ls-files: add pathspec matching for submodules

Pathspecs can be a bit tricky when trying to apply them to submodules.
The main challenge is that the pathspecs will be with respect to the
superproject and not with respect to paths in the submodule.  The
approach this patch takes is to pass in the identical pathspec from the
superproject to the submodule in addition to the submodule-prefix, which
is the path from the root of the superproject to the submodule, and then
we can compare an entry in the submodule prepended with the
submodule-prefix to the pathspec in order to determine if there is a
match.

This patch also permits the pathspec logic to perform a prefix match against
submodules since a pathspec could refer to a file inside of a submodule.
Due to limitations in the wildmatch logic, a prefix match is only done
literally.  If any wildcard character is encountered we'll simply punt
and produce a false positive match.  More accurate matching will be done
once inside the submodule.  This is due to the superproject not knowing
what files could exist in the submodule.

Signed-off-by: Brandon Williams <bmwill@google.com>
Reviewed-by: Stefan Beller <sbeller@google.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

1 files changed, 21 insertions, 6 deletions

diff --git a/builtin/ls-files.c b/builtin/ls-files.c
index b6144a56d..0f2591434 100644
--- a/builtin/ls-files.c
+++ b/builtin/ls-files.c
@@ -195,6 +195,7 @@ static void show_gitlink(const struct cache_entry *ce)
 {
 	struct child_process cp = CHILD_PROCESS_INIT;
 	int status;
+	int i;
 
 	argv_array_pushf(&cp.args, "--super-prefix=%s%s/",
 			 super_prefix ? super_prefix : "",
@@ -205,6 +206,15 @@ static void show_gitlink(const struct cache_entry *ce)
 	/* add supported options */
 	argv_array_pushv(&cp.args, submodules_options.argv);
 
+	/*
+	 * Pass in the original pathspec args.  The submodule will be
+	 * responsible for prepending the 'submodule_prefix' prior to comparing
+	 * against the pathspec for matches.
+	 */
+	argv_array_push(&cp.args, "--");
+	for (i = 0; i < pathspec.nr; i++)
+		argv_array_push(&cp.args, pathspec.items[i].original);
+
 	cp.git_cmd = 1;
 	cp.dir = ce->name;
 	status = run_command(&cp);
@@ -223,7 +233,8 @@ static void show_ce_entry(const char *tag, const struct cache_entry *ce)
 	if (len >= ce_namelen(ce))
 		die("git ls-files: internal error - cache entry not superset of prefix");
 
-	if (recurse_submodules && S_ISGITLINK(ce->ce_mode)) {
+	if (recurse_submodules && S_ISGITLINK(ce->ce_mode) &&
+	    submodule_path_match(&pathspec, name.buf, ps_matched)) {
 		show_gitlink(ce);
 	} else if (match_pathspec(&pathspec, name.buf, name.len,
 				  len, ps_matched,
@@ -602,16 +613,20 @@ int cmd_ls_files(int argc, const char **argv, const char *cmd_prefix)
 		die("ls-files --recurse-submodules does not support "
 		    "--error-unmatch");
 
-	if (recurse_submodules && argc)
-		die("ls-files --recurse-submodules does not support pathspec");
-
 	parse_pathspec(&pathspec, 0,
 		       PATHSPEC_PREFER_CWD |
 		       PATHSPEC_STRIP_SUBMODULE_SLASH_CHEAP,
 		       prefix, argv);
 
-	/* Find common prefix for all pathspec's */
-	max_prefix = common_prefix(&pathspec);
+	/*
+	 * Find common prefix for all pathspec's
+	 * This is used as a performance optimization which unfortunately cannot
+	 * be done when recursing into submodules
+	 */
+	if (recurse_submodules)
+		max_prefix = NULL;
+	else
+		max_prefix = common_prefix(&pathspec);
 	max_prefix_len = max_prefix ? strlen(max_prefix) : 0;
 
 	/* Treat unmatching pathspec elements as errors */