[PATCH v3 4/8] dir: hide untracked contents of untracked dirs

[Samuel Lijin <sxlijin@gmail.com>]

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.

Signed-off-by: Samuel Lijin <sxlijin@gmail.com>
---
 dir.c | 54 ++++++++++++++++++++++++++++++++++++++++++++++++++++++
 dir.h |  3 ++-
 2 files changed, 56 insertions(+), 1 deletion(-)

diff --git a/dir.c b/dir.c
index 6bd0350e9..214a148ee 100644
--- a/dir.c
+++ b/dir.c
@@ -1852,6 +1852,14 @@ 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 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)
@@ -2067,6 +2075,52 @@ 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, 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, nr_removed = 0;
+
+		// remove from dir->entries untracked contents of untracked dirs
+		for (i = 0; i < dir->nr; i++) {
+			if (!dir->entries[i])
+				continue;
+
+			for (j = i + 1; j < dir->nr; j++) {
+				if (!dir->entries[j])
+					continue;
+				if (check_contains(dir->entries[i], dir->entries[j])) {
+					nr_removed++;
+					free(dir->entries[j]);
+					dir->entries[j] = NULL;
+				}
+				else {
+					break;
+				}
+			}
+		}
+
+		// strip dir->entries of NULLs
+		if (nr_removed) {
+			for (i = 0;;) {
+				while (i < dir->nr && dir->entries[i])
+					i++;
+				if (i == dir->nr)
+					break;
+				j = i;
+				while (j < dir->nr && !dir->entries[j])
+					j++;
+				if (j == dir->nr)
+					break;
+				dir->entries[i] = dir->entries[j];
+				dir->entries[j] = NULL;
+			}
+			dir->nr -= nr_removed;
+		}
+	}
+
 	if (dir->untracked) {
 		static struct trace_key trace_untracked_stats = TRACE_KEY_INIT(UNTRACKED_STATS);
 		trace_printf_key(&trace_untracked_stats,
diff --git a/dir.h b/dir.h
index bf23a470a..650e54bdf 100644
--- a/dir.h
+++ b/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;
-- 
2.12.2