[PATCH v3 5/6] path-walk: support wildcard pathspecs for blob filtering

["Derrick Stolee via GitGitGadget" <gitgitgadget@gmail.com>]

From: Derrick Stolee <stolee@gmail.com>

Previously, walk_objects_by_path() silently ignored pathspecs containing
wildcards or magic by clearing them. This caused all blobs to be
downloaded regardless of the given pathspec. Wildcard pathspecs like
"d/file.*.txt" are useful for narrowing which blobs to process (e.g.,
during 'git backfill').

Support wildcard pathspecs by making two changes:

 1. Add an 'exact_pathspecs' flag to path_walk_context. When the
    pathspec has no wildcards or magic, set this flag and use the
    existing fast-path prefix matching in add_tree_entries(). When
    wildcards are present, skip that block since prefix matching
    cannot handle glob patterns.

 2. Add a match_pathspec() check in walk_path() to filter out blobs
    whose full path does not match the pathspec. This provides the
    actual blob-level filtering for wildcard pathspecs.

Signed-off-by: Derrick Stolee <stolee@gmail.com>
---
 path-walk.c         | 22 +++++++++++++---------
 t/t5620-backfill.sh |  7 +++----
 2 files changed, 16 insertions(+), 13 deletions(-)

diff --git a/path-walk.c b/path-walk.c
index 3750552978..2aa3e7d8a4 100644
--- a/path-walk.c
+++ b/path-walk.c
@@ -63,6 +63,8 @@ struct path_walk_context {
 	 */
 	struct prio_queue path_stack;
 	struct strset path_stack_pushed;
+
+	unsigned exact_pathspecs:1;
 };
 
 static int compare_by_type(const void *one, const void *two, void *cb_data)
@@ -207,7 +209,7 @@ static int add_tree_entries(struct path_walk_context *ctx,
 				 match != MATCHED)
 				continue;
 		}
-		if (ctx->revs->prune_data.nr) {
+		if (ctx->revs->prune_data.nr && ctx->exact_pathspecs) {
 			struct pathspec *pd = &ctx->revs->prune_data;
 			bool found = false;
 			int did_strip_suffix = strbuf_strip_suffix(&path, "/");
@@ -302,6 +304,13 @@ static int walk_path(struct path_walk_context *ctx,
 			return 0;
 	}
 
+	if (list->type == OBJ_BLOB &&
+	    ctx->revs->prune_data.nr &&
+	    !match_pathspec(ctx->repo->index, &ctx->revs->prune_data,
+			   path, strlen(path), 0,
+			   NULL, 0))
+		return 0;
+
 	/* Evaluate function pointer on this data, if requested. */
 	if ((list->type == OBJ_TREE && ctx->info->trees) ||
 	    (list->type == OBJ_BLOB && ctx->info->blobs) ||
@@ -510,14 +519,9 @@ int walk_objects_by_path(struct path_walk_info *info)
 		info->revs->tag_objects = 1;
 
 	if (ctx.revs->prune_data.nr) {
-		/*
-		 * Only exact prefix pathspecs are currently supported.
-		 * Clear any wildcard or magic pathspecs to avoid
-		 * incorrect prefix matching.
-		 */
-		if (ctx.revs->prune_data.has_wildcard ||
-		    ctx.revs->prune_data.magic)
-			clear_pathspec(&ctx.revs->prune_data);
+		if (!ctx.revs->prune_data.has_wildcard &&
+		    !ctx.revs->prune_data.magic)
+			ctx.exact_pathspecs = 1;
 	}
 
 	/* Insert a single list for the root tree into the paths. */
diff --git a/t/t5620-backfill.sh b/t/t5620-backfill.sh
index 52f6484ca1..c6f54ee91c 100755
--- a/t/t5620-backfill.sh
+++ b/t/t5620-backfill.sh
@@ -307,12 +307,11 @@ test_expect_success 'backfill with wildcard pathspec' '
 	git -C backfill-path rev-list --quiet --objects --missing=print HEAD >missing &&
 	test_line_count = 48 missing &&
 
-	# TODO: The wildcard pathspec should limit downloaded blobs,
-	# but currently all blobs are downloaded.
-	git -C backfill-path backfill HEAD -- "d/file.*.txt" &&
+	git -C backfill-path backfill HEAD -- "d/file.*.txt" 2>err &&
+	test_must_be_empty err &&
 
 	git -C backfill-path rev-list --quiet --objects --missing=print HEAD >missing &&
-	test_line_count = 0 missing
+	test_line_count = 40 missing
 '
 
 test_expect_success 'backfill with --all' '
-- 
gitgitgadget