Merge branch 'en/clean-cleanups'

gitster · gitster · commit 53674699c0b4 · 2020-06-25T12:27:45.000-07:00
Code clean-up of "git clean" resulted in a fix of recent
performance regression.

* en/clean-cleanups:
  clean: optimize and document cases where we recurse into subdirectories
  clean: consolidate handling of ignored parameters
  dir, clean: avoid disallowed behavior
  dir: fix a few confusing comments
diff --git a/builtin/clean.c b/builtin/clean.c
@@ -924,12 +924,6 @@ int cmd_clean(int argc, const char **argv, const char *prefix)
 			     0);
 
 	memset(&dir, 0, sizeof(dir));
-	if (ignored_only)
-		dir.flags |= DIR_SHOW_IGNORED;
-
-	if (ignored && ignored_only)
-		die(_("-x and -X cannot be used together"));
-
 	if (!interactive && !dry_run && !force) {
 		if (config_set)
 			die(_("clean.requireForce set to true and neither -i, -n, nor -f given; "
@@ -946,6 +940,13 @@ int cmd_clean(int argc, const char **argv, const char *prefix)
 
 	dir.flags |= DIR_SHOW_OTHER_DIRECTORIES;
 
+	if (ignored && ignored_only)
+		die(_("-x and -X cannot be used together"));
+	if (!ignored)
+		setup_standard_excludes(&dir);
+	if (ignored_only)
+		dir.flags |= DIR_SHOW_IGNORED;
+
 	if (argc) {
 		/*
 		 * Remaining args implies pathspecs specified, and we should
@@ -954,15 +955,41 @@ int cmd_clean(int argc, const char **argv, const char *prefix)
 		remove_directories = 1;
 	}
 
-	if (remove_directories)
-		dir.flags |= DIR_SHOW_IGNORED_TOO | DIR_KEEP_UNTRACKED_CONTENTS;
+	if (remove_directories && !ignored_only) {
+		/*
+		 * We need to know about ignored files too:
+		 *
+		 * If (ignored), then we will delete ignored files as well.
+		 *
+		 * If (!ignored), then even though we not are doing
+		 * anything with ignored files, we need to know about them
+		 * so that we can avoid deleting a directory of untracked
+		 * files that also contains an ignored file within it.
+		 *
+		 * For the (!ignored) case, since we only need to avoid
+		 * deleting ignored files, we can set
+		 * DIR_SHOW_IGNORED_TOO_MODE_MATCHING in order to avoid
+		 * recursing into a directory which is itself ignored.
+		 */
+		dir.flags |= DIR_SHOW_IGNORED_TOO;
+		if (!ignored)
+			dir.flags |= DIR_SHOW_IGNORED_TOO_MODE_MATCHING;
+
+		/*
+		 * Let the fill_directory() machinery know that we aren't
+		 * just recursing to collect the ignored files; we want all
+		 * the untracked ones so that we can delete them.  (Note:
+		 * we could also set DIR_KEEP_UNTRACKED_CONTENTS when
+		 * ignored_only is true, since DIR_KEEP_UNTRACKED_CONTENTS
+		 * only has effect in combination with DIR_SHOW_IGNORED_TOO.  It makes
+		 * the code clearer to exclude it, though.
+		 */
+		dir.flags |= DIR_KEEP_UNTRACKED_CONTENTS;
+	}
 
 	if (read_cache() < 0)
 		die(_("index file corrupt"));
 
-	if (!ignored)
-		setup_standard_excludes(&dir);
-
 	pl = add_pattern_list(&dir, EXC_CMDL, "--exclude option");
 	for (i = 0; i < exclude_list.nr; i++)
 		add_pattern(exclude_list.items[i].string, "", 0, pl, -(i+1));
diff --git a/dir.c b/dir.c
@@ -193,6 +193,10 @@ int fill_directory(struct dir_struct *dir,
 	const char *prefix;
 	size_t prefix_len;
 
+	unsigned exclusive_flags = DIR_SHOW_IGNORED | DIR_SHOW_IGNORED_TOO;
+	if ((dir->flags & exclusive_flags) == exclusive_flags)
+		BUG("DIR_SHOW_IGNORED and DIR_SHOW_IGNORED_TOO are exclusive");
+
 	/*
 	 * Calculate common prefix for the pathspec, and
 	 * use that to optimize the directory walk
@@ -1836,7 +1840,7 @@ static enum path_treatment treat_directory(struct dir_struct *dir,
 	 * to recurse into untracked/ignored directories if either of the
 	 * following bits is set:
 	 *   - DIR_SHOW_IGNORED_TOO (because then we need to determine if
-	 *                           there are ignored directories below)
+	 *                           there are ignored entries below)
 	 *   - DIR_HIDE_EMPTY_DIRECTORIES (because we have to determine if
 	 *                                 the directory is empty)
 	 */
@@ -1854,10 +1858,11 @@ static enum path_treatment treat_directory(struct dir_struct *dir,
 		return path_excluded;
 
 	/*
-	 * If we have we don't want to know the all the paths under an
-	 * untracked or ignored directory, we still need to go into the
-	 * directory to determine if it is empty (because an empty directory
-	 * should be path_none instead of path_excluded or path_untracked).
+	 * Even if we don't want to know all the paths under an untracked or
+	 * ignored directory, we may still need to go into the directory to
+	 * determine if it is empty (because with DIR_HIDE_EMPTY_DIRECTORIES,
+	 * an empty directory should be path_none instead of path_excluded or
+	 * path_untracked).
 	 */
 	check_only = ((dir->flags & DIR_HIDE_EMPTY_DIRECTORIES) &&
 		      !(dir->flags & DIR_SHOW_IGNORED_TOO));
