-command.sh +++ b/t/t0061-run-command.sh @@ -145,7 +145,7 @@ test_trace () { expect="$1" shift GIT_TRACE=1 test-tool run-command "$@" run-command true 2>&1 >/dev/null | \ - sed 's/.* run_command: //' >actual && + sed -e 's/.* run_command: //' -e '/trace: .*/d' >actual && echo "$expect true" >expect && test_cmp expect actual } diff --git a/t/t1300-repo-config.sh b/t/t1300-config.sh index e95b1e67da..03c223708e 100755 --- a/t/t1300-repo-config.sh +++ b/t/t1300-config.sh @@ -108,6 +108,7 @@ bar = foo [beta] baz = multiple \ lines +foo = bar EOF test_expect_success 'unset with cont. lines' ' @@ -118,6 +119,7 @@ cat > expect <<\EOF [alpha] bar = foo [beta] +foo = bar EOF test_expect_success 'unset with cont. lines is correct' 'test_cmp expect .git/config' @@ -740,7 +742,7 @@ test_expect_success bool ' do git config --bool --get bool.true$i >>result git config --bool --get bool.false$i >>result - done && + done && test_cmp expect result' test_expect_success 'invalid bool (--get)' ' @@ -931,6 +933,36 @@ test_expect_success 'get --expiry-date' ' test_must_fail git config --expiry-date date.invalid1 ' +test_expect_success 'get --type=color' ' + rm .git/config && + git config foo.color "red" && + git config --get --type=color foo.color >actual.raw && + test_decode_color <actual.raw >actual && + echo "<RED>" >expect && + test_cmp expect actual +' + +cat >expect << EOF +[foo] + color = red +EOF + +test_expect_success 'set --type=color' ' + rm .git/config && + git config --type=color foo.color "red" && + test_cmp expect .git/config +' + +test_expect_success 'get --type=color barfs on non-color' ' + echo "[foo]bar=not-a-color" >.git/config && + test_must_fail git config --get --type=color foo.bar +' + +test_expect_success 'set --type=color barfs on non-color' ' + test_must_fail git config --type=color foo.color "not-a-color" 2>error && + test_i18ngrep "cannot parse color" error +' + cat > expect << EOF [quote] leading = " test" @@ -1411,7 +1443,7 @@ test_expect_success 'urlmatch with wildcard' ' ' # good section hygiene -test_expect_failure 'unsetting the last key in a section removes header' ' +test_expect_success '--unset last key removes section (except if commented)' ' cat >.git/config <<-\EOF && # some generic comment on the configuration file itself # a comment specific to this "section" section. @@ -1425,13 +1457,86 @@ test_expect_failure 'unsetting the last key in a section removes header' ' cat >expect <<-\EOF && # some generic comment on the configuration file itself + # a comment specific to this "section" section. + [section] + # some intervening lines + # that should also be dropped + + # please be careful when you update the above variable EOF git config --unset section.key && - test_cmp expect .git/config + test_cmp expect .git/config && + + cat >.git/config <<-\EOF && + [section] + key = value + [next-section] + EOF + + cat >expect <<-\EOF && + [next-section] + EOF + + git config --unset section.key && + test_cmp expect .git/config && + + q_to_tab >.git/config <<-\EOF && + [one] + Qkey = "multiline \ + QQ# with comment" + [two] + key = true + EOF + git config --unset two.key && + ! grep two .git/config && + + q_to_tab >.git/config <<-\EOF && + [one] + Qkey = "multiline \ + QQ# with comment" + [one] + key = true + EOF + git config --unset-all one.key && + test_line_count = 0 .git/config && + + q_to_tab >.git/config <<-\EOF && + [one] + Qkey = true + Q# a comment not at the start + [two] + Qkey = true + EOF + git config --unset two.key && + grep two .git/config && + + q_to_tab >.git/config <<-\EOF && + [one] + Qkey = not [two "subsection"] + [two "subsection"] + [two "subsection"] + Qkey = true + [TWO "subsection"] + [one] + EOF + git config --unset two.subsection.key && + test "not [two subsection]" = "$(git config one.key)" && + test_line_count = 3 .git/config ' -test_expect_failure 'adding a key into an empty section reuses header' ' +test_expect_success '--unset-all removes section if empty & uncommented' ' + cat >.git/config <<-\EOF && + [section] + key = value1 + key = value2 + EOF + + git config --unset-all section.key && + test_line_count = 0 .git/config +' + +test_expect_success 'adding a key into an empty section reuses header' ' cat >.git/config <<-\EOF && [section] EOF @@ -1611,4 +1716,88 @@ test_expect_success '--local requires a repo' ' test_expect_code 128 nongit git config --local foo.bar ' +cat >.git/config <<-\EOF && +[core] +foo = true +number = 10 +big = 1M +EOF + +test_expect_success 'identical modern --type specifiers are allowed' ' + git config --type=int --type=int core.big >actual && + echo 1048576 >expect && + test_cmp expect actual +' + +test_expect_success 'identical legacy --type specifiers are allowed' ' + git config --int --int core.big >actual && + echo 1048576 >expect && + test_cmp expect actual +' + +test_expect_success 'identical mixed --type specifiers are allowed' ' + git config --int --type=int core.big >actual && + echo 1048576 >expect && + test_cmp expect actual +' + +test_expect_success 'non-identical modern --type specifiers are not allowed' ' + test_must_fail git config --type=int --type=bool core.big 2>error && + test_i18ngrep "only one type at a time" error +' + +test_expect_success 'non-identical legacy --type specifiers are not allowed' ' + test_must_fail git config --int --bool core.big 2>error && + test_i18ngrep "only one type at a time" error +' + +test_expect_success 'non-identical mixed --type specifiers are not allowed' ' + test_must_fail git config --type=int --bool core.big 2>error && + test_i18ngrep "only one type at a time" error +' + +test_expect_success '--type allows valid type specifiers' ' + echo "true" >expect && + git config --type=bool core.foo >actual && + test_cmp expect actual +' + +test_expect_success '--no-type unsets type specifiers' ' + echo "10" >expect && + git config --type=bool --no-type core.number >actual && + test_cmp expect actual +' + +test_expect_success 'unset type specifiers may be reset to conflicting ones' ' + echo 1048576 >expect && + git config --type=bool --no-type --type=int core.big >actual && + test_cmp expect actual +' + +test_expect_success '--type rejects unknown specifiers' ' + test_must_fail git config --type=nonsense core.foo 2>error && + test_i18ngrep "unrecognized --type argument" error +' + +test_expect_success '--replace-all does not invent newlines' ' + q_to_tab >.git/config <<-\EOF && + [abc]key + QkeepSection + [xyz] + Qkey = 1 + [abc] + Qkey = a + EOF + q_to_tab >expect <<-\EOF && + [abc] + QkeepSection + [xyz] + Qkey = 1 + [abc] + Qkey = b + EOF + git config --replace-all abc.key b && + test_cmp .git/config expect +' + test_done diff --git a/t/t1310-config-default.sh b/t/t1310-config-default.sh new file mode 100755 index 0000000000..6049d91708 --- /dev/null +++ b/t/t1310-config-default.sh @@ -0,0 +1,36 @@ +#!/bin/sh + +test_description='Test git config in different settings (with --default)' + +. ./test-lib.sh + +test_expect_success 'uses --default when entry missing' ' + echo quux >expect && + git config -f config --default=quux core.foo >actual && + test_cmp expect actual +' + +test_expect_success 'does not use --default when entry present' ' + echo bar >expect && + git -c core.foo=bar config --default=baz core.foo >actual && + test_cmp expect actual +' + +test_expect_success 'canonicalizes --default with appropriate type' ' + echo true >expect && + git config -f config --default=yes --bool core.foo >actual && + test_cmp expect actual +' + +test_expect_success 'dies when --default cannot be parsed' ' + test_must_fail git config -f config --type=expiry-date --default=x --get \ + not.a.section 2>error && + test_i18ngrep "failed to format default config value" error +' + +test_expect_success 'does not allow --default without --get' ' + test_must_fail git config --default=quux --unset a.section >output 2>&1 && + test_i18ngrep "\-\-default is only applicable to" output +' + +test_done diff --git a/t/t1510-repo-setup.sh b/t/t1510-repo-setup.sh index e6854b828e..972bd9c785 100755 --- a/t/t1510-repo-setup.sh +++ b/t/t1510-repo-setup.sh @@ -238,7 +238,6 @@ test_expect_success '#0: nonbare repo, no explicit configuration' ' ' test_expect_success '#1: GIT_WORK_TREE without explicit GIT_DIR is accepted' ' - mkdir -p wt && try_repo 1 "$here" unset unset "" unset \ "$here/1/.git" "$here" "$here" 1/ \ "$here/1/.git" "$here" "$here" 1/sub/ 2>message && diff --git a/t/t2025-worktree-add.sh b/t/t2025-worktree-add.sh index d0d2e4f7ec..2240498924 100755 --- a/t/t2025-worktree-add.sh +++ b/t/t2025-worktree-add.sh @@ -198,13 +198,25 @@ test_expect_success '"add" with <branch> omitted' ' test_cmp_rev HEAD bat ' -test_expect_success '"add" auto-vivify does not clobber existing branch' ' - test_commit c1 && - test_commit c2 && - git branch precious HEAD~1 && - test_must_fail git worktree add precious && - test_cmp_rev HEAD~1 precious && - test_path_is_missing precious +test_expect_success '"add" checks out existing branch of dwimd name' ' + git branch dwim HEAD~1 && + git worktree add dwim && + test_cmp_rev HEAD~1 dwim && + ( + cd dwim && + test_cmp_rev HEAD dwim + ) +' + +test_expect_success '"add <path>" dwim fails with checked out branch' ' + git checkout -b test-branch && + test_must_fail git worktree add test-branch && + test_path_is_missing test-branch +' + +test_expect_success '"add --force" with existing dwimd name doesnt die' ' + git checkout test-branch && + git worktree add --force test-branch ' test_expect_success '"add" no auto-vivify with --detach and <branch> omitted' ' diff --git a/t/t3418-rebase-continue.sh b/t/t3418-rebase-continue.sh index 9214d0bb51..03bf1b8a3b 100755 --- a/t/t3418-rebase-continue.sh +++ b/t/t3418-rebase-continue.sh @@ -88,6 +88,55 @@ test_expect_success 'rebase passes merge strategy options correctly' ' git rebase --continue ' +test_expect_success '--skip after failed fixup cleans commit message' ' + test_when_finished "test_might_fail git rebase --abort" && + git checkout -b with-conflicting-fixup && + test_commit wants-fixup && + test_commit "fixup! wants-fixup" wants-fixup.t 1 wants-fixup-1 && + test_commit "fixup! wants-fixup" wants-fixup.t 2 wants-fixup-2 && + test_commit "fixup! wants-fixup" wants-fixup.t 3 wants-fixup-3 && + test_must_fail env FAKE_LINES="1 fixup 2 squash 4" \ + git rebase -i HEAD~4 && + + : now there is a conflict, and comments in the commit message && + git show HEAD >out && + grep "fixup! wants-fixup" out && + + : skip and continue && + echo "cp \"\$1\" .git/copy.txt" | write_script copy-editor.sh && + (test_set_editor "$PWD/copy-editor.sh" && git rebase --skip) && + + : the user should not have had to edit the commit message && + test_path_is_missing .git/copy.txt && + + : now the comments in the commit message should have been cleaned up && + git show HEAD >out && + ! grep "fixup! wants-fixup" out && + + : now, let us ensure that "squash" is handled correctly && + git reset --hard wants-fixup-3 && + test_must_fail env FAKE_LINES="1 squash 4 squash 2 squash 4" \ + git rebase -i HEAD~4 && + + : the first squash failed, but there are two more in the chain && + (test_set_editor "$PWD/copy-editor.sh" && + test_must_fail git rebase --skip) && + + : not the final squash, no need to edit the commit message && + test_path_is_missing .git/copy.txt && + + : The first squash was skipped, therefore: && + git show HEAD >out && + test_i18ngrep "# This is a combination of 2 commits" out && + + (test_set_editor "$PWD/copy-editor.sh" && git rebase --skip) && + git show HEAD >out && + test_i18ngrep ! "# This is a combination" out && + + : Final squash failed, but there was still a squash && + test_i18ngrep "# This is a combination of 2 commits" .git/copy.txt +' + test_expect_success 'setup rerere database' ' rm -fr .git/rebase-* && git reset --hard commit-new-file-F3-on-topic-branch && diff --git a/t/t3501-revert-cherry-pick.sh b/t/t3501-revert-cherry-pick.sh index ccbc118514..d1c68af8c5 100755 --- a/t/t3501-revert-cherry-pick.sh +++ b/t/t3501-revert-cherry-pick.sh @@ -141,7 +141,7 @@ test_expect_success 'cherry-pick "-" works with arguments' ' test_cmp expect actual ' -test_expect_failure 'cherry-pick works with dirty renamed file' ' +test_expect_success 'cherry-pick works with dirty renamed file' ' test_commit to-rename && git checkout -b unrelated && test_commit unrelated && @@ -150,9 +150,8 @@ test_expect_failure 'cherry-pick works with dirty renamed file' ' test_tick && git commit -m renamed && echo modified >renamed && - test_must_fail git cherry-pick refs/heads/unrelated >out && - test_i18ngrep "Refusing to lose dirty file at renamed" out && - test $(git rev-parse :0:renamed) = $(git rev-parse HEAD^:to-rename.t) && + git cherry-pick refs/heads/unrelated >out && + test $(git rev-parse :0:renamed) = $(git rev-parse HEAD~2:to-rename.t) && grep -q "^modified$" renamed ' diff --git a/t/t5300-pack-object.sh b/t/t5300-pack-object.sh index 65ff60f2ee..54eff03851 100755 --- a/t/t5300-pack-object.sh +++ b/t/t5300-pack-object.sh @@ -457,6 +457,11 @@ test_expect_success !PTHREADS,C_LOCALE_OUTPUT 'pack-objects --threads=N or pack. grep -F "no threads support, ignoring pack.threads" err ' +test_expect_success 'pack-objects in too-many-packs mode' ' + GIT_TEST_FULL_IN_PACK_ARRAY=1 git repack -ad && + git fsck +' + # # WARNING! # diff --git a/t/t5304-prune.sh b/t/t5304-prune.sh index f0f6e2a5f3..f20f03c103 100755 --- a/t/t5304-prune.sh +++ b/t/t5304-prune.sh @@ -320,4 +320,14 @@ test_expect_success 'prune: handle HEAD reflog in multiple worktrees' ' test_cmp expected actual ' +test_expect_success 'prune: handle expire option correctly' ' + test_must_fail git prune --expire 2>error && + test_i18ngrep "requires a value" error && + + test_must_fail git prune --expire=nyah 2>error && + test_i18ngrep "malformed expiration" error && + + git prune --no-expire +' + test_done diff --git a/t/t5310-pack-bitmaps.sh b/t/t5310-pack-bitmaps.sh index f6d600fd82..423c0a475f 100755 --- a/t/t5310-pack-bitmaps.sh +++ b/t/t5310-pack-bitmaps.sh @@ -264,9 +264,9 @@ test_expect_success 'pack with missing parent' ' ' test_expect_success JGIT 'we can read jgit bitmaps' ' - git clone . compat-jgit && + git clone --bare . compat-jgit.git && ( - cd compat-jgit && + cd compat-jgit.git && rm -f .git/objects/pack/*.bitmap && jgit gc && git rev-list --test-bitmap HEAD @@ -274,9 +274,9 @@ test_expect_success JGIT 'we can read jgit bitmaps' ' ' test_expect_success JGIT 'jgit can read our bitmaps' ' - git clone . compat-us && + git clone --bare . compat-us.git && ( - cd compat-us && + cd compat-us.git && git repack -adb && # jgit gc will barf if it does not like our bitmaps jgit gc diff --git a/t/t5318-commit-graph.sh b/t/t5318-commit-graph.sh new file mode 100755 index 0000000000..a380419b65 --- /dev/null +++ b/t/t5318-commit-graph.sh @@ -0,0 +1,224 @@ +#!/bin/sh + +test_description='commit graph' +. ./test-lib.sh + +test_expect_success 'setup full repo' ' + mkdir full && + cd "$TRASH_DIRECTORY/full" && + git init && + git config core.commitGraph true && + objdir=".git/objects" +' + +test_expect_success 'write graph with no packs' ' + cd "$TRASH_DIRECTORY/full" && + git commit-graph write --object-dir . && + test_path_is_file info/commit-graph +' + +test_expect_success 'create commits and repack' ' + cd "$TRASH_DIRECTORY/full" && + for i in $(test_seq 3) + do + test_commit $i && + git branch commits/$i + done && + git repack +' + +graph_git_two_modes() { + git -c core.graph=true $1 >output + git -c core.graph=false $1 >expect + test_cmp output expect +} + +graph_git_behavior() { + MSG=$1 + DIR=$2 + BRANCH=$3 + COMPARE=$4 + test_expect_success "check normal git operations: $MSG" ' + cd "$TRASH_DIRECTORY/$DIR" && + graph_git_two_modes "log --oneline $BRANCH" && + graph_git_two_modes "log --topo-order $BRANCH" && + graph_git_two_modes "log --graph $COMPARE..$BRANCH" && + graph_git_two_modes "branch -vv" && + graph_git_two_modes "merge-base -a $BRANCH $COMPARE" + ' +} + +graph_git_behavior 'no graph' full commits/3 commits/1 + +graph_read_expect() { + OPTIONAL="" + NUM_CHUNKS=3 + if test ! -z $2 + then + OPTIONAL=" $2" + NUM_CHUNKS=$((3 + $(echo "$2" | wc -w))) + fi + cat >expect <<- EOF + header: 43475048 1 1 $NUM_CHUNKS 0 + num_commits: $1 + chunks: oid_fanout oid_lookup commit_metadata$OPTIONAL + EOF + git commit-graph read >output && + test_cmp expect output +} + +test_expect_success 'write graph' ' + cd "$TRASH_DIRECTORY/full" && + graph1=$(git commit-graph write) && + test_path_is_file $objdir/info/commit-graph && + graph_read_expect "3" +' + +graph_git_behavior 'graph exists' full commits/3 commits/1 + +test_expect_success 'Add more commits' ' + cd "$TRASH_DIRECTORY/full" && + git reset --hard commits/1 && + for i in $(test_seq 4 5) + do + test_commit $i && + git branch commits/$i + done && + git reset --hard commits/2 && + for i in $(test_seq 6 7) + do + test_commit $i && + git branch commits/$i + done && + git reset --hard commits/2 && + git merge commits/4 && + git branch merge/1 && + git reset --hard commits/4 && + git merge commits/6 && + git branch merge/2 && + git reset --hard commits/3 && + git merge commits/5 commits/7 && + git branch merge/3 && + git repack +' + +# Current graph structure: +# +# __M3___ +# / | \ +# 3 M1 5 M2 7 +# |/ \|/ \| +# 2 4 6 +# |___/____/ +# 1 + +test_expect_success 'write graph with merges' ' + cd "$TRASH_DIRECTORY/full" && + git commit-graph write && + test_path_is_file $objdir/info/commit-graph && + graph_read_expect "10" "large_edges" +' + +graph_git_behavior 'merge 1 vs 2' full merge/1 merge/2 +graph_git_behavior 'merge 1 vs 3' full merge/1 merge/3 +graph_git_behavior 'merge 2 vs 3' full merge/2 merge/3 + +test_expect_success 'Add one more commit' ' + cd "$TRASH_DIRECTORY/full" && + test_commit 8 && + git branch commits/8 && + ls $objdir/pack | grep idx >existing-idx && + git repack && + ls $objdir/pack| grep idx | grep -v --file=existing-idx >new-idx +' + +# Current graph structure: +# +# 8 +# | +# __M3___ +# / | \ +# 3 M1 5 M2 7 +# |/ \|/ \| +# 2 4 6 +# |___/____/ +# 1 + +graph_git_behavior 'mixed mode, commit 8 vs merge 1' full commits/8 merge/1 +graph_git_behavior 'mixed mode, commit 8 vs merge 2' full commits/8 merge/2 + +test_expect_success 'write graph with new commit' ' + cd "$TRASH_DIRECTORY/full" && + git commit-graph write && + test_path_is_file $objdir/info/commit-graph && + graph_read_expect "11" "large_edges" +' + +graph_git_behavior 'full graph, commit 8 vs merge 1' full commits/8 merge/1 +graph_git_behavior 'full graph, commit 8 vs merge 2' full commits/8 merge/2 + +test_expect_success 'write graph with nothing new' ' + cd "$TRASH_DIRECTORY/full" && + git commit-graph write && + test_path_is_file $objdir/info/commit-graph && + graph_read_expect "11" "large_edges" +' + +graph_git_behavior 'cleared graph, commit 8 vs merge 1' full commits/8 merge/1 +graph_git_behavior 'cleared graph, commit 8 vs merge 2' full commits/8 merge/2 + +test_expect_success 'build graph from latest pack with closure' ' + cd "$TRASH_DIRECTORY/full" && + cat new-idx | git commit-graph write --stdin-packs && + test_path_is_file $objdir/info/commit-graph && + graph_read_expect "9" "large_edges" +' + +graph_git_behavior 'graph from pack, commit 8 vs merge 1' full commits/8 merge/1 +graph_git_behavior 'graph from pack, commit 8 vs merge 2' full commits/8 merge/2 + +test_expect_success 'build graph from commits with closure' ' + cd "$TRASH_DIRECTORY/full" && + git tag -a -m "merge" tag/merge merge/2 && + git rev-parse tag/merge >commits-in && + git rev-parse merge/1 >>commits-in && + cat commits-in | git commit-graph write --stdin-commits && + test_path_is_file $objdir/info/commit-graph && + graph_read_expect "6" +' + +graph_git_behavior 'graph from commits, commit 8 vs merge 1' full commits/8 merge/1 +graph_git_behavior 'graph from commits, commit 8 vs merge 2' full commits/8 merge/2 + +test_expect_success 'build graph from commits with append' ' + cd "$TRASH_DIRECTORY/full" && + git rev-parse merge/3 | git commit-graph write --stdin-commits --append && + test_path_is_file $objdir/info/commit-graph && + graph_read_expect "10" "large_edges" +' + +graph_git_behavior 'append graph, commit 8 vs merge 1' full commits/8 merge/1 +graph_git_behavior 'append graph, commit 8 vs merge 2' full commits/8 merge/2 + +test_expect_success 'setup bare repo' ' + cd "$TRASH_DIRECTORY" && + git clone --bare --no-local full bare && + cd bare && + git config core.commitGraph true && + baredir="./objects" +' + +graph_git_behavior 'bare repo, commit 8 vs merge 1' bare commits/8 merge/1 +graph_git_behavior 'bare repo, commit 8 vs merge 2' bare commits/8 merge/2 + +test_expect_success 'write graph in bare repo' ' + cd "$TRASH_DIRECTORY/bare" && + git commit-graph write && + test_path_is_file $baredir/info/commit-graph && + graph_read_expect "11" "large_edges" +' + +graph_git_behavior 'bare repo with graph, commit 8 vs merge 1' bare commits/8 merge/1 +graph_git_behavior 'bare repo with graph, commit 8 vs merge 2' bare commits/8 merge/2 + +test_done diff --git a/t/t5512-ls-remote.sh b/t/t5512-ls-remote.sh index 02106c9226..6a949484d0 100755 --- a/t/t5512-ls-remote.sh +++ b/t/t5512-ls-remote.sh @@ -10,6 +10,9 @@ test_expect_success setup ' test_tick && git commit -m initial && git tag mark && + git tag mark1.1 && + git tag mark1.2 && + git tag mark1.10 && git show-ref --tags -d | sed -e "s/ / /" >expected.tag && ( echo "$(git rev-parse HEAD) HEAD" @@ -39,6 +42,39 @@ test_expect_success 'ls-remote self' ' test_cmp expected.all actual ' +test_expect_success 'ls-remote --sort="version:refname" --tags self' ' + cat >expect <<-EOF && + $(git rev-parse mark) refs/tags/mark + $(git rev-parse mark1.1) refs/tags/mark1.1 + $(git rev-parse mark1.2) refs/tags/mark1.2 + $(git rev-parse mark1.10) refs/tags/mark1.10 + EOF + git ls-remote --sort="version:refname" --tags self >actual && + test_cmp expect actual +' + +test_expect_success 'ls-remote --sort="-version:refname" --tags self' ' + cat >expect <<-EOF && + $(git rev-parse mark1.10) refs/tags/mark1.10 + $(git rev-parse mark1.2) refs/tags/mark1.2 + $(git rev-parse mark1.1) refs/tags/mark1.1 + $(git rev-parse mark) refs/tags/mark + EOF + git ls-remote --sort="-version:refname" --tags self >actual && + test_cmp expect actual +' + +test_expect_success 'ls-remote --sort="-refname" --tags self' ' + cat >expect <<-EOF && + $(git rev-parse mark1.2) refs/tags/mark1.2 + $(git rev-parse mark1.10) refs/tags/mark1.10 + $(git rev-parse mark1.1) refs/tags/mark1.1 + $(git rev-parse mark) refs/tags/mark + EOF + git ls-remote --sort="-refname" --tags self >actual && + test_cmp expect actual +' + test_expect_success 'dies when no remote specified and no default remotes found' ' test_must_fail git ls-remote ' @@ -131,7 +167,7 @@ test_expect_success 'Report no-match with --exit-code' ' test_expect_success 'Report match with --exit-code' ' git ls-remote --exit-code other.git "refs/tags/*" >actual && - git ls-remote . tags/mark >expect && + git ls-remote . tags/mark* >expect && test_cmp expect actual ' @@ -171,13 +207,17 @@ test_expect_success 'overrides work between mixed transfer/upload-pack hideRefs' ' test_expect_success 'ls-remote --symref' ' - cat >expect <<-\EOF && + git fetch origin && + cat >expect <<-EOF && ref: refs/heads/master HEAD - 1bd44cb9d13204b0fe1958db0082f5028a16eb3a HEAD - 1bd44cb9d13204b0fe1958db0082f5028a16eb3a refs/heads/master - 1bd44cb9d13204b0fe1958db0082f5028a16eb3a refs/remotes/origin/HEAD - 1bd44cb9d13204b0fe1958db0082f5028a16eb3a refs/remotes/origin/master - 1bd44cb9d13204b0fe1958db0082f5028a16eb3a refs/tags/mark + $(git rev-parse HEAD) HEAD + $(git rev-parse refs/heads/master) refs/heads/master + $(git rev-parse HEAD) refs/remotes/origin/HEAD + $(git rev-parse refs/remotes/origin/master) refs/remotes/origin/master + $(git rev-parse refs/tags/mark) refs/tags/mark + $(git rev-parse refs/tags/mark1.1) refs/tags/mark1.1 + $(git rev-parse refs/tags/mark1.10) refs/tags/mark1.10 + $(git rev-parse refs/tags/mark1.2) refs/tags/mark1.2 EOF git ls-remote --symref >actual && test_cmp expect actual diff --git a/t/t5516-fetch-push.sh b/t/t5516-fetch-push.sh index 82239138d5..3e8940eee5 100755 --- a/t/t5516-fetch-push.sh +++ b/t/t5516-fetch-push.sh @@ -94,6 +94,9 @@ mk_child() { } check_push_result () { + test $# -ge 3 || + error "bug in the test script: check_push_result requires at least 3 parameters" + repo_name="$1" shift @@ -553,10 +556,7 @@ test_expect_success 'branch.*.pushremote config order is irrelevant' ' test_expect_success 'push with dry-run' ' mk_test testrepo heads/master && - ( - cd testrepo && - old_commit=$(git show-ref -s --verify refs/heads/master) - ) && + old_commit=$(git -C testrepo show-ref -s --verify refs/heads/master) && git push --dry-run testrepo : && check_push_result testrepo $old_commit heads/master ' @@ -612,7 +612,7 @@ test_expect_success 'push does not update local refs on failure' ' chmod +x testrepo/.git/hooks/pre-receive && ( cd child && - git pull .. master + git pull .. master && test_must_fail git push && test $(git rev-parse master) != \ $(git rev-parse remotes/origin/master) diff --git a/t/t5541-http-push-smart.sh b/t/t5541-http-push-smart.sh index 21340e89c9..a2af693068 100755 --- a/t/t5541-http-push-smart.sh +++ b/t/t5541-http-push-smart.sh @@ -377,5 +377,17 @@ test_expect_success 'push status output scrubs password' ' grep "^To $HTTPD_URL/smart/test_repo.git" status ' +test_expect_success 'colorize errors/hints' ' + cd "$ROOT_PATH"/test_repo_clone && + test_must_fail git -c color.transport=always -c color.advice=always \ + -c color.push=always \ + push origin origin/master^:master 2>act && + test_decode_color <act >decoded && + test_i18ngrep "<RED>.*rejected.*<RESET>" decoded && + test_i18ngrep "<RED>error: failed to push some refs" decoded && + test_i18ngrep "<YELLOW>hint: " decoded && + test_i18ngrep ! "^hint: " decoded +' + stop_httpd test_done diff --git a/t/t5550-http-fetch-dumb.sh b/t/t5550-http-fetch-dumb.sh index 8552184e74..6d7d88ccc9 100755 --- a/t/t5550-http-fetch-dumb.sh +++ b/t/t5550-http-fetch-dumb.sh @@ -169,6 +169,17 @@ test_expect_success 'fetch changes via manual http-fetch' ' test_cmp file clone2/file ' +test_expect_success 'manual http-fetch without -a works just as well' ' + cp -R clone-tmpl clone3 && + + HEAD=$(git rev-parse --verify HEAD) && + (cd clone3 && + git http-fetch -w heads/master-new $HEAD $(git config remote.origin.url) && + git checkout master-new && + test $HEAD = $(git rev-parse --verify HEAD)) && + test_cmp file clone3/file +' + test_expect_success 'http remote detects correct HEAD' ' git push public master:other && (cd clone && diff --git a/t/t5701-git-serve.sh b/t/t5701-git-serve.sh new file mode 100755 index 0000000000..011a5796db --- /dev/null +++ b/t/t5701-git-serve.sh @@ -0,0 +1,197 @@ +#!/bin/sh + +test_description='test git-serve and server commands' + +. ./test-lib.sh + +test_expect_success 'test capability advertisement' ' + cat >expect <<-EOF && + version 2 + agent=git/$(git version | cut -d" " -f3) + ls-refs + fetch=shallow + server-option + 0000 + EOF + + git serve --advertise-capabilities >out && + test-pkt-line unpack <out >actual && + test_cmp actual expect +' + +test_expect_success 'stateless-rpc flag does not list capabilities' ' + # Empty request + test-pkt-line pack >in <<-EOF && + 0000 + EOF + git serve --stateless-rpc >out <in && + test_must_be_empty out && + + # EOF + git serve --stateless-rpc >out && + test_must_be_empty out +' + +test_expect_success 'request invalid capability' ' + test-pkt-line pack >in <<-EOF && + foobar + 0000 + EOF + test_must_fail git serve --stateless-rpc 2>err <in && + test_i18ngrep "unknown capability" err +' + +test_expect_success 'request with no command' ' + test-pkt-line pack >in <<-EOF && + agent=git/test + 0000 + EOF + test_must_fail git serve --stateless-rpc 2>err <in && + test_i18ngrep "no command requested" err +' + +test_expect_success 'request invalid command' ' + test-pkt-line pack >in <<-EOF && + command=foo + agent=git/test + 0000 + EOF + test_must_fail git serve --stateless-rpc 2>err <in && + test_i18ngrep "invalid command" err +' + +# Test the basics of ls-refs +# +test_expect_success 'setup some refs and tags' ' + test_commit one && + git branch dev master && + test_commit two && + git symbolic-ref refs/heads/release refs/heads/master && + git tag -a -m "annotated tag" annotated-tag +' + +test_expect_success 'basics of ls-refs' ' + test-pkt-line pack >in <<-EOF && + command=ls-refs + 0000 + EOF + + cat >expect <<-EOF && + $(git rev-parse HEAD) HEAD + $(git rev-parse refs/heads/dev) refs/heads/dev + $(git rev-parse refs/heads/master) refs/heads/master + $(git rev-parse refs/heads/release) refs/heads/release + $(git rev-parse refs/tags/annotated-tag) refs/tags/annotated-tag + $(git rev-parse refs/tags/one) refs/tags/one + $(git rev-parse refs/tags/two) refs/tags/two + 0000 + EOF + + git serve --stateless-rpc <in >out && + test-pkt-line unpack <out >actual && + test_cmp actual expect +' + +test_expect_success 'basic ref-prefixes' ' + test-pkt-line pack >in <<-EOF && + command=ls-refs + 0001 + ref-prefix refs/heads/master + ref-prefix refs/tags/one + 0000 + EOF + + cat >expect <<-EOF && + $(git rev-parse refs/heads/master) refs/heads/master + $(git rev-parse refs/tags/one) refs/tags/one + 0000 + EOF + + git serve --stateless-rpc <in >out && + test-pkt-line unpack <out >actual && + test_cmp actual expect +' + +test_expect_success 'refs/heads prefix' ' + test-pkt-line pack >in <<-EOF && + command=ls-refs + 0001 + ref-prefix refs/heads/ + 0000 + EOF + + cat >expect <<-EOF && + $(git rev-parse refs/heads/dev) refs/heads/dev + $(git rev-parse refs/heads/master) refs/heads/master + $(git rev-parse refs/heads/release) refs/heads/release + 0000 + EOF + + git serve --stateless-rpc <in >out && + test-pkt-line unpack <out >actual && + test_cmp actual expect +' + +test_expect_success 'peel parameter' ' + test-pkt-line pack >in <<-EOF && + command=ls-refs + 0001 + peel + ref-prefix refs/tags/ + 0000 + EOF + + cat >expect <<-EOF && + $(git rev-parse refs/tags/annotated-tag) refs/tags/annotated-tag peeled:$(git rev-parse refs/tags/annotated-tag^{}) + $(git rev-parse refs/tags/one) refs/tags/one + $(git rev-parse refs/tags/two) refs/tags/two + 0000 + EOF + + git serve --stateless-rpc <in >out && + test-pkt-line unpack <out >actual && + test_cmp actual expect +' + +test_expect_success 'symrefs parameter' ' + test-pkt-line pack >in <<-EOF && + command=ls-refs + 0001 + symrefs + ref-prefix refs/heads/ + 0000 + EOF + + cat >expect <<-EOF && + $(git rev-parse refs/heads/dev) refs/heads/dev + $(git rev-parse refs/heads/master) refs/heads/master + $(git rev-parse refs/heads/release) refs/heads/release symref-target:refs/heads/master + 0000 + EOF + + git serve --stateless-rpc <in >out && + test-pkt-line unpack <out >actual && + test_cmp actual expect +' + +test_expect_success 'sending server-options' ' + test-pkt-line pack >in <<-EOF && + command=ls-refs + server-option=hello + server-option=world + 0001 + ref-prefix HEAD + 0000 + EOF + + cat >expect <<-EOF && + $(git rev-parse HEAD) HEAD + 0000 + EOF + + git serve --stateless-rpc <in >out && + test-pkt-line unpack <out >actual && + test_cmp actual expect +' + +test_done diff --git a/t/t5702-protocol-v2.sh b/t/t5702-protocol-v2.sh new file mode 100755 index 0000000000..dbfd0691c0 --- /dev/null +++ b/t/t5702-protocol-v2.sh @@ -0,0 +1,305 @@ +#!/bin/sh + +test_description='test git wire-protocol version 2' + +TEST_NO_CREATE_REPO=1 + +. ./test-lib.sh + +# Test protocol v2 with 'git://' transport +# +. "$TEST_DIRECTORY"/lib-git-daemon.sh +start_git_daemon --export-all --enable=receive-pack +daemon_parent=$GIT_DAEMON_DOCUMENT_ROOT_PATH/parent + +test_expect_success 'create repo to be served by git-daemon' ' + git init "$daemon_parent" && + test_commit -C "$daemon_parent" one +' + +test_expect_success 'list refs with git:// using protocol v2' ' + test_when_finished "rm -f log" && + + GIT_TRACE_PACKET="$(pwd)/log" git -c protocol.version=2 \ + ls-remote --symref "$GIT_DAEMON_URL/parent" >actual && + + # Client requested to use protocol v2 + grep "git> .*\\\0\\\0version=2\\\0$" log && + # Server responded using protocol v2 + grep "git< version 2" log && + + git ls-remote --symref "$GIT_DAEMON_URL/parent" >expect && + test_cmp actual expect +' + +test_expect_success 'ref advertisment is filtered with ls-remote using protocol v2' ' + test_when_finished "rm -f log" && + + GIT_TRACE_PACKET="$(pwd)/log" git -c protocol.version=2 \ + ls-remote "$GIT_DAEMON_URL/parent" master >actual && + + cat >expect <<-EOF && + $(git -C "$daemon_parent" rev-parse refs/heads/master)$(printf "\t")refs/heads/master + EOF + + test_cmp actual expect +' + +test_expect_success 'clone with git:// using protocol v2' ' + test_when_finished "rm -f log" && + + GIT_TRACE_PACKET="$(pwd)/log" git -c protocol.version=2 \ + clone "$GIT_DAEMON_URL/parent" daemon_child && + + git -C daemon_child log -1 --format=%s >actual && + git -C "$daemon_parent" log -1 --format=%s >expect && + test_cmp expect actual && + + # Client requested to use protocol v2 + grep "clone> .*\\\0\\\0version=2\\\0$" log && + # Server responded using protocol v2 + grep "clone< version 2" log +' + +test_expect_success 'fetch with git:// using protocol v2' ' + test_when_finished "rm -f log" && + + test_commit -C "$daemon_parent" two && + + GIT_TRACE_PACKET="$(pwd)/log" git -C daemon_child -c protocol.version=2 \ + fetch && + + git -C daemon_child log -1 --format=%s origin/master >actual && + git -C "$daemon_parent" log -1 --format=%s >expect && + test_cmp expect actual && + + # Client requested to use protocol v2 + grep "fetch> .*\\\0\\\0version=2\\\0$" log && + # Server responded using protocol v2 + grep "fetch< version 2" log +' + +test_expect_success 'pull with git:// using protocol v2' ' + test_when_finished "rm -f log" && + + GIT_TRACE_PACKET="$(pwd)/log" git -C daemon_child -c protocol.version=2 \ + pull && + + git -C daemon_child log -1 --format=%s >actual && + git -C "$daemon_parent" log -1 --format=%s >expect && + test_cmp expect actual && + + # Client requested to use protocol v2 + grep "fetch> .*\\\0\\\0version=2\\\0$" log && + # Server responded using protocol v2 + grep "fetch< version 2" log +' + +test_expect_success 'push with git:// and a config of v2 does not request v2' ' + test_when_finished "rm -f log" && + + # Till v2 for push is designed, make sure that if a client has + # protocol.version configured to use v2, that the client instead falls + # back and uses v0. + + test_commit -C daemon_child three && + + # Push to another branch, as the target repository has the + # master branch checked out and we cannot push into it. + GIT_TRACE_PACKET="$(pwd)/log" git -C daemon_child -c protocol.version=2 \ + push origin HEAD:client_branch && + + git -C daemon_child log -1 --format=%s >actual && + git -C "$daemon_parent" log -1 --format=%s client_branch >expect && + test_cmp expect actual && + + # Client requested to use protocol v2 + ! grep "push> .*\\\0\\\0version=2\\\0$" log && + # Server responded using protocol v2 + ! grep "push< version 2" log +' + +stop_git_daemon + +# Test protocol v2 with 'file://' transport +# +test_expect_success 'create repo to be served by file:// transport' ' + git init file_parent && + test_commit -C file_parent one +' + +test_expect_success 'list refs with file:// using protocol v2' ' + test_when_finished "rm -f log" && + + GIT_TRACE_PACKET="$(pwd)/log" git -c protocol.version=2 \ + ls-remote --symref "file://$(pwd)/file_parent" >actual && + + # Server responded using protocol v2 + grep "git< version 2" log && + + git ls-remote --symref "file://$(pwd)/file_parent" >expect && + test_cmp actual expect +' + +test_expect_success 'ref advertisment is filtered with ls-remote using protocol v2' ' + test_when_finished "rm -f log" && + + GIT_TRACE_PACKET="$(pwd)/log" git -c protocol.version=2 \ + ls-remote "file://$(pwd)/file_parent" master >actual && + + cat >expect <<-EOF && + $(git -C file_parent rev-parse refs/heads/master)$(printf "\t")refs/heads/master + EOF + + test_cmp actual expect +' + +test_expect_success 'server-options are sent when using ls-remote' ' + test_when_finished "rm -f log" && + + GIT_TRACE_PACKET="$(pwd)/log" git -c protocol.version=2 \ + ls-remote -o hello -o world "file://$(pwd)/file_parent" master >actual && + + cat >expect <<-EOF && + $(git -C file_parent rev-parse refs/heads/master)$(printf "\t")refs/heads/master + EOF + + test_cmp actual expect && + grep "server-option=hello" log && + grep "server-option=world" log +' + + +test_expect_success 'clone with file:// using protocol v2' ' + test_when_finished "rm -f log" && + + GIT_TRACE_PACKET="$(pwd)/log" git -c protocol.version=2 \ + clone "file://$(pwd)/file_parent" file_child && + + git -C file_child log -1 --format=%s >actual && + git -C file_parent log -1 --format=%s >expect && + test_cmp expect actual && + + # Server responded using protocol v2 + grep "clone< version 2" log +' + +test_expect_success 'fetch with file:// using protocol v2' ' + test_when_finished "rm -f log" && + + test_commit -C file_parent two && + + GIT_TRACE_PACKET="$(pwd)/log" git -C file_child -c protocol.version=2 \ + fetch origin && + + git -C file_child log -1 --format=%s origin/master >actual && + git -C file_parent log -1 --format=%s >expect && + test_cmp expect actual && + + # Server responded using protocol v2 + grep "fetch< version 2" log +' + +test_expect_success 'ref advertisment is filtered during fetch using protocol v2' ' + test_when_finished "rm -f log" && + + test_commit -C file_parent three && + + GIT_TRACE_PACKET="$(pwd)/log" git -C file_child -c protocol.version=2 \ + fetch origin master && + + git -C file_child log -1 --format=%s origin/master >actual && + git -C file_parent log -1 --format=%s >expect && + test_cmp expect actual && + + ! grep "refs/tags/one" log && + ! grep "refs/tags/two" log && + ! grep "refs/tags/three" log +' + +test_expect_success 'server-options are sent when fetching' ' + test_when_finished "rm -f log" && + + test_commit -C file_parent four && + + GIT_TRACE_PACKET="$(pwd)/log" git -C file_child -c protocol.version=2 \ + fetch -o hello -o world origin master && + + git -C file_child log -1 --format=%s origin/master >actual && + git -C file_parent log -1 --format=%s >expect && + test_cmp expect actual && + + grep "server-option=hello" log && + grep "server-option=world" log +' + +# Test protocol v2 with 'http://' transport +# +. "$TEST_DIRECTORY"/lib-httpd.sh +start_httpd + +test_expect_success 'create repo to be served by http:// transport' ' + git init "$HTTPD_DOCUMENT_ROOT_PATH/http_parent" && + git -C "$HTTPD_DOCUMENT_ROOT_PATH/http_parent" config http.receivepack true && + test_commit -C "$HTTPD_DOCUMENT_ROOT_PATH/http_parent" one +' + +test_expect_success 'clone with http:// using protocol v2' ' + test_when_finished "rm -f log" && + + GIT_TRACE_PACKET="$(pwd)/log" GIT_TRACE_CURL="$(pwd)/log" git -c protocol.version=2 \ + clone "$HTTPD_URL/smart/http_parent" http_child && + + git -C http_child log -1 --format=%s >actual && + git -C "$HTTPD_DOCUMENT_ROOT_PATH/http_parent" log -1 --format=%s >expect && + test_cmp expect actual && + + # Client requested to use protocol v2 + grep "Git-Protocol: version=2" log && + # Server responded using protocol v2 + grep "git< version 2" log +' + +test_expect_success 'fetch with http:// using protocol v2' ' + test_when_finished "rm -f log" && + + test_commit -C "$HTTPD_DOCUMENT_ROOT_PATH/http_parent" two && + + GIT_TRACE_PACKET="$(pwd)/log" git -C http_child -c protocol.version=2 \ + fetch && + + git -C http_child log -1 --format=%s origin/master >actual && + git -C "$HTTPD_DOCUMENT_ROOT_PATH/http_parent" log -1 --format=%s >expect && + test_cmp expect actual && + + # Server responded using protocol v2 + grep "git< version 2" log +' + +test_expect_success 'push with http:// and a config of v2 does not request v2' ' + test_when_finished "rm -f log" && + # Till v2 for push is designed, make sure that if a client has + # protocol.version configured to use v2, that the client instead falls + # back and uses v0. + + test_commit -C http_child three && + + # Push to another branch, as the target repository has the + # master branch checked out and we cannot push into it. + GIT_TRACE_PACKET="$(pwd)/log" git -C http_child -c protocol.version=2 \ + push origin HEAD:client_branch && + + git -C http_child log -1 --format=%s >actual && + git -C "$HTTPD_DOCUMENT_ROOT_PATH/http_parent" log -1 --format=%s client_branch >expect && + test_cmp expect actual && + + # Client didnt request to use protocol v2 + ! grep "Git-Protocol: version=2" log && + # Server didnt respond using protocol v2 + ! grep "git< version 2" log +' + + +stop_httpd + +test_done diff --git a/t/t6001-rev-list-graft.sh b/t/t6001-rev-list-graft.sh index 05ddc69cf2..7504ba4751 100755 --- a/t/t6001-rev-list-graft.sh +++ b/t/t6001-rev-list-graft.sh @@ -110,4 +110,13 @@ do " done + +test_expect_success 'show advice that grafts are deprecated' ' + git show HEAD 2>err && + test_i18ngrep "git replace" err && + test_config advice.graftFileDeprecated false && + git show HEAD 2>err && + test_i18ngrep ! "git replace" err +' + test_done diff --git a/t/t6022-merge-rename.sh b/t/t6022-merge-rename.sh index 48747e71df..b760c223c6 100755 --- a/t/t6022-merge-rename.sh +++ b/t/t6022-merge-rename.sh @@ -247,7 +247,7 @@ test_expect_success 'merge of identical changes in a renamed file' ' git reset --hard HEAD^ && git checkout change && GIT_MERGE_VERBOSITY=3 git merge change+rename >out && - test_i18ngrep "^Skipped B" out + test_i18ngrep ! "^Skipped B" out ' test_expect_success 'setup for rename + d/f conflicts' ' diff --git a/t/t6043-merge-rename-directories.sh b/t/t6043-merge-rename-directories.sh new file mode 100755 index 0000000000..2e28f2908d --- /dev/null +++ b/t/t6043-merge-rename-directories.sh @@ -0,0 +1,3998 @@ +#!/bin/sh + +test_description="recursive merge with directory renames" +# includes checking of many corner cases, with a similar methodology to: +# t6042: corner cases with renames but not criss-cross merges +# t6036: corner cases with both renames and criss-cross merges +# +# The setup for all of them, pictorially, is: +# +# A +# o +# / \ +# O o ? +# \ / +# o +# B +# +# To help make it easier to follow the flow of tests, they have been +# divided into sections and each test will start with a quick explanation +# of what commits O, A, and B contain. +# +# Notation: +# z/{b,c} means files z/b and z/c both exist +# x/d_1 means file x/d exists with content d1. (Purpose of the +# underscore notation is to differentiate different +# files that might be renamed into each other's paths.) + +. ./test-lib.sh + + +########################################################################### +# SECTION 1: Basic cases we should be able to handle +########################################################################### + +# Testcase 1a, Basic directory rename. +# Commit O: z/{b,c} +# Commit A: y/{b,c} +# Commit B: z/{b,c,d,e/f} +# Expected: y/{b,c,d,e/f} + +test_expect_success '1a-setup: Simple directory rename detection' ' + test_create_repo 1a && + ( + cd 1a && + + mkdir z && + echo b >z/b && + echo c >z/c && + git add z && + test_tick && + git commit -m "O" && + + git branch O && + git branch A && + git branch B && + + git checkout A && + git mv z y && + test_tick && + git commit -m "A" && + + git checkout B && + echo d >z/d && + mkdir z/e && + echo f >z/e/f && + git add z/d z/e/f && + test_tick && + git commit -m "B" + ) +' + +test_expect_success '1a-check: Simple directory rename detection' ' + ( + cd 1a && + + git checkout A^0 && + + git merge -s recursive B^0 && + + git ls-files -s >out && + test_line_count = 4 out && + + git rev-parse >actual \ + HEAD:y/b HEAD:y/c HEAD:y/d HEAD:y/e/f && + git rev-parse >expect \ + O:z/b O:z/c B:z/d B:z/e/f && + test_cmp expect actual && + + git hash-object y/d >actual && + git rev-parse B:z/d >expect && + test_cmp expect actual && + + test_must_fail git rev-parse HEAD:z/d && + test_must_fail git rev-parse HEAD:z/e/f && + test_path_is_missing z/d && + test_path_is_missing z/e/f + ) +' + +# Testcase 1b, Merge a directory with another +# Commit O: z/{b,c}, y/d +# Commit A: z/{b,c,e}, y/d +# Commit B: y/{b,c,d} +# Expected: y/{b,c,d,e} + +test_expect_success '1b-setup: Merge a directory with another' ' + test_create_repo 1b && + ( + cd 1b && + + mkdir z && + echo b >z/b && + echo c >z/c && + mkdir y && + echo d >y/d && + git add z y && + test_tick && + git commit -m "O" && + + git branch O && + git branch A && + git branch B && + + git checkout A && + echo e >z/e && + git add z/e && + test_tick && + git commit -m "A" && + + git checkout B && + git mv z/b y && + git mv z/c y && + rmdir z && + test_tick && + git commit -m "B" + ) +' + +test_expect_success '1b-check: Merge a directory with another' ' + ( + cd 1b && + + git checkout A^0 && + + git merge -s recursive B^0 && + + git ls-files -s >out && + test_line_count = 4 out && + + git rev-parse >actual \ + HEAD:y/b HEAD:y/c HEAD:y/d HEAD:y/e && + git rev-parse >expect \ + O:z/b O:z/c O:y/d A:z/e && + test_cmp expect actual && + test_must_fail git rev-parse HEAD:z/e + ) +' + +# Testcase 1c, Transitive renaming +# (Related to testcases 3a and 6d -- when should a transitive rename apply?) +# (Related to testcases 9c and 9d -- can transitivity repeat?) +# (Related to testcase 12b -- joint-transitivity?) +# Commit O: z/{b,c}, x/d +# Commit A: y/{b,c}, x/d +# Commit B: z/{b,c,d} +# Expected: y/{b,c,d} (because x/d -> z/d -> y/d) + +test_expect_success '1c-setup: Transitive renaming' ' + test_create_repo 1c && + ( + cd 1c && + + mkdir z && + echo b >z/b && + echo c >z/c && + mkdir x && + echo d >x/d && + git add z x && + test_tick && + git commit -m "O" && + + git branch O && + git branch A && + git branch B && + + git checkout A && + git mv z y && + test_tick && + git commit -m "A" && + + git checkout B && + git mv x/d z/d && + test_tick && + git commit -m "B" + ) +' + +test_expect_success '1c-check: Transitive renaming' ' + ( + cd 1c && + + git checkout A^0 && + + git merge -s recursive B^0 && + + git ls-files -s >out && + test_line_count = 3 out && + + git rev-parse >actual \ + HEAD:y/b HEAD:y/c HEAD:y/d && + git rev-parse >expect \ + O:z/b O:z/c O:x/d && + test_cmp expect actual && + test_must_fail git rev-parse HEAD:x/d && + test_must_fail git rev-parse HEAD:z/d && + test_path_is_missing z/d + ) +' + +# Testcase 1d, Directory renames (merging two directories into one new one) +# cause a rename/rename(2to1) conflict +# (Related to testcases 1c and 7b) +# Commit O. z/{b,c}, y/{d,e} +# Commit A. x/{b,c}, y/{d,e,m,wham_1} +# Commit B. z/{b,c,n,wham_2}, x/{d,e} +# Expected: x/{b,c,d,e,m,n}, CONFLICT:(y/wham_1 & z/wham_2 -> x/wham) +# Note: y/m & z/n should definitely move into x. By the same token, both +# y/wham_1 & z/wham_2 should too...giving us a conflict. + +test_expect_success '1d-setup: Directory renames cause a rename/rename(2to1) conflict' ' + test_create_repo 1d && + ( + cd 1d && + + mkdir z && + echo b >z/b && + echo c >z/c && + mkdir y && + echo d >y/d && + echo e >y/e && + git add z y && + test_tick && + git commit -m "O" && + + git branch O && + git branch A && + git branch B && + + git checkout A && + git mv z x && + echo m >y/m && + echo wham1 >y/wham && + git add y && + test_tick && + git commit -m "A" && + + git checkout B && + git mv y x && + echo n >z/n && + echo wham2 >z/wham && + git add z && + test_tick && + git commit -m "B" + ) +' + +test_expect_success '1d-check: Directory renames cause a rename/rename(2to1) conflict' ' + ( + cd 1d && + + git checkout A^0 && + + test_must_fail git merge -s recursive B^0 >out && + test_i18ngrep "CONFLICT (rename/rename)" out && + + git ls-files -s >out && + test_line_count = 8 out && + git ls-files -u >out && + test_line_count = 2 out && + git ls-files -o >out && + test_line_count = 3 out && + + git rev-parse >actual \ + :0:x/b :0:x/c :0:x/d :0:x/e :0:x/m :0:x/n && + git rev-parse >expect \ + O:z/b O:z/c O:y/d O:y/e A:y/m B:z/n && + test_cmp expect actual && + + test_must_fail git rev-parse :0:x/wham && + git rev-parse >actual \ + :2:x/wham :3:x/wham && + git rev-parse >expect \ + A:y/wham B:z/wham && + test_cmp expect actual && + + test_path_is_missing x/wham && + test_path_is_file x/wham~HEAD && + test_path_is_file x/wham~B^0 && + + git hash-object >actual \ + x/wham~HEAD x/wham~B^0 && + git rev-parse >expect \ + A:y/wham B:z/wham && + test_cmp expect actual + ) +' + +# Testcase 1e, Renamed directory, with all filenames being renamed too +# (Related to testcases 9f & 9g) +# Commit O: z/{oldb,oldc} +# Commit A: y/{newb,newc} +# Commit B: z/{oldb,oldc,d} +# Expected: y/{newb,newc,d} + +test_expect_success '1e-setup: Renamed directory, with all files being renamed too' ' + test_create_repo 1e && + ( + cd 1e && + + mkdir z && + echo b >z/oldb && + echo c >z/oldc && + git add z && + test_tick && + git commit -m "O" && + + git branch O && + git branch A && + git branch B && + + git checkout A && + mkdir y && + git mv z/oldb y/newb && + git mv z/oldc y/newc && + test_tick && + git commit -m "A" && + + git checkout B && + echo d >z/d && + git add z/d && + test_tick && + git commit -m "B" + ) +' + +test_expect_success '1e-check: Renamed directory, with all files being renamed too' ' + ( + cd 1e && + + git checkout A^0 && + + git merge -s recursive B^0 && + + git ls-files -s >out && + test_line_count = 3 out && + + git rev-parse >actual \ + HEAD:y/newb HEAD:y/newc HEAD:y/d && + git rev-parse >expect \ + O:z/oldb O:z/oldc B:z/d && + test_cmp expect actual && + test_must_fail git rev-parse HEAD:z/d + ) +' + +# Testcase 1f, Split a directory into two other directories +# (Related to testcases 3a, all of section 2, and all of section 4) +# Commit O: z/{b,c,d,e,f} +# Commit A: z/{b,c,d,e,f,g} +# Commit B: y/{b,c}, x/{d,e,f} +# Expected: y/{b,c}, x/{d,e,f,g} + +test_expect_success '1f-setup: Split a directory into two other directories' ' + test_create_repo 1f && + ( + cd 1f && + + mkdir z && + echo b >z/b && + echo c >z/c && + echo d >z/d && + echo e >z/e && + echo f >z/f && + git add z && + test_tick && + git commit -m "O" && + + git branch O && + git branch A && + git branch B && + + git checkout A && + echo g >z/g && + git add z/g && + test_tick && + git commit -m "A" && + + git checkout B && + mkdir y && + mkdir x && + git mv z/b y/ && + git mv z/c y/ && + git mv z/d x/ && + git mv z/e x/ && + git mv z/f x/ && + rmdir z && + test_tick && + git commit -m "B" + ) +' + +test_expect_success '1f-check: Split a directory into two other directories' ' + ( + cd 1f && + + git checkout A^0 && + + git merge -s recursive B^0 && + + git ls-files -s >out && + test_line_count = 6 out && + + git rev-parse >actual \ + HEAD:y/b HEAD:y/c HEAD:x/d HEAD:x/e HEAD:x/f HEAD:x/g && + git rev-parse >expect \ + O:z/b O:z/c O:z/d O:z/e O:z/f A:z/g && + test_cmp expect actual && + test_path_is_missing z/g && + test_must_fail git rev-parse HEAD:z/g + ) +' + +########################################################################### +# Rules suggested by testcases in section 1: +# +# We should still detect the directory rename even if it wasn't just +# the directory renamed, but the files within it. (see 1b) +# +# If renames split a directory into two or more others, the directory +# with the most renames, "wins" (see 1c). However, see the testcases +# in section 2, plus testcases 3a and 4a. +########################################################################### + + +########################################################################### +# SECTION 2: Split into multiple directories, with equal number of paths +# +# Explore the splitting-a-directory rules a bit; what happens in the +# edge cases? +# +# Note that there is a closely related case of a directory not being +# split on either side of history, but being renamed differently on +# each side. See testcase 8e for that. +########################################################################### + +# Testcase 2a, Directory split into two on one side, with equal numbers of paths +# Commit O: z/{b,c} +# Commit A: y/b, w/c +# Commit B: z/{b,c,d} +# Expected: y/b, w/c, z/d, with warning about z/ -> (y/ vs. w/) conflict +test_expect_success '2a-setup: Directory split into two on one side, with equal numbers of paths' ' + test_create_repo 2a && + ( + cd 2a && + + mkdir z && + echo b >z/b && + echo c >z/c && + git add z && + test_tick && + git commit -m "O" && + + git branch O && + git branch A && + git branch B && + + git checkout A && + mkdir y && + mkdir w && + git mv z/b y/ && + git mv z/c w/ && + test_tick && + git commit -m "A" && + + git checkout B && + echo d >z/d && + git add z/d && + test_tick && + git commit -m "B" + ) +' + +test_expect_success '2a-check: Directory split into two on one side, with equal numbers of paths' ' + ( + cd 2a && + + git checkout A^0 && + + test_must_fail git merge -s recursive B^0 >out && + test_i18ngrep "CONFLICT.