[thirdparty/git.git] / builtin-unpack-objects.c

#include "builtin.h"
#include "cache.h"
#include "object.h"
#include "delta.h"
#include "pack.h"
#include "blob.h"
#include "commit.h"
#include "tag.h"
#include "tree.h"

#include <sys/time.h>

static int dry_run, quiet, recover, has_errors;
static const char unpack_usage[] = "git-unpack-objects [-n] [-q] [-r] < pack-file";

/* We always read in 4kB chunks. */
static unsigned char buffer[4096];
static unsigned long offset, len;
static SHA_CTX ctx;

/*
 * Make sure at least "min" bytes are available in the buffer, and
 * return the pointer to the buffer.
 */
static void * fill(int min)
{
	if (min <= len)
		return buffer + offset;
	if (min > sizeof(buffer))
		die("cannot fill %d bytes", min);
	if (offset) {
		SHA1_Update(&ctx, buffer, offset);
		memcpy(buffer, buffer + offset, len);
		offset = 0;
	}
	do {
		int ret = xread(0, buffer + len, sizeof(buffer) - len);
		if (ret <= 0) {
			if (!ret)
				die("early EOF");
			die("read error on input: %s", strerror(errno));
		}
		len += ret;
	} while (len < min);
	return buffer;
}

static void use(int bytes)
{
	if (bytes > len)
		die("used more bytes than were available");
	len -= bytes;
	offset += bytes;
}

static void *get_data(unsigned long size)
{
	z_stream stream;
	void *buf = xmalloc(size);

	memset(&stream, 0, sizeof(stream));

	stream.next_out = buf;
	stream.avail_out = size;
	stream.next_in = fill(1);
	stream.avail_in = len;
	inflateInit(&stream);

	for (;;) {
		int ret = inflate(&stream, 0);
		use(len - stream.avail_in);
		if (stream.total_out == size && ret == Z_STREAM_END)
			break;
		if (ret != Z_OK) {
			error("inflate returned %d\n", ret);
			free(buf);
			buf = NULL;
			if (!recover)
				exit(1);
			has_errors = 1;
			break;
		}
		stream.next_in = fill(1);
		stream.avail_in = len;
	}
	inflateEnd(&stream);
	return buf;
}

struct delta_info {
	unsigned char base_sha1[20];
	unsigned long size;
	void *delta;
	struct delta_info *next;
};

static struct delta_info *delta_list;

static void add_delta_to_list(unsigned char *base_sha1, void *delta, unsigned long size)
{
	struct delta_info *info = xmalloc(sizeof(*info));

	hashcpy(info->base_sha1, base_sha1);
	info->size = size;
	info->delta = delta;
	info->next = delta_list;
	delta_list = info;
}

static void added_object(unsigned char *sha1, const char *type, void *data, unsigned long size);

static void write_object(void *buf, unsigned long size, const char *type)
{
	unsigned char sha1[20];
	if (write_sha1_file(buf, size, type, sha1) < 0)
		die("failed to write object");
	added_object(sha1, type, buf, size);
}

static void resolve_delta(const char *type,
			  void *base, unsigned long base_size,
			  void *delta, unsigned long delta_size)
{
	void *result;
	unsigned long result_size;

	result = patch_delta(base, base_size,
			     delta, delta_size,
			     &result_size);
	if (!result)
		die("failed to apply delta");
	free(delta);
	write_object(result, result_size, type);
	free(result);
}

static void added_object(unsigned char *sha1, const char *type, void *data, unsigned long size)
{
	struct delta_info **p = &delta_list;
	struct delta_info *info;

	while ((info = *p) != NULL) {
		if (!hashcmp(info->base_sha1, sha1)) {
			*p = info->next;
			p = &delta_list;
			resolve_delta(type, data, size, info->delta, info->size);
			free(info);
			continue;
		}
		p = &info->next;
	}
}

static void unpack_non_delta_entry(enum object_type kind, unsigned long size)
{
	void *buf = get_data(size);
	const char *type;

	switch (kind) {
	case OBJ_COMMIT: type = commit_type; break;
	case OBJ_TREE:   type = tree_type; break;
	case OBJ_BLOB:   type = blob_type; break;
	case OBJ_TAG:    type = tag_type; break;
	default: die("bad type %d", kind);
	}
	if (!dry_run && buf)
		write_object(buf, size, type);
	free(buf);
}

static void unpack_delta_entry(unsigned long delta_size)
{
	void *delta_data, *base;
	unsigned long base_size;
	char type[20];
	unsigned char base_sha1[20];

	hashcpy(base_sha1, fill(20));
	use(20);

	delta_data = get_data(delta_size);
	if (dry_run || !delta_data) {
		free(delta_data);
		return;
	}

	if (!has_sha1_file(base_sha1)) {
		add_delta_to_list(base_sha1, delta_data, delta_size);
		return;
	}
	base = read_sha1_file(base_sha1, type, &base_size);
	if (!base) {
		error("failed to read delta-pack base object %s",
		      sha1_to_hex(base_sha1));
		if (!recover)
			exit(1);
		has_errors = 1;
		return;
	}
	resolve_delta(type, base, base_size, delta_data, delta_size);
	free(base);
}

static void unpack_one(unsigned nr, unsigned total)
{
	unsigned shift;
	unsigned char *pack, c;
	unsigned long size;
	enum object_type type;

	pack = fill(1);
	c = *pack;
	use(1);
	type = (c >> 4) & 7;
	size = (c & 15);
	shift = 4;
	while (c & 0x80) {
		pack = fill(1);
		c = *pack++;
		use(1);
		size += (c & 0x7f) << shift;
		shift += 7;
	}
	if (!quiet) {
		static unsigned long last_sec;
		static unsigned last_percent;
		struct timeval now;
		unsigned percentage = (nr * 100) / total;

		gettimeofday(&now, NULL);
		if (percentage != last_percent || now.tv_sec != last_sec) {
			last_sec = now.tv_sec;
			last_percent = percentage;
			fprintf(stderr, "%4u%% (%u/%u) done\r", percentage, nr, total);
		}
	}
	switch (type) {
	case OBJ_COMMIT:
	case OBJ_TREE:
	case OBJ_BLOB:
	case OBJ_TAG:
		unpack_non_delta_entry(type, size);
		return;
	case OBJ_DELTA:
		unpack_delta_entry(size);
		return;
	default:
		error("bad object type %d", type);
		has_errors = 1;
		if (recover)
			return;
		exit(1);
	}
}

static void unpack_all(void)
{
	int i;
	struct pack_header *hdr = fill(sizeof(struct pack_header));
	unsigned nr_objects = ntohl(hdr->hdr_entries);

	if (ntohl(hdr->hdr_signature) != PACK_SIGNATURE)
		die("bad pack file");
	if (!pack_version_ok(hdr->hdr_version))
		die("unknown pack file version %d", ntohl(hdr->hdr_version));
	fprintf(stderr, "Unpacking %d objects\n", nr_objects);

	use(sizeof(struct pack_header));
	for (i = 0; i < nr_objects; i++)
		unpack_one(i+1, nr_objects);
	if (delta_list)
		die("unresolved deltas left after unpacking");
}

int cmd_unpack_objects(int argc, const char **argv, const char *prefix)
{
	int i;
	unsigned char sha1[20];

	git_config(git_default_config);

	quiet = !isatty(2);

	for (i = 1 ; i < argc; i++) {
		const char *arg = argv[i];

		if (*arg == '-') {
			if (!strcmp(arg, "-n")) {
				dry_run = 1;
				continue;
			}
			if (!strcmp(arg, "-q")) {
				quiet = 1;
				continue;
			}
			if (!strcmp(arg, "-r")) {
				recover = 1;
				continue;
			}
			usage(unpack_usage);
		}

		/* We don't take any non-flag arguments now.. Maybe some day */
		usage(unpack_usage);
	}
	SHA1_Init(&ctx);
	unpack_all();
	SHA1_Update(&ctx, buffer, offset);
	SHA1_Final(sha1, &ctx);
	if (hashcmp(fill(20), sha1))
		die("final sha1 did not match");
	use(20);

	/* Write the last part of the buffer to stdout */
	while (len) {
		int ret = xwrite(1, buffer + offset, len);
		if (ret <= 0)
			break;
		len -= ret;
		offset += ret;
	}

	/* All done */
	if (!quiet)
		fprintf(stderr, "\n");
	return has_errors;
}
Commit	Line	Data
64413630	1	#include "builtin.h"
bad50dc8	2	#include "cache.h"
74536958	3	#include "object.h"
8ee378a0	4	#include "delta.h"
a733cb60	5	#include "pack.h"
8e440259 PE	6	#include "blob.h"
	7	#include "commit.h"
	8	#include "tag.h"
	9	#include "tree.h"
bad50dc8	10
d36f7b80 LT	11	#include <sys/time.h>
d36f7b80 LT	12
3b67d291 JH	13	static int dry_run, quiet, recover, has_errors;
3b67d291 JH	14	static const char unpack_usage[] = "git-unpack-objects [-n] [-q] [-r] < pack-file";
bad50dc8	15
67e5a5ec LT	16	/* We always read in 4kB chunks. */
67e5a5ec LT	17	static unsigned char buffer[4096];
c9b0597d	18	static unsigned long offset, len;
67e5a5ec	19	static SHA_CTX ctx;
bad50dc8	20
67e5a5ec LT	21	/*
	22	* Make sure at least "min" bytes are available in the buffer, and
	23	* return the pointer to the buffer.
	24	*/
	25	static void * fill(int min)
	26	{
	27	if (min <= len)
	28	return buffer + offset;
67e5a5ec LT	29	if (min > sizeof(buffer))
	30	die("cannot fill %d bytes", min);
	31	if (offset) {
	32	SHA1_Update(&ctx, buffer, offset);
	33	memcpy(buffer, buffer + offset, len);
	34	offset = 0;
	35	}
	36	do {
1c15afb9	37	int ret = xread(0, buffer + len, sizeof(buffer) - len);
67e5a5ec LT	38	if (ret <= 0) {
	39	if (!ret)
	40	die("early EOF");
67e5a5ec LT	41	die("read error on input: %s", strerror(errno));
	42	}
	43	len += ret;
	44	} while (len < min);
	45	return buffer;
	46	}
74536958	47
67e5a5ec LT	48	static void use(int bytes)
	49	{
	50	if (bytes > len)
	51	die("used more bytes than were available");
	52	len -= bytes;
	53	offset += bytes;
	54	}
bad50dc8	55
67e5a5ec	56	static void *get_data(unsigned long size)
bad50dc8	57	{
67e5a5ec LT	58	z_stream stream;
	59	void *buf = xmalloc(size);
	60
67e5a5ec LT	61	memset(&stream, 0, sizeof(stream));
	62
	63	stream.next_out = buf;
	64	stream.avail_out = size;
	65	stream.next_in = fill(1);
	66	stream.avail_in = len;
	67	inflateInit(&stream);
	68
	69	for (;;) {
	70	int ret = inflate(&stream, 0);
	71	use(len - stream.avail_in);
	72	if (stream.total_out == size && ret == Z_STREAM_END)
	73	break;
f986f2c8 JH	74	if (ret != Z_OK) {
	75	error("inflate returned %d\n", ret);
	76	free(buf);
	77	buf = NULL;
3b67d291	78	if (!recover)
f986f2c8 JH	79	exit(1);
	80	has_errors = 1;
	81	break;
	82	}
67e5a5ec LT	83	stream.next_in = fill(1);
	84	stream.avail_in = len;
	85	}
ee639140	86	inflateEnd(&stream);
67e5a5ec	87	return buf;
bad50dc8 LT	88	}
bad50dc8 LT	89
67e5a5ec LT	90	struct delta_info {
	91	unsigned char base_sha1[20];
	92	unsigned long size;
	93	void *delta;
	94	struct delta_info *next;
	95	};
	96
	97	static struct delta_info *delta_list;
	98
	99	static void add_delta_to_list(unsigned char base_sha1, void delta, unsigned long size)
bad50dc8	100	{
67e5a5ec	101	struct delta_info info = xmalloc(sizeof(info));
bad50dc8	102
e702496e	103	hashcpy(info->base_sha1, base_sha1);
67e5a5ec LT	104	info->size = size;
	105	info->delta = delta;
	106	info->next = delta_list;
	107	delta_list = info;
bad50dc8 LT	108	}
bad50dc8 LT	109
cca7081a	110	static void added_object(unsigned char sha1, const char type, void *data, unsigned long size);
67e5a5ec	111
cca7081a LT	112	static void write_object(void buf, unsigned long size, const char type)
	113	{
	114	unsigned char sha1[20];
	115	if (write_sha1_file(buf, size, type, sha1) < 0)
	116	die("failed to write object");
	117	added_object(sha1, type, buf, size);
	118	}
	119
f986f2c8 JH	120	static void resolve_delta(const char *type,
	121	void *base, unsigned long base_size,
	122	void *delta, unsigned long delta_size)
bad50dc8	123	{
67e5a5ec LT	124	void *result;
67e5a5ec LT	125	unsigned long result_size;
bad50dc8	126
67e5a5ec LT	127	result = patch_delta(base, base_size,
	128	delta, delta_size,
	129	&result_size);
	130	if (!result)
	131	die("failed to apply delta");
	132	free(delta);
cca7081a	133	write_object(result, result_size, type);
67e5a5ec	134	free(result);
bad50dc8 LT	135	}
bad50dc8 LT	136
cca7081a	137	static void added_object(unsigned char sha1, const char type, void *data, unsigned long size)
74536958	138	{
67e5a5ec LT	139	struct delta_info **p = &delta_list;
	140	struct delta_info *info;
	141
	142	while ((info = *p) != NULL) {
a89fccd2	143	if (!hashcmp(info->base_sha1, sha1)) {
67e5a5ec LT	144	*p = info->next;
	145	p = &delta_list;
	146	resolve_delta(type, data, size, info->delta, info->size);
	147	free(info);
	148	continue;
	149	}
	150	p = &info->next;
	151	}
	152	}
	153
f986f2c8	154	static void unpack_non_delta_entry(enum object_type kind, unsigned long size)
67e5a5ec LT	155	{
67e5a5ec LT	156	void *buf = get_data(size);
cca7081a	157	const char *type;
8ee378a0	158
8ee378a0	159	switch (kind) {
8e440259 PE	160	case OBJ_COMMIT: type = commit_type; break;
	161	case OBJ_TREE: type = tree_type; break;
	162	case OBJ_BLOB: type = blob_type; break;
	163	case OBJ_TAG: type = tag_type; break;
67e5a5ec	164	default: die("bad type %d", kind);
8ee378a0	165	}
f986f2c8	166	if (!dry_run && buf)
dddafffe	167	write_object(buf, size, type);
67e5a5ec	168	free(buf);
8ee378a0 JH	169	}
8ee378a0 JH	170
f986f2c8	171	static void unpack_delta_entry(unsigned long delta_size)
8ee378a0	172	{
67e5a5ec LT	173	void delta_data, base;
67e5a5ec LT	174	unsigned long base_size;
8ee378a0	175	char type[20];
67e5a5ec	176	unsigned char base_sha1[20];
8ee378a0	177
e702496e	178	hashcpy(base_sha1, fill(20));
67e5a5ec	179	use(20);
c4fb06c0	180
67e5a5ec	181	delta_data = get_data(delta_size);
f986f2c8	182	if (dry_run \|\| !delta_data) {
dddafffe	183	free(delta_data);
f986f2c8	184	return;
dddafffe	185	}
8ee378a0	186
c4fb06c0	187	if (!has_sha1_file(base_sha1)) {
67e5a5ec	188	add_delta_to_list(base_sha1, delta_data, delta_size);
f986f2c8	189	return;
8ee378a0	190	}
c4fb06c0	191	base = read_sha1_file(base_sha1, type, &base_size);
f986f2c8 JH	192	if (!base) {
	193	error("failed to read delta-pack base object %s",
	194	sha1_to_hex(base_sha1));
3b67d291	195	if (!recover)
f986f2c8 JH	196	exit(1);
	197	has_errors = 1;
	198	return;
	199	}
	200	resolve_delta(type, base, base_size, delta_data, delta_size);
ee639140	201	free(base);
8ee378a0 JH	202	}
8ee378a0 JH	203
d36f7b80	204	static void unpack_one(unsigned nr, unsigned total)
8ee378a0	205	{
01247d87	206	unsigned shift;
a733cb60	207	unsigned char *pack, c;
67e5a5ec LT	208	unsigned long size;
67e5a5ec LT	209	enum object_type type;
74536958	210
67e5a5ec LT	211	pack = fill(1);
	212	c = *pack;
	213	use(1);
a733cb60 LT	214	type = (c >> 4) & 7;
a733cb60 LT	215	size = (c & 15);
01247d87	216	shift = 4;
a733cb60	217	while (c & 0x80) {
67e5a5ec	218	pack = fill(1);
a733cb60	219	c = *pack++;
67e5a5ec	220	use(1);
01247d87 LT	221	size += (c & 0x7f) << shift;
01247d87 LT	222	shift += 7;
a733cb60	223	}
d36f7b80 LT	224	if (!quiet) {
	225	static unsigned long last_sec;
	226	static unsigned last_percent;
	227	struct timeval now;
cf219196	228	unsigned percentage = (nr * 100) / total;
d36f7b80 LT	229
	230	gettimeofday(&now, NULL);
	231	if (percentage != last_percent \|\| now.tv_sec != last_sec) {
	232	last_sec = now.tv_sec;
	233	last_percent = percentage;
	234	fprintf(stderr, "%4u%% (%u/%u) done\r", percentage, nr, total);
	235	}
	236	}
a733cb60 LT	237	switch (type) {
	238	case OBJ_COMMIT:
	239	case OBJ_TREE:
	240	case OBJ_BLOB:
	241	case OBJ_TAG:
67e5a5ec	242	unpack_non_delta_entry(type, size);
a733cb60 LT	243	return;
a733cb60 LT	244	case OBJ_DELTA:
67e5a5ec	245	unpack_delta_entry(size);
a733cb60	246	return;
67e5a5ec	247	default:
f986f2c8 JH	248	error("bad object type %d", type);
f986f2c8 JH	249	has_errors = 1;
3b67d291	250	if (recover)
f986f2c8 JH	251	return;
f986f2c8 JH	252	exit(1);
74536958 LT	253	}
	254	}
	255
74536958 LT	256	static void unpack_all(void)
74536958 LT	257	{
67e5a5ec LT	258	int i;
67e5a5ec LT	259	struct pack_header *hdr = fill(sizeof(struct pack_header));
67e5a5ec LT	260	unsigned nr_objects = ntohl(hdr->hdr_entries);
	261
	262	if (ntohl(hdr->hdr_signature) != PACK_SIGNATURE)
	263	die("bad pack file");
d60fc1c8 NP	264	if (!pack_version_ok(hdr->hdr_version))
d60fc1c8 NP	265	die("unknown pack file version %d", ntohl(hdr->hdr_version));
67e5a5ec LT	266	fprintf(stderr, "Unpacking %d objects\n", nr_objects);
	267
	268	use(sizeof(struct pack_header));
	269	for (i = 0; i < nr_objects; i++)
cf219196	270	unpack_one(i+1, nr_objects);
67e5a5ec LT	271	if (delta_list)
67e5a5ec LT	272	die("unresolved deltas left after unpacking");
74536958 LT	273	}
74536958 LT	274
64413630	275	int cmd_unpack_objects(int argc, const char *argv, const char prefix)
bad50dc8 LT	276	{
bad50dc8 LT	277	int i;
67e5a5ec	278	unsigned char sha1[20];
bad50dc8	279
8e273641	280	git_config(git_default_config);
53228a5f	281
476e8011 JH	282	quiet = !isatty(2);
476e8011 JH	283
bad50dc8 LT	284	for (i = 1 ; i < argc; i++) {
	285	const char *arg = argv[i];
	286
	287	if (*arg == '-') {
74536958 LT	288	if (!strcmp(arg, "-n")) {
	289	dry_run = 1;
	290	continue;
	291	}
d36f7b80 LT	292	if (!strcmp(arg, "-q")) {
	293	quiet = 1;
	294	continue;
	295	}
f986f2c8	296	if (!strcmp(arg, "-r")) {
3b67d291	297	recover = 1;
f986f2c8 JH	298	continue;
f986f2c8 JH	299	}
bad50dc8 LT	300	usage(unpack_usage);
bad50dc8 LT	301	}
67e5a5ec LT	302
67e5a5ec LT	303	/* We don't take any non-flag arguments now.. Maybe some day */
bad50dc8	304	usage(unpack_usage);
67e5a5ec LT	305	}
67e5a5ec LT	306	SHA1_Init(&ctx);
74536958	307	unpack_all();
67e5a5ec LT	308	SHA1_Update(&ctx, buffer, offset);
67e5a5ec LT	309	SHA1_Final(sha1, &ctx);
a89fccd2	310	if (hashcmp(fill(20), sha1))
67e5a5ec LT	311	die("final sha1 did not match");
	312	use(20);
	313
	314	/* Write the last part of the buffer to stdout */
	315	while (len) {
1c15afb9 JH	316	int ret = xwrite(1, buffer + offset, len);
1c15afb9 JH	317	if (ret <= 0)
67e5a5ec	318	break;
67e5a5ec LT	319	len -= ret;
	320	offset += ret;
	321	}
	322
	323	/* All done */
d36f7b80 LT	324	if (!quiet)
d36f7b80 LT	325	fprintf(stderr, "\n");
f986f2c8	326	return has_errors;
bad50dc8	327	}