1 files changed, 206 insertions, 80 deletions

diff --git a/builtin/commit-graph.c b/builtin/commit-graph.c
index c02a3f1221..78fa08f43a 100644
--- a/builtin/commit-graph.c
+++ b/builtin/commit-graph.c
@@ -5,27 +5,29 @@
 #include "parse-options.h"
 #include "repository.h"
 #include "commit-graph.h"
+#include "object-store.h"
+#include "progress.h"
+#include "tag.h"
 
 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 verify [--object-dir <objdir>]"),
-	N_("git commit-graph write [--object-dir <objdir>] [--append] [--reachable|--stdin-packs|--stdin-commits]"),
+	N_("git commit-graph verify [--object-dir <objdir>] [--shallow] [--[no-]progress]"),
+	N_("git commit-graph write [--object-dir <objdir>] [--append] "
+	   "[--split[=<strategy>]] [--reachable|--stdin-packs|--stdin-commits] "
+	   "[--changed-paths] [--[no-]max-new-filters <n>] [--[no-]progress] "
+	   "<split options>"),
 	NULL
 };
 
 static const char * const builtin_commit_graph_verify_usage[] = {
-	N_("git commit-graph verify [--object-dir <objdir>]"),
-	NULL
-};
-
-static const char * const builtin_commit_graph_read_usage[] = {
-	N_("git commit-graph read [--object-dir <objdir>]"),
+	N_("git commit-graph verify [--object-dir <objdir>] [--shallow] [--[no-]progress]"),
 	NULL
 };
 
 static const char * const builtin_commit_graph_write_usage[] = {
-	N_("git commit-graph write [--object-dir <objdir>] [--append] [--reachable|--stdin-packs|--stdin-commits]"),
+	N_("git commit-graph write [--object-dir <objdir>] [--append] "
+	   "[--split[=<strategy>]] [--reachable|--stdin-packs|--stdin-commits] "
+	   "[--changed-paths] [--[no-]max-new-filters <n>] [--[no-]progress] "
+	   "<split options>"),
 	NULL
 };
 
@@ -35,97 +37,173 @@ static struct opts_commit_graph {
 	int stdin_packs;
 	int stdin_commits;
 	int append;
+	int split;
+	int shallow;
+	int progress;
+	int enable_changed_paths;
 } opts;
 
+static struct object_directory *find_odb(struct repository *r,
+					 const char *obj_dir)
+{
+	struct object_directory *odb;
+	char *obj_dir_real = real_pathdup(obj_dir, 1);
+	struct strbuf odb_path_real = STRBUF_INIT;
+
+	prepare_alt_odb(r);
+	for (odb = r->objects->odb; odb; odb = odb->next) {
+		strbuf_realpath(&odb_path_real, odb->path, 1);
+		if (!strcmp(obj_dir_real, odb_path_real.buf))
+			break;
+	}
+
+	free(obj_dir_real);
+	strbuf_release(&odb_path_real);
+
+	if (!odb)
+		die(_("could not find object directory matching %s"), obj_dir);
+	return odb;
+}
 
 static int graph_verify(int argc, const char **argv)
 {
 	struct commit_graph *graph = NULL;
+	struct object_directory *odb = NULL;
 	char *graph_name;
+	int open_ok;
+	int fd;
+	struct stat st;
+	int flags = 0;
 
 	static struct option builtin_commit_graph_verify_options[] = {
 		OPT_STRING(0, "object-dir", &opts.obj_dir,
 			   N_("dir"),
 			   N_("The object directory to store the graph")),
+		OPT_BOOL(0, "shallow", &opts.shallow,
+			 N_("if the commit-graph is split, only verify the tip file")),
+		OPT_BOOL(0, "progress", &opts.progress, N_("force progress reporting")),
 		OPT_END(),
 	};
 
+	trace2_cmd_mode("verify");
+
+	opts.progress = isatty(2);
 	argc = parse_options(argc, argv, NULL,
 			     builtin_commit_graph_verify_options,
 			     builtin_commit_graph_verify_usage, 0);
 
 	if (!opts.obj_dir)
 		opts.obj_dir = get_object_directory();
+	if (opts.shallow)
+		flags |= COMMIT_GRAPH_VERIFY_SHALLOW;
+	if (opts.progress)
+		flags |= COMMIT_GRAPH_WRITE_PROGRESS;
+
+	odb = find_odb(the_repository, opts.obj_dir);
+	graph_name = get_commit_graph_filename(odb);
+	open_ok = open_commit_graph(graph_name, &fd, &st);
+	if (!open_ok && errno != ENOENT)
+		die_errno(_("Could not open commit-graph '%s'"), graph_name);
 
-	graph_name = get_commit_graph_filename(opts.obj_dir);
-	graph = load_commit_graph_one(graph_name);
 	FREE_AND_NULL(graph_name);
 
+	if (open_ok)
+		graph = load_commit_graph_one_fd_st(the_repository, fd, &st, odb);
+	else
+		graph = read_commit_graph_one(the_repository, odb);
+
+	/* Return failure if open_ok predicted success */
 	if (!graph)
-		return 0;
+		return !!open_ok;
 
