path-walk: add pl_sparse_trees to control tree pruning

The path-walk API prunes trees and blobs when a sparse-checkout pattern
list is provided, which is the correct behavior for 'git backfill
--sparse' since it only needs to fill in objects at paths within the
sparse cone.

However, a future change will use the path-walk API with a sparse:<oid>
filter that restricts only blobs while retaining all reachable trees.
To support both behaviors, add a 'pl_sparse_trees' flag to
path_walk_info. When set (as in 'git backfill --sparse' and the
--stdin-pl test helper mode), the sparse patterns prune both trees and
blobs. When unset, only blobs are filtered and all trees are walked and
reported.

Additionally, move the SEEN flag assignment in add_tree_entries() to
after the sparse pattern and pathspec checks. Previously, SEEN was set
immediately upon discovering an object, before checking whether its path
matched the sparse patterns. When the same object ID appeared at
multiple paths (e.g. sibling directories with identical contents), the
first path to be visited would mark the object as SEEN. If that path was
outside the sparse cone, the object would be skipped there but also
never discovered at its in-cone path.

By deferring the SEEN flag until after the checks pass, objects that are
skipped due to sparse filtering remain discoverable at other paths where
they may be in scope.

Signed-off-by: Derrick Stolee <stolee@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

builtin/backfill.c

@@ -109,6 +109,7 @@ static int do_backfill(struct backfill_context *ctx)
 
 	if (ctx->sparse) {
 		CALLOC_ARRAY(info.pl, 1);
+		info.pl_sparse_trees = 1;
 		if (get_sparse_checkout_patterns(info.pl)) {
 			path_walk_info_clear(&info);
 			return error(_("problem loading sparse-checkout"));

path-walk.c

@@ -183,7 +183,6 @@ static int add_tree_entries(struct path_walk_context *ctx,
 		/* Skip this object if already seen. */
 		if (o->flags & SEEN)
 			continue;
-		o->flags |= SEEN;
 
 		strbuf_setlen(&path, base_len);
 		strbuf_add(&path, entry.path, entry.pathlen);
@@ -204,7 +203,8 @@ static int add_tree_entries(struct path_walk_context *ctx,
 							  ctx->repo->index);
 
 			if (ctx->info->pl->use_cone_patterns &&
-			    match == NOT_MATCHED)
+			    match == NOT_MATCHED &&
+			    (type == OBJ_BLOB || ctx->info->pl_sparse_trees))
 				continue;
 			else if (!ctx->info->pl->use_cone_patterns &&
 				 type == OBJ_BLOB &&
@@ -239,6 +239,7 @@ static int add_tree_entries(struct path_walk_context *ctx,
 				continue;
 		}
 
+		o->flags |= SEEN;
 		add_path_to_list(ctx, path.buf, type, &entry.oid,
 				 !(o->flags & UNINTERESTING));
 

path-walk.h

@@ -76,8 +76,14 @@ struct path_walk_info {
 	 * of the cone. If not in cone mode, then all tree paths will be
 	 * explored but the path_fn will only be called when the path matches
 	 * the sparse-checkout patterns.
+	 *
+	 * When 'pl_sparse_trees' is zero, the sparse patterns only restrict
+	 * blobs and all trees are included in the walk output. This matches
+	 * the behavior of the sparse:oid object filter. When nonzero, trees
+	 * are also pruned by the sparse patterns (as used by backfill).
 	 */
 	struct pattern_list *pl;
+	int pl_sparse_trees;
 };
 
 #define PATH_WALK_INFO_INIT {   \

t/helper/test-path-walk.c

@@ -68,7 +68,7 @@ static int emit_block(const char *path, struct oid_array *oids,
 
 int cmd__path_walk(int argc, const char **argv)
 {
-	int res, stdin_pl = 0;
+	int res, stdin_pl = 0, pl_sparse_trees = -1;
 	struct rev_info revs = REV_INFO_INIT;
 	struct path_walk_info info = PATH_WALK_INFO_INIT;
 	struct path_walk_test_data data = { 0 };
@@ -89,6 +89,8 @@ int cmd__path_walk(int argc, const char **argv)
 			 N_("toggle aggressive edge walk")),
 		OPT_BOOL(0, "stdin-pl", &stdin_pl,
 			 N_("read a pattern list over stdin")),
+		OPT_BOOL(0, "pl-sparse-trees", &pl_sparse_trees,
+			 N_("toggle pruning of trees by sparse patterns")),
 		OPT_PARSE_LIST_OBJECTS_FILTER(&filter_options),
 		OPT_END(),
 	};
@@ -116,6 +118,8 @@ int cmd__path_walk(int argc, const char **argv)
 	if (stdin_pl) {
 		struct strbuf in = STRBUF_INIT;
 		CALLOC_ARRAY(info.pl, 1);
+		info.pl_sparse_trees = (pl_sparse_trees >= 0) ?
+			pl_sparse_trees : 1;
 
 		info.pl->use_cone_patterns = 1;
 

t/t6601-path-walk.sh

@@ -206,6 +206,43 @@ test_expect_success 'base & topic, sparse' '
 	test_cmp_sorted expect out
 '
 
+test_expect_success 'base & topic, sparse, no tree pruning' '
+	cat >patterns <<-EOF &&
+	/*
+	!/*/
+	/left/
+	EOF
+
+	test-tool path-walk --stdin-pl --no-pl-sparse-trees \
+		-- base topic <patterns >out &&
+
+	cat >expect <<-EOF &&
+	0:commit::$(git rev-parse topic)
+	0:commit::$(git rev-parse base)
+	0:commit::$(git rev-parse base~1)
+	0:commit::$(git rev-parse base~2)
+	1:tree::$(git rev-parse topic^{tree})
+	1:tree::$(git rev-parse base^{tree})
+	1:tree::$(git rev-parse base~1^{tree})
+	1:tree::$(git rev-parse base~2^{tree})
+	2:blob:a:$(git rev-parse base~2:a)
+	3:tree:a/:$(git rev-parse base:a)
+	4:tree:left/:$(git rev-parse base:left)
+	4:tree:left/:$(git rev-parse base~2:left)
+	5:blob:left/b:$(git rev-parse base~2:left/b)
+	5:blob:left/b:$(git rev-parse base:left/b)
+	6:tree:right/:$(git rev-parse topic:right)
+	6:tree:right/:$(git rev-parse base~1:right)
+	6:tree:right/:$(git rev-parse base~2:right)
+	blobs:3
+	commits:4
+	tags:0
+	trees:10
+	EOF
+
+	test_cmp_sorted expect out
+'
+
 test_expect_success 'topic only' '
 	test-tool path-walk -- topic >out &&