Merge branch 'ab/fsck-unexpected-type'

"git fsck" has been taught to report mismatch between expected and
actual types of an object better.

* ab/fsck-unexpected-type:
  fsck: report invalid object type-path combinations
  fsck: don't hard die on invalid object types
  object-file.c: stop dying in parse_loose_header()
  object-file.c: return ULHR_TOO_LONG on "header too long"
  object-file.c: use "enum" return type for unpack_loose_header()
  object-file.c: simplify unpack_loose_short_header()
  object-file.c: make parse_loose_header_extended() public
  object-file.c: return -1, not "status" from unpack_loose_header()
  object-file.c: don't set "typep" when returning non-zero
  cat-file tests: test for current --allow-unknown-type behavior
  cat-file tests: add corrupt loose object test
  cat-file tests: test for missing/bogus object with -t, -s and -p
  cat-file tests: move bogus_* variable declarations earlier
  fsck tests: test for garbage appended to a loose object
  fsck tests: test current hash/type mismatch behavior
  fsck tests: refactor one test to use a sub-repo
  fsck tests: add test for fsck-ing an unknown type

1 files changed, 42 insertions, 3 deletions

diff --git a/cache.h b/cache.h
index d092820c94..acb67dbd64 100644
--- a/cache.h
+++ b/cache.h
@@ -1268,11 +1268,50 @@ char *xdg_cache_home(const char *filename);
 
 int git_open_cloexec(const char *name, int flags);
 #define git_open(name) git_open_cloexec(name, O_RDONLY)
-int unpack_loose_header(git_zstream *stream, unsigned char *map, unsigned long mapsize, void *buffer, unsigned long bufsiz);
-int parse_loose_header(const char *hdr, unsigned long *sizep);
+
+/**
+ * unpack_loose_header() initializes the data stream needed to unpack
+ * a loose object header.
+ *
+ * Returns:
+ *
+ * - ULHR_OK on success
+ * - ULHR_BAD on error
+ * - ULHR_TOO_LONG if the header was too long
+ *
+ * It will only parse up to MAX_HEADER_LEN bytes unless an optional
+ * "hdrbuf" argument is non-NULL. This is intended for use with
+ * OBJECT_INFO_ALLOW_UNKNOWN_TYPE to extract the bad type for (error)
+ * reporting. The full header will be extracted to "hdrbuf" for use
+ * with parse_loose_header(), ULHR_TOO_LONG will still be returned
+ * from this function to indicate that the header was too long.
+ */
+enum unpack_loose_header_result {
+	ULHR_OK,
+	ULHR_BAD,
+	ULHR_TOO_LONG,
+};
+enum unpack_loose_header_result unpack_loose_header(git_zstream *stream,
+						    unsigned char *map,
+						    unsigned long mapsize,
+						    void *buffer,
+						    unsigned long bufsiz,
+						    struct strbuf *hdrbuf);
+
+/**
+ * parse_loose_header() parses the starting "<type> <len>\0" of an
+ * object. If it doesn't follow that format -1 is returned. To check
+ * the validity of the <type> populate the "typep" in the "struct
+ * object_info". It will be OBJ_BAD if the object type is unknown. The
+ * parsed <len> can be retrieved via "oi->sizep", and from there
+ * passed to unpack_loose_rest().
+ */
+struct object_info;
+int parse_loose_header(const char *hdr, struct object_info *oi);
 
 int check_object_signature(struct repository *r, const struct object_id *oid,
-			   void *buf, unsigned long size, const char *type);
+			   void *buf, unsigned long size, const char *type,
+			   struct object_id *real_oidp);
 
 int finalize_object_file(const char *tmpfile, const char *filename);