Improvements to sha1_file

index 59a4ed2ed..a52b27541 100644
@@ -2277,9 +2277,18 @@ int packed_object_info(struct packed_git *p, off_t obj_offset,
 		*oi->disk_sizep = revidx[1].offset - obj_offset;
 	}
 
-	if (oi->typep) {
-		*oi->typep = packed_to_object_type(p, obj_offset, type, &w_curs, curpos);
-		if (*oi->typep < 0) {
+	if (oi->typep || oi->typename) {
+		enum object_type ptot;
+		ptot = packed_to_object_type(p, obj_offset, type, &w_curs,
+					     curpos);
+		if (oi->typep)
+			*oi->typep = ptot;
+		if (oi->typename) {
+			const char *tn = typename(ptot);
+			if (tn)
+				strbuf_addstr(oi->typename, tn);
+		}
+		if (ptot < 0) {
 			type = OBJ_BAD;
 			goto out;
 		}

@@ -2960,7 +2969,6 @@ int sha1_object_info_extended(const unsigned char *sha1, struct object_info *oi,
 	struct cached_object *co;
 	struct pack_entry e;
 	int rtype;
-	enum object_type real_type;
 	const unsigned char *real = lookup_replace_object_extended(sha1, flags);
 
 	co = find_cached_object(real);

@@ -2992,18 +3000,9 @@ int sha1_object_info_extended(const unsigned char *sha1, struct object_info *oi,
 			return -1;
 	}
 
-	/*
-	 * packed_object_info() does not follow the delta chain to
-	 * find out the real type, unless it is given oi->typep.
-	 */
-	if (oi->typename && !oi->typep)
-		oi->typep = &real_type;
-
 	rtype = packed_object_info(e.p, e.offset, oi);
 	if (rtype < 0) {
 		mark_bad_packed_object(e.p, real);
-		if (oi->typep == &real_type)
-			oi->typep = NULL;
 		return sha1_object_info_extended(real, oi, 0);
 	} else if (in_delta_base_cache(e.p, e.offset)) {
 		oi->whence = OI_DBCACHED;

@@ -3014,10 +3013,6 @@ int sha1_object_info_extended(const unsigned char *sha1, struct object_info *oi,
 		oi->u.packed.is_delta = (rtype == OBJ_REF_DELTA ||
 					 rtype == OBJ_OFS_DELTA);
 	}
-	if (oi->typename)
-		strbuf_addstr(oi->typename, typename(*oi->typep));
-	if (oi->typep == &real_type)
-		oi->typep = NULL;
 
 	return 0;
 }

index 4bffd7a2d..5bb16c045 100644
@@ -75,7 +75,8 @@ static int cat_one_file(int opt, const char *exp_type, const char *obj_name,
 	switch (opt) {
 	case 't':
 		oi.typename = &sb;
-		if (sha1_object_info_extended(oid.hash, &oi, flags) < 0)
+		if (sha1_object_info_extended(oid.hash, NULL, NULL, &oi,
+					      flags) < 0)
 			die("git cat-file: could not get object info");
 		if (sb.len) {
 			printf("%s\n", sb.buf);

@@ -85,8 +86,8 @@ static int cat_one_file(int opt, const char *exp_type, const char *obj_name,
 		break;
 
 	case 's':
-		oi.sizep = &size;
-		if (sha1_object_info_extended(oid.hash, &oi, flags) < 0)
+		if (sha1_object_info_extended(oid.hash, NULL, &size, &oi,
+					      flags) < 0)
 			die("git cat-file: could not get object info");
 		printf("%lu\n", size);
 		return 0;

@@ -194,10 +195,12 @@ struct expand_data {
 	int split_on_whitespace;
 
 	/*
-	 * After a mark_query run, this object_info is set up to be
-	 * passed to sha1_object_info_extended. It will point to the data
+	 * After a mark_query run, these fields are set up to be
+	 * passed to sha1_object_info_extended. They will point to the data
 	 * elements above, so you can retrieve the response from there.
 	 */
+	enum object_type *typep;
+	unsigned long *sizep;
 	struct object_info info;
 
 	/*

@@ -224,12 +227,12 @@ static void expand_atom(struct strbuf *sb, const char *atom, int len,
 			strbuf_addstr(sb, oid_to_hex(&data->oid));
 	} else if (is_atom("objecttype", atom, len)) {
 		if (data->mark_query)
-			data->info.typep = &data->type;
+			data->typep = &data->type;
 		else
 			strbuf_addstr(sb, typename(data->type));
 	} else if (is_atom("objectsize", atom, len)) {
 		if (data->mark_query)
-			data->info.sizep = &data->size;
+			data->sizep = &data->size;
 		else
 			strbuf_addf(sb, "%lu", data->size);
 	} else if (is_atom("objectsize:disk", atom, len)) {

@@ -280,7 +283,7 @@ static void print_object_or_die(struct batch_options *opt, struct expand_data *d
 {
 	const struct object_id *oid = &data->oid;
 
-	assert(data->info.typep);
+	assert(data->typep);
 
 	if (data->type == OBJ_BLOB) {
 		if (opt->buffer_output)

@@ -323,7 +326,7 @@ static void print_object_or_die(struct batch_options *opt, struct expand_data *d
 			die("object %s disappeared", oid_to_hex(oid));
 		if (type != data->type)
 			die("object %s changed type!?", oid_to_hex(oid));
-		if (data->info.sizep && size != data->size)
+		if (data->sizep && size != data->size)
 			die("object %s changed size!?", oid_to_hex(oid));
 
 		batch_write(opt, contents, size);

@@ -337,7 +340,8 @@ static void batch_object_write(const char *obj_name, struct batch_options *opt,
 	struct strbuf buf = STRBUF_INIT;
 
 	if (!data->skip_object_info &&
-	    sha1_object_info_extended(data->oid.hash, &data->info, LOOKUP_REPLACE_OBJECT) < 0) {
+	    sha1_object_info_extended(data->oid.hash, data->typep, data->sizep,
+				      &data->info, LOOKUP_REPLACE_OBJECT) < 0) {
 		printf("%s missing\n",
 		       obj_name ? obj_name : oid_to_hex(&data->oid));
 		fflush(stdout);

@@ -454,7 +458,8 @@ static int batch_objects(struct batch_options *opt)
 
 	if (opt->all_objects) {
 		struct object_info empty = OBJECT_INFO_INIT;
-		if (!memcmp(&data.info, &empty, sizeof(empty)))
+		if (!data.typep && !data.sizep &&
+		    !memcmp(&data.info, &empty, sizeof(empty)))
 			data.skip_object_info = 1;
 	}
 

@@ -463,7 +468,7 @@ static int batch_objects(struct batch_options *opt)
 	 * since we will want to decide whether or not to stream.
 	 */
 	if (opt->print_contents)
-		data.info.typep = &data.type;
+		data.typep = &data.type;
 
 	if (opt->all_objects) {
 		struct oid_array sa = OID_ARRAY_INIT;

index f672225de..9cecc82b2 100644
@@ -1557,9 +1557,8 @@ static void drop_reused_delta(struct object_entry *entry)
 	entry->delta = NULL;
 	entry->depth = 0;
 
-	oi.sizep = &entry->size;
-	oi.typep = &entry->type;
-	if (packed_object_info(entry->in_pack, entry->in_pack_offset, &oi) < 0) {
+	if (packed_object_info(entry->in_pack, entry->in_pack_offset,
+			       &entry->type, &entry->size, &oi) < 0) {
 		/*
 		 * We failed to get the info from this pack for some reason;
 		 * fall back to sha1_object_info, which may find another copy.

index 4d92aae0e..bf09962e4 100644
@@ -1830,8 +1830,6 @@ extern int for_each_packed_object(each_packed_object_fn, void *, unsigned flags)
 
 struct object_info {
 	/* Request */
-	enum object_type *typep;
-	unsigned long *sizep;
 	off_t *disk_sizep;
 	unsigned char *delta_base_sha1;
 	struct strbuf *typename;

@@ -1866,8 +1864,8 @@ struct object_info {
  */
 #define OBJECT_INFO_INIT {NULL}
 
-extern int sha1_object_info_extended(const unsigned char *, struct object_info *, unsigned flags);
-extern int packed_object_info(struct packed_git *pack, off_t offset, struct object_info *);
+extern int sha1_object_info_extended(const unsigned char *, enum object_type *typep, unsigned long *sizep, struct object_info *, unsigned flags);
+extern int packed_object_info(struct packed_git *pack, off_t offset, enum object_type *typep, unsigned long *sizep, struct object_info *);
 
 /* Dumb servers support */
 extern int update_server_info(int);

180 lines not on this page · raw message

index 9afa66b8b..ee5d1f684 100644
@@ -111,9 +111,7 @@ static enum input_source istream_source(const unsigned char *sha1,
 	unsigned long size;
 	int status;
 
