[PATCH 3/4] builtin/repo: add keyvalue format for stats

From: Justin Tobler <jltobler@gmail.com>
Date: Sep 23, 2025, 02:56 UTC
Message-ID: <20250923025700.3046260-4-jltobler@gmail.com>
In-Reply-To: <20250923025700.3046260-1-jltobler@gmail.com>

All repository stats are outputted in a human-friendly table form. This format is not suitable for machine parsing. Add a --format option that supports two output modes: `table` and `keyvalue`. The `table` mode is the default format and prints the same table output as before. With the `keyvalue` mode, each line of output contains a key-value pair of a repository stat. The '=' character is used to delimit between keys and values. This mode provides output that is more machine-friendly.

Signed-off-by: Justin Tobler <jltobler@gmail.com>
---
 Documentation/git-repo.adoc | 16 ++++++++--
 builtin/repo.c              | 61 ++++++++++++++++++++++++++++++++++---
 t/t1901-repo-stats.sh       | 25 +++++++++++++++
 3 files changed, 94 insertions(+), 8 deletions(-)

diff --git a/Documentation/git-repo.adoc b/Documentation/git-repo.adoc
index 2a67abfca8..7d0341e4f1 100644
--- a/Documentation/git-repo.adoc
+++ b/Documentation/git-repo.adoc
@@ -9,7 +9,7 @@ SYNOPSIS
 --------
 [synopsis]
 git repo info [--format=(keyvalue|nul)] [-z] [<key>...]
-git repo stats
+git repo stats [--format=(table|keyvalue)]
 
 DESCRIPTION
 -----------
@@ -44,12 +44,22 @@ supported:
 +
 `-z` is an alias for `--format=nul`.
 
-stats::
+`stats [--format=(table|keyvalue)]`::
 	Retrieve stats about the current repository. All references and
 	reachable objects in the repository are categorized and counted
 	accordingly.
 +
-The table output format may change and is not intended for machine parsing.
+The output format can be chosen through the flag `--format`. Two formats are
+supported:
++
+`table`:::
+	Outputs repository stats in a human-friendly table and is used by
+	default. This format may change and is not intended for machine
+	parsing.
+
+`keyvalue`:::
+	Each line of output contains a key-value pair of a repostiory stat. The
+	'=' character is used to delimit between the key and the value.
 
 INFO KEYS
 ---------
diff --git a/builtin/repo.c b/builtin/repo.c
index a24ea0e66b..4c16a68e4e 100644
--- a/builtin/repo.c
+++ b/builtin/repo.c
@@ -14,13 +14,14 @@
 
 static const char *const repo_usage[] = {
 	"git repo info [--format=(keyvalue|nul)] [-z] [<key>...]",
-	"git repo stats",
+	"git repo stats [--format=(table|keyvalue)]",
 	NULL
 };
 
 typedef int get_value_fn(struct repository *repo, struct strbuf *buf);
 
 enum output_format {
+	FORMAT_TABLE,
 	FORMAT_KEYVALUE,
 	FORMAT_NUL_TERMINATED,
 };
@@ -135,6 +136,8 @@ static int parse_format_cb(const struct option *opt,
 		*format = FORMAT_NUL_TERMINATED;
 	else if (!strcmp(arg, "keyvalue"))
 		*format = FORMAT_KEYVALUE;
+	else if (!strcmp(arg, "table"))
+		*format = FORMAT_TABLE;
 	else
 		die(_("invalid format '%s'"), arg);
 
@@ -157,6 +160,8 @@ static int repo_info(int argc, const char **argv, const char *prefix,
 	};
 
 	argc = parse_options(argc, argv, prefix, options, repo_usage, 0);
+	if (format == FORMAT_TABLE)
+		die(_("table format not supported"));
 
 	return print_fields(argc, argv, repo, format);
 }
@@ -286,6 +291,32 @@ static void stats_table_print(struct stats_table *table)
 	strbuf_release(&buf);
 }
 
