dir-iterator: refactor state machine model

dir_iterator_advance() is a large function with two nested loops. Let's
improve its readability factoring out three functions and simplifying
its mechanics. The refactored model will no longer depend on
level.initialized and level.dir_state to keep track of the iteration
state and will perform on a single loop.

Also, dir_iterator_begin() currently does not check if the given string
represents a valid directory path. Since the refactored model will have
to stat() the given path at initialization, let's also check for this
kind of error and make dir_iterator_begin() return NULL, on failures,
with errno appropriately set. And add tests for this new behavior.

Improve documentation at dir-iteration.h and code comments at
dir-iterator.c to reflect the changes and eliminate possible
ambiguities.

Finally, adjust refs/files-backend.c to check for now possible
dir_iterator_begin() failures.

Original-patch-by: Daniel Ferreira <bnmvco@gmail.com>
Signed-off-by: Matheus Tavares <matheus.bernardino@usp.br>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

1 files changed, 122 insertions, 112 deletions

diff --git a/dir-iterator.c b/dir-iterator.c
index 0c88808..594fe4d 100644
--- a/dir-iterator.c
+++ b/dir-iterator.c
@@ -4,8 +4,6 @@
 #include "dir-iterator.h"
 
 struct dir_iterator_level {
-	int initialized;
-
 	DIR *dir;
 
 	/*
@@ -13,16 +11,6 @@ struct dir_iterator_level {
 	 * (including a trailing '/'):
 	 */
 	size_t prefix_len;
-
-	/*
-	 * The last action that has been taken with the current entry
-	 * (needed for directories, which have to be included in the
-	 * iteration and also iterated into):
-	 */
-	enum {
-		DIR_STATE_ITER,
-		DIR_STATE_RECURSE
-	} dir_state;
 };
 
 /*
@@ -34,9 +22,11 @@ struct dir_iterator_int {
 	struct dir_iterator base;
 
 	/*
-	 * The number of levels currently on the stack. This is always
-	 * at least 1, because when it becomes zero the iteration is
-	 * ended and this struct is freed.
+	 * The number of levels currently on the stack. After the first
+	 * call to dir_iterator_begin(), if it succeeds to open the
+	 * first level's dir, this will always be at least 1. Then,
+	 * when it comes to zero the iteration is ended and this
+	 * struct is freed.
 	 */
 	size_t levels_nr;
 
@@ -50,113 +40,118 @@ struct dir_iterator_int {
 	struct dir_iterator_level *levels;
 };
 
+/*
+ * 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
+ * strbuf points to a valid directory path. Return 0 on success and -1
+ * otherwise, leaving the stack unchanged.
+ */
+static int push_level(struct dir_iterator_int *iter)
+{
+	struct dir_iterator_level *level;
+
+	ALLOC_GROW(iter->levels, iter->levels_nr + 1, iter->levels_alloc);
+	level = &iter->levels[iter->levels_nr++];
+
+	if (!is_dir_sep(iter->base.path.buf[iter->base.path.len - 1]))
+		strbuf_addch(&iter->base.path, '/');
+	level->prefix_len = iter->base.path.len;
+
+	level->dir = opendir(iter->base.path.buf);
+	if (!level->dir) {
+		if (errno != ENOENT) {
+			warning_errno("error opening directory '%s'",
+				      iter->base.path.buf);
+		}
+		iter->levels_nr--;
+		return -1;
+	}
+
+	return 0;
+}
+
+/*
+ * Pop the top level on the iter stack, releasing any resources associated
+ * with it. Return the new value of iter->levels_nr.
+ */
+static int pop_level(struct dir_iterator_int *iter)
+{
+	struct dir_iterator_level *level =
+		&iter->levels[iter->levels_nr - 1];
+
+	if (level->dir && closedir(level->dir))
+		warning_errno("error closing directory '%s'",
+			      iter->base.path.buf);
+	level->dir = NULL;
+
+	return --iter->levels_nr;
+}
+
+/*
+ * Populate iter->base with the necessary information on the next iteration
+ * entry, represented by the given dirent de. Return 0 on success and -1
+ * otherwise.
+ */
+static int prepare_next_entry_data(struct dir_iterator_int *iter,
+				   struct dirent *de)
+{
+	strbuf_addstr(&iter->base.path, de->d_name);
+	/*
+	 * We have to reset these because the path strbuf might have
+	 * been realloc()ed at the previous strbuf_addstr().
+	 */
+	iter->base.relative_path = iter->base.path.buf +
+				   iter->levels[0].prefix_len;
+	iter->base.basename = iter->base.path.buf +
+			      iter->levels[iter->levels_nr - 1].prefix_len;
+
+	if (lstat(iter->base.path.buf, &iter->base.st)) {
+		if (errno != ENOENT)
+			warning_errno("failed to stat '%s'", iter->base.path.buf);
+		return -1;
+	}
+
+	return 0;
+}
+
 int dir_iterator_advance(struct dir_iterator *dir_iterator)
 {
 	struct dir_iterator_int *iter =
 		(struct dir_iterator_int *)dir_iterator;
 
