From 7c67d2a07055150b76e81efa8850221d52705305 Mon Sep 17 00:00:00 2001 From: Justin Tobler Date: Fri, 28 Feb 2025 15:33:43 -0600 Subject: [PATCH 1/4] diff: return diff_filepair from diff queue helpers The `diff_addremove()` and `diff_change()` functions set up and queue diffs, but do not return the `diff_filepair` added to the queue. In a subsequent commit, modifications to `diff_filepair` need to occur in certain cases after being queued. Since the existing `diff_addremove()` and `diff_change()` are also used for callbacks in `diff_options` as types `add_remove_fn_t` and `change_fn_t`, modifying the existing function signatures requires further changes. The diff options for pruning use `file_add_remove()` and `file_change()` where file pairs do not even get queued. Thus, separate functions are implemented instead. Split out the queuing operations into `diff_queue_addremove()` and `diff_queue_change()` which also return a handle to the queued `diff_filepair`. Both `diff_addremove()` and `diff_change()` are reimplemented as thin wrappers around the new functions. Signed-off-by: Justin Tobler Signed-off-by: Junio C Hamano --- diff.c | 70 +++++++++++++++++++++++++++++++++++++++++----------------- diff.h | 25 +++++++++++++++++++++ 2 files changed, 75 insertions(+), 20 deletions(-) diff --git a/diff.c b/diff.c index c89c15d98e..4ddfe523fe 100644 --- a/diff.c +++ b/diff.c @@ -7161,16 +7161,19 @@ void compute_diffstat(struct diff_options *options, options->found_changes = !!diffstat->nr; } -void diff_addremove(struct diff_options *options, - int addremove, unsigned mode, - const struct object_id *oid, - int oid_valid, - const char *concatpath, unsigned dirty_submodule) +struct diff_filepair *diff_queue_addremove(struct diff_queue_struct *queue, + struct diff_options *options, + int addremove, unsigned mode, + const struct object_id *oid, + int oid_valid, + const char *concatpath, + unsigned dirty_submodule) { struct diff_filespec *one, *two; + struct diff_filepair *pair; if (S_ISGITLINK(mode) && is_submodule_ignored(concatpath, options)) - return; + return NULL; /* This may look odd, but it is a preparation for * feeding "there are unchanged files which should @@ -7190,7 +7193,7 @@ void diff_addremove(struct diff_options *options, if (options->prefix && strncmp(concatpath, options->prefix, options->prefix_length)) - return; + return NULL; one = alloc_filespec(concatpath); two = alloc_filespec(concatpath); @@ -7202,25 +7205,29 @@ void diff_addremove(struct diff_options *options, two->dirty_submodule = dirty_submodule; } - diff_queue(&diff_queued_diff, one, two); + pair = diff_queue(queue, one, two); if (!options->flags.diff_from_contents) options->flags.has_changes = 1; + + return pair; } -void diff_change(struct diff_options *options, - unsigned old_mode, unsigned new_mode, - const struct object_id *old_oid, - const struct object_id *new_oid, - int old_oid_valid, int new_oid_valid, - const char *concatpath, - unsigned old_dirty_submodule, unsigned new_dirty_submodule) +struct diff_filepair *diff_queue_change(struct diff_queue_struct *queue, + struct diff_options *options, + unsigned old_mode, unsigned new_mode, + const struct object_id *old_oid, + const struct object_id *new_oid, + int old_oid_valid, int new_oid_valid, + const char *concatpath, + unsigned old_dirty_submodule, + unsigned new_dirty_submodule) { struct diff_filespec *one, *two; struct diff_filepair *p; if (S_ISGITLINK(old_mode) && S_ISGITLINK(new_mode) && is_submodule_ignored(concatpath, options)) - return; + return NULL; if (options->flags.reverse_diff) { SWAP(old_mode, new_mode); @@ -7231,7 +7238,7 @@ void diff_change(struct diff_options *options, if (options->prefix && strncmp(concatpath, options->prefix, options->prefix_length)) - return; + return