builtin/repo: find commit with most parents

Complex merge events may produce an octopus merge where the resulting
merge commit has more than two parents. While iterating through objects
in the repository for git-repo-structure, identify the commit with the
most parents and display it in the output.

Signed-off-by: Justin Tobler <jltobler@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
This commit is contained in:
Justin Tobler
2026-03-02 15:45:25 -06:00
committed by Junio C Hamano
parent e00bb8c76e
commit 18952a1ef1
2 changed files with 123 additions and 73 deletions

View File

@@ -1,6 +1,7 @@
#define USE_THE_REPOSITORY_VARIABLE
#include "builtin.h"
#include "commit.h"
#include "environment.h"
#include "hash.h"
#include "hex.h"
@@ -208,6 +209,8 @@ struct largest_objects {
struct object_data commit_size;
struct object_data tree_size;
struct object_data blob_size;
struct object_data parent_count;
};
struct ref_stats {
@@ -318,6 +321,27 @@ static void stats_table_count_addf(struct stats_table *table, size_t value,
va_end(ap);
}
static void stats_table_object_count_addf(struct stats_table *table,
struct object_id *oid, size_t value,
const char *format, ...)
{
struct stats_table_entry *entry;
va_list ap;
CALLOC_ARRAY(entry, 1);
humanise_count(value, &entry->value, &entry->unit);
/*
* A NULL OID should not have a table annotation.
*/
if (!is_null_oid(oid))
entry->oid = oid;
va_start(ap, format);
stats_table_vaddf(table, entry, format, ap);
va_end(ap);
}
static void stats_table_size_addf(struct stats_table *table, size_t value,
const char *format, ...)
{
@@ -425,6 +449,10 @@ static void stats_table_setup_structure(struct stats_table *table,
&objects->largest.commit_size.oid,
objects->largest.commit_size.value,
" * %s", _("Maximum size"));
stats_table_object_count_addf(table,
&objects->largest.parent_count.oid,
objects->largest.parent_count.value,
" * %s", _("Maximum parents"));
stats_table_addf(table, " * %s", _("Trees"));
stats_table_object_size_addf(table,
&objects->largest.tree_size.oid,
@@ -595,6 +623,9 @@ static void structure_keyvalue_print(struct repo_structure *stats,
print_object_data("objects.tags.max_size", key_delim,
&stats->objects.largest.tag_size, value_delim);
print_object_data("objects.commits.max_parents", key_delim,
&stats->objects.largest.parent_count, value_delim);
fflush(stdout);
}
@@ -682,16 +713,24 @@ static int count_objects(const char *path UNUSED, struct oid_array *oids,
for (size_t i = 0; i < oids->nr; i++) {
struct object_info oi = OBJECT_INFO_INIT;
unsigned long inflated;
struct commit *commit;
struct object *obj;
void *content;
off_t disk;
int eaten;
oi.sizep = &inflated;
oi.disk_sizep = &disk;
oi.contentp = &content;
if (odb_read_object_info_extended(data->odb, &oids->oid[i], &oi,
OBJECT_INFO_SKIP_FETCH_OBJECT |
OBJECT_INFO_QUICK) < 0)
continue;
obj = parse_object_buffer(the_repository, &oids->oid[i], type,
inflated, content, &eaten);
switch (type) {
case OBJ_TAG:
stats->type_counts.tags++;
@@ -701,11 +740,14 @@ static int count_objects(const char *path UNUSED, struct oid_array *oids,
inflated);
break;
case OBJ_COMMIT:
commit = object_as_type(obj, OBJ_COMMIT, 0);
stats->type_counts.commits++;
stats->inflated_sizes.commits += inflated;
stats->disk_sizes.commits += disk;
check_largest(&stats->largest.commit_size, &oids->oid[i],
inflated);
check_largest(&stats->largest.parent_count, &oids->oid[i],
commit_list_count(commit->parents));
break;
case OBJ_TREE:
stats->type_counts.trees++;
@@ -724,6 +766,9 @@ static int count_objects(const char *path UNUSED, struct oid_array *oids,
default:
BUG("invalid object type");
}
if (!eaten)
free(content);
}
object_count = get_total_object_values(&stats->type_counts);

