[thirdparty/git.git] / archive-tar.c

/*
 * Copyright (c) 2005, 2006 Rene Scharfe
 */
#include "cache.h"
#include "tar.h"
#include "archive.h"
#include "run-command.h"

#define RECORDSIZE	(512)
#define BLOCKSIZE	(RECORDSIZE * 20)

static char block[BLOCKSIZE];
static unsigned long offset;

static int tar_umask = 002;

static int write_tar_filter_archive(const struct archiver *ar,
				    struct archiver_args *args);

/* writes out the whole block, but only if it is full */
static void write_if_needed(void)
{
	if (offset == BLOCKSIZE) {
		write_or_die(1, block, BLOCKSIZE);
		offset = 0;
	}
}

/*
 * queues up writes, so that all our write(2) calls write exactly one
 * full block; pads writes to RECORDSIZE
 */
static void write_blocked(const void *data, unsigned long size)
{
	const char *buf = data;
	unsigned long tail;

	if (offset) {
		unsigned long chunk = BLOCKSIZE - offset;
		if (size < chunk)
			chunk = size;
		memcpy(block + offset, buf, chunk);
		size -= chunk;
		offset += chunk;
		buf += chunk;
		write_if_needed();
	}
	while (size >= BLOCKSIZE) {
		write_or_die(1, buf, BLOCKSIZE);
		size -= BLOCKSIZE;
		buf += BLOCKSIZE;
	}
	if (size) {
		memcpy(block + offset, buf, size);
		offset += size;
	}
	tail = offset % RECORDSIZE;
	if (tail)  {
		memset(block + offset, 0, RECORDSIZE - tail);
		offset += RECORDSIZE - tail;
	}
	write_if_needed();
}

/*
 * The end of tar archives is marked by 2*512 nul bytes and after that
 * follows the rest of the block (if any).
 */
static void write_trailer(void)
{
	int tail = BLOCKSIZE - offset;
	memset(block + offset, 0, tail);
	write_or_die(1, block, BLOCKSIZE);
	if (tail < 2 * RECORDSIZE) {
		memset(block, 0, offset);
		write_or_die(1, block, BLOCKSIZE);
	}
}

/*
 * pax extended header records have the format "%u %s=%s\n".  %u contains
 * the size of the whole string (including the %u), the first %s is the
 * keyword, the second one is the value.  This function constructs such a
 * string and appends it to a struct strbuf.
 */
static void strbuf_append_ext_header(struct strbuf *sb, const char *keyword,
                                     const char *value, unsigned int valuelen)
{
	int len, tmp;

	/* "%u %s=%s\n" */
	len = 1 + 1 + strlen(keyword) + 1 + valuelen + 1;
	for (tmp = len; tmp > 9; tmp /= 10)
		len++;

	strbuf_grow(sb, len);
	strbuf_addf(sb, "%u %s=", len, keyword);
	strbuf_add(sb, value, valuelen);
	strbuf_addch(sb, '\n');
}

static unsigned int ustar_header_chksum(const struct ustar_header *header)
{
	char *p = (char *)header;
	unsigned int chksum = 0;
	while (p < header->chksum)
		chksum += *p++;
	chksum += sizeof(header->chksum) * ' ';
	p += sizeof(header->chksum);
	while (p < (char *)header + sizeof(struct ustar_header))
		chksum += *p++;
	return chksum;
}

static size_t get_path_prefix(const char *path, size_t pathlen, size_t maxlen)
{
	size_t i = pathlen;
	if (i > maxlen)
		i = maxlen;
	do {
		i--;
	} while (i > 0 && path[i] != '/');
	return i;
}

static int write_tar_entry(struct archiver_args *args,
		const unsigned char *sha1, const char *path, size_t pathlen,
		unsigned int mode, void *buffer, unsigned long size)
{
	struct ustar_header header;
	struct strbuf ext_header = STRBUF_INIT;
	int err = 0;

