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 <[email protected]>
Signed-off-by: Justin Tobler <[email protected]>
Signed-off-by: Junio C Hamano <[email protected]>

Author: jltobler

.gitignore

@@ -55,6 +55,7 @@
 /git-diff
 /git-diff-files
 /git-diff-index
+/git-diff-pairs
 /git-diff-tree
 /git-difftool
 /git-difftool--helper

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 [<diff-options>]
+
+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

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,

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

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);

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 [<diff-options>]"),
+		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;
+}

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

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 },

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',

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',