[PATCH v6 6/7] builtin/repo: add keyvalue and nul format for structure stats

[Justin Tobler <jltobler@gmail.com>]

All repository structure stats are outputted in a human-friendly table
form. This format is not suitable for machine parsing. Add a --format
option that supports three output modes: `table`, `keyvalue`, and `nul`.
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. The `nul` mode is similar to `keyvalue`, but key-values are
delimited by a NUL character instead of a newline. Also, instead of a
'=' character to delimit between keys and values, a newline character is
used. This allows stat values to support special characters without
having to cquote them. These two new modes provides output that is more
machine-friendly.

Signed-off-by: Justin Tobler <jltobler@gmail.com>
---
 Documentation/git-repo.adoc | 25 +++++++++++++++--
 builtin/repo.c              | 55 ++++++++++++++++++++++++++++++++++---
 t/t1901-repo-structure.sh   | 33 ++++++++++++++++++++++
 3 files changed, 106 insertions(+), 7 deletions(-)

diff --git a/Documentation/git-repo.adoc b/Documentation/git-repo.adoc
index ae62d2415f..ce43cb19c8 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 structure
+git repo structure [--format=(table|keyvalue|nul)]
 
 DESCRIPTION
 -----------
@@ -44,7 +44,7 @@ supported:
 +
 `-z` is an alias for `--format=nul`.
 
-`structure`::
+`structure [--format=(table|keyvalue|nul)]`::
 	Retrieve statistics about the current repository structure. The
 	following kinds of information are reported:
 +
@@ -52,7 +52,26 @@ supported:
 * Reachable object counts categorized by type
 
 +
-The table output format may change and is not intended for machine parsing.
+The output format can be chosen through the flag `--format`. Three formats are
+supported:
++
+`table`:::
+	Outputs repository stats in a human-friendly table. This format may
+	change and is not intended for machine parsing. This is the default
+	format.
+
+`keyvalue`:::
+	Each line of output contains a key-value pair for a repository stat.
+	The '=' character is used to delimit between the key and the value.
+	Values containing "unusual" characters are quoted as explained for the
+	configuration variable `core.quotePath` (see linkgit:git-config[1]).
+
+`nul`:::
+	Similar to `keyvalue`, but uses a NUL character to delimit between
+	key-value pairs instead of a newline. Also uses a newline character as
+	the delimiter between the key and value instead of '='. Unlike the
+	`keyvalue` format, values containing "unusual" characters are never
+	quoted.
 
 INFO KEYS
 ---------
diff --git a/builtin/repo.c b/builtin/repo.c
index f39f06ee8c..1754cc7e5d 100644
--- a/builtin/repo.c
+++ b/builtin/repo.c
@@ -15,13 +15,14 @@
 
 static const char *const repo_usage[] = {
 	"git repo info [--format=(keyvalue|nul)] [-z] [<key>...]",
-	"git repo structure",
+	"git repo structure [--format=(table|keyvalue|nul)]",
 	NULL
 };
 
 typedef int get_value_fn(struct repository *repo, struct strbuf *buf);
 
 enum output_format {
+	FORMAT_TABLE,
 	FORMAT_KEYVALUE,
 	FORMAT_NUL_TERMINATED,
 };
@@ -136,6 +137,8 @@ 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);
 
@@ -158,6 +161,8 @@ static int cmd_repo_info(int argc, const char **argv, const char *prefix,
 	};
 
 	argc = parse_options(argc, argv, prefix, options, repo_usage, 0);
+	if (format != FORMAT_KEYVALUE && format != FORMAT_NUL_TERMINATED)
+		die(_("unsupported output format"));
 
 	return print_fields(argc, argv, repo, format);
 }
@@ -330,6 +335,30 @@ static void stats_table_clear(struct stats_table *table)
 	string_list_clear(&table->rows, 1);
 }
 
