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

/*
 * Copyright (c) 2005, 2006 Rene Scharfe
 */
#include "git-compat-util.h"
#include "alloc.h"
#include "config.h"
#include "gettext.h"
#include "hex.h"
#include "tar.h"
#include "archive.h"
#include "object-store.h"
#include "streaming.h"
#include "run-command.h"
#include "write-or-die.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);

/*
 * This is the max value that a ustar size header can specify, as it is fixed
 * at 11 octal digits. POSIX specifies that we switch to extended headers at
 * this size.
 *
 * Likewise for the mtime (which happens to use a buffer of the same size).
 */
#if ULONG_MAX == 0xFFFFFFFF
#define USTAR_MAX_SIZE ULONG_MAX
#else
#define USTAR_MAX_SIZE 077777777777UL
#endif
#if TIME_MAX == 0xFFFFFFFF
#define USTAR_MAX_MTIME TIME_MAX
#else
#define USTAR_MAX_MTIME 077777777777ULL
#endif

static void tar_write_block(const void *buf)
{
	write_or_die(1, buf, BLOCKSIZE);
}

static void (*write_block)(const void *) = tar_write_block;

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

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

	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_block(buf);
		size -= BLOCKSIZE;
		buf += BLOCKSIZE;
	}
	if (size) {
		memcpy(block + offset, buf, size);
		offset += size;
	}
}

static void finish_record(void)
{
	unsigned long tail;
	tail = offset % RECORDSIZE;
	if (tail)  {
		memset(block + offset, 0, RECORDSIZE - tail);
		offset += RECORDSIZE - tail;
	}
	write_if_needed();
}

static void write_blocked(const void *data, unsigned long size)
{
	do_write_blocked(data, size);
	finish_record();
}

/*
 * 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_block(block);
	if (tail < 2 * RECORDSIZE) {
		memset(block, 0, offset);
		write_block(block);
	}
}

/*
 * queues up writes, so that all our write(2) calls write exactly one
 * full block; pads writes to RECORDSIZE
 */
static int stream_blocked(struct repository *r, const struct object_id *oid)
{
	struct git_istream *st;
	enum object_type type;
	unsigned long sz;
	char buf[BLOCKSIZE];
	ssize_t readlen;

	st = open_istream(r, oid, &type, &sz, NULL);
	if (!st)
		return error(_("cannot stream blob %s"), oid_to_hex(oid));
	for (;;) {
		readlen = read_istream(st, buf, sizeof(buf));
		if (readlen <= 0)
			break;
		do_write_blocked(buf, readlen);
	}
	close_istream(st);
	if (!readlen)
		finish_record();
	return readlen;
}

/*
 * 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, size_t valuelen)
{
	size_t orig_len = sb->len;
	size_t len, tmp;

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

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

	if (len != sb->len - orig_len)
		BUG("pax extended header length miscalculated as %"PRIuMAX
		    ", should be %"PRIuMAX,
		    (uintmax_t)len, (uintmax_t)(sb->len - orig_len));
}

/*
 * Like strbuf_append_ext_header, but for numeric values.
 */
static void strbuf_append_ext_header_uint(struct strbuf *sb,
					  const char *keyword,
					  uintmax_t value)
{
	char buf[40]; /* big enough for 2^128 in decimal, plus NUL */
	int len;

	len = xsnprintf(buf, sizeof(buf), "%"PRIuMAX, value);
	strbuf_append_ext_header(sb, keyword, buf, len);
}

static unsigned int ustar_header_chksum(const struct ustar_header *header)
{
	const unsigned char *p = (const unsigned char *)header;
	unsigned int chksum = 0;
	while (p < (const unsigned char *)header->chksum)
		chksum += *p++;
	chksum += sizeof(header->chksum) * ' ';
	p += sizeof(header->chksum);
	while (p < (const unsigned 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 > 1 && path[i - 1] == '/')
		i--;
	if (i > maxlen)
		i = maxlen;
	do {
		i--;
	} while (i > 0 && path[i] != '/');
	return i;
}

static void prepare_header(struct archiver_args *args,
			   struct ustar_header *header,
			   unsigned int mode, unsigned long size)
{
	xsnprintf(header->mode, sizeof(header->mode), "%07o", mode & 07777);
	xsnprintf(header->size, sizeof(header->size), "%011"PRIoMAX , S_ISREG(mode) ? (uintmax_t)size : (uintmax_t)0);
	xsnprintf(header->mtime, sizeof(header->mtime), "%011lo", (unsigned long) args->time);

	xsnprintf(header->uid, sizeof(header->uid), "%07o", 0);
	xsnprintf(header->gid, sizeof(header->gid), "%07o", 0);
	strlcpy(header->uname, "root", sizeof(header->uname));
	strlcpy(header->gname, "root", sizeof(header->gname));
	xsnprintf(header->devmajor, sizeof(header->devmajor), "%07o", 0);
	xsnprintf(header->devminor, sizeof(header->devminor), "%07o", 0);

