From: Justin Tobler <jltobler@gmail•com>
To: git@vger•kernel.org
Cc: ps@pks•im, karthik.188@gmail•com, sunshine@sunshineco•com,
gitster@pobox•com, Justin Tobler <jltobler@gmail•com>
Subject: [PATCH v6 5/7] builtin/repo: add object counts in structure output
Date: Tue, 21 Oct 2025 13:25:59 -0500 [thread overview]
Message-ID: <20251021182601.2687284-6-jltobler@gmail.com> (raw)
In-Reply-To: <20251021182601.2687284-1-jltobler@gmail.com>
The amount of objects in a repository can provide insight regarding its
shape. To surface this information, use the path-walk API to count the
number of reachable objects in the repository by object type. All
regular references are used to determine the reachable set of objects.
The object counts are appended to the same table containing the
reference information.
Signed-off-by: Justin Tobler <jltobler@gmail•com>
---
Documentation/git-repo.adoc | 1 +
builtin/repo.c | 105 +++++++++++++++++++++++++++++++++---
t/t1901-repo-structure.sh | 19 ++++++-
3 files changed, 117 insertions(+), 8 deletions(-)
diff --git a/Documentation/git-repo.adoc b/Documentation/git-repo.adoc
index 8193298dd5..ae62d2415f 100644
--- a/Documentation/git-repo.adoc
+++ b/Documentation/git-repo.adoc
@@ -49,6 +49,7 @@ supported:
following kinds of information are reported:
+
* Reference counts categorized by type
+* Reachable object counts categorized by type
+
The table output format may change and is not intended for machine parsing.
diff --git a/builtin/repo.c b/builtin/repo.c
index e77e8db563..f39f06ee8c 100644
--- a/builtin/repo.c
+++ b/builtin/repo.c
@@ -3,9 +3,11 @@
#include "builtin.h"
#include "environment.h"
#include "parse-options.h"
+#include "path-walk.h"
#include "quote.h"
#include "ref-filter.h"
#include "refs.h"
+#include "revision.h"
#include "strbuf.h"
#include "string-list.h"
#include "shallow.h"
@@ -167,6 +169,18 @@ struct ref_stats {
size_t others;
};
+struct object_stats {
+ size_t tags;
+ size_t commits;
+ size_t trees;
+ size_t blobs;
+};
+
+struct repo_structure {
+ struct ref_stats refs;
+ struct object_stats objects;
+};
+
struct stats_table {
struct string_list rows;
@@ -234,9 +248,17 @@ static inline size_t get_total_reference_count(struct ref_stats *stats)
return stats->branches + stats->remotes + stats->tags + stats->others;
}
+static inline size_t get_total_object_count(struct object_stats *stats)
+{
+ return stats->tags + stats->commits + stats->trees + stats->blobs;
+}
+
static void stats_table_setup_structure(struct stats_table *table,
- struct ref_stats *refs)
+ struct repo_structure *stats)
{
+ struct object_stats *objects = &stats->objects;
+ struct ref_stats *refs = &stats->refs;
+ size_t object_total;
size_t ref_total;
ref_total = get_total_reference_count(refs);
@@ -246,6 +268,15 @@ static void stats_table_setup_structure(struct stats_table *table,
stats_table_count_addf(table, refs->tags, " * %s", _("Tags"));
stats_table_count_addf(table, refs->remotes, " * %s", _("Remotes"));
stats_table_count_addf(table, refs->others, " * %s", _("Others"));
+
+ object_total = get_total_object_count(objects);
+ stats_table_addf(table, "");
+ stats_table_addf(table, "* %s", _("Reachable objects"));
+ stats_table_count_addf(table, object_total, " * %s", _("Count"));
+ stats_table_count_addf(table, objects->commits, " * %s", _("Commits"));
+ stats_table_count_addf(table, objects->trees, " * %s", _("Trees"));
+ stats_table_count_addf(table, objects->blobs, " * %s", _("Blobs"));
+ stats_table_count_addf(table, objects->tags, " * %s", _("Tags"));
}
static void stats_table_print_structure(const struct stats_table *table)
@@ -299,12 +330,18 @@ static void stats_table_clear(struct stats_table *table)
string_list_clear(&table->rows, 1);
}
+struct count_references_data {
+ struct ref_stats *stats;
+ struct rev_info *revs;
+};
+
static int count_references(const char *refname,
const char *referent UNUSED,
- const struct object_id *oid UNUSED,
+ const struct object_id *oid,
int flags UNUSED, void *cb_data)
{
- struct ref_stats *stats = cb_data;
+ struct count_references_data *data = cb_data;
+ struct ref_stats *stats = data->stats;
switch (ref_kind_from_refname(refname)) {
case FILTER_REFS_BRANCHES:
@@ -323,13 +360,64 @@ static int count_references(const char *refname,
BUG("unexpected reference type");
}
+ /*
+ * While iterating through references for counting, also add OIDs in
+ * preparation for the path walk.