-	oi->typep = type;
-	oi->sizep = &size;
-	status = sha1_object_info_extended(sha1, oi, 0);
+	status = sha1_object_info_extended(sha1, type, &size, oi, 0);
 	if (status < 0)
 		return stream_error;
 

index ac4d77ccc..deb08b0f1 100644
@@ -1959,7 +1959,7 @@ static int parse_sha1_header_extended(const char *hdr, enum object_type *typep,
 	}
 
 	type = type_from_string_gently(type_buf, type_len, 1);
-	if (oi->typename)
+	if (oi && oi->typename)
 		strbuf_add(oi->typename, type_buf, type_len);
 	/*
 	 * Set type to 0 if its an unknown object and

@@ -2001,12 +2001,13 @@ static int parse_sha1_header_extended(const char *hdr, enum object_type *typep,
 
 int parse_sha1_header(const char *hdr, unsigned long *sizep)
 {
-	struct object_info oi = OBJECT_INFO_INIT;
-	return parse_sha1_header_extended(hdr, NULL, sizep, &oi,
+	return parse_sha1_header_extended(hdr, NULL, sizep, NULL,
 					  LOOKUP_REPLACE_OBJECT);
 }
 
-static void *unpack_sha1_file(void *map, unsigned long mapsize, enum object_type *type, unsigned long *size, const unsigned char *sha1)
+static void *unpack_sha1_file(void *map, unsigned long mapsize,
+			      enum object_type *type, unsigned long *size,
+			      const unsigned char *sha1)
 {
 	int ret;
 	git_zstream stream;

@@ -2274,18 +2275,18 @@ int packed_object_info(struct packed_git *p, off_t obj_offset,
 		}
 	}
 
-	if (oi->disk_sizep) {
+	if (oi && oi->disk_sizep) {
 		struct revindex_entry *revidx = find_pack_revindex(p, obj_offset);
 		*oi->disk_sizep = revidx[1].offset - obj_offset;
 	}
 
-	if (typep || oi->typename) {
+	if (typep || (oi && oi->typename)) {
 		enum object_type ptot;
 		ptot = packed_to_object_type(p, obj_offset, type, &w_curs,
 					     curpos);
 		if (typep)
 			*typep = ptot;
-		if (oi->typename) {
+		if (oi && oi->typename) {
 			const char *tn = typename(ptot);
 			if (tn)
 				strbuf_addstr(oi->typename, tn);

@@ -2296,7 +2297,7 @@ int packed_object_info(struct packed_git *p, off_t obj_offset,
 		}
 	}
 
-	if (oi->delta_base_sha1) {
+	if (oi && oi->delta_base_sha1) {
 		if (type == OBJ_OFS_DELTA || type == OBJ_REF_DELTA) {
 			const unsigned char *base;
 

@@ -2438,8 +2439,10 @@ static void *cache_or_unpack_entry(struct packed_git *p, off_t base_offset,
 	if (!ent)
 		return unpack_entry(p, base_offset, type, base_size);
 
-	*type = ent->type;
-	*base_size = ent->size;
+	if (type)
+		*type = ent->type;
+	if (base_size)
+		*base_size = ent->size;
 	return xmemdupz(ent->data, ent->size);
 }
 

@@ -2907,43 +2910,20 @@ struct packed_git *find_sha1_pack(const unsigned char *sha1,
 }
 
 static int sha1_loose_object_info(const unsigned char *sha1,
+				  void *map, unsigned long mapsize,
 				  enum object_type *typep,
 				  unsigned long *sizep,
 				  struct object_info *oi,
 				  int flags)
 {
 	int status = 0;
-	unsigned long mapsize;
-	void *map;
 	git_zstream stream;
 	char hdr[32];
 	struct strbuf hdrbuf = STRBUF_INIT;
 
-	if (oi->delta_base_sha1)
+	if (oi && oi->delta_base_sha1)
 		hashclr(oi->delta_base_sha1);
-
-	/*
-	 * If we don't care about type or size, then we don't
-	 * need to look inside the object at all. Note that we
-	 * do not optimize out the stat call, even if the
-	 * caller doesn't care about the disk-size, since our
-	 * return value implicitly indicates whether the
-	 * object even exists.
-	 */
-	if (!typep && !oi->typename && !sizep) {
-		const char *path;
-		struct stat st;
-		if (stat_sha1_file(sha1, &st, &path) < 0)
-			return -1;
-		if (oi->disk_sizep)
-			*oi->disk_sizep = st.st_size;
-		return 0;
-	}
-
-	map = map_sha1_file(sha1, &mapsize);
-	if (!map)
-		return -1;
-	if (oi->disk_sizep)
+	if (oi && oi->disk_sizep)
 		*oi->disk_sizep = mapsize;
 	if ((flags & LOOKUP_UNKNOWN_OBJECT)) {
 		if (unpack_sha1_header_to_strbuf(&stream, map, mapsize, hdr, sizeof(hdr), &hdrbuf) < 0)

@@ -2963,29 +2943,25 @@ static int sha1_loose_object_info(const unsigned char *sha1,
 							flags)) < 0)
 		status = error("unable to parse %s header", sha1_to_hex(sha1));
 	git_inflate_end(&stream);
-	munmap(map, mapsize);
 	if (status && typep)
 		*typep = status;
 	strbuf_release(&hdrbuf);
 	return (status < 0) ? status : 0;
 }
 
-int sha1_object_info_extended(const unsigned char *sha1,
-			      enum object_type *typep,
-			      unsigned long *sizep, struct object_info *oi,
-			      unsigned flags)
+static int get_cached_object(const unsigned char *sha1, enum object_type *typep,
+			     unsigned long *sizep, struct object_info *oi,
+			     void **buf)
 {
-	struct cached_object *co;
-	struct pack_entry e;
-	int rtype;
-	const unsigned char *real = lookup_replace_object_extended(sha1, flags);
+	struct cached_object *co = find_cached_object(sha1);
+	if (!co)
+		return 0;
 
-	co = find_cached_object(real);
-	if (co) {
-		if (typep)
-			*typep = co->type;
-		if (sizep)
-			*sizep = co->size;
+	if (typep)
+		*typep = co->type;
+	if (sizep)
+		*sizep = co->size;
+	if (oi) {
 		if (oi->disk_sizep)
 			*(oi->disk_sizep) = 0;
 		if (oi->delta_base_sha1)

@@ -2993,75 +2969,160 @@ int sha1_object_info_extended(const unsigned char *sha1,
 		if (oi->typename)
 			strbuf_addstr(oi->typename, typename(co->type));
 		oi->whence = OI_CACHED;
+	}
+	if (buf)
+		*buf = xmemdupz(co->buf, co->size);
+	return 1;
+}
+
+static int get_loose_object(const unsigned char *sha1, enum object_type *typep,
+			    unsigned long *sizep, struct object_info *oi,
+			    void **buf, int tolerate_bad_type)
+{
+	const char *path;
+	struct stat st;
+
+	if (!typep && !sizep && !oi && !buf)
+		return has_loose_object(sha1);
+
+	if (buf || typep || sizep || (oi && oi->typename)) {
+		/* Need to look inside the object */
+		unsigned long mapsize;
+		int ret = 1;
+		void *map = map_sha1_file(sha1, &mapsize);
+		if (!map)
+			return 0;
+		if (buf) {
+			*buf = unpack_sha1_file(map, mapsize, typep, sizep,
+						sha1);
+			if (!*buf)
+				return 0;
+			/* avoid redundant type and size calculations */
+			typep = NULL;
+			sizep = NULL;
+		}
+		if (typep || sizep || oi) {
+			int f = tolerate_bad_type ? LOOKUP_UNKNOWN_OBJECT : 0;
+			if (sha1_loose_object_info(sha1, map, mapsize, typep,
+						   sizep, oi, f)) {
+				ret = 0;
+				goto cleanup;
+			}
+			if (oi)
+				oi->whence = OI_LOOSE;
+		}
+cleanup:
+		munmap(map, mapsize);
+		return ret;
+	}
+
+	/*
+	 * If we don't care about type or size, then we don't
+	 * need to look inside the object at all. Note that we
+	 * do not optimize out the stat call, even if the
+	 * caller doesn't care about the disk-size, since our
+	 * return value implicitly indicates whether the
+	 * object even exists.
+	 */
+	if (stat_sha1_file(sha1, &st, &path) < 0)
 		return 0;
+	if (oi) {
+		if (oi->disk_sizep)
+			*oi->disk_sizep = st.st_size;
+		oi->whence = OI_LOOSE;
 	}
+	return 1;
+}
 