NULL; one = alloc_filespec(concatpath); two = alloc_filespec(concatpath); @@ -7239,19 +7246,42 @@ void diff_change(struct diff_options *options, fill_filespec(two, new_oid, new_oid_valid, new_mode); one->dirty_submodule = old_dirty_submodule; two->dirty_submodule = new_dirty_submodule; - p = diff_queue(&diff_queued_diff, one, two); + p = diff_queue(queue, one, two); if (options->flags.diff_from_contents) - return; + return p; if (options->flags.quick && options->skip_stat_unmatch && !diff_filespec_check_stat_unmatch(options->repo, p)) { diff_free_filespec_data(p->one); diff_free_filespec_data(p->two); - return; + return p; } options->flags.has_changes = 1; + + return p; +} + +void diff_addremove(struct diff_options *options, int addremove, unsigned mode, + const struct object_id *oid, int oid_valid, + const char *concatpath, unsigned dirty_submodule) +{ + diff_queue_addremove(&diff_queued_diff, options, addremove, mode, oid, + oid_valid, concatpath, dirty_submodule); +} + +void diff_change(struct diff_options *options, + unsigned old_mode, unsigned new_mode, + const struct object_id *old_oid, + const struct object_id *new_oid, + int old_oid_valid, int new_oid_valid, + const char *concatpath, + unsigned old_dirty_submodule, unsigned new_dirty_submodule) +{ + diff_queue_change(&diff_queued_diff, options, old_mode, new_mode, + old_oid, new_oid, old_oid_valid, new_oid_valid, + concatpath, old_dirty_submodule, new_dirty_submodule); } struct diff_filepair *diff_unmerge(struct diff_options *options, const char *path) diff --git a/diff.h b/diff.h index 0a566f5531..63afa17e84 100644 --- a/diff.h +++ b/diff.h @@ -508,6 +508,31 @@ void diff_set_default_prefix(struct diff_options *options); int diff_can_quit_early(struct diff_options *); +/* + * Stages changes in the provided diff queue for file additions and deletions. + * If a file pair gets queued, it is returned. + */ +struct diff_filepair *diff_queue_addremove(struct diff_queue_struct *queue, + struct diff_options *, + int addremove, unsigned mode, + const struct object_id *oid, + int oid_valid, const char *fullpath, + unsigned dirty_submodule); + +/* + * Stages changes in the provided diff queue for file modifications. + * If a file pair gets queued, it is returned. + */ +struct diff_filepair *diff_queue_change(struct diff_queue_struct *queue, + struct diff_options *, + unsigned mode1, unsigned mode2, + const struct object_id *old_oid, + const struct object_id *new_oid, + int old_oid_valid, int new_oid_valid, + const char *fullpath, + unsigned dirty_submodule1, + unsigned dirty_submodule2); + void diff_addremove(struct diff_options *, int addremove, unsigned mode, From c8a8e04099a99d6eafbe6e9bb1db3b50996836f8 Mon Sep 17 00:00:00 2001 From: Justin Tobler Date: Fri, 28 Feb 2025 15:33:44 -0600 Subject: [PATCH 2/4] diff: add option to skip resolving diff statuses By default, `diffcore_std()` resolves the statuses for queued diff file pairs by calling `diff_resolve_rename_copy()`. If status information is already manually set, invoking `diffcore_std()` may change the status value. Introduce the `skip_resolving_statuses` diff option that prevents `diffcore_std()` from resolving file pair statuses when enabled. Signed-off-by: Justin Tobler Signed-off-by: Junio C Hamano --- diff.c | 2 +- diff.h | 8 ++++++++ 2 files changed, 9 insertions(+), 1 deletion(-) diff --git a/diff.c b/diff.c index 4ddfe523fe..08f5e00a2c 100644 --- a/diff.c +++ b/diff.c @@ -7085,7 +7085,7 @@ void diffcore_std(struct diff_options *options) diffcore_order(options->orderfile); if (options->rotate_to) diffcore_rotate(options); - if (!options->found_follow) + if (!options->found_follow && !options->skip_resolving_statuses) /* See try_to_follow_renames() in tree-diff.c */ diff_resolve_rename_copy(); diffcore_apply_filter(options); diff --git a/diff.h b/diff.h index 63afa17e84..fc791ee2cc 100644 --- a/diff.h +++ b/diff.h @@ -353,6 +353,14 @@ struct diff_options { /* to support internal diff recursion by --follow hack*/ int found_follow; + /* + * By default, diffcore_std() resolves the statuses for queued diff file + * pairs by calling diff_resolve_rename_copy(). If status information + * has already been manually set, this option prevents diffcore_std() + * from resetting statuses. + */ + int skip_resolving_statuses; + /* Callback which allows tweaking the options in diff_setup_done(). */ void (*set_default)(struct diff_options *); From 5bd10b2adcf3a080169574dd08c5529de81eecb1 Mon Sep 17 00:00:00 2001 From: Justin Tobler Date: Fri, 28 Feb 2025 15:33:45 -0600 Subject: [PATCH 3/4] builtin: introduce diff-pairs command Through git-diff(1), a single diff can be generated from a pair of blob revisions directly. Unfortunately, there is not a mechanism to compute batches of specific file pair diffs in a single process. Such a feature is particularly useful on the server-side where diffing between a large set of changes is not feasible all at once due to timeout concerns. To facilitate this, introduce git-diff-pairs(1) which acts as a backend passing its NUL-terminated raw diff format input from stdin through diff machinery to produce various forms of output such as patch or raw. The raw format was originally designed as an interchange format and represents the contents of the diff_queued_diff list making it possible to break the diff pipeline into separate stages. For example, git-diff-tree(1) can be used as a frontend to compute file pairs to queue and feed its raw output to git-diff-pairs(1) to compute patches. With this, batches of diffs can be progressively generated without having to recompute renames or retrieve object context. Something like the following: git diff-tree -r -z -M $old $new | git diff-pairs -p -z should generate the same output as `git diff-tree -p -M`. Furthermore, each line of raw diff formatted input can also be individually fed to a separate git-diff-pairs(1) process and still produce the same output. Based-on-patch-by: Jeff King Signed-off-by: Justin Tobler Signed-off-by: Junio C Hamano --- .gitignore | 1 + Documentation/git-diff-pairs.adoc | 56 +++++++++ Documentation/meson.build | 1 + Makefile | 1 + builtin.h | 1 + builtin/diff-pairs.c | 193 ++++++++++++++++++++++++++++++ command-list.txt | 1 + git.c | 1 + meson.build | 1 + t/meson.build | 1 + t/t4070-diff-pairs.sh | 81 +++++++++++++ 11 files changed, 338 insertions(+) create mode 100644 Documentation/git-diff-pairs.adoc create mode 100644 builtin/diff-pairs.c create mode 100755 t/t4070-diff-pairs.sh diff --git a/.gitignore b/.gitignore index 08a66ca508..04c444404e 100644 --- a/.gitignore +++ b/.gitignore @@ -55,6 +55,7 @@ /git-diff /git-diff-files /git-diff-index +/git-diff-pairs /git-diff-tree /git-difftool /git-difftool--helper diff --git a/Documentation/git-diff-pairs.adoc b/Documentation/git-diff-pairs.adoc new file mode 100644 index 0000000000..e31f2e2fbb --- /dev/null +++ b/Documentation/git-diff-pairs.adoc @@ -0,0 +1,56 @@ +git-diff-pairs(1) +================= + +NAME +---- +git-diff-pairs - Compare the content and mode of provided blob pairs + +SYNOPSIS +-------- +[synopsis] +git diff-pairs -z [] + +DESCRIPTION +----------- +Show changes for file pairs provided on stdin. Input for this command must be +in the NUL-terminated raw output format as generated by commands such as `git +diff-tree -z -r --raw`. By default, the outputted diffs are computed and shown +in the patch format when stdin closes. + +Usage of this command enables the traditional diff pipeline to be broken up +into separate stages where `diff-pairs` acts as the