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

	if (!sha1) {
		*header.typeflag = TYPEFLAG_GLOBAL_HEADER;
		mode = 0100666;
		strcpy(header.name, "pax_global_header");
	} else if (!path) {
		*header.typeflag = TYPEFLAG_EXT_HEADER;
		mode = 0100666;
		sprintf(header.name, "%s.paxheader", sha1_to_hex(sha1));
	} else {
		if (S_ISDIR(mode) || S_ISGITLINK(mode)) {
			*header.typeflag = TYPEFLAG_DIR;
			mode = (mode | 0777) & ~tar_umask;
		} else if (S_ISLNK(mode)) {
			*header.typeflag = TYPEFLAG_LNK;
			mode |= 0777;
		} else if (S_ISREG(mode)) {
			*header.typeflag = TYPEFLAG_REG;
			mode = (mode | ((mode & 0100) ? 0777 : 0666)) & ~tar_umask;
		} else {
			return error("unsupported file mode: 0%o (SHA1: %s)",
					mode, sha1_to_hex(sha1));
		}
		if (pathlen > sizeof(header.name)) {
			size_t plen = get_path_prefix(path, pathlen,
					sizeof(header.prefix));
			size_t rest = pathlen - plen - 1;
			if (plen > 0 && rest <= sizeof(header.name)) {
				memcpy(header.prefix, path, plen);
				memcpy(header.name, path + plen + 1, rest);
			} else {
				sprintf(header.name, "%s.data",
				        sha1_to_hex(sha1));
				strbuf_append_ext_header(&ext_header, "path",
						path, pathlen);
			}
		} else
			memcpy(header.name, path, pathlen);
	}

	if (S_ISLNK(mode) && buffer) {
		if (size > sizeof(header.linkname)) {
			sprintf(header.linkname, "see %s.paxheader",
			        sha1_to_hex(sha1));
			strbuf_append_ext_header(&ext_header, "linkpath",
			                         buffer, size);
		} else
			memcpy(header.linkname, buffer, size);
	}

	sprintf(header.mode, "%07o", mode & 07777);
	sprintf(header.size, "%011lo", S_ISREG(mode) ? size : 0);
	sprintf(header.mtime, "%011lo", (unsigned long) args->time);

	sprintf(header.uid, "%07o", 0);
	sprintf(header.gid, "%07o", 0);
	strlcpy(header.uname, "root", sizeof(header.uname));
	strlcpy(header.gname, "root", sizeof(header.gname));
	sprintf(header.devmajor, "%07o", 0);
	sprintf(header.devminor, "%07o", 0);

	memcpy(header.magic, "ustar", 6);
	memcpy(header.version, "00", 2);

	sprintf(header.chksum, "%07o", ustar_header_chksum(&header));

	if (ext_header.len > 0) {
		err = write_tar_entry(args, sha1, NULL, 0, 0, ext_header.buf,
				ext_header.len);
		if (err)
			return err;
	}
	strbuf_release(&ext_header);
	write_blocked(&header, sizeof(header));
	if (S_ISREG(mode) && buffer && size > 0)
		write_blocked(buffer, size);
	return err;
}

static int write_global_extended_header(struct archiver_args *args)
{
	const unsigned char *sha1 = args->commit_sha1;
	struct strbuf ext_header = STRBUF_INIT;
	int err;

	strbuf_append_ext_header(&ext_header, "comment", sha1_to_hex(sha1), 40);
	err = write_tar_entry(args, NULL, NULL, 0, 0, ext_header.buf,
			ext_header.len);
	strbuf_release(&ext_header);
	return err;
}

static struct archiver **tar_filters;
static int nr_tar_filters;
static int alloc_tar_filters;

static struct archiver *find_tar_filter(const char *name, int len)
{
	int i;
	for (i = 0; i < nr_tar_filters; i++) {
		struct archiver *ar = tar_filters[i];
		if (!strncmp(ar->name, name, len) && !ar->name[len])
			return ar;
	}
	return NULL;
}

static int tar_filter_config(const char *var, const char *value, void *data)
{
	struct archiver *ar;
	const char *dot;
	const char *name;
	const char *type;
	int namelen;

	if (prefixcmp(var, "tar."))
		return 0;
	dot = strrchr(var, '.');
	if (dot == var + 9)
		return 0;

	name = var + 4;
	namelen = dot - name;
	type = dot + 1;

	ar = find_tar_filter(name, namelen);
	if (!ar) {
		ar = xcalloc(1, sizeof(*ar));
		ar->name = xmemdupz(name, namelen);
		ar->write_archive = write_tar_filter_archive;
		ar->flags = ARCHIVER_WANT_COMPRESSION_LEVELS;
		ALLOC_GROW(tar_filters, nr_tar_filters + 1, alloc_tar_filters);
		tar_filters[nr_tar_filters++] = ar;
	}