 	UNLEAK(graph);
-	return verify_commit_graph(the_repository, graph);
+	return verify_commit_graph(the_repository, graph, flags);
 }
 
-static int graph_read(int argc, const char **argv)
+extern int read_replace_refs;
+static struct commit_graph_opts write_opts;
+
+static int write_option_parse_split(const struct option *opt, const char *arg,
+				    int unset)
 {
-	struct commit_graph *graph = NULL;
-	char *graph_name;
+	enum commit_graph_split_flags *flags = opt->value;
 
-	static struct option builtin_commit_graph_read_options[] = {
-		OPT_STRING(0, "object-dir", &opts.obj_dir,
-			N_("dir"),
-			N_("The object directory to store the graph")),
-		OPT_END(),
-	};
+	BUG_ON_OPT_NEG(unset);
 
-	argc = parse_options(argc, argv, NULL,
-			     builtin_commit_graph_read_options,
-			     builtin_commit_graph_read_usage, 0);
+	opts.split = 1;
+	if (!arg)
+		return 0;
 
-	if (!opts.obj_dir)
-		opts.obj_dir = get_object_directory();
+	if (!strcmp(arg, "no-merge"))
+		*flags = COMMIT_GRAPH_SPLIT_MERGE_PROHIBITED;
+	else if (!strcmp(arg, "replace"))
+		*flags = COMMIT_GRAPH_SPLIT_REPLACE;
+	else
+		die(_("unrecognized --split argument, %s"), arg);
 
-	graph_name = get_commit_graph_filename(opts.obj_dir);
-	graph = load_commit_graph_one(graph_name);
+	return 0;
+}
 
-	if (!graph)
-		die("graph file %s does not exist", graph_name);
+static int read_one_commit(struct oidset *commits, struct progress *progress,
+			   const char *hash)
+{
+	struct object *result;
+	struct object_id oid;
+	const char *end;
 
-	FREE_AND_NULL(graph_name);
+	if (parse_oid_hex(hash, &oid, &end))
+		return error(_("unexpected non-hex object ID: %s"), hash);
 
-	printf("header: %08x %d %d %d %d\n",
-		ntohl(*(uint32_t*)graph->data),
-		*(unsigned char*)(graph->data + 4),
-		*(unsigned char*)(graph->data + 5),
-		*(unsigned char*)(graph->data + 6),
-		*(unsigned char*)(graph->data + 7));
-	printf("num_commits: %u\n", graph->num_commits);
-	printf("chunks:");
-
-	if (graph->chunk_oid_fanout)
-		printf(" oid_fanout");
-	if (graph->chunk_oid_lookup)
-		printf(" oid_lookup");
-	if (graph->chunk_commit_data)
-		printf(" commit_metadata");
-	if (graph->chunk_large_edges)
-		printf(" large_edges");
-	printf("\n");
+	result = deref_tag(the_repository, parse_object(the_repository, &oid),
+			   NULL, 0);
+	if (!result)
+		return error(_("invalid object: %s"), hash);
+	else if (object_as_type(result, OBJ_COMMIT, 1))
+		oidset_insert(commits, &result->oid);
 
-	UNLEAK(graph);
+	display_progress(progress, oidset_size(commits));
 
 	return 0;
 }
 
-extern int read_replace_refs;
+static int write_option_max_new_filters(const struct option *opt,
+					const char *arg,
+					int unset)
+{
+	int *to = opt->value;
+	if (unset)
+		*to = -1;
+	else {
+		const char *s;
+		*to = strtol(arg, (char **)&s, 10);
+		if (*s)
+			return error(_("%s expects a numerical value"),
+				     optname(opt, opt->flags));
+	}
+	return 0;
+}
+
+static int git_commit_graph_write_config(const char *var, const char *value,
+					 void *cb)
+{
+	if (!strcmp(var, "commitgraph.maxnewfilters"))
+		write_opts.max_new_filters = git_config_int(var, value);
+	/*
+	 * No need to fall-back to 'git_default_config', since this was already
+	 * called in 'cmd_commit_graph()'.
+	 */
+	return 0;
+}
 
 static int graph_write(int argc, const char **argv)
 {
-	struct string_list *pack_indexes = NULL;
-	struct string_list *commit_hex = NULL;
-	struct string_list lines;
+	struct string_list pack_indexes = STRING_LIST_INIT_NODUP;
+	struct strbuf buf = STRBUF_INIT;
+	struct oidset commits = OIDSET_INIT;
+	struct object_directory *odb = NULL;
+	int result = 0;
+	enum commit_graph_write_flags flags = 0;
+	struct progress *progress = NULL;
 
