builtin/repo: collect largest inflated objects

The "structure" output for git-repo(1) shows the total inflated and disk
sizes of reachable objects in the repository, but doesn't show the size
of the largest individual objects. Since an individual object may be a
large contributor to the overall repository size, it is useful for users
to know the maximum size of individual objects.

While interating across objects, record the size and OID of the largest
objects encountered for each object type to provide as output. Note that
the default "table" output format only displays size information and not
the corresponding OID. In a subsequent commit, the table format is
updated to add table annotations that mention the OID.

Signed-off-by: Justin Tobler <jltobler@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

3 files changed, 92 insertions, 0 deletions

diff --git a/Documentation/git-repo.adoc b/Documentation/git-repo.adoc
index 7d70270dfa..e812e59158 100644
--- a/Documentation/git-repo.adoc
+++ b/Documentation/git-repo.adoc
@@ -52,6 +52,7 @@ supported:
 * Reachable object counts categorized by type
 * Total inflated size of reachable objects by type
 * Total disk size of reachable objects by type
+* Largest reachable objects in the repository by type
 +
 The output format can be chosen through the flag `--format`. Three formats are
 supported:
diff --git a/builtin/repo.c b/builtin/repo.c
index 782194cf4c..59d5cb2551 100644
--- a/builtin/repo.c
+++ b/builtin/repo.c
@@ -2,6 +2,7 @@
 
 #include "builtin.h"
 #include "environment.h"
+#include "hash.h"
 #include "hex.h"
 #include "odb.h"
 #include "parse-options.h"
@@ -197,6 +198,18 @@ static int cmd_repo_info(int argc, const char **argv, const char *prefix,
 		return print_fields(argc, argv, repo, format);
 }
 
+struct object_data {
+	struct object_id oid;
+	size_t value;
+};
+
+struct largest_objects {
+	struct object_data tag_size;
+	struct object_data commit_size;
+	struct object_data tree_size;
+	struct object_data blob_size;
+};
+
 struct ref_stats {
 	size_t branches;
 	size_t remotes;
@@ -215,6 +228,7 @@ struct object_stats {
 	struct object_values type_counts;
 	struct object_values inflated_sizes;
 	struct object_values disk_sizes;
+	struct largest_objects largest;
 };
 
 struct repo_structure {
@@ -371,6 +385,21 @@ static void stats_table_setup_structure(struct stats_table *table,
 			      "    * %s", _("Blobs"));
 	stats_table_size_addf(table, objects->disk_sizes.tags,
 			      "    * %s", _("Tags"));
+
+	stats_table_addf(table, "");
+	stats_table_addf(table, "* %s", _("Largest objects"));
+	stats_table_addf(table, "  * %s", _("Commits"));
+	stats_table_size_addf(table, objects->largest.commit_size.value,
+			      "    * %s", _("Maximum size"));
+	stats_table_addf(table, "  * %s", _("Trees"));
+	stats_table_size_addf(table, objects->largest.tree_size.value,
+			      "    * %s", _("Maximum size"));
+	stats_table_addf(table, "  * %s", _("Blobs"));
+	stats_table_size_addf(table, objects->largest.blob_size.value,
+			      "    * %s", _("Maximum size"));
+	stats_table_addf(table, "  * %s", _("Tags"));
+	stats_table_size_addf(table, objects->largest.tag_size.value,
+			      "    * %s", _("Maximum size"));
 }
 
 static void stats_table_print_structure(const struct stats_table *table)
@@ -453,6 +482,14 @@ static inline void print_keyvalue(const char *key, char key_delim, size_t value,
 	       value_delim);
 }
 
+static void print_object_data(const char *key, char key_delim,
+			      struct object_data *data, char value_delim)
+{
+	print_keyvalue(key, key_delim, data->value, value_delim);
+	printf("%s_oid%c%s%c", key, key_delim, oid_to_hex(&data->oid),
+	       value_delim);
+}
+
 static void structure_keyvalue_print(struct repo_structure *stats,
 				     char key_delim, char value_delim)
 {
@@ -492,6 +529,15 @@ static void structure_keyvalue_print(struct repo_structure *stats,
 	print_keyvalue("objects.tags.disk_size", key_delim,
 		       stats->objects.disk_sizes.tags, value_delim);
 
