path-walk: add 'edge_aggressive' option

Signed-off-by: Derrick Stolee <[email protected]>

Author: derrickstolee

Documentation/technical/api-path-walk.txt

@@ -65,6 +65,14 @@ better off using the revision walk API instead.
 	the revision walk so that the walk emits commits marked with the
 	`UNINTERESTING` flag.
 
+`edge_aggressive`::
+	For performance reasons, usually only the boundary commits are
+	explored to find UNINITERESTING objects. However, in the case of
+	shallow clones it can be helpful to mark all trees and blobs
+	reachable from UNINTERESTING tip commits as UNINTERESTING. This
+	matches the behavior of `--objects-edge-aggressive` in the
+	revision API.
+
 `pl`::
 	This pattern list pointer allows focusing the path-walk search to
 	a set of patterns, only emitting paths that match the given

builtin/pack-objects.c

@@ -201,6 +201,7 @@ static int keep_unreachable, unpack_unreachable, include_tag;
 static timestamp_t unpack_unreachable_expiration;
 static int pack_loose_unreachable;
 static int cruft;
+int shallow = 0;
 static timestamp_t cruft_expiration;
 static int local;
 static int have_non_local_packs;
@@ -4438,6 +4439,7 @@ static void get_object_list_path_walk(struct rev_info *revs)
 	 * base objects.
 	 */
 	info.prune_all_uninteresting = sparse;
+	info.edge_aggressive = shallow;
 
 	if (walk_objects_by_path(&info))
 		die(_("failed to pack objects via path-walk"));
@@ -4627,7 +4629,6 @@ int cmd_pack_objects(int argc,
 		     struct repository *repo UNUSED)
 {
 	int use_internal_rev_list = 0;
-	int shallow = 0;
 	int all_progress_implied = 0;
 	struct strvec rp = STRVEC_INIT;
 	int rev_list_unpacked = 0, rev_list_all = 0, rev_list_reflog = 0;

path-walk.c

@@ -280,6 +280,28 @@ int walk_objects_by_path(struct path_walk_info *info)
 	if (prepare_revision_walk(info->revs))
 		die(_("failed to setup revision walk"));
 
+	if (info->edge_aggressive) {
+		for (struct commit_list *list = info->revs->commits;
+		     list;
+		     list = list->next) {
+			struct commit *commit = list->item;
+			if (commit->object.flags & UNINTERESTING) {
+				struct tree *t = repo_get_commit_tree(info->revs->repo, commit);
+				mark_tree_uninteresting(info->revs->repo, t);
+				if (!(commit->object.flags & SHOWN))
+					commit->object.flags |= SHOWN;
+			}
+		}
+		for (size_t i = 0; i < info->revs->cmdline.nr; i++) {
+			struct object *obj = info->revs->cmdline.rev[i].item;
+			struct commit *commit = (struct commit *)obj;
+			if (obj->type != OBJ_COMMIT || !(obj->flags & UNINTERESTING))
+				continue;
+			mark_tree_uninteresting(info->revs->repo,
+						repo_get_commit_tree(info->revs->repo, commit));
+		}
+	}
+
 	info->revs->blob_objects = info->revs->tree_objects = 0;
 
 	if (info->tags) {

path-walk.h

@@ -48,6 +48,13 @@ struct path_walk_info {
 	 */
 	int prune_all_uninteresting;
 
+	/**
+	 * When 'edge_aggressive' is set, then the revision walk will use
+	 * the '--object-edge-aggressive' option to mark even more objects
+	 * as uniniteresting.
+	 */
+	int edge_aggressive;
+
 	/**
 	 * Specify a sparse-checkout definition to match our paths to. Do not
 	 * walk outside of this sparse definition. If the patterns are in

t/t5500-fetch-pack.sh

@@ -464,17 +464,6 @@ test_expect_success 'fetch in shallow repo unreachable shallow objects' '
 	)
 '
 
-# At the moment, the --path-walk option may provide more objects
-# when combined with --shallow than the --no-path-walk option.
-if test_bool_env GIT_TEST_PACK_PATH_WALK false
-then
-	EXPECTED_SHALLOW_OBJECTS=3 &&
-	export EXPECTED_SHALLOW_OBJECTS
-else
-	EXPECTED_SHALLOW_OBJECTS=1 &&
-	export EXPECTED_SHALLOW_OBJECTS
-fi
-
 test_expect_success 'fetch creating new shallow root' '
 	(
 		git clone "file://$(pwd)/." shallow10 &&
@@ -483,7 +472,7 @@ test_expect_success 'fetch creating new shallow root' '
 		git fetch --depth=1 --progress 2>actual &&
 		# This should fetch only the empty commit, no tree or
 		# blob objects
-		test_grep "remote: Total $EXPECTED_SHALLOW_OBJECTS" actual
+		test_grep "remote: Total 1" actual
 	)
 '