+static void stats_print(struct stats *stats)
+{
+	struct strbuf buf = STRBUF_INIT;
+
+	strbuf_addf(&buf, "references.branches.count=%" PRIuMAX "\n",
+		    (uintmax_t)stats->refs.branches);
+	strbuf_addf(&buf, "references.tags.count=%" PRIuMAX "\n",
+		    (uintmax_t)stats->refs.tags);
+	strbuf_addf(&buf, "references.remotes.count=%" PRIuMAX "\n",
+		    (uintmax_t)stats->refs.remotes);
+	strbuf_addf(&buf, "references.others.count=%" PRIuMAX "\n",
+		    (uintmax_t)stats->refs.others);
+
+	strbuf_addf(&buf, "objects.commits.count=%" PRIuMAX "\n",
+		    (uintmax_t)stats->objects.commits);
+	strbuf_addf(&buf, "objects.trees.count=%" PRIuMAX "\n",
+		    (uintmax_t)stats->objects.trees);
+	strbuf_addf(&buf, "objects.blobs.count=%" PRIuMAX "\n",
+		    (uintmax_t)stats->objects.blobs);
+	strbuf_addf(&buf, "objects.tags.count=%" PRIuMAX "\n",
+		    (uintmax_t)stats->objects.tags);
+
+	fwrite(buf.buf, sizeof(char), buf.len, stdout);
+	strbuf_release(&buf);
+}
+
 static void stats_count_references(struct ref_stats *stats, struct ref_array *refs)
 {
 	for (int i = 0; i < refs->nr; i++) {
@@ -359,9 +390,16 @@ static void stats_count_objects(struct object_stats *stats,
 	path_walk_info_clear(&info);
 }
 
-static int repo_stats(int argc UNUSED, const char **argv UNUSED,
-		      const char *prefix, struct repository *repo)
+static int repo_stats(int argc, const char **argv, const char *prefix,
+		      struct repository *repo)
 {
+	enum output_format format = FORMAT_TABLE;
+	struct option options[] = {
+		OPT_CALLBACK_F(0, "format", &format, N_("format"),
+			       N_("output format"),
+			       PARSE_OPT_NONEG, parse_format_cb),
+		OPT_END()
+	};
 	struct ref_filter filter = REF_FILTER_INIT;
 	struct strvec ref_patterns = STRVEC_INIT;
 	struct stats_table table = { 0 };
@@ -369,6 +407,10 @@ static int repo_stats(int argc UNUSED, const char **argv UNUSED,
 	struct stats stats = { 0 };
 	struct rev_info revs;
 
+	parse_options(argc, argv, prefix, options, repo_usage, 0);
+	if (format == FORMAT_NUL_TERMINATED)
+		die(_("nul format not yet supported"));
+
 	repo_init_revisions(repo, &revs, prefix);
 	filter.name_patterns = ref_patterns.v;
 	filter_refs(&refs, &filter, FILTER_REFS_REGULAR);
@@ -376,8 +418,17 @@ static int repo_stats(int argc UNUSED, const char **argv UNUSED,
 	stats_count_references(&stats.refs, &refs);
 	stats_count_objects(&stats.objects, &refs, &revs);
 
-	stats_table_setup(&table, &stats);
-	stats_table_print(&table);
+	switch (format) {
+	case FORMAT_TABLE:
+		stats_table_setup(&table, &stats);
+		stats_table_print(&table);
+		break;
+	case FORMAT_KEYVALUE:
+		stats_print(&stats);
+		break;
+	default:
+		BUG("not a valid output format: %d", format);
+	}
 
 	string_list_clear(&table.rows, 1);
 	strvec_clear(&ref_patterns);
diff --git a/t/t1901-repo-stats.sh b/t/t1901-repo-stats.sh
index c6a7f08be5..5bc6d9d5c4 100755
--- a/t/t1901-repo-stats.sh
+++ b/t/t1901-repo-stats.sh
@@ -102,4 +102,29 @@ test_expect_success 'repository stats with objects' '
 	)
 '
 
+test_expect_success 'repository stats with keyvalue format' '
+	test_when_finished "rm -rf repo" &&
+	git init repo &&
+	(
+		cd repo &&
+		test_commit_bulk 42 &&
+		git tag -a foo -m bar &&
+		git repo stats --format=keyvalue >out 2>err &&
+
+		cat >expect <<-EOF &&
+		references.branches.count=1
+		references.tags.count=1
+		references.remotes.count=0
+		references.others.count=0
+		objects.commits.count=42
+		objects.trees.count=42
+		objects.blobs.count=42
+		objects.tags.count=1
+		EOF
+
+		test_cmp expect out &&
+		test_line_count = 0 err
+	)
+'
+
 test_done

-- 
2.51.0.193.g4975ec3473b