prune: factor out loose-object directory traversal

Prune has to walk $GIT_DIR/objects/?? in order to find the
set of loose objects to prune. Other parts of the code
(e.g., count-objects) want to do the same. Let's factor it
out into a reusable for_each-style function.

Note that this is not quite a straight code movement. The
original code had strange behavior when it found a file of
the form "[0-9a-f]{2}/.{38}" that did _not_ contain all hex
digits. It executed a "break" from the loop, meaning that we
stopped pruning in that directory (but still pruned other
directories!). This was probably a bug; we do not want to
process the file as an object, but we should keep going
otherwise (and that is how the new code handles it).

We are also a little more careful with loose object
directories which fail to open. The original code silently
ignored any failures, but the new code will complain about
any problems besides ENOENT.

Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

1 files changed, 26 insertions, 61 deletions

diff --git a/builtin/prune.c b/builtin/prune.c
index 144a3bd..763f53e 100644
--- a/builtin/prune.c
+++ b/builtin/prune.c
@@ -31,11 +31,23 @@ static int prune_tmp_file(const char *fullpath)
 	return 0;
 }
 
-static int prune_object(const char *fullpath, const unsigned char *sha1)
+static int prune_object(const unsigned char *sha1, const char *fullpath,
+			void *data)
 {
 	struct stat st;
-	if (lstat(fullpath, &st))
-		return error("Could not stat '%s'", fullpath);
+
+	/*
+	 * Do we know about this object?
+	 * It must have been reachable
+	 */
+	if (lookup_object(sha1))
+		return 0;
+
+	if (lstat(fullpath, &st)) {
+		/* report errors, but do not stop pruning */
+		error("Could not stat '%s'", fullpath);
+		return 0;
+	}
 	if (st.st_mtime > expire)
 		return 0;
 	if (show_only || verbose) {
@@ -48,68 +60,20 @@ static int prune_object(const char *fullpath, const unsigned char *sha1)
 	return 0;
 }
 
-static int prune_dir(int i, struct strbuf *path)
+static int prune_cruft(const char *basename, const char *path, void *data)
 {
-	size_t baselen = path->len;
-	DIR *dir = opendir(path->buf);
-	struct dirent *de;
-
-	if (!dir)
-		return 0;
-
-	while ((de = readdir(dir)) != NULL) {
-		char name[100];
-		unsigned char sha1[20];
-
-		if (is_dot_or_dotdot(de->d_name))
-			continue;
-		if (strlen(de->d_name) == 38) {
-			sprintf(name, "%02x", i);
-			memcpy(name+2, de->d_name, 39);
-			if (get_sha1_hex(name, sha1) < 0)
-				break;
-
-			/*
-			 * Do we know about this object?
-			 * It must have been reachable
-			 */
-			if (lookup_object(sha1))
-				continue;
-
-			strbuf_addf(path, "/%s", de->d_name);
-			prune_object(path->buf, sha1);
-			strbuf_setlen(path, baselen);
-			continue;
-		}
-		if (starts_with(de->d_name, "tmp_obj_")) {
-			strbuf_addf(path, "/%s", de->d_name);
-			prune_tmp_file(path->buf);
-			strbuf_setlen(path, baselen);
-			continue;
-		}
-		fprintf(stderr, "bad sha1 file: %s/%s\n", path->buf, de->d_name);
-	}
-	closedir(dir);
-	if (!show_only)
-		rmdir(path->buf);
+	if (starts_with(basename, "tmp_obj_"))
+		prune_tmp_file(path);
+	else
+		fprintf(stderr, "bad sha1 file: %s\n", path);
 	return 0;
 }
 
-static void prune_object_dir(const char *path)
+static int prune_subdir(int nr, const char *path, void *data)
 {
-	struct strbuf buf = STRBUF_INIT;
-	size_t baselen;
-	int i;
-
-	strbuf_addstr(&buf, path);
-	strbuf_addch(&buf, '/');
-	baselen = buf.len;
-
-	for (i = 0; i < 256; i++) {
-		strbuf_addf(&buf, "%02x", i);
-		prune_dir(i, &buf);
-		strbuf_setlen(&buf, baselen);
-	}
+	if (!show_only)
+		rmdir(path);
+	return 0;
 }
 
 /*
@@ -173,7 +137,8 @@ int cmd_prune(int argc, const char **argv, const char *prefix)
 
 	mark_reachable_objects(&revs, 1, progress);
 	stop_progress(&progress);
-	prune_object_dir(get_object_directory());
+	for_each_loose_file_in_objdir(get_object_directory(), prune_object,
+				      prune_cruft, prune_subdir, NULL);
 
 	prune_packed_objects(show_only ? PRUNE_PACKED_DRY_RUN : 0);
 	remove_temporary_files(get_object_directory());