Merge branch 'tb/bloom-improvements'

"git commit-graph write" learned to limit the number of bloom
filters that are computed from scratch with the --max-new-filters
option.

* tb/bloom-improvements:
  commit-graph: introduce 'commitGraph.maxNewFilters'
  builtin/commit-graph.c: introduce '--max-new-filters=<n>'
  commit-graph: rename 'split_commit_graph_opts'
  bloom: encode out-of-bounds filters as non-empty
  bloom/diff: properly short-circuit on max_changes
  bloom: use provided 'struct bloom_filter_settings'
  bloom: split 'get_bloom_filter()' in two
  commit-graph.c: store maximum changed paths
  commit-graph: respect 'commitGraph.readChangedPaths'
  t/helper/test-read-graph.c: prepare repo settings
  commit-graph: pass a 'struct repository *' in more places
  t4216: use an '&&'-chain
  commit-graph: introduce 'get_bloom_filter_settings()'

1 files changed, 50 insertions, 13 deletions

diff --git a/builtin/commit-graph.c b/builtin/commit-graph.c
index 523501f217..988445abdf 100644
--- a/builtin/commit-graph.c
+++ b/builtin/commit-graph.c
@@ -13,7 +13,8 @@ static char const * const builtin_commit_graph_usage[] = {
 	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-]progress] <split options>"),
+	   "[--changed-paths] [--[no-]max-new-filters <n>] [--[no-]progress] "
+	   "<split options>"),
 	NULL
 };
 
@@ -25,7 +26,8 @@ static const char * const builtin_commit_graph_verify_usage[] = {
 static const char * const builtin_commit_graph_write_usage[] = {
 	N_("git commit-graph write [--object-dir <objdir>] [--append] "
 	   "[--split[=<strategy>]] [--reachable|--stdin-packs|--stdin-commits] "
-	   "[--changed-paths] [--[no-]progress] <split options>"),
+	   "[--changed-paths] [--[no-]max-new-filters <n>] [--[no-]progress] "
+	   "<split options>"),
 	NULL
 };
 
@@ -106,7 +108,7 @@ static int graph_verify(int argc, const char **argv)
 	FREE_AND_NULL(graph_name);
 
 	if (open_ok)
-		graph = load_commit_graph_one_fd_st(fd, &st, odb);
+		graph = load_commit_graph_one_fd_st(the_repository, fd, &st, odb);
 	else
 		graph = read_commit_graph_one(the_repository, odb);
 
@@ -119,7 +121,7 @@ static int graph_verify(int argc, const char **argv)
 }
 
 extern int read_replace_refs;
-static struct split_commit_graph_opts split_opts;
+static struct commit_graph_opts write_opts;
 
 static int write_option_parse_split(const struct option *opt, const char *arg,
 				    int unset)
@@ -162,6 +164,35 @@ static int read_one_commit(struct oidset *commits, struct progress *progress,
 	return 0;
 }
 
+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 = STRING_LIST_INIT_NODUP;
@@ -187,27 +218,33 @@ static int graph_write(int argc, const char **argv)
 		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", &split_opts.flags, NULL,
+		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", &split_opts.max_commits,
+		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", &split_opts.size_multiple,
+		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", &split_opts.expire_time,
+		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;
-	split_opts.size_multiple = 2;
-	split_opts.max_commits = 0;
-	split_opts.expire_time = 0;
+	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);
@@ -232,7 +269,7 @@ static int graph_write(int argc, const char **argv)
 	odb = find_odb(the_repository, opts.obj_dir);
 
 	if (opts.reachable) {
-		if (write_commit_graph_reachable(odb, flags, &split_opts))
+		if (write_commit_graph_reachable(odb, flags, &write_opts))
 			return 1;
 		return 0;
 	}
@@ -261,7 +298,7 @@ static int graph_write(int argc, const char **argv)
 			       opts.stdin_packs ? &pack_indexes : NULL,
 			       opts.stdin_commits ? &commits : NULL,
 			       flags,
-			       &split_opts))
+			       &write_opts))
 		result = 1;
 
 cleanup: