[PATCH 4/4] ls-files: fix overeager pathspec optimization

From: Junio C Hamano <gitster@pobox.com>
Date: Jan 9, 2010, 07:35 UTC
Message-ID: <1263022535-12822-4-git-send-email-gitster@pobox.com>
In-Reply-To: <1263022535-12822-1-git-send-email-gitster@pobox.com>

Given pathspecs that share a common prefix, ls-files optimized its call into recursive directory reader by starting at the common prefix directory.

If you have a directory "t" with an untracked file "t/junk" in it, but the top-level .gitignore file told us to ignore "t/", this resulted in:

    $ git ls-files -o --exclude-standard
    $ git ls-files -o --exclude-standard t/
    t/junk
    $ git ls-files -o --exclude-standard t/junk
    t/junk
    $ cd t && git ls-files -o --exclude-standard
    junk

We could argue that you are overriding the ignore file by giving a patchspec that matches or being in that directory, but it is somewhat unexpected. Worse yet, these behave differently:

    $ git ls-files -o --exclude-standard t/ .
    $ git ls-files -o --exclude-standard t/
    t/junk

This patch changes the optimization so that it notices when the common prefix directory that it starts reading from is an ignored one.

Signed-off-by: Junio C Hamano <gitster@pobox.com>
---
 dir.c                              |   38 +++++++++++++++++++++++++++++++++++-
 t/t3001-ls-files-others-exclude.sh |    2 +-
 2 files changed, 38 insertions(+), 2 deletions(-)

diff --git a/dir.c b/dir.c
index 35cc89b..00d698d 100644
--- a/dir.c
+++ b/dir.c
@@ -813,6 +813,41 @@ static void free_simplify(struct path_simplify *simplify)
 	free(simplify);
 }
 
+static int treat_leading_path(struct dir_struct *dir,
+			      const char *path, int len,
+			      const struct path_simplify *simplify)
+{
+	char pathbuf[PATH_MAX];
+	int baselen, blen;
+	const char *cp;
+
+	while (len && path[len - 1] == '/')
+		len--;
+	if (!len)
+		return 1;
+	baselen = 0;
+	while (1) {
+		cp = path + baselen + !!baselen;
+		cp = memchr(cp, '/', path + len - cp);
+		if (!cp)
+			baselen = len;
+		else
+			baselen = cp - path;
+		memcpy(pathbuf, path, baselen);
+		pathbuf[baselen] = '\0';
+		if (!is_directory(pathbuf))
+			return 0;
+		if (simplify_away(pathbuf, baselen, simplify))
+			return 0;
+		blen = baselen;
+		if (treat_one_path(dir, pathbuf, &blen, simplify,
+				   DT_DIR, NULL) == path_ignored)
+			return 0; /* do not recurse into it */
+		if (len <= baselen)
+			return 1; /* finished checking */
+	}
+}
+
 int read_directory(struct dir_struct *dir, const char *path, int len, const char **pathspec)
 {
 	struct path_simplify *simplify;
@@ -821,7 +856,8 @@ int read_directory(struct dir_struct *dir, const char *path, int len, const char
 		return dir->nr;
 
 	simplify = create_simplify(pathspec);
-	read_directory_recursive(dir, path, len, 0, simplify);
+	if (!len || treat_leading_path(dir, path, len, simplify))
+		read_directory_recursive(dir, path, len, 0, simplify);
 	free_simplify(simplify);
 	qsort(dir->entries, dir->nr, sizeof(struct dir_entry *), cmp_name);
 	qsort(dir->ignored, dir->ignored_nr, sizeof(struct dir_entry *), cmp_name);
diff --git a/t/t3001-ls-files-others-exclude.sh b/t/t3001-ls-files-others-exclude.sh
index e3e4d71..9e71260 100755
--- a/t/t3001-ls-files-others-exclude.sh
+++ b/t/t3001-ls-files-others-exclude.sh
@@ -183,7 +183,7 @@ test_expect_success 'subdirectory ignore (l1/l2)' '
 	test_cmp expect actual
 '
 
-test_expect_failure 'subdirectory ignore (l1)' '
+test_expect_success 'subdirectory ignore (l1)' '
 	(
 		cd top/l1 &&
 		git ls-files -o --exclude-standard

-- 
1.6.6.209.g52296.dirty