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 takes the
null-terminated raw diff format as input on stdin and produces diffs in
other formats. As the raw diff format already contains the necessary
metadata, it becomes possible to progressively generate batches of diffs
without having to recompute rename detection or retrieve object context.
Something like the following:

	git diff-tree -r -z -M $old $new |
	git diff-pairs -p

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

@@ -54,6 +54,7 @@
 /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 +1,62 @@
+git-diff-pairs(1)
+=================
+
+NAME
+----
+git-diff-pairs - Compare blob pairs generated by `diff-tree --raw`
+
+SYNOPSIS
+--------
+[verse]
+'git diff-pairs' [diff-options]
+
+DESCRIPTION
+-----------
+
+Given the output of `diff-tree -z` on its stdin, `diff-pairs` will
+reformat that output into whatever format is requested on its command
+line.  For example:
+
+-----------------------------
+git diff-tree -z -M $a $b |
+git diff-pairs -p
+-----------------------------
+
+will compute the tree diff in one step (including renames), and then
+`diff-pairs` will compute and format the blob-level diffs for each pair.
+This can be used to modify the raw diff in the middle (without having to
+parse or re-create more complicated formats like `--patch`), or to
+compute diffs progressively over the course of multiple invocations of
+`diff-pairs`.
+
+Each blob pair is fed to the diff machinery individually queued and the output
+is flushed on stdin EOF.
+
+OPTIONS
+-------
+
+include::diff-options.adoc[]
+
+include::diff-generate-patch.adoc[]
+
+NOTES
+----
+
+`diff-pairs` should handle any input generated by `diff-tree --raw -z`.
+It may choke or otherwise misbehave on output from `diff-files`, etc.
+
+Here's an incomplete list of things that `diff-pairs` could do, but
+doesn't (mostly in the name of simplicity):
+
+ - Only `-z` input is accepted, not normal `--raw` input.
+
+ - Abbreviated sha1s are rejected in the input from `diff-tree`; if you
+   want to abbreviate the output, you can pass `--abbrev` to
+   `diff-pairs`.
+
+ - Pathspecs are not handled by `diff-pairs`; you can limit the diff via
+   the initial `diff-tree` invocation.
+
+GIT
+---
+Part of the linkgit:git[1] suite

Documentation/meson.build

@@ -41,6 +41,7 @@ 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

@@ -1232,6 +1232,7 @@ 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

@@ -152,6 +152,7 @@ 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 +1,178 @@
+#include "builtin.h"
+#include "commit.h"
+#include "config.h"
+#include "diff.h"
+#include "diffcore.h"
+#include "gettext.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 **endp)
+{
+	uint16_t ret;
+
+	*endp = parse_mode(mode, &ret);
+	if (!*endp)
+		die("unable to parse mode: %s", mode);
+	return ret;
+}
+
+static void parse_oid(const char *p, struct object_id *oid, const char **endp,
+		      const struct git_hash_algo *algop)
+{
+	if (parse_oid_hex_algop(p, oid, endp, algop) || *(*endp)++ != ' ')
+		die("unable to parse object id: %s", p);
+}
+
+static unsigned short parse_score(const char *score)
+{
+	unsigned long ret;
+	char *endp;
+
+	errno = 0;
+	ret = strtoul(score, &endp, 10);
+	ret *= MAX_SCORE / 100;
+	if (errno || endp == score || *endp || (unsigned short)ret != ret)
+		die("unable to parse rename/copy score: %s", score);
+	return ret;
+}
+
+static void flush_diff_queue(struct diff_options *options)
+{
+	/*
+	 * If rename detection is not requested, use rename information from the
+	 * raw diff formatted input. Setting found_follow ensures diffcore_std()
+	 * does not mess with rename information already present in queued
+	 * filepairs.
+	 */
+	if (!options->detect_rename)
+		options->found_follow = 1;
+	diffcore_std(options);
+	diff_flush(options);
+}
+
+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 rev_info revs;
+	int ret;
+
+	const char * const usage[] = {
+		N_("git diff-pairs [diff-options]"),
+		NULL
+	};
+	struct option options[] = {
+		OPT_END()
+	};
+
+	show_usage_with_options_if_asked(argc, argv, usage, options);
+
+	repo_init_revisions(repo, &revs, prefix);
+	repo_config(repo, git_diff_basic_config, NULL);
+	revs.disable_stdin = 1;
+	revs.abbrev = 0;
+	revs.diff = 1;
+
+	argc = setup_revisions(argc, argv, &revs, NULL);
+
+	/* Don't allow pathspecs at all. */
+	if (revs.prune_data.nr)
+		usage_with_options(usage, options);
+
+	if (!revs.diffopt.output_format)
+		revs.diffopt.output_format = DIFF_FORMAT_RAW;
+
+	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_getline_nul(&meta, stdin) == 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);
+
+		parse_oid(p, &oid_a, &p, repo->hash_algo);
+		parse_oid(p, &oid_b, &p, repo->hash_algo);
+
+		status = *p++;
+
+		if (strbuf_getline_nul(&path, stdin) == EOF)
+			die("got EOF while reading path");
+
+		switch (status) {
+		case DIFF_STATUS_ADDED:
+			pair = diff_filepair_addremove(&revs.diffopt, '+',
+						       mode_b, &oid_b,
+						       1, path.buf, 0);
+			if (pair)
+				pair->status = status;
+			break;
+
+		case DIFF_STATUS_DELETED:
+			pair = diff_filepair_addremove(&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_filepair_change(&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;
+
+				if (strbuf_getline_nul(&path_dst, stdin) == 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);
+				pair->status = status;
+				pair->score = parse_score(p);
+				pair->renamed_pair = 1;
+			}
+			break;
+
+		default:
+			die("unknown diff status: %c", status);
+		}
+	}
+
+	flush_diff_queue(&revs.diffopt);
+	ret = diff_result_code(&revs);
+
+	strbuf_release(&path_dst);
+	strbuf_release(&path);
+	strbuf_release(&meta);
+	release_revisions(&revs);
+
+	return ret;
+}

command-list.txt

@@ -95,6 +95,7 @@ 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

@@ -540,6 +540,7 @@ 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

@@ -537,6 +537,7 @@ 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',