*directory rename split" out && + + git ls-files -s >out && + test_line_count = 3 out && + git ls-files -u >out && + test_line_count = 0 out && + git ls-files -o >out && + test_line_count = 1 out && + + git rev-parse >actual \ + :0:y/b :0:w/c :0:z/d && + git rev-parse >expect \ + O:z/b O:z/c B:z/d && + test_cmp expect actual + ) +' + +# Testcase 2b, Directory split into two on one side, with equal numbers of paths +# Commit O: z/{b,c} +# Commit A: y/b, w/c +# Commit B: z/{b,c}, x/d +# Expected: y/b, w/c, x/d; No warning about z/ -> (y/ vs. w/) conflict +test_expect_success '2b-setup: Directory split into two on one side, with equal numbers of paths' ' + test_create_repo 2b && + ( + cd 2b && + + mkdir z && + echo b >z/b && + echo c >z/c && + git add z && + test_tick && + git commit -m "O" && + + git branch O && + git branch A && + git branch B && + + git checkout A && + mkdir y && + mkdir w && + git mv z/b y/ && + git mv z/c w/ && + test_tick && + git commit -m "A" && + + git checkout B && + mkdir x && + echo d >x/d && + git add x/d && + test_tick && + git commit -m "B" + ) +' + +test_expect_success '2b-check: Directory split into two on one side, with equal numbers of paths' ' + ( + cd 2b && + + git checkout A^0 && + + git merge -s recursive B^0 >out && + + git ls-files -s >out && + test_line_count = 3 out && + git ls-files -u >out && + test_line_count = 0 out && + git ls-files -o >out && + test_line_count = 1 out && + + git rev-parse >actual \ + :0:y/b :0:w/c :0:x/d && + git rev-parse >expect \ + O:z/b O:z/c B:x/d && + test_cmp expect actual && + test_i18ngrep ! "CONFLICT.*directory rename split" out + ) +' + +########################################################################### +# Rules suggested by section 2: +# +# None; the rule was already covered in section 1. These testcases are +# here just to make sure the conflict resolution and necessary warning +# messages are handled correctly. +########################################################################### + + +########################################################################### +# SECTION 3: Path in question is the source path for some rename already +# +# Combining cases from Section 1 and trying to handle them could lead to +# directory renaming detection being over-applied. So, this section +# provides some good testcases to check that the implementation doesn't go +# too far. +########################################################################### + +# Testcase 3a, Avoid implicit rename if involved as source on other side +# (Related to testcases 1c, 1f, and 9h) +# Commit O: z/{b,c,d} +# Commit A: z/{b,c,d} (no change) +# Commit B: y/{b,c}, x/d +# Expected: y/{b,c}, x/d +test_expect_success '3a-setup: Avoid implicit rename if involved as source on other side' ' + test_create_repo 3a && + ( + cd 3a && + + mkdir z && + echo b >z/b && + echo c >z/c && + echo d >z/d && + git add z && + test_tick && + git commit -m "O" && + + git branch O && + git branch A && + git branch B && + + git checkout A && + test_tick && + git commit --allow-empty -m "A" && + + git checkout B && + mkdir y && + mkdir x && + git mv z/b y/ && + git mv z/c y/ && + git mv z/d x/ && + rmdir z && + test_tick && + git commit -m "B" + ) +' + +test_expect_success '3a-check: Avoid implicit rename if involved as source on other side' ' + ( + cd 3a && + + git checkout A^0 && + + git merge -s recursive B^0 && + + git ls-files -s >out && + test_line_count = 3 out && + + git rev-parse >actual \ + HEAD:y/b HEAD:y/c HEAD:x/d && + git rev-parse >expect \ + O:z/b O:z/c O:z/d && + test_cmp expect actual + ) +' + +# Testcase 3b, Avoid implicit rename if involved as source on other side +# (Related to testcases 5c and 7c, also kind of 1e and 1f) +# Commit O: z/{b,c,d} +# Commit A: y/{b,c}, x/d +# Commit B: z/{b,c}, w/d +# Expected: y/{b,c}, CONFLICT:(z/d -> x/d vs. w/d) +# NOTE: We're particularly checking that since z/d is already involved as +# a source in a file rename on the same side of history, that we don't +# get it involved in directory rename detection. If it were, we might +# end up with CONFLICT:(z/d -> y/d vs. x/d vs. w/d), i.e. a +# rename/rename/rename(1to3) conflict, which is just weird. +test_expect_success '3b-setup: Avoid implicit rename if involved as source on current side' ' + test_create_repo 3b && + ( + cd 3b && + + mkdir z && + echo b >z/b && + echo c >z/c && + echo d >z/d && + git add z && + test_tick && + git commit -m "O" && + + git branch O && + git branch A && + git branch B && + + git checkout A && + mkdir y && + mkdir x && + git mv z/b y/ && + git mv z/c y/ && + git mv z/d x/ && + rmdir z && + test_tick && + git commit -m "A" && + + git checkout B && + mkdir w && + git mv z/d w/ && + test_tick && + git commit -m "B" + ) +' + +test_expect_success '3b-check: Avoid implicit rename if involved as source on current side' ' + ( + cd 3b && + + git checkout A^0 && + + test_must_fail git merge -s recursive B^0 >out && + test_i18ngrep CONFLICT.*rename/rename.*z/d.*x/d.*w/d out && + test_i18ngrep ! CONFLICT.*rename/rename.*y/d out && + + git ls-files -s >out && + test_line_count = 5 out && + git ls-files -u >out && + test_line_count = 3 out && + git ls-files -o >out && + test_line_count = 1 out && + + git rev-parse >actual \ + :0:y/b :0:y/c :1:z/d :2:x/d :3:w/d && + git rev-parse >expect \ + O:z/b O:z/c O:z/d O:z/d O:z/d && + test_cmp expect actual && + + test_path_is_missing z/d && + git hash-object >actual \ + x/d w/d && + git rev-parse >expect \ + O:z/d O:z/d && + test_cmp expect actual + ) +' + +########################################################################### +# Rules suggested by section 3: +# +# Avoid directory-rename-detection for a path, if that path is the source +# of a rename on either side of a merge. +########################################################################### + + +########################################################################### +# SECTION 4: Partially renamed directory; still exists on both sides of merge +# +# What if we were to attempt to do directory rename detection when someone +# "mostly" moved a directory but still left some files around, or, +# equivalently, fully renamed a directory in one commmit and then recreated +# that directory in a later commit adding some new files and then tried to +# merge? +# +# It's hard to divine user intent in these cases, because you can make an +# argument that, depending on the intermediate history of the side being +# merged, that some users will want files in that directory to +# automatically be detected and renamed, while users with a different +# intermediate history wouldn't want that rename to happen. +# +# I think that it is best to simply not have directory rename detection +# apply to such cases. My reasoning for this is four-fold: (1) it's +# easiest for users in general to figure out what happened if we don't +# apply directory rename detection in any such case, (2) it's an easy rule +# to explain ["We don't do directory rename detection if the directory +# still exists on both sides of the merge"], (3) we can get some hairy +# edge/corner cases that would be really confusing and possibly not even +# representable in the index if we were to even try, and [related to 3] (4) +# attempting to resolve this issue of divining user intent by examining +# intermediate history goes against the spirit of three-way merges and is a +# path towards crazy corner cases that are far more complex than what we're +# already dealing with. +# +# Note that the wording of the rule ("We don't do directory rename +# detection if the directory still exists on both sides of the merge.") +# also excludes "renaming" of a directory into a subdirectory of itself +# (e.g. /some/dir/* -> /some/dir/subdir/*). It may be possible to carve +# out an exception for "renaming"-beneath-itself cases without opening +# weird edge/corner cases for other partial directory renames, but for now +# we are keeping the rule simple. +# +# This section contains a test for a partially-renamed-directory case. +########################################################################### + +# Testcase 4a, Directory split, with original directory still present +# (Related to testcase 1f) +# Commit O: z/{b,c,d,e} +# Commit A: y/{b,c,d}, z/e +# Commit B: z/{b,c,d,e,f} +# Expected: y/{b,c,d}, z/{e,f} +# NOTE: Even though most files from z moved to y, we don't want f to follow. + +test_expect_success '4a-setup: Directory split, with original directory still present' ' + test_create_repo 4a && + ( + cd 4a && + + mkdir z && + echo b >z/b && + echo c >z/c && + echo d >z/d && + echo e >z/e && + git add z && + test_tick && + git commit -m "O" && + + git branch O && + git branch A && + git branch B && + + git checkout A && + mkdir y && + git mv z/b y/ && + git mv z/c y/ && + git mv z/d y/ && + test_tick && + git commit -m "A" && + + git checkout B && + echo f >z/f && + git add z/f && + test_tick && + git commit -m "B" + ) +' + +test_expect_success '4a-check: Directory split, with original directory still present' ' + ( + cd 4a && + + git checkout A^0 && + + git merge -s recursive B^0 && + + git ls-files -s >out && + test_line_count = 5 out && + git ls-files -u >out && + test_line_count = 0 out && + git ls-files -o >out && + test_line_count = 1 out && + + git rev-parse >actual \ + HEAD:y/b HEAD:y/c HEAD:y/d HEAD:z/e HEAD:z/f && + git rev-parse >expect \ + O:z/b O:z/c O:z/d O:z/e B:z/f && + test_cmp expect actual + ) +' + +########################################################################### +# Rules suggested by section 4: +# +# Directory-rename-detection should be turned off for any directories (as +# a source for renames) that exist on both sides of the merge. (The "as +# a source for renames" clarification is due to cases like 1c where +# the target directory exists on both sides and we do want the rename +# detection.) But, sadly, see testcase 8b. +########################################################################### + + +########################################################################### +# SECTION 5: Files/directories in the way of subset of to-be-renamed paths +# +# Implicitly renaming files due to a detected directory rename could run +# into problems if there are files or directories in the way of the paths +# we want to rename. Explore such cases in this section. +########################################################################### + +# Testcase 5a, Merge directories, other side adds files to original and target +# Commit O: z/{b,c}, y/d +# Commit A: z/{b,c,e_1,f}, y/{d,e_2} +# Commit B: y/{b,c,d} +# Expected: z/e_1, y/{b,c,d,e_2,f} + CONFLICT warning +# NOTE: While directory rename detection is active here causing z/f to +# become y/f, we did not apply this for z/e_1 because that would +# give us an add/add conflict for y/e_1 vs y/e_2. This problem with +# this add/add, is that both versions of y/e are from the same side +# of history, giving us no way to represent this conflict in the +# index. + +test_expect_success '5a-setup: Merge directories, other side adds files to original and target' ' + test_create_repo 5a && + ( + cd 5a && + + mkdir z && + echo b >z/b && + echo c >z/c && + mkdir y && + echo d >y/d && + git add z y && + test_tick && + git commit -m "O" && + + git branch O && + git branch A && + git branch B && + + git checkout A && + echo e1 >z/e && + echo f >z/f && + echo e2 >y/e && + git add z/e z/f y/e && + test_tick && + git commit -m "A" && + + git checkout B && + git mv z/b y/ && + git mv z/c y/ && + rmdir z && + test_tick && + git commit -m "B" + ) +' + +test_expect_success '5a-check: Merge directories, other side adds files to original and target' ' + ( + cd 5a && + + git checkout A^0 && + + test_must_fail git merge -s recursive B^0 >out && + test_i18ngrep "CONFLICT.*implicit dir rename" out && + + git ls-files -s >out && + test_line_count = 6 out && + git ls-files -u >out && + test_line_count = 0 out && + git ls-files -o >out && + test_line_count = 1 out && + + git rev-parse >actual \ + :0:y/b :0:y/c :0:y/d :0:y/e :0:z/e :0:y/f && + git rev-parse >expect \ + O:z/b O:z/c O:y/d A:y/e A:z/e A:z/f && + test_cmp expect actual + ) +' + +# Testcase 5b, Rename/delete in order to get add/add/add conflict +# (Related to testcase 8d; these may appear slightly inconsistent to users; +# Also related to testcases 7d and 7e) +# Commit O: z/{b,c,d_1} +# Commit A: y/{b,c,d_2} +# Commit B: z/{b,c,d_1,e}, y/d_3 +# Expected: y/{b,c,e}, CONFLICT(add/add: y/d_2 vs. y/d_3) +# NOTE: If z/d_1 in commit B were to be involved in dir rename detection, as +# we normaly would since z/ is being renamed to y/, then this would be +# a rename/delete (z/d_1 -> y/d_1 vs. deleted) AND an add/add/add +# conflict of y/d_1 vs. y/d_2 vs. y/d_3. Add/add/add is not +# representable in the index, so the existence of y/d_3 needs to +# cause us to bail on directory rename detection for that path, falling +# back to git behavior without the directory rename detection. + +test_expect_success '5b-setup: Rename/delete in order to get add/add/add conflict' ' + test_create_repo 5b && + ( + cd 5b && + + mkdir z && + echo b >z/b && + echo c >z/c && + echo d1 >z/d && + git add z && + test_tick && + git commit -m "O" && + + git branch O && + git branch A && + git branch B && + + git checkout A && + git rm z/d && + git mv z y && + echo d2 >y/d && + git add y/d && + test_tick && + git commit -m "A" && + + git checkout B && + mkdir y && + echo d3 >y/d && + echo e >z/e && + git add y/d z/e && + test_tick && + git commit -m "B" + ) +' + +test_expect_success '5b-check: Rename/delete in order to get add/add/add conflict' ' + ( + cd 5b && + + git checkout A^0 && + + test_must_fail git merge -s recursive B^0 >out && + test_i18ngrep "CONFLICT (add/add).* y/d" out && + + git ls-files -s >out && + test_line_count = 5 out && + git ls-files -u >out && + test_line_count = 2 out && + git ls-files -o >out && + test_line_count = 1 out && + + git rev-parse >actual \ + :0:y/b :0:y/c :0:y/e :2:y/d :3:y/d && + git rev-parse >expect \ + O:z/b O:z/c B:z/e A:y/d B:y/d && + test_cmp expect actual && + + test_must_fail git rev-parse :1:y/d && + test_path_is_file y/d + ) +' + +# Testcase 5c, Transitive rename would cause rename/rename/rename/add/add/add +# (Directory rename detection would result in transitive rename vs. +# rename/rename(1to2) and turn it into a rename/rename(1to3). Further, +# rename paths conflict with separate adds on the other side) +# (Related to testcases 3b and 7c) +# Commit O: z/{b,c}, x/d_1 +# Commit A: y/{b,c,d_2}, w/d_1 +# Commit B: z/{b,c,d_1,e}, w/d_3, y/d_4 +# Expected: A mess, but only a rename/rename(1to2)/add/add mess. Use the +# presence of y/d_4 in B to avoid doing transitive rename of +# x/d_1 -> z/d_1 -> y/d_1, so that the only paths we have at +# y/d are y/d_2 and y/d_4. We still do the move from z/e to y/e, +# though, because it doesn't have anything in the way. + +test_expect_success '5c-setup: Transitive rename would cause rename/rename/rename/add/add/add' ' + test_create_repo 5c && + ( + cd 5c && + + mkdir z && + echo b >z/b && + echo c >z/c && + mkdir x && + echo d1 >x/d && + git add z x && + test_tick && + git commit -m "O" && + + git branch O && + git branch A && + git branch B && + + git checkout A && + git mv z y && + echo d2 >y/d && + git add y/d && + git mv x w && + test_tick && + git commit -m "A" && + + git checkout B && + git mv x/d z/ && + mkdir w && + mkdir y && + echo d3 >w/d && + echo d4 >y/d && + echo e >z/e && + git add w/ y/ z/e && + test_tick && + git commit -m "B" + ) +' + +test_expect_success '5c-check: Transitive rename would cause rename/rename/rename/add/add/add' ' + ( + cd 5c && + + git checkout A^0 && + + test_must_fail git merge -s recursive B^0 >out && + test_i18ngrep "CONFLICT (rename/rename).*x/d.*w/d.*z/d" out && + test_i18ngrep "CONFLICT (add/add).* y/d" out && + + git ls-files -s >out && + test_line_count = 9 out && + git ls-files -u >out && + test_line_count = 6 out && + git ls-files -o >out && + test_line_count = 3 out && + + git rev-parse >actual \ + :0:y/b :0:y/c :0:y/e && + git rev-parse >expect \ + O:z/b O:z/c B:z/e && + test_cmp expect actual && + + test_must_fail git rev-parse :1:y/d && + git rev-parse >actual \ + :2:w/d :3:w/d :1:x/d :2:y/d :3:y/d :3:z/d && + git rev-parse >expect \ + O:x/d B:w/d O:x/d A:y/d B:y/d O:x/d && + test_cmp expect actual && + + git hash-object >actual \ + w/d~HEAD w/d~B^0 z/d && + git rev-parse >expect \ + O:x/d B:w/d O:x/d && + test_cmp expect actual && + test_path_is_missing x/d && + test_path_is_file y/d && + grep -q "<<<<" y/d # conflict markers should be present + ) +' + +# Testcase 5d, Directory/file/file conflict due to directory rename +# Commit O: z/{b,c} +# Commit A: y/{b,c,d_1} +# Commit B: z/{b,c,d_2,f}, y/d/e +# Expected: y/{b,c,d/e,f}, z/d_2, CONFLICT(file/directory), y/d_1~HEAD +# Note: The fact that y/d/ exists in B makes us bail on directory rename +# detection for z/d_2, but that doesn't prevent us from applying the +# directory rename detection for z/f -> y/f. + +test_expect_success '5d-setup: Directory/file/file conflict due to directory rename' ' + test_create_repo 5d && + ( + cd 5d && + + mkdir z && + echo b >z/b && + echo c >z/c && + git add z && + test_tick && + git commit -m "O" && + + git branch O && + git branch A && + git branch B && + + git checkout A && + git mv z y && + echo d1 >y/d && + git add y/d && + test_tick && + git commit -m "A" && + + git checkout B && + mkdir -p y/d && + echo e >y/d/e && + echo d2 >z/d && + echo f >z/f && + git add y/d/e z/d z/f && + test_tick && + git commit -m "B" + ) +' + +test_expect_success '5d-check: Directory/file/file conflict due to directory rename' ' + ( + cd 5d && + + git checkout A^0 && + + test_must_fail git merge -s recursive B^0 >out && + test_i18ngrep "CONFLICT (file/directory).*y/d" out && + + git ls-files -s >out && + test_line_count = 6 out && + git ls-files -u >out && + test_line_count = 1 out && + git ls-files -o >out && + test_line_count = 2 out && + + git rev-parse >actual \ + :0:y/b :0:y/c :0:z/d :0:y/f :2:y/d :0:y/d/e && + git rev-parse >expect \ + O:z/b O:z/c B:z/d B:z/f A:y/d B:y/d/e && + test_cmp expect actual && + + git hash-object y/d~HEAD >actual && + git rev-parse A:y/d >expect && + test_cmp expect actual + ) +' + +########################################################################### +# Rules suggested by section 5: +# +# If a subset of to-be-renamed files have a file or directory in the way, +# "turn off" the directory rename for those specific sub-paths, falling +# back to old handling. But, sadly, see testcases 8a and 8b. +########################################################################### + + +########################################################################### +# SECTION 6: Same side of the merge was the one that did the rename +# +# It may sound obvious that you only want to apply implicit directory +# renames to directories if the _other_ side of history did the renaming. +# If you did make an implementation that didn't explicitly enforce this +# rule, the majority of cases that would fall under this section would +# also be solved by following the rules from the above sections. But +# there are still a few that stick out, so this section covers them just +# to make sure we also get them right. +########################################################################### + +# Testcase 6a, Tricky rename/delete +# Commit O: z/{b,c,d} +# Commit A: z/b +# Commit B: y/{b,c}, z/d +# Expected: y/b, CONFLICT(rename/delete, z/c -> y/c vs. NULL) +# Note: We're just checking here that the rename of z/b and z/c to put +# them under y/ doesn't accidentally catch z/d and make it look like +# it is also involved in a rename/delete conflict. + +test_expect_success '6a-setup: Tricky rename/delete' ' + test_create_repo 6a && + ( + cd 6a && + + mkdir z && + echo b >z/b && + echo c >z/c && + echo d >z/d && + git add z && + test_tick && + git commit -m "O" && + + git branch O && + git branch A && + git branch B && + + git checkout A && + git rm z/c && + git rm z/d && + test_tick && + git commit -m "A" && + + git checkout B && + mkdir y && + git mv z/b y/ && + git mv z/c y/ && + test_tick && + git commit -m "B" + ) +' + +test_expect_success '6a-check: Tricky rename/delete' ' + ( + cd 6a && + + git checkout A^0 && + + test_must_fail git merge -s recursive B^0 >out && + test_i18ngrep "CONFLICT (rename/delete).*z/c.*y/c" out && + + git ls-files -s >out && + test_line_count = 2 out && + git ls-files -u >out && + test_line_count = 1 out && + git ls-files -o >out && + test_line_count = 1 out && + + git rev-parse >actual \ + :0:y/b :3:y/c && + git rev-parse >expect \ + O:z/b O:z/c && + test_cmp expect actual + ) +' + +# Testcase 6b, Same rename done on both sides +# (Related to testcases 6c and 8e) +# Commit O: z/{b,c} +# Commit A: y/{b,c} +# Commit B: y/{b,c}, z/d +# Expected: y/{b,c}, z/d +# Note: If we did directory rename detection here, we'd move z/d into y/, +# but B did that rename and still decided to put the file into z/, +# so we probably shouldn't apply directory rename detection for it. + +test_expect_success '6b-setup: Same rename done on both sides' ' + test_create_repo 6b && + ( + cd 6b && + + mkdir z && + echo b >z/b && + echo c >z/c && + git add z && + test_tick && + git commit -m "O" && + + git branch O && + git branch A && + git branch B && + + git checkout A && + git mv z y && + test_tick && + git commit -m "A" && + + git checkout B && + git mv z y && + mkdir z && + echo d >z/d && + git add z/d && + test_tick && + git commit -m "B" + ) +' + +test_expect_success '6b-check: Same rename done on both sides' ' + ( + cd 6b && + + git checkout A^0 && + + git merge -s recursive B^0 && + + git ls-files -s >out && + test_line_count = 3 out && + git ls-files -u >out && + test_line_count = 0 out && + git ls-files -o >out && + test_line_count = 1 out && + + git rev-parse >actual \ + HEAD:y/b HEAD:y/c HEAD:z/d && + git rev-parse >expect \ + O:z/b O:z/c B:z/d && + test_cmp expect actual + ) +' + +# Testcase 6c, Rename only done on same side +# (Related to testcases 6b and 8e) +# Commit O: z/{b,c} +# Commit A: z/{b,c} (no change) +# Commit B: y/{b,c}, z/d +# Expected: y/{b,c}, z/d +# NOTE: Seems obvious, but just checking that the implementation doesn't +# "accidentally detect a rename" and give us y/{b,c,d}. + +test_expect_success '6c-setup: Rename only done on same side' ' + test_create_repo 6c && + ( + cd 6c && + + mkdir z && + echo b >z/b && + echo c >z/c && + git add z && + test_tick && + git commit -m "O" && + + git branch O && + git branch A && + git branch B && + + git checkout A && + test_tick && + git commit --allow-empty -m "A" && + + git checkout B && + git mv z y && + mkdir z && + echo d >z/d && + git add z/d && + test_tick && + git commit -m "B" + ) +' + +test_expect_success '6c-check: Rename only done on same side' ' + ( + cd 6c && + + git checkout A^0 && + + git merge -s recursive B^0 && + + git ls-files -s >out && + test_line_count = 3 out && + git ls-files -u >out && + test_line_count = 0 out && + git ls-files -o >out && + test_line_count = 1 out && + + git rev-parse >actual \ + HEAD:y/b HEAD:y/c HEAD:z/d && + git rev-parse >expect \ + O:z/b O:z/c B:z/d && + test_cmp expect actual + ) +' + +# Testcase 6d, We don't always want transitive renaming +# (Related to testcase 1c) +# Commit O: z/{b,c}, x/d +# Commit A: z/{b,c}, x/d (no change) +# Commit B: y/{b,c}, z/d +# Expected: y/{b,c}, z/d +# NOTE: Again, this seems obvious but just checking that the implementation +# doesn't "accidentally detect a rename" and give us y/{b,c,d}. + +test_expect_success '6d-setup: We do not always want transitive renaming' ' + test_create_repo 6d && + ( + cd 6d && + + mkdir z && + echo b >z/b && + echo c >z/c && + mkdir x && + echo d >x/d && + git add z x && + test_tick && + git commit -m "O" && + + git branch O && + git branch A && + git branch B && + + git checkout A && + test_tick && + git commit --allow-empty -m "A" && + + git checkout B && + git mv z y && + git mv x z && + test_tick && + git commit -m "B" + ) +' + +test_expect_success '6d-check: We do not always want transitive renaming' ' + ( + cd 6d && + + git checkout A^0 && + + git merge -s recursive B^0 && + + git ls-files -s >out && + test_line_count = 3 out && + git ls-files -u >out && + test_line_count = 0 out && + git ls-files -o >out && + test_line_count = 1 out && + + git rev-parse >actual \ + HEAD:y/b HEAD:y/c HEAD:z/d && + git rev-parse >expect \ + O:z/b O:z/c O:x/d && + test_cmp expect actual + ) +' + +# Testcase 6e, Add/add from one-side +# Commit O: z/{b,c} +# Commit A: z/{b,c} (no change) +# Commit B: y/{b,c,d_1}, z/d_2 +# Expected: y/{b,c,d_1}, z/d_2 +# NOTE: Again, this seems obvious but just checking that the implementation +# doesn't "accidentally detect a rename" and give us y/{b,c} + +# add/add conflict on y/d_1 vs y/d_2. + +test_expect_success '6e-setup: Add/add from one side' ' + test_create_repo 6e && + ( + cd 6e && + + mkdir z && + echo b >z/b && + echo c >z/c && + git add z && + test_tick && + git commit -m "O" && + + git branch O && + git branch A && + git branch B && + + git checkout A && + test_tick && + git commit --allow-empty -m "A" && + + git checkout B && + git mv z y && + echo d1 > y/d && + mkdir z && + echo d2 > z/d && + git add y/d z/d && + test_tick && + git commit -m "B" + ) +' + +test_expect_success '6e-check: Add/add from one side' ' + ( + cd 6e && + + git checkout A^0 && + + git merge -s recursive B^0 && + + git ls-files -s >out && + test_line_count = 4 out && + git ls-files -u >out && + test_line_count = 0 out && + git ls-files -o >out && + test_line_count = 1 out && + + git rev-parse >actual \ + HEAD:y/b HEAD:y/c HEAD:y/d HEAD:z/d && + git rev-parse >expect \ + O:z/b O:z/c B:y/d B:z/d && + test_cmp expect actual + ) +' + +########################################################################### +# Rules suggested by section 6: +# +# Only apply implicit directory renames to directories if the other +# side of history is the one doing the renaming. +########################################################################### + + +########################################################################### +# SECTION 7: More involved Edge/Corner cases +# +# The ruleset we have generated in the above sections seems to provide +# well-defined merges. But can we find edge/corner cases that either (a) +# are harder for users to understand, or (b) have a resolution that is +# non-intuitive or suboptimal? +# +# The testcases in this section dive into cases that I've tried to craft in +# a way to find some that might be surprising to users or difficult for +# them to understand (the next section will look at non-intuitive or +# suboptimal merge results). Some of the testcases are similar to ones +# from past sections, but have been simplified to try to highlight error +# messages using a "modified" path (due to the directory rename). Are +# users okay with these? +# +# In my opinion, testcases that are difficult to understand from this +# section is due to difficulty in the testcase rather than the directory +# renaming (similar to how t6042 and t6036 have difficult resolutions due +# to the problem setup itself being complex). And I don't think the +# error messages are a problem. +# +# On the other hand, the testcases in section 8 worry me slightly more... +########################################################################### + +# Testcase 7a, rename-dir vs. rename-dir (NOT split evenly) PLUS add-other-file +# Commit O: z/{b,c} +# Commit A: y/{b,c} +# Commit B: w/b, x/c, z/d +# Expected: y/d, CONFLICT(rename/rename for both z/b and z/c) +# NOTE: There's a rename of z/ here, y/ has more renames, so z/d -> y/d. + +test_expect_success '7a-setup: rename-dir vs. rename-dir (NOT split evenly) PLUS add-other-file' ' + test_create_repo 7a && + ( + cd 7a && + + mkdir z && + echo b >z/b && + echo c >z/c && + git add z && + test_tick && + git commit -m "O" && + + git branch O && + git branch A && + git branch B && + + git checkout A && + git mv z y && + test_tick && + git commit -m "A" && + + git checkout B && + mkdir w && + mkdir x && + git mv z/b w/ && + git mv z/c x/ && + echo d > z/d && + git add z/d && + test_tick && + git commit -m "B" + ) +' + +test_expect_success '7a-check: rename-dir vs. rename-dir (NOT split evenly) PLUS add-other-file' ' + ( + cd 7a && + + git checkout A^0 && + + test_must_fail git merge -s recursive B^0 >out && + test_i18ngrep "CONFLICT (rename/rename).