+	print_object_data("objects.commits.max_size", key_delim,
+			  &stats->objects.largest.commit_size, value_delim);
+	print_object_data("objects.trees.max_size", key_delim,
+			  &stats->objects.largest.tree_size, value_delim);
+	print_object_data("objects.blobs.max_size", key_delim,
+			  &stats->objects.largest.blob_size, value_delim);
+	print_object_data("objects.tags.max_size", key_delim,
+			  &stats->objects.largest.tag_size, value_delim);
+
 	fflush(stdout);
 }
 
@@ -560,6 +606,15 @@ struct count_objects_data {
 	struct progress *progress;
 };
 
+static void check_largest(struct object_data *data, struct object_id *oid,
+			  size_t value)
+{
+	if (value > data->value || is_null_oid(&data->oid)) {
+		oidcpy(&data->oid, oid);
+		data->value = value;
+	}
+}
+
 static int count_objects(const char *path UNUSED, struct oid_array *oids,
 			 enum object_type type, void *cb_data)
 {
@@ -585,21 +640,29 @@ static int count_objects(const char *path UNUSED, struct oid_array *oids,
 			stats->type_counts.tags++;
 			stats->inflated_sizes.tags += inflated;
 			stats->disk_sizes.tags += disk;
+			check_largest(&stats->largest.tag_size, &oids->oid[i],
+				      inflated);
 			break;
 		case OBJ_COMMIT:
 			stats->type_counts.commits++;
 			stats->inflated_sizes.commits += inflated;
 			stats->disk_sizes.commits += disk;
+			check_largest(&stats->largest.commit_size, &oids->oid[i],
+				      inflated);
 			break;
 		case OBJ_TREE:
 			stats->type_counts.trees++;
 			stats->inflated_sizes.trees += inflated;
 			stats->disk_sizes.trees += disk;
+			check_largest(&stats->largest.tree_size, &oids->oid[i],
+				      inflated);
 			break;
 		case OBJ_BLOB:
 			stats->type_counts.blobs++;
 			stats->inflated_sizes.blobs += inflated;
 			stats->disk_sizes.blobs += disk;
+			check_largest(&stats->largest.blob_size, &oids->oid[i],
+				      inflated);
 			break;
 		default:
 			BUG("invalid object type");
diff --git a/t/t1901-repo-structure.sh b/t/t1901-repo-structure.sh
index 17ff164b05..1999f325d0 100755
--- a/t/t1901-repo-structure.sh
+++ b/t/t1901-repo-structure.sh
@@ -52,6 +52,16 @@ test_expect_success 'empty repository' '
 		|     * 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 |
 		EOF
 
 		git repo structure >out 2>err &&
@@ -104,6 +114,16 @@ test_expect_success SHA1 'repository with references and objects' '
 		|     * 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   |    223 B   |
+		|   * Trees            |            |
+		|     * Maximum size   |  32.29 KiB |
+		|   * Blobs            |            |
+		|     * Maximum size   |     13 B   |
+		|   * Tags             |            |
+		|     * Maximum size   |    132 B   |
 		EOF
 
 		git repo structure >out 2>err &&
@@ -138,6 +158,14 @@ test_expect_success SHA1 'keyvalue and nul format' '
 		objects.trees.disk_size=$(object_type_disk_usage tree)
 		objects.blobs.disk_size=$(object_type_disk_usage blob)
 		objects.tags.disk_size=$(object_type_disk_usage tag)
+		objects.commits.max_size=221
+		objects.commits.max_size_oid=de3508174b5c2ace6993da67cae9be9069e2df39
+		objects.trees.max_size=1335
+		objects.trees.max_size_oid=09931deea9d81ec21300d3e13c74412f32eacec5
+		objects.blobs.max_size=11
+		objects.blobs.max_size_oid=eaeeedced46482bd4281fda5a5f05ce24854151f
+		objects.tags.max_size=132
+		objects.tags.max_size_oid=1ee0f2b16ea37d895dbe9dbd76cd2ac70446176c
 		EOF
 
 		git repo structure --format=keyvalue >out 2>err &&