+ */
+ add_pending_oid(data->revs, NULL, oid, 0);
+
return 0;
}
static void structure_count_references(struct ref_stats *stats,
+ struct rev_info *revs,
struct repository *repo)
{
- refs_for_each_ref(get_main_ref_store(repo), count_references, &stats);
+ struct count_references_data data = {
+ .stats = stats,
+ .revs = revs,
+ };
+
+ refs_for_each_ref(get_main_ref_store(repo), count_references, &data);
+}
+
+
+static int count_objects(const char *path UNUSED, struct oid_array *oids,
+ enum object_type type, void *cb_data)
+{
+ struct object_stats *stats = cb_data;
+
+ switch (type) {
+ case OBJ_TAG:
+ stats->tags += oids->nr;
+ break;
+ case OBJ_COMMIT:
+ stats->commits += oids->nr;
+ break;
+ case OBJ_TREE:
+ stats->trees += oids->nr;
+ break;
+ case OBJ_BLOB:
+ stats->blobs += oids->nr;
+ break;
+ default:
+ BUG("invalid object type");
+ }
+
+ return 0;
+}
+
+static void structure_count_objects(struct object_stats *stats,
+ struct rev_info *revs)
+{
+ struct path_walk_info info = PATH_WALK_INFO_INIT;
+
+ info.revs = revs;
+ info.path_fn = count_objects;
+ info.path_fn_data = stats;
+
+ walk_objects_by_path(&info);
+ path_walk_info_clear(&info);
}
static int cmd_repo_structure(int argc, const char **argv, const char *prefix,
@@ -338,19 +426,24 @@ static int cmd_repo_structure(int argc, const char **argv, const char *prefix,
struct stats_table table = {
.rows = STRING_LIST_INIT_DUP,
};
- struct ref_stats stats = { 0 };
+ struct repo_structure stats = { 0 };
+ struct rev_info revs;
struct option options[] = { 0 };
argc = parse_options(argc, argv, prefix, options, repo_usage, 0);
if (argc)
usage(_("too many arguments"));
- structure_count_references(&stats, repo);
+ repo_init_revisions(repo, &revs, 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);
stats_table_clear(&table);
+ release_revisions(&revs);
return 0;
}
diff --git a/t/t1901-repo-structure.sh b/t/t1901-repo-structure.sh
index e592eea0eb..c32cf4e239 100755
--- a/t/t1901-repo-structure.sh
+++ b/t/t1901-repo-structure.sh
@@ -18,6 +18,13 @@ test_expect_success 'empty repository' '
| * Tags | 0 |
| * Remotes | 0 |
| * Others | 0 |
+ | | |
+ | * Reachable objects | |
+ | * Count | 0 |
+ | * Commits | 0 |
+ | * Trees | 0 |
+ | * Blobs | 0 |
+ | * Tags | 0 |
EOF
git repo structure >out 2>err &&
@@ -27,17 +34,18 @@ test_expect_success 'empty repository' '
)
'
-test_expect_success 'repository with references' '
+test_expect_success 'repository with references and objects' '
test_when_finished "rm -rf repo" &&
git init repo &&
(
cd repo &&
- git commit --allow-empty -m init &&
+ test_commit_bulk 42 &&
git tag -a foo -m bar &&
oid="$(git rev-parse HEAD)" &&
git update-ref refs/remotes/origin/foo "$oid" &&
+ # Also creates a commit, tree, and blob.