output phase. Other +commands, such as `diff-tree`, may serve as a frontend to compute the raw +diff format used as input. + +Instead of computing diffs via `git diff-tree -p -M` in one step, `diff-tree` +can compute the file pairs and rename information without the blob diffs. This +output can be fed to `diff-pairs` to generate the underlying blob diffs as done +in the following example: + +----------------------------- +git diff-tree -z -r -M $a $b | +git diff-pairs -z +----------------------------- + +Computing the tree diff upfront with rename information allows patch output +from `diff-pairs` to be progressively computed over the course of potentially +multiple invocations. + +Pathspecs are not currently supported by `diff-pairs`. Pathspec limiting should +be performed by the upstream command generating the raw diffs used as input. + +Tree objects are not currently supported as input and are rejected. + +Abbreviated object IDs in the `diff-pairs` input are not supported. Outputted +object IDs can be abbreviated using the `--abbrev` option. + +OPTIONS +------- + +include::diff-options.adoc[] + +include::diff-generate-patch.adoc[] + +GIT +--- +Part of the linkgit:git[1] suite diff --git a/Documentation/meson.build b/Documentation/meson.build index 1129ce4c85..ce990e9fe5 100644 --- a/Documentation/meson.build +++ b/Documentation/meson.build @@ -42,6 +42,7 @@ manpages = { 'git-diagnose.adoc' : 1, 'git-diff-files.adoc' : 1, 'git-diff-index.adoc' : 1, + 'git-diff-pairs.adoc' : 1, 'git-difftool.adoc' : 1, 'git-diff-tree.adoc' : 1, 'git-diff.adoc' : 1, diff --git a/Makefile b/Makefile index 6d45093089..ee48bcad20 100644 --- a/Makefile +++ b/Makefile @@ -1242,6 +1242,7 @@ BUILTIN_OBJS += builtin/describe.o BUILTIN_OBJS += builtin/diagnose.o BUILTIN_OBJS += builtin/diff-files.o BUILTIN_OBJS += builtin/diff-index.o +BUILTIN_OBJS += builtin/diff-pairs.o BUILTIN_OBJS += builtin/diff-tree.o BUILTIN_OBJS += builtin/diff.o BUILTIN_OBJS += builtin/difftool.o diff --git a/builtin.h b/builtin.h index 89928ccf92..e6aad3a6a1 100644 --- a/builtin.h +++ b/builtin.h @@ -153,6 +153,7 @@ int cmd_diagnose(int argc, const char **argv, const char *prefix, struct reposit int cmd_diff_files(int argc, const char **argv, const char *prefix, struct repository *repo); int cmd_diff_index(int argc, const char **argv, const char *prefix, struct repository *repo); int cmd_diff(int argc, const char **argv, const char *prefix, struct repository *repo); +int cmd_diff_pairs(int argc, const char **argv, const char *prefix, struct repository *repo); int cmd_diff_tree(int argc, const char **argv, const char *prefix, struct repository *repo); int cmd_difftool(int argc, const char **argv, const char *prefix, struct repository *repo); int cmd_env__helper(int argc, const char **argv, const char *prefix, struct repository *repo); diff --git a/builtin/diff-pairs.c b/builtin/diff-pairs.c new file mode 100644 index 0000000000..6be17c1abd --- /dev/null +++ b/builtin/diff-pairs.c @@ -0,0 +1,193 @@ +#include "builtin.h" +#include "config.h" +#include "diff.h" +#include "diffcore.h" +#include "gettext.h" +#include "hash.h" +#include "hex.h" +#include "object.h" +#include "parse-options.h" +#include "revision.h" +#include "strbuf.h" + +static unsigned parse_mode_or_die(const char *mode, const char **end) +{ + uint16_t ret; + + *end = parse_mode(mode, &ret); + if (!