[thirdparty/git.git] / index-pack.c

#include "cache.h"
#include "delta.h"
#include "pack.h"
#include "csum-file.h"
#include "blob.h"
#include "commit.h"
#include "tag.h"
#include "tree.h"

static const char index_pack_usage[] =
"git-index-pack [-o <index-file>] { <pack-file> | --stdin [<pack-file>] }";

struct object_entry
{
	unsigned long offset;
	unsigned long size;
	unsigned int hdr_size;
	enum object_type type;
	enum object_type real_type;
	unsigned char sha1[20];
};

union delta_base {
	unsigned char sha1[20];
	unsigned long offset;
};

/*
 * Even if sizeof(union delta_base) == 24 on 64-bit archs, we really want
 * to memcmp() only the first 20 bytes.
 */
#define UNION_BASE_SZ	20

struct delta_entry
{
	struct object_entry *obj;
	union delta_base base;
};

static struct object_entry *objects;
static struct delta_entry *deltas;
static int nr_objects;
static int nr_deltas;

static int from_stdin;

/* We always read in 4kB chunks. */
static unsigned char input_buffer[4096];
static unsigned long input_offset, input_len, consumed_bytes;
static SHA_CTX input_ctx;
static int input_fd, output_fd, mmap_fd;

/*
 * 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 <= input_len)
		return input_buffer + input_offset;
	if (min > sizeof(input_buffer))
		die("cannot fill %d bytes", min);
	if (input_offset) {
		if (output_fd >= 0)
			write_or_die(output_fd, input_buffer, input_offset);
		SHA1_Update(&input_ctx, input_buffer, input_offset);
		memcpy(input_buffer, input_buffer + input_offset, input_len);
		input_offset = 0;
	}
	do {
		int ret = xread(input_fd, input_buffer + input_len,
				sizeof(input_buffer) - input_len);
		if (ret <= 0) {
			if (!ret)
				die("early EOF");
			die("read error on input: %s", strerror(errno));
		}
		input_len += ret;
	} while (input_len < min);
	return input_buffer;
}

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

static const char * open_pack_file(const char *pack_name)
{
	if (from_stdin) {
		input_fd = 0;
		if (!pack_name) {
			static char tmpfile[PATH_MAX];
			snprintf(tmpfile, sizeof(tmpfile),
				 "%s/pack_XXXXXX", get_object_directory());
			output_fd = mkstemp(tmpfile);
			pack_name = xstrdup(tmpfile);
		} else
			output_fd = open(pack_name, O_CREAT|O_EXCL|O_RDWR, 0600);
		if (output_fd < 0)
			die("unable to create %s: %s\n", pack_name, strerror(errno));
		mmap_fd = output_fd;
	} else {
		input_fd = open(pack_name, O_RDONLY);
		if (input_fd < 0)
			die("cannot open packfile '%s': %s",
			    pack_name, strerror(errno));
		output_fd = -1;
		mmap_fd = input_fd;
	}
	SHA1_Init(&input_ctx);
	return pack_name;
}

static void parse_pack_header(void)
{
	struct pack_header *hdr = fill(sizeof(struct pack_header));

	/* Header consistency check */
	if (hdr->hdr_signature != htonl(PACK_SIGNATURE))
		die("pack signature mismatch");
	if (!pack_version_ok(hdr->hdr_version))
		die("pack version %d unsupported", ntohl(hdr->hdr_version));

	nr_objects = ntohl(hdr->hdr_entries);
	use(sizeof(struct pack_header));
	/*fprintf(stderr, "Indexing %d objects\n", nr_objects);*/
}

static void bad_object(unsigned long offset, const char *format,
		       ...) NORETURN __attribute__((format (printf, 2, 3)));

static void bad_object(unsigned long offset, const char *format, ...)
{
	va_list params;
	char buf[1024];

	va_start(params, format);
	vsnprintf(buf, sizeof(buf), format, params);
	va_end(params);
	die("pack has bad object at offset %lu: %s", offset, buf);
}

static void *unpack_entry_data(unsigned long offset, 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 = input_len;
	inflateInit(&stream);

	for (;;) {
		int ret = inflate(&stream, 0);
		use(input_len - stream.avail_in);
		if (stream.total_out == size && ret == Z_STREAM_END)
			break;
		if (ret != Z_OK)
			bad_object(offset, "inflate returned %d", ret);
		stream.next_in = fill(1);
		stream.avail_in = input_len;
	}
	inflateEnd(&stream);
	return buf;
}

static void *unpack_raw_entry(struct object_entry *obj, union delta_base *delta_base)
{
	unsigned char *p, c;
	unsigned long size, base_offset;
	unsigned shift;

	obj->offset = consumed_bytes;

	p = fill(1);
	c = *p;
	use(1);
	obj->type = (c >> 4) & 7;
	size = (c & 15);
	shift = 4;
	while (c & 0x80) {
		p = fill(1);
		c = *p;
		use(1);
		size += (c & 0x7fUL) << shift;
		shift += 7;
	}
	obj->size = size;

	switch (obj->type) {
	case OBJ_REF_DELTA:
		hashcpy(delta_base->sha1, fill(20));
		use(20);
		break;
	case OBJ_OFS_DELTA:
		memset(delta_base, 0, sizeof(*delta_base));
		p = fill(1);
		c = *p;
		use(1);
		base_offset = c & 127;
		while (c & 128) {
			base_offset += 1;
			if (!base_offset || base_offset & ~(~0UL >> 7))
				bad_object(obj->offset, "offset value overflow for delta base object");
			p = fill(1);
			c = *p;
			use(1);
			base_offset = (base_offset << 7) + (c & 127);
		}
		delta_base->offset = obj->offset - base_offset;
		if (delta_base->offset >= obj->offset)
			bad_object(obj->offset, "delta base offset is out of bound");
		break;
	case OBJ_COMMIT:
	case OBJ_TREE:
	case OBJ_BLOB:
	case OBJ_TAG:
		break;
	default:
		bad_object(obj->offset, "bad object type %d", obj->type);
	}
	obj->hdr_size = consumed_bytes - obj->offset;

	return unpack_entry_data(obj->offset, obj->size);
}

static void * get_data_from_pack(struct object_entry *obj)
{
	unsigned long from = obj[0].offset + obj[0].hdr_size;
	unsigned long len = obj[1].offset - from;
	unsigned pg_offset = from % getpagesize();
	unsigned char *map, *data;
	z_stream stream;
	int st;

	map = mmap(NULL, len + pg_offset, PROT_READ, MAP_PRIVATE,
		   mmap_fd, from - pg_offset);
	if (map == MAP_FAILED)
		die("cannot mmap pack file: %s", strerror(errno));
	data = xmalloc(obj->size);
	memset(&stream, 0, sizeof(stream));
	stream.next_out = data;
	stream.avail_out = obj->size;
	stream.next_in = map + pg_offset;
	stream.avail_in = len;
	inflateInit(&stream);
	while ((st = inflate(&stream, Z_FINISH)) == Z_OK);
	inflateEnd(&stream);
	if (st != Z_STREAM_END || stream.total_out != obj->size)
		die("serious inflate inconsistency");
	munmap(map, len + pg_offset);
	return data;
}

static int find_delta(const union delta_base *base)
{
	int first = 0, last = nr_deltas;

        while (first < last) {
                int next = (first + last) / 2;
                struct delta_entry *delta = &deltas[next];
                int cmp;

                cmp = memcmp(base, &delta->base, UNION_BASE_SZ);
                if (!cmp)
                        return next;
                if (cmp < 0) {
                        last = next;
                        continue;
                }
                first = next+1;
        }
        return -first-1;
}

static int find_delta_childs(const union delta_base *base,
			     int *first_index, int *last_index)
{
	int first = find_delta(base);
	int last = first;
	int end = nr_deltas - 1;

	if (first < 0)
		return -1;
	while (first > 0 && !memcmp(&deltas[first - 1].base, base, UNION_BASE_SZ))
		--first;
	while (last < end && !memcmp(&deltas[last + 1].base, base, UNION_BASE_SZ))
		++last;
	*first_index = first;
	*last_index = last;
	return 0;
}

static void sha1_object(const void *data, unsigned long size,
			enum object_type type, unsigned char *sha1)
{
	SHA_CTX ctx;
	char header[50];
	int header_size;
	const char *type_str;

	switch (type) {
	case OBJ_COMMIT: type_str = commit_type; break;
	case OBJ_TREE:   type_str = tree_type; break;
	case OBJ_BLOB:   type_str = blob_type; break;
	case OBJ_TAG:    type_str = tag_type; break;
	default:
		die("bad type %d", type);
	}

	header_size = sprintf(header, "%s %lu", type_str, size) + 1;

	SHA1_Init(&ctx);
	SHA1_Update(&ctx, header, header_size);
	SHA1_Update(&ctx, data, size);
	SHA1_Final(sha1, &ctx);
}

static void resolve_delta(struct delta_entry *delta, void *base_data,
			  unsigned long base_size, enum object_type type)
{
	struct object_entry *obj = delta->obj;
	void *delta_data;
	unsigned long delta_size;
	void *result;
	unsigned long result_size;
	union delta_base delta_base;
	int j, first, last;

	obj->real_type = type;
	delta_data = get_data_from_pack(obj);
	delta_size = obj->size;
	result = patch_delta(base_data, base_size, delta_data, delta_size,
			     &result_size);
	free(delta_data);
	if (!result)
		bad_object(obj->offset, "failed to apply delta");
	sha1_object(result, result_size, type, obj->sha1);

	hashcpy(delta_base.sha1, obj->sha1);
	if (!find_delta_childs(&delta_base, &first, &last)) {
		for (j = first; j <= last; j++)
			if (deltas[j].obj->type == OBJ_REF_DELTA)
				resolve_delta(&deltas[j], result, result_size, type);
	}

	memset(&delta_base, 0, sizeof(delta_base));
	delta_base.offset = obj->offset;
	if (!find_delta_childs(&delta_base, &first, &last)) {
		for (j = first; j <= last; j++)
			if (deltas[j].obj->type == OBJ_OFS_DELTA)
				resolve_delta(&deltas[j], result, result_size, type);
	}

	free(result);
}

static int compare_delta_entry(const void *a, const void *b)
{
	const struct delta_entry *delta_a = a;
	const struct delta_entry *delta_b = b;
	return memcmp(&delta_a->base, &delta_b->base, UNION_BASE_SZ);
}

/* Parse all objects and return the pack content SHA1 hash */
static void parse_pack_objects(unsigned char *sha1)
{
	int i;
	struct delta_entry *delta = deltas;
	void *data;
	struct stat st;

	/*
	 * First pass:
	 * - find locations of all objects;
	 * - calculate SHA1 of all non-delta objects;
	 * - remember base SHA1 for all deltas.
	 */
	for (i = 0; i < nr_objects; i++) {
		struct object_entry *obj = &objects[i];
		data = unpack_raw_entry(obj, &delta->base);
		obj->real_type = obj->type;
		if (obj->type == OBJ_REF_DELTA || obj->type == OBJ_OFS_DELTA) {
			nr_deltas++;
			delta->obj = obj;
			delta++;
		} else
			sha1_object(data, obj->size, obj->type, obj->sha1);
		free(data);
	}
	objects[i].offset = consumed_bytes;

	/* Check pack integrity */
	SHA1_Update(&input_ctx, input_buffer, input_offset);
	SHA1_Final(sha1, &input_ctx);
	if (hashcmp(fill(20), sha1))
		die("pack is corrupted (SHA1 mismatch)");
	use(20);
	if (output_fd >= 0)
		write_or_die(output_fd, input_buffer, input_offset);

	/* If input_fd is a file, we should have reached its end now. */
	if (fstat(input_fd, &st))
		die("cannot fstat packfile: %s", strerror(errno));
	if (S_ISREG(st.st_mode) && st.st_size != consumed_bytes)
		die("pack has junk at the end");

	/* Sort deltas by base SHA1/offset for fast searching */
	qsort(deltas, nr_deltas, sizeof(struct delta_entry),
	      compare_delta_entry);

	/*
	 * Second pass:
	 * - for all non-delta objects, look if it is used as a base for
	 *   deltas;
	 * - if used as a base, uncompress the object and apply all deltas,
	 *   recursively checking if the resulting object is used as a base
	 *   for some more deltas.
	 */
	for (i = 0; i < nr_objects; i++) {
		struct object_entry *obj = &objects[i];
		union delta_base base;
		int j, ref, ref_first, ref_last, ofs, ofs_first, ofs_last;

		if (obj->type == OBJ_REF_DELTA || obj->type == OBJ_OFS_DELTA)
			continue;
		hashcpy(base.sha1, obj->sha1);
		ref = !find_delta_childs(&base, &ref_first, &ref_last);
		memset(&base, 0, sizeof(base));
		base.offset = obj->offset;
		ofs = !find_delta_childs(&base, &ofs_first, &ofs_last);
		if (!ref && !ofs)
			continue;
		data = get_data_from_pack(obj);
		if (ref)
			for (j = ref_first; j <= ref_last; j++)
				if (deltas[j].obj->type == OBJ_REF_DELTA)
					resolve_delta(&deltas[j], data,
						      obj->size, obj->type);
		if (ofs)
			for (j = ofs_first; j <= ofs_last; j++)
				if (deltas[j].obj->type == OBJ_OFS_DELTA)
					resolve_delta(&deltas[j], data,
						      obj->size, obj->type);
		free(data);
	}

	/* Check for unresolved deltas */
	for (i = 0; i < nr_deltas; i++) {
		if (deltas[i].obj->real_type == OBJ_REF_DELTA ||
		    deltas[i].obj->real_type == OBJ_OFS_DELTA)
			die("pack has unresolved deltas");
	}
}

static int sha1_compare(const void *_a, const void *_b)
{
	struct object_entry *a = *(struct object_entry **)_a;
	struct object_entry *b = *(struct object_entry **)_b;
	return hashcmp(a->sha1, b->sha1);
}

/*
 * On entry *sha1 contains the pack content SHA1 hash, on exit it is
 * the SHA1 hash of sorted object names.
 */
static const char * write_index_file(const char *index_name, unsigned char *sha1)
{
	struct sha1file *f;
	struct object_entry **sorted_by_sha, **list, **last;
	unsigned int array[256];
	int i, fd;
	SHA_CTX ctx;

	if (nr_objects) {
		sorted_by_sha =
			xcalloc(nr_objects, sizeof(struct object_entry *));
		list = sorted_by_sha;
		last = sorted_by_sha + nr_objects;
		for (i = 0; i < nr_objects; ++i)
			sorted_by_sha[i] = &objects[i];
		qsort(sorted_by_sha, nr_objects, sizeof(sorted_by_sha[0]),
		      sha1_compare);

	}
	else
		sorted_by_sha = list = last = NULL;

	if (!index_name) {
		static char tmpfile[PATH_MAX];
		snprintf(tmpfile, sizeof(tmpfile),
			 "%s/index_XXXXXX", get_object_directory());
		fd = mkstemp(tmpfile);
		index_name = xstrdup(tmpfile);
	} else {
		unlink(index_name);
		fd = open(index_name, O_CREAT|O_EXCL|O_WRONLY, 0600);
	}
	if (fd < 0)
		die("unable to create %s: %s", index_name, strerror(errno));
	f = sha1fd(fd, index_name);

	/*
	 * Write the first-level table (the list is sorted,
	 * but we use a 256-entry lookup to be able to avoid
	 * having to do eight extra binary search iterations).
	 */
	for (i = 0; i < 256; i++) {
		struct object_entry **next = list;
		while (next < last) {
			struct object_entry *obj = *next;
			if (obj->sha1[0] != i)
				break;
			next++;
		}
		array[i] = htonl(next - sorted_by_sha);
		list = next;
	}
	sha1write(f, array, 256 * sizeof(int));

	/* recompute the SHA1 hash of sorted object names.
	 * currently pack-objects does not do this, but that
	 * can be fixed.
	 */
	SHA1_Init(&ctx);
	/*
	 * Write the actual SHA1 entries..
	 */
	list = sorted_by_sha;
	for (i = 0; i < nr_objects; i++) {
		struct object_entry *obj = *list++;
		unsigned int offset = htonl(obj->offset);
		sha1write(f, &offset, 4);
		sha1write(f, obj->sha1, 20);
		SHA1_Update(&ctx, obj->sha1, 20);
	}
	sha1write(f, sha1, 20);
	sha1close(f, NULL, 1);
	free(sorted_by_sha);
	SHA1_Final(sha1, &ctx);
	return index_name;
}

static void final(const char *final_pack_name, const char *curr_pack_name,
		  const char *final_index_name, const char *curr_index_name,
		  unsigned char *sha1)
{
	char name[PATH_MAX];
	int err;

	if (!from_stdin) {
		close(input_fd);
	} else {
		err = close(output_fd);
		if (err)
			die("error while closing pack file: %s", strerror(errno));
		chmod(curr_pack_name, 0444);
	}

	if (final_pack_name != curr_pack_name) {
		if (!final_pack_name) {
			snprintf(name, sizeof(name), "%s/pack/pack-%s.pack",
				 get_object_directory(), sha1_to_hex(sha1));
			final_pack_name = name;
		}
		if (move_temp_to_file(curr_pack_name, final_pack_name))
			die("cannot store pack file");
	}

	chmod(curr_index_name, 0444);
	if (final_index_name != curr_index_name) {
		if (!final_index_name) {
			snprintf(name, sizeof(name), "%s/pack/pack-%s.idx",
				 get_object_directory(), sha1_to_hex(sha1));
			final_index_name = name;
		}
		if (move_temp_to_file(curr_index_name, final_index_name))
			die("cannot store index file");
	}
}

int main(int argc, char **argv)
{
	int i;
	const char *curr_pack, *pack_name = NULL;
	const char *curr_index, *index_name = NULL;
	char *index_name_buf = NULL;
	unsigned char sha1[20];

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

		if (*arg == '-') {
			if (!strcmp(arg, "--stdin")) {
				from_stdin = 1;
			} else if (!strcmp(arg, "-o")) {
				if (index_name || (i+1) >= argc)
					usage(index_pack_usage);
				index_name = argv[++i];
			} else
				usage(index_pack_usage);
			continue;
		}

		if (pack_name)
			usage(index_pack_usage);
		pack_name = arg;
	}

	if (!pack_name && !from_stdin)
		usage(index_pack_usage);
	if (!index_name && pack_name) {
		int len = strlen(pack_name);
		if (!has_extension(pack_name, ".pack"))
			die("packfile name '%s' does not end with '.pack'",
			    pack_name);
		index_name_buf = xmalloc(len);
		memcpy(index_name_buf, pack_name, len - 5);
		strcpy(index_name_buf + len - 5, ".idx");
		index_name = index_name_buf;
	}

	curr_pack = open_pack_file(pack_name);
	parse_pack_header();
	objects = xcalloc(nr_objects + 1, sizeof(struct object_entry));
	deltas = xcalloc(nr_objects, sizeof(struct delta_entry));
	parse_pack_objects(sha1);
	free(deltas);
	curr_index = write_index_file(index_name, sha1);
	final(pack_name, curr_pack, index_name, curr_index, sha1);
	free(objects);
	free(index_name_buf);

	printf("%s\n", sha1_to_hex(sha1));

	return 0;
}
Commit	Line	Data
9cf6d335 SV	1	#include "cache.h"
	2	#include "delta.h"
	3	#include "pack.h"
	4	#include "csum-file.h"
8e440259 PE	5	#include "blob.h"
	6	#include "commit.h"
	7	#include "tag.h"
	8	#include "tree.h"
9cf6d335 SV	9
9cf6d335 SV	10	static const char index_pack_usage[] =
e42797f5	11	"git-index-pack [-o <index-file>] { <pack-file> \| --stdin [<pack-file>] }";
9cf6d335 SV	12
	13	struct object_entry
	14	{
	15	unsigned long offset;
2d477051 NP	16	unsigned long size;
2d477051 NP	17	unsigned int hdr_size;
9cf6d335 SV	18	enum object_type type;
	19	enum object_type real_type;
	20	unsigned char sha1[20];
	21	};
	22
53dda6ff NP	23	union delta_base {
	24	unsigned char sha1[20];
	25	unsigned long offset;
	26	};
	27
3c552873 NP	28	/*
	29	* Even if sizeof(union delta_base) == 24 on 64-bit archs, we really want
	30	* to memcmp() only the first 20 bytes.
	31	*/
	32	#define UNION_BASE_SZ 20
	33
9cf6d335 SV	34	struct delta_entry
	35	{
	36	struct object_entry *obj;
53dda6ff	37	union delta_base base;
9cf6d335 SV	38	};
9cf6d335 SV	39
9cf6d335 SV	40	static struct object_entry *objects;
	41	static struct delta_entry *deltas;
	42	static int nr_objects;
	43	static int nr_deltas;
	44
e42797f5 NP	45	static int from_stdin;
e42797f5 NP	46
2d477051 NP	47	/* We always read in 4kB chunks. */
	48	static unsigned char input_buffer[4096];
	49	static unsigned long input_offset, input_len, consumed_bytes;
	50	static SHA_CTX input_ctx;
e42797f5	51	static int input_fd, output_fd, mmap_fd;
2d477051 NP	52
	53	/*
	54	* Make sure at least "min" bytes are available in the buffer, and
	55	* return the pointer to the buffer.
	56	*/
	57	static void * fill(int min)
9cf6d335	58	{
2d477051 NP	59	if (min <= input_len)
	60	return input_buffer + input_offset;
	61	if (min > sizeof(input_buffer))
	62	die("cannot fill %d bytes", min);
	63	if (input_offset) {
e42797f5 NP	64	if (output_fd >= 0)
e42797f5 NP	65	write_or_die(output_fd, input_buffer, input_offset);
2d477051 NP	66	SHA1_Update(&input_ctx, input_buffer, input_offset);
	67	memcpy(input_buffer, input_buffer + input_offset, input_len);
	68	input_offset = 0;
	69	}
	70	do {
	71	int ret = xread(input_fd, input_buffer + input_len,
	72	sizeof(input_buffer) - input_len);
	73	if (ret <= 0) {
	74	if (!ret)
	75	die("early EOF");
	76	die("read error on input: %s", strerror(errno));
	77	}
	78	input_len += ret;
	79	} while (input_len < min);
	80	return input_buffer;
	81	}
	82
	83	static void use(int bytes)
	84	{
	85	if (bytes > input_len)
	86	die("used more bytes than were available");
	87	input_len -= bytes;
	88	input_offset += bytes;
	89	consumed_bytes += bytes;
	90	}
9cf6d335	91
e42797f5	92	static const char * open_pack_file(const char *pack_name)
2d477051	93	{
e42797f5 NP	94	if (from_stdin) {
	95	input_fd = 0;
	96	if (!pack_name) {
	97	static char tmpfile[PATH_MAX];
	98	snprintf(tmpfile, sizeof(tmpfile),
	99	"%s/pack_XXXXXX", get_object_directory());
	100	output_fd = mkstemp(tmpfile);
	101	pack_name = xstrdup(tmpfile);
	102	} else
	103	output_fd = open(pack_name, O_CREAT\|O_EXCL\|O_RDWR, 0600);
	104	if (output_fd < 0)
	105	die("unable to create %s: %s\n", pack_name, strerror(errno));
	106	mmap_fd = output_fd;
	107	} else {
	108	input_fd = open(pack_name, O_RDONLY);
	109	if (input_fd < 0)
	110	die("cannot open packfile '%s': %s",
	111	pack_name, strerror(errno));
	112	output_fd = -1;
	113	mmap_fd = input_fd;
	114	}
2d477051	115	SHA1_Init(&input_ctx);
e42797f5	116	return pack_name;
9cf6d335 SV	117	}
	118
	119	static void parse_pack_header(void)
	120	{
2d477051	121	struct pack_header *hdr = fill(sizeof(struct pack_header));
9cf6d335 SV	122
9cf6d335 SV	123	/* Header consistency check */
9cf6d335	124	if (hdr->hdr_signature != htonl(PACK_SIGNATURE))
e42797f5	125	die("pack signature mismatch");
d60fc1c8	126	if (!pack_version_ok(hdr->hdr_version))
e42797f5	127	die("pack version %d unsupported", ntohl(hdr->hdr_version));
9cf6d335 SV	128
9cf6d335 SV	129	nr_objects = ntohl(hdr->hdr_entries);
2d477051 NP	130	use(sizeof(struct pack_header));
2d477051 NP	131	/fprintf(stderr, "Indexing %d objects\n", nr_objects);/
9cf6d335 SV	132	}
	133
	134	static void bad_object(unsigned long offset, const char *format,
	135	...) NORETURN __attribute__((format (printf, 2, 3)));
	136
	137	static void bad_object(unsigned long offset, const char *format, ...)
	138	{
	139	va_list params;
	140	char buf[1024];
	141
	142	va_start(params, format);
	143	vsnprintf(buf, sizeof(buf), format, params);
	144	va_end(params);
e42797f5	145	die("pack has bad object at offset %lu: %s", offset, buf);
9cf6d335 SV	146	}
9cf6d335 SV	147
2d477051	148	static void *unpack_entry_data(unsigned long offset, unsigned long size)
9cf6d335	149	{
9cf6d335 SV	150	z_stream stream;
	151	void *buf = xmalloc(size);
	152
	153	memset(&stream, 0, sizeof(stream));
	154	stream.next_out = buf;
	155	stream.avail_out = size;
2d477051 NP	156	stream.next_in = fill(1);
2d477051 NP	157	stream.avail_in = input_len;
9cf6d335 SV	158	inflateInit(&stream);
	159
	160	for (;;) {
	161	int ret = inflate(&stream, 0);
2d477051 NP	162	use(input_len - stream.avail_in);
2d477051 NP	163	if (stream.total_out == size && ret == Z_STREAM_END)
9cf6d335 SV	164	break;
	165	if (ret != Z_OK)
	166	bad_object(offset, "inflate returned %d", ret);
2d477051 NP	167	stream.next_in = fill(1);
2d477051 NP	168	stream.avail_in = input_len;
9cf6d335 SV	169	}
9cf6d335 SV	170	inflateEnd(&stream);
9cf6d335 SV	171	return buf;
	172	}
	173
2d477051	174	static void unpack_raw_entry(struct object_entry obj, union delta_base *delta_base)
9cf6d335	175	{
2d477051	176	unsigned char *p, c;
53dda6ff	177	unsigned long size, base_offset;
9cf6d335	178	unsigned shift;
9cf6d335	179
2d477051 NP	180	obj->offset = consumed_bytes;
	181
	182	p = fill(1);
	183	c = *p;
	184	use(1);
	185	obj->type = (c >> 4) & 7;
9cf6d335 SV	186	size = (c & 15);
	187	shift = 4;
	188	while (c & 0x80) {
2d477051 NP	189	p = fill(1);
	190	c = *p;
	191	use(1);
9cf6d335 SV	192	size += (c & 0x7fUL) << shift;
	193	shift += 7;
	194	}
2d477051	195	obj->size = size;
9cf6d335	196
2d477051	197	switch (obj->type) {
eb32d236	198	case OBJ_REF_DELTA:
2d477051 NP	199	hashcpy(delta_base->sha1, fill(20));
2d477051 NP	200	use(20);
53dda6ff NP	201	break;
	202	case OBJ_OFS_DELTA:
	203	memset(delta_base, 0, sizeof(*delta_base));
2d477051 NP	204	p = fill(1);
	205	c = *p;
	206	use(1);
53dda6ff NP	207	base_offset = c & 127;
	208	while (c & 128) {
	209	base_offset += 1;
	210	if (!base_offset \|\| base_offset & ~(~0UL >> 7))
2d477051 NP	211	bad_object(obj->offset, "offset value overflow for delta base object");
	212	p = fill(1);
	213	c = *p;
	214	use(1);
53dda6ff NP	215	base_offset = (base_offset << 7) + (c & 127);
53dda6ff NP	216	}
2d477051 NP	217	delta_base->offset = obj->offset - base_offset;
	218	if (delta_base->offset >= obj->offset)
	219	bad_object(obj->offset, "delta base offset is out of bound");
53dda6ff	220	break;
9cf6d335 SV	221	case OBJ_COMMIT:
	222	case OBJ_TREE:
	223	case OBJ_BLOB:
	224	case OBJ_TAG:
9cf6d335 SV	225	break;
9cf6d335 SV	226	default:
2d477051	227	bad_object(obj->offset, "bad object type %d", obj->type);
9cf6d335	228	}
2d477051 NP	229	obj->hdr_size = consumed_bytes - obj->offset;
	230
	231	return unpack_entry_data(obj->offset, obj->size);
	232	}
	233
	234	static void * get_data_from_pack(struct object_entry *obj)
	235	{
	236	unsigned long from = obj[0].offset + obj[0].hdr_size;
	237	unsigned long len = obj[1].offset - from;
	238	unsigned pg_offset = from % getpagesize();
	239	unsigned char map, data;
	240	z_stream stream;
	241	int st;
9cf6d335	242
2d477051	243	map = mmap(NULL, len + pg_offset, PROT_READ, MAP_PRIVATE,
e42797f5	244	mmap_fd, from - pg_offset);
2d477051	245	if (map == MAP_FAILED)
e42797f5	246	die("cannot mmap pack file: %s", strerror(errno));
2d477051 NP	247	data = xmalloc(obj->size);
	248	memset(&stream, 0, sizeof(stream));
	249	stream.next_out = data;
	250	stream.avail_out = obj->size;
	251	stream.next_in = map + pg_offset;
	252	stream.avail_in = len;
	253	inflateInit(&stream);
	254	while ((st = inflate(&stream, Z_FINISH)) == Z_OK);
	255	inflateEnd(&stream);
	256	if (st != Z_STREAM_END \|\| stream.total_out != obj->size)
	257	die("serious inflate inconsistency");
	258	munmap(map, len + pg_offset);
9cf6d335 SV	259	return data;
	260	}
	261
53dda6ff	262	static int find_delta(const union delta_base *base)
9cf6d335 SV	263	{
	264	int first = 0, last = nr_deltas;
	265
	266	while (first < last) {
	267	int next = (first + last) / 2;
	268	struct delta_entry *delta = &deltas[next];
	269	int cmp;
	270
3c552873	271	cmp = memcmp(base, &delta->base, UNION_BASE_SZ);
9cf6d335 SV	272	if (!cmp)
	273	return next;
	274	if (cmp < 0) {
	275	last = next;
	276	continue;
	277	}
	278	first = next+1;
	279	}
	280	return -first-1;
	281	}
	282
53dda6ff NP	283	static int find_delta_childs(const union delta_base *base,
53dda6ff NP	284	int first_index, int last_index)
9cf6d335	285	{
53dda6ff	286	int first = find_delta(base);
9cf6d335 SV	287	int last = first;
	288	int end = nr_deltas - 1;
	289
	290	if (first < 0)
	291	return -1;
3c552873	292	while (first > 0 && !memcmp(&deltas[first - 1].base, base, UNION_BASE_SZ))
9cf6d335	293	--first;
3c552873	294	while (last < end && !memcmp(&deltas[last + 1].base, base, UNION_BASE_SZ))
9cf6d335 SV	295	++last;
	296	*first_index = first;
	297	*last_index = last;
	298	return 0;
	299	}
	300
	301	static void sha1_object(const void *data, unsigned long size,
	302	enum object_type type, unsigned char *sha1)
	303	{
	304	SHA_CTX ctx;
	305	char header[50];
	306	int header_size;
	307	const char *type_str;
	308
	309	switch (type) {
8e440259 PE	310	case OBJ_COMMIT: type_str = commit_type; break;
	311	case OBJ_TREE: type_str = tree_type; break;
	312	case OBJ_BLOB: type_str = blob_type; break;
	313	case OBJ_TAG: type_str = tag_type; break;
9cf6d335 SV	314	default:
	315	die("bad type %d", type);
	316	}
	317
	318	header_size = sprintf(header, "%s %lu", type_str, size) + 1;
	319
	320	SHA1_Init(&ctx);
	321	SHA1_Update(&ctx, header, header_size);
	322	SHA1_Update(&ctx, data, size);
	323	SHA1_Final(sha1, &ctx);
	324	}
	325
	326	static void resolve_delta(struct delta_entry delta, void base_data,
	327	unsigned long base_size, enum object_type type)
	328	{
	329	struct object_entry *obj = delta->obj;
	330	void *delta_data;
	331	unsigned long delta_size;
	332	void *result;
	333	unsigned long result_size;
53dda6ff	334	union delta_base delta_base;
9cf6d335 SV	335	int j, first, last;
	336
	337	obj->real_type = type;
2d477051 NP	338	delta_data = get_data_from_pack(obj);
2d477051 NP	339	delta_size = obj->size;
9cf6d335 SV	340	result = patch_delta(base_data, base_size, delta_data, delta_size,
	341	&result_size);
	342	free(delta_data);
	343	if (!result)
	344	bad_object(obj->offset, "failed to apply delta");
	345	sha1_object(result, result_size, type, obj->sha1);
53dda6ff NP	346
	347	hashcpy(delta_base.sha1, obj->sha1);
	348	if (!find_delta_childs(&delta_base, &first, &last)) {
	349	for (j = first; j <= last; j++)
	350	if (deltas[j].obj->type == OBJ_REF_DELTA)
	351	resolve_delta(&deltas[j], result, result_size, type);
	352	}
	353
	354	memset(&delta_base, 0, sizeof(delta_base));
	355	delta_base.offset = obj->offset;
	356	if (!find_delta_childs(&delta_base, &first, &last)) {
9cf6d335	357	for (j = first; j <= last; j++)
53dda6ff NP	358	if (deltas[j].obj->type == OBJ_OFS_DELTA)
53dda6ff NP	359	resolve_delta(&deltas[j], result, result_size, type);
9cf6d335	360	}
53dda6ff	361
9cf6d335 SV	362	free(result);
	363	}
	364
	365	static int compare_delta_entry(const void a, const void b)
	366	{
	367	const struct delta_entry *delta_a = a;
	368	const struct delta_entry *delta_b = b;
3c552873	369	return memcmp(&delta_a->base, &delta_b->base, UNION_BASE_SZ);
9cf6d335 SV	370	}
9cf6d335 SV	371
2d477051 NP	372	/* Parse all objects and return the pack content SHA1 hash */
2d477051 NP	373	static void parse_pack_objects(unsigned char *sha1)
9cf6d335 SV	374	{
9cf6d335 SV	375	int i;
53dda6ff	376	struct delta_entry *delta = deltas;
9cf6d335	377	void *data;
2d477051	378	struct stat st;
9cf6d335 SV	379
	380	/*
	381	* First pass:
	382	* - find locations of all objects;
	383	* - calculate SHA1 of all non-delta objects;
	384	* - remember base SHA1 for all deltas.
	385	*/
	386	for (i = 0; i < nr_objects; i++) {
	387	struct object_entry *obj = &objects[i];
2d477051	388	data = unpack_raw_entry(obj, &delta->base);
9cf6d335	389	obj->real_type = obj->type;
53dda6ff NP	390	if (obj->type == OBJ_REF_DELTA \|\| obj->type == OBJ_OFS_DELTA) {
53dda6ff NP	391	nr_deltas++;
9cf6d335	392	delta->obj = obj;
53dda6ff	393	delta++;
9cf6d335	394	} else
2d477051	395	sha1_object(data, obj->size, obj->type, obj->sha1);
9cf6d335 SV	396	free(data);
9cf6d335 SV	397	}
2d477051 NP	398	objects[i].offset = consumed_bytes;
	399
	400	/* Check pack integrity */
	401	SHA1_Update(&input_ctx, input_buffer, input_offset);
	402	SHA1_Final(sha1, &input_ctx);
	403	if (hashcmp(fill(20), sha1))
e42797f5	404	die("pack is corrupted (SHA1 mismatch)");
2d477051	405	use(20);
e42797f5 NP	406	if (output_fd >= 0)
e42797f5 NP	407	write_or_die(output_fd, input_buffer, input_offset);
2d477051 NP	408
	409	/* If input_fd is a file, we should have reached its end now. */
	410	if (fstat(input_fd, &st))
e42797f5	411	die("cannot fstat packfile: %s", strerror(errno));
2d477051	412	if (S_ISREG(st.st_mode) && st.st_size != consumed_bytes)
e42797f5	413	die("pack has junk at the end");
9cf6d335	414
53dda6ff	415	/* Sort deltas by base SHA1/offset for fast searching */
9cf6d335 SV	416	qsort(deltas, nr_deltas, sizeof(struct delta_entry),
	417	compare_delta_entry);
	418
	419	/*
	420	* Second pass:
	421	* - for all non-delta objects, look if it is used as a base for
	422	* deltas;
	423	* - if used as a base, uncompress the object and apply all deltas,
	424	* recursively checking if the resulting object is used as a base
	425	* for some more deltas.
	426	*/
	427	for (i = 0; i < nr_objects; i++) {
	428	struct object_entry *obj = &objects[i];
53dda6ff NP	429	union delta_base base;
53dda6ff NP	430	int j, ref, ref_first, ref_last, ofs, ofs_first, ofs_last;
9cf6d335	431
53dda6ff	432	if (obj->type == OBJ_REF_DELTA \|\| obj->type == OBJ_OFS_DELTA)
9cf6d335	433	continue;
53dda6ff NP	434	hashcpy(base.sha1, obj->sha1);
	435	ref = !find_delta_childs(&base, &ref_first, &ref_last);
	436	memset(&base, 0, sizeof(base));
	437	base.offset = obj->offset;
	438	ofs = !find_delta_childs(&base, &ofs_first, &ofs_last);
	439	if (!ref && !ofs)
9cf6d335	440	continue;
2d477051	441	data = get_data_from_pack(obj);
53dda6ff NP	442	if (ref)
	443	for (j = ref_first; j <= ref_last; j++)
	444	if (deltas[j].obj->type == OBJ_REF_DELTA)
	445	resolve_delta(&deltas[j], data,
2d477051	446	obj->size, obj->type);
53dda6ff NP	447	if (ofs)
	448	for (j = ofs_first; j <= ofs_last; j++)
	449	if (deltas[j].obj->type == OBJ_OFS_DELTA)
	450	resolve_delta(&deltas[j], data,
2d477051	451	obj->size, obj->type);
9cf6d335 SV	452	free(data);
	453	}
	454
	455	/* Check for unresolved deltas */
	456	for (i = 0; i < nr_deltas; i++) {
53dda6ff NP	457	if (deltas[i].obj->real_type == OBJ_REF_DELTA \|\|
53dda6ff NP	458	deltas[i].obj->real_type == OBJ_OFS_DELTA)
e42797f5	459	die("pack has unresolved deltas");
9cf6d335 SV	460	}
	461	}
	462
	463	static int sha1_compare(const void _a, const void _b)
	464	{
	465	struct object_entry a = (struct object_entry **)_a;
	466	struct object_entry b = (struct object_entry **)_b;
a89fccd2	467	return hashcmp(a->sha1, b->sha1);
9cf6d335 SV	468	}
9cf6d335 SV	469
2d477051 NP	470	/*
	471	* On entry *sha1 contains the pack content SHA1 hash, on exit it is
	472	* the SHA1 hash of sorted object names.
	473	*/
e42797f5	474	static const char * write_index_file(const char index_name, unsigned char sha1)
9cf6d335 SV	475	{
9cf6d335 SV	476	struct sha1file *f;
7e4a2a84	477	struct object_entry sorted_by_sha, list, **last;
9cf6d335	478	unsigned int array[256];
e42797f5	479	int i, fd;
84c8d8ae	480	SHA_CTX ctx;
9cf6d335	481
7e4a2a84 JH	482	if (nr_objects) {
	483	sorted_by_sha =
	484	xcalloc(nr_objects, sizeof(struct object_entry *));
	485	list = sorted_by_sha;
	486	last = sorted_by_sha + nr_objects;
	487	for (i = 0; i < nr_objects; ++i)
	488	sorted_by_sha[i] = &objects[i];
	489	qsort(sorted_by_sha, nr_objects, sizeof(sorted_by_sha[0]),
	490	sha1_compare);
	491
	492	}
	493	else
	494	sorted_by_sha = list = last = NULL;
9cf6d335	495
e42797f5 NP	496	if (!index_name) {
	497	static char tmpfile[PATH_MAX];
	498	snprintf(tmpfile, sizeof(tmpfile),
	499	"%s/index_XXXXXX", get_object_directory());
	500	fd = mkstemp(tmpfile);
	501	index_name = xstrdup(tmpfile);
	502	} else {
	503	unlink(index_name);
	504	fd = open(index_name, O_CREAT\|O_EXCL\|O_WRONLY, 0600);
	505	}
	506	if (fd < 0)
	507	die("unable to create %s: %s", index_name, strerror(errno));
	508	f = sha1fd(fd, index_name);
9cf6d335 SV	509
	510	/*
	511	* Write the first-level table (the list is sorted,
	512	* but we use a 256-entry lookup to be able to avoid
	513	* having to do eight extra binary search iterations).
	514	*/
	515	for (i = 0; i < 256; i++) {
	516	struct object_entry **next = list;
	517	while (next < last) {
	518	struct object_entry obj = next;
	519	if (obj->sha1[0] != i)
	520	break;
	521	next++;
	522	}
	523	array[i] = htonl(next - sorted_by_sha);
	524	list = next;
	525	}
	526	sha1write(f, array, 256 * sizeof(int));
	527
84c8d8ae JH	528	/* recompute the SHA1 hash of sorted object names.
	529	* currently pack-objects does not do this, but that
	530	* can be fixed.
	531	*/
	532	SHA1_Init(&ctx);
9cf6d335 SV	533	/*
	534	* Write the actual SHA1 entries..
	535	*/
	536	list = sorted_by_sha;
	537	for (i = 0; i < nr_objects; i++) {
	538	struct object_entry obj = list++;
	539	unsigned int offset = htonl(obj->offset);
	540	sha1write(f, &offset, 4);
	541	sha1write(f, obj->sha1, 20);
84c8d8ae	542	SHA1_Update(&ctx, obj->sha1, 20);
9cf6d335	543	}
2d477051	544	sha1write(f, sha1, 20);
9cf6d335 SV	545	sha1close(f, NULL, 1);
9cf6d335 SV	546	free(sorted_by_sha);
84c8d8ae	547	SHA1_Final(sha1, &ctx);
e42797f5 NP	548	return index_name;
	549	}
	550
	551	static void final(const char final_pack_name, const char curr_pack_name,
	552	const char final_index_name, const char curr_index_name,
	553	unsigned char *sha1)
	554	{
	555	char name[PATH_MAX];
	556	int err;
	557
	558	if (!from_stdin) {
	559	close(input_fd);
	560	} else {
	561	err = close(output_fd);
	562	if (err)
	563	die("error while closing pack file: %s", strerror(errno));
	564	chmod(curr_pack_name, 0444);
	565	}
	566
	567	if (final_pack_name != curr_pack_name) {
	568	if (!final_pack_name) {
	569	snprintf(name, sizeof(name), "%s/pack/pack-%s.pack",
	570	get_object_directory(), sha1_to_hex(sha1));
	571	final_pack_name = name;
	572	}
	573	if (move_temp_to_file(curr_pack_name, final_pack_name))
	574	die("cannot store pack file");
	575	}
	576
	577	chmod(curr_index_name, 0444);
	578	if (final_index_name != curr_index_name) {
	579	if (!final_index_name) {
	580	snprintf(name, sizeof(name), "%s/pack/pack-%s.idx",
	581	get_object_directory(), sha1_to_hex(sha1));
	582	final_index_name = name;
	583	}
	584	if (move_temp_to_file(curr_index_name, final_index_name))
	585	die("cannot store index file");
	586	}
9cf6d335 SV	587	}
	588
	589	int main(int argc, char **argv)
	590	{
	591	int i;
e42797f5 NP	592	const char curr_pack, pack_name = NULL;
e42797f5 NP	593	const char curr_index, index_name = NULL;
9cf6d335	594	char *index_name_buf = NULL;
84c8d8ae	595	unsigned char sha1[20];
9cf6d335 SV	596
	597	for (i = 1; i < argc; i++) {
	598	const char *arg = argv[i];
	599
	600	if (*arg == '-') {
e42797f5 NP	601	if (!strcmp(arg, "--stdin")) {
	602	from_stdin = 1;
	603	} else if (!strcmp(arg, "-o")) {
9cf6d335 SV	604	if (index_name \|\| (i+1) >= argc)
	605	usage(index_pack_usage);
	606	index_name = argv[++i];
	607	} else
	608	usage(index_pack_usage);
	609	continue;
	610	}
	611
	612	if (pack_name)
	613	usage(index_pack_usage);
	614	pack_name = arg;
	615	}
	616
e42797f5	617	if (!pack_name && !from_stdin)
9cf6d335	618	usage(index_pack_usage);
e42797f5	619	if (!index_name && pack_name) {
9cf6d335	620	int len = strlen(pack_name);
5bb1cda5	621	if (!has_extension(pack_name, ".pack"))
9cf6d335 SV	622	die("packfile name '%s' does not end with '.pack'",
9cf6d335 SV	623	pack_name);
6689f087	624	index_name_buf = xmalloc(len);
9cf6d335 SV	625	memcpy(index_name_buf, pack_name, len - 5);
	626	strcpy(index_name_buf + len - 5, ".idx");
	627	index_name = index_name_buf;
	628	}
	629
e42797f5	630	curr_pack = open_pack_file(pack_name);
9cf6d335	631	parse_pack_header();
2d477051	632	objects = xcalloc(nr_objects + 1, sizeof(struct object_entry));
9cf6d335	633	deltas = xcalloc(nr_objects, sizeof(struct delta_entry));
2d477051	634	parse_pack_objects(sha1);
9cf6d335	635	free(deltas);
e42797f5 NP	636	curr_index = write_index_file(index_name, sha1);
e42797f5 NP	637	final(pack_name, curr_pack, index_name, curr_index, sha1);
9cf6d335 SV	638	free(objects);
	639	free(index_name_buf);
	640
84c8d8ae JH	641	printf("%s\n", sha1_to_hex(sha1));
84c8d8ae JH	642
9cf6d335 SV	643	return 0;
9cf6d335 SV	644	}