git notes add -m foo &&
cat >expect <<-\EOF &&
@@ -49,6 +57,13 @@ test_expect_success 'repository with references' '
| * Tags | 1 |
| * Remotes | 1 |
| * Others | 1 |
+ | | |
+ | * Reachable objects | |
+ | * Count | 130 |
+ | * Commits | 43 |
+ | * Trees | 43 |
+ | * Blobs | 43 |
+ | * Tags | 1 |
EOF
git repo structure >out 2>err &&
--
2.51.0.193.g4975ec3473b
next prev parent reply other threads:[~2025-10-21 18:26 UTC|newest]
Thread overview: 92+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-09-23 2:56 [PATCH 0/4] builtin/repo: introduce stats subcommand Justin Tobler
2025-09-23 2:56 ` [PATCH 1/4] " Justin Tobler
2025-09-23 10:52 ` Patrick Steinhardt
2025-09-23 15:10 ` Justin Tobler
2025-09-23 15:26 ` Patrick Steinhardt
2025-09-23 15:22 ` Karthik Nayak
2025-09-23 15:55 ` Justin Tobler
2025-09-23 2:56 ` [PATCH 2/4] builtin/repo: add object counts in stats output Justin Tobler
2025-09-23 10:52 ` Patrick Steinhardt
2025-09-23 15:19 ` Justin Tobler
2025-09-23 15:30 ` Karthik Nayak
2025-09-23 15:56 ` Justin Tobler
2025-09-23 2:56 ` [PATCH 3/4] builtin/repo: add keyvalue format for stats Justin Tobler
2025-09-23 10:53 ` Patrick Steinhardt
2025-09-23 15:26 ` Justin Tobler
2025-09-23 15:39 ` Karthik Nayak
2025-09-23 15:59 ` Justin Tobler
2025-09-23 2:57 ` [PATCH 4/4] builtin/repo: add nul " Justin Tobler
2025-09-23 10:53 ` Patrick Steinhardt
2025-09-23 15:33 ` Justin Tobler
2025-09-24 4:48 ` Patrick Steinhardt
2025-09-23 15:41 ` Karthik Nayak
2025-09-23 16:02 ` Justin Tobler
2025-09-24 21:24 ` [PATCH v2 0/6] builtin/repo: introduce stats subcommand Justin Tobler
2025-09-24 21:24 ` [PATCH v2 1/6] builtin/repo: rename repo_info() to cmd_repo_info() Justin Tobler
2025-09-24 21:24 ` [PATCH v2 2/6] ref-filter: allow NULL filter pattern Justin Tobler
2025-09-24 21:24 ` [PATCH v2 3/6] builtin/repo: introduce stats subcommand Justin Tobler
2025-09-25 5:38 ` Patrick Steinhardt
2025-09-25 13:01 ` Justin Tobler
2025-09-24 21:24 ` [PATCH v2 4/6] builtin/repo: add object counts in stats output Justin Tobler
2025-09-24 21:24 ` [PATCH v2 5/6] builtin/repo: add keyvalue and nul format for stats Justin Tobler
2025-09-25 5:39 ` Patrick Steinhardt
2025-09-25 13:16 ` Justin Tobler
2025-09-25 13:58 ` Patrick Steinhardt
2025-09-24 21:24 ` [PATCH v2 6/6] builtin/repo: add progress meter " Justin Tobler
2025-09-25 5:39 ` Patrick Steinhardt
2025-09-25 13:20 ` Justin Tobler
2025-09-25 23:29 ` [PATCH v3 0/7] builtin/repo: introduce stats subcommand Justin Tobler
2025-09-25 23:29 ` [PATCH v3 1/7] builtin/repo: rename repo_info() to cmd_repo_info() Justin Tobler
2025-09-25 23:29 ` [PATCH v3 2/7] ref-filter: allow NULL filter pattern Justin Tobler
2025-09-25 23:29 ` [PATCH v3 3/7] clang-format: exclude control macros from SpaceBeforeParens Justin Tobler
2025-09-25 23:29 ` [PATCH v3 4/7] builtin/repo: introduce stats subcommand Justin Tobler
2025-09-25 23:51 ` Eric Sunshine
2025-09-26 1:38 ` Justin Tobler
2025-09-25 23:29 ` [PATCH v3 5/7] builtin/repo: add object counts in stats output Justin Tobler
2025-09-25 23:29 ` [PATCH v3 6/7] builtin/repo: add keyvalue and nul format for stats Justin Tobler
2025-09-25 23:29 ` [PATCH v3 7/7] builtin/repo: add progress meter " Justin Tobler
2025-09-27 14:50 ` [PATCH v4 0/7] builtin/repo: introduce stats subcommand Justin Tobler
