[PATCH v2 12/14] commit-graph: read only from specific pack-indexes

[Derrick Stolee <stolee@gmail.com>]

Teach git-commit-graph to inspect the objects only in a certain list
of pack-indexes within the given pack directory. This allows updating
the commit graph iteratively, since we add all commits stored in a
previous commit graph.

Signed-off-by: Derrick Stolee <dstolee@microsoft.com>
---
 Documentation/git-commit-graph.txt | 13 +++++++++++++
 builtin/commit-graph.c             | 25 ++++++++++++++++++++++---
 commit-graph.c                     | 25 +++++++++++++++++++++++--
 commit-graph.h                     |  4 +++-
 packfile.c                         |  4 ++--
 packfile.h                         |  2 ++
 t/t5318-commit-graph.sh            |  6 ++++--
 7 files changed, 69 insertions(+), 10 deletions(-)

diff --git a/Documentation/git-commit-graph.txt b/Documentation/git-commit-graph.txt
index 7b376e9212..d0571cd896 100644
--- a/Documentation/git-commit-graph.txt
+++ b/Documentation/git-commit-graph.txt
@@ -43,6 +43,11 @@ OPTIONS
 	When used with --write and --update-head, delete the graph file
 	previously referenced by graph-head.
 
+--stdin-packs::
+	When used with --write, generate the new graph by walking objects
+	only in the specified packfiles and any commits in the
+	existing graph-head.
+
 EXAMPLES
 --------
 
@@ -65,6 +70,14 @@ $ git commit-graph --write
 $ git commit-graph --write --update-head --delete-expired
 ------------------------------------------------
 
+* Write a graph file, extending the current graph file using commits
+* in <pack-index>, update graph-head, and delete the old graph-<hash>.graph
+* file.
++
+------------------------------------------------
+$ echo <pack-index> | git commit-graph --write --update-head --delete-expired --stdin-packs
+------------------------------------------------
+
 * Read basic information from a graph file.
 +
 ------------------------------------------------
diff --git a/builtin/commit-graph.c b/builtin/commit-graph.c
index 766f09e6fc..80a409e784 100644
--- a/builtin/commit-graph.c
+++ b/builtin/commit-graph.c
@@ -12,7 +12,7 @@ static char const * const builtin_commit_graph_usage[] = {
 	N_("git commit-graph [--pack-dir <packdir>]"),
 	N_("git commit-graph --clear [--pack-dir <packdir>]"),
 	N_("git commit-graph --read [--graph-hash=<hash>]"),
-	N_("git commit-graph --write [--pack-dir <packdir>] [--update-head] [--delete-expired]"),
+	N_("git commit-graph --write [--pack-dir <packdir>] [--update-head] [--delete-expired] [--stdin-packs]"),
 	NULL
 };
 
@@ -24,6 +24,7 @@ static struct opts_commit_graph {
 	int write;
 	int update_head;
 	int delete_expired;
+	int stdin_packs;
 	int has_existing;
 	struct object_id old_graph_hash;
 } opts;
@@ -114,7 +115,24 @@ static void update_head_file(const char *pack_dir, const struct object_id *graph
 
 static int graph_write(void)
 {
-	struct object_id *graph_hash = construct_commit_graph(opts.pack_dir);
+	struct object_id *graph_hash;
+	char **pack_indexes = NULL;
+	int num_packs = 0;
+	int size_packs = 0;
+
+	if (opts.stdin_packs) {
+		struct strbuf buf = STRBUF_INIT;
+		size_packs = 128;
+		ALLOC_ARRAY(pack_indexes, size_packs);
+
+		while (strbuf_getline(&buf, stdin) != EOF) {
+			ALLOC_GROW(pack_indexes, num_packs + 1, size_packs);
+			pack_indexes[num_packs++] = buf.buf;
+			strbuf_detach(&buf, NULL);
+		}
+	}
+
+	graph_hash = construct_commit_graph(opts.pack_dir, pack_indexes, num_packs);
 
 	if (opts.update_head)
 		update_head_file(opts.pack_dir, graph_hash);
@@ -122,7 +140,6 @@ static int graph_write(void)
 	if (graph_hash)
 		printf("%s\n", oid_to_hex(graph_hash));
 