*z/b.*y/b.*w/b" out && + test_i18ngrep "CONFLICT (rename/rename).*z/c.*y/c.*x/c" out && + + git ls-files -s >out && + test_line_count = 7 out && + git ls-files -u >out && + test_line_count = 6 out && + git ls-files -o >out && + test_line_count = 1 out && + + git rev-parse >actual \ + :1:z/b :2:y/b :3:w/b :1:z/c :2:y/c :3:x/c :0:y/d && + git rev-parse >expect \ + O:z/b O:z/b O:z/b O:z/c O:z/c O:z/c B:z/d && + test_cmp expect actual && + + git hash-object >actual \ + y/b w/b y/c x/c && + git rev-parse >expect \ + O:z/b O:z/b O:z/c O:z/c && + test_cmp expect actual + ) +' + +# Testcase 7b, rename/rename(2to1), but only due to transitive rename +# (Related to testcase 1d) +# Commit O: z/{b,c}, x/d_1, w/d_2 +# Commit A: y/{b,c,d_2}, x/d_1 +# Commit B: z/{b,c,d_1}, w/d_2 +# Expected: y/{b,c}, CONFLICT(rename/rename(2to1): x/d_1, w/d_2 -> y_d) + +test_expect_success '7b-setup: rename/rename(2to1), but only due to transitive rename' ' + test_create_repo 7b && + ( + cd 7b && + + mkdir z && + mkdir x && + mkdir w && + echo b >z/b && + echo c >z/c && + echo d1 > x/d && + echo d2 > w/d && + git add z x w && + test_tick && + git commit -m "O" && + + git branch O && + git branch A && + git branch B && + + git checkout A && + git mv z y && + git mv w/d y/ && + test_tick && + git commit -m "A" && + + git checkout B && + git mv x/d z/ && + rmdir x && + test_tick && + git commit -m "B" + ) +' + +test_expect_success '7b-check: rename/rename(2to1), but only due to transitive rename' ' + ( + cd 7b && + + git checkout A^0 && + + test_must_fail git merge -s recursive B^0 >out && + test_i18ngrep "CONFLICT (rename/rename)" out && + + git ls-files -s >out && + test_line_count = 4 out && + git ls-files -u >out && + test_line_count = 2 out && + git ls-files -o >out && + test_line_count = 3 out && + + git rev-parse >actual \ + :0:y/b :0:y/c :2:y/d :3:y/d && + git rev-parse >expect \ + O:z/b O:z/c O:w/d O:x/d && + test_cmp expect actual && + + test_path_is_missing y/d && + test_path_is_file y/d~HEAD && + test_path_is_file y/d~B^0 && + + git hash-object >actual \ + y/d~HEAD y/d~B^0 && + git rev-parse >expect \ + O:w/d O:x/d && + test_cmp expect actual + ) +' + +# Testcase 7c, rename/rename(1to...2or3); transitive rename may add complexity +# (Related to testcases 3b and 5c) +# Commit O: z/{b,c}, x/d +# Commit A: y/{b,c}, w/d +# Commit B: z/{b,c,d} +# Expected: y/{b,c}, CONFLICT(x/d -> w/d vs. y/d) +# NOTE: z/ was renamed to y/ so we do want to report +# neither CONFLICT(x/d -> w/d vs. z/d) +# nor CONFLiCT x/d -> w/d vs. y/d vs. z/d) + +test_expect_success '7c-setup: rename/rename(1to...2or3); transitive rename may add complexity' ' + test_create_repo 7c && + ( + cd 7c && + + mkdir z && + echo b >z/b && + echo c >z/c && + mkdir x && + echo d >x/d && + git add z x && + test_tick && + git commit -m "O" && + + git branch O && + git branch A && + git branch B && + + git checkout A && + git mv z y && + git mv x w && + test_tick && + git commit -m "A" && + + git checkout B && + git mv x/d z/ && + rmdir x && + test_tick && + git commit -m "B" + ) +' + +test_expect_success '7c-check: rename/rename(1to...2or3); transitive rename may add complexity' ' + ( + cd 7c && + + git checkout A^0 && + + test_must_fail git merge -s recursive B^0 >out && + test_i18ngrep "CONFLICT (rename/rename).*x/d.*w/d.*y/d" out && + + git ls-files -s >out && + test_line_count = 5 out && + git ls-files -u >out && + test_line_count = 3 out && + git ls-files -o >out && + test_line_count = 1 out && + + git rev-parse >actual \ + :0:y/b :0:y/c :1:x/d :2:w/d :3:y/d && + git rev-parse >expect \ + O:z/b O:z/c O:x/d O:x/d O:x/d && + test_cmp expect actual + ) +' + +# Testcase 7d, transitive rename involved in rename/delete; how is it reported? +# (Related somewhat to testcases 5b and 8d) +# Commit O: z/{b,c}, x/d +# Commit A: y/{b,c} +# Commit B: z/{b,c,d} +# Expected: y/{b,c}, CONFLICT(delete x/d vs rename to y/d) +# NOTE: z->y so NOT CONFLICT(delete x/d vs rename to z/d) + +test_expect_success '7d-setup: transitive rename involved in rename/delete; how is it reported?' ' + test_create_repo 7d && + ( + cd 7d && + + mkdir z && + echo b >z/b && + echo c >z/c && + mkdir x && + echo d >x/d && + git add z x && + test_tick && + git commit -m "O" && + + git branch O && + git branch A && + git branch B && + + git checkout A && + git mv z y && + git rm -rf x && + test_tick && + git commit -m "A" && + + git checkout B && + git mv x/d z/ && + rmdir x && + test_tick && + git commit -m "B" + ) +' + +test_expect_success '7d-check: transitive rename involved in rename/delete; how is it reported?' ' + ( + cd 7d && + + git checkout A^0 && + + test_must_fail git merge -s recursive B^0 >out && + test_i18ngrep "CONFLICT (rename/delete).*x/d.*y/d" out && + + git ls-files -s >out && + test_line_count = 3 out && + git ls-files -u >out && + test_line_count = 1 out && + git ls-files -o >out && + test_line_count = 1 out && + + git rev-parse >actual \ + :0:y/b :0:y/c :3:y/d && + git rev-parse >expect \ + O:z/b O:z/c O:x/d && + test_cmp expect actual + ) +' + +# Testcase 7e, transitive rename in rename/delete AND dirs in the way +# (Very similar to 'both rename source and destination involved in D/F conflict' from t6022-merge-rename.sh) +# (Also related to testcases 9c and 9d) +# Commit O: z/{b,c}, x/d_1 +# Commit A: y/{b,c,d/g}, x/d/f +# Commit B: z/{b,c,d_1} +# Expected: rename/delete(x/d_1->y/d_1 vs. None) + D/F conflict on y/d +# y/{b,c,d/g}, y/d_1~B^0, x/d/f + +# NOTE: The main path of interest here is d_1 and where it ends up, but +# this is actually a case that has two potential directory renames +# involved and D/F conflict(s), so it makes sense to walk through +# each step. +# +# Commit A renames z/ -> y/. Thus everything that B adds to z/ +# should be instead moved to y/. This gives us the D/F conflict on +# y/d because x/d_1 -> z/d_1 -> y/d_1 conflicts with y/d/g. +# +# Further, commit B renames x/ -> z/, thus everything A adds to x/ +# should instead be moved to z/...BUT we removed z/ and renamed it +# to y/, so maybe everything should move not from x/ to z/, but +# from x/ to z/ to y/. Doing so might make sense from the logic so +# far, but note that commit A had both an x/ and a y/; it did the +# renaming of z/ to y/ and created x/d/f and it clearly made these +# things separate, so it doesn't make much sense to push these +# together. Doing so is what I'd call a doubly transitive rename; +# see testcases 9c and 9d for further discussion of this issue and +# how it's resolved. + +test_expect_success '7e-setup: transitive rename in rename/delete AND dirs in the way' ' + test_create_repo 7e && + ( + cd 7e && + + mkdir z && + echo b >z/b && + echo c >z/c && + mkdir x && + echo d1 >x/d && + git add z x && + test_tick && + git commit -m "O" && + + git branch O && + git branch A && + git branch B && + + git checkout A && + git mv z y && + git rm x/d && + mkdir -p x/d && + mkdir -p y/d && + echo f >x/d/f && + echo g >y/d/g && + git add x/d/f y/d/g && + test_tick && + git commit -m "A" && + + git checkout B && + git mv x/d z/ && + rmdir x && + test_tick && + git commit -m "B" + ) +' + +test_expect_success '7e-check: transitive rename in rename/delete AND dirs in the way' ' + ( + cd 7e && + + git checkout A^0 && + + test_must_fail git merge -s recursive B^0 >out && + test_i18ngrep "CONFLICT (rename/delete).*x/d.*y/d" out && + + git ls-files -s >out && + test_line_count = 5 out && + git ls-files -u >out && + test_line_count = 1 out && + git ls-files -o >out && + test_line_count = 2 out && + + git rev-parse >actual \ + :0:x/d/f :0:y/d/g :0:y/b :0:y/c :3:y/d && + git rev-parse >expect \ + A:x/d/f A:y/d/g O:z/b O:z/c O:x/d && + test_cmp expect actual && + + git hash-object y/d~B^0 >actual && + git rev-parse O:x/d >expect && + test_cmp expect actual + ) +' + +########################################################################### +# SECTION 8: Suboptimal merges +# +# As alluded to in the last section, the ruleset we have built up for +# detecting directory renames unfortunately has some special cases where it +# results in slightly suboptimal or non-intuitive behavior. This section +# explores these cases. +# +# To be fair, we already had non-intuitive or suboptimal behavior for most +# of these cases in git before introducing implicit directory rename +# detection, but it'd be nice if there was a modified ruleset out there +# that handled these cases a bit better. +########################################################################### + +# Testcase 8a, Dual-directory rename, one into the others' way +# Commit O. x/{a,b}, y/{c,d} +# Commit A. x/{a,b,e}, y/{c,d,f} +# Commit B. y/{a,b}, z/{c,d} +# +# Possible Resolutions: +# w/o dir-rename detection: y/{a,b,f}, z/{c,d}, x/e +# Currently expected: y/{a,b,e,f}, z/{c,d} +# Optimal: y/{a,b,e}, z/{c,d,f} +# +# Note: Both x and y got renamed and it'd be nice to detect both, and we do +# better with directory rename detection than git did without, but the +# simple rule from section 5 prevents me from handling this as optimally as +# we potentially could. + +test_expect_success '8a-setup: Dual-directory rename, one into the others way' ' + test_create_repo 8a && + ( + cd 8a && + + mkdir x && + mkdir y && + echo a >x/a && + echo b >x/b && + echo c >y/c && + echo d >y/d && + git add x y && + test_tick && + git commit -m "O" && + + git branch O && + git branch A && + git branch B && + + git checkout A && + echo e >x/e && + echo f >y/f && + git add x/e y/f && + test_tick && + git commit -m "A" && + + git checkout B && + git mv y z && + git mv x y && + test_tick && + git commit -m "B" + ) +' + +test_expect_success '8a-check: Dual-directory rename, one into the others way' ' + ( + cd 8a && + + git checkout A^0 && + + git merge -s recursive B^0 && + + git ls-files -s >out && + test_line_count = 6 out && + git ls-files -u >out && + test_line_count = 0 out && + git ls-files -o >out && + test_line_count = 1 out && + + git rev-parse >actual \ + HEAD:y/a HEAD:y/b HEAD:y/e HEAD:y/f HEAD:z/c HEAD:z/d && + git rev-parse >expect \ + O:x/a O:x/b A:x/e A:y/f O:y/c O:y/d && + test_cmp expect actual + ) +' + +# Testcase 8b, Dual-directory rename, one into the others' way, with conflicting filenames +# Commit O. x/{a_1,b_1}, y/{a_2,b_2} +# Commit A. x/{a_1,b_1,e_1}, y/{a_2,b_2,e_2} +# Commit B. y/{a_1,b_1}, z/{a_2,b_2} +# +# w/o dir-rename detection: y/{a_1,b_1,e_2}, z/{a_2,b_2}, x/e_1 +# Currently expected: <same> +# Scary: y/{a_1,b_1}, z/{a_2,b_2}, CONFLICT(add/add, e_1 vs. e_2) +# Optimal: y/{a_1,b_1,e_1}, z/{a_2,b_2,e_2} +# +# Note: Very similar to 8a, except instead of 'e' and 'f' in directories x and +# y, both are named 'e'. Without directory rename detection, neither file +# moves directories. Implement directory rename detection suboptimally, and +# you get an add/add conflict, but both files were added in commit A, so this +# is an add/add conflict where one side of history added both files -- +# something we can't represent in the index. Obviously, we'd prefer the last +# resolution, but our previous rules are too coarse to allow it. Using both +# the rules from section 4 and section 5 save us from the Scary resolution, +# making us fall back to pre-directory-rename-detection behavior for both +# e_1 and e_2. + +test_expect_success '8b-setup: Dual-directory rename, one into the others way, with conflicting filenames' ' + test_create_repo 8b && + ( + cd 8b && + + mkdir x && + mkdir y && + echo a1 >x/a && + echo b1 >x/b && + echo a2 >y/a && + echo b2 >y/b && + git add x y && + test_tick && + git commit -m "O" && + + git branch O && + git branch A && + git branch B && + + git checkout A && + echo e1 >x/e && + echo e2 >y/e && + git add x/e y/e && + test_tick && + git commit -m "A" && + + git checkout B && + git mv y z && + git mv x y && + test_tick && + git commit -m "B" + ) +' + +test_expect_success '8b-check: Dual-directory rename, one into the others way, with conflicting filenames' ' + ( + cd 8b && + + git checkout A^0 && + + git merge -s recursive B^0 && + + git ls-files -s >out && + test_line_count = 6 out && + git ls-files -u >out && + test_line_count = 0 out && + git ls-files -o >out && + test_line_count = 1 out && + + git rev-parse >actual \ + HEAD:y/a HEAD:y/b HEAD:z/a HEAD:z/b HEAD:x/e HEAD:y/e && + git rev-parse >expect \ + O:x/a O:x/b O:y/a O:y/b A:x/e A:y/e && + test_cmp expect actual + ) +' + +# Testcase 8c, modify/delete or rename+modify/delete? +# (Related to testcases 5b, 8d, and 9h) +# Commit O: z/{b,c,d} +# Commit A: y/{b,c} +# Commit B: z/{b,c,d_modified,e} +# Expected: y/{b,c,e}, CONFLICT(modify/delete: on z/d) +# +# Note: It could easily be argued that the correct resolution here is +# y/{b,c,e}, CONFLICT(rename/delete: z/d -> y/d vs deleted) +# and that the modifed version of d should be present in y/ after +# the merge, just marked as conflicted. Indeed, I previously did +# argue that. But applying directory renames to the side of +# history where a file is merely modified results in spurious +# rename/rename(1to2) conflicts -- see testcase 9h. See also +# notes in 8d. + +test_expect_success '8c-setup: modify/delete or rename+modify/delete?' ' + test_create_repo 8c && + ( + cd 8c && + + mkdir z && + echo b >z/b && + echo c >z/c && + test_seq 1 10 >z/d && + git add z && + test_tick && + git commit -m "O" && + + git branch O && + git branch A && + git branch B && + + git checkout A && + git rm z/d && + git mv z y && + test_tick && + git commit -m "A" && + + git checkout B && + echo 11 >z/d && + test_chmod +x z/d && + echo e >z/e && + git add z/d z/e && + test_tick && + git commit -m "B" + ) +' + +test_expect_success '8c-check: modify/delete or rename+modify/delete' ' + ( + cd 8c && + + git checkout A^0 && + + test_must_fail git merge -s recursive B^0 >out && + test_i18ngrep "CONFLICT (modify/delete).* z/d" out && + + git ls-files -s >out && + test_line_count = 5 out && + git ls-files -u >out && + test_line_count = 2 out && + git ls-files -o >out && + test_line_count = 1 out && + + git rev-parse >actual \ + :0:y/b :0:y/c :0:y/e :1:z/d :3:z/d && + git rev-parse >expect \ + O:z/b O:z/c B:z/e O:z/d B:z/d && + test_cmp expect actual && + + test_must_fail git rev-parse :2:z/d && + git ls-files -s z/d | grep ^100755 && + test_path_is_file z/d && + test_path_is_missing y/d + ) +' + +# Testcase 8d, rename/delete...or not? +# (Related to testcase 5b; these may appear slightly inconsistent to users; +# Also related to testcases 7d and 7e) +# Commit O: z/{b,c,d} +# Commit A: y/{b,c} +# Commit B: z/{b,c,d,e} +# Expected: y/{b,c,e} +# +# Note: It would also be somewhat reasonable to resolve this as +# y/{b,c,e}, CONFLICT(rename/delete: x/d -> y/d or deleted) +# +# In this case, I'm leaning towards: commit A was the one that deleted z/d +# and it did the rename of z to y, so the two "conflicts" (rename vs. +# delete) are both coming from commit A, which is illogical. Conflicts +# during merging are supposed to be about opposite sides doing things +# differently. + +test_expect_success '8d-setup: rename/delete...or not?' ' + test_create_repo 8d && + ( + cd 8d && + + mkdir z && + echo b >z/b && + echo c >z/c && + test_seq 1 10 >z/d && + git add z && + test_tick && + git commit -m "O" && + + git branch O && + git branch A && + git branch B && + + git checkout A && + git rm z/d && + git mv z y && + test_tick && + git commit -m "A" && + + git checkout B && + echo e >z/e && + git add z/e && + test_tick && + git commit -m "B" + ) +' + +test_expect_success '8d-check: rename/delete...or not?' ' + ( + cd 8d && + + git checkout A^0 && + + git merge -s recursive B^0 && + + git ls-files -s >out && + test_line_count = 3 out && + + git rev-parse >actual \ + HEAD:y/b HEAD:y/c HEAD:y/e && + git rev-parse >expect \ + O:z/b O:z/c B:z/e && + test_cmp expect actual + ) +' + +# Testcase 8e, Both sides rename, one side adds to original directory +# Commit O: z/{b,c} +# Commit A: y/{b,c} +# Commit B: w/{b,c}, z/d +# +# Possible Resolutions: +# w/o dir-rename detection: z/d, CONFLICT(z/b -> y/b vs. w/b), +# CONFLICT(z/c -> y/c vs. w/c) +# Currently expected: y/d, CONFLICT(z/b -> y/b vs. w/b), +# CONFLICT(z/c -> y/c vs. w/c) +# Optimal: ?? +# +# Notes: In commit A, directory z got renamed to y. In commit B, directory z +# did NOT get renamed; the directory is still present; instead it is +# considered to have just renamed a subset of paths in directory z +# elsewhere. Therefore, the directory rename done in commit A to z/ +# applies to z/d and maps it to y/d. +# +# It's possible that users would get confused about this, but what +# should we do instead? Silently leaving at z/d seems just as bad or +# maybe even worse. Perhaps we could print a big warning about z/d +# and how we're moving to y/d in this case, but when I started thinking +# about the ramifications of doing that, I didn't know how to rule out +# that opening other weird edge and corner cases so I just punted. + +test_expect_success '8e-setup: Both sides rename, one side adds to original directory' ' + test_create_repo 8e && + ( + cd 8e && + + mkdir z && + echo b >z/b && + echo c >z/c && + git add z && + test_tick && + git commit -m "O" && + + git branch O && + git branch A && + git branch B && + + git checkout A && + git mv z y && + test_tick && + git commit -m "A" && + + git checkout B && + git mv z w && + mkdir z && + echo d >z/d && + git add z/d && + test_tick && + git commit -m "B" + ) +' + +test_expect_success '8e-check: Both sides rename, one side adds to original directory' ' + ( + cd 8e && + + git checkout A^0 && + + test_must_fail git merge -s recursive B^0 >out 2>err && + test_i18ngrep CONFLICT.*rename/rename.*z/c.*y/c.*w/c out && + test_i18ngrep CONFLICT.*rename/rename.*z/b.*y/b.*w/b out && + + git ls-files -s >out && + test_line_count = 7 out && + git ls-files -u >out && + test_line_count = 6 out && + git ls-files -o >out && + test_line_count = 2 out && + + git rev-parse >actual \ + :1:z/b :2:y/b :3:w/b :1:z/c :2:y/c :3:w/c :0:y/d && + git rev-parse >expect \ + O:z/b O:z/b O:z/b O:z/c O:z/c O:z/c B:z/d && + test_cmp expect actual && + + git hash-object >actual \ + y/b w/b y/c w/c && + git rev-parse >expect \ + O:z/b O:z/b O:z/c O:z/c && + test_cmp expect actual && + + test_path_is_missing z/b && + test_path_is_missing z/c + ) +' + +########################################################################### +# SECTION 9: Other testcases +# +# This section consists of miscellaneous testcases I thought of during +# the implementation which round out the testing. +########################################################################### + +# Testcase 9a, Inner renamed directory within outer renamed directory +# (Related to testcase 1f) +# Commit O: z/{b,c,d/{e,f,g}} +# Commit A: y/{b,c}, x/w/{e,f,g} +# Commit B: z/{b,c,d/{e,f,g,h},i} +# Expected: y/{b,c,i}, x/w/{e,f,g,h} +# NOTE: The only reason this one is interesting is because when a directory +# is split into multiple other directories, we determine by the weight +# of which one had the most paths going to it. A naive implementation +# of that could take the new file in commit B at z/i to x/w/i or x/i. + +test_expect_success '9a-setup: Inner renamed directory within outer renamed directory' ' + test_create_repo 9a && + ( + cd 9a && + + mkdir -p z/d && + echo b >z/b && + echo c >z/c && + echo e >z/d/e && + echo f >z/d/f && + echo g >z/d/g && + git add z && + test_tick && + git commit -m "O" && + + git branch O && + git branch A && + git branch B && + + git checkout A && + mkdir x && + git mv z/d x/w && + git mv z y && + test_tick && + git commit -m "A" && + + git checkout B && + echo h >z/d/h && + echo i >z/i && + git add z && + test_tick && + git commit -m "B" + ) +' + +test_expect_success '9a-check: Inner renamed directory within outer renamed directory' ' + ( + cd 9a && + + git checkout A^0 && + + git merge -s recursive B^0 && + + git ls-files -s >out && + test_line_count = 7 out && + git ls-files -u >out && + test_line_count = 0 out && + git ls-files -o >out && + test_line_count = 1 out && + + git rev-parse >actual \ + HEAD:y/b HEAD:y/c HEAD:y/i && + git rev-parse >expect \ + O:z/b O:z/c B:z/i && + test_cmp expect actual && + + git rev-parse >actual \ + HEAD:x/w/e HEAD:x/w/f HEAD:x/w/g HEAD:x/w/h && + git rev-parse >expect \ + O:z/d/e O:z/d/f O:z/d/g B:z/d/h && + test_cmp expect actual + ) +' + +# Testcase 9b, Transitive rename with content merge +# (Related to testcase 1c) +# Commit O: z/{b,c}, x/d_1 +# Commit A: y/{b,c}, x/d_2 +# Commit B: z/{b,c,d_3} +# Expected: y/{b,c,d_merged} + +test_expect_success '9b-setup: Transitive rename with content merge' ' + test_create_repo 9b && + ( + cd 9b && + + mkdir z && + echo b >z/b && + echo c >z/c && + mkdir x && + test_seq 1 10 >x/d && + git add z x && + test_tick && + git commit -m "O" && + + git branch O && + git branch A && + git branch B && + + git checkout A && + git mv z y && + test_seq 1 11 >x/d && + git add x/d && + test_tick && + git commit -m "A" && + + git checkout B && + test_seq 0 10 >x/d && + git mv x/d z/d && + git add z/d && + test_tick && + git commit -m "B" + ) +' + +test_expect_success '9b-check: Transitive rename with content merge' ' + ( + cd 9b && + + git checkout A^0 && + + git merge -s recursive B^0 && + + git ls-files -s >out && + test_line_count = 3 out && + + test_seq 0 11 >expected && + test_cmp expected y/d && + git add expected && + git rev-parse >actual \ + HEAD:y/b HEAD:y/c HEAD:y/d && + git rev-parse >expect \ + O:z/b O:z/c :0:expected && + test_cmp expect actual && + test_must_fail git rev-parse HEAD:x/d && + test_must_fail git rev-parse HEAD:z/d && + test_path_is_missing z/d && + + test $(git rev-parse HEAD:y/d) != $(git rev-parse O:x/d) && + test $(git rev-parse HEAD:y/d) != $(git rev-parse A:x/d) && + test $(git rev-parse HEAD:y/d) != $(git rev-parse B:z/d) + ) +' + +# Testcase 9c, Doubly transitive rename? +# (Related to testcase 1c, 7e, and 9d) +# Commit O: z/{b,c}, x/{d,e}, w/f +# Commit A: y/{b,c}, x/{d,e,f,g} +# Commit B: z/{b,c,d,e}, w/f +# Expected: y/{b,c,d,e}, x/{f,g} +# +# NOTE: x/f and x/g may be slightly confusing here. The rename from w/f to +# x/f is clear. Let's look beyond that. Here's the logic: +# Commit B renamed x/ -> z/ +# Commit A renamed z/ -> y/ +# So, we could possibly further rename x/f to z/f to y/f, a doubly +# transient rename. However, where does it end? We can chain these +# indefinitely (see testcase 9d). What if there is a D/F conflict +# at z/f/ or y/f/? Or just another file conflict at one of those +# paths? In the case of an N-long chain of transient renamings, +# where do we "abort" the rename at? Can the user make sense of +# the resulting conflict and resolve it? +# +# To avoid this confusion I use the simple rule that if the other side +# of history did a directory rename to a path that your side renamed +# away, then ignore that particular rename from the other side of +# history for any implicit directory renames. + +test_expect_success '9c-setup: Doubly transitive rename?' ' + test_create_repo 9c && + ( + cd 9c && + + mkdir z && + echo b >z/b && + echo c >z/c && + mkdir x && + echo d >x/d && + echo e >x/e && + mkdir w && + echo f >w/f && + git add z x w && + test_tick && + git commit -m "O" && + + git branch O && + git branch A && + git branch B && + + git checkout A && + git mv z y && + git mv w/f x/ && + echo g >x/g && + git add x/g && + test_tick && + git commit -m "A" && + + git checkout B && + git mv x/d z/d && + git mv x/e z/e && + test_tick && + git commit -m "B" + ) +' + +test_expect_success '9c-check: Doubly transitive rename?' ' + ( + cd 9c && + + git checkout A^0 && + + git merge -s recursive B^0 >out && + test_i18ngrep "WARNING: Avoiding applying x -> z rename to x/f" out && + + git ls-files -s >out && + test_line_count = 6 out && + git ls-files -o >out && + test_line_count = 1 out && + + git rev-parse >actual \ + HEAD:y/b HEAD:y/c HEAD:y/d HEAD:y/e HEAD:x/f HEAD:x/g && + git rev-parse >expect \ + O:z/b O:z/c O:x/d O:x/e O:w/f A:x/g && + test_cmp expect actual + ) +' + +# Testcase 9d, N-fold transitive rename? +# (Related to testcase 9c...and 1c and 7e) +# Commit O: z/a, y/b, x/c, w/d, v/e, u/f +# Commit A: y/{a,b}, w/{c,d}, u/{e,f} +# Commit B: z/{a,t}, x/{b,c}, v/{d,e}, u/f +# Expected: <see NOTE