Merge branch 'kn/cat-file-literally'

Add the "--allow-unknown-type" option to "cat-file" to allow
inspecting loose objects of an experimental or a broken type.

* kn/cat-file-literally:
  t1006: add tests for git cat-file --allow-unknown-type
  cat-file: teach cat-file a '--allow-unknown-type' option
  cat-file: make the options mutually exclusive
  sha1_file: support reading from a loose object of unknown type

5 files changed, 188 insertions, 43 deletions

diff --git a/Documentation/git-cat-file.txt b/Documentation/git-cat-file.txt
index f6a16f4300..499ae7b98a 100644
--- a/Documentation/git-cat-file.txt
+++ b/Documentation/git-cat-file.txt
@@ -9,7 +9,7 @@ git-cat-file - Provide content or type and size information for repository objec
 SYNOPSIS
 --------
 [verse]
-'git cat-file' (-t | -s | -e | -p | <type> | --textconv ) <object>
+'git cat-file' (-t [--allow-unknown-type]| -s [--allow-unknown-type]| -e | -p | <type> | --textconv ) <object>
 'git cat-file' (--batch | --batch-check) < <list-of-objects>
 
 DESCRIPTION
@@ -69,6 +69,9 @@ OPTIONS
 	not be combined with any other options or arguments.  See the
 	section `BATCH OUTPUT` below for details.
 
+--allow-unknown-type::
+	Allow -s or -t to query broken/corrupt objects of unknown type.
+
 OUTPUT
 ------
 If '-t' is specified, one of the <type>.
diff --git a/builtin/cat-file.c b/builtin/cat-file.c
index df99df4db1..ecb488822f 100644
--- a/builtin/cat-file.c
+++ b/builtin/cat-file.c
@@ -9,13 +9,20 @@
 #include "userdiff.h"
 #include "streaming.h"
 
-static int cat_one_file(int opt, const char *exp_type, const char *obj_name)
+static int cat_one_file(int opt, const char *exp_type, const char *obj_name,
+			int unknown_type)
 {
 	unsigned char sha1[20];
 	enum object_type type;
 	char *buf;
 	unsigned long size;
 	struct object_context obj_context;
+	struct object_info oi = {NULL};
+	struct strbuf sb = STRBUF_INIT;
+	unsigned flags = LOOKUP_REPLACE_OBJECT;
+
+	if (unknown_type)
+		flags |= LOOKUP_UNKNOWN_OBJECT;
 
 	if (get_sha1_with_context(obj_name, 0, sha1, &obj_context))
 		die("Not a valid object name %s", obj_name);
@@ -23,20 +30,22 @@ static int cat_one_file(int opt, const char *exp_type, const char *obj_name)
 	buf = NULL;
 	switch (opt) {
 	case 't':
-		type = sha1_object_info(sha1, NULL);
-		if (type > 0) {
-			printf("%s\n", typename(type));
+		oi.typename = &sb;
+		if (sha1_object_info_extended(sha1, &oi, flags) < 0)
+			die("git cat-file: could not get object info");
+		if (sb.len) {
+			printf("%s\n", sb.buf);
+			strbuf_release(&sb);
 			return 0;
 		}
 		break;
 
 	case 's':
-		type = sha1_object_info(sha1, &size);
-		if (type > 0) {
-			printf("%lu\n", size);
-			return 0;
-		}
-		break;
+		oi.sizep = &size;
+		if (sha1_object_info_extended(sha1, &oi, flags) < 0)
+			die("git cat-file: could not get object info");
+		printf("%lu\n", size);
+		return 0;
 
 	case 'e':
 		return !has_sha1_file(sha1);
@@ -323,7 +332,7 @@ static int batch_objects(struct batch_options *opt)
 }
 
 static const char * const cat_file_usage[] = {
-	N_("git cat-file (-t | -s | -e | -p | <type> | --textconv) <object>"),
+	N_("git cat-file (-t [--allow-unknown-type]|-s [--allow-unknown-type]|-e|-p|<type>|--textconv) <object>"),
 	N_("git cat-file (--batch | --batch-check) < <list-of-objects>"),
 	NULL
 };
@@ -359,16 +368,19 @@ int cmd_cat_file(int argc, const char **argv, const char *prefix)
 	int opt = 0;
 	const char *exp_type = NULL, *obj_name = NULL;
 	struct batch_options batch = {0};
+	int unknown_type = 0;
 
