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, 84 insertions, 0 deletions

diff --git a/sha1_file.c b/sha1_file.c
index aaa3c52869..fa08475c91 100644
--- a/sha1_file.c
+++ b/sha1_file.c
@@ -3264,3 +3264,87 @@ void assert_sha1_type(const unsigned char *sha1, enum object_type expect)
 		die("%s is not a valid '%s' object", sha1_to_hex(sha1),
 		    typename(expect));
 }
+
+static int for_each_file_in_obj_subdir(int subdir_nr,
+				       struct strbuf *path,
+				       each_loose_object_fn obj_cb,
+				       each_loose_cruft_fn cruft_cb,
+				       each_loose_subdir_fn subdir_cb,
+				       void *data)
+{
+	size_t baselen = path->len;
+	DIR *dir = opendir(path->buf);
+	struct dirent *de;
+	int r = 0;
+
+	if (!dir) {
+		if (errno == ENOENT)
+			return 0;
+		return error("unable to open %s: %s", path->buf, strerror(errno));
+	}
+
+	while ((de = readdir(dir))) {
+		if (is_dot_or_dotdot(de->d_name))
+			continue;
+
+		strbuf_setlen(path, baselen);
+		strbuf_addf(path, "/%s", de->d_name);
+
+		if (strlen(de->d_name) == 38)  {
+			char hex[41];
+			unsigned char sha1[20];
+
+			snprintf(hex, sizeof(hex), "%02x%s",
+				 subdir_nr, de->d_name);
+			if (!get_sha1_hex(hex, sha1)) {
+				if (obj_cb) {
+					r = obj_cb(sha1, path->buf, data);
+					if (r)
+						break;
+				}
+				continue;
+			}
+		}
+
+		if (cruft_cb) {
+			r = cruft_cb(de->d_name, path->buf, data);
+			if (r)
+				break;
+		}
+	}
+	strbuf_setlen(path, baselen);
+
+	if (!r && subdir_cb)
+		r = subdir_cb(subdir_nr, path->buf, data);
+
+	closedir(dir);
+	return r;
+}
+
+int for_each_loose_file_in_objdir(const char *path,
+			    each_loose_object_fn obj_cb,
+			    each_loose_cruft_fn cruft_cb,
+			    each_loose_subdir_fn subdir_cb,
+			    void *data)
+{
+	struct strbuf buf = STRBUF_INIT;
+	size_t baselen;
+	int r = 0;
+	int i;
+
+	strbuf_addstr(&buf, path);
+	strbuf_addch(&buf, '/');
+	baselen = buf.len;
+
+	for (i = 0; i < 256; i++) {
+		strbuf_addf(&buf, "%02x", i);
+		r = for_each_file_in_obj_subdir(i, &buf, obj_cb, cruft_cb,
+						subdir_cb, data);
+		strbuf_setlen(&buf, baselen);
+		if (r)
+			break;
+	}
+
+	strbuf_release(&buf);
+	return r;
+}