[PATCH v5 12/13] commit-graph: build graph from starting commits

[Derrick Stolee <stolee@gmail.com>]

Teach git-commit-graph to read commits from stdin when the
--stdin-commits flag is specified. Commits reachable from these
commits are added to the graph. This is a much faster way to construct
the graph than inspecting all packed objects, but is restricted to
known tips.

For the Linux repository, 700,000+ commits were added to the graph
file starting from 'master' in 7-9 seconds, depending on the number
of packfiles in the repo (1, 24, or 120).

Signed-off-by: Derrick Stolee <dstolee@microsoft.com>
---
 Documentation/git-commit-graph.txt | 14 +++++++++++++-
 builtin/commit-graph.c             | 27 +++++++++++++++++++++------
 commit-graph.c                     | 27 +++++++++++++++++++++++++--
 commit-graph.h                     |  4 +++-
 t/t5318-commit-graph.sh            | 13 +++++++++++++
 5 files changed, 75 insertions(+), 10 deletions(-)

diff --git a/Documentation/git-commit-graph.txt b/Documentation/git-commit-graph.txt
index b945510..0710a68 100644
--- a/Documentation/git-commit-graph.txt
+++ b/Documentation/git-commit-graph.txt
@@ -34,7 +34,13 @@ COMMANDS
 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 packfiles.
+walking objects only in the specified packfiles. (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.)
 
 'read'::
 
@@ -58,6 +64,12 @@ $ git commit-graph write
 $ 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
+------------------------------------------------
+
 * Read basic information from the commit-graph file.
 +
 ------------------------------------------------
diff --git a/builtin/commit-graph.c b/builtin/commit-graph.c
index eebca57..1c7b7e7 100644
--- a/builtin/commit-graph.c
+++ b/builtin/commit-graph.c
@@ -8,7 +8,7 @@
 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>] [--stdin-packs]"),
+	N_("git commit-graph write [--object-dir <objdir>] [--stdin-packs|--stdin-commits]"),
 	NULL
 };
 
@@ -18,13 +18,14 @@ static const char * const builtin_commit_graph_read_usage[] = {
 };
 
 static const char * const builtin_commit_graph_write_usage[] = {
-	N_("git commit-graph write [--object-dir <objdir>] [--stdin-packs]"),
+	N_("git commit-graph write [--object-dir <objdir>] [--stdin-packs|--stdin-commits]"),
 	NULL
 };
 
 static struct opts_commit_graph {
 	const char *obj_dir;
 	int stdin_packs;
+	int stdin_commits;
 } opts;
 
 static int graph_read(int argc, const char **argv)
@@ -79,6 +80,8 @@ 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;
@@ -89,6 +92,8 @@ static int graph_write(int argc, const char **argv)
 			N_("The object directory to store the graph")),
 		OPT_BOOL(0, "stdin-packs", &opts.stdin_packs,
 			N_("scan packfiles listed by stdin for commits")),
+		OPT_BOOL(0, "stdin-commits", &opts.stdin_commits,
+			N_("start walk at commits listed by stdin")),
 		OPT_END(),
 	};
 
@@ -96,10 +101,12 @@ static int graph_write(int argc, const char **argv)
 			     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) {
+	if (opts.stdin_packs || opts.stdin_commits) {
 		struct strbuf buf = STRBUF_INIT;
 		lines_nr = 0;
 		lines_alloc = 128;
@@ -110,13 +117,21 @@ static int graph_write(int argc, const char **argv)
 			lines[lines_nr++] = strbuf_detach(&buf, NULL);
 		}
 
-		pack_indexes = lines;
-		packs_nr = lines_nr;
+		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);
+			   packs_nr,
+			   commit_hex,
+			   commits_nr);
 
 	return 0;
 }
diff --git a/commit-graph.c b/commit-graph.c
index 4e9f1d5..dbb9801 100644
--- a/commit-graph.c
+++ b/commit-graph.c
@@ -531,7 +531,9 @@ static void close_reachable(struct packed_oid_list *oids)
 
 void write_commit_graph(const char *obj_dir,
 			const char **pack_indexes,
-			int nr_packs)
+			int nr_packs,
+			const char **commit_hex,
+			int nr_commits)
 {
 	struct packed_oid_list oids;
 	struct packed_commit_list commits;
@@ -572,7 +574,28 @@ void write_commit_graph(const char *obj_dir,
 			close_pack(p);
 		}
 		strbuf_release(&packname);
-	} else
+	}
+
+	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);
diff --git a/commit-graph.h b/commit-graph.h
index 65fe770..4c70281 100644
--- a/commit-graph.h
+++ b/commit-graph.h
@@ -38,7 +38,9 @@ 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);
+			int nr_packs,
+			const char **commit_hex,
+			int nr_commits);
 
 #endif
 
diff --git a/t/t5318-commit-graph.sh b/t/t5318-commit-graph.sh
index 6bc529c..9589238 100755
--- a/t/t5318-commit-graph.sh
+++ b/t/t5318-commit-graph.sh
@@ -177,6 +177,19 @@ test_expect_success 'build graph from latest pack with closure' '
 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 $objdir/info/commit-graph &&
+	graph_read_expect "6"
+'
+
+graph_git_behavior 'graph from commits, commit 8 vs merge 1' full commits/8 merge/1
+graph_git_behavior 'graph from commits, commit 8 vs merge 2' full commits/8 merge/2
+
 test_expect_success 'setup bare repo' '
 	cd "$TRASH_DIRECTORY" &&
 	git clone --bare --no-local full bare &&
-- 
2.7.4