 	const struct option options[] = {
 		OPT_GROUP(N_("<type> can be one of: blob, tree, commit, tag")),
-		OPT_SET_INT('t', NULL, &opt, N_("show object type"), 't'),
-		OPT_SET_INT('s', NULL, &opt, N_("show object size"), 's'),
-		OPT_SET_INT('e', NULL, &opt,
+		OPT_CMDMODE('t', NULL, &opt, N_("show object type"), 't'),
+		OPT_CMDMODE('s', NULL, &opt, N_("show object size"), 's'),
+		OPT_CMDMODE('e', NULL, &opt,
 			    N_("exit with zero when there's no error"), 'e'),
-		OPT_SET_INT('p', NULL, &opt, N_("pretty-print object's content"), 'p'),
-		OPT_SET_INT(0, "textconv", &opt,
+		OPT_CMDMODE('p', NULL, &opt, N_("pretty-print object's content"), 'p'),
+		OPT_CMDMODE(0, "textconv", &opt,
 			    N_("for blob objects, run textconv on object's content"), 'c'),
+		OPT_BOOL( 0, "allow-unknown-type", &unknown_type,
+			  N_("allow -s and -t to work with broken/corrupt objects")),
 		{ OPTION_CALLBACK, 0, "batch", &batch, "format",
 			N_("show info and content of objects fed from the standard input"),
 			PARSE_OPT_OPTARG, batch_option_callback },
@@ -380,9 +392,6 @@ int cmd_cat_file(int argc, const char **argv, const char *prefix)
 
 	git_config(git_cat_file_config, NULL);
 
-	if (argc != 3 && argc != 2)
-		usage_with_options(cat_file_usage, options);
-
 	argc = parse_options(argc, argv, prefix, options, cat_file_usage, 0);
 
 	if (opt) {
@@ -405,5 +414,7 @@ int cmd_cat_file(int argc, const char **argv, const char *prefix)
 	if (batch.enabled)
 		return batch_objects(&batch);
 
-	return cat_one_file(opt, exp_type, obj_name);
+	if (unknown_type && opt != 't' && opt != 's')
+		die("git cat-file --allow-unknown-type: use with -s or -t");
+	return cat_one_file(opt, exp_type, obj_name, unknown_type);
 }
diff --git a/cache.h b/cache.h
index 54f108a28f..c97d8071e1 100644
--- a/cache.h
+++ b/cache.h
@@ -879,6 +879,7 @@ extern char *xdg_config_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)
 {
@@ -1351,6 +1352,7 @@ struct object_info {
 	unsigned long *sizep;
 	unsigned long *disk_sizep;
 	unsigned char *delta_base_sha1;
+	struct strbuf *typename;
 
 	/* Response */
 	enum {
diff --git a/sha1_file.c b/sha1_file.c
index 866021b2b1..ccc6dac54b 100644
--- a/sha1_file.c
+++ b/sha1_file.c
@@ -1564,6 +1564,40 @@ int unpack_sha1_header(git_zstream *stream, unsigned char *map, unsigned long ma
 	return git_inflate(stream, 0);
 }
 
+static int unpack_sha1_header_to_strbuf(git_zstream *stream, unsigned char *map,
+					unsigned long mapsize, void *buffer,
+					unsigned long bufsiz, struct strbuf *header)
+{
+	int status;
+
+	status = unpack_sha1_header(stream, map, mapsize, buffer, bufsiz);
+
+	/*
+	 * Check if entire header is unpacked in the first iteration.
+	 */
+	if (memchr(buffer, '\0', stream->next_out - (unsigned char *)buffer))
+		return 0;
+
+	/*
+	 * buffer[0..bufsiz] was not large enough.  Copy the partial
+	 * result out to header, and then append the result of further
+	 * reading the stream.
+	 */
+	strbuf_add(header, buffer, stream->next_out - (unsigned char *)buffer);
+	stream->next_out = buffer;
+	stream->avail_out = bufsiz;
+
+	do {
+		status = git_inflate(stream, 0);
+		strbuf_add(header, buffer, stream->next_out - (unsigned char *)buffer);
+		if (memchr(buffer, '\0', stream->next_out - (unsigned char *)buffer))
+			return 0;
+		stream->next_out = buffer;
+		stream->avail_out = bufsiz;
+	} while (status != Z_STREAM_END);
+	return -1;
+}
+
 static void *unpack_sha1_rest(git_zstream *stream, void *buffer, unsigned long size, const unsigned char *sha1)
 {
 	int bytes = strlen(buffer) + 1;
@@ -1614,27 +1648,38 @@ static void *unpack_sha1_rest(git_zstream *stream, void *buffer, unsigned long s
  * too permissive for what we want to check. So do an anal
  * object header parse by hand.
  */
-int parse_sha1_header(const char *hdr, unsigned long *sizep)
+static int parse_sha1_header_extended(const char *hdr, struct object_info *oi,
+			       unsigned int flags)
 {
-	char type[10];
-	int i;
+	const char *type_buf = hdr;
 	unsigned long size;
+	int type, type_len = 0;
 