-	if (!find_pack_entry(real, &e)) {
-		/* Most likely it's a loose object. */
-		if (!sha1_loose_object_info(real, typep, sizep, oi, flags)) {
-			oi->whence = OI_LOOSE;
+static int get_packed_object(struct pack_entry *e, enum object_type *typep,
+			     unsigned long *sizep, struct object_info *oi,
+			     void **buf)
+{
+	int rtype;
+	if (buf) {
+		*buf = cache_or_unpack_entry(e->p, e->offset, sizep, typep);
+		if (!*buf)
 			return 0;
+		/* avoid redundant type and size calculations */
+		typep = NULL;
+		sizep = NULL;
+	}
+	if (typep || sizep || oi) {
+		rtype = packed_object_info(e->p, e->offset, typep, sizep, oi);
+		if (rtype < 0)
+			return 0;
+	}
+	if (oi) {
+		if (in_delta_base_cache(e->p, e->offset)) {
+			oi->whence = OI_DBCACHED;
+		} else {
+			oi->whence = OI_PACKED;
+			oi->u.packed.offset = e->offset;
+			oi->u.packed.pack = e->p;
+			oi->u.packed.is_delta = (rtype == OBJ_REF_DELTA ||
+						 rtype == OBJ_OFS_DELTA);
 		}
+	}
+	return 1;
+}
+
+/* start at 1 << 5 to leave room for LOOKUP_ flags */
+#define GET_OBJECT_QUICK (1 << 5)
+#define GET_OBJECT_IGNORE_CACHED (1 << 6)
+static int get_object(const unsigned char *sha1, enum object_type *typep,
+		      unsigned long *sizep, struct object_info *oi,
+		      void **buf, unsigned flags)
+{
+	struct pack_entry e;
+	const unsigned char *real = lookup_replace_object_extended(sha1, flags);
+
+	if (!(flags & GET_OBJECT_IGNORE_CACHED) &&
+	    get_cached_object(real, typep, sizep, oi, buf))
+		return 1;
+
+	if (!find_pack_entry(real, &e)) {
+		/* Most likely it's a loose object. */
+		if (get_loose_object(real, typep, sizep, oi, buf,
+				     flags & LOOKUP_UNKNOWN_OBJECT))
+			return 1;
 
 		/* Not a loose object; someone else may have just packed it. */
+		if (flags & GET_OBJECT_QUICK)
+			return 0;
 		reprepare_packed_git();
 		if (!find_pack_entry(real, &e))
-			return -1;
+			return 0;
 	}
 
-	rtype = packed_object_info(e.p, e.offset, typep, sizep, oi);
-	if (rtype < 0) {
-		mark_bad_packed_object(e.p, real);
-		return sha1_object_info_extended(real, typep, sizep, oi, 0);
-	} else if (in_delta_base_cache(e.p, e.offset)) {
-		oi->whence = OI_DBCACHED;
-	} else {
-		oi->whence = OI_PACKED;
-		oi->u.packed.offset = e.offset;
-		oi->u.packed.pack = e.p;
-		oi->u.packed.is_delta = (rtype == OBJ_REF_DELTA ||
-					 rtype == OBJ_OFS_DELTA);
-	}
+	if (get_packed_object(&e, typep, sizep, oi, buf))
+		return 1;
 
-	return 0;
+	/*
+	 * Try to fetch the required object anyway from another pack or loose.
+	 * This should happen only in the presence of a corrupted
+	 * pack, and is better than failing outright.
+	 */
+	mark_bad_packed_object(e.p, real);
+	return get_object(real, typep, sizep, oi, buf, flags);
+}
+
+int sha1_object_info_extended(const unsigned char *sha1,
+			      enum object_type *typep, unsigned long *sizep,
+			      struct object_info *oi, unsigned flags)
+{
+	return get_object(sha1, typep, sizep, oi, NULL, flags) ? 0 : -1;
 }
 
 /* returns enum object_type or negative */
 int sha1_object_info(const unsigned char *sha1, unsigned long *sizep)
 {
 	enum object_type type;
-	struct object_info oi = OBJECT_INFO_INIT;
-
-	if (sha1_object_info_extended(sha1, &type, sizep, &oi,
+	if (sha1_object_info_extended(sha1, &type, sizep, NULL,
 				      LOOKUP_REPLACE_OBJECT) < 0)
 		return -1;
 	return type;
 }
 
-static void *read_packed_sha1(const unsigned char *sha1,
-			      enum object_type *type, unsigned long *size)
-{
-	struct pack_entry e;
-	void *data;
-
-	if (!find_pack_entry(sha1, &e))
-		return NULL;
-	data = cache_or_unpack_entry(e.p, e.offset, size, type);
-	if (!data) {
-		/*
-		 * We're probably in deep shit, but let's try to fetch
-		 * the required object anyway from another pack or loose.
-		 * This should happen only in the presence of a corrupted
-		 * pack, and is better than failing outright.
-		 */
-		error("failed to read object %s at offset %"PRIuMAX" from %s",
-		      sha1_to_hex(sha1), (uintmax_t)e.offset, e.p->pack_name);
-		mark_bad_packed_object(e.p, sha1);
-		data = read_object(sha1, type, size);
-	}
-	return data;
-}
-
 int pretend_sha1_file(void *buf, unsigned long len, enum object_type type,
 		      unsigned char *sha1)
 {

@@ -3083,28 +3144,10 @@ int pretend_sha1_file(void *buf, unsigned long len, enum object_type type,
 static void *read_object(const unsigned char *sha1, enum object_type *type,
 			 unsigned long *size)
 {
-	unsigned long mapsize;
-	void *map, *buf;
-	struct cached_object *co;
-
-	co = find_cached_object(sha1);
-	if (co) {
-		*type = co->type;
-		*size = co->size;
-		return xmemdupz(co->buf, co->size);
-	}
-
-	buf = read_packed_sha1(sha1, type, size);
-	if (buf)
-		return buf;
-	map = map_sha1_file(sha1, &mapsize);
-	if (map) {
-		buf = unpack_sha1_file(map, mapsize, type, size, sha1);
-		munmap(map, mapsize);
+	void *buf;
+	if (get_object(sha1, type, size, NULL, &buf, 0))
 		return buf;
-	}
-	reprepare_packed_git();
-	return read_packed_sha1(sha1, type, size);
+	return NULL;
 }
 
 /*

@@ -3456,7 +3499,7 @@ int force_object_loose(const unsigned char *sha1, time_t mtime)
 
 	if (has_loose_object(sha1))
 		return 0;
-	buf = read_packed_sha1(sha1, &type, &len);
+	buf = read_object(sha1, &type, &len);
 	if (!buf)
 		return error("cannot read sha1_file for %s", sha1_to_hex(sha1));
 	hdrlen = xsnprintf(hdr, sizeof(hdr), "%s %lu", typename(type), len) + 1;

@@ -3482,18 +3525,11 @@ int has_sha1_pack(const unsigned char *sha1)
 
 int has_sha1_file_with_flags(const unsigned char *sha1, int flags)
 {
-	struct pack_entry e;
-
+	int f = GET_OBJECT_IGNORE_CACHED |
+		(flags & HAS_SHA1_QUICK ? GET_OBJECT_QUICK : 0);
 	if (!startup_info->have_repository)
 		return 0;
-	if (find_pack_entry(sha1, &e))
-		return 1;
-	if (has_loose_object(sha1))
-		return 1;
-	if (flags & HAS_SHA1_QUICK)
-		return 0;
-	reprepare_packed_git();
-	return find_pack_entry(sha1, &e);
+	return get_object(sha1, NULL, NULL, NULL, NULL, f);
 }
 
 int has_object_file(const struct object_id *oid)

index cb2ba6cd1..6f10d6034 100644
@@ -37,6 +37,7 @@ static int verbose;
 static int show_progress = -1;
 static int show_dangling = 1;
 static int name_objects;
+static int missing_blob_ok;
 #define ERROR_OBJECT 01
 #define ERROR_REACHABLE 02
 #define ERROR_PACK 04

@@ -93,6 +94,9 @@ static int fsck_config(const char *var, const char *value, void *cb)
 		return 0;
 	}
 
+	if (!strcmp(var, "core.missingblobcommand"))
+		missing_blob_ok = 1;
+
 	return git_default_config(var, value, cb);
 }
 

@@ -222,6 +226,9 @@ static void check_reachable_object(struct object *obj)
 	if (!(obj->flags & HAS_OBJ)) {
 		if (has_sha1_pack(obj->oid.hash))
 			return; /* it is in pack - forget about it */
+		if (missing_blob_ok && obj->type == OBJ_BLOB &&
+		    has_missing_blob(obj->oid.hash, NULL))
+			return;
 		printf("missing %s %s\n", printable_type(obj),
 			describe_object(obj));
 		errors_found |= ERROR_REACHABLE;

index bf09962e4..b9221b7e2 100644
@@ -1867,6 +1867,12 @@ struct object_info {
 extern int sha1_object_info_extended(const unsigned char *, enum object_type *typep, unsigned long *sizep, struct object_info *, unsigned flags);
 extern int packed_object_info(struct packed_git *pack, off_t offset, enum object_type *typep, unsigned long *sizep, struct object_info *);
 
+/*
+ * Returns 1 if sha1 is the hash of a known missing blob. If size is not NULL,
+ * also returns its size.
+ */
+extern int has_missing_blob(const unsigned char *sha1, unsigned long *size);
+
 /* Dumb servers support */
 extern int update_server_info(int);
 

180 lines not on this page · raw message

index 59a4ed2ed..a52b27541 100644
@@ -2277,9 +2277,18 @@ int packed_object_info(struct packed_git *p, off_t obj_offset,
 		*oi->disk_sizep = revidx[1].offset - obj_offset;
 	}
 
-	if (oi->typep) {
-		*oi->typep = packed_to_object_type(p, obj_offset, type, &w_curs, curpos);
-		if (*oi->typep < 0) {
+	if (oi->typep || oi->typename) {
+		enum object_type ptot;
+		ptot = packed_to_object_type(p, obj_offset, type, &w_curs,
+					     curpos);
+		if (oi->typep)
+			*oi->typep = ptot;
+		if (oi->typename) {
+			const char *tn = typename(ptot);
+			if (tn)
+				strbuf_addstr(oi->typename, tn);
+		}
+		if (ptot < 0) {
 			type = OBJ_BAD;
 			goto out;
 		}

@@ -2960,7 +2969,6 @@ int sha1_object_info_extended(const unsigned char *sha1, struct object_info *oi,
 	struct cached_object *co;
 	struct pack_entry e;
 	int rtype;
-	enum object_type real_type;
 	const unsigned char *real = lookup_replace_object_extended(sha1, flags);
 
 	co = find_cached_object(real);

@@ -2992,18 +3000,9 @@ int sha1_object_info_extended(const unsigned char *sha1, struct object_info *oi,
 			return -1;
 	}
 
-	/*
-	 * packed_object_info() does not follow the delta chain to
-	 * find out the real type, unless it is given oi->typep.
-	 */
-	if (oi->typename && !oi->typep)
-		oi->typep = &real_type;
-
 	rtype = packed_object_info(e.p, e.offset, oi);
 	if (rtype < 0) {
 		mark_bad_packed_object(e.p, real);
-		if (oi->typep == &real_type)
-			oi->typep = NULL;
 		return sha1_object_info_extended(real, oi, 0);
 	} else if (in_delta_base_cache(e.p, e.offset)) {
 		oi->whence = OI_DBCACHED;

@@ -3014,10 +3013,6 @@ int sha1_object_info_extended(const unsigned char *sha1, struct object_info *oi,
 		oi->u.packed.is_delta = (rtype == OBJ_REF_DELTA ||
 					 rtype == OBJ_OFS_DELTA);
 	}
-	if (oi->typename)
-		strbuf_addstr(oi->typename, typename(*oi->typep));
-	if (oi->typep == &real_type)
-		oi->typep = NULL;
 
 	return 0;
 }

index a52b27541..a158907d1 100644
@@ -2239,116 +2239,6 @@ static enum object_type packed_to_object_type(struct packed_git *p,
 	goto out;
 }
 
-int packed_object_info(struct packed_git *p, off_t obj_offset,
-		       struct object_info *oi)
-{
-	struct pack_window *w_curs = NULL;
-	unsigned long size;
-	off_t curpos = obj_offset;
-	enum object_type type;
-
-	/*
-	 * We always get the representation type, but only convert it to
-	 * a "real" type later if the caller is interested.
-	 */
-	type = unpack_object_header(p, &w_curs, &curpos, &size);
-
-	if (oi->sizep) {
-		if (type == OBJ_OFS_DELTA || type == OBJ_REF_DELTA) {
-			off_t tmp_pos = curpos;
-			off_t base_offset = get_delta_base(p, &w_curs, &tmp_pos,
-							   type, obj_offset);
-			if (!base_offset) {
-				type = OBJ_BAD;
-				goto out;
-			}
-			*oi->sizep = get_size_from_delta(p, &w_curs, tmp_pos);
-			if (*oi->sizep == 0) {
-				type = OBJ_BAD;
-				goto out;
-			}
-		} else {
-			*oi->sizep = size;
-		}
-	}
-
-	if (oi->disk_sizep) {
-		struct revindex_entry *revidx = find_pack_revindex(p, obj_offset);
-		*oi->disk_sizep = revidx[1].offset - obj_offset;
-	}
-
-	if (oi->typep || oi->typename) {
-		enum object_type ptot;
-		ptot = packed_to_object_type(p, obj_offset, type, &w_curs,
-					     curpos);
-		if (oi->typep)
-			*oi->typep = ptot;
-		if (oi->typename) {
-			const char *tn = typename(ptot);
-			if (tn)
-				strbuf_addstr(oi->typename, tn);
-		}
-		if (ptot < 0) {
-			type = OBJ_BAD;
-			goto out;
-		}
-	}
-
-	if (oi->delta_base_sha1) {
-		if (type == OBJ_OFS_DELTA || type == OBJ_REF_DELTA) {
-			const unsigned char *base;
-
-			base = get_delta_base_sha1(p, &w_curs, curpos,
-						   type, obj_offset);
-			if (!base) {
-				type = OBJ_BAD;
-				goto out;
-			}
-
-			hashcpy(oi->delta_base_sha1, base);
-		} else
-			hashclr(oi->delta_base_sha1);
-	}
-
-out:
-	unuse_pack(&w_curs);
-	return type;
-}
-
-static void *unpack_compressed_entry(struct packed_git *p,
-				    struct pack_window **w_curs,
-				    off_t curpos,
-				    unsigned long size)
-{
-	int st;
-	git_zstream stream;
-	unsigned char *buffer, *in;
-
-	buffer = xmallocz_gently(size);
-	if (!buffer)
-		return NULL;
-	memset(&stream, 0, sizeof(stream));
-	stream.next_out = buffer;
-	stream.avail_out = size + 1;
-
-	git_inflate_init(&stream);
-	do {
-		in = use_pack(p, w_curs, curpos, &stream.avail_in);
-		stream.next_in = in;
-		st = git_inflate(&stream, Z_FINISH);
-		if (!stream.avail_out)
-			break; /* the payload is larger than it should be */
-		curpos += stream.next_in - in;
-	} while (st == Z_OK || st == Z_BUF_ERROR);
-	git_inflate_end(&stream);
-	if ((st != Z_STREAM_END) || stream.total_out != size) {
-		free(buffer);
-		return NULL;
-	}
-
-	return buffer;
-}
-
 static struct hashmap delta_base_cache;
 static size_t delta_base_cached;
 

@@ -2486,6 +2376,122 @@ static void add_delta_base_cache(struct packed_git *p, off_t base_offset,
 	hashmap_add(&delta_base_cache, ent);
 }
 
+int packed_object_info(struct packed_git *p, off_t obj_offset,
+		       struct object_info *oi)
+{
+	struct pack_window *w_curs = NULL;
+	unsigned long size;
+	off_t curpos = obj_offset;
+	enum object_type type;
+
+	/*
+	 * We always get the representation type, but only convert it to
+	 * a "real" type later if the caller is interested.
+	 */
+	type = unpack_object_header(p, &w_curs, &curpos, &size);
+
+	if (oi->sizep) {
+		if (type == OBJ_OFS_DELTA || type == OBJ_REF_DELTA) {
+			off_t tmp_pos = curpos;
+			off_t base_offset = get_delta_base(p, &w_curs, &tmp_pos,
+							   type, obj_offset);
+			if (!base_offset) {
+				type = OBJ_BAD;
+				goto out;
+			}
+			*oi->sizep = get_size_from_delta(p, &w_curs, tmp_pos);
+			if (*oi->sizep == 0) {
+				type = OBJ_BAD;
+				goto out;
+			}
+		} else {
+			*oi->sizep = size;
+		}
+	}
+
+	if (oi->disk_sizep) {
+		struct revindex_entry *revidx = find_pack_revindex(p, obj_offset);
+		*oi->disk_sizep = revidx[1].offset - obj_offset;
+	}
+
+	if (oi->typep || oi->typename) {
+		enum object_type ptot;
+		ptot = packed_to_object_type(p, obj_offset, type, &w_curs,
+					     curpos);
+		if (oi->typep)
+			*oi->typep = ptot;
+		if (oi->typename) {
+			const char *tn = typename(ptot);
+			if (tn)
+				strbuf_addstr(oi->typename, tn);
+		}
+		if (ptot < 0) {
+			type = OBJ_BAD;
+			goto out;
+		}
+	}
+
+	if (oi->delta_base_sha1) {
+		if (type == OBJ_OFS_DELTA || type == OBJ_REF_DELTA) {
+			const unsigned char *base;
+
+			base = get_delta_base_sha1(p, &w_curs, curpos,
+						   type, obj_offset);
+			if (!base) {
+				type = OBJ_BAD;
+				goto out;
+			}
+
+			hashcpy(oi->delta_base_sha1, base);
+		} else
+			hashclr(oi->delta_base_sha1);
+	}
+
+	oi->whence = OI_PACKED;
+	oi->u.packed.offset = obj_offset;
+	oi->u.packed.pack = p;
+	oi->u.packed.is_delta = (type == OBJ_REF_DELTA ||
+				 type == OBJ_OFS_DELTA);
+
+out:
+	unuse_pack(&w_curs);
+	return type;
+}
+
+static void *unpack_compressed_entry(struct packed_git *p,
+				    struct pack_window **w_curs,
+				    off_t curpos,
+				    unsigned long size)
+{
+	int st;
+	git_zstream stream;
+	unsigned char *buffer, *in;
+
+	buffer = xmallocz_gently(size);
+	if (!buffer)
+		return NULL;
+	memset(&stream, 0, sizeof(stream));
+	stream.next_out = buffer;
+	stream.avail_out = size + 1;
+
+	git_inflate_init(&stream);
+	do {
+		in = use_pack(p, w_curs, curpos, &stream.avail_in);
+		stream.next_in = in;
+		st = git_inflate(&stream, Z_FINISH);
+		if (!stream.avail_out)
+			break; /* the payload is larger than it should be */
+		curpos += stream.next_in - in;
+	} while (st == Z_OK || st == Z_BUF_ERROR);
+	git_inflate_end(&stream);
+	if ((st != Z_STREAM_END) || stream.total_out != size) {
+		free(buffer);
+		return NULL;
+	}
+
+	return buffer;
+}
+
 static void *read_object(const unsigned char *sha1, enum object_type *type,
 			 unsigned long *size);
 