-
 	if (opts.delete_expired && opts.update_head && opts.has_existing &&
 	    oidcmp(graph_hash, &opts.old_graph_hash)) {
 		char *old_path = get_commit_graph_filename_hash(opts.pack_dir,
@@ -153,6 +170,8 @@ int cmd_commit_graph(int argc, const char **argv, const char *prefix)
 			N_("update graph-head to written graph file")),
 		OPT_BOOL('d', "delete-expired", &opts.delete_expired,
 			N_("delete expired head graph file")),
+		OPT_BOOL('s', "stdin-packs", &opts.stdin_packs,
+			N_("only scan packfiles listed by stdin")),
 		{ OPTION_STRING, 'H', "graph-hash", &opts.graph_hash,
 			N_("hash"),
 			N_("A hash for a specific graph file in the pack-dir."),
diff --git a/commit-graph.c b/commit-graph.c
index fc816533c6..e5a1d9ee8b 100644
--- a/commit-graph.c
+++ b/commit-graph.c
@@ -638,7 +638,9 @@ static int if_packed_commit_add_to_list(const struct object_id *oid,
 	return 0;
 }
 
-struct object_id *construct_commit_graph(const char *pack_dir)
+struct object_id *construct_commit_graph(const char *pack_dir,
+					 char **pack_indexes,
+					 int nr_packs)
 {
 	struct packed_oid_list oids;
 	struct packed_commit_list commits;
@@ -674,7 +676,26 @@ struct object_id *construct_commit_graph(const char *pack_dir)
 		oids.num = commit_graph->num_commits;
 	}
 
-	for_each_packed_object(if_packed_commit_add_to_list, &oids, 0);
+	if (pack_indexes) {
+		int pack_dir_len = strlen(pack_dir) + 1;
+		struct strbuf packname = STRBUF_INIT;
+		strbuf_add(&packname, pack_dir, pack_dir_len - 1);
+		strbuf_addch(&packname, '/');
+		for (i = 0; i < nr_packs; i++) {
+			struct packed_git *p;
+			strbuf_setlen(&packname, pack_dir_len);
+			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, if_packed_commit_add_to_list, &oids);
+			close_pack(p);
+		}
+	} else {
+		for_each_packed_object(if_packed_commit_add_to_list, &oids, 0);
+	}
 	QSORT(oids.list, oids.num, commit_compare);
 
 	count_distinct = 1;
diff --git a/commit-graph.h b/commit-graph.h
index 05ddbbe165..3ae1eadce0 100644
--- a/commit-graph.h
+++ b/commit-graph.h
@@ -60,6 +60,8 @@ extern struct object_id *get_nth_commit_oid(struct commit_graph *g,
 					    uint32_t n,
 					    struct object_id *oid);
 
-extern struct object_id *construct_commit_graph(const char *pack_dir);
+extern struct object_id *construct_commit_graph(const char *pack_dir,
+						char **pack_indexes,
+						int nr_packs);
 
 #endif
diff --git a/packfile.c b/packfile.c
index 4a5fe7ab18..48133bd669 100644
--- a/packfile.c
+++ b/packfile.c
@@ -299,7 +299,7 @@ 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);
@@ -1860,7 +1860,7 @@ 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;
diff --git a/packfile.h b/packfile.h
index 0cdeb54dcd..cde868feb6 100644
--- a/packfile.h
+++ b/packfile.h
@@ -61,6 +61,7 @@ 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(void);
 extern void unuse_pack(struct pack_window **);
 extern void clear_delta_base_cache(void);
@@ -133,6 +134,7 @@ 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 cb, void *data);
 extern int for_each_packed_object(each_packed_object_fn, void *, unsigned flags);
 
 #endif
diff --git a/t/t5318-commit-graph.sh b/t/t5318-commit-graph.sh
index 93b0d4f51b..b9a73f398c 100755
--- a/t/t5318-commit-graph.sh
+++ b/t/t5318-commit-graph.sh
@@ -137,7 +137,9 @@ test_expect_success 'Add more commits' \
         git commit -m "commit $i" &&
         git branch commits/$i
      done &&
-     git repack'
+     ls ${packdir} | grep idx >existing-idx &&
+     git repack &&
+     ls ${packdir} | grep idx | grep -v --file=existing-idx >new-idx'
 
 # Current graph structure:
 #
@@ -174,7 +176,7 @@ _graph_git_behavior commits/20 merge/1
 _graph_git_behavior commits/20 merge/2
 
 test_expect_success 'write graph with merges' \
-    'graph3=$(git commit-graph --write --update-head --delete-expired) &&
+    'graph3=$(cat new-idx | git commit-graph --write --update-head --delete-expired --stdin-packs) &&
      test_path_is_file ${packdir}/graph-${graph3}.graph &&
      test_path_is_missing ${packdir}/graph-${graph2}.graph &&
      test_path_is_file ${packdir}/graph-${graph1}.graph &&
-- 
2.16.0.15.g9c3cf44.dirty