[PATCH v4 6/6] clean: teach clean -d to skip dirs containing ignored files

[Samuel Lijin <sxlijin@xxxxxxxxx>]

There is an implicit assumption that a directory containing only
untracked and ignored files should itself be considered untracked. This
makes sense in use cases where we're asking if a directory should be
added to the git database, but not when we're asking if a directory can
be safely removed from the working tree; as a result, clean -d would
assume that an "untracked" directory containing ignored files could be
deleted.

To get around this, we teach clean -d to collect ignored files and skip
over so-called "untracked" directories if they contain any ignored
files (while still removing the untracked contents of such dirs).

This also fixes the known breakage in t7300 since clean -d now skips
untracked directories containing ignored files.

Signed-off-by: Samuel Lijin <sxlijin@xxxxxxxxx>
---
 builtin/clean.c  | 38 +++++++++++++++++++++++++++++++++++++-
 t/t7300-clean.sh |  2 +-
 2 files changed, 38 insertions(+), 2 deletions(-)

diff --git a/builtin/clean.c b/builtin/clean.c
index d861f836a..0d490d76e 100644
--- a/builtin/clean.c
+++ b/builtin/clean.c
@@ -859,7 +859,7 @@ static void interactive_main_loop(void)
 
 int cmd_clean(int argc, const char **argv, const char *prefix)
 {
-	int i, res;
+	int i, j, res;
 	int dry_run = 0, remove_directories = 0, quiet = 0, ignored = 0;
 	int ignored_only = 0, config_set = 0, errors = 0, gone = 1;
 	int rm_flags = REMOVE_DIR_KEEP_NESTED_GIT;
@@ -911,6 +911,9 @@ int cmd_clean(int argc, const char **argv, const char *prefix)
 				  " refusing to clean"));
 	}
 
+	if (remove_directories)
+		dir.flags |= DIR_SHOW_IGNORED_TOO | DIR_KEEP_UNTRACKED_CONTENTS;
+
 	if (force > 1)
 		rm_flags = 0;
 
@@ -932,12 +935,39 @@ int cmd_clean(int argc, const char **argv, const char *prefix)
 
 	fill_directory(&dir, &pathspec);
 
+	for (j = i = 0; i < dir.nr;) {
+		for (;
+		     j < dir.ignored_nr &&
+		       0 <= cmp_dir_entry(&dir.entries[i], &dir.ignored[j]);
+		     j++);
+
+		if ((j < dir.ignored_nr) &&
+				check_dir_entry_contains(dir.entries[i], dir.ignored[j])) {
+			/* skip any dir.entries which contains a dir.ignored */
+			free(dir.entries[i]);
+			dir.entries[i++] = NULL;
+		} else {
+			/* prune the contents of a dir.entries which will be removed */
+			struct dir_entry *ent = dir.entries[i++];
+			for (;
+			     i < dir.nr &&
+			       check_dir_entry_contains(ent, dir.entries[i]);
+			     i++) {
+				free(dir.entries[i]);
+				dir.entries[i] = NULL;
+			}
+		}
+	}
+
 	for (i = 0; i < dir.nr; i++) {
 		struct dir_entry *ent = dir.entries[i];
 		int matches = 0;
 		struct stat st;
 		const char *rel;
 
+		if (!ent)
+			continue;
+
 		if (!cache_name_is_other(ent->name, ent->len))
 			continue;
 
@@ -958,6 +988,12 @@ int cmd_clean(int argc, const char **argv, const char *prefix)
 		string_list_append(&del_list, rel);
 	}
 
+	for (i = 0; i < dir.nr; i++)
+		free(dir.entries[i]);
+
+	for (i = 0; i < dir.ignored_nr; i++)
+		free(dir.ignored[i]);
+
 	if (interactive && del_list.nr > 0)
 		interactive_main_loop();
 
diff --git a/t/t7300-clean.sh b/t/t7300-clean.sh
index 3a2d709c2..7b36954d6 100755
--- a/t/t7300-clean.sh
+++ b/t/t7300-clean.sh
@@ -653,7 +653,7 @@ test_expect_success 'git clean -d respects pathspecs (pathspec is prefix of dir)
 	test_path_is_dir foobar
 '
 
-test_expect_failure 'git clean -d skips untracked dirs containing ignored files' '
+test_expect_success 'git clean -d skips untracked dirs containing ignored files' '
 	echo /foo/bar >.gitignore &&
 	echo ignoreme >>.gitignore &&
 	rm -rf foo &&
-- 
2.13.0