first> +# +# NOTE: z/ -> y/ (in commit A) +# y/ -> x/ (in commit B) +# x/ -> w/ (in commit A) +# w/ -> v/ (in commit B) +# v/ -> u/ (in commit A) +# So, if we add a file to z, say z/t, where should it end up? In u? +# What if there's another file or directory named 't' in one of the +# intervening directories and/or in u itself? Also, shouldn't the +# same logic that places 't' in u/ also move ALL other files to u/? +# What if there are file or directory conflicts in any of them? If +# we attempted to do N-way (N-fold? N-ary? N-uple?) transitive renames +# like this, would the user have any hope of understanding any +# conflicts or how their working tree ended up? I think not, so I'm +# ruling out N-ary transitive renames for N>1. +# +# Therefore our expected result is: +# z/t, y/a, x/b, w/c, u/d, u/e, u/f +# The reason that v/d DOES get transitively renamed to u/d is that u/ isn't +# renamed somewhere. A slightly sub-optimal result, but it uses fairly +# simple rules that are consistent with what we need for all the other +# testcases and simplifies things for the user. + +test_expect_success '9d-setup: N-way transitive rename?' ' + test_create_repo 9d && + ( + cd 9d && + + mkdir z y x w v u && + echo a >z/a && + echo b >y/b && + echo c >x/c && + echo d >w/d && + echo e >v/e && + echo f >u/f && + git add z y x w v u && + test_tick && + git commit -m "O" && + + git branch O && + git branch A && + git branch B && + + git checkout A && + git mv z/a y/ && + git mv x/c w/ && + git mv v/e u/ && + test_tick && + git commit -m "A" && + + git checkout B && + echo t >z/t && + git mv y/b x/ && + git mv w/d v/ && + git add z/t && + test_tick && + git commit -m "B" + ) +' + +test_expect_success '9d-check: N-way transitive rename?' ' + ( + cd 9d && + + git checkout A^0 && + + git merge -s recursive B^0 >out && + test_i18ngrep "WARNING: Avoiding applying z -> y rename to z/t" out && + test_i18ngrep "WARNING: Avoiding applying y -> x rename to y/a" out && + test_i18ngrep "WARNING: Avoiding applying x -> w rename to x/b" out && + test_i18ngrep "WARNING: Avoiding applying w -> v rename to w/c" out && + + git ls-files -s >out && + test_line_count = 7 out && + git ls-files -o >out && + test_line_count = 1 out && + + git rev-parse >actual \ + HEAD:z/t \ + HEAD:y/a HEAD:x/b HEAD:w/c \ + HEAD:u/d HEAD:u/e HEAD:u/f && + git rev-parse >expect \ + B:z/t \ + O:z/a O:y/b O:x/c \ + O:w/d O:v/e A:u/f && + test_cmp expect actual + ) +' + +# Testcase 9e, N-to-1 whammo +# (Related to testcase 9c...and 1c and 7e) +# Commit O: dir1/{a,b}, dir2/{d,e}, dir3/{g,h}, dirN/{j,k} +# Commit A: dir1/{a,b,c,yo}, dir2/{d,e,f,yo}, dir3/{g,h,i,yo}, dirN/{j,k,l,yo} +# Commit B: combined/{a,b,d,e,g,h,j,k} +# Expected: combined/{a,b,c,d,e,f,g,h,i,j,k,l}, CONFLICT(Nto1) warnings, +# dir1/yo, dir2/yo, dir3/yo, dirN/yo + +test_expect_success '9e-setup: N-to-1 whammo' ' + test_create_repo 9e && + ( + cd 9e && + + mkdir dir1 dir2 dir3 dirN && + echo a >dir1/a && + echo b >dir1/b && + echo d >dir2/d && + echo e >dir2/e && + echo g >dir3/g && + echo h >dir3/h && + echo j >dirN/j && + echo k >dirN/k && + git add dir* && + test_tick && + git commit -m "O" && + + git branch O && + git branch A && + git branch B && + + git checkout A && + echo c >dir1/c && + echo yo >dir1/yo && + echo f >dir2/f && + echo yo >dir2/yo && + echo i >dir3/i && + echo yo >dir3/yo && + echo l >dirN/l && + echo yo >dirN/yo && + git add dir* && + test_tick && + git commit -m "A" && + + git checkout B && + git mv dir1 combined && + git mv dir2/* combined/ && + git mv dir3/* combined/ && + git mv dirN/* combined/ && + test_tick && + git commit -m "B" + ) +' + +test_expect_success C_LOCALE_OUTPUT '9e-check: N-to-1 whammo' ' + ( + cd 9e && + + git checkout A^0 && + + test_must_fail git merge -s recursive B^0 >out && + grep "CONFLICT (implicit dir rename): Cannot map more than one path to combined/yo" out >error_line && + grep -q dir1/yo error_line && + grep -q dir2/yo error_line && + grep -q dir3/yo error_line && + grep -q dirN/yo error_line && + + git ls-files -s >out && + test_line_count = 16 out && + git ls-files -u >out && + test_line_count = 0 out && + git ls-files -o >out && + test_line_count = 2 out && + + git rev-parse >actual \ + :0:combined/a :0:combined/b :0:combined/c \ + :0:combined/d :0:combined/e :0:combined/f \ + :0:combined/g :0:combined/h :0:combined/i \ + :0:combined/j :0:combined/k :0:combined/l && + git rev-parse >expect \ + O:dir1/a O:dir1/b A:dir1/c \ + O:dir2/d O:dir2/e A:dir2/f \ + O:dir3/g O:dir3/h A:dir3/i \ + O:dirN/j O:dirN/k A:dirN/l && + test_cmp expect actual && + + git rev-parse >actual \ + :0:dir1/yo :0:dir2/yo :0:dir3/yo :0:dirN/yo && + git rev-parse >expect \ + A:dir1/yo A:dir2/yo A:dir3/yo A:dirN/yo && + test_cmp expect actual + ) +' + +# Testcase 9f, Renamed directory that only contained immediate subdirs +# (Related to testcases 1e & 9g) +# Commit O: goal/{a,b}/$more_files +# Commit A: priority/{a,b}/$more_files +# Commit B: goal/{a,b}/$more_files, goal/c +# Expected: priority/{a,b}/$more_files, priority/c + +test_expect_success '9f-setup: Renamed directory that only contained immediate subdirs' ' + test_create_repo 9f && + ( + cd 9f && + + mkdir -p goal/a && + mkdir -p goal/b && + echo foo >goal/a/foo && + echo bar >goal/b/bar && + echo baz >goal/b/baz && + git add goal && + test_tick && + git commit -m "O" && + + git branch O && + git branch A && + git branch B && + + git checkout A && + git mv goal/ priority && + test_tick && + git commit -m "A" && + + git checkout B && + echo c >goal/c && + git add goal/c && + test_tick && + git commit -m "B" + ) +' + +test_expect_success '9f-check: Renamed directory that only contained immediate subdirs' ' + ( + cd 9f && + + git checkout A^0 && + + git merge -s recursive B^0 && + + git ls-files -s >out && + test_line_count = 4 out && + + git rev-parse >actual \ + HEAD:priority/a/foo \ + HEAD:priority/b/bar \ + HEAD:priority/b/baz \ + HEAD:priority/c && + git rev-parse >expect \ + O:goal/a/foo \ + O:goal/b/bar \ + O:goal/b/baz \ + B:goal/c && + test_cmp expect actual && + test_must_fail git rev-parse HEAD:goal/c + ) +' + +# Testcase 9g, Renamed directory that only contained immediate subdirs, immediate subdirs renamed +# (Related to testcases 1e & 9f) +# Commit O: goal/{a,b}/$more_files +# Commit A: priority/{alpha,bravo}/$more_files +# Commit B: goal/{a,b}/$more_files, goal/c +# Expected: priority/{alpha,bravo}/$more_files, priority/c + +test_expect_success '9g-setup: Renamed directory that only contained immediate subdirs, immediate subdirs renamed' ' + test_create_repo 9g && + ( + cd 9g && + + mkdir -p goal/a && + mkdir -p goal/b && + echo foo >goal/a/foo && + echo bar >goal/b/bar && + echo baz >goal/b/baz && + git add goal && + test_tick && + git commit -m "O" && + + git branch O && + git branch A && + git branch B && + + git checkout A && + mkdir priority && + git mv goal/a/ priority/alpha && + git mv goal/b/ priority/beta && + rmdir goal/ && + test_tick && + git commit -m "A" && + + git checkout B && + echo c >goal/c && + git add goal/c && + test_tick && + git commit -m "B" + ) +' + +test_expect_failure '9g-check: Renamed directory that only contained immediate subdirs, immediate subdirs renamed' ' + ( + cd 9g && + + git checkout A^0 && + + git merge -s recursive B^0 && + + git ls-files -s >out && + test_line_count = 4 out && + + git rev-parse >actual \ + HEAD:priority/alpha/foo \ + HEAD:priority/beta/bar \ + HEAD:priority/beta/baz \ + HEAD:priority/c && + git rev-parse >expect \ + O:goal/a/foo \ + O:goal/b/bar \ + O:goal/b/baz \ + B:goal/c && + test_cmp expect actual && + test_must_fail git rev-parse HEAD:goal/c + ) +' + +# Testcase 9h, Avoid implicit rename if involved as source on other side +# (Extremely closely related to testcase 3a) +# Commit O: z/{b,c,d_1} +# Commit A: z/{b,c,d_2} +# Commit B: y/{b,c}, x/d_1 +# Expected: y/{b,c}, x/d_2 +# NOTE: If we applied the z/ -> y/ rename to z/d, then we'd end up with +# a rename/rename(1to2) conflict (z/d -> y/d vs. x/d) +test_expect_success '9h-setup: Avoid dir rename on merely modified path' ' + test_create_repo 9h && + ( + cd 9h && + + mkdir z && + echo b >z/b && + echo c >z/c && + printf "1\n2\n3\n4\n5\n6\n7\n8\nd\n" >z/d && + git add z && + test_tick && + git commit -m "O" && + + git branch O && + git branch A && + git branch B && + + git checkout A && + test_tick && + echo more >>z/d && + git add z/d && + git commit -m "A" && + + git checkout B && + mkdir y && + mkdir x && + git mv z/b y/ && + git mv z/c y/ && + git mv z/d x/ && + rmdir z && + test_tick && + git commit -m "B" + ) +' + +test_expect_success '9h-check: Avoid dir rename on merely modified path' ' + ( + cd 9h && + + git checkout A^0 && + + git merge -s recursive B^0 && + + git ls-files -s >out && + test_line_count = 3 out && + + git rev-parse >actual \ + HEAD:y/b HEAD:y/c HEAD:x/d && + git rev-parse >expect \ + O:z/b O:z/c A:z/d && + test_cmp expect actual + ) +' + +########################################################################### +# Rules suggested by section 9: +# +# If the other side of history did a directory rename to a path that your +# side renamed away, then ignore that particular rename from the other +# side of history for any implicit directory renames. +########################################################################### + +########################################################################### +# SECTION 10: Handling untracked files +# +# unpack_trees(), upon which the recursive merge algorithm is based, aborts +# the operation if untracked or dirty files would be deleted or overwritten +# by the merge. Unfortunately, unpack_trees() does not understand renames, +# and if it doesn't abort, then it muddies up the working directory before +# we even get to the point of detecting renames, so we need some special +# handling, at least in the case of directory renames. +########################################################################### + +# Testcase 10a, Overwrite untracked: normal rename/delete +# Commit O: z/{b,c_1} +# Commit A: z/b + untracked z/c + untracked z/d +# Commit B: z/{b,d_1} +# Expected: Aborted Merge + +# ERROR_MSG(untracked working tree files would be overwritten by merge) + +test_expect_success '10a-setup: Overwrite untracked with normal rename/delete' ' + test_create_repo 10a && + ( + cd 10a && + + mkdir z && + echo b >z/b && + echo c >z/c && + git add z && + test_tick && + git commit -m "O" && + + git branch O && + git branch A && + git branch B && + + git checkout A && + git rm z/c && + test_tick && + git commit -m "A" && + + git checkout B && + git mv z/c z/d && + test_tick && + git commit -m "B" + ) +' + +test_expect_success '10a-check: Overwrite untracked with normal rename/delete' ' + ( + cd 10a && + + git checkout A^0 && + echo very >z/c && + echo important >z/d && + + test_must_fail git merge -s recursive B^0 >out 2>err && + test_i18ngrep "The following untracked working tree files would be overwritten by merge" err && + + git ls-files -s >out && + test_line_count = 1 out && + git ls-files -o >out && + test_line_count = 4 out && + + echo very >expect && + test_cmp expect z/c && + + echo important >expect && + test_cmp expect z/d && + + git rev-parse HEAD:z/b >actual && + git rev-parse O:z/b >expect && + test_cmp expect actual + ) +' + +# Testcase 10b, Overwrite untracked: dir rename + delete +# Commit O: z/{b,c_1} +# Commit A: y/b + untracked y/{c,d,e} +# Commit B: z/{b,d_1,e} +# Expected: Failed Merge; y/b + untracked y/c + untracked y/d on disk + +# z/c_1 -> z/d_1 rename recorded at stage 3 for y/d + +# ERROR_MSG(refusing to lose untracked file at 'y/d') + +test_expect_success '10b-setup: Overwrite untracked with dir rename + delete' ' + test_create_repo 10b && + ( + cd 10b && + + mkdir z && + echo b >z/b && + echo c >z/c && + git add z && + test_tick && + git commit -m "O" && + + git branch O && + git branch A && + git branch B && + + git checkout A && + git rm z/c && + git mv z/ y/ && + test_tick && + git commit -m "A" && + + git checkout B && + git mv z/c z/d && + echo e >z/e && + git add z/e && + test_tick && + git commit -m "B" + ) +' + +test_expect_success '10b-check: Overwrite untracked with dir rename + delete' ' + ( + cd 10b && + + git checkout A^0 && + echo very >y/c && + echo important >y/d && + echo contents >y/e && + + test_must_fail git merge -s recursive B^0 >out 2>err && + test_i18ngrep "CONFLICT (rename/delete).*Version B\^0 of y/d left in tree at y/d~B\^0" out && + test_i18ngrep "Error: Refusing to lose untracked file at y/e; writing to y/e~B\^0 instead" out && + + git ls-files -s >out && + test_line_count = 3 out && + git ls-files -u >out && + test_line_count = 2 out && + git ls-files -o >out && + test_line_count = 5 out && + + git rev-parse >actual \ + :0:y/b :3:y/d :3:y/e && + git rev-parse >expect \ + O:z/b O:z/c B:z/e && + test_cmp expect actual && + + echo very >expect && + test_cmp expect y/c && + + echo important >expect && + test_cmp expect y/d && + + echo contents >expect && + test_cmp expect y/e + ) +' + +# Testcase 10c, Overwrite untracked: dir rename/rename(1to2) +# Commit O: z/{a,b}, x/{c,d} +# Commit A: y/{a,b}, w/c, x/d + different untracked y/c +# Commit B: z/{a,b,c}, x/d +# Expected: Failed Merge; y/{a,b} + x/d + untracked y/c + +# CONFLICT(rename/rename) x/c -> w/c vs y/c + +# y/c~B^0 + +# ERROR_MSG(Refusing to lose untracked file at y/c) + +test_expect_success '10c-setup: Overwrite untracked with dir rename/rename(1to2)' ' + test_create_repo 10c && + ( + cd 10c && + + mkdir z x && + echo a >z/a && + echo b >z/b && + echo c >x/c && + echo d >x/d && + git add z x && + test_tick && + git commit -m "O" && + + git branch O && + git branch A && + git branch B && + + git checkout A && + mkdir w && + git mv x/c w/c && + git mv z/ y/ && + test_tick && + git commit -m "A" && + + git checkout B && + git mv x/c z/ && + test_tick && + git commit -m "B" + ) +' + +test_expect_success '10c-check: Overwrite untracked with dir rename/rename(1to2)' ' + ( + cd 10c && + + git checkout A^0 && + echo important >y/c && + + test_must_fail git merge -s recursive B^0 >out 2>err && + test_i18ngrep "CONFLICT (rename/rename)" out && + test_i18ngrep "Refusing to lose untracked file at y/c; adding as y/c~B\^0 instead" out && + + git ls-files -s >out && + test_line_count = 6 out && + git ls-files -u >out && + test_line_count = 3 out && + git ls-files -o >out && + test_line_count = 3 out && + + git rev-parse >actual \ + :0:y/a :0:y/b :0:x/d :1:x/c :2:w/c :3:y/c && + git rev-parse >expect \ + O:z/a O:z/b O:x/d O:x/c O:x/c O:x/c && + test_cmp expect actual && + + git hash-object y/c~B^0 >actual && + git rev-parse O:x/c >expect && + test_cmp expect actual && + + echo important >expect && + test_cmp expect y/c + ) +' + +# Testcase 10d, Delete untracked w/ dir rename/rename(2to1) +# Commit O: z/{a,b,c_1}, x/{d,e,f_2} +# Commit A: y/{a,b}, x/{d,e,f_2,wham_1} + untracked y/wham +# Commit B: z/{a,b,c_1,wham_2}, y/{d,e} +# Expected: Failed Merge; y/{a,b,d,e} + untracked y/{wham,wham~B^0,wham~HEAD}+ +# CONFLICT(rename/rename) z/c_1 vs x/f_2 -> y/wham +# ERROR_MSG(Refusing to lose untracked file at y/wham) + +test_expect_success '10d-setup: Delete untracked with dir rename/rename(2to1)' ' + test_create_repo 10d && + ( + cd 10d && + + mkdir z x && + echo a >z/a && + echo b >z/b && + echo c >z/c && + echo d >x/d && + echo e >x/e && + echo f >x/f && + git add z x && + test_tick && + git commit -m "O" && + + git branch O && + git branch A && + git branch B && + + git checkout A && + git mv z/c x/wham && + git mv z/ y/ && + test_tick && + git commit -m "A" && + + git checkout B && + git mv x/f z/wham && + git mv x/ y/ && + test_tick && + git commit -m "B" + ) +' + +test_expect_success '10d-check: Delete untracked with dir rename/rename(2to1)' ' + ( + cd 10d && + + git checkout A^0 && + echo important >y/wham && + + test_must_fail git merge -s recursive B^0 >out 2>err && + test_i18ngrep "CONFLICT (rename/rename)" out && + test_i18ngrep "Refusing to lose untracked file at y/wham" out && + + git ls-files -s >out && + test_line_count = 6 out && + git ls-files -u >out && + test_line_count = 2 out && + git ls-files -o >out && + test_line_count = 4 out && + + git rev-parse >actual \ + :0:y/a :0:y/b :0:y/d :0:y/e :2:y/wham :3:y/wham && + git rev-parse >expect \ + O:z/a O:z/b O:x/d O:x/e O:z/c O:x/f && + test_cmp expect actual && + + test_must_fail git rev-parse :1:y/wham && + + echo important >expect && + test_cmp expect y/wham && + + git hash-object >actual \ + y/wham~B^0 y/wham~HEAD && + git rev-parse >expect \ + O:x/f O:z/c && + test_cmp expect actual + ) +' + +# Testcase 10e, Does git complain about untracked file that's not in the way? +# Commit O: z/{a,b} +# Commit A: y/{a,b} + untracked z/c +# Commit B: z/{a,b,c} +# Expected: y/{a,b,c} + untracked z/c + +test_expect_success '10e-setup: Does git complain about untracked file that is not really in the way?' ' + test_create_repo 10e && + ( + cd 10e && + + mkdir z && + echo a >z/a && + echo b >z/b && + git add z && + test_tick && + git commit -m "O" && + + git branch O && + git branch A && + git branch B && + + git checkout A && + git mv z/ y/ && + test_tick && + git commit -m "A" && + + git checkout B && + echo c >z/c && + git add z/c && + test_tick && + git commit -m "B" + ) +' + +test_expect_failure '10e-check: Does git complain about untracked file that is not really in the way?' ' + ( + cd 10e && + + git checkout A^0 && + mkdir z && + echo random >z/c && + + git merge -s recursive B^0 >out 2>err && + test_i18ngrep ! "following untracked working tree files would be overwritten by merge" err && + + git ls-files -s >out && + test_line_count = 3 out && + git ls-files -u >out && + test_line_count = 0 out && + git ls-files -o >out && + test_line_count = 3 out && + + git rev-parse >actual \ + :0:y/a :0:y/b :0:y/c && + git rev-parse >expect \ + O:z/a O:z/b B:z/c && + test_cmp expect actual && + + echo random >expect && + test_cmp expect z/c + ) +' + +########################################################################### +# SECTION 11: Handling dirty (not up-to-date) files +# +# unpack_trees(), upon which the recursive merge algorithm is based, aborts +# the operation if untracked or dirty files would be deleted or overwritten +# by the merge. Unfortunately, unpack_trees() does not understand renames, +# and if it doesn't abort, then it muddies up the working directory before +# we even get to the point of detecting renames, so we need some special +# handling. This was true even of normal renames, but there are additional +# codepaths that need special handling with directory renames. Add +# testcases for both renamed-by-directory-rename-detection and standard +# rename cases. +########################################################################### + +# Testcase 11a, Avoid losing dirty contents with simple rename +# Commit O: z/{a,b_v1}, +# Commit A: z/{a,c_v1}, and z/c_v1 has uncommitted mods +# Commit B: z/{a,b_v2} +# Expected: ERROR_MSG(Refusing to lose dirty file at z/c) + +# z/a, staged version of z/c has sha1sum matching B:z/b_v2, +# z/c~HEAD with contents of B:z/b_v2, +# z/c with uncommitted mods on top of A:z/c_v1 + +test_expect_success '11a-setup: Avoid losing dirty contents with simple rename' ' + test_create_repo 11a && + ( + cd 11a && + + mkdir z && + echo a >z/a && + test_seq 1 10 >z/b && + git add z && + test_tick && + git commit -m "O" && + + git branch O && + git branch A && + git branch B && + + git checkout A && + git mv z/b z/c && + test_tick && + git commit -m "A" && + + git checkout B && + echo 11 >>z/b && + git add z/b && + test_tick && + git commit -m "B" + ) +' + +test_expect_success '11a-check: Avoid losing dirty contents with simple rename' ' + ( + cd 11a && + + git checkout A^0 && + echo stuff >>z/c && + + test_must_fail git merge -s recursive B^0 >out 2>err && + test_i18ngrep "Refusing to lose dirty file at z/c" out && + + test_seq 1 10 >expected && + echo stuff >>expected && + test_cmp expected z/c && + + git ls-files -s >out && + test_line_count = 2 out && + git ls-files -u >out && + test_line_count = 1 out && + git ls-files -o >out && + test_line_count = 4 out && + + git rev-parse >actual \ + :0:z/a :2:z/c && + git rev-parse >expect \ + O:z/a B:z/b && + test_cmp expect actual && + + git hash-object z/c~HEAD >actual && + git rev-parse B:z/b >expect && + test_cmp expect actual + ) +' + +# Testcase 11b, Avoid losing dirty file involved in directory rename +# Commit O: z/a, x/{b,c_v1} +# Commit A: z/{a,c_v1}, x/b, and z/c_v1 has uncommitted mods +# Commit B: y/a, x/{b,c_v2} +# Expected: y/{a,c_v2}, x/b, z/c_v1 with uncommitted mods untracked, +# ERROR_MSG(Refusing to lose dirty file at z/c) + + +test_expect_success '11b-setup: Avoid losing dirty file involved in directory rename' ' + test_create_repo 11b && + ( + cd 11b && + + mkdir z x && + echo a >z/a && + echo b >x/b && + test_seq 1 10 >x/c && + git add z x && + test_tick && + git commit -m "O" && + + git branch O && + git branch A && + git branch B && + + git checkout A && + git mv x/c z/c && + test_tick && + git commit -m "A" && + + git checkout B && + git mv z y && + echo 11 >>x/c && + git add x/c && + test_tick && + git commit -m "B" + ) +' + +test_expect_success '11b-check: Avoid losing dirty file involved in directory rename' ' + ( + cd 11b && + + git checkout A^0 && + echo stuff >>z/c && + + git merge -s recursive B^0 >out 2>err && + test_i18ngrep "Refusing to lose dirty file at z/c" out && + + grep -q stuff z/c && + test_seq 1 10 >expected && + echo stuff >>expected && + test_cmp expected z/c && + + git ls-files -s >out && + test_line_count = 3 out && + git ls-files -u >out && + test_line_count = 0 out && + git ls-files -m >out && + test_line_count = 0 out && + git ls-files -o >out && + test_line_count = 4 out && + + git rev-parse >actual \ + :0:x/b :0:y/a :0:y/c && + git rev-parse >expect \ + O:x/b O:z/a B:x/c && + test_cmp expect actual && + + git hash-object y/c >actual && + git rev-parse B:x/c >expect && + test_cmp expect actual + ) +' + +# Testcase 11c, Avoid losing not-up-to-date with rename + D/F conflict +# Commit O: y/a, x/{b,c_v1} +# Commit A: y/{a,c_v1}, x/b, and y/c_v1 has uncommitted mods +# Commit B: y/{a,c/d}, x/{b,c_v2} +# Expected: Abort_msg("following files would be overwritten by merge") + +# y/c left untouched (still has uncommitted mods) + +test_expect_success '11c-setup: Avoid losing not-uptodate with rename + D/F conflict' ' + test_create_repo 11c && + ( + cd 11c && + + mkdir y x && + echo a >y/a && + echo b >x/b && + test_seq 1 10 >x/c && + git add y x && + test_tick && + git commit -m "O" && + + git branch O && + git branch A && + git branch B && + + git checkout A && + git mv x/c y/c && + test_tick && + git commit -m "A" && + + git checkout B && + mkdir y/c && + echo d >y/c/d && + echo 11 >>x/c && + git add x/c y/c/d && + test_tick && + git commit -m "B" + ) +' + +test_expect_success '11c-check: Avoid losing not-uptodate with rename + D/F conflict' ' + ( + cd 11c && + + git checkout A^0 && + echo stuff >>y/c && + + test_must_fail git merge -s recursive B^0 >out 2>err && + test_i18ngrep "following files would be overwritten by merge" err && + + grep -q stuff y/c && + test_seq 1 10 >expected && + echo stuff >>expected && + test_cmp expected y/c && + + git ls-files -s >out && + test_line_count = 3 out && + git ls-files -u >out && + test_line_count = 0 out && + git ls-files -m >out && + test_line_count = 1 out && + git ls-files -o >out && + test_line_count = 3 out + ) +' + +# Testcase 11d, Avoid losing not-up-to-date with rename + D/F conflict +# Commit O: z/a, x/{b,c_v1} +# Commit A: z/{a,c_v1}, x/b, and z/c_v1 has uncommitted mods +# Commit B: y/{a,c/d}, x/{b,c_v2} +# Expected: D/F: y/c_v2 vs y/c/d) + +# Warning_Msg("Refusing to lose dirty file at z/c) + +# y/{a,c~HEAD,c/d}, x/b, now-untracked z/c_v1 with uncommitted mods + +test_expect_success '11d-setup: Avoid losing not-uptodate with rename + D/F conflict' ' + test_create_repo 11d && + ( + cd 11d && + + mkdir z x && + echo a >z/a && + echo b >x/b && + test_seq 1 10 >x/c && + git add z x && + test_tick && + git commit -m "O" && + + git branch O && + git branch A && + git branch B && + + git checkout A && + git mv x/c z/c && + test_tick && + git commit -m "A" && + + git checkout B && + git mv z y && + mkdir y/c && + echo d >y/c/d && + echo 11 >>x/c && + git add x/c y/c/d && + test_tick && + git commit -m "B" + ) +' + +test_expect_success '11d-check: Avoid losing not-uptodate with rename + D/F conflict' ' + ( + cd 11d && + + git checkout A^0 && + echo stuff >>z/c && + + test_must_fail git merge -s recursive B^0 >out 2>err && + test_i18ngrep "Refusing to lose dirty file at z/c" out && + + grep -q stuff z/c && + test_seq 1 10 >expected && + echo stuff >>expected && + test_cmp expected z/c + + git ls-files -s >out && + test_line_count = 4 out && + git ls-files -u >out && + test_line_count = 1 out && + git ls-files -o >out && + test_line_count = 5 out && + + git rev-parse >actual \ + :0:x/b :0:y/a :0:y/c/d :3:y/c && + git rev-parse >expect \ + O:x/b O:z/a B:y/c/d B:x/c && + test_cmp expect actual && + + git hash-object y/c~HEAD >actual && + git rev-parse B:x/c >expect && + test_cmp expect actual + ) +' + +# Testcase 11e, Avoid deleting not-up-to-date with dir rename/rename(1to2)/add +# Commit O: z/{a,b}, x/{c_1,d} +# Commit A: y/{a,b,c_2}, x/d, w/c_1, and y/c_2 has uncommitted mods +# Commit B: z/{a,b,c_1}, x/d +# Expected: Failed Merge; y/{a,b} + x/d + +# CONFLICT(rename/rename) x/c_1 -> w/c_1 vs y/c_1 + +# ERROR_MSG(Refusing to lose dirty file at y/c) +# y/c~B^0 has O:x/c_1 contents +# y/c~HEAD has A:y/c_2 contents +# y/c has dirty file from before merge + +test_expect_success '11e-setup: Avoid deleting not-uptodate with dir rename/rename(1to2)/add' ' + test_create_repo 11e && + ( + cd 11e && + + mkdir z x && + echo a >z/a && + echo b >z/b && + echo c >x/c && + echo d >x/d && + git add z x && + test_tick && + git commit -m "O" && + + git branch O && + git branch A && + git branch B && + + git checkout A && + git mv z/ y/ && + echo different >y/c && + mkdir w && + git mv x/c w/ && + git add y/c && + test_tick && + git commit -m "A" && + + git checkout B && + git mv x/c z/ && + test_tick && + git commit -m "B" + ) +' + +test_expect_success '11e-check: Avoid deleting not-uptodate with dir rename/rename(1to2)/add' ' + ( + cd 11e && + + git checkout A^0 && + echo mods >>y/c && + + test_must_fail