View File

@@ -27,41 +27,42 @@ test_expect_success 'empty repository' '
(
cd repo &&
cat >expect <<-\EOF &&
| Repository structure | Value |
| ------------------------ | ------ |
| * References | |
| * Count | 0 |
| * Branches | 0 |
| * Tags | 0 |
| * Remotes | 0 |
| * Others | 0 |
| | |
| * Reachable objects | |
| * Count | 0 |
| * Commits | 0 |
| * Trees | 0 |
| * Blobs | 0 |
| * Tags | 0 |
| * Inflated size | 0 B |
| * Commits | 0 B |
| * Trees | 0 B |
| * Blobs | 0 B |
| * Tags | 0 B |
| * Disk size | 0 B |
| * Commits | 0 B |
| * Trees | 0 B |
| * Blobs | 0 B |
| * Tags | 0 B |
| | |
| * Largest objects | |
| * Commits | |
| * Maximum size | 0 B |
| * Trees | |
| * Maximum size | 0 B |
| * Blobs | |
| * Maximum size | 0 B |
| * Tags | |
| * Maximum size | 0 B |
| Repository structure | Value |
| ------------------------- | ------ |
| * References | |
| * Count | 0 |
| * Branches | 0 |
| * Tags | 0 |
| * Remotes | 0 |
| * Others | 0 |
| | |
| * Reachable objects | |
| * Count | 0 |
| * Commits | 0 |
| * Trees | 0 |
| * Blobs | 0 |
| * Tags | 0 |
| * Inflated size | 0 B |
| * Commits | 0 B |
| * Trees | 0 B |
| * Blobs | 0 B |
| * Tags | 0 B |
| * Disk size | 0 B |
| * Commits | 0 B |
| * Trees | 0 B |
| * Blobs | 0 B |
| * Tags | 0 B |
| | |
| * Largest objects | |
| * Commits | |
| * Maximum size | 0 B |
| * Maximum parents | 0 |
| * Trees | |
| * Maximum size | 0 B |
| * Blobs | |
| * Maximum size | 0 B |
| * Tags | |
| * Maximum size | 0 B |
EOF
git repo structure >out 2>err &&
@@ -89,46 +90,48 @@ test_expect_success SHA1 'repository with references and objects' '
# git-rev-list(1) --disk-usage=human option printing the full
# "byte/bytes" unit string instead of just "B".
cat >expect <<-EOF &&
| Repository structure | Value |
| ------------------------ | ---------- |
| * References | |
| * Count | 4 |
| * Branches | 1 |
| * Tags | 1 |
| * Remotes | 1 |
| * Others | 1 |
| | |
| * Reachable objects | |
| * Count | 3.02 k |
| * Commits | 1.01 k |
| * Trees | 1.01 k |
| * Blobs | 1.01 k |
| * Tags | 1 |
| * Inflated size | 16.03 MiB |
| * Commits | 217.92 KiB |
| * Trees | 15.81 MiB |
| * Blobs | 11.68 KiB |
| * Tags | 132 B |
| * Disk size | $(object_type_disk_usage all true) |
| * Commits | $(object_type_disk_usage commit true) |
| * Trees | $(object_type_disk_usage tree true) |
| * Blobs | $(object_type_disk_usage blob true) |
| * Tags | $(object_type_disk_usage tag) B |
| | |
| * Largest objects | |
| * Commits | |
| * Maximum size [1] | 223 B |
| * Trees | |
| * Maximum size [2] | 32.29 KiB |
| * Blobs | |
| * Maximum size [3] | 13 B |
| * Tags | |
| * Maximum size [4] | 132 B |
| Repository structure | Value |
| ------------------------- | ---------- |
| * References | |
| * Count | 4 |
| * Branches | 1 |
| * Tags | 1 |
| * Remotes | 1 |
| * Others | 1 |
| | |
| * Reachable objects | |
| * Count | 3.02 k |
| * Commits | 1.01 k |
| * Trees | 1.01 k |
| * Blobs | 1.01 k |
| * Tags | 1 |
| * Inflated size | 16.03 MiB |
| * Commits | 217.92 KiB |
| * Trees | 15.81 MiB |
| * Blobs | 11.68 KiB |
| * Tags | 132 B |
| * Disk size | $(object_type_disk_usage all true) |
| * Commits | $(object_type_disk_usage commit true) |
| * Trees | $(object_type_disk_usage tree true) |
| * Blobs | $(object_type_disk_usage blob true) |
| * Tags | $(object_type_disk_usage tag) B |
| | |
| * Largest objects | |
| * Commits | |
| * Maximum size [1] | 223 B |
| * Maximum parents [2] | 1 |
| * Trees | |
| * Maximum size [3] | 32.29 KiB |
| * Blobs | |
| * Maximum size [4] | 13 B |
| * Tags | |
| * Maximum size [5] | 132 B |
[1] 0dc91eb18580102a3a216c8bfecedeba2b9f9b9a
[2] 60665251ab71dbd8c18d9bf2174f4ee0d58aa06c
[3] 97d808e45116bf02103490294d3d46dad7a2ac62
[4] 4dae4f5954f5e6feb3577cfb1b181daa3fd3afd2
[2] 0dc91eb18580102a3a216c8bfecedeba2b9f9b9a
[3] 60665251ab71dbd8c18d9bf2174f4ee0d58aa06c
[4] 97d808e45116bf02103490294d3d46dad7a2ac62
[5] 4dae4f5954f5e6feb3577cfb1b181daa3fd3afd2
EOF
git repo structure >out 2>err &&
@@ -171,6 +174,8 @@ test_expect_success SHA1 'keyvalue and nul format' '
objects.blobs.max_size_oid=eaeeedced46482bd4281fda5a5f05ce24854151f
objects.tags.max_size=132
objects.tags.max_size_oid=1ee0f2b16ea37d895dbe9dbd76cd2ac70446176c
objects.commits.max_parents=1
objects.commits.max_parents_oid=de3508174b5c2ace6993da67cae9be9069e2df39
EOF
git repo structure --format=keyvalue >out 2>err &&