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

	xsnprintf(header->chksum, sizeof(header->chksum), "%07o", ustar_header_chksum(header));
}

static void write_extended_header(struct archiver_args *args,
				  const struct object_id *oid,
				  const void *buffer, unsigned long size)
{
	struct ustar_header header;
	unsigned int mode;
	memset(&header, 0, sizeof(header));
	*header.typeflag = TYPEFLAG_EXT_HEADER;
	mode = 0100666;
	xsnprintf(header.name, sizeof(header.name), "%s.paxheader", oid_to_hex(oid));
	prepare_header(args, &header, mode, size);
	write_blocked(&header, sizeof(header));
	write_blocked(buffer, size);
}

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

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

	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, oid_to_hex(oid));
	}
	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 {
			xsnprintf(header.name, sizeof(header.name), "%s.data",
				  oid_to_hex(oid));
			strbuf_append_ext_header(&ext_header, "path",
						 path, pathlen);
		}
	} else
		memcpy(header.name, path, pathlen);

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

	size_in_header = size;
	if (S_ISREG(mode) && size > USTAR_MAX_SIZE) {
		size_in_header = 0;
		strbuf_append_ext_header_uint(&ext_header, "size", size);
	}

	prepare_header(args, &header, mode, size_in_header);

	if (ext_header.len > 0) {
		write_extended_header(args, oid, ext_header.buf,
				      ext_header.len);
	}
	strbuf_release(&ext_header);
	write_blocked(&header, sizeof(header));
	if (S_ISREG(mode) && size > 0) {
		if (buffer)
			write_blocked(buffer, size);
		else
			err = stream_blocked(args->repo, oid);
	}
	return err;
}

static void write_global_extended_header(struct archiver_args *args)
{
	const struct object_id *oid = args->commit_oid;
	struct strbuf ext_header = STRBUF_INIT;
	struct ustar_header header;
	unsigned int mode;

	if (oid)
		strbuf_append_ext_header(&ext_header, "comment",
					 oid_to_hex(oid),
					 the_hash_algo->hexsz);
	if (args->time > USTAR_MAX_MTIME) {
		strbuf_append_ext_header_uint(&ext_header, "mtime",
					      args->time);
		args->time = USTAR_MAX_MTIME;
	}

	if (!ext_header.len)
		return;

	memset(&header, 0, sizeof(header));
	*header.typeflag = TYPEFLAG_GLOBAL_HEADER;
	mode = 0100666;
	xsnprintf(header.name, sizeof(header.name), "pax_global_header");
	prepare_header(args, &header, mode, ext_header.len);
	write_blocked(&header, sizeof(header));
	write_blocked(ext_header.buf, ext_header.len);
	strbuf_release(&ext_header);
}

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

static struct archiver *find_tar_filter(const char *name, size_t 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 UNUSED)
{
	struct archiver *ar;
	const char *name;
	const char *type;
	size_t namelen;

	if (parse_config_key(var, "tar", &name, &namelen, &type) < 0 || !name)
		return 0;

	ar = find_tar_filter(name, namelen);
	if (!ar) {
		CALLOC_ARRAY(ar, 1);
		ar->name = xmemdupz(name, namelen);
		ar->write_archive = write_tar_filter_archive;
		ar->flags = ARCHIVER_WANT_COMPRESSION_LEVELS |
			    ARCHIVER_HIGH_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->filter_command);
		ar->filter_command = 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 UNUSED,
			     struct archiver_args *args)
{
	int err = 0;

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

static git_zstream gzstream;
static unsigned char outbuf[16384];

static void tgz_deflate(int flush)
{
	while (gzstream.avail_in || flush == Z_FINISH) {
		int status = git_deflate(&gzstream, flush);
		if (!gzstream.avail_out || status == Z