 	static struct option builtin_commit_graph_write_options[] = {
 		OPT_STRING(0, "object-dir", &opts.obj_dir,
@@ -139,9 +217,36 @@ static int graph_write(int argc, const char **argv)
 			N_("start walk at commits listed by stdin")),
 		OPT_BOOL(0, "append", &opts.append,
 			N_("include all commits already in the commit-graph file")),
+		OPT_BOOL(0, "changed-paths", &opts.enable_changed_paths,
+			N_("enable computation for changed paths")),
+		OPT_BOOL(0, "progress", &opts.progress, N_("force progress reporting")),
+		OPT_CALLBACK_F(0, "split", &write_opts.split_flags, NULL,
+			N_("allow writing an incremental commit-graph file"),
+			PARSE_OPT_OPTARG | PARSE_OPT_NONEG,
+			write_option_parse_split),
+		OPT_INTEGER(0, "max-commits", &write_opts.max_commits,
+			N_("maximum number of commits in a non-base split commit-graph")),
+		OPT_INTEGER(0, "size-multiple", &write_opts.size_multiple,
+			N_("maximum ratio between two levels of a split commit-graph")),
+		OPT_EXPIRY_DATE(0, "expire-time", &write_opts.expire_time,
+			N_("only expire files older than a given date-time")),
+		OPT_CALLBACK_F(0, "max-new-filters", &write_opts.max_new_filters,
+			NULL, N_("maximum number of changed-path Bloom filters to compute"),
+			0, write_option_max_new_filters),
 		OPT_END(),
 	};
 
+	opts.progress = isatty(2);
+	opts.enable_changed_paths = -1;
+	write_opts.size_multiple = 2;
+	write_opts.max_commits = 0;
+	write_opts.expire_time = 0;
+	write_opts.max_new_filters = -1;
+
+	trace2_cmd_mode("write");
+
+	git_config(git_commit_graph_write_config, &opts);
+
 	argc = parse_options(argc, argv, NULL,
 			     builtin_commit_graph_write_options,
 			     builtin_commit_graph_write_usage, 0);
@@ -150,37 +255,58 @@ static int graph_write(int argc, const char **argv)
 		die(_("use at most one of --reachable, --stdin-commits, or --stdin-packs"));
 	if (!opts.obj_dir)
 		opts.obj_dir = get_object_directory();
+	if (opts.append)
+		flags |= COMMIT_GRAPH_WRITE_APPEND;
+	if (opts.split)
+		flags |= COMMIT_GRAPH_WRITE_SPLIT;
+	if (opts.progress)
+		flags |= COMMIT_GRAPH_WRITE_PROGRESS;
+	if (!opts.enable_changed_paths)
+		flags |= COMMIT_GRAPH_NO_WRITE_BLOOM_FILTERS;
+	if (opts.enable_changed_paths == 1 ||
+	    git_env_bool(GIT_TEST_COMMIT_GRAPH_CHANGED_PATHS, 0))
+		flags |= COMMIT_GRAPH_WRITE_BLOOM_FILTERS;
 
 	read_replace_refs = 0;
+	odb = find_odb(the_repository, opts.obj_dir);
 
 	if (opts.reachable) {
-		write_commit_graph_reachable(opts.obj_dir, opts.append, 1);
+		if (write_commit_graph_reachable(odb, flags, &write_opts))
+			return 1;
 		return 0;
 	}
 
-	string_list_init(&lines, 0);
-	if (opts.stdin_packs || opts.stdin_commits) {
-		struct strbuf buf = STRBUF_INIT;
-
+	if (opts.stdin_packs) {
 		while (strbuf_getline(&buf, stdin) != EOF)
-			string_list_append(&lines, strbuf_detach(&buf, NULL));
-
-		if (opts.stdin_packs)
-			pack_indexes = &lines;
-		if (opts.stdin_commits)
-			commit_hex = &lines;
-
-		UNLEAK(buf);
+			string_list_append(&pack_indexes,
+					   strbuf_detach(&buf, NULL));
+	} else if (opts.stdin_commits) {
+		oidset_init(&commits, 0);
+		if (opts.progress)
+			progress = start_delayed_progress(
+				_("Collecting commits from input"), 0);
+
+		while (strbuf_getline(&buf, stdin) != EOF) {
+			if (read_one_commit(&commits, progress, buf.buf)) {
+				result = 1;
+				goto cleanup;
+			}
+		}
+
+		stop_progress(&progress);
 	}
 
-	write_commit_graph(opts.obj_dir,
-			   pack_indexes,
-			   commit_hex,
-			   opts.append,
-			   1);
-
-	UNLEAK(lines);
-	return 0;
+	if (write_commit_graph(odb,
+			       opts.stdin_packs ? &pack_indexes : NULL,
+			       opts.stdin_commits ? &commits : NULL,
+			       flags,
+			       &write_opts))
+		result = 1;
+
+cleanup:
+	string_list_clear(&pack_indexes, 0);
+	strbuf_release(&buf);
+	return result;
 }
 
 int cmd_commit_graph(int argc, const char **argv, const char *prefix)
@@ -202,9 +328,9 @@ int cmd_commit_graph(int argc, const char **argv, const char *prefix)
 			     builtin_commit_graph_usage,
 			     PARSE_OPT_STOP_AT_NON_OPTION);
 
+	save_commit_buffer = 0;
+
 	if (argc > 0) {
-		if (!strcmp(argv[0], "read"))
-			return graph_read(argc, argv);
 		if (!strcmp(argv[0], "verify"))
 			return graph_verify(argc, argv);
 		if (!strcmp(argv[0], "write"))