*end) + die(_("unable to parse mode: %s"), mode); + return ret; +} + +static void parse_oid_or_die(const char *hex, struct object_id *oid, + const char **end, const struct git_hash_algo *algop) +{ + if (parse_oid_hex_algop(hex, oid, end, algop) || *(*end)++ != ' ') + die(_("unable to parse object id: %s"), hex); +} + +int cmd_diff_pairs(int argc, const char **argv, const char *prefix, + struct repository *repo) +{ + struct strbuf path_dst = STRBUF_INIT; + struct strbuf path = STRBUF_INIT; + struct strbuf meta = STRBUF_INIT; + struct option *parseopts; + struct rev_info revs; + int line_term = '\0'; + int ret; + + const char * const builtin_diff_pairs_usage[] = { + N_("git diff-pairs -z []"), + NULL + }; + struct option builtin_diff_pairs_options[] = { + OPT_END() + }; + + repo_init_revisions(repo, &revs, prefix); + + /* + * Diff options are usually parsed implicitly as part of + * setup_revisions(). Explicitly handle parsing to ensure options are + * printed in the usage message. + */ + parseopts = add_diff_options(builtin_diff_pairs_options, &revs.diffopt); + show_usage_with_options_if_asked(argc, argv, builtin_diff_pairs_usage, parseopts); + + repo_config(repo, git_diff_basic_config, NULL); + revs.disable_stdin = 1; + revs.abbrev = 0; + revs.diff = 1; + + argc = parse_options(argc, argv, prefix, parseopts, builtin_diff_pairs_usage, + PARSE_OPT_KEEP_ARGV0 | PARSE_OPT_KEEP_DASHDASH); + + if (setup_revisions(argc, argv, &revs, NULL) > 1) + usagef(_("unrecognized argument: %s"), argv[0]); + + /* + * With the -z option, both command input and raw output are + * NUL-delimited (this mode does not affect patch output). At present + * only NUL-delimited raw diff formatted input is supported. + */ + if (revs.diffopt.line_termination) + usage(_("working without -z is not supported")); + + if (revs.prune_data.nr) + usage(_("pathspec arguments not supported")); + + if (revs.pending.nr || revs.max_count != -1 || + revs.min_age != (timestamp_t)-1 || + revs.max_age != (timestamp_t)-1) + usage(_("revision arguments not allowed")); + + if (!revs.diffopt.output_format) + revs.diffopt.output_format = DIFF_FORMAT_PATCH; + + /* + * If rename detection is not requested, use rename information from the + * raw diff formatted input. Setting skip_resolving_statuses ensures + * diffcore_std() does not mess with rename information already present + * in queued filepairs. + */ + if (!revs.diffopt.detect_rename) + revs.diffopt.skip_resolving_statuses = 1; + + while (1) { + struct object_id oid_a, oid_b; + struct diff_filepair *pair; + unsigned mode_a, mode_b; + const char *p; + char status; + + if (strbuf_getwholeline(&meta, stdin, line_term) == EOF) + break; + + p = meta.buf; + if (*p != ':') + die(_("invalid raw diff input")); + p++; + + mode_a = parse_mode_or_die(p, &p); + mode_b = parse_mode_or_die(p, &p); + + if (S_ISDIR(mode_a) || S_ISDIR(mode_b)) + die(_("tree objects not supported")); + + parse_oid_or_die(p, &oid_a, &p, repo->hash_algo); + parse_oid_or_die(p, &oid_b, &p, repo->hash_algo); + + status = *p++; + + if (strbuf_getwholeline(&path, stdin, line_term) == EOF) + die(_("got EOF while reading path")); + + switch (status) { + case DIFF_STATUS_ADDED: + pair = diff_queue_addremove(&diff_queued_diff, + &revs.diffopt, '+', mode_b, + &oid_b, 1, path.buf, 0); + if (pair) + pair->status = status; + break; + + case DIFF_STATUS_DELETED: + pair = diff_queue_addremove(&diff_queued_diff, + &revs.diffopt, '-', mode_a, + &oid_a, 1, path.buf, 0); + if (pair) + pair->status = status; + break; + + case DIFF_STATUS_TYPE_CHANGED: + case DIFF_STATUS_MODIFIED: + pair = diff_queue_change(&diff_queued_diff, &revs.diffopt, + mode_a, mode_b, &oid_a, &oid_b, + 1, 1, path.buf, 0, 0); + if (pair) + pair->status = status; + break; + + case DIFF_STATUS_RENAMED: + case DIFF_STATUS_COPIED: { + struct diff_filespec *a, *b; + unsigned int score; + + if (strbuf_getwholeline(&path_dst, stdin, line_term) == EOF) + die(_("got EOF while reading destination path")); + + a = alloc_filespec(path.buf); + b = alloc_filespec(path_dst.buf); + fill_filespec(a, &oid_a, 1, mode_a); + fill_filespec(b, &oid_b, 1, mode_b); + + pair = diff_queue(&diff_queued_diff, a, b); + + if (strtoul_ui(p, 10, &score)) + die(_("unable to parse rename/copy score: %s"), p); + + pair->score = score * MAX_SCORE / 100; + pair->status = status; + pair->renamed_pair = 1; + } + break; + + default: + die(_("unknown diff status: %c"), status); + } + } + + diffcore_std(&revs.diffopt); + diff_flush(&revs.diffopt); + ret = diff_result_code(&revs); + + strbuf_release(&path_dst); + strbuf_release(&path); + strbuf_release(&meta); + release_revisions(&revs); + FREE_AND_NULL(parseopts); + + return ret; +} diff --git a/command-list.txt b/command-list.txt index c537114b46..b7ade3ab9f 100644 --- a/command-list.txt +++ b/command-list.txt @@ -96,6 +96,7 @@ git-diagnose ancillaryinterrogators git-diff mainporcelain info git-diff-files plumbinginterrogators git-diff-index plumbinginterrogators +git-diff-pairs plumbinginterrogators git-diff-tree plumbinginterrogators git-difftool ancillaryinterrogators complete git-fast-export ancillarymanipulators diff --git a/git.c b/git.c index 450d6aaa86..77c4359522 100644 --- a/git.c +++ b/git.c @@ -541,6 +541,7 @@ static struct cmd_struct commands[] = { { "diff", cmd_diff, NO_PARSEOPT }, { "diff-files", cmd_diff_files, RUN_SETUP | NEED_WORK_TREE | NO_PARSEOPT }, { "diff-index", cmd_diff_index, RUN_SETUP | NO_PARSEOPT }, + { "diff-pairs", cmd_diff_pairs, RUN_SETUP | NO_PARSEOPT }, { "diff-tree", cmd_diff_tree, RUN_SETUP | NO_PARSEOPT }, { "difftool", cmd_difftool, RUN_SETUP_GENTLY }, { "fast-export", cmd_fast_export, RUN_SETUP }, diff --git a/meson.build b/meson.build index 021a182135..383e304798 100644 --- a/meson.build +++ b/meson.build @@ -540,6 +540,7 @@ builtin_sources = [ 'builtin/diagnose.c', 'builtin/diff-files.c', 'builtin/diff-index.c', + 'builtin/diff-pairs.c', 'builtin/diff-tree.c', 'builtin/diff.c', 'builtin/difftool.c', diff --git a/t/meson.build b/t/meson.build index 780939d49f..09c7bc2fad 100644 --- a/t/meson.build +++ b/t/meson.build @@ -500,6 +500,7 @@ integration_tests = [ 't4067-diff-partial-clone.sh', 't4068-diff-symmetric-merge-base.sh', 't4069-remerge-diff.sh', + 't4070-diff-pairs.sh', 't4100-apply-stat.sh', 't4101-apply-nonl.sh', 't4102-apply-rename.sh', diff --git a/t/t4070-diff-pairs.sh b/t/t4070-diff-pairs.sh new file mode 100755 index 0000000000..0878ad0ad1 --- /dev/null +++ b/t/t4070-diff-pairs.sh @@ -0,0 +1,81 @@ +#!/bin/sh + +test_description='basic diff-pairs tests' +. ./test-lib.sh + +# This creates a diff with added, modified, deleted, renamed, copied, and +# typechange entries. This includes a submodule to test submodule diff support. +test_expect_success 'setup' ' + test_config_global protocol.file.allow always && + git init sub && + test_commit -C sub initial && + + git init main && + cd main && + echo to-be-gone >deleted && + echo original >modified && + echo now-a-file >symlink && + test_seq 200 >two-hundred && + test_seq 201 500 >five-hundred && + git add . && + test_tick && + git commit -m base && + git tag base && + + git submodule add ../sub && + echo now-here >added && + echo new >modified && + rm deleted && + mkdir subdir && + echo content >subdir/file && + mv two-hundred renamed && + test_seq 201 500 | sed s/300/modified/ >copied && + rm symlink && + git add -A . && + test_ln_s_add dest symlink && + test_tick && + git commit -m new && + git tag new +' + +test_expect_success 'diff-pairs recreates --raw' ' + git diff-tree -r -M -C -C -z base new >expect && + git diff-pairs --raw -z >actual expect && + git diff-tree -r -M -C -C -z base new | + git diff-pairs -p -z >actual && + test_cmp expect actual +' + +test_expect_success 'diff-pairs does not support normal raw diff input' ' + git diff-tree -r base new | + test_must_fail git diff-pairs >out 2>err && + + echo "usage: working without -z is not supported" >expect && + test_must_be_empty