index 4d92aae0e..3c85867c3 100644
@@ -1835,6 +1835,7 @@ struct object_info {
 	off_t *disk_sizep;
 	unsigned char *delta_base_sha1;
 	struct strbuf *typename;
+	void **contentp;
 
 	/* Response */
 	enum {

@@ -1866,6 +1867,12 @@ struct object_info {
  */
 #define OBJECT_INFO_INIT {NULL}
 
+/*
+ * sha1_object_info_extended() supports the LOOKUP_ flags and the OBJECT_INFO_
+ * flags.
+ */
+#define OBJECT_INFO_QUICK 4
+#define OBJECT_INFO_SKIP_CACHED 8
 extern int sha1_object_info_extended(const unsigned char *, struct object_info *, unsigned flags);
 extern int packed_object_info(struct packed_git *pack, off_t offset, struct object_info *);
 

233 lines not on this page · raw message

index cb2ba6cd1..6f10d6034 100644
@@ -37,6 +37,7 @@ static int verbose;
 static int show_progress = -1;
 static int show_dangling = 1;
 static int name_objects;
+static int missing_blob_ok;
 #define ERROR_OBJECT 01
 #define ERROR_REACHABLE 02
 #define ERROR_PACK 04

@@ -93,6 +94,9 @@ static int fsck_config(const char *var, const char *value, void *cb)
 		return 0;
 	}
 
+	if (!strcmp(var, "core.missingblobcommand"))
+		missing_blob_ok = 1;
+
 	return git_default_config(var, value, cb);
 }
 

@@ -222,6 +226,9 @@ static void check_reachable_object(struct object *obj)
 	if (!(obj->flags & HAS_OBJ)) {
 		if (has_sha1_pack(obj->oid.hash))
 			return; /* it is in pack - forget about it */
+		if (missing_blob_ok && obj->type == OBJ_BLOB &&
+		    has_missing_blob(obj->oid.hash, NULL))
+			return;
 		printf("missing %s %s\n", printable_type(obj),
 			describe_object(obj));
 		errors_found |= ERROR_REACHABLE;

index 3c85867c3..2853b39c4 100644
@@ -1876,6 +1876,12 @@ struct object_info {
 extern int sha1_object_info_extended(const unsigned char *, struct object_info *, unsigned flags);
 extern int packed_object_info(struct packed_git *pack, off_t offset, struct object_info *);
 
+/*
+ * Returns 1 if sha1 is the hash of a known missing blob. If size is not NULL,
+ * also returns its size.
+ */
+extern int has_missing_blob(const unsigned char *sha1, unsigned long *size);
+
 /* Dumb servers support */
 extern int update_server_info(int);
 

189 lines not on this page · raw message

index 59a4ed2ed..a52b27541 100644
@@ -2277,9 +2277,18 @@ int packed_object_info(struct packed_git *p, off_t obj_offset,
 		*oi->disk_sizep = revidx[1].offset - obj_offset;
 	}
 
-	if (oi->typep) {
-		*oi->typep = packed_to_object_type(p, obj_offset, type, &w_curs, curpos);
-		if (*oi->typep < 0) {
+	if (oi->typep || oi->typename) {
+		enum object_type ptot;
+		ptot = packed_to_object_type(p, obj_offset, type, &w_curs,
+					     curpos);
+		if (oi->typep)
+			*oi->typep = ptot;
+		if (oi->typename) {
+			const char *tn = typename(ptot);
+			if (tn)
+				strbuf_addstr(oi->typename, tn);
+		}
+		if (ptot < 0) {
 			type = OBJ_BAD;
 			goto out;
 		}

@@ -2960,7 +2969,6 @@ int sha1_object_info_extended(const unsigned char *sha1, struct object_info *oi,
 	struct cached_object *co;
 	struct pack_entry e;
 	int rtype;
-	enum object_type real_type;
 	const unsigned char *real = lookup_replace_object_extended(sha1, flags);
 
 	co = find_cached_object(real);

@@ -2992,18 +3000,9 @@ int sha1_object_info_extended(const unsigned char *sha1, struct object_info *oi,
 			return -1;
 	}
 
-	/*
-	 * packed_object_info() does not follow the delta chain to
-	 * find out the real type, unless it is given oi->typep.
-	 */
-	if (oi->typename && !oi->typep)
-		oi->typep = &real_type;
-
 	rtype = packed_object_info(e.p, e.offset, oi);
 	if (rtype < 0) {
 		mark_bad_packed_object(e.p, real);
-		if (oi->typep == &real_type)
-			oi->typep = NULL;
 		return sha1_object_info_extended(real, oi, 0);
 	} else if (in_delta_base_cache(e.p, e.offset)) {
 		oi->whence = OI_DBCACHED;

@@ -3014,10 +3013,6 @@ int sha1_object_info_extended(const unsigned char *sha1, struct object_info *oi,
 		oi->u.packed.is_delta = (rtype == OBJ_REF_DELTA ||
 					 rtype == OBJ_OFS_DELTA);
 	}
-	if (oi->typename)
-		strbuf_addstr(oi->typename, typename(*oi->typep));
-	if (oi->typep == &real_type)
-		oi->typep = NULL;
 
 	return 0;
 }

index a52b27541..a38319443 100644
@@ -2239,116 +2239,6 @@ static enum object_type packed_to_object_type(struct packed_git *p,
 	goto out;
 }
 
-int packed_object_info(struct packed_git *p, off_t obj_offset,
-		       struct object_info *oi)
-{
-	struct pack_window *w_curs = NULL;
-	unsigned long size;
-	off_t curpos = obj_offset;
-	enum object_type type;
-
-	/*
-	 * We always get the representation type, but only convert it to
-	 * a "real" type later if the caller is interested.
-	 */
-	type = unpack_object_header(p, &w_curs, &curpos, &size);
-
-	if (oi->sizep) {
-		if (type == OBJ_OFS_DELTA || type == OBJ_REF_DELTA) {
-			off_t tmp_pos = curpos;
-			off_t base_offset = get_delta_base(p, &w_curs, &tmp_pos,
-							   type, obj_offset);
-			if (!base_offset) {
-				type = OBJ_BAD;
-				goto out;
-			}
-			*oi->sizep = get_size_from_delta(p, &w_curs, tmp_pos);
-			if (*oi->sizep == 0) {
-				type = OBJ_BAD;
-				goto out;
-			}
-		} else {
-			*oi->sizep = size;
-		}
-	}
-
-	if (oi->disk_sizep) {
-		struct revindex_entry *revidx = find_pack_revindex(p, obj_offset);
-		*oi->disk_sizep = revidx[1].offset - obj_offset;
-	}
-
-	if (oi->typep || oi->typename) {
-		enum object_type ptot;
-		ptot = packed_to_object_type(p, obj_offset, type, &w_curs,
-					     curpos);
-		if (oi->typep)
-			*oi->typep = ptot;
-		if (oi->typename) {
-			const char *tn = typename(ptot);
-			if (tn)
-				strbuf_addstr(oi->typename, tn);
-		}
-		if (ptot < 0) {
-			type = OBJ_BAD;
-			goto out;
-		}
-	}
-
-	if (oi->delta_base_sha1) {
-		if (type == OBJ_OFS_DELTA || type == OBJ_REF_DELTA) {
-			const unsigned char *base;
-
-			base = get_delta_base_sha1(p, &w_curs, curpos,
-						   type, obj_offset);
-			if (!base) {
-				type = OBJ_BAD;
-				goto out;
-			}
-
-			hashcpy(oi->delta_base_sha1, base);
-		} else
-			hashclr(oi->delta_base_sha1);
-	}
-
-out:
-	unuse_pack(&w_curs);
-	return type;
-}
-
-static void *unpack_compressed_entry(struct packed_git *p,
-				    struct pack_window **w_curs,
-				    off_t curpos,
-				    unsigned long size)
-{
-	int st;
-	git_zstream stream;
-	unsigned char *buffer, *in;
-
-	buffer = xmallocz_gently(size);
-	if (!buffer)
-		return NULL;
-	memset(&stream, 0, sizeof(stream));
-	stream.next_out = buffer;
-	stream.avail_out = size + 1;
-
-	git_inflate_init(&stream);
-	do {
-		in = use_pack(p, w_curs, curpos, &stream.avail_in);
-		stream.next_in = in;
-		st = git_inflate(&stream, Z_FINISH);
-		if (!stream.avail_out)
-			break; /* the payload is larger than it should be */
-		curpos += stream.next_in - in;
-	} while (st == Z_OK || st == Z_BUF_ERROR);
-	git_inflate_end(&stream);
-	if ((st != Z_STREAM_END) || stream.total_out != size) {
-		free(buffer);
-		return NULL;
-	}
-
-	return buffer;
-}
-
 static struct hashmap delta_base_cache;
 static size_t delta_base_cached;
 

