backfill: work with prefix pathspecs

The previous change allowed specifying revision arguments over the 'git
backfill' command-line. This created the opportunity for pathspecs that
specify a smaller set of starting commits, but otherwise did not restrict
the blob paths that were downloaded.

Update the path-walk API to accept certain kinds of pathspecs and to reject
anything too complex. The current behavior focuses on pathspecs that match
paths exactly. This includes exact filenames, including directory names as
prefixes.

The reason for this restriction is to allow for a faster execution by
pruning the path walk to only trees that could contribute towards one of
those paths as a parent directory.

The test directory 'd/f/' (next to 'd/file*.txt') was prepared in a
previous commit to exercise the subtlety in prefix matching.

Signed-off-by: Derrick Stolee <stolee@gmail.com>

Author: derrickstolee

path-walk.c

@@ -206,6 +206,49 @@ static int add_tree_entries(struct path_walk_context *ctx,
 				 match != MATCHED)
 				continue;
 		}
+		if (ctx->revs->prune_data.nr) {
+			struct pathspec *pd = &ctx->revs->prune_data;
+			bool found = false;
+
+			for (int i = 0; i < pd->nr; i++) {
+				struct pathspec_item *item = &pd->items[i];
+
+				/*
+				 * Is this path a parent directory of
+				 * the pathspec item?
+				 */
+				if (path.len < (size_t)item->len &&
+				    !strncmp(path.buf, item->match, path.len) &&
+				    item->match[path.len - 1] == '/') {
+					found = true;
+					break;
+				}
+
+				/*
+				 * Or, is the pathspec an exact match?
+				 */
+				if (path.len == (size_t)item->len &&
+				    !strcmp(path.buf, item->match)) {
+					found = true;
+					break;
+				}
+
+				/*
+				 * Or, is the pathspec a directory prefix
+				 * match?
+				 */
+				if (path.len > (size_t)item->len &&
+				    !strncmp(path.buf, item->match, item->len) &&
+				    path.buf[item->len] == '/') {
+					found = true;
+					break;
+				}
+			}
+
+			/* Skip paths that do not match the prefix. */
+			if (!found)
+				continue;
+		}
 
 		add_path_to_list(ctx, path.buf, type, &entry.oid,
 				 !(o->flags & UNINTERESTING));
@@ -481,6 +524,17 @@ int walk_objects_by_path(struct path_walk_info *info)
 	if (info->tags)
 		info->revs->tag_objects = 1;
 
+	if (ctx.revs->prune_data.nr) {
+		/*
+		 * Check that all pathspecs are prefixes, or remove
+		 * them from consideration, with a warning.
+		 */
+		struct pathspec *pd = &ctx.revs->prune_data;
+
+		if (pd->has_wildcard || pd->magic)
+			return error(_("provided pathspec is too generic"));
+	}
+
 	/* Insert a single list for the root tree into the paths. */
 	CALLOC_ARRAY(root_tree_list, 1);
 	root_tree_list->type = OBJ_TREE;

t/t5620-backfill.sh

@@ -263,7 +263,7 @@ test_expect_success 'backfill with revisions over stdin' '
 	test_line_count = 18 missing
 '
 
-test_expect_success 'backfill with pathspec' '
+test_expect_success 'backfill with prefix pathspec' '
 	test_when_finished rm -rf backfill-path &&
 	git clone --bare --filter=blob:none		        \
 		--single-branch --branch=main   		\
@@ -273,13 +273,28 @@ test_expect_success 'backfill with pathspec' '
 	git -C backfill-path rev-list --quiet --objects --missing=print HEAD >missing &&
 	test_line_count = 48 missing &&
 
-	# TODO: We want this pathspec to be respected in limiting
-	# the downloaded files.
-	git -C backfill-path backfill HEAD -- d/f &&
+	git -C backfill-path backfill HEAD -- d/f 2>err &&
+	test_must_be_empty err &&
 
-	# TODO: We only want specific objects downloaded.
 	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 multiple pathspecs' '
+	test_when_finished rm -rf backfill-path &&
+	git clone --bare --filter=blob:none		        \
+		--single-branch --branch=main   		\
+		"file://$(pwd)/srv.bare" backfill-path &&
+
+	# No blobs yet
+	git -C backfill-path rev-list --quiet --objects --missing=print HEAD >missing &&
+	test_line_count = 48 missing &&
+
+	git -C backfill-path backfill HEAD -- d/f a 2>err &&
+	test_must_be_empty err &&
+
+	git -C backfill-path rev-list --quiet --objects --missing=print HEAD >missing &&
+	test_line_count = 16 missing
 '
 
 test_expect_success 'backfill with --all' '