[PATCH 5/6] builtin/repo: add disk size info to keyvalue stucture output

[Justin Tobler <jltobler@gmail.com>]

Similar to a prior commit, extend the keyvalue and nul output formats of
the git-repo(1) structure command to additionally provide info regarding
total object disk sizes by object type.

Since disk size may vary between platforms, tests do not validate actual
values and only check that size info is printed in an empty repository.

Signed-off-by: Justin Tobler <jltobler@gmail.com>
---
 Documentation/git-repo.adoc |  1 +
 builtin/repo.c              | 18 +++++++++++++++
 t/t1901-repo-structure.sh   | 45 +++++++++++++++++++++++++++++--------
 3 files changed, 55 insertions(+), 9 deletions(-)

diff --git a/Documentation/git-repo.adoc b/Documentation/git-repo.adoc
index 287eee4b93..861073f641 100644
--- a/Documentation/git-repo.adoc
+++ b/Documentation/git-repo.adoc
@@ -51,6 +51,7 @@ supported:
 * Reference counts categorized by type
 * Reachable object counts categorized by type
 * Total inflated size of reachable objects by type
+* Total disk size of reachable objects by type
 
 +
 The output format can be chosen through the flag `--format`. Three formats are
diff --git a/builtin/repo.c b/builtin/repo.c
index 5c37f4116f..8ea7c9b24f 100644
--- a/builtin/repo.c
+++ b/builtin/repo.c
@@ -214,6 +214,7 @@ struct object_values {
 struct object_stats {
 	struct object_values type_counts;
 	struct object_values inflated_sizes;
+	struct object_values disk_sizes;
 };
 
 struct repo_structure {
@@ -509,6 +510,15 @@ static void structure_keyvalue_print(struct repo_structure *stats,
 	printf("objects.tags.inflated%c%" PRIuMAX "%c", key_delim,
 	       (uintmax_t)stats->objects.inflated_sizes.tags, value_delim);
 
+	printf("objects.commits.disk%c%" PRIuMAX "%c", key_delim,
+	       (uintmax_t)stats->objects.disk_sizes.commits, value_delim);
+	printf("objects.trees.disk%c%" PRIuMAX "%c", key_delim,
+	       (uintmax_t)stats->objects.disk_sizes.trees, value_delim);
+	printf("objects.blobs.disk%c%" PRIuMAX "%c", key_delim,
+	       (uintmax_t)stats->objects.disk_sizes.blobs, value_delim);
+	printf("objects.tags.disk%c%" PRIuMAX "%c", key_delim,
+	       (uintmax_t)stats->objects.disk_sizes.tags, value_delim);
+
 	fflush(stdout);
 }
 
@@ -583,13 +593,16 @@ static int count_objects(const char *path UNUSED, struct oid_array *oids,
 	struct count_objects_data *data = cb_data;
 	struct object_stats *stats = data->stats;
 	size_t inflated_total = 0;
+	size_t disk_total = 0;
 	size_t object_count;
 
 	for (size_t i = 0; i < oids->nr; i++) {
 		struct object_info oi = OBJECT_INFO_INIT;
 		unsigned long inflated;
+		off_t disk;
 
 		oi.sizep = &inflated;
+		oi.disk_sizep = &disk;
 
 		if (odb_read_object_info_extended(data->odb, &oids->oid[i], &oi,
 						  OBJECT_INFO_FOR_PREFETCH) < 0)
@@ -597,24 +610,29 @@ static int count_objects(const char *path UNUSED, struct oid_array *oids,
 			    oid_to_hex(&oids->oid[i]));
 
 		inflated_total += inflated;
+		disk_total += disk;
 	}
 
 	switch (type) {
 	case OBJ_TAG:
 		stats->type_counts.tags += oids->nr;
 		stats->inflated_sizes.tags += inflated_total;
+		stats->disk_sizes.tags += disk_total;
 		break;
 	case OBJ_COMMIT:
 		stats->type_counts.commits += oids->nr;
 		stats->inflated_sizes.commits += inflated_total;
+		stats->disk_sizes.commits += disk_total;
 		break;
 	case OBJ_TREE:
 		stats->type_counts.trees += oids->nr;
 		stats->inflated_sizes.trees += inflated_total;
+		stats->disk_sizes.trees += disk_total;
 		break;
 	case OBJ_BLOB:
 		stats->type_counts.blobs += oids->nr;
 		stats->inflated_sizes.blobs += inflated_total;
+		stats->disk_sizes.blobs += disk_total;
 		break;
 	default:
 		BUG("invalid object type");
diff --git a/t/t1901-repo-structure.sh b/t/t1901-repo-structure.sh
index 0ae96e6bbf..a98c651f1d 100755
--- a/t/t1901-repo-structure.sh
+++ b/t/t1901-repo-structure.sh
@@ -35,6 +35,37 @@ test_expect_success 'empty repository' '
 		git repo structure >out 2>err &&
 
 		test_cmp expect out &&
+		test_line_count = 0 err &&
+
+		cat >expect <<-\EOF &&
+		references.branches.count=0
+		references.tags.count=0
+		references.remotes.count=0
+		references.others.count=0
+		objects.commits.count=0
+		objects.trees.count=0
+		objects.blobs.count=0
+		objects.tags.count=0
+		objects.commits.inflated=0
+		objects.trees.inflated=0
+		objects.blobs.inflated=0
+		objects.tags.inflated=0
+		objects.commits.disk=0
+		objects.trees.disk=0
+		objects.blobs.disk=0
+		objects.tags.disk=0
+		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
 	)
 '
@@ -83,7 +114,7 @@ test_expect_success SHA1 'repository with references and objects' '
 	)
 '
 
-test_expect_success SHA1 'keyvalue and nul format' '
+test_expect_success SHA1 'keyvalue format' '
 	test_when_finished "rm -rf repo" &&
 	git init repo &&
 	(
@@ -106,16 +137,12 @@ test_expect_success SHA1 'keyvalue and nul format' '
 		objects.tags.inflated=132
 		EOF
 
-		git repo structure --format=keyvalue >out 2>err &&
+		git repo structure --format=keyvalue >out.raw 2>err &&
 
-		test_cmp expect out &&
-		test_line_count = 0 err &&
+		# Strip object disk usage from output due to platform variance.
+		grep -v "objects\..*\.disk=" out.raw >out &&
 
-		# 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_cmp expect out &&
 		test_line_count = 0 err
 	)
 '
-- 
2.52.0.209.ge85ae279b0