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, 33 insertions, 0 deletions

diff --git a/cache.h b/cache.h
index de290c4..bdfbbcf 100644
--- a/cache.h
+++ b/cache.h
@@ -1239,6 +1239,39 @@ extern unsigned long unpack_object_header_buffer(const unsigned char *buf, unsig
 extern unsigned long get_size_from_delta(struct packed_git *, struct pack_window **, off_t);
 extern int unpack_object_header(struct packed_git *, struct pack_window **, off_t *, unsigned long *);
 
+/*
+ * Iterate over the files in the loose-object parts of the object
+ * directory "path", triggering the following callbacks:
+ *
+ *  - loose_object is called for each loose object we find.
+ *
+ *  - loose_cruft is called for any files that do not appear to be
+ *    loose objects. Note that we only look in the loose object
+ *    directories "objects/[0-9a-f]{2}/", so we will not report
+ *    "objects/foobar" as cruft.
+ *
+ *  - loose_subdir is called for each top-level hashed subdirectory
+ *    of the object directory (e.g., "$OBJDIR/f0"). It is called
+ *    after the objects in the directory are processed.
+ *
+ * Any callback that is NULL will be ignored. Callbacks returning non-zero
+ * will end the iteration.
+ */
+typedef int each_loose_object_fn(const unsigned char *sha1,
+				 const char *path,
+				 void *data);
+typedef int each_loose_cruft_fn(const char *basename,
+				const char *path,
+				void *data);
+typedef int each_loose_subdir_fn(int nr,
+				 const char *path,
+				 void *data);
+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 object_info {
 	/* Request */
 	enum object_type *typep;