 	/*
-	 * The type can be at most ten bytes (including the
-	 * terminating '\0' that we add), and is followed by
+	 * The type can be of any size but is followed by
 	 * a space.
 	 */
-	i = 0;
 	for (;;) {
 		char c = *hdr++;
 		if (c == ' ')
 			break;
-		type[i++] = c;
-		if (i >= sizeof(type))
-			return -1;
+		type_len++;
 	}
-	type[i] = 0;
+
+	type = type_from_string_gently(type_buf, type_len, 1);
+	if (oi->typename)
+		strbuf_add(oi->typename, type_buf, type_len);
+	/*
+	 * Set type to 0 if its an unknown object and
+	 * we're obtaining the type using '--allow-unkown-type'
+	 * option.
+	 */
+	if ((flags & LOOKUP_UNKNOWN_OBJECT) && (type < 0))
+		type = 0;
+	else if (type < 0)
+		die("invalid object type");
+	if (oi->typep)
+		*oi->typep = type;
 
 	/*
 	 * The length must follow immediately, and be in canonical
@@ -1652,12 +1697,24 @@ int parse_sha1_header(const char *hdr, unsigned long *sizep)
 			size = size * 10 + c;
 		}
 	}
-	*sizep = size;
+
+	if (oi->sizep)
+		*oi->sizep = size;
 
 	/*
 	 * The length must be followed by a zero byte
 	 */
-	return *hdr ? -1 : type_from_string(type);
+	return *hdr ? -1 : type;
+}
+
+int parse_sha1_header(const char *hdr, unsigned long *sizep)
+{
+	struct object_info oi;
+
+	oi.sizep = sizep;
+	oi.typename = NULL;
+	oi.typep = NULL;
+	return parse_sha1_header_extended(hdr, &oi, LOOKUP_REPLACE_OBJECT);
 }
 
 static void *unpack_sha1_file(void *map, unsigned long mapsize, enum object_type *type, unsigned long *size, const unsigned char *sha1)
@@ -2522,13 +2579,15 @@ struct packed_git *find_sha1_pack(const unsigned char *sha1,
 }
 
 static int sha1_loose_object_info(const unsigned char *sha1,
-				  struct object_info *oi)
+				  struct object_info *oi,
+				  int flags)
 {
-	int status;
-	unsigned long mapsize, size;
+	int status = 0;
+	unsigned long mapsize;
 	void *map;
 	git_zstream stream;
 	char hdr[32];
+	struct strbuf hdrbuf = STRBUF_INIT;
 
 	if (oi->delta_base_sha1)
 		hashclr(oi->delta_base_sha1);
@@ -2541,7 +2600,7 @@ static int sha1_loose_object_info(const unsigned char *sha1,
 	 * return value implicitly indicates whether the
 	 * object even exists.
 	 */
-	if (!oi->typep && !oi->sizep) {
+	if (!oi->typep && !oi->typename && !oi->sizep) {
 		struct stat st;
 		if (stat_sha1_file(sha1, &st) < 0)
 			return -1;
@@ -2555,17 +2614,26 @@ static int sha1_loose_object_info(const unsigned char *sha1,
 		return -1;
 	if (oi->disk_sizep)
 		*oi->disk_sizep = mapsize;
-	if (unpack_sha1_header(&stream, map, mapsize, hdr, sizeof(hdr)) < 0)
+	if ((flags & LOOKUP_UNKNOWN_OBJECT)) {
+		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));
+	} else if (unpack_sha1_header(&stream, map, mapsize, hdr, sizeof(hdr)) < 0)
 		status = error("unable to unpack %s header",
 			       sha1_to_hex(sha1));
-	else if ((status = parse_sha1_header(hdr, &size)) < 0)
+	if (status < 0)
+		; /* Do nothing */
+	else if (hdrbuf.len) {
+		if ((status = parse_sha1_header_extended(hdrbuf.buf, oi, flags)) < 0)
+			status = error("unable to parse %s header with --allow-unknown-type",
+				       sha1_to_hex(sha1));
+	} else if ((status = parse_sha1_header_extended(hdr, oi, flags)) < 0)
 		status = error("unable to parse %s header", sha1_to_hex(sha1));
-	else if (oi->sizep)
-		*oi->sizep = size;
 	git_inflate_end(&stream);
 	munmap(map, mapsize);
-	if (oi->typep)
+	if (status && oi->typep)
 		*oi->typep = status;
+	strbuf_release(&hdrbuf);
 	return 0;
 }
 