out && + test_cmp expect err +' + +test_expect_success 'diff-pairs does not support tree objects as input' ' + git diff-tree -z base new | + test_must_fail git diff-pairs -z >out 2>err && + + echo "fatal: tree objects not supported" >expect && + test_must_be_empty out && + test_cmp expect err +' + +test_expect_success 'diff-pairs does not support pathspec arguments' ' + git diff-tree -r -z base new | + test_must_fail git diff-pairs -z -- new >out 2>err && + + echo "usage: pathspec arguments not supported" >expect && + test_must_be_empty out && + test_cmp expect err +' + +test_done From cf15095ec52f1e997ec9eef42bdf275d2a68fe66 Mon Sep 17 00:00:00 2001 From: Justin Tobler Date: Fri, 28 Feb 2025 15:33:46 -0600 Subject: [PATCH 4/4] builtin/diff-pairs: allow explicit diff queue flush The diffs queued from git-diff-pairs(1) are flushed when stdin is closed. To enable greater flexibility, allow control over when the diff queue is flushed by writing a single NUL byte on stdin between input file pairs. Diff output between flushes is separated by a single NUL byte. Signed-off-by: Justin Tobler Signed-off-by: Junio C Hamano --- Documentation/git-diff-pairs.adoc | 4 ++++ builtin/diff-pairs.c | 14 ++++++++++++++ t/t4070-diff-pairs.sh | 9 +++++++++ 3 files changed, 27 insertions(+) diff --git a/Documentation/git-diff-pairs.adoc b/Documentation/git-diff-pairs.adoc index e31f2e2fbb..f99fcd1ead 100644 --- a/Documentation/git-diff-pairs.adoc +++ b/Documentation/git-diff-pairs.adoc @@ -17,6 +17,10 @@ in the NUL-terminated raw output format as generated by commands such as `git diff-tree -z -r --raw`. By default, the outputted diffs are computed and shown in the patch format when stdin closes. +A single NUL byte may be written to stdin between raw input lines to compute +file pair diffs up to that point instead of waiting for stdin to close. A NUL +byte is also written to the output to delimit between these batches of diffs. + Usage of this command enables the traditional diff pipeline to be broken up into separate stages where `diff-pairs` acts as the output phase. Other commands, such as `diff-tree`, may serve as a frontend to compute the raw diff --git a/builtin/diff-pairs.c b/builtin/diff-pairs.c index 6be17c1abd..71c045331a 100644 --- a/builtin/diff-pairs.c +++ b/builtin/diff-pairs.c @@ -57,6 +57,7 @@ int cmd_diff_pairs(int argc, const char **argv, const char *prefix, show_usage_with_options_if_asked(argc, argv, builtin_diff_pairs_usage, parseopts); repo_config(repo, git_diff_basic_config, NULL); + revs.diffopt.no_free = 1; revs.disable_stdin = 1; revs.abbrev = 0; revs.diff = 1; @@ -106,6 +107,18 @@ int cmd_diff_pairs(int argc, const char **argv, const char *prefix, break; p = meta.buf; + if (!*p) { + diffcore_std(&revs.diffopt); + diff_flush(&revs.diffopt); + /* + * When the diff queue is explicitly flushed, append a + * NUL byte to separate batches of diffs. + */ + fputc('\0', revs.diffopt.file); + fflush(revs.diffopt.file); + continue; + } + if (*p != ':') die(_("invalid raw diff input")); p++; @@ -179,6 +192,7 @@ int cmd_diff_pairs(int argc, const char **argv, const char *prefix, } } + revs.diffopt.no_free = 0; diffcore_std(&revs.diffopt); diff_flush(&revs.diffopt); ret = diff_result_code(&revs); diff --git a/t/t4070-diff-pairs.sh b/t/t4070-diff-pairs.sh index 0878ad0ad1..70deafb860 100755 --- a/t/t4070-diff-pairs.sh +++ b/t/t4070-diff-pairs.sh @@ -78,4 +78,13 @@ test_expect_success 'diff-pairs does not support pathspec arguments' ' test_cmp expect err ' +test_expect_success 'diff-pairs explicit queue flush' ' + git diff-tree -r -M -C -C -z base new >expect && + printf "\0" >>expect && + git diff-tree -r -M -C -C -z base new >>expect && + + git diff-pairs --raw -z actual && + test_cmp expect actual +' + test_done