@@ -2486,6 +2376,116 @@ static void add_delta_base_cache(struct packed_git *p, off_t base_offset,
 	hashmap_add(&delta_base_cache, ent);
 }
 
+int packed_object_info(struct packed_git *p, off_t obj_offset,
+		       struct object_info *oi)
+{
+	struct pack_window *w_curs = NULL;
+	unsigned long size;
+	off_t curpos = obj_offset;
+	enum object_type type;
+
+	/*
+	 * We always get the representation type, but only convert it to
+	 * a "real" type later if the caller is interested.
+	 */
+	type = unpack_object_header(p, &w_curs, &curpos, &size);
+
+	if (oi->sizep) {
+		if (type == OBJ_OFS_DELTA || type == OBJ_REF_DELTA) {
+			off_t tmp_pos = curpos;
+			off_t base_offset = get_delta_base(p, &w_curs, &tmp_pos,
+							   type, obj_offset);
+			if (!base_offset) {
+				type = OBJ_BAD;
+				goto out;
+			}
+			*oi->sizep = get_size_from_delta(p, &w_curs, tmp_pos);
+			if (*oi->sizep == 0) {
+				type = OBJ_BAD;
+				goto out;
+			}
+		} else {
+			*oi->sizep = size;
+		}
+	}
+
+	if (oi->disk_sizep) {
+		struct revindex_entry *revidx = find_pack_revindex(p, obj_offset);
+		*oi->disk_sizep = revidx[1].offset - obj_offset;
+	}
+
+	if (oi->typep || oi->typename) {
+		enum object_type ptot;
+		ptot = packed_to_object_type(p, obj_offset, type, &w_curs,
+					     curpos);
+		if (oi->typep)
+			*oi->typep = ptot;
+		if (oi->typename) {
+			const char *tn = typename(ptot);
+			if (tn)
+				strbuf_addstr(oi->typename, tn);
+		}
+		if (ptot < 0) {
+			type = OBJ_BAD;
+			goto out;
+		}
+	}
+
+	if (oi->delta_base_sha1) {
+		if (type == OBJ_OFS_DELTA || type == OBJ_REF_DELTA) {
+			const unsigned char *base;
+
+			base = get_delta_base_sha1(p, &w_curs, curpos,
+						   type, obj_offset);
+			if (!base) {
+				type = OBJ_BAD;
+				goto out;
+			}
+
+			hashcpy(oi->delta_base_sha1, base);
+		} else
+			hashclr(oi->delta_base_sha1);
+	}
+
+out:
+	unuse_pack(&w_curs);
+	return type;
+}
+
+static void *unpack_compressed_entry(struct packed_git *p,
+				    struct pack_window **w_curs,
+				    off_t curpos,
+				    unsigned long size)
+{
+	int st;
+	git_zstream stream;
+	unsigned char *buffer, *in;
+
+	buffer = xmallocz_gently(size);
+	if (!buffer)
+		return NULL;
+	memset(&stream, 0, sizeof(stream));
+	stream.next_out = buffer;
+	stream.avail_out = size + 1;
+
+	git_inflate_init(&stream);
+	do {
+		in = use_pack(p, w_curs, curpos, &stream.avail_in);
+		stream.next_in = in;
+		st = git_inflate(&stream, Z_FINISH);
+		if (!stream.avail_out)
+			break; /* the payload is larger than it should be */
+		curpos += stream.next_in - in;
+	} while (st == Z_OK || st == Z_BUF_ERROR);
+	git_inflate_end(&stream);
+	if ((st != Z_STREAM_END) || stream.total_out != size) {
+		free(buffer);
+		return NULL;
+	}
+
+	return buffer;
+}
+
 static void *read_object(const unsigned char *sha1, enum object_type *type,
 			 unsigned long *size);
 

index 4d92aae0e..63a73af17 100644
@@ -1835,6 +1835,7 @@ struct object_info {
 	off_t *disk_sizep;
 	unsigned char *delta_base_sha1;
 	struct strbuf *typename;
+	void **contentp;
 
 	/* Response */
 	enum {

149 lines not on this page · raw message

index cb2ba6cd1..b447bd5f9 100644
@@ -37,6 +37,7 @@ static int verbose;
 static int show_progress = -1;
 static int show_dangling = 1;
 static int name_objects;
+static int missing_blob_ok;
 #define ERROR_OBJECT 01
 #define ERROR_REACHABLE 02
 #define ERROR_PACK 04

@@ -93,6 +94,9 @@ static int fsck_config(const char *var, const char *value, void *cb)
 		return 0;
 	}
 
+	if (!strcmp(var, "core.missingblobcommand"))
+		missing_blob_ok = 1;
+
 	return git_default_config(var, value, cb);
 }
 

@@ -222,6 +226,9 @@ static void check_reachable_object(struct object *obj)
 	if (!(obj->flags & HAS_OBJ)) {
 		if (has_sha1_pack(obj->oid.hash))
 			return; /* it is in pack - forget about it */
+		if (missing_blob_ok && obj->type == OBJ_BLOB &&
+		    in_missing_blob_manifest(obj->oid.hash, NULL))
+			return;
 		printf("missing %s %s\n", printable_type(obj),
 			describe_object(obj));
 		errors_found |= ERROR_REACHABLE;

index 63a73af17..dd69c75f5 100644
@@ -1870,6 +1870,13 @@ struct object_info {
 extern int sha1_object_info_extended(const unsigned char *, struct object_info *, unsigned flags);
 extern int packed_object_info(struct packed_git *pack, off_t offset, struct object_info *);
 
+/*
+ * Returns 1 if sha1 is the hash of a known missing blob. If size is not NULL,
+ * also returns its size.
+ */
+extern int in_missing_blob_manifest(const unsigned char *sha1,
+				    unsigned long *size);
+
 /* Dumb servers support */
 extern int update_server_info(int);
 

217 lines not on this page · raw message

index 59a4ed2ed..a52b27541 100644
@@ -2277,9 +2277,18 @@ int packed_object_info(struct packed_git *p, off_t obj_offset,
 		*oi->disk_sizep = revidx[1].offset - obj_offset;
 	}
 
-	if (oi->typep) {
-		*oi->typep = packed_to_object_type(p, obj_offset, type, &w_curs, curpos);
-		if (*oi->typep < 0) {
+	if (oi->typep || oi->typename) {
+		enum object_type ptot;
+		ptot = packed_to_object_type(p, obj_offset, type, &w_curs,
+					     curpos);
+		if (oi->typep)
+			*oi->typep = ptot;
+		if (oi->typename) {
+			const char *tn = typename(ptot);
+			if (tn)
+				strbuf_addstr(oi->typename, tn);
+		}
+		if (ptot < 0) {
 			type = OBJ_BAD;
 			goto out;
 		}

@@ -2960,7 +2969,6 @@ int sha1_object_info_extended(const unsigned char *sha1, struct object_info *oi,
 	struct cached_object *co;
 	struct pack_entry e;
 	int rtype;
-	enum object_type real_type;
 	const unsigned char *real = lookup_replace_object_extended(sha1, flags);
 
 	co = find_cached_object(real);

