builtin/repo: find tree with most entries

The size of a tree object usually corresponds with the number of entries it has. While iterating through objects in the repository for git-repo-structure, identify the tree with the most entries and display it in the output. Signed-off-by: Justin Tobler <jltobler@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>

Justin Tobler committed Mar 2, 2026 at 15:45 UTC 42e69594113d647f53d65440f2ede554570b9f40
2 files changed +34 -4
builtin/repo.c
+25
@@ -16,6 +16,8 @@
16 #include "strbuf.h"
17 #include "string-list.h"
18 #include "shallow.h"
19 +#include "tree.h"
20 +#include "tree-walk.h"
21 #include "utf8.h"
22
23 static const char *const repo_usage[] = {
@@ -211,6 +213,7 @@ struct largest_objects {
213 struct object_data blob_size;
214
215 struct object_data parent_count;
216 + struct object_data tree_entries;
217 };
218
219 struct ref_stats {
@@ -458,6 +461,10 @@ static void stats_table_setup_structure(struct stats_table *table,
461 &objects->largest.tree_size.oid,
462 objects->largest.tree_size.value,
463 " * %s", _("Maximum size"));
464 + stats_table_object_count_addf(table,
465 + &objects->largest.tree_entries.oid,
466 + objects->largest.tree_entries.value,
467 + " * %s", _("Maximum entries"));
468 stats_table_addf(table, " * %s", _("Blobs"));
469 stats_table_object_size_addf(table,
470 &objects->largest.blob_size.oid,
@@ -625,6 +632,8 @@ static void structure_keyvalue_print(struct repo_structure *stats,
632
633 print_object_data("objects.commits.max_parents", key_delim,
634 &stats->objects.largest.parent_count, value_delim);
635 + print_object_data("objects.trees.max_entries", key_delim,
636 + &stats->objects.largest.tree_entries, value_delim);
637
638 fflush(stdout);
639 }
@@ -703,6 +712,20 @@ static void check_largest(struct object_data *data, struct object_id *oid,
712 }
713 }
714
715 +static size_t count_tree_entries(struct object *obj)
716 +{
717 + struct tree *t = object_as_type(obj, OBJ_TREE, 0);
718 + struct name_entry entry;
719 + struct tree_desc desc;
720 + size_t count = 0;
721 +
722 + init_tree_desc(&desc, &t->object.oid, t->buffer, t->size);
723 + while (tree_entry(&desc, &entry))
724 + count++;
725 +
726 + return count;
727 +}
728 +
729 static int count_objects(const char *path UNUSED, struct oid_array *oids,
730 enum object_type type, void *cb_data)
731 {
@@ -755,6 +778,8 @@ static int count_objects(const char *path UNUSED, struct oid_array *oids,
778 stats->disk_sizes.trees += disk;
779 check_largest(&stats->largest.tree_size, &oids->oid[i],
780 inflated);
781 + check_largest(&stats->largest.tree_entries, &oids->oid[i],
782 + count_tree_entries(obj));
783 break;
784 case OBJ_BLOB:
785 stats->type_counts.blobs++;
t/t1901-repo-structure.sh
+9 -4
@@ -59,6 +59,7 @@ test_expect_success 'empty repository' '
59 | * Maximum parents | 0 |
60 | * Trees | |
61 | * Maximum size | 0 B |
62 + | * Maximum entries | 0 |
63 | * Blobs | |
64 | * Maximum size | 0 B |
65 | * Tags | |
@@ -122,16 +123,18 @@ test_expect_success SHA1 'repository with references and objects' '
123 | * Maximum parents [2] | 1 |
124 | * Trees | |
125 | * Maximum size [3] | 32.29 KiB |
126 + | * Maximum entries [4] | 1.01 k |
127 | * Blobs | |
126 - | * Maximum size [4] | 13 B |
128 + | * Maximum size [5] | 13 B |
129 | * Tags | |
128 - | * Maximum size [5] | 132 B |
130 + | * Maximum size [6] | 132 B |
131
132 [1] 0dc91eb18580102a3a216c8bfecedeba2b9f9b9a
133 [2] 0dc91eb18580102a3a216c8bfecedeba2b9f9b9a
134 [3] 60665251ab71dbd8c18d9bf2174f4ee0d58aa06c
133 - [4] 97d808e45116bf02103490294d3d46dad7a2ac62
134 - [5] 4dae4f5954f5e6feb3577cfb1b181daa3fd3afd2
135 + [4] 60665251ab71dbd8c18d9bf2174f4ee0d58aa06c
136 + [5] 97d808e45116bf02103490294d3d46dad7a2ac62
137 + [6] 4dae4f5954f5e6feb3577cfb1b181daa3fd3afd2
138 EOF
139
140 git repo structure >out 2>err &&
@@ -176,6 +179,8 @@ test_expect_success SHA1 'keyvalue and nul format' '
179 objects.tags.max_size_oid=1ee0f2b16ea37d895dbe9dbd76cd2ac70446176c
180 objects.commits.max_parents=1
181 objects.commits.max_parents_oid=de3508174b5c2ace6993da67cae9be9069e2df39
182 + objects.trees.max_entries=42
183 + objects.trees.max_entries_oid=09931deea9d81ec21300d3e13c74412f32eacec5
184 EOF
185
186 git repo structure --format=keyvalue >out 2>err &&