+static void structure_keyvalue_print(struct repo_structure *stats,
+				     char key_delim, char value_delim)
+{
+	printf("references.branches.count%c%" PRIuMAX "%c", key_delim,
+	       (uintmax_t)stats->refs.branches, value_delim);
+	printf("references.tags.count%c%" PRIuMAX "%c", key_delim,
+	       (uintmax_t)stats->refs.tags, value_delim);
+	printf("references.remotes.count%c%" PRIuMAX "%c", key_delim,
+	       (uintmax_t)stats->refs.remotes, value_delim);
+	printf("references.others.count%c%" PRIuMAX "%c", key_delim,
+	       (uintmax_t)stats->refs.others, value_delim);
+
+	printf("objects.commits.count%c%" PRIuMAX "%c", key_delim,
+	       (uintmax_t)stats->objects.commits, value_delim);
+	printf("objects.trees.count%c%" PRIuMAX "%c", key_delim,
+	       (uintmax_t)stats->objects.trees, value_delim);
+	printf("objects.blobs.count%c%" PRIuMAX "%c", key_delim,
+	       (uintmax_t)stats->objects.blobs, value_delim);
+	printf("objects.tags.count%c%" PRIuMAX "%c", key_delim,
+	       (uintmax_t)stats->objects.tags, value_delim);
+
+	fflush(stdout);
+}
+
 struct count_references_data {
 	struct ref_stats *stats;
 	struct rev_info *revs;
@@ -426,9 +455,15 @@ static int cmd_repo_structure(int argc, const char **argv, const char *prefix,
 	struct stats_table table = {
 		.rows = STRING_LIST_INIT_DUP,
 	};
+	enum output_format format = FORMAT_TABLE;
 	struct repo_structure stats = { 0 };
 	struct rev_info revs;
-	struct option options[] = { 0 };
+	struct option options[] = {
+		OPT_CALLBACK_F(0, "format", &format, N_("format"),
+			       N_("output format"),
+			       PARSE_OPT_NONEG, parse_format_cb),
+		OPT_END()
+	};
 
 	argc = parse_options(argc, argv, prefix, options, repo_usage, 0);
 	if (argc)
@@ -439,8 +474,20 @@ static int cmd_repo_structure(int argc, const char **argv, const char *prefix,
 	structure_count_references(&stats.refs, &revs, repo);
 	structure_count_objects(&stats.objects, &revs);
 
-	stats_table_setup_structure(&table, &stats);
-	stats_table_print_structure(&table);
+	switch (format) {
+	case FORMAT_TABLE:
+		stats_table_setup_structure(&table, &stats);
+		stats_table_print_structure(&table);
+		break;
+	case FORMAT_KEYVALUE:
+		structure_keyvalue_print(&stats, '=', '\n');
+		break;
+	case FORMAT_NUL_TERMINATED:
+		structure_keyvalue_print(&stats, '\n', '\0');
+		break;
+	default:
+		BUG("invalid output format");
+	}
 
 	stats_table_clear(&table);
 	release_revisions(&revs);
diff --git a/t/t1901-repo-structure.sh b/t/t1901-repo-structure.sh
index c32cf4e239..14bd8aede5 100755
--- a/t/t1901-repo-structure.sh
+++ b/t/t1901-repo-structure.sh
@@ -73,4 +73,37 @@ test_expect_success 'repository with references and objects' '
 	)
 '
 
+test_expect_success 'keyvalue and nul format' '
+	test_when_finished "rm -rf repo" &&
+	git init repo &&
+	(
+		cd repo &&
+		test_commit_bulk 42 &&
+		git tag -a foo -m bar &&
+
+		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
+
+		git repo structure --format=keyvalue >out 2>err &&
+
+		test_cmp expect out &&
+		test_line_count = 0 err &&
+
+		# Replace key and value delimiters for nul format.
+		tr "\n=" "\0\n" <expect >expect_nul &&
+		git repo structure --format=nul >out 2>err &&
+
+		test_cmp expect_nul out &&
+		test_line_count = 0 err
+	)
+'
+
 test_done
-- 
2.51.0.193.g4975ec3473b