dir: hide untracked contents of untracked dirs

When we taught read_directory_recursive() to recurse into untracked
directories in search of ignored files given DIR_SHOW_IGNORED_TOO, that
had the side effect of teaching it to collect the untracked contents of
untracked directories. It doesn't always make sense to return these,
though (we do need them for `clean -d`), so we introduce a flag
(DIR_KEEP_UNTRACKED_CONTENTS) to control whether or not read_directory()
strips dir->entries of the untracked contents of untracked dirs.

We also introduce check_contains() to check if one dir_entry corresponds
to a path which contains the path corresponding to another dir_entry.

This also fixes known breakages in t7061, since status --ignored now
searches untracked directories for ignored files.

Signed-off-by: Samuel Lijin <[email protected]>
Signed-off-by: Junio C Hamano <[email protected]>

Author: Samuel Lijin

Documentation/technical/api-directory-listing.txt

@@ -33,6 +33,12 @@ The notable options are:
 	Similar to `DIR_SHOW_IGNORED`, but return ignored files in `ignored[]`
 	in addition to untracked files in `entries[]`.
 
+`DIR_KEEP_UNTRACKED_CONTENTS`:::
+
+	Only has meaning if `DIR_SHOW_IGNORED_TOO` is also set; if this is set, the
+	untracked contents of untracked directories are also returned in
+	`entries[]`.
+
 `DIR_COLLECT_IGNORED`:::
 
 	Special mode for git-add. Return ignored files in `ignored[]` and

dir.c

@@ -1813,6 +1813,14 @@ static int cmp_name(const void *p1, const void *p2)
 	return name_compare(e1->name, e1->len, e2->name, e2->len);
 }
 
+/* check if *out lexically strictly contains *in */
+static int check_contains(const struct dir_entry *out, const struct dir_entry *in)
+{
+	return (out->len < in->len) &&
+		(out->name[out->len - 1] == '/') &&
+		!memcmp(out->name, in->name, out->len);
+}
+
 static int treat_leading_path(struct dir_struct *dir,
 			      const char *path, int len,
 			      const struct pathspec *pathspec)
@@ -2028,6 +2036,29 @@ int read_directory(struct dir_struct *dir, const char *path,
 		read_directory_recursive(dir, path, len, untracked, 0, pathspec);
 	QSORT(dir->entries, dir->nr, cmp_name);
 	QSORT(dir->ignored, dir->ignored_nr, cmp_name);
+
+	/*
+	 * If DIR_SHOW_IGNORED_TOO is set, read_directory_recursive() will
+	 * also pick up untracked contents of untracked dirs; by default
+	 * we discard these, but given DIR_KEEP_UNTRACKED_CONTENTS we do not.
+	 */
+	if ((dir->flags & DIR_SHOW_IGNORED_TOO) &&
+		     !(dir->flags & DIR_KEEP_UNTRACKED_CONTENTS)) {
+		int i, j;
+
+		/* remove from dir->entries untracked contents of untracked dirs */
+		for (i = j = 0; j < dir->nr; j++) {
+			if (i && check_contains(dir->entries[i - 1], dir->entries[j])) {
+				free(dir->entries[j]);
+				dir->entries[j] = NULL;
+			} else {
+				dir->entries[i++] = dir->entries[j];
+			}
+		}
+
+		dir->nr = i;
+	}
+
 	if (dir->untracked) {
 		static struct trace_key trace_untracked_stats = TRACE_KEY_INIT(UNTRACKED_STATS);
 		trace_printf_key(&trace_untracked_stats,

dir.h

@@ -151,7 +151,8 @@ struct dir_struct {
 		DIR_NO_GITLINKS = 1<<3,
 		DIR_COLLECT_IGNORED = 1<<4,
 		DIR_SHOW_IGNORED_TOO = 1<<5,
-		DIR_COLLECT_KILLED_ONLY = 1<<6
+		DIR_COLLECT_KILLED_ONLY = 1<<6,
+		DIR_KEEP_UNTRACKED_CONTENTS = 1<<7
 	} flags;
 	struct dir_entry **entries;
 	struct dir_entry **ignored;

t/t7061-wtstatus-ignore.sh

@@ -12,7 +12,7 @@ cat >expected <<\EOF
 !! untracked/ignored
 EOF
 
-test_expect_failure 'status untracked directory with --ignored' '
+test_expect_success 'status untracked directory with --ignored' '
 	echo "ignored" >.gitignore &&
 	mkdir untracked &&
 	: >untracked/ignored &&
@@ -21,7 +21,7 @@ test_expect_failure 'status untracked directory with --ignored' '
 	test_cmp expected actual
 '
 
-test_expect_failure 'same with gitignore starting with BOM' '
+test_expect_success 'same with gitignore starting with BOM' '
 	printf "\357\273\277ignored\n" >.gitignore &&
 	mkdir -p untracked &&
 	: >untracked/ignored &&