git merge -s recursive B^0 >out 2>err && + test_i18ngrep "CONFLICT (rename/rename)" out && + test_i18ngrep "Refusing to lose dirty file at y/c" out && + + git ls-files -s >out && + test_line_count = 7 out && + git ls-files -u >out && + test_line_count = 4 out && + git ls-files -o >out && + test_line_count = 4 out && + + echo different >expected && + echo mods >>expected && + test_cmp expected y/c && + + git rev-parse >actual \ + :0:y/a :0:y/b :0:x/d :1:x/c :2:w/c :2:y/c :3:y/c && + git rev-parse >expect \ + O:z/a O:z/b O:x/d O:x/c O:x/c A:y/c O:x/c && + test_cmp expect actual && + + git hash-object >actual \ + y/c~B^0 y/c~HEAD && + git rev-parse >expect \ + O:x/c A:y/c && + test_cmp expect actual + ) +' + +# Testcase 11f, Avoid deleting not-up-to-date w/ dir rename/rename(2to1) +# Commit O: z/{a,b}, x/{c_1,d_2} +# Commit A: y/{a,b,wham_1}, x/d_2, except y/wham has uncommitted mods +# Commit B: z/{a,b,wham_2}, x/c_1 +# Expected: Failed Merge; y/{a,b} + untracked y/{wham~B^0,wham~B^HEAD} + +# y/wham with dirty changes from before merge + +# CONFLICT(rename/rename) x/c vs x/d -> y/wham +# ERROR_MSG(Refusing to lose dirty file at y/wham) + +test_expect_success '11f-setup: Avoid deleting not-uptodate with dir rename/rename(2to1)' ' + test_create_repo 11f && + ( + cd 11f && + + mkdir z x && + echo a >z/a && + echo b >z/b && + test_seq 1 10 >x/c && + echo d >x/d && + git add z x && + test_tick && + git commit -m "O" && + + git branch O && + git branch A && + git branch B && + + git checkout A && + git mv z/ y/ && + git mv x/c y/wham && + test_tick && + git commit -m "A" && + + git checkout B && + git mv x/d z/wham && + test_tick && + git commit -m "B" + ) +' + +test_expect_success '11f-check: Avoid deleting not-uptodate with dir rename/rename(2to1)' ' + ( + cd 11f && + + git checkout A^0 && + echo important >>y/wham && + + test_must_fail git merge -s recursive B^0 >out 2>err && + test_i18ngrep "CONFLICT (rename/rename)" out && + test_i18ngrep "Refusing to lose dirty file at y/wham" out && + + git ls-files -s >out && + test_line_count = 4 out && + git ls-files -u >out && + test_line_count = 2 out && + git ls-files -o >out && + test_line_count = 4 out && + + test_seq 1 10 >expected && + echo important >>expected && + test_cmp expected y/wham && + + test_must_fail git rev-parse :1:y/wham && + git hash-object >actual \ + y/wham~B^0 y/wham~HEAD && + git rev-parse >expect \ + O:x/d O:x/c && + test_cmp expect actual && + + git rev-parse >actual \ + :0:y/a :0:y/b :2:y/wham :3:y/wham && + git rev-parse >expect \ + O:z/a O:z/b O:x/c O:x/d && + test_cmp expect actual + ) +' + +########################################################################### +# SECTION 12: Everything else +# +# Tests suggested by others. Tests added after implementation completed +# and submitted. Grab bag. +########################################################################### + +# Testcase 12a, Moving one directory hierarchy into another +# (Related to testcase 9a) +# Commit O: node1/{leaf1,leaf2}, node2/{leaf3,leaf4} +# Commit A: node1/{leaf1,leaf2,node2/{leaf3,leaf4}} +# Commit B: node1/{leaf1,leaf2,leaf5}, node2/{leaf3,leaf4,leaf6} +# Expected: node1/{leaf1,leaf2,leaf5,node2/{leaf3,leaf4,leaf6}} + +test_expect_success '12a-setup: Moving one directory hierarchy into another' ' + test_create_repo 12a && + ( + cd 12a && + + mkdir -p node1 node2 && + echo leaf1 >node1/leaf1 && + echo leaf2 >node1/leaf2 && + echo leaf3 >node2/leaf3 && + echo leaf4 >node2/leaf4 && + git add node1 node2 && + test_tick && + git commit -m "O" && + + git branch O && + git branch A && + git branch B && + + git checkout A && + git mv node2/ node1/ && + test_tick && + git commit -m "A" && + + git checkout B && + echo leaf5 >node1/leaf5 && + echo leaf6 >node2/leaf6 && + git add node1 node2 && + test_tick && + git commit -m "B" + ) +' + +test_expect_success '12a-check: Moving one directory hierarchy into another' ' + ( + cd 12a && + + git checkout A^0 && + + git merge -s recursive B^0 && + + git ls-files -s >out && + test_line_count = 6 out && + + git rev-parse >actual \ + HEAD:node1/leaf1 HEAD:node1/leaf2 HEAD:node1/leaf5 \ + HEAD:node1/node2/leaf3 \ + HEAD:node1/node2/leaf4 \ + HEAD:node1/node2/leaf6 && + git rev-parse >expect \ + O:node1/leaf1 O:node1/leaf2 B:node1/leaf5 \ + O:node2/leaf3 \ + O:node2/leaf4 \ + B:node2/leaf6 && + test_cmp expect actual + ) +' + +# Testcase 12b, Moving two directory hierarchies into each other +# (Related to testcases 1c and 12c) +# Commit O: node1/{leaf1, leaf2}, node2/{leaf3, leaf4} +# Commit A: node1/{leaf1, leaf2, node2/{leaf3, leaf4}} +# Commit B: node2/{leaf3, leaf4, node1/{leaf1, leaf2}} +# Expected: node1/node2/node1/{leaf1, leaf2}, +# node2/node1/node2/{leaf3, leaf4} +# NOTE: Without directory renames, we would expect +# node2/node1/{leaf1, leaf2}, +# node1/node2/{leaf3, leaf4} +# with directory rename detection, we note that +# commit A renames node2/ -> node1/node2/ +# commit B renames node1/ -> node2/node1/ +# therefore, applying those directory renames to the initial result +# (making all four paths experience a transitive renaming), yields +# the expected result. +# +# You may ask, is it weird to have two directories rename each other? +# To which, I can do no more than shrug my shoulders and say that +# even simple rules give weird results when given weird inputs. + +test_expect_success '12b-setup: Moving one directory hierarchy into another' ' + test_create_repo 12b && + ( + cd 12b && + + mkdir -p node1 node2 && + echo leaf1 >node1/leaf1 && + echo leaf2 >node1/leaf2 && + echo leaf3 >node2/leaf3 && + echo leaf4 >node2/leaf4 && + git add node1 node2 && + test_tick && + git commit -m "O" && + + git branch O && + git branch A && + git branch B && + + git checkout A && + git mv node2/ node1/ && + test_tick && + git commit -m "A" && + + git checkout B && + git mv node1/ node2/ && + test_tick && + git commit -m "B" + ) +' + +test_expect_success '12b-check: Moving one directory hierarchy into another' ' + ( + cd 12b && + + git checkout A^0 && + + git merge -s recursive B^0 && + + git ls-files -s >out && + test_line_count = 4 out && + + git rev-parse >actual \ + HEAD:node1/node2/node1/leaf1 \ + HEAD:node1/node2/node1/leaf2 \ + HEAD:node2/node1/node2/leaf3 \ + HEAD:node2/node1/node2/leaf4 && + git rev-parse >expect \ + O:node1/leaf1 \ + O:node1/leaf2 \ + O:node2/leaf3 \ + O:node2/leaf4 && + test_cmp expect actual + ) +' + +# Testcase 12c, Moving two directory hierarchies into each other w/ content merge +# (Related to testcase 12b) +# Commit O: node1/{ leaf1_1, leaf2_1}, node2/{leaf3_1, leaf4_1} +# Commit A: node1/{ leaf1_2, leaf2_2, node2/{leaf3_2, leaf4_2}} +# Commit B: node2/{node1/{leaf1_3, leaf2_3}, leaf3_3, leaf4_3} +# Expected: Content merge conflicts for each of: +# node1/node2/node1/{leaf1, leaf2}, +# node2/node1/node2/{leaf3, leaf4} +# NOTE: This is *exactly* like 12c, except that every path is modified on +# each side of the merge. + +test_expect_success '12c-setup: Moving one directory hierarchy into another w/ content merge' ' + test_create_repo 12c && + ( + cd 12c && + + mkdir -p node1 node2 && + printf "1\n2\n3\n4\n5\n6\n7\n8\nleaf1\n" >node1/leaf1 && + printf "1\n2\n3\n4\n5\n6\n7\n8\nleaf2\n" >node1/leaf2 && + printf "1\n2\n3\n4\n5\n6\n7\n8\nleaf3\n" >node2/leaf3 && + printf "1\n2\n3\n4\n5\n6\n7\n8\nleaf4\n" >node2/leaf4 && + git add node1 node2 && + test_tick && + git commit -m "O" && + + git branch O && + git branch A && + git branch B && + + git checkout A && + git mv node2/ node1/ && + for i in `git ls-files`; do echo side A >>$i; done && + git add -u && + test_tick && + git commit -m "A" && + + git checkout B && + git mv node1/ node2/ && + for i in `git ls-files`; do echo side B >>$i; done && + git add -u && + test_tick && + git commit -m "B" + ) +' + +test_expect_success '12c-check: Moving one directory hierarchy into another w/ content merge' ' + ( + cd 12c && + + git checkout A^0 && + + test_must_fail git merge -s recursive B^0 && + + git ls-files -u >out && + test_line_count = 12 out && + + git rev-parse >actual \ + :1:node1/node2/node1/leaf1 \ + :1:node1/node2/node1/leaf2 \ + :1:node2/node1/node2/leaf3 \ + :1:node2/node1/node2/leaf4 \ + :2:node1/node2/node1/leaf1 \ + :2:node1/node2/node1/leaf2 \ + :2:node2/node1/node2/leaf3 \ + :2:node2/node1/node2/leaf4 \ + :3:node1/node2/node1/leaf1 \ + :3:node1/node2/node1/leaf2 \ + :3:node2/node1/node2/leaf3 \ + :3:node2/node1/node2/leaf4 && + git rev-parse >expect \ + O:node1/leaf1 \ + O:node1/leaf2 \ + O:node2/leaf3 \ + O:node2/leaf4 \ + A:node1/leaf1 \ + A:node1/leaf2 \ + A:node1/node2/leaf3 \ + A:node1/node2/leaf4 \ + B:node2/node1/leaf1 \ + B:node2/node1/leaf2 \ + B:node2/leaf3 \ + B:node2/leaf4 && + test_cmp expect actual + ) +' + +test_done diff --git a/t/t6046-merge-skip-unneeded-updates.sh b/t/t6046-merge-skip-unneeded-updates.sh new file mode 100755 index 0000000000..fcefffcaec --- /dev/null +++ b/t/t6046-merge-skip-unneeded-updates.sh @@ -0,0 +1,761 @@ +#!/bin/sh + +test_description="merge cases" + +# The setup for all of them, pictorially, is: +# +# A +# o +# / \ +# O o ? +# \ / +# o +# B +# +# To help make it easier to follow the flow of tests, they have been +# divided into sections and each test will start with a quick explanation +# of what commits O, A, and B contain. +# +# Notation: +# z/{b,c} means files z/b and z/c both exist +# x/d_1 means file x/d exists with content d1. (Purpose of the +# underscore notation is to differentiate different +# files that might be renamed into each other's paths.) + +. ./test-lib.sh + + +########################################################################### +# SECTION 1: Cases involving no renames (one side has subset of changes of +# the other side) +########################################################################### + +# Testcase 1a, Changes on A, subset of changes on B +# Commit O: b_1 +# Commit A: b_2 +# Commit B: b_3 +# Expected: b_2 + +test_expect_success '1a-setup: Modify(A)/Modify(B), change on B subset of A' ' + test_create_repo 1a && + ( + cd 1a && + + test_write_lines 1 2 3 4 5 6 7 8 9 10 >b && + git add b && + test_tick && + git commit -m "O" && + + git branch O && + git branch A && + git branch B && + + git checkout A && + test_write_lines 1 2 3 4 5 5.5 6 7 8 9 10 10.5 >b && + git add b && + test_tick && + git commit -m "A" && + + git checkout B && + test_write_lines 1 2 3 4 5 5.5 6 7 8 9 10 >b && + git add b && + test_tick && + git commit -m "B" + ) +' + +test_expect_success '1a-check-L: Modify(A)/Modify(B), change on B subset of A' ' + test_when_finished "git -C 1a reset --hard" && + test_when_finished "git -C 1a clean -fd" && + ( + cd 1a && + + git checkout A^0 && + + test-tool chmtime =31337 b && + test-tool chmtime -v +0 b >expected-mtime && + + GIT_MERGE_VERBOSITY=3 git merge -s recursive B^0 >out 2>err && + + test_i18ngrep "Skipped b" out && + test_must_be_empty err && + + test-tool chmtime -v +0 b >actual-mtime && + test_cmp expected-mtime actual-mtime && + + git ls-files -s >index_files && + test_line_count = 1 index_files && + + git rev-parse >actual HEAD:b && + git rev-parse >expect A:b && + test_cmp expect actual && + + git hash-object b >actual && + git rev-parse A:b >expect && + test_cmp expect actual + ) +' + +test_expect_success '1a-check-R: Modify(A)/Modify(B), change on B subset of A' ' + test_when_finished "git -C 1a reset --hard" && + test_when_finished "git -C 1a clean -fd" && + ( + cd 1a && + + git checkout B^0 && + + GIT_MERGE_VERBOSITY=3 git merge -s recursive A^0 >out 2>err && + + test_i18ngrep "Auto-merging b" out && + test_must_be_empty err && + + git ls-files -s >index_files && + test_line_count = 1 index_files && + + git rev-parse >actual HEAD:b && + git rev-parse >expect A:b && + test_cmp expect actual && + + git hash-object b >actual && + git rev-parse A:b >expect && + test_cmp expect actual + ) +' + + +########################################################################### +# SECTION 2: Cases involving basic renames +########################################################################### + +# Testcase 2a, Changes on A, rename on B +# Commit O: b_1 +# Commit A: b_2 +# Commit B: c_1 +# Expected: c_2 + +test_expect_success '2a-setup: Modify(A)/rename(B)' ' + test_create_repo 2a && + ( + cd 2a && + + test_seq 1 10 >b && + git add b && + test_tick && + git commit -m "O" && + + git branch O && + git branch A && + git branch B && + + git checkout A && + test_seq 1 11 >b && + git add b && + test_tick && + git commit -m "A" && + + git checkout B && + git mv b c && + test_tick && + git commit -m "B" + ) +' + +test_expect_success '2a-check-L: Modify/rename, merge into modify side' ' + test_when_finished "git -C 2a reset --hard" && + test_when_finished "git -C 2a clean -fd" && + ( + cd 2a && + + git checkout A^0 && + + GIT_MERGE_VERBOSITY=3 git merge -s recursive B^0 >out 2>err && + + test_i18ngrep ! "Skipped c" out && + test_must_be_empty err && + + git ls-files -s >index_files && + test_line_count = 1 index_files && + + git rev-parse >actual HEAD:c && + git rev-parse >expect A:b && + test_cmp expect actual && + + git hash-object c >actual && + git rev-parse A:b >expect && + test_cmp expect actual && + + test_must_fail git rev-parse HEAD:b && + test_path_is_missing b + ) +' + +test_expect_success '2a-check-R: Modify/rename, merge into rename side' ' + test_when_finished "git -C 2a reset --hard" && + test_when_finished "git -C 2a clean -fd" && + ( + cd 2a && + + git checkout B^0 && + + GIT_MERGE_VERBOSITY=3 git merge -s recursive A^0 >out 2>err && + + test_i18ngrep ! "Skipped c" out && + test_must_be_empty err && + + git ls-files -s >index_files && + test_line_count = 1 index_files && + + git rev-parse >actual HEAD:c && + git rev-parse >expect A:b && + test_cmp expect actual && + + git hash-object c >actual && + git rev-parse A:b >expect && + test_cmp expect actual && + + test_must_fail git rev-parse HEAD:b && + test_path_is_missing b + ) +' + +# Testcase 2b, Changed and renamed on A, subset of changes on B +# Commit O: b_1 +# Commit A: c_2 +# Commit B: b_3 +# Expected: c_2 + +test_expect_success '2b-setup: Rename+Mod(A)/Mod(B), B mods subset of A' ' + test_create_repo 2b && + ( + cd 2b && + + test_write_lines 1 2 3 4 5 6 7 8 9 10 >b && + git add b && + test_tick && + git commit -m "O" && + + git branch O && + git branch A && + git branch B && + + git checkout A && + test_write_lines 1 2 3 4 5 5.5 6 7 8 9 10 10.5 >b && + git add b && + git mv b c && + test_tick && + git commit -m "A" && + + git checkout B && + test_write_lines 1 2 3 4 5 5.5 6 7 8 9 10 >b && + git add b && + test_tick && + git commit -m "B" + ) +' + +test_expect_success '2b-check-L: Rename+Mod(A)/Mod(B), B mods subset of A' ' + test_when_finished "git -C 2b reset --hard" && + test_when_finished "git -C 2b clean -fd" && + ( + cd 2b && + + git checkout A^0 && + + test-tool chmtime =31337 c && + test-tool chmtime -v +0 c >expected-mtime && + + GIT_MERGE_VERBOSITY=3 git merge -s recursive B^0 >out 2>err && + + test_i18ngrep "Skipped c" out && + test_must_be_empty err && + + test-tool chmtime -v +0 c >actual-mtime && + test_cmp expected-mtime actual-mtime && + + git ls-files -s >index_files && + test_line_count = 1 index_files && + + git rev-parse >actual HEAD:c && + git rev-parse >expect A:c && + test_cmp expect actual && + + git hash-object c >actual && + git rev-parse A:c >expect && + test_cmp expect actual && + + test_must_fail git rev-parse HEAD:b && + test_path_is_missing b + ) +' + +test_expect_success '2b-check-R: Rename+Mod(A)/Mod(B), B mods subset of A' ' + test_when_finished "git -C 2b reset --hard" && + test_when_finished "git -C 2b clean -fd" && + ( + cd 2b && + + git checkout B^0 && + + GIT_MERGE_VERBOSITY=3 git merge -s recursive A^0 >out 2>err && + + test_i18ngrep "Auto-merging c" out && + test_must_be_empty err && + + git ls-files -s >index_files && + test_line_count = 1 index_files && + + git rev-parse >actual HEAD:c && + git rev-parse >expect A:c && + test_cmp expect actual && + + git hash-object c >actual && + git rev-parse A:c >expect && + test_cmp expect actual && + + test_must_fail git rev-parse HEAD:b && + test_path_is_missing b + ) +' + +# Testcase 2c, Changes on A, rename on B +# Commit O: b_1 +# Commit A: b_2, c_3 +# Commit B: c_1 +# Expected: rename/add conflict c_2 vs c_3 +# +# NOTE: Since A modified b_1->b_2, and B renamed b_1->c_1, the threeway +# merge of those files should result in c_2. We then should have a +# rename/add conflict between c_2 and c_3. However, if we note in +# merge_content() that A had the right contents (b_2 has same +# contents as c_2, just at a different name), and that A had the +# right path present (c_3 existed) and thus decides that it can +# skip the update, then we're in trouble. This test verifies we do +# not make that particular mistake. + +test_expect_success '2c-setup: Modify b & add c VS rename b->c' ' + test_create_repo 2c && + ( + cd 2c && + + test_seq 1 10 >b && + git add b && + test_tick && + git commit -m "O" && + + git branch O && + git branch A && + git branch B && + + git checkout A && + test_seq 1 11 >b && + echo whatever >c && + git add b c && + test_tick && + git commit -m "A" && + + git checkout B && + git mv b c && + test_tick && + git commit -m "B" + ) +' + +test_expect_success '2c-check: Modify b & add c VS rename b->c' ' + ( + cd 2c && + + git checkout A^0 && + + GIT_MERGE_VERBOSITY=3 test_must_fail git merge -s recursive B^0 >out 2>err && + + test_i18ngrep "CONFLICT (rename/add): Rename b->c" out && + test_i18ngrep ! "Skipped c" out && + test_must_be_empty err + + # FIXME: rename/add conflicts are horribly broken right now; + # when I get back to my patch series fixing it and + # rename/rename(2to1) conflicts to bring them in line with + # how add/add conflicts behave, then checks like the below + # could be added. But that patch series is waiting until + # the rename-directory-detection series lands, which this + # is part of. And in the mean time, I do not want to further + # enforce broken behavior. So for now, the main test is the + # one above that err is an empty file. + + #git ls-files -s >index_files && + #test_line_count = 2 index_files && + + #git rev-parse >actual :2:c :3:c && + #git rev-parse >expect A:b A:c && + #test_cmp expect actual && + + #git cat-file -p A:b >>merged && + #git cat-file -p A:c >>merge-me && + #>empty && + #test_must_fail git merge-file \ + # -L "Temporary merge branch 1" \ + # -L "" \ + # -L "Temporary merge branch 2" \ + # merged empty merge-me && + #sed -e "s/^\([<=>]\)/\1\1\1/" merged >merged-internal && + + #git hash-object c >actual && + #git hash-object merged-internal >expect && + #test_cmp expect actual && + + #test_path_is_missing b + ) +' + + +########################################################################### +# SECTION 3: Cases involving directory renames +# +# NOTE: +# Directory renames only apply when one side renames a directory, and the +# other side adds or renames a path into that directory. Applying the +# directory rename to that new path creates a new pathname that didn't +# exist on either side of history. Thus, it is impossible for the +# merge contents to already be at the right path, so all of these checks +# exist just to make sure that updates are not skipped. +########################################################################### + +# Testcase 3a, Change + rename into dir foo on A, dir rename foo->bar on B +# Commit O: bq_1, foo/whatever +# Commit A: foo/{bq_2, whatever} +# Commit B: bq_1, bar/whatever +# Expected: bar/{bq_2, whatever} + +test_expect_success '3a-setup: bq_1->foo/bq_2 on A, foo/->bar/ on B' ' + test_create_repo 3a && + ( + cd 3a && + + mkdir foo && + test_seq 1 10 >bq && + test_write_lines a b c d e f g h i j k >foo/whatever && + git add bq foo/whatever && + test_tick && + git commit -m "O" && + + git branch O && + git branch A && + git branch B && + + git checkout A && + test_seq 1 11 >bq && + git add bq && + git mv bq foo/ && + test_tick && + git commit -m "A" && + + git checkout B && + git mv foo/ bar/ && + test_tick && + git commit -m "B" + ) +' + +test_expect_success '3a-check-L: bq_1->foo/bq_2 on A, foo/->bar/ on B' ' + test_when_finished "git -C 3a reset --hard" && + test_when_finished "git -C 3a clean -fd" && + ( + cd 3a && + + git checkout A^0 && + + GIT_MERGE_VERBOSITY=3 git merge -s recursive B^0 >out 2>err && + + test_i18ngrep ! "Skipped bar/bq" out && + test_must_be_empty err && + + git ls-files -s >index_files && + test_line_count = 2 index_files && + + git rev-parse >actual HEAD:bar/bq HEAD:bar/whatever && + git rev-parse >expect A:foo/bq A:foo/whatever && + test_cmp expect actual && + + git hash-object bar/bq bar/whatever >actual && + git rev-parse A:foo/bq A:foo/whatever >expect && + test_cmp expect actual && + + test_must_fail git rev-parse HEAD:bq HEAD:foo/bq && + test_path_is_missing bq foo/bq foo/whatever + ) +' + +test_expect_success '3a-check-R: bq_1->foo/bq_2 on A, foo/->bar/ on B' ' + test_when_finished "git -C 3a reset --hard" && + test_when_finished "git -C 3a clean -fd" && + ( + cd 3a && + + git checkout B^0 && + + GIT_MERGE_VERBOSITY=3 git merge -s recursive A^0 >out 2>err && + + test_i18ngrep ! "Skipped bar/bq" out && + test_must_be_empty err && + + git ls-files -s >index_files && + test_line_count = 2 index_files && + + git rev-parse >actual HEAD:bar/bq HEAD:bar/whatever && + git rev-parse >expect A:foo/bq A:foo/whatever && + test_cmp expect actual && + + git hash-object bar/bq bar/whatever >actual && + git rev-parse A:foo/bq A:foo/whatever >expect && + test_cmp expect actual && + + test_must_fail git rev-parse HEAD:bq HEAD:foo/bq && + test_path_is_missing bq foo/bq foo/whatever + ) +' + +# Testcase 3b, rename into dir foo on A, dir rename foo->bar + change on B +# Commit O: bq_1, foo/whatever +# Commit A: foo/{bq_1, whatever} +# Commit B: bq_2, bar/whatever +# Expected: bar/{bq_2, whatever} + +test_expect_success '3b-setup: bq_1->foo/bq_2 on A, foo/->bar/ on B' ' + test_create_repo 3b && + ( + cd 3b && + + mkdir foo && + test_seq 1 10 >bq && + test_write_lines a b c d e f g h i j k >foo/whatever && + git add bq foo/whatever && + test_tick && + git commit -m "O" && + + git branch O && + git branch A && + git branch B && + + git checkout A && + git mv bq foo/ && + test_tick && + git commit -m "A" && + + git checkout B && + test_seq 1 11 >bq && + git add bq && + git mv foo/ bar/ && + test_tick && + git commit -m "B" + ) +' + +test_expect_success '3b-check-L: bq_1->foo/bq_2 on A, foo/->bar/ on B' ' + test_when_finished "git -C 3b reset --hard" && + test_when_finished "git -C 3b clean -fd" && + ( + cd 3b && + + git checkout A^0 && + + GIT_MERGE_VERBOSITY=3 git merge -s recursive B^0 >out 2>err && + + test_i18ngrep ! "Skipped bar/bq" out && + test_must_be_empty err && + + git ls-files -s >index_files && + test_line_count = 2 index_files && + + git rev-parse >actual HEAD:bar/bq HEAD:bar/whatever && + git rev-parse >expect B:bq A:foo/whatever && + test_cmp expect actual && + + git hash-object bar/bq bar/whatever >actual && + git rev-parse B:bq A:foo/whatever >expect && + test_cmp expect actual && + + test_must_fail git rev-parse HEAD:bq HEAD:foo/bq && + test_path_is_missing bq foo/bq foo/whatever + ) +' + +test_expect_success '3b-check-R: bq_1->foo/bq_2 on A, foo/->bar/ on B' ' + test_when_finished "git -C 3b reset --hard" && + test_when_finished "git -C 3b clean -fd" && + ( + cd 3b && + + git checkout B^0 && + + GIT_MERGE_VERBOSITY=3 git merge -s recursive A^0 >out 2>err && + + test_i18ngrep ! "Skipped bar/bq" out && + test_must_be_empty err && + + git ls-files -s >index_files && + test_line_count = 2 index_files && + + git rev-parse >actual HEAD:bar/bq HEAD:bar/whatever && + git rev-parse >expect B:bq A:foo/whatever && + test_cmp expect actual && + + git hash-object bar/bq bar/whatever >actual && + git rev-parse B:bq A:foo/whatever >expect && + test_cmp expect actual && + + test_must_fail git rev-parse HEAD:bq HEAD:foo/bq && + test_path_is_missing bq foo/bq foo/whatever + ) +' + +########################################################################### +# SECTION 4: Cases involving dirty changes +########################################################################### + +# Testcase 4a, Changed on A, subset of changes on B, locally modified +# Commit O: b_1 +# Commit A: b_2 +# Commit B: b_3 +# Working copy: b_4 +# Expected: b_2 for merge, b_4 in working copy + +test_expect_success '4a-setup: Change on A, change on B subset of A, dirty mods present' ' + test_create_repo 4a && + ( + cd 4a && + + test_write_lines 1 2 3 4 5 6 7 8 9 10 >b && + git add b && + test_tick && + git commit -m "O" && + + git branch O && + git branch A && + git branch B && + + git checkout A && + test_write_lines 1 2 3 4 5 5.5 6 7 8 9 10 10.5 >b && + git add b && + test_tick && + git commit -m "A" && + + git checkout B && + test_write_lines 1 2 3 4 5 5.5 6 7 8 9 10 >b && + git add b && + test_tick && + git commit -m "B" + ) +' + +# NOTE: For as long as we continue using unpack_trees() without index_only +# set to true, it will error out on a case like this claiming the the locally +# modified file would be overwritten by the merge. Getting this testcase +# correct requires doing the merge in-memory first, then realizing that no +# updates to the file are necessary, and thus that we can just leave the path +# alone. +test_expect_failure '4a-check: Change on A, change on B subset of A, dirty mods present' ' + test_when_finished "git -C 4a reset --hard" && + test_when_finished "git -C 4a clean -fd" && + ( + cd 4a && + + git checkout A^0 && + echo "File rewritten" >b && + + test-tool chmtime =31337 b && + test-tool chmtime -v +0 b >expected-mtime && + + GIT_MERGE_VERBOSITY=3 git merge -s recursive B^0 >out 2>err && + + test_i18ngrep "Skipped b" out && + test_must_be_empty err && + + test-tool chmtime -v +0 b >actual-mtime && + test_cmp expected-mtime actual-mtime && + + git ls-files -s >index_files && + test_line_count = 1 index_files && + + git rev-parse >actual :0:b && + git rev-parse >expect A:b && + test_cmp expect actual && + + git hash-object b >actual && + echo "File rewritten" | git hash-object --stdin >expect && + test_cmp expect actual + ) +' + +# Testcase 4b, Changed+renamed on A, subset of changes on B, locally modified +# Commit O: b_1 +# Commit A: c_2 +# Commit B: b_3 +# Working copy: c_4 +# Expected: c_2 + +test_expect_success '4b-setup: Rename+Mod(A)/Mod(B), change on B subset of A, dirty mods present' ' + test_create_repo 4b && + ( + cd 4b && + + test_write_lines 1 2 3 4 5 6 7 8 9 10 >b && + git add b && + test_tick && + git commit -m "O" && + + git branch O && + git branch A && + git branch B && + + git checkout A && + test_write_lines 1 2 3 4 5 5.5 6 7 8 9 10 10.5 >b && + git add b && + git mv b c && + test_tick && + git commit -m "A" && + + git checkout B && + test_write_lines 1 2 3 4 5 5.5 6 7 8 9 10 >b && + git add b && + test_tick && + git commit -m "B" + ) +' + +test_expect_success '4b-check: Rename+Mod(A)/Mod(B), change on B subset of A, dirty mods present' ' + test_when_finished "git -C 4b reset --hard" && + test_when_finished "git -C 4b clean -fd" && + ( + cd 4b && + + git checkout A^0 && + echo "File rewritten" >c && + + test-tool chmtime =31337 c && + test-tool chmtime -v +0 c >expected-mtime && + + GIT_MERGE_VERBOSITY=3 git merge -s recursive B^0 >out 2>err && + + test_i18ngrep "Skipped c" out && + test_must_be_empty err && + + test-tool chmtime -v +0 c >actual-mtime && + test_cmp expected-mtime actual-mtime && + + git ls-files -s >index_files && + test_line_count = 1 index_files && + + git rev-parse >actual :0:c && + git rev-parse >expect A:c && + test_cmp expect actual && + + git hash-object c >actual && + echo "File rewritten" | git hash-object --stdin >expect && + test_cmp expect actual && + + test_must_fail git rev-parse HEAD:b && + test_path_is_missing b + ) +' + +test_done diff --git a/t/t6050-replace.sh b/t/t6050-replace.sh index c630aba657..d174bfed30 100755 --- a/t/t6050-replace.sh +++ b/t/t6050-replace.sh @@ -444,4 +444,32 @@ test_expect_success GPG '--graft on a commit with a mergetag' ' git replace -d $HASH10 ' +test_expect_success '--convert-graft-file' ' + git checkout -b with-graft-file && + test_commit root2 && + git reset --hard root2^ && + test_commit root1 && + test_commit after-root1 && + test_tick && + git merge -m merge-root2 root2 && + + : add and convert graft file && + printf "%s\n%s %s\n\n# comment\n%s\n" \ + $(git rev-parse HEAD^^ HEAD^ HEAD^^ HEAD^2) \ + >.git/info/grafts && + git replace --convert-graft-file && + test_path_is_missing .git/info/grafts && + + : verify that the history is now "grafted" && + git rev-list HEAD >out && + test_line_count = 4 out && + + : create invalid graft file and verify that it is not deleted && + test_when_finished "rm -f .git/info/grafts" && + echo $EMPTY_BLOB $EMPTY_TREE >.git/info/grafts && + test_must_fail git replace --convert-graft-file 2>err && + test_i18ngrep "$EMPTY_BLOB $EMPTY_TREE" err && + test_i18ngrep "$EMPTY_BLOB $EMPTY_TREE" .git/info/grafts +' + test_done diff --git a/t/t6500-gc.sh b/t/t6500-gc.sh index d5255dd576..818435f04e 100755 --- a/t/t6500-gc.sh +++ b/t/t6500-gc.sh @@ -5,6 +5,13 @@ test_description='basic git gc tests . ./test-lib.sh +test_expect_success 'setup' ' + # do not let the amount of physical memory affects gc + # behavior, make sure we always pack everything to one pack by + # default + git config gc.bigPackThreshold 2g +' + test_expect_success 'gc empty repository' ' git gc ' @@ -43,6 +50,31 @@ test_expect_success 'gc is not aborted due to a stale symref' ' ) ' +test_expect_success 'gc --keep-largest-pack' ' + test_create_repo keep-pack && + ( + cd keep-pack && + test_commit one && + test_commit two && + test_commit three && + git gc && + ( cd .git/objects/pack && ls *.pack ) >pack-list && + test_line_count = 1 pack-list && + BASE_PACK=.git/objects/pack/pack-*.pack && + test_commit four && + git repack -d && + test_commit five && + git repack -d && + ( cd .git/objects/pack && ls *.pack ) >pack-list && + test_line_count = 3 pack-list && + git gc --keep-largest-pack && + ( cd .git/objects/pack && ls *.pack ) >pack-list && + test_line_count = 2 pack-list && + test_path_is_file $BASE_PACK && + git fsck + ) +' + test_expect_success 'auto gc with too many loose objects does not attempt to create bitmaps' ' test_config gc.auto 3 && test_config gc.autodetach false && diff --git a/t/t7001-mv.sh b/t/t7001-mv.sh index e96cbdb105..cc3fd2baf2 100755 --- a/t/t7001-mv.sh +++ b/t/t7001-mv.sh @@ -495,7 +495,7 @@ test_expect_success 'moving a submodule in nested directories' ' test_cmp expect actual ' -test_expect_failure 'moving nested submodules' ' +test_expect_success 'moving nested submodules' ' git commit -am "cleanup commit" && mkdir sub_nested_nested && (cd sub_nested_nested && diff --git a/t/t7004-tag.sh b/t/t7004-tag.sh index 2aac77af70..d7b319e919 100755 --- a/t/t7004-tag.sh +++ b/t/t7004-tag.sh @@ -363,7 +363,7 @@ test_expect_success 'tag -l <pattern> -l <pattern> works, as our buggy documenta ' test_expect_success 'listing tags in column' ' - COLUMNS=40 git tag -l --column=row >actual && + COLUMNS=41 git tag -l --column=row >actual && cat >expected <<\EOF && a1 aa1 cba t210 t211 v0.2.1 v1.0 v1.0.1 v1.1.3 @@ -1056,7 +1056,18 @@ test_expect_success GPG \ git tag -s -F sigblanknonlfile blanknonlfile-signed-tag && get_tag_msg blanknonlfile-signed-tag >actual && test_cmp expect actual && - git tag -v signed-tag + git tag -v blanknonlfile-signed-tag +' + +test_expect_success GPG 'signed tag with embedded PGP message' ' + cat >msg <<-\EOF && + -----BEGIN PGP MESSAGE----- + + this is not a real PGP message + -----END PGP MESSAGE----- + EOF + git tag -s -F msg confusing-pgp-message && + git tag -v confusing-pgp-message ' # messages with commented lines for signed tags: diff --git a/t/t7005-editor.sh b/t/t7005-editor.sh index 29e5043b94..b2ca77b338 100755 --- a/t/t7005-editor.sh +++ b/t/t7005-editor.sh @@ -111,14 +111,8 @@ do ' done -if echo 'echo space > "$1"' > "e space.sh" -then - # FS supports spaces in filenames - test_set_prereq SPACES_IN_FILENAMES -fi - -test_expect_success SPACES_IN_FILENAMES 'editor with a space' ' - +test_expect_success 'editor with a space' ' + echo "echo space >\$1" >"e space.sh" && chmod a+x "e space.sh" && GIT_EDITOR="./e\ space.sh" git commit --amend && test space = "$(git show -s --pretty=format:%s)" @@ -126,7 +120,7 @@ test_expect_success SPACES_IN_FILENAMES 'editor with a space' ' ' unset GIT_EDITOR -test_expect_success SPACES_IN_FILENAMES 'core.editor with a space' ' +test_expect_success 'core.editor with a space' ' git config core.editor \"./e\ space.sh\" && git commit --amend && diff --git a/t/t7607-merge-overwrite.sh b/t/t7607-merge-overwrite.sh index 9c422bcd7c..dd8ab7ede1 100755 --- a/t/t7607-merge-overwrite.sh +++ b/t/t7607-merge-overwrite.sh @@ -92,7 +92,7 @@ test_expect_success 'will not overwrite removed file with staged changes' ' test_cmp important c1.c ' -test_expect_failure 'will not overwrite unstaged changes in renamed file' ' +test_expect_success 'will not overwrite unstaged changes in renamed file' ' git reset --hard c1 && git mv c1.c other.c && git commit -m rename && diff --git a/t/t7700-repack.sh b/t/t7700-repack.sh index 6061a04147..6162e2a8e6 100755 --- a/t/t7700-repack.sh +++ b/t/t7700-repack.sh @@ -4,6 +4,12 @@ test_description='git repack works correctly' . ./test-lib.sh +commit_and_pack() { + test_commit "$@" >/dev/null && + SHA1=$(git pack-objects --all --unpacked --incremental .git/objects/pack/pack </dev/null) && + echo pack-${SHA1}.pack +} + test_expect_success 'objects in packs marked .keep are not repacked' ' echo content1 > file1 && echo content2 > file2 && @@ -194,7 +200,26 @@ test_expect_success 'objects made unreachable by grafts only are kept' ' git reflog expire --expire=$test_tick --expire-unreachable=$test_tick --all && git repack -a -d && git cat-file -t $H1 - ' +' + +test_expect_success 'repack --keep-pack' ' + test_create_repo keep-pack && + ( + cd keep-pack && + P1=$(commit_and_pack 1) && + P2=$(commit_and_pack 2) && + P3=$(commit_and_pack 3) && + P4=$(commit_and_pack 4) && + ls .git/objects/pack/*.pack >old-counts && + test_line_count = 4 old-counts && + git repack -a -d --keep-pack $P1 --keep-pack $P4 && + ls .git/objects/pack/*.pack >new-counts && + grep -q $P1 new-counts && + grep -q $P4 new-counts && + test_line_count = 3 new-counts && + git fsck + ) +' test_done diff --git a/t/t9350-fast-export.sh b/t/t9350-fast-export.sh index d5679ffb87..6a392e87bc 100755 --- a/t/t9350-fast-export.sh +++ b/t/t9350-fast-export.sh @@ -538,4 +538,22 @@ test_expect_success 'when using -C, do not declare copy when source of copy is a test_cmp expected actual ' +test_expect_success 'merge commit gets exported with --import-marks' ' + test_create_repo merging && + ( + cd merging && + test_commit initial && + git checkout -b topic && + test_commit on-topic && + git checkout master && + test_commit on-master && + test_tick && + git merge --no-ff -m Yeah topic && + + echo ":1 $(git rev-parse HEAD^^)" >marks && + git fast-export --import-marks=marks master >out && + grep Yeah out + ) +' + test_done diff --git a/t/test-lib-functions.sh b/t/test-lib-functions.sh index 7d620bf2a9..2b2181dca0 100644 --- a/t/test-lib-functions.sh +++ b/t/test-lib-functions.sh @@ -145,12 +145,28 @@ test_pause () { "$SHELL_PATH" <&6 >&5 2>&7 } -# Wrap git in gdb. Adding this to a command can make it easier to -# understand what is going on in a failing test. +# Wrap git with a debugger. Adding this to a command can make it easier +# to understand what is going on in a failing test. # -# Example: "debug git checkout master". +# Examples: +# debug git checkout master +# debug --debugger=nemiver git $ARGS +# debug -d "valgrind --tool=memcheck --track-origins=yes" git $ARGS debug () { - GIT_TEST_GDB=1 "$@" <&6 >&5 2>&7 + case "$1" in + -d) + GIT_DEBUGGER="$2" && + shift 2 + ;; + --debugger=*) + GIT_DEBUGGER="${1#*=}" && + shift 1 + ;; + *) + GIT_DEBUGGER=1 + ;; + esac && + GIT_DEBUGGER="${GIT_DEBUGGER}" "$@" <&6 >&5 2>&7 } # Call test_commit with the arguments @@ -278,8 +294,20 @@ write_script () { # The single parameter is the prerequisite tag (a simple word, in all # capital letters by convention). +test_unset_prereq () { + ! test_have_prereq "$1" || + satisfied_prereq="${satisfied_prereq% $1 *} ${satisfied_prereq#* $1 }" +} + test_set_prereq () { - satisfied_prereq="$satisfied_prereq$1 " + case "$1" in + !*) + test_unset_prereq "${1#!}" + ;; + *) + satisfied_prereq="$satisfied_prereq$1 " + ;; + esac } satisfied_prereq=" " lazily_testable_prereq= lazily_tested_prereq= @@ -41,7 +41,7 @@ int gpg_verify_tag(const struct object_id *oid, const char *name_to_report, unsigned long size; int ret; - type = oid_object_info(oid, NULL); + type = oid_object_info(the_repository, oid, NULL); if (type != OBJ_TAG) return error("%s: cannot verify a non-tag object of type %s.", name_to_report ? diff --git a/transport-helper.c b/transport-helper.c index 3f380d87d9..11f1055b47 100644 --- a/transport-helper.c +++ b/transport-helper.c @@ -12,6 +12,7 @@ #include "argv-array.h" #include "refs.h" #include "transport-internal.h" +#include "protocol.h" static int debug; @@ -26,6 +27,7 @@ struct helper_data { option : 1, push : 1, connect : 1, + stateless_connect : 1, signed_tags : 1, check_connectivity : 1, no_disconnect_req : 1, @@ -49,7 +51,7 @@ static void sendline(struct helper_data *helper, struct strbuf *buffer) die_errno("Full write to remote helper failed"); } -static int recvline_fh(FILE *helper, struct strbuf *buffer, const char *name) +static int recvline_fh(FILE *helper, struct strbuf *buffer) { strbuf_reset(buffer); if (debug) @@ -67,7 +69,7 @@ static int recvline_fh(FILE *helper, struct strbuf *buffer, const char *name) static int recvline(struct helper_data *helper, struct strbuf *buffer) { - return recvline_fh(helper->out, buffer, helper->name); + return recvline_fh(helper->out, buffer); } static void write_constant(int fd, const char *str) @@ -188,6 +190,8 @@ static struct child_process *get_helper(struct transport *transport) refspecs[refspec_nr++] = xstrdup(arg); } else if (!strcmp(capname, "connect")) { data->connect = 1; + } else if (!strcmp(capname, "stateless-connect")) { + data->stateless_connect = 1; } else if (!strcmp(capname, "signed-tags")) { data->signed_tags = 1; } else if (skip_prefix(capname, "export-marks ", &arg)) { @@ -545,14 +549,13 @@ static int fetch_with_import(struct transport *transport, return 0; } -static int process_connect_service(struct transport *transport, - const char *name, const char *exec) +static int run_connect(struct transport *transport, struct strbuf *cmdbuf) { struct helper_data *data = transport->data; - struct strbuf cmdbuf = STRBUF_INIT; - struct child_process *helper; - int r, duped, ret = 0; + int ret = 0; + int duped; FILE *input; + struct child_process *helper; helper = get_helper(transport); @@ -568,44 +571,61 @@ static int process_connect_service(struct transport *transport, input = xfdopen(duped, "r"); setvbuf(input, NULL, _IONBF, 0); + sendline(data, cmdbuf); + if (recvline_fh(input, cmdbuf)) + exit(128); + + if (!strcmp(cmdbuf->buf, "")) { + data->no_disconnect_req = 1; + if (debug) + fprintf(stderr, "Debug: Smart transport connection " + "ready.\n"); + ret = 1; + } else if (!strcmp(cmdbuf->buf, "fallback")) { + if (debug) + fprintf(stderr, "Debug: Falling back to dumb " + "transport.\n"); + } else { + die("Unknown response to connect: %s", + cmdbuf->buf); + } + + fclose(input); + return ret; +} + +static int process_connect_service(struct transport *transport, + const char *name, const char *exec) +{ + struct helper_data *data = transport->data; + struct strbuf cmdbuf = STRBUF_INIT; + int ret = 0; + /* * Handle --upload-pack and friends. This is fire and forget... * just warn if it fails. */ if (strcmp(name, exec)) { - r = set_helper_option(transport, "servpath", exec); + int r = set_helper_option(transport, "servpath", exec); if (r > 0) warning("Setting remote service path not supported by protocol."); else if (r < 0) warning("Invalid remote service path."); } - if (data->connect) + if (data->connect) { strbuf_addf(&cmdbuf, "connect %s\n", name); - else - goto exit; - - sendline(data, &cmdbuf); - if (recvline_fh(input, &cmdbuf, name)) - exit(128); - - if (!strcmp(cmdbuf.buf, "")) { - data->no_disconnect_req = 1; - if (debug) - fprintf(stderr, "Debug: Smart transport connection " - "ready.\n"); - ret = 1; - } else if (!strcmp(cmdbuf.buf, "fallback")) { - if (debug) - fprintf(stderr, "Debug: Falling back to dumb " - "transport.\n"); - } else - die("Unknown response to connect: %s", - cmdbuf.buf); + ret = run_connect(transport, &cmdbuf); + } else if (data->stateless_connect && + (get_protocol_version_config() == protocol_v2) && + !strcmp("git-upload-pack", name)) { + strbuf_addf(&cmdbuf, "stateless-connect %s\n", name); + ret = run_connect(transport, &cmdbuf); + if (ret) + transport->stateless_rpc = 1; + } -exit: strbuf_release(&cmdbuf); - fclose(input); return ret; } @@ -1031,7 +1051,8 @@ static int has_attribute(const char *attrs, const char *attr) { } } -static struct ref *get_refs_list(struct transport *transport, int for_push) +static struct ref *get_refs_list(struct transport *transport, int for_push, + const struct argv_array *ref_prefixes) { struct helper_data *data = transport->data; struct child_process *helper; @@ -1044,7 +1065,7 @@ static struct ref *get_refs_list(struct transport *transport, int for_push) if (process_connect(transport, for_push)) { do_take_over(transport); - return transport->vtable->get_refs_list(transport, for_push); + return transport->vtable->get_refs_list(transport, for_push, ref_prefixes); } if (data->push && for_push) diff --git a/transport-internal.h b/transport-internal.h index 3c1a29d727..1cde6258a7 100644 --- a/transport-internal.h +++ b/transport-internal.h @@ -3,6 +3,7 @@ struct ref; struct transport; +struct argv_array; struct transport_vtable { /** @@ -17,11 +18,19 @@ struct transport_vtable { * the transport to try to share connections, for_push is a * hint as to whether the ultimate operation is a push or a fetch. * + * If communicating using protocol v2 a list of prefixes can be + * provided to be sent to the server to enable it to limit the ref + * advertisement. Since ref filtering is done on the server's end, and + * only when using protocol v2, this list will be ignored when not + * using protocol v2 meaning this function can return refs which don't + * match the provided ref_prefixes. + * * If the transport is able to determine the remote hash for * the ref without a huge amount of effort, it should store it * in the ref's old_sha1 field; otherwise it should be all 0. **/ - struct ref *(*get_refs_list)(struct transport *transport, int for_push); + struct ref *(*get_refs_list)(struct transport *transport, int for_push, + const struct argv_array *ref_prefixes); /** * Fetch the objects for the given refs. Note that this gets diff --git a/transport.c b/transport.c index 94eccf29aa..2c4de32b33 100644 --- a/transport.c +++ b/transport.c @@ -18,7 +18,58 @@ #include "sha1-array.h" #include "sigchain.h" #include "transport-internal.h" +#include "protocol.h" #include "object-store.h" +#include "color.h" + +static int transport_use_color = -1; +static char transport_colors[][COLOR_MAXLEN] = { + GIT_COLOR_RESET, + GIT_COLOR_RED /* REJECTED */ +}; + +enum color_transport { + TRANSPORT_COLOR_RESET = 0, + TRANSPORT_COLOR_REJECTED = 1 +}; + +static int transport_color_config(void) +{ + const char *keys[] = { + "color.transport.reset", + "color.transport.rejected" + }, *key = "color.transport"; + char *value; + int i; + static int initialized; + + if (initialized) + return 0; + initialized = 1; + + if (!git_config_get_string(key, &value)) + transport_use_color = git_config_colorbool(key, value); + + if (!want_color_stderr(transport_use_color)) + return 0; + + for (i = 0; i < ARRAY_SIZE(keys); i++) + if (!git_config_get_string(keys[i], &value)) { + if (!value) + return config_error_nonbool(keys[i]); + if (color_parse(value, transport_colors[i]) < 0) + return -1; + } + + return 0; +} + +static const char *transport_get_color(enum color_transport ix) +{ + if (want_color_stderr(transport_use_color)) + return transport_colors[ix]; + return ""; +} static void set_upstreams(struct transport *transport, struct ref *refs, int pretend) @@ -72,7 +123,9 @@ struct bundle_transport_data { struct bundle_header header; }; -static struct ref *get_refs_from_bundle(struct transport *transport, int for_push) +static struct ref *get_refs_from_bundle(struct transport *transport, + int for_push, + const struct argv_array *ref_prefixes) { struct bundle_transport_data *data = transport->data; struct ref *result = NULL; @@ -118,6 +171,7 @@ struct git_transport_data { struct child_process *conn; int fd[2]; unsigned got_remote_heads : 1; + enum protocol_version version; struct oid_array extra_have; struct oid_array shallow; }; @@ -197,16 +251,35 @@ static int connect_setup(struct transport *transport, int for_push) return 0; } -static struct ref *get_refs_via_connect(struct transport *transport, int for_push) +static struct ref *get_refs_via_connect(struct transport *transport, int for_push, + const struct argv_array *ref_prefixes) { struct git_transport_data *data = transport->data; - struct ref *refs; + struct ref *refs = NULL; + struct packet_reader reader; connect_setup(transport, for_push); - get_remote_heads(data->fd[0], NULL, 0, &refs, - for_push ? REF_NORMAL : 0, - &data->extra_have, - &data->shallow); + + packet_reader_init(&reader, data->fd[0], NULL, 0, + PACKET_READ_CHOMP_NEWLINE | + PACKET_READ_GENTLE_ON_EOF); + + data->version = discover_version(&reader); + switch (data->version) { + case protocol_v2: + get_remote_refs(data->fd[1], &reader, &refs, for_push, + ref_prefixes, transport->server_options); + break; + case protocol_v1: + case protocol_v0: + get_remote_heads(&reader, &refs, + for_push ? REF_NORMAL : 0, + &data->extra_have, + &data->shallow); + break; + case protocol_unknown_version: + BUG("unknown protocol version"); + } data->got_remote_heads = 1; return refs; @@ -217,7 +290,7 @@ static int fetch_refs_via_pack(struct transport *transport, { int ret = 0; struct git_transport_data *data = transport->data; - struct ref *refs; + struct ref *refs = NULL; char *dest = xstrdup(transport->url); struct fetch_pack_args args; struct ref *refs_tmp = NULL; @@ -242,18 +315,30 @@ static int fetch_refs_via_pack(struct transport *transport, args.from_promisor = data->options.from_promisor; args.no_dependents = data->options.no_dependents; args.filter_options = data->options.filter_options; - - if (!data->got_remote_heads) { - connect_setup(transport, 0); - get_remote_heads(data->fd[0], NULL, 0, &refs_tmp, 0, - NULL, &data->shallow); - data->got_remote_heads = 1; + args.stateless_rpc = transport->stateless_rpc; + args.server_options = transport->server_options; + + if (!data->got_remote_heads) + refs_tmp = get_refs_via_connect(transport, 0, NULL); + + switch (data->version) { + case protocol_v2: + refs = fetch_pack(&args, data->fd, data->conn, + refs_tmp ? refs_tmp : transport->remote_refs, + dest, to_fetch, nr_heads, &data->shallow, + &transport->pack_lockfile, data->version); + break; + case protocol_v1: + case protocol_v0: + refs = fetch_pack(&args, data->fd, data->conn, + refs_tmp ? refs_tmp : transport->remote_refs, + dest, to_fetch, nr_heads, &data->shallow, + &transport->pack_lockfile, data->version); + break; + case protocol_unknown_version: + BUG("unknown protocol version"); } - refs = fetch_pack(&args, data->fd, data->conn, - refs_tmp ? refs_tmp : transport->remote_refs, - dest, to_fetch, nr_heads, &data->shallow, - &transport->pack_lockfile); close(data->fd[0]); close(data->fd[1]); if (finish_connect(data->conn)) @@ -339,7 +424,13 @@ static void print_ref_status(char flag, const char *summary, else fprintf(stdout, "%s\n", summary); } else { - fprintf(stderr, " %c %-*s ", flag, summary_width, summary); + const char *red = "", *reset = ""; + if (push_had_errors(to)) { + red = transport_get_color(TRANSPORT_COLOR_REJECTED); + reset = transport_get_color(TRANSPORT_COLOR_RESET); + } + fprintf(stderr, " %s%c %-*s%s ", red, flag, summary_width, + summary, reset); if (from) fprintf(stderr, "%s -> %s", prettify_refname(from->name), prettify_refname(to->name)); else @@ -488,6 +579,9 @@ void transport_print_push_status(const char *dest, struct ref *refs, char *head; int summary_width = transport_summary_width(refs); + if (transport_color_config() < 0) + warning(_("could not parse transport.color.* config")); + head = resolve_refdup("HEAD", RESOLVE_REF_READING, NULL, NULL); if (verbose) { @@ -552,16 +646,13 @@ static int git_transport_push(struct transport *transport, struct ref *remote_re { struct git_transport_data *data = transport->data; struct send_pack_args args; - int ret; + int ret = 0; - if (!data->got_remote_heads) { - struct ref *tmp_refs; - connect_setup(transport, 1); + if (transport_color_config() < 0) + return -1; - get_remote_heads(data->fd[0], NULL, 0, &tmp_refs, REF_NORMAL, - NULL, &data->shallow); - data->got_remote_heads = 1; - } + if (!data->got_remote_heads) + get_refs_via_connect(transport, 1, NULL); memset(&args, 0, sizeof(args)); args.send_mirror = !!(flags & TRANSPORT_PUSH_MIRROR); @@ -583,8 +674,18 @@ static int git_transport_push(struct transport *transport, struct ref *remote_re else args.push_cert = SEND_PACK_PUSH_CERT_NEVER; - ret = send_pack(&args, data->fd, data->conn, remote_refs, - &data->extra_have); + switch (data->version) { + case protocol_v2: + die("support for protocol v2 not implemented yet"); + break; + case protocol_v1: + case protocol_v0: + ret = send_pack(&args, data->fd, data->conn, remote_refs, + &data->extra_have); + break; + case protocol_unknown_version: + BUG("unknown protocol version"); + } close(data->fd[1]); close(data->fd[0]); @@ -998,6 +1099,9 @@ int transport_push(struct transport *transport, *reject_reasons = 0; transport_verify_remote_names(refspec_nr, refspec); + if (transport_color_config() < 0) + return -1; + if (transport->vtable->push_refs) { struct ref *remote_refs; struct ref *local_refs = get_local_heads(); @@ -1007,11 +1111,38 @@ int transport_push(struct transport *transport, int porcelain = flags & TRANSPORT_PUSH_PORCELAIN; int pretend = flags & TRANSPORT_PUSH_DRY_RUN; int push_ret, ret, err; + struct refspec *tmp_rs; + struct argv_array ref_prefixes = ARGV_ARRAY_INIT; + int i; if (check_push_refs(local_refs, refspec_nr, refspec) < 0) return -1; - remote_refs = transport->vtable->get_refs_list(transport, 1); + tmp_rs = parse_push_refspec(refspec_nr, refspec); + for (i = 0; i < refspec_nr; i++) { + const char *prefix = NULL; + + if (tmp_rs[i].dst) + prefix = tmp_rs[i].dst; + else if (tmp_rs[i].src && !tmp_rs[i].exact_sha1) + prefix = tmp_rs[i].src; + + if (prefix) { + const char *glob = strchr(prefix, '*'); + if (glob) + argv_array_pushf(&ref_prefixes, "%.*s", + (int)(glob - prefix), + prefix); + else + expand_ref_prefix(&ref_prefixes, prefix); + } + } + + remote_refs = transport->vtable->get_refs_list(transport, 1, + &ref_prefixes); + + argv_array_clear(&ref_prefixes); + free_refspec(refspec_nr, tmp_rs); if (flags & TRANSPORT_PUSH_ALL) match_flags |= MATCH_REFS_ALL; @@ -1117,10 +1248,13 @@ int transport_push(struct transport *transport, return 1; } -const struct ref *transport_get_remote_refs(struct transport *transport) +const struct ref *transport_get_remote_refs(struct transport *transport, + const struct argv_array *ref_prefixes) { if (!transport->got_remote_refs) { - transport->remote_refs = transport->vtable->get_refs_list(transport, 0); + transport->remote_refs = + transport->vtable->get_refs_list(transport, 0, + ref_prefixes); transport->got_remote_refs = 1; } diff --git a/transport.h b/transport.h index 3c68d73b21..73a7be3c8a 100644 --- a/transport.h +++ b/transport.h @@ -60,11 +60,23 @@ struct transport { unsigned cloning : 1; /* + * Indicates that the transport is connected via a half-duplex + * connection and should operate in stateless-rpc mode. + */ + unsigned stateless_rpc : 1; + + /* * These strings will be passed to the {pre, post}-receive hook, * on the remote side, if both sides support the push options capability. */ const struct string_list *push_options; + /* + * These strings will be passed to the remote side on each command + * request, if both sides support the server-option capability. + */ + const struct string_list *server_options; + char *pack_lockfile; signed verbose : 3; /** @@ -194,7 +206,17 @@ int transport_push(struct transport *connection, int refspec_nr, const char **refspec, int flags, unsigned int * reject_reasons); -const struct ref *transport_get_remote_refs(struct transport *transport); +/* + * Retrieve refs from a remote. + * + * Optionally a list of ref prefixes can be provided which can be sent to the + * server (when communicating using protocol v2) to enable it to limit the ref + * advertisement. Since ref filtering is done on the server's end (and only + * when using protocol v2), this can return refs which don't match the provided + * ref_prefixes. + */ +const struct ref *transport_get_remote_refs(struct transport *transport, + const struct argv_array *ref_prefixes); int transport_fetch_refs(struct transport *transport, struct ref *refs); void transport_unlock_pack(struct transport *transport); @@ -109,7 +109,7 @@ static int read_tree_1(struct tree *tree, struct strbuf *base, oid_to_hex(entry.oid), base->buf, entry.path); - oidcpy(&oid, &commit->tree->object.oid); + oidcpy(&oid, get_commit_tree_oid(commit)); } else continue; @@ -248,7 +248,7 @@ struct tree *parse_tree_indirect(const struct object_id *oid) if (obj->type == OBJ_TREE) return (struct tree *) obj; else if (obj->type == OBJ_COMMIT) - obj = &(((struct commit *) obj)->tree->object); + obj = &(get_commit_tree(((struct commit *)obj))->object); else if (obj->type == OBJ_TAG) obj = ((struct tag *) obj)->tagged; else diff --git a/unpack-trees.c b/unpack-trees.c index e73745051e..3b6c3eeccd 100644 --- a/unpack-trees.c +++ b/unpack-trees.c @@ -290,7 +290,7 @@ static void load_gitmodules_file(struct index_state *index, if (!state && ce->ce_flags & CE_WT_REMOVE) { repo_read_gitmodules(the_repository); } else if (state && (ce->ce_flags & CE_UPDATE)) { - submodule_free(); + submodule_free(the_repository); checkout_entry(ce, state, NULL); repo_read_gitmodules(the_repository); } @@ -1509,8 +1509,8 @@ static int verify_uptodate_1(const struct cache_entry *ce, add_rejected_path(o, error_type, ce->name); } -static int verify_uptodate(const struct cache_entry *ce, - struct unpack_trees_options *o) +int verify_uptodate(const struct cache_entry *ce, + struct unpack_trees_options *o) { if (!o->skip_sparse_checkout && (ce->ce_flags & CE_NEW_SKIP_WORKTREE)) return 0; diff --git a/unpack-trees.h b/unpack-trees.h index 6c48117b84..41178ada94 100644 --- a/unpack-trees.h +++ b/unpack-trees.h @@ -1,6 +1,7 @@ #ifndef UNPACK_TREES_H #define UNPACK_TREES_H +#include "tree-walk.h" #include "string-list.h" #define MAX_UNPACK_TREES 8 @@ -78,6 +79,9 @@ struct unpack_trees_options { extern int unpack_trees(unsigned n, struct tree_desc *t, struct unpack_trees_options *options); +int verify_uptodate(const struct cache_entry *ce, + struct unpack_trees_options *o); + int threeway_merge(const struct cache_entry * const *stages, struct unpack_trees_options *o); int twoway_merge(const struct cache_entry * const *src, diff --git a/upload-pack.c b/upload-pack.c index 6261d4fab3..87b4d32a6e 100644 --- a/upload-pack.c +++ b/upload-pack.c @@ -6,7 +6,6 @@ #include "tag.h" #include "object.h" #include "commit.h" -#include "exec-cmd.h" #include "diff.h" #include "revision.h" #include "list-objects.h" @@ -17,16 +16,12 @@ #include "sigchain.h" #include "version.h" #include "string-list.h" -#include "parse-options.h" #include "argv-array.h" #include "prio-queue.h" #include "protocol.h" #include "quote.h" - -static const char * const upload_pack_usage[] = { - N_("git upload-pack [<options>] <dir>"), - NULL -}; +#include "upload-pack.h" +#include "serve.h" /* Remember to update object flag allocation in object.h */ #define THEY_HAVE (1u << 11) @@ -64,7 +59,6 @@ static int keepalive = 5; * otherwise maximum packet size (up to 65520 bytes). */ static int use_sideband; -static int advertise_refs; static int stateless_rpc; static const char *pack_objects_hook; @@ -734,7 +728,6 @@ static void deepen(int depth, int deepen_relative, } send_unshallow(shallows); - packet_flush(1); } static void deepen_by_rev_list(int ac, const char **av, @@ -746,7 +739,122 @@ static void deepen_by_rev_list(int ac, const char **av, send_shallow(result); free_commit_list(result); send_unshallow(shallows); - packet_flush(1); +} + +/* Returns 1 if a shallow list is sent or 0 otherwise */ +static int send_shallow_list(int depth, int deepen_rev_list, + timestamp_t deepen_since, + struct string_list *deepen_not, + struct object_array *shallows) +{ + int ret = 0; + + if (depth > 0 && deepen_rev_list) + die("git upload-pack: deepen and deepen-since (or deepen-not) cannot be used together"); + if (depth > 0) { + deepen(depth, deepen_relative, shallows); + ret = 1; + } else if (deepen_rev_list) { + struct argv_array av = ARGV_ARRAY_INIT; + int i; + + argv_array_push(&av, "rev-list"); + if (deepen_since) + argv_array_pushf(&av, "--max-age=%"PRItime, deepen_since); + if (deepen_not->nr) { + argv_array_push(&av, "--not"); + for (i = 0; i < deepen_not->nr; i++) { + struct string_list_item *s = deepen_not->items + i; + argv_array_push(&av, s->string); + } + argv_array_push(&av, "--not"); + } + for (i = 0; i < want_obj.nr; i++) { + struct object *o = want_obj.objects[i].item; + argv_array_push(&av, oid_to_hex(&o->oid)); + } + deepen_by_rev_list(av.argc, av.argv, shallows); + argv_array_clear(&av); + ret = 1; + } else { + if (shallows->nr > 0) { + int i; + for (i = 0; i < shallows->nr; i++) + register_shallow(&shallows->objects[i].item->oid); + } + } + + shallow_nr += shallows->nr; + return ret; +} + +static int process_shallow(const char *line, struct object_array *shallows) +{ + const char *arg; + if (skip_prefix(line, "shallow ", &arg)) { + struct object_id oid; + struct object *object; + if (get_oid_hex(arg, &oid)) + die("invalid shallow line: %s", line); + object = parse_object(&oid); + if (!object) + return 1; + if (object->type != OBJ_COMMIT) + die("invalid shallow object %s", oid_to_hex(&oid)); + if (!(object->flags & CLIENT_SHALLOW)) { + object->flags |= CLIENT_SHALLOW; + add_object_array(object, NULL, shallows); + } + return 1; + } + + return 0; +} + +static int process_deepen(const char *line, int *depth) +{ + const char *arg; + if (skip_prefix(line, "deepen ", &arg)) { + char *end = NULL; + *depth = (int)strtol(arg, &end, 0); + if (!end || *end || *depth <= 0) + die("Invalid deepen: %s", line); + return 1; + } + + return 0; +} + +static int process_deepen_since(const char *line, timestamp_t *deepen_since, int *deepen_rev_list) +{ + const char *arg; + if (skip_prefix(line, "deepen-since ", &arg)) { + char *end = NULL; + *deepen_since = parse_timestamp(arg, &end, 0); + if (!end || *end || !deepen_since || + /* revisions.c's max_age -1 is special */ + *deepen_since == -1) + die("Invalid deepen-since: %s", line); + *deepen_rev_list = 1; + return 1; + } + return 0; +} + +static int process_deepen_not(const char *line, struct string_list *deepen_not, int *deepen_rev_list) +{ + const char *arg; + if (skip_prefix(line, "deepen-not ", &arg)) { + char *ref = NULL; + struct object_id oid; + if (expand_ref(arg, strlen(arg), &oid, &ref) != 1) + die("git upload-pack: ambiguous deepen-not: %s", line); + string_list_append(deepen_not, ref); + free(ref); + *deepen_rev_list = 1; + return 1; + } + return 0; } static void receive_needs(void) @@ -770,55 +878,22 @@ static void receive_needs(void) if (!line) break; - if (skip_prefix(line, "shallow ", &arg)) { - struct object_id oid; - struct object *object; - if (get_oid_hex(arg, &oid)) - die("invalid shallow line: %s", line); - object = parse_object(&oid); - if (!object) - continue; - if (object->type != OBJ_COMMIT) - die("invalid shallow object %s", oid_to_hex(&oid)); - if (!(object->flags & CLIENT_SHALLOW)) { - object->flags |= CLIENT_SHALLOW; - add_object_array(object, NULL, &shallows); - } + if (process_shallow(line, &shallows)) continue; - } - if (skip_prefix(line, "deepen ", &arg)) { - char *end = NULL; - depth = strtol(arg, &end, 0); - if (!end || *end || depth <= 0) - die("Invalid deepen: %s", line); + if (process_deepen(line, &depth)) continue; - } - if (skip_prefix(line, "deepen-since ", &arg)) { - char *end = NULL; - deepen_since = parse_timestamp(arg, &end, 0); - if (!end || *end || !deepen_since || - /* revisions.c's max_age -1 is special */ - deepen_since == -1) - die("Invalid deepen-since: %s", line); - deepen_rev_list = 1; + if (process_deepen_since(line, &deepen_since, &deepen_rev_list)) continue; - } - if (skip_prefix(line, "deepen-not ", &arg)) { - char *ref = NULL; - struct object_id oid; - if (expand_ref(arg, strlen(arg), &oid, &ref) != 1) - die("git upload-pack: ambiguous deepen-not: %s", line); - string_list_append(&deepen_not, ref); - free(ref); - deepen_rev_list = 1; + if (process_deepen_not(line, &deepen_not, &deepen_rev_list)) continue; - } + if (skip_prefix(line, "filter ", &arg)) { if (!filter_capability_requested) die("git upload-pack: filtering capability not negotiated"); parse_list_objects_filter(&filter_options, arg); continue; } + if (!skip_prefix(line, "want ", &arg) || get_oid_hex(arg, &oid_buf)) die("git upload-pack: protocol error, " @@ -881,40 +956,10 @@ static void receive_needs(void) if (depth == 0 && !deepen_rev_list && shallows.nr == 0) return; - if (depth > 0 && deepen_rev_list) - die("git upload-pack: deepen and deepen-since (or deepen-not) cannot be used together"); - if (depth > 0) - deepen(depth, deepen_relative, &shallows); - else if (deepen_rev_list) { - struct argv_array av = ARGV_ARRAY_INIT; - int i; - argv_array_push(&av, "rev-list"); - if (deepen_since) - argv_array_pushf(&av, "--max-age=%"PRItime, deepen_since); - if (deepen_not.nr) { - argv_array_push(&av, "--not"); - for (i = 0; i < deepen_not.nr; i++) { - struct string_list_item *s = deepen_not.items + i; - argv_array_push(&av, s->string); - } - argv_array_push(&av, "--not"); - } - for (i = 0; i < want_obj.nr; i++) { - struct object *o = want_obj.objects[i].item; - argv_array_push(&av, oid_to_hex(&o->oid)); - } - deepen_by_rev_list(av.argc, av.argv, &shallows); - argv_array_clear(&av); - } - else - if (shallows.nr > 0) { - int i; - for (i = 0; i < shallows.nr; i++) - register_shallow(&shallows.objects[i].item->oid); - } - - shallow_nr += shallows.nr; + if (send_shallow_list(depth, deepen_rev_list, deepen_since, + &deepen_not, &shallows)) + packet_flush(1); object_array_clear(&shallows); } @@ -1004,33 +1049,6 @@ static int find_symref(const char *refname, const struct object_id *oid, return 0; } -static void upload_pack(void) -{ - struct string_list symref = STRING_LIST_INIT_DUP; - - head_ref_namespaced(find_symref, &symref); - - if (advertise_refs || !stateless_rpc) { - reset_timeout(); - head_ref_namespaced(send_ref, &symref); - for_each_namespaced_ref(send_ref, &symref); - advertise_shallow_grafts(1); - packet_flush(1); - } else { - head_ref_namespaced(check_ref, NULL); - for_each_namespaced_ref(check_ref, NULL); - } - string_list_clear(&symref, 1); - if (advertise_refs) - return; - - receive_needs(); - if (want_obj.nr) { - get_common_commits(); - create_pack_file(); - } -} - static int upload_pack_config(const char *var, const char *value, void *unused) { if (!strcmp("uploadpack.allowtipsha1inwant", var)) { @@ -1061,58 +1079,356 @@ static int upload_pack_config(const char *var, const char *value, void *unused) return parse_hide_refs_config(var, value, "uploadpack"); } -int cmd_main(int argc, const char **argv) +void upload_pack(struct upload_pack_options *options) { - const char *dir; - int strict = 0; - struct option options[] = { - OPT_BOOL(0, "stateless-rpc", &stateless_rpc, - N_("quit after a single request/response exchange")), - OPT_BOOL(0, "advertise-refs", &advertise_refs, - N_("exit immediately after initial ref advertisement")), - OPT_BOOL(0, "strict", &strict, - N_("do not try <directory>/.git/ if <directory> is no Git directory")), - OPT_INTEGER(0, "timeout", &timeout, - N_("interrupt transfer after <n> seconds of inactivity")), - OPT_END() - }; + struct string_list symref = STRING_LIST_INIT_DUP; - packet_trace_identity("upload-pack"); - check_replace_refs = 0; + stateless_rpc = options->stateless_rpc; + timeout = options->timeout; + daemon_mode = options->daemon_mode; - argc = parse_options(argc, argv, NULL, options, upload_pack_usage, 0); + git_config(upload_pack_config, NULL); - if (argc != 1) - usage_with_options(upload_pack_usage, options); + head_ref_namespaced(find_symref, &symref); - if (timeout) - daemon_mode = 1; + if (options->advertise_refs || !stateless_rpc) { + reset_timeout(); + head_ref_namespaced(send_ref, &symref); + for_each_namespaced_ref(send_ref, &symref); + advertise_shallow_grafts(1); + packet_flush(1); + } else { + head_ref_namespaced(check_ref, NULL); + for_each_namespaced_ref(check_ref, NULL); + } + string_list_clear(&symref, 1); + if (options->advertise_refs) + return; - setup_path(); + receive_needs(); + if (want_obj.nr) { + get_common_commits(); + create_pack_file(); + } +} - dir = argv[0]; +struct upload_pack_data { + struct object_array wants; + struct oid_array haves; - if (!enter_repo(dir, strict)) - die("'%s' does not appear to be a git repository", dir); + struct object_array shallows; + struct string_list deepen_not; + int depth; + timestamp_t deepen_since; + int deepen_rev_list; + int deepen_relative; - git_config(upload_pack_config, NULL); + unsigned stateless_rpc : 1; - switch (determine_protocol_version_server()) { - case protocol_v1: - /* - * v1 is just the original protocol with a version string, - * so just fall through after writing the version string. - */ - if (advertise_refs || !stateless_rpc) - packet_write_fmt(1, "version 1\n"); - - /* fallthrough */ - case protocol_v0: - upload_pack(); - break; - case protocol_unknown_version: - BUG("unknown protocol version"); + unsigned use_thin_pack : 1; + unsigned use_ofs_delta : 1; + unsigned no_progress : 1; + unsigned use_include_tag : 1; + unsigned done : 1; +}; + +static void upload_pack_data_init(struct upload_pack_data *data) +{ + struct object_array wants = OBJECT_ARRAY_INIT; + struct oid_array haves = OID_ARRAY_INIT; + struct object_array shallows = OBJECT_ARRAY_INIT; + struct string_list deepen_not = STRING_LIST_INIT_DUP; + + memset(data, 0, sizeof(*data)); + data->wants = wants; + data->haves = haves; + data->shallows = shallows; + data->deepen_not = deepen_not; +} + +static void upload_pack_data_clear(struct upload_pack_data *data) +{ + object_array_clear(&data->wants); + oid_array_clear(&data->haves); + object_array_clear(&data->shallows); + string_list_clear(&data->deepen_not, 0); +} + +static int parse_want(const char *line) +{ + const char *arg; + if (skip_prefix(line, "want ", &arg)) { + struct object_id oid; + struct object *o; + + if (get_oid_hex(arg, &oid)) + die("git upload-pack: protocol error, " + "expected to get oid, not '%s'", line); + + o = parse_object(&oid); + if (!o) { + packet_write_fmt(1, + "ERR upload-pack: not our ref %s", + oid_to_hex(&oid)); + die("git upload-pack: not our ref %s", + oid_to_hex(&oid)); + } + + if (!(o->flags & WANTED)) { + o->flags |= WANTED; + add_object_array(o, NULL, &want_obj); + } + + return 1; + } + + return 0; +} + +static int parse_have(const char *line, struct oid_array *haves) +{ + const char *arg; + if (skip_prefix(line, "have ", &arg)) { + struct object_id oid; + + if (get_oid_hex(arg, &oid)) + die("git upload-pack: expected SHA1 object, got '%s'", arg); + oid_array_append(haves, &oid); + return 1; } return 0; } + +static void process_args(struct packet_reader *request, + struct upload_pack_data *data) +{ + while (packet_reader_read(request) != PACKET_READ_FLUSH) { + const char *arg = request->line; + + /* process want */ + if (parse_want(arg)) + continue; + /* process have line */ + if (parse_have(arg, &data->haves)) + continue; + + /* process args like thin-pack */ + if (!strcmp(arg, "thin-pack")) { + use_thin_pack = 1; + continue; + } + if (!strcmp(arg, "ofs-delta")) { + use_ofs_delta = 1; + continue; + } + if (!strcmp(arg, "no-progress")) { + no_progress = 1; + continue; + } + if (!strcmp(arg, "include-tag")) { + use_include_tag = 1; + continue; + } + if (!strcmp(arg, "done")) { + data->done = 1; + continue; + } + + /* Shallow related arguments */ + if (process_shallow(arg, &data->shallows)) + continue; + if (process_deepen(arg, &data->depth)) + continue; + if (process_deepen_since(arg, &data->deepen_since, + &data->deepen_rev_list)) + continue; + if (process_deepen_not(arg, &data->deepen_not, + &data->deepen_rev_list)) + continue; + if (!strcmp(arg, "deepen-relative")) { + data->deepen_relative = 1; + continue; + } + + /* ignore unknown lines maybe? */ + die("unexpect line: '%s'", arg); + } +} + +static int process_haves(struct oid_array *haves, struct oid_array *common) +{ + int i; + + /* Process haves */ + for (i = 0; i < haves->nr; i++) { + const struct object_id *oid = &haves->oid[i]; + struct object *o; + int we_knew_they_have = 0; + + if (!has_object_file(oid)) + continue; + + oid_array_append(common, oid); + + o = parse_object(oid); + if (!o) + die("oops (%s)", oid_to_hex(oid)); + if (o->type == OBJ_COMMIT) { + struct commit_list *parents; + struct commit *commit = (struct commit *)o; + if (o->flags & THEY_HAVE) + we_knew_they_have = 1; + else + o->flags |= THEY_HAVE; + if (!oldest_have || (commit->date < oldest_have)) + oldest_have = commit->date; + for (parents = commit->parents; + parents; + parents = parents->next) + parents->item->object.flags |= THEY_HAVE; + } + if (!we_knew_they_have) + add_object_array(o, NULL, &have_obj); + } + + return 0; +} + +static int send_acks(struct oid_array *acks, struct strbuf *response) +{ + int i; + + packet_buf_write(response, "acknowledgments\n"); + + /* Send Acks */ + if (!acks->nr) + packet_buf_write(response, "NAK\n"); + + for (i = 0; i < acks->nr; i++) { + packet_buf_write(response, "ACK %s\n", + oid_to_hex(&acks->oid[i])); + } + + if (ok_to_give_up()) { + /* Send Ready */ + packet_buf_write(response, "ready\n"); + return 1; + } + + return 0; +} + +static int process_haves_and_send_acks(struct upload_pack_data *data) +{ + struct oid_array common = OID_ARRAY_INIT; + struct strbuf response = STRBUF_INIT; + int ret = 0; + + process_haves(&data->haves, &common); + if (data->done) { + ret = 1; + } else if (send_acks(&common, &response)) { + packet_buf_delim(&response); + ret = 1; + } else { + /* Add Flush */ + packet_buf_flush(&response); + ret = 0; + } + + /* Send response */ + write_or_die(1, response.buf, response.len); + strbuf_release(&response); + + oid_array_clear(&data->haves); + oid_array_clear(&common); + return ret; +} + +static void send_shallow_info(struct upload_pack_data *data) +{ + /* No shallow info needs to be sent */ + if (!data->depth && !data->deepen_rev_list && !data->shallows.nr && + !is_repository_shallow()) + return; + + packet_write_fmt(1, "shallow-info\n"); + + if (!send_shallow_list(data->depth, data->deepen_rev_list, + data->deepen_since, &data->deepen_not, + &data->shallows) && is_repository_shallow()) + deepen(INFINITE_DEPTH, data->deepen_relative, &data->shallows); + + packet_delim(1); +} + +enum fetch_state { + FETCH_PROCESS_ARGS = 0, + FETCH_SEND_ACKS, + FETCH_SEND_PACK, + FETCH_DONE, +}; + +int upload_pack_v2(struct repository *r, struct argv_array *keys, + struct packet_reader *request) +{ + enum fetch_state state = FETCH_PROCESS_ARGS; + struct upload_pack_data data; + + upload_pack_data_init(&data); + use_sideband = LARGE_PACKET_MAX; + + while (state != FETCH_DONE) { + switch (state) { + case FETCH_PROCESS_ARGS: + process_args(request, &data); + + if (!want_obj.nr) { + /* + * Request didn't contain any 'want' lines, + * guess they didn't want anything. + */ + state = FETCH_DONE; + } else if (data.haves.nr) { + /* + * Request had 'have' lines, so lets ACK them. + */ + state = FETCH_SEND_ACKS; + } else { + /* + * Request had 'want's but no 'have's so we can + * immedietly go to construct and send a pack. + */ + state = FETCH_SEND_PACK; + } + break; + case FETCH_SEND_ACKS: + if (process_haves_and_send_acks(&data)) + state = FETCH_SEND_PACK; + else + state = FETCH_DONE; + break; + case FETCH_SEND_PACK: + send_shallow_info(&data); + + packet_write_fmt(1, "packfile\n"); + create_pack_file(); + state = FETCH_DONE; + break; + case FETCH_DONE: + continue; + } + } + + upload_pack_data_clear(&data); + return 0; +} + +int upload_pack_advertise(struct repository *r, + struct strbuf *value) +{ + if (value) + strbuf_addstr(value, "shallow"); + return 1; +} diff --git a/upload-pack.h b/upload-pack.h new file mode 100644 index 0000000000..cab2178796 --- /dev/null +++ b/upload-pack.h @@ -0,0 +1,23 @@ +#ifndef UPLOAD_PACK_H +#define UPLOAD_PACK_H + +struct upload_pack_options { + int stateless_rpc; + int advertise_refs; + unsigned int timeout; + int daemon_mode; +}; + +void upload_pack(struct upload_pack_options *options); + +struct repository; +struct argv_array; +struct packet_reader; +extern int upload_pack_v2(struct repository *r, struct argv_array *keys, + struct packet_reader *request); + +struct strbuf; +extern int upload_pack_advertise(struct repository *r, + struct strbuf *value); + +#endif /* UPLOAD_PACK_H */ @@ -401,18 +401,40 @@ out: strbuf_release(&sb_dst); } +/* + * Returns true (1) if the src encoding name matches the dst encoding + * name directly or one of its alternative names. E.g. UTF-16BE is the + * same as UTF16BE. + */ +static int same_utf_encoding(const char *src, const char *dst) +{ + if (istarts_with(src, "utf") && istarts_with(dst, "utf")) { + /* src[3] or dst[3] might be '\0' */ + int i = (src[3] == '-' ? 4 : 3); + int j = (dst[3] == '-' ? 4 : 3); + return !strcasecmp(src+i, dst+j); + } + return 0; +} + int is_encoding_utf8(const char *name) { if (!name) return 1; - if (!strcasecmp(name, "utf-8") || !strcasecmp(name, "utf8")) + if (same_utf_encoding("utf-8", name)) return 1; return 0; } int same_encoding(const char *src, const char *dst) { - if (is_encoding_utf8(src) && is_encoding_utf8(dst)) + static const char utf8[] = "UTF-8"; + + if (!src) + src = utf8; + if (!dst) + dst = utf8; + if (same_utf_encoding(src, dst)) return 1; return !strcasecmp(src, dst); } @@ -538,6 +560,45 @@ char *reencode_string_len(const char *in, int insz, } #endif +static int has_bom_prefix(const char *data, size_t len, + const char *bom, size_t bom_len) +{ + return data && bom && (len >= bom_len) && !memcmp(data, bom, bom_len); +} + +static const char utf16_be_bom[] = {0xFE, 0xFF}; +static const char utf16_le_bom[] = {0xFF, 0xFE}; +static const char utf32_be_bom[] = {0x00, 0x00, 0xFE, 0xFF}; +static const char utf32_le_bom[] = {0xFF, 0xFE, 0x00, 0x00}; + +int has_prohibited_utf_bom(const char *enc, const char *data, size_t len) +{ + return ( + (same_utf_encoding("UTF-16BE", enc) || + same_utf_encoding("UTF-16LE", enc)) && + (has_bom_prefix(data, len, utf16_be_bom, sizeof(utf16_be_bom)) || + has_bom_prefix(data, len, utf16_le_bom, sizeof(utf16_le_bom))) + ) || ( + (same_utf_encoding("UTF-32BE", enc) || + same_utf_encoding("UTF-32LE", enc)) && + (has_bom_prefix(data, len, utf32_be_bom, sizeof(utf32_be_bom)) || + has_bom_prefix(data, len, utf32_le_bom, sizeof(utf32_le_bom))) + ); +} + +int is_missing_required_utf_bom(const char *enc, const char *data, size_t len) +{ + return ( + (same_utf_encoding(enc, "UTF-16")) && + !(has_bom_prefix(data, len, utf16_be_bom, sizeof(utf16_be_bom)) || + has_bom_prefix(data, len, utf16_le_bom, sizeof(utf16_le_bom))) + ) || ( + (same_utf_encoding(enc, "UTF-32")) && + !(has_bom_prefix(data, len, utf32_be_bom, sizeof(utf32_be_bom)) || + has_bom_prefix(data, len, utf32_le_bom, sizeof(utf32_le_bom))) + ); +} + /* * Returns first character length in bytes for multi-byte `text` according to * `encoding`. @@ -70,4 +70,32 @@ typedef enum { void strbuf_utf8_align(struct strbuf *buf, align_type position, unsigned int width, const char *s); +/* + * If a data stream is declared as UTF-16BE or UTF-16LE, then a UTF-16 + * BOM must not be used [1]. The same applies for the UTF-32 equivalents. + * The function returns true if this rule is violated. + * + * [1] http://unicode.org/faq/utf_bom.html#bom10 + */ +int has_prohibited_utf_bom(const char *enc, const char *data, size_t len); + +/* + * If the endianness is not defined in the encoding name, then we + * require a BOM. The function returns true if a required BOM is missing. + * + * The Unicode standard instructs to assume big-endian if there in no + * BOM for UTF-16/32 [1][2]. However, the W3C/WHATWG encoding standard + * used in HTML5 recommends to assume little-endian to "deal with + * deployed content" [3]. + * + * Therefore, strictly requiring a BOM seems to be the safest option for + * content in Git. + * + * [1] http://unicode.org/faq/utf_bom.html#gen6 + * [2] http://www.unicode.org/versions/Unicode10.0.0/ch03.pdf + * Section 3.10, D98, page 132 + * [3] https://encoding.spec.whatwg.org/#utf-16le + */ +int is_missing_required_utf_bom(const char *enc, const char *data, size_t len); + #endif @@ -72,6 +72,8 @@ static struct commit_list *complete = NULL; static int process_commit(struct walker *walker, struct commit *commit) { + struct commit_list *parents; + if (parse_commit(commit)) return -1; @@ -86,19 +88,14 @@ static int process_commit(struct walker *walker, struct commit *commit) walker_say(walker, "walk %s\n", oid_to_hex(&commit->object.oid)); - if (walker->get_tree) { - if (process(walker, &commit->tree->object)) + if (process(walker, &get_commit_tree(commit)->object)) + return -1; + + for (parents = commit->parents; parents; parents = parents->next) { + if (process(walker, &parents->item->object)) return -1; - if (!walker->get_all) - walker->get_tree = 0; - } - if (walker->get_history) { - struct commit_list *parents = commit->parents; - for (; parents; parents = parents->next) { - if (process(walker, &parents->item->object)) - return -1; - } } + return 0; } @@ -9,9 +9,6 @@ struct walker { void (*prefetch)(struct walker *, unsigned char *sha1); int (*fetch)(struct walker *, unsigned char *sha1); void (*cleanup)(struct walker *); - int get_tree; - int get_history; - int get_all; int get_verbosely; int get_recover; diff --git a/wrap-for-bin.sh b/wrap-for-bin.sh index 5842408817..95851b85b6 100644 --- a/wrap-for-bin.sh +++ b/wrap-for-bin.sh @@ -20,10 +20,17 @@ PATH='@@BUILD_DIR@@/bin-wrappers:'"$PATH" export GIT_EXEC_PATH GITPERLLIB PATH GIT_TEXTDOMAINDIR -if test -n "$GIT_TEST_GDB" -then - unset GIT_TEST_GDB - exec gdb --args "${GIT_EXEC_PATH}/@@PROG@@" "$@" -else +case "$GIT_DEBUGGER" in +'') exec "${GIT_EXEC_PATH}/@@PROG@@" "$@" -fi + ;; +1) + unset GIT_DEBUGGER + exec gdb --args "${GIT_EXEC_PATH}/@@PROG@@" "$@" + ;; +*) + GIT_DEBUGGER_ARGS="$GIT_DEBUGGER" + unset GIT_DEBUGGER + exec ${GIT_DEBUGGER_ARGS} "${GIT_EXEC_PATH}/@@PROG@@" "$@" + ;; +esac |