	if (!strcmp(type, "command")) {
		if (!value)
			return config_error_nonbool(var);
		free(ar->data);
		ar->data = xstrdup(value);
		return 0;
	}
	if (!strcmp(type, "remote")) {
		if (git_config_bool(var, value))
			ar->flags |= ARCHIVER_REMOTE;
		else
			ar->flags &= ~ARCHIVER_REMOTE;
		return 0;
	}

	return 0;
}

static int git_tar_config(const char *var, const char *value, void *cb)
{
	if (!strcmp(var, "tar.umask")) {
		if (value && !strcmp(value, "user")) {
			tar_umask = umask(0);
			umask(tar_umask);
		} else {
			tar_umask = git_config_int(var, value);
		}
		return 0;
	}

	return tar_filter_config(var, value, cb);
}

static int write_tar_archive(const struct archiver *ar,
			     struct archiver_args *args)
{
	int err = 0;

	if (args->commit_sha1)
		err = write_global_extended_header(args);
	if (!err)
		err = write_archive_entries(args, write_tar_entry);
	if (!err)
		write_trailer();
	return err;
}

static int write_tar_filter_archive(const struct archiver *ar,
				    struct archiver_args *args)
{
	struct strbuf cmd = STRBUF_INIT;
	struct child_process filter;
	const char *argv[2];
	int r;

	if (!ar->data)
		die("BUG: tar-filter archiver called with no filter defined");

	strbuf_addstr(&cmd, ar->data);
	if (args->compression_level >= 0)
		strbuf_addf(&cmd, " -%d", args->compression_level);

	memset(&filter, 0, sizeof(filter));
	argv[0] = cmd.buf;
	argv[1] = NULL;
	filter.argv = argv;
	filter.use_shell = 1;
	filter.in = -1;

	if (start_command(&filter) < 0)
		die_errno("unable to start '%s' filter", argv[0]);
	close(1);
	if (dup2(filter.in, 1) < 0)
		die_errno("unable to redirect descriptor");
	close(filter.in);

	r = write_tar_archive(ar, args);

	close(1);
	if (finish_command(&filter) != 0)
		die("'%s' filter reported error", argv[0]);

	strbuf_release(&cmd);
	return r;
}

static struct archiver tar_archiver = {
	"tar",
	write_tar_archive,
	ARCHIVER_REMOTE
};

void init_tar_archiver(void)
{
	int i;
	register_archiver(&tar_archiver);

	tar_filter_config("tar.tgz.command", "gzip -cn", NULL);
	tar_filter_config("tar.tgz.remote", "true", NULL);
	tar_filter_config("tar.tar.gz.command", "gzip -cn", NULL);
	tar_filter_config("tar.tar.gz.remote", "true", NULL);
	git_config(git_tar_config, NULL);
	for (i = 0; i < nr_tar_filters; i++) {
		/* omit any filters that never had a command configured */
		if (tar_filters[i]->data)
			register_archiver(tar_filters[i]);
	}
}
Commit	Line	Data
	1	/*
	2	* Copyright (c) 2005, 2006 Rene Scharfe
	3	*/
	4	#include "cache.h"
	5	#include "tar.h"
	6	#include "archive.h"
	7	#include "run-command.h"
	8
	9	#define RECORDSIZE (512)
	10	#define BLOCKSIZE (RECORDSIZE * 20)
	11
	12	static char block[BLOCKSIZE];
	13	static unsigned long offset;
	14
	15	static int tar_umask = 002;
	16
	17	static int write_tar_filter_archive(const struct archiver *ar,
	18	struct archiver_args *args);
	19
	20	/* writes out the whole block, but only if it is full */
	21	static void write_if_needed(void)
	22	{
	23	if (offset == BLOCKSIZE) {
	24	write_or_die(1, block, BLOCKSIZE);
	25	offset = 0;
	26	}
	27	}
	28
	29	/*
	30	* queues up writes, so that all our write(2) calls write exactly one
	31	* full block; pads writes to RECORDSIZE
	32	*/
	33	static void write_blocked(const void *data, unsigned long size)
	34	{
	35	const char *buf = data;
	36	unsigned long tail;
	37
	38	if (offset) {
	39	unsigned long chunk = BLOCKSIZE - offset;
	40	if (size < chunk)
	41	chunk = size;
	42	memcpy(block + offset, buf, chunk);
	43	size -= chunk;
	44	offset += chunk;
	45	buf += chunk;
	46	write_if_needed();
	47	}
	48	while (size >= BLOCKSIZE) {
	49	write_or_die(1, buf, BLOCKSIZE);
	50	size -= BLOCKSIZE;
	51	buf += BLOCKSIZE;
	52	}
	53	if (size) {
	54	memcpy(block + offset, buf, size);
	55	offset += size;
	56	}
	57	tail = offset % RECORDSIZE;
	58	if (tail) {
	59	memset(block + offset, 0, RECORDSIZE - tail);
	60	offset += RECORDSIZE - tail;
	61	}
	62	write_if_needed();
	63	}
	64
	65	/*
	66	* The end of tar archives is marked by 2*512 nul bytes and after that
	67	* follows the rest of the block (if any).
	68	*/
	69	static void write_trailer(void)
	70	{
	71	int tail = BLOCKSIZE - offset;
	72	memset(block + offset, 0, tail);
	73	write_or_die(1, block, BLOCKSIZE);
	74	if (tail < 2 * RECORDSIZE) {
	75	memset(block, 0, offset);
	76	write_or_die(1, block, BLOCKSIZE);
	77	}
	78	}
	79
	80	/*
	81	* pax extended header records have the format "%u %s=%s\n". %u contains
	82	* the size of the whole string (including the %u), the first %s is the
	83	* keyword, the second one is the value. This function constructs such a
	84	* string and appends it to a struct strbuf.
	85	*/
	86	static void strbuf_append_ext_header(struct strbuf sb, const char keyword,
	87	const char *value, unsigned int valuelen)
	88	{
	89	int len, tmp;
	90
	91	/* "%u %s=%s\n" */
	92	len = 1 + 1 + strlen(keyword) + 1 + valuelen + 1;
	93	for (tmp = len; tmp > 9; tmp /= 10)
	94	len++;
	95
	96	strbuf_grow(sb, len);
	97	strbuf_addf(sb, "%u %s=", len, keyword);
	98	strbuf_add(sb, value, valuelen);
	99	strbuf_addch(sb, '\n');
	100	}
	101
	102	static unsigned int ustar_header_chksum(const struct ustar_header *header)
	103	{
	104	char p = (char )header;
	105	unsigned int chksum = 0;
	106	while (p < header->chksum)
	107	chksum += *p++;
	108	chksum += sizeof(header->chksum) * ' ';
	109	p += sizeof(header->chksum);
	110	while (p < (char *)header + sizeof(struct ustar_header))
	111	chksum += *p++;
	112	return chksum;
	113	}
	114
	115	static size_t get_path_prefix(const char *path, size_t pathlen, size_t maxlen)
	116	{
	117	size_t i = pathlen;
	118	if (i > maxlen)
	119	i = maxlen;
	120	do {
	121	i--;
	122	} while (i > 0 && path[i] != '/');
	123	return i;
	124	}
	125
	126	static int write_tar_entry(struct archiver_args *args,
	127	const unsigned char sha1, const char path, size_t pathlen,
	128	unsigned int mode, void *buffer, unsigned long size)
	129	{
	130	struct ustar_header header;
	131	struct strbuf ext_header = STRBUF_INIT;
	132	int err = 0;
	133
	134	memset(&header, 0, sizeof(header));
	135
	136	if (!sha1) {
	137	*header.typeflag = TYPEFLAG_GLOBAL_HEADER;
	138	mode = 0100666;
	139	strcpy(header.name, "pax_global_header");
	140	} else if (!path) {
	141	*header.typeflag = TYPEFLAG_EXT_HEADER;
	142	mode = 0100666;
	143	sprintf(header.name, "%s.paxheader", sha1_to_hex(sha1));
	144	} else {
	145	if (S_ISDIR(mode) \|\| S_ISGITLINK(mode)) {
	146	*header.typeflag = TYPEFLAG_DIR;
	147	mode = (mode \| 0777) & ~tar_umask;
	148	} else if (S_ISLNK(mode)) {
	149	*header.typeflag = TYPEFLAG_LNK;
	150	mode \|= 0777;
	151	} else if (S_ISREG(mode)) {
	152	*header.typeflag = TYPEFLAG_REG;
	153	mode = (mode \| ((mode & 0100) ? 0777 : 0666)) & ~tar_umask;
	154	} else {
	155	return error("unsupported file mode: 0%o (SHA1: %s)",
	156	mode, sha1_to_hex(sha1));
	157	}
	158	if (pathlen > sizeof(header.name)) {
	159	size_t plen = get_path_prefix(path, pathlen,
	160	sizeof(header.prefix));
	161	size_t rest = pathlen - plen - 1;
	162	if (plen > 0 && rest <= sizeof(header.name)) {
	163	memcpy(header.prefix, path, plen);
	164	memcpy(header.name, path + plen + 1, rest);
	165	} else {
	166	sprintf(header.name, "%s.data",
	167	sha1_to_hex(sha1));
	168	strbuf_append_ext_header(&ext_header, "path",
	169	path, pathlen);
	170	}
	171	} else
	172	memcpy(header.name, path, pathlen);
	173	}
	174
	175	if (S_ISLNK(mode) && buffer) {
	176	if (size > sizeof(header.linkname)) {
	177	sprintf(header.linkname, "see %s.paxheader",
	178	sha1_to_hex(sha1));
	179	strbuf_append_ext_header(&ext_header, "linkpath",
	180	buffer, size);
	181	} else
	182	memcpy(header.linkname, buffer, size);
	183	}
	184
	185	sprintf(header.mode, "%07o", mode & 07777);
	186	sprintf(header.size, "%011lo", S_ISREG(mode) ? size : 0);
	187	sprintf(header.mtime, "%011lo", (unsigned long) args->time);
	188
	189	sprintf(header.uid, "%07o", 0);
	190	sprintf(header.gid, "%07o", 0);
	191	strlcpy(header.uname, "root", sizeof(header.uname));
	192	strlcpy(header.gname, "root", sizeof(header.gname));
	193	sprintf(header.devmajor, "%07o", 0);
	194	sprintf(header.devminor, "%07o", 0);
	195
	196	memcpy(header.magic, "ustar", 6);
	197	memcpy(header.version, "00", 2);
	198
	199	sprintf(header.chksum, "%07o", ustar_header_chksum(&header));
	200
	201	if (ext_header.len > 0) {
	202	err = write_tar_entry(args, sha1, NULL, 0, 0, ext_header.buf,
	203	ext_header.len);
	204	if (err)
	205	return err;
	206	}
	207	strbuf_release(&ext_header);
	208	write_blocked(&header, sizeof(header));
	209	if (S_ISREG(mode) && buffer && size > 0)
	210	write_blocked(buffer, size);
	211	return err;
	212	}
	213
	214	static int write_global_extended_header(struct archiver_args *args)
	215	{
	216	const unsigned char *sha1 = args->commit_sha1;
	217	struct strbuf ext_header = STRBUF_INIT;
	218	int err;
	219
	220	strbuf_append_ext_header(&ext_header, "comment", sha1_to_hex(sha1), 40);
	221	err = write_tar_entry(args, NULL, NULL, 0, 0, ext_header.buf,
	222	ext_header.len);
	223	strbuf_release(&ext_header);
	224	return err;
	225	}
	226
	227	static struct archiver **tar_filters;
	228	static int nr_tar_filters;
	229	static int alloc_tar_filters;
	230
	231	static struct archiver find_tar_filter(const char name, int len)
	232	{
	233	int i;
	234	for (i = 0; i < nr_tar_filters; i++) {
	235	struct archiver *ar = tar_filters[i];
	236	if (!strncmp(ar->name, name, len) && !ar->name[len])
	237	return ar;
	238	}
	239	return NULL;
	240	}
	241
	242	static int tar_filter_config(const char var, const char value, void *data)
	243	{
	244	struct archiver *ar;
	245	const char *dot;
	246	const char *name;
	247	const char *type;
	248	int namelen;
	249
	250	if (prefixcmp(var, "tar."))
	251	return 0;
	252	dot = strrchr(var, '.');
	253	if (dot == var + 9)
	254	return 0;
	255
	256	name = var + 4;
	257	namelen = dot - name;
	258	type = dot + 1;
	259
	260	ar = find_tar_filter(name, namelen);
	261	if (!ar) {
	262	ar = xcalloc(1, sizeof(*ar));
	263	ar->name = xmemdupz(name, namelen);
	264	ar->write_archive = write_tar_filter_archive;
	265	ar->flags = ARCHIVER_WANT_COMPRESSION_LEVELS;
	266	ALLOC_GROW(tar_filters, nr_tar_filters + 1, alloc_tar_filters);
	267	tar_filters[nr_tar_filters++] = ar;
	268	}
	269
	270	if (!strcmp(type, "command")) {
	271	if (!value)
	272	return config_error_nonbool(var);
	273	free(ar->data);
	274	ar->data = xstrdup(value);
	275	return 0;
	276	}
	277	if (!strcmp(type, "remote")) {
	278	if (git_config_bool(var, value))
	279	ar->flags \|= ARCHIVER_REMOTE;
	280	else
	281	ar->flags &= ~ARCHIVER_REMOTE;
	282	return 0;
	283	}
	284
	285	return 0;
	286	}
	287
	288	static int git_tar_config(const char var, const char value, void *cb)
	289	{
	290	if (!strcmp(var, "tar.umask")) {
	291	if (value && !strcmp(value, "user")) {
	292	tar_umask = umask(0);
	293	umask(tar_umask);
	294	} else {
	295	tar_umask = git_config_int(var, value);
	296	}
	297	return 0;
	298	}
	299
	300	return tar_filter_config(var, value, cb);
	301	}
	302
	303	static int write_tar_archive(const struct archiver *ar,
	304	struct archiver_args *args)
	305	{
	306	int err = 0;
	307
	308	if (args->commit_sha1)
	309	err = write_global_extended_header(args);
	310	if (!err)
	311	err = write_archive_entries(args, write_tar_entry);
	312	if (!err)
	313	write_trailer();
	314	return err;
	315	}
	316
	317	static int write_tar_filter_archive(const struct archiver *ar,
	318	struct archiver_args *args)
	319	{
	320	struct strbuf cmd = STRBUF_INIT;
	321	struct child_process filter;
	322	const char *argv[2];
	323	int r;
	324
	325	if (!ar->data)
	326	die("BUG: tar-filter archiver called with no filter defined");
	327
	328	strbuf_addstr(&cmd, ar->data);
	329	if (args->compression_level >= 0)
	330	strbuf_addf(&cmd, " -%d", args->compression_level);
	331
	332	memset(&filter, 0, sizeof(filter));
	333	argv[0] = cmd.buf;
	334	argv[1] = NULL;
	335	filter.argv = argv;
	336	filter.use_shell = 1;
	337	filter.in = -1;
	338
	339	if (start_command(&filter) < 0)
	340	die_errno("unable to start '%s' filter", argv[0]);
	341	close(1);
	342	if (dup2(filter.in, 1) < 0)
	343	die_errno("unable to redirect descriptor");
	344	close(filter.in);
	345
	346	r = write_tar_archive(ar, args);
	347
	348	close(1);
	349	if (finish_command(&filter) != 0)
	350	die("'%s' filter reported error", argv[0]);
	351
	352	strbuf_release(&cmd);
	353	return r;
	354	}
	355
	356	static struct archiver tar_archiver = {
	357	"tar",
	358	write_tar_archive,
	359	ARCHIVER_REMOTE
	360	};
	361
	362	void init_tar_archiver(void)
	363	{
	364	int i;
	365	register_archiver(&tar_archiver);
	366
	367	tar_filter_config("tar.tgz.command", "gzip -cn", NULL);
	368	tar_filter_config("tar.tgz.remote", "true", NULL);
	369	tar_filter_config("tar.tar.gz.command", "gzip -cn", NULL);
	370	tar_filter_config("tar.tar.gz.remote", "true", NULL);
	371	git_config(git_tar_config, NULL);
	372	for (i = 0; i < nr_tar_filters; i++) {
	373	/* omit any filters that never had a command configured */
	374	if (tar_filters[i]->data)
	375	register_archiver(tar_filters[i]);
	376	}
	377	}