@@ -2992,18 +3000,9 @@ int sha1_object_info_extended(const unsigned char *sha1, struct object_info *oi,
 			return -1;
 	}
 
-	/*
-	 * packed_object_info() does not follow the delta chain to
-	 * find out the real type, unless it is given oi->typep.
-	 */
-	if (oi->typename && !oi->typep)
-		oi->typep = &real_type;
-
 	rtype = packed_object_info(e.p, e.offset, oi);
 	if (rtype < 0) {
 		mark_bad_packed_object(e.p, real);
-		if (oi->typep == &real_type)
-			oi->typep = NULL;
 		return sha1_object_info_extended(real, oi, 0);
 	} else if (in_delta_base_cache(e.p, e.offset)) {
 		oi->whence = OI_DBCACHED;

@@ -3014,10 +3013,6 @@ int sha1_object_info_extended(const unsigned char *sha1, struct object_info *oi,
 		oi->u.packed.is_delta = (rtype == OBJ_REF_DELTA ||
 					 rtype == OBJ_OFS_DELTA);
 	}
-	if (oi->typename)
-		strbuf_addstr(oi->typename, typename(*oi->typep));
-	if (oi->typep == &real_type)
-		oi->typep = NULL;
 
 	return 0;
 }

index 4bffd7a2d..209374b3c 100644
@@ -60,7 +60,7 @@ static int cat_one_file(int opt, const char *exp_type, const char *obj_name,
 	const char *path = force_path;
 
 	if (unknown_type)
-		flags |= LOOKUP_UNKNOWN_OBJECT;
+		flags |= OBJECT_INFO_ALLOW_UNKNOWN_TYPE;
 
 	if (get_sha1_with_context(obj_name, GET_SHA1_RECORD_PATH,
 				  oid.hash, &obj_context))

index 4d92aae0e..e2ec45dfe 100644
@@ -1207,7 +1207,6 @@ extern char *xdg_cache_home(const char *filename);
 
 /* object replacement */
 #define LOOKUP_REPLACE_OBJECT 1
-#define LOOKUP_UNKNOWN_OBJECT 2
 extern void *read_sha1_file_extended(const unsigned char *sha1, enum object_type *type, unsigned long *size, unsigned flag);
 static inline void *read_sha1_file(const unsigned char *sha1, enum object_type *type, unsigned long *size)
 {

@@ -1866,6 +1865,8 @@ struct object_info {
  */
 #define OBJECT_INFO_INIT {NULL}
 
+/* Allow reading from a loose object file of unknown/bogus type */
+#define OBJECT_INFO_ALLOW_UNKNOWN_TYPE 2
 extern int sha1_object_info_extended(const unsigned char *, struct object_info *, unsigned flags);
 extern int packed_object_info(struct packed_git *pack, off_t offset, struct object_info *);
 

index a52b27541..ad04ea8e0 100644
@@ -1964,7 +1964,7 @@ static int parse_sha1_header_extended(const char *hdr, struct object_info *oi,
 	 * we're obtaining the type using '--allow-unknown-type'
 	 * option.
 	 */
-	if ((flags & LOOKUP_UNKNOWN_OBJECT) && (type < 0))
+	if ((flags & OBJECT_INFO_ALLOW_UNKNOWN_TYPE) && (type < 0))
 		type = 0;
 	else if (type < 0)
 		die("invalid object type");

@@ -2941,7 +2941,7 @@ static int sha1_loose_object_info(const unsigned char *sha1,
 		return -1;
 	if (oi->disk_sizep)
 		*oi->disk_sizep = mapsize;
-	if ((flags & LOOKUP_UNKNOWN_OBJECT)) {
+	if ((flags & OBJECT_INFO_ALLOW_UNKNOWN_TYPE)) {
 		if (unpack_sha1_header_to_strbuf(&stream, map, mapsize, hdr, sizeof(hdr), &hdrbuf) < 0)
 			status = error("unable to unpack %s header with --allow-unknown-type",
 				       sha1_to_hex(sha1));

index 209374b3c..923786c00 100644
@@ -56,7 +56,7 @@ static int cat_one_file(int opt, const char *exp_type, const char *obj_name,
 	struct object_context obj_context;
 	struct object_info oi = OBJECT_INFO_INIT;
 	struct strbuf sb = STRBUF_INIT;
-	unsigned flags = LOOKUP_REPLACE_OBJECT;
+	unsigned flags = OBJECT_INFO_LOOKUP_REPLACE;
 	const char *path = force_path;
 
 	if (unknown_type)

@@ -337,7 +337,8 @@ static void batch_object_write(const char *obj_name, struct batch_options *opt,
 	struct strbuf buf = STRBUF_INIT;
 
 	if (!data->skip_object_info &&
-	    sha1_object_info_extended(data->oid.hash, &data->info, LOOKUP_REPLACE_OBJECT) < 0) {
+	    sha1_object_info_extended(data->oid.hash, &data->info,
+				      OBJECT_INFO_LOOKUP_REPLACE)) {
 		printf("%s missing\n",
 		       obj_name ? obj_name : oid_to_hex(&data->oid));
 		fflush(stdout);

index e2ec45dfe..a3631b237 100644
@@ -1205,12 +1205,12 @@ extern char *xdg_config_home(const char *filename);
  */
 extern char *xdg_cache_home(const char *filename);
 
-/* object replacement */
-#define LOOKUP_REPLACE_OBJECT 1
-extern void *read_sha1_file_extended(const unsigned char *sha1, enum object_type *type, unsigned long *size, unsigned flag);
+extern void *read_sha1_file_extended(const unsigned char *sha1,
+				     enum object_type *type,
+				     unsigned long *size, int lookup_replace);
 static inline void *read_sha1_file(const unsigned char *sha1, enum object_type *type, unsigned long *size)
 {
-	return read_sha1_file_extended(sha1, type, size, LOOKUP_REPLACE_OBJECT);
+	return read_sha1_file_extended(sha1, type, size, 1);
 }
 
 /*

@@ -1232,13 +1232,6 @@ static inline const unsigned char *lookup_replace_object(const unsigned char *sh
 	return do_lookup_replace_object(sha1);
 }
 
-static inline const unsigned char *lookup_replace_object_extended(const unsigned char *sha1, unsigned flag)
-{
-	if (!(flag & LOOKUP_REPLACE_OBJECT))
-		return sha1;
-	return lookup_replace_object(sha1);
-}
-
 /* Read and unpack a sha1 file into memory, write memory to a sha1 file */
 extern int sha1_object_info(const unsigned char *, unsigned long *);
 extern int hash_sha1_file(const void *buf, unsigned long len, const char *type, unsigned char *sha1);

@@ -1865,6 +1858,8 @@ struct object_info {
  */
 #define OBJECT_INFO_INIT {NULL}
 
+/* Invoke lookup_replace_object() on the given hash */
+#define OBJECT_INFO_LOOKUP_REPLACE 1
 /* Allow reading from a loose object file of unknown/bogus type */
 #define OBJECT_INFO_ALLOW_UNKNOWN_TYPE 2
 extern int sha1_object_info_extended(const unsigned char *, struct object_info *, unsigned flags);

index ad04ea8e0..ae44b32f3 100644
@@ -2002,7 +2002,7 @@ int parse_sha1_header(const char *hdr, unsigned long *sizep)
 	struct object_info oi = OBJECT_INFO_INIT;
 
 	oi.sizep = sizep;
-	return parse_sha1_header_extended(hdr, &oi, LOOKUP_REPLACE_OBJECT);
+	return parse_sha1_header_extended(hdr, &oi, 0);
 }
 
 static void *unpack_sha1_file(void *map, unsigned long mapsize, enum object_type *type, unsigned long *size, const unsigned char *sha1)

@@ -2969,7 +2969,9 @@ int sha1_object_info_extended(const unsigned char *sha1, struct object_info *oi,
 	struct cached_object *co;
 	struct pack_entry e;
 	int rtype;
-	const unsigned char *real = lookup_replace_object_extended(sha1, flags);
+	const unsigned char *real = (flags & OBJECT_INFO_LOOKUP_REPLACE) ?
+				    lookup_replace_object(sha1) :
+				    sha1;
 
 	co = find_cached_object(real);
 	if (co) {

@@ -3025,7 +3027,7 @@ int sha1_object_info(const unsigned char *sha1, unsigned long *sizep)
 
 	oi.typep = &type;
 	oi.sizep = sizep;
-	if (sha1_object_info_extended(sha1, &oi, LOOKUP_REPLACE_OBJECT) < 0)
+	if (sha1_object_info_extended(sha1, &oi, OBJECT_INFO_LOOKUP_REPLACE))
 		return -1;
 	return type;
 }