+	if (S_ISDIR(iter->base.st.st_mode)) {
+		if (push_level(iter) && iter->levels_nr == 0) {
+			/* Pushing the first level failed */
+			return dir_iterator_abort(dir_iterator);
+		}
+	}
+
+	/* Loop until we find an entry that we can give back to the caller. */
 	while (1) {
+		struct dirent *de;
 		struct dir_iterator_level *level =
 			&iter->levels[iter->levels_nr - 1];
-		struct dirent *de;
 
-		if (!level->initialized) {
-			/*
-			 * Note: dir_iterator_begin() ensures that
-			 * path is not the empty string.
-			 */
-			if (!is_dir_sep(iter->base.path.buf[iter->base.path.len - 1]))
-				strbuf_addch(&iter->base.path, '/');
-			level->prefix_len = iter->base.path.len;
-
-			level->dir = opendir(iter->base.path.buf);
-			if (!level->dir && errno != ENOENT) {
-				warning_errno("error opening directory '%s'",
+		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);
-				/* Popping the level is handled below */
-			}
-
-			level->initialized = 1;
-		} else if (S_ISDIR(iter->base.st.st_mode)) {
-			if (level->dir_state == DIR_STATE_ITER) {
-				/*
-				 * The directory was just iterated
-				 * over; now prepare to iterate into
-				 * it.
-				 */
-				level->dir_state = DIR_STATE_RECURSE;
-				ALLOC_GROW(iter->levels, iter->levels_nr + 1,
-					   iter->levels_alloc);
-				level = &iter->levels[iter->levels_nr++];
-				level->initialized = 0;
-				continue;
-			} else {
-				/*
-				 * The directory has already been
-				 * iterated over and iterated into;
-				 * we're done with it.
-				 */
-			}
+			else if (pop_level(iter) == 0)
+				return dir_iterator_abort(dir_iterator);
+			continue;
 		}
 
-		if (!level->dir) {
-			/*
-			 * This level is exhausted (or wasn't opened
-			 * successfully); pop up a level.
-			 */
-			if (--iter->levels_nr == 0)
-				return dir_iterator_abort(dir_iterator);
+		if (is_dot_or_dotdot(de->d_name))
+			continue;
 
+		if (prepare_next_entry_data(iter, de))
 			continue;
-		}
 
-		/*
-		 * Loop until we find an entry that we can give back
-		 * to the caller:
-		 */
-		while (1) {
-			strbuf_setlen(&iter->base.path, level->prefix_len);
-			errno = 0;
-			de = readdir(level->dir);
-
-			if (!de) {
-				/* This level is exhausted; pop up a level. */
-				if (errno) {
-					warning_errno("error reading directory '%s'",
-						      iter->base.path.buf);
-				} else if (closedir(level->dir))
-					warning_errno("error closing directory '%s'",
-						      iter->base.path.buf);
-
-				level->dir = NULL;
-				if (--iter->levels_nr == 0)
-					return dir_iterator_abort(dir_iterator);
-				break;
-			}
-
-			if (is_dot_or_dotdot(de->d_name))
-				continue;
-
-			strbuf_addstr(&iter->base.path, de->d_name);
-			if (lstat(iter->base.path.buf, &iter->base.st) < 0) {
-				if (errno != ENOENT)
-					warning_errno("failed to stat '%s'",
-						      iter->base.path.buf);
-				continue;
-			}
-
-			/*
-			 * We have to set these each time because
-			 * the path strbuf might have been realloc()ed.
-			 */
-			iter->base.relative_path =
-				iter->base.path.buf + iter->levels[0].prefix_len;
-			iter->base.basename =
-				iter->base.path.buf + level->prefix_len;
-			level->dir_state = DIR_STATE_ITER;
-
-			return ITER_OK;
-		}
+		return ITER_OK;
 	}
 }
 
@@ -187,17 +182,32 @@ struct dir_iterator *dir_iterator_begin(const char *path)
 {
 	struct dir_iterator_int *iter = xcalloc(1, sizeof(*iter));
 	struct dir_iterator *dir_iterator = &iter->base;
-
-	if (!path || !*path)
-		BUG("empty path passed to dir_iterator_begin()");
+	int saved_errno;
 
 	strbuf_init(&iter->base.path, PATH_MAX);
 	strbuf_addstr(&iter->base.path, path);
 
 	ALLOC_GROW(iter->levels, 10, iter->levels_alloc);
+	iter->levels_nr = 0;
 
-	iter->levels_nr = 1;
-	iter->levels[0].initialized = 0;
+	/*
+	 * Note: stat already checks for NULL or empty strings and
+	 * inexistent paths.
+	 */
+	if (stat(iter->base.path.buf, &iter->base.st) < 0) {
+		saved_errno = errno;
+		goto error_out;
+	}
+
+	if (!S_ISDIR(iter->base.st.st_mode)) {
+		saved_errno = ENOTDIR;
+		goto error_out;
+	}
 
 	return dir_iterator;
+
+error_out:
+	dir_iterator_abort(dir_iterator);
+	errno = saved_errno;
+	return NULL;
 }