2025-09-27 14:50 ` [PATCH v4 1/7] builtin/repo: rename repo_info() to cmd_repo_info() Justin Tobler
2025-09-27 14:50 ` [PATCH v4 2/7] ref-filter: allow NULL filter pattern Justin Tobler
2025-09-27 14:50 ` [PATCH v4 3/7] clang-format: exclude control macros from SpaceBeforeParens Justin Tobler
2025-09-27 15:40 ` Junio C Hamano
2025-09-27 15:51 ` Justin Tobler
2025-09-27 23:49 ` Junio C Hamano
2025-09-27 14:50 ` [PATCH v4 4/7] builtin/repo: introduce stats subcommand Justin Tobler
2025-09-27 16:32 ` Junio C Hamano
2025-10-09 22:09 ` Justin Tobler
2025-10-10 0:42 ` Justin Tobler
2025-10-10 6:53 ` Patrick Steinhardt
2025-10-10 14:34 ` Justin Tobler
2025-10-13 6:13 ` Patrick Steinhardt
2025-09-27 14:50 ` [PATCH v4 5/7] builtin/repo: add object counts in stats output Justin Tobler
2025-09-27 14:50 ` [PATCH v4 6/7] builtin/repo: add keyvalue and nul format for stats Justin Tobler
2025-09-27 14:50 ` [PATCH v4 7/7] builtin/repo: add progress meter " Justin Tobler
2025-09-27 16:33 ` [PATCH v4 0/7] builtin/repo: introduce stats subcommand Junio C Hamano
2025-10-15 21:12 ` [PATCH v5 0/6] builtin/repo: introduce structure subcommand Justin Tobler
2025-10-15 21:12 ` [PATCH v5 1/6] builtin/repo: rename repo_info() to cmd_repo_info() Justin Tobler
2025-10-15 21:12 ` [PATCH v5 2/6] ref-filter: allow NULL filter pattern Justin Tobler
2025-10-15 21:12 ` [PATCH v5 3/6] builtin/repo: introduce structure subcommand Justin Tobler
2025-10-16 10:58 ` Patrick Steinhardt
2025-10-21 16:04 ` Justin Tobler
2025-10-15 21:12 ` [PATCH v5 4/6] builtin/repo: add object counts in structure output Justin Tobler
2025-10-15 21:12 ` [PATCH v5 5/6] builtin/repo: add keyvalue and nul format for structure stats Justin Tobler
2025-10-15 21:12 ` [PATCH v5 6/6] builtin/repo: add progress meter " Justin Tobler
2025-10-21 18:25 ` [PATCH v6 0/7] builtin/repo: introduce structure subcommand Justin Tobler
2025-10-21 18:25 ` [PATCH v6 1/7] builtin/repo: rename repo_info() to cmd_repo_info() Justin Tobler
2025-10-21 18:25 ` [PATCH v6 2/7] ref-filter: allow NULL filter pattern Justin Tobler
2025-10-21 18:25 ` [PATCH v6 3/7] ref-filter: export ref_kind_from_refname() Justin Tobler
2025-10-21 18:25 ` [PATCH v6 4/7] builtin/repo: introduce structure subcommand Justin Tobler
2025-10-22 5:01 ` Patrick Steinhardt
2025-10-22 13:50 ` Justin Tobler
2025-10-22 20:15 ` Lucas Seiki Oshiro
2025-10-22 23:42 ` Justin Tobler
2025-10-21 18:25 ` Justin Tobler [this message]
2025-10-21 18:26 ` [PATCH v6 6/7] builtin/repo: add keyvalue and nul format for structure stats Justin Tobler
2025-10-22 20:34 ` Lucas Seiki Oshiro
2025-10-23 0:03 ` Justin Tobler
2025-10-21 18:26 ` [PATCH v6 7/7] builtin/repo: add progress meter " Justin Tobler
2025-10-22 19:23 ` [PATCH v6 0/7] builtin/repo: introduce structure subcommand Lucas Seiki Oshiro
2025-10-23 0:05 ` Justin Tobler
2025-10-23 20:54 ` Junio C Hamano
2025-10-24 5:14 ` Patrick Steinhardt
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20251021182601.2687284-6-jltobler@gmail.com \
--to=jltobler@gmail$(echo .)com \
--cc=git@vger$(echo .)kernel.org \
--cc=gitster@pobox$(echo .)com \
--cc=karthik.188@gmail$(echo .)com \
--cc=ps@pks$(echo .)im \
--cc=sunshine@sunshineco$(echo .)com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox