odb/source: introduce generic object counting

Introduce generic object counting on the object database source level
with a new backend-specific callback function.

Signed-off-by: Patrick Steinhardt <ps@pks.im>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

4 files changed, 60 insertions, 2 deletions

diff --git a/odb/source-files.c b/odb/source-files.c
index 14cb9adeca..c08d8993e3 100644
--- a/odb/source-files.c
+++ b/odb/source-files.c
@@ -93,6 +93,35 @@ static int odb_source_files_for_each_object(struct odb_source *source,
 	return 0;
 }
 
+static int odb_source_files_count_objects(struct odb_source *source,
+					  enum odb_count_objects_flags flags,
+					  unsigned long *out)
+{
+	struct odb_source_files *files = odb_source_files_downcast(source);
+	unsigned long count;
+	int ret;
+
+	ret = packfile_store_count_objects(files->packed, flags, &count);
+	if (ret < 0)
+		goto out;
+
+	if (!(flags & ODB_COUNT_OBJECTS_APPROXIMATE)) {
+		unsigned long loose_count;
+
+		ret = odb_source_loose_count_objects(source, flags, &loose_count);
+		if (ret < 0)
+			goto out;
+
+		count += loose_count;
+	}
+
+	*out = count;
+	ret = 0;
+
+out:
+	return ret;
+}
+
 static int odb_source_files_freshen_object(struct odb_source *source,
 					   const struct object_id *oid)
 {
@@ -220,6 +249,7 @@ struct odb_source_files *odb_source_files_new(struct object_database *odb,
 	files->base.read_object_info = odb_source_files_read_object_info;
 	files->base.read_object_stream = odb_source_files_read_object_stream;
 	files->base.for_each_object = odb_source_files_for_each_object;
+	files->base.count_objects = odb_source_files_count_objects;
 	files->base.freshen_object = odb_source_files_freshen_object;
 	files->base.write_object = odb_source_files_write_object;
 	files->base.write_object_stream = odb_source_files_write_object_stream;
diff --git a/odb/source.h b/odb/source.h
index a1fd9dd920..96c906e7a1 100644
--- a/odb/source.h
+++ b/odb/source.h
@@ -143,6 +143,21 @@ struct odb_source {
 			       unsigned flags);
 
 	/*
+	 * This callback is expected to count objects in the given object
+	 * database source. The callback function does not have to guarantee
+	 * that only unique objects are counted. The result shall be assigned
+	 * to the `out` pointer.
+	 *
+	 * Accepts `enum odb_count_objects_flag` flags to alter the behaviour.
+	 *
+	 * The callback is expected to return 0 on success, or a negative error
+	 * code otherwise.
+	 */
+	int (*count_objects)(struct odb_source *source,
+			     enum odb_count_objects_flags flags,
+			     unsigned long *out);
+
+	/*
 	 * This callback is expected to freshen the given object so that its
 	 * last access time is set to the current time. This is used to ensure
 	 * that objects that are recent will not get garbage collected even if
@@ -334,6 +349,18 @@ static inline int odb_source_for_each_object(struct odb_source *source,
 }
 
 /*
+ * Count the number of objects in the given object database source.
+ *
+ * Returns 0 on success, a negative error code otherwise.
+ */
+static inline int odb_source_count_objects(struct odb_source *source,
+					   enum odb_count_objects_flags flags,
+					   unsigned long *out)
+{
+	return source->count_objects(source, flags, out);
+}
+
+/*
  * Freshen an object in the object database by updating its timestamp.
  * Returns 1 in case the object has been freshened, 0 in case the object does
  * not exist.
diff --git a/packfile.c b/packfile.c
index 1ee5dd3da3..8ee462303a 100644
--- a/packfile.c
+++ b/packfile.c
@@ -1102,6 +1102,7 @@ struct packfile_list_entry *packfile_store_get_packs(struct packfile_store *stor
 }
 
 int packfile_store_count_objects(struct packfile_store *store,
+				 enum odb_count_objects_flags flags UNUSED,
 				 unsigned long *out)
 {
 	struct packfile_list_entry *e;
@@ -1146,10 +1147,9 @@ unsigned long repo_approximate_object_count(struct repository *r)
 
 		odb_prepare_alternates(r->objects);
 		for (source = r->objects->sources; source; source = source->next) {
-			struct odb_source_files *files = odb_source_files_downcast(source);
 			unsigned long c;
 
-			if (!packfile_store_count_objects(files->packed, &c))
+			if (!odb_source_count_objects(source, ODB_COUNT_OBJECTS_APPROXIMATE, &c))
 				count += c;
 		}
 
diff --git a/packfile.h b/packfile.h
index 1da8c729cb..74b6bc58c5 100644
--- a/packfile.h
+++ b/packfile.h
@@ -275,6 +275,7 @@ enum kept_pack_type {
  * Return 0 on success, a negative error code otherwise.
  */
 int packfile_store_count_objects(struct packfile_store *store,
+				 enum odb_count_objects_flags flags,
 				 unsigned long *out);
 
 /*