@@ -3107,13 +3109,14 @@ static void *read_object(const unsigned char *sha1, enum object_type *type,
 void *read_sha1_file_extended(const unsigned char *sha1,
 			      enum object_type *type,
 			      unsigned long *size,
-			      unsigned flag)
+			      int lookup_replace)
 {
 	void *data;
 	const struct packed_git *p;
 	const char *path;
 	struct stat st;
-	const unsigned char *repl = lookup_replace_object_extended(sha1, flag);
+	const unsigned char *repl = lookup_replace ? lookup_replace_object(sha1)
+						   : sha1;
 
 	errno = 0;
 	data = read_object(repl, type, size);

index ae44b32f3..a7be45efe 100644
@@ -2239,116 +2239,6 @@ static enum object_type packed_to_object_type(struct packed_git *p,
 	goto out;
 }
 
-int packed_object_info(struct packed_git *p, off_t obj_offset,
-		       struct object_info *oi)
-{
-	struct pack_window *w_curs = NULL;
-	unsigned long size;
-	off_t curpos = obj_offset;
-	enum object_type type;
-
-	/*
-	 * We always get the representation type, but only convert it to
-	 * a "real" type later if the caller is interested.
-	 */
-	type = unpack_object_header(p, &w_curs, &curpos, &size);
-
-	if (oi->sizep) {
-		if (type == OBJ_OFS_DELTA || type == OBJ_REF_DELTA) {
-			off_t tmp_pos = curpos;
-			off_t base_offset = get_delta_base(p, &w_curs, &tmp_pos,
-							   type, obj_offset);
-			if (!base_offset) {
-				type = OBJ_BAD;
-				goto out;
-			}
-			*oi->sizep = get_size_from_delta(p, &w_curs, tmp_pos);
-			if (*oi->sizep == 0) {
-				type = OBJ_BAD;
-				goto out;
-			}
-		} else {
-			*oi->sizep = size;
-		}
-	}
-
-	if (oi->disk_sizep) {
-		struct revindex_entry *revidx = find_pack_revindex(p, obj_offset);
-		*oi->disk_sizep = revidx[1].offset - obj_offset;
-	}
-
-	if (oi->typep || oi->typename) {
-		enum object_type ptot;
-		ptot = packed_to_object_type(p, obj_offset, type, &w_curs,
-					     curpos);
-		if (oi->typep)
-			*oi->typep = ptot;
-		if (oi->typename) {
-			const char *tn = typename(ptot);
-			if (tn)
-				strbuf_addstr(oi->typename, tn);
-		}
-		if (ptot < 0) {
-			type = OBJ_BAD;
-			goto out;
-		}
-	}
-
-	if (oi->delta_base_sha1) {
-		if (type == OBJ_OFS_DELTA || type == OBJ_REF_DELTA) {
-			const unsigned char *base;
-
-			base = get_delta_base_sha1(p, &w_curs, curpos,
-						   type, obj_offset);
-			if (!base) {
-				type = OBJ_BAD;
-				goto out;
-			}
-
-			hashcpy(oi->delta_base_sha1, base);
-		} else
-			hashclr(oi->delta_base_sha1);
-	}
-
-out:
-	unuse_pack(&w_curs);
-	return type;
-}
-
-static void *unpack_compressed_entry(struct packed_git *p,
-				    struct pack_window **w_curs,
-				    off_t curpos,
-				    unsigned long size)
-{
-	int st;
-	git_zstream stream;
-	unsigned char *buffer, *in;
-
-	buffer = xmallocz_gently(size);
-	if (!buffer)
-		return NULL;
-	memset(&stream, 0, sizeof(stream));
-	stream.next_out = buffer;
-	stream.avail_out = size + 1;
-
-	git_inflate_init(&stream);
-	do {
-		in = use_pack(p, w_curs, curpos, &stream.avail_in);
-		stream.next_in = in;
-		st = git_inflate(&stream, Z_FINISH);
-		if (!stream.avail_out)
-			break; /* the payload is larger than it should be */
-		curpos += stream.next_in - in;
-	} while (st == Z_OK || st == Z_BUF_ERROR);
-	git_inflate_end(&stream);
-	if ((st != Z_STREAM_END) || stream.total_out != size) {
-		free(buffer);
-		return NULL;
-	}
-
-	return buffer;
-}
-
 static struct hashmap delta_base_cache;
 static size_t delta_base_cached;
 

@@ -2486,6 +2376,116 @@ static void add_delta_base_cache(struct packed_git *p, off_t base_offset,
 	hashmap_add(&delta_base_cache, ent);
 }
 
+int packed_object_info(struct packed_git *p, off_t obj_offset,
+		       struct object_info *oi)
+{
+	struct pack_window *w_curs = NULL;
+	unsigned long size;
+	off_t curpos = obj_offset;
+	enum object_type type;
+
+	/*
+	 * We always get the representation type, but only convert it to
+	 * a "real" type later if the caller is interested.
+	 */
+	type = unpack_object_header(p, &w_curs, &curpos, &size);
+
+	if (oi->sizep) {
+		if (type == OBJ_OFS_DELTA || type == OBJ_REF_DELTA) {
+			off_t tmp_pos = curpos;
+			off_t base_offset = get_delta_base(p, &w_curs, &tmp_pos,
+							   type, obj_offset);
+			if (!base_offset) {
+				type = OBJ_BAD;
+				goto out;
+			}
+			*oi->sizep = get_size_from_delta(p, &w_curs, tmp_pos);
+			if (*oi->sizep == 0) {
+				type = OBJ_BAD;
+				goto out;
+			}
+		} else {
+			*oi->sizep = size;
+		}
+	}
+
+	if (oi->disk_sizep) {
+		struct revindex_entry *revidx = find_pack_revindex(p, obj_offset);
+		*oi->disk_sizep = revidx[1].offset - obj_offset;
+	}
+
+	if (oi->typep || oi->typename) {
+		enum object_type ptot;
+		ptot = packed_to_object_type(p, obj_offset, type, &w_curs,
+					     curpos);
+		if (oi->typep)
+			*oi->typep = ptot;
+		if (oi->typename) {
+			const char *tn = typename(ptot);
+			if (tn)
+				strbuf_addstr(oi->typename, tn);
+		}
+		if (ptot < 0) {
+			type = OBJ_BAD;
+			goto out;
+		}
+	}
+
+	if (oi->delta_base_sha1) {
+		if (type == OBJ_OFS_DELTA || type == OBJ_REF_DELTA) {
+			const unsigned char *base;
+
+			base = get_delta_base_sha1(p, &w_curs, curpos,
+						   type, obj_offset);
+			if (!base) {
+				type = OBJ_BAD;
+				goto out;
+			}
+
+			hashcpy(oi->delta_base_sha1, base);
+		} else
+			hashclr(oi->delta_base_sha1);
+	}
+
+out:
+	unuse_pack(&w_curs);
+	return type;
+}
+
+static void *unpack_compressed_entry(struct packed_git *p,
+				    struct pack_window **w_curs,
+				    off_t curpos,
+				    unsigned long size)
+{
+	int st;
+	git_zstream stream;
+	unsigned char *buffer, *in;
+
+	buffer = xmallocz_gently(size);
+	if (!buffer)
+		return NULL;
+	memset(&stream, 0, sizeof(stream));
+	stream.next_out = buffer;
+	stream.avail_out = size + 1;
+
+	git_inflate_init(&stream);
+	do {
+		in = use_pack(p, w_curs, curpos, &stream.avail_in);
+		stream.next_in = in;
+		st = git_inflate(&stream, Z_FINISH);
+		if (!stream.avail_out)
+			break; /* the payload is larger than it should be */
+		curpos += stream.next_in - in;
+	} while (st == Z_OK || st == Z_BUF_ERROR);
+	git_inflate_end(&stream);
+	if ((st != Z_STREAM_END) || stream.total_out != size) {
+		free(buffer);
+		return NULL;
+	}
+
+	return buffer;
+}
+
 static void *read_object(const unsigned char *sha1, enum object_type *type,
 			 unsigned long *size);
 

index a3631b237..48aea923b 100644
@@ -1827,6 +1827,7 @@ struct object_info {
 	off_t *disk_sizep;
 	unsigned char *delta_base_sha1;
 	struct strbuf *typename;
+	void **contentp;
 
 	/* Response */
 	enum {

149 lines not on this page · raw message

index 48aea923b..7cf2ca466 100644
@@ -1863,6 +1863,10 @@ struct object_info {
 #define OBJECT_INFO_LOOKUP_REPLACE 1
 /* Allow reading from a loose object file of unknown/bogus type */
 #define OBJECT_INFO_ALLOW_UNKNOWN_TYPE 2
+/* Do not check cached storage */
+#define OBJECT_INFO_SKIP_CACHED 4
+/* Do not retry packed storage after checking packed and loose storage */
+#define OBJECT_INFO_QUICK 8
 extern int sha1_object_info_extended(const unsigned char *, struct object_info *, unsigned flags);
 extern int packed_object_info(struct packed_git *pack, off_t offset, struct object_info *);
 

62 lines not on this page · raw message