dir-iterator: support iteration in sorted order

The `struct dir_iterator` is a helper that allows us to iterate through
directory entries. This iterator returns entries in the exact same order
as readdir(3P) does -- or in other words, it guarantees no specific
order at all.

This is about to become problematic as we are introducing a new reflog
subcommand to list reflogs. As the "files" backend uses the directory
iterator to enumerate reflogs, returning reflog names and exposing them
to the user would inherit the indeterministic ordering. Naturally, it
would make for a terrible user interface to show a list with no
discernible order.

While this could be handled at a higher level by the new subcommand
itself by collecting and ordering the reflogs, this would be inefficient
because we would first have to collect all reflogs before we can sort
them, which would introduce additional latency when there are many
reflogs.

Instead, introduce a new option into the directory iterator that asks
for its entries to be yielded in lexicographical order. If set, the
iterator will read all directory entries greedily and sort them before
we start to iterate over them.

While this will of course also incur overhead as we cannot yield the
directory entries immediately, it should at least be more efficient than
having to sort the complete list of reflogs as we only need to sort one
directory at a time.

This functionality will be used in a follow-up commit.

Signed-off-by: Patrick Steinhardt <[email protected]>
Signed-off-by: Junio C Hamano <[email protected]>

Author: pks-t

dir-iterator.c

@@ -2,10 +2,19 @@
 #include "dir.h"
 #include "iterator.h"
 #include "dir-iterator.h"
+#include "string-list.h"
 
 struct dir_iterator_level {
 	DIR *dir;
 
+	/*
+	 * The directory entries of the current level. This list will only be
+	 * populated when the iterator is ordered. In that case, `dir` will be
+	 * set to `NULL`.
+	 */
+	struct string_list entries;
+	size_t entries_idx;
+
 	/*
 	 * The length of the directory part of path at this level
 	 * (including a trailing '/'):
@@ -43,6 +52,31 @@ struct dir_iterator_int {
 	unsigned int flags;
 };
 
+static int next_directory_entry(DIR *dir, const char *path,
+				struct dirent **out)
+{
+	struct dirent *de;
+
+repeat:
+	errno = 0;
+	de = readdir(dir);
+	if (!de) {
+		if (errno) {
+			warning_errno("error reading directory '%s'",
+				      path);
+			return -1;
+		}
+
+		return 1;
+	}
+
+	if (is_dot_or_dotdot(de->d_name))
+		goto repeat;
+
+	*out = de;
+	return 0;
+}
+
 /*
  * Push a level in the iter stack and initialize it with information from
  * the directory pointed by iter->base->path. It is assumed that this
@@ -72,6 +106,35 @@ static int push_level(struct dir_iterator_int *iter)
 		return -1;
 	}
 
+	string_list_init_dup(&level->entries);
+	level->entries_idx = 0;
+
+	/*
+	 * When the iterator is sorted we read and sort all directory entries
+	 * directly.
+	 */
+	if (iter->flags & DIR_ITERATOR_SORTED) {
+		struct dirent *de;
+
+		while (1) {
+			int ret = next_directory_entry(level->dir, iter->base.path.buf, &de);
+			if (ret < 0) {
+				if (errno != ENOENT &&
+				    iter->flags & DIR_ITERATOR_PEDANTIC)
+					return -1;
+				continue;
+			} else if (ret > 0) {
+				break;
+			}
+
+			string_list_append(&level->entries, de->d_name);
+		}
+		string_list_sort(&level->entries);
+
+		closedir(level->dir);
+		level->dir = NULL;
+	}
+
 	return 0;
 }
 
@@ -88,6 +151,7 @@ static int pop_level(struct dir_iterator_int *iter)
 		warning_errno("error closing directory '%s'",
 			      iter->base.path.buf);
 	level->dir = NULL;
+	string_list_clear(&level->entries, 0);
 
 	return --iter->levels_nr;
 }
@@ -139,27 +203,34 @@ int dir_iterator_advance(struct dir_iterator *dir_iterator)
 		struct dirent *de;
 		struct dir_iterator_level *level =
 			&iter->levels[iter->levels_nr - 1];
+		const char *name;
 
 		strbuf_setlen(&iter->base.path, level->prefix_len);
-		errno = 0;
-		de = readdir(level->dir);
 
-		if (!de) {
-			if (errno) {
-				warning_errno("error reading directory '%s'",
-					      iter->base.path.buf);
+		if (level->dir) {
+			int ret = next_directory_entry(level->dir, iter->base.path.buf, &de);
+			if (ret < 0) {
 				if (iter->flags & DIR_ITERATOR_PEDANTIC)
 					goto error_out;
-			} else if (pop_level(iter) == 0) {
-				return dir_iterator_abort(dir_iterator);
+				continue;
+			} else if (ret > 0) {
+				if (pop_level(iter) == 0)
+					return dir_iterator_abort(dir_iterator);
+				continue;
 			}
-			continue;
-		}
 
-		if (is_dot_or_dotdot(de->d_name))
-			continue;
+			name = de->d_name;
+		} else {
+			if (level->entries_idx >= level->entries.nr) {
+				if (pop_level(iter) == 0)
+					return dir_iterator_abort(dir_iterator);
+				continue;
+			}
 
-		if (prepare_next_entry_data(iter, de->d_name)) {
+			name = level->entries.items[level->entries_idx++].string;
+		}
+
+		if (prepare_next_entry_data(iter, name)) {
 			if (errno != ENOENT && iter->flags & DIR_ITERATOR_PEDANTIC)
 				goto error_out;
 			continue;
@@ -188,6 +259,8 @@ int dir_iterator_abort(struct dir_iterator *dir_iterator)
 			warning_errno("error closing directory '%s'",
 				      iter->base.path.buf);
 		}
+
+		string_list_clear(&level->entries, 0);
 	}
 
 	free(iter->levels);

dir-iterator.h

@@ -54,8 +54,11 @@
  *   and ITER_ERROR is returned immediately. In both cases, a meaningful
  *   warning is emitted. Note: ENOENT errors are always ignored so that
  *   the API users may remove files during iteration.
+ *
+ * - DIR_ITERATOR_SORTED: sort directory entries alphabetically.
  */
 #define DIR_ITERATOR_PEDANTIC (1 << 0)
+#define DIR_ITERATOR_SORTED   (1 << 1)
 
 struct dir_iterator {
 	/* The current path: */