@@ -2574,6 +2642,7 @@ 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);
@@ -2586,13 +2655,15 @@ int sha1_object_info_extended(const unsigned char *sha1, struct object_info *oi,
 			*(oi->disk_sizep) = 0;
 		if (oi->delta_base_sha1)
 			hashclr(oi->delta_base_sha1);
+		if (oi->typename)
+			strbuf_addstr(oi->typename, typename(co->type));
 		oi->whence = OI_CACHED;
 		return 0;
 	}
 
 	if (!find_pack_entry(real, &e)) {
 		/* Most likely it's a loose object. */
-		if (!sha1_loose_object_info(real, oi)) {
+		if (!sha1_loose_object_info(real, oi, flags)) {
 			oi->whence = OI_LOOSE;
 			return 0;
 		}
@@ -2603,9 +2674,18 @@ 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;
@@ -2616,6 +2696,10 @@ 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;
 }
diff --git a/t/t1006-cat-file.sh b/t/t1006-cat-file.sh
index ab36b1eb72..4f225db9a7 100755
--- a/t/t1006-cat-file.sh
+++ b/t/t1006-cat-file.sh
@@ -47,6 +47,18 @@ $content"
 	test_cmp expect actual
     '
 
+    test_expect_success "Type of $type is correct using --allow-unknown-type" '
+	echo $type >expect &&
+	git cat-file -t --allow-unknown-type $sha1 >actual &&
+	test_cmp expect actual
+    '
+
+    test_expect_success "Size of $type is correct using --allow-unknown-type" '
+	echo $size >expect &&
+	git cat-file -s --allow-unknown-type $sha1 >actual &&
+	test_cmp expect actual
+    '
+
     test -z "$content" ||
     test_expect_success "Content of $type is correct" '
 	maybe_remove_timestamp "$content" $no_ts >expect &&
@@ -296,4 +308,37 @@ test_expect_success '%(deltabase) reports packed delta bases' '
 	}
 '
 
+bogus_type="bogus"
+bogus_content="bogus"
+bogus_size=$(strlen "$bogus_content")
+bogus_sha1=$(echo_without_newline "$bogus_content" | git hash-object -t $bogus_type --literally -w --stdin)
+
+test_expect_success "Type of broken object is correct" '
+	echo $bogus_type >expect &&
+	git cat-file -t --allow-unknown-type $bogus_sha1 >actual &&
+	test_cmp expect actual
+'
+
+test_expect_success "Size of broken object is correct" '
+	echo $bogus_size >expect &&
+	git cat-file -s --allow-unknown-type $bogus_sha1 >actual &&
+	test_cmp expect actual
+'
+bogus_type="abcdefghijklmnopqrstuvwxyz1234679"
+bogus_content="bogus"
+bogus_size=$(strlen "$bogus_content")
+bogus_sha1=$(echo_without_newline "$bogus_content" | git hash-object -t $bogus_type --literally -w --stdin)
+
+test_expect_success "Type of broken object is correct when type is large" '
+	echo $bogus_type >expect &&
+	git cat-file -t --allow-unknown-type $bogus_sha1 >actual &&
+	test_cmp expect actual
+'
+
+test_expect_success "Size of large broken object is correct when type is large" '
+	echo $bogus_size >expect &&
+	git cat-file -s --allow-unknown-type $bogus_sha1 >actual &&
+	test_cmp expect actual
+'
+
 test_done