object-file.c: simplify unpack_loose_short_header()

avar · gitster · commit 01cab9767929 · 2021-10-01T15:06:00.000-07:00
Combine the unpack_loose_short_header(), unpack_loose_header_to_strbuf() and unpack_loose_header() functions into one. The unpack_loose_header_to_strbuf() function was added in 46f0344 (sha1_file: support reading from a loose object of unknown type, 2015-05-03). Its code was mostly copy/pasted between it and both of unpack_loose_header() and unpack_loose_short_header(). We now have a single unpack_loose_header() function which accepts an optional "struct strbuf *" instead. I think the remaining unpack_loose_header() function could be further simplified, we're carrying some complexity just to be able to emit a garbage type longer than MAX_HEADER_LEN, we could alternatively just say "we found a garbage type <first 32 bytes>..." instead. But let's leave the current behavior in place for now. Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
diff --git a/cache.h b/cache.h
@@ -1302,7 +1302,22 @@ 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);
+
+/**
+ * unpack_loose_header() initializes the data stream needed to unpack
+ * a loose object header.
+ *
+ * Returns 0 on success. Returns negative values on error.
+ *
+ * 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().
+ */
+int unpack_loose_header(git_zstream *stream, unsigned char *map,
+			unsigned long mapsize, void *buffer,
+			unsigned long bufsiz, struct strbuf *hdrbuf);
 struct object_info;
 int parse_loose_header(const char *hdr, struct object_info *oi,
 		       unsigned int flags);
diff --git a/object-file.c b/object-file.c
@@ -1210,11 +1210,12 @@ void *map_loose_object(struct repository *r,
 	return map_loose_object_1(r, NULL, oid, size);
 }
 
-static int unpack_loose_short_header(git_zstream *stream,
-				     unsigned char *map, unsigned long mapsize,
-				     void *buffer, unsigned long bufsiz)
+int unpack_loose_header(git_zstream *stream,
+			unsigned char *map, unsigned long mapsize,
+			void *buffer, unsigned long bufsiz,
+			struct strbuf *header)
 {
-	int ret;
+	int status;
 
 	/* Get the data stream */
 	memset(stream, 0, sizeof(*stream));
@@ -1225,35 +1226,8 @@ static int unpack_loose_short_header(git_zstream *stream,
 
 	git_inflate_init(stream);
 	obj_read_unlock();
-	ret = git_inflate(stream, 0);
+	status = git_inflate(stream, 0);
 	obj_read_lock();
-
-	return ret;
-}
-
-int unpack_loose_header(git_zstream *stream,
-			unsigned char *map, unsigned long mapsize,
-			void *buffer, unsigned long bufsiz)
-{
-	int status = unpack_loose_short_header(stream, map, mapsize,
-					       buffer, bufsiz);
-
-	if (status < Z_OK)
-		return -1;
-
-	/* Make sure we have the terminating NUL */
-	if (!memchr(buffer, '\0', stream->next_out - (unsigned char *)buffer))
-		return -1;
-	return 0;
-}
-
-static int unpack_loose_header_to_strbuf(git_zstream *stream, unsigned char *map,
-					 unsigned long mapsize, void *buffer,
-					 unsigned long bufsiz, struct strbuf *header)
-{
-	int status;
-
-	status = unpack_loose_short_header(stream, map, mapsize, buffer, bufsiz);
 	if (status < Z_OK)
 		return -1;
 
@@ -1263,6 +1237,14 @@ static int unpack_loose_header_to_strbuf(git_zstream *stream, unsigned char *map
 	if (memchr(buffer, '\0', stream->next_out - (unsigned char *)buffer))
 		return 0;
 
+	/*
+	 * We have a header longer than MAX_HEADER_LEN. The "header"
+	 * here is only non-NULL when we run "cat-file
+	 * --allow-unknown-type".
+	 */
+	if (!header)
+		return -1;
+
 	/*
 	 * buffer[0..bufsiz] was not large enough.  Copy the partial
 	 * result out to header, and then append the result of further
@@ -1412,6 +1394,7 @@ static int loose_object_info(struct repository *r,
 	char hdr[MAX_HEADER_LEN];
 	struct strbuf hdrbuf = STRBUF_INIT;
 	unsigned long size_scratch;
+	int allow_unknown = flags & OBJECT_INFO_ALLOW_UNKNOWN_TYPE;
 
 	if (oi->delta_base_oid)
 		oidclr(oi->delta_base_oid);
@@ -1445,11 +1428,9 @@ static int loose_object_info(struct repository *r,
 
 	if (oi->disk_sizep)
 		*oi->disk_sizep = mapsize;
-	if ((flags & OBJECT_INFO_ALLOW_UNKNOWN_TYPE)) {
-		if (unpack_loose_header_to_strbuf(&stream, map, mapsize, hdr, sizeof(hdr), &hdrbuf) < 0)
-			status = error(_("unable to unpack %s header with --allow-unknown-type"),
-				       oid_to_hex(oid));
-	} else if (unpack_loose_header(&stream, map, mapsize, hdr, sizeof(hdr)) < 0)
+
+	if (unpack_loose_header(&stream, map, mapsize, hdr, sizeof(hdr),
+				allow_unknown ? &hdrbuf : NULL) < 0)
 		status = error(_("unable to unpack %s header"),
 			       oid_to_hex(oid));
 	if (status < 0)
@@ -2550,7 +2531,8 @@ int read_loose_object(const char *path,
 		goto out;
 	}
 
-	if (unpack_loose_header(&stream, map, mapsize, hdr, sizeof(hdr)) < 0) {
+	if (unpack_loose_header(&stream, map, mapsize, hdr, sizeof(hdr),
+				NULL) < 0) {
 		error(_("unable to unpack header of %s"), path);
 		goto out;
 	}
diff --git a/streaming.c b/streaming.c
@@ -233,7 +233,8 @@ static int open_istream_loose(struct git_istream *st, struct repository *r,
 				 st->u.loose.mapped,
 				 st->u.loose.mapsize,
 				 st->u.loose.hdr,
-				 sizeof(st->u.loose.hdr)) < 0) ||
+				 sizeof(st->u.loose.hdr),
+				 NULL) < 0) ||
 	    (parse_loose_header(st->u.loose.hdr, &oi, 0) < 0)) {
 		git_inflate_end(&st->z);
 		munmap(st->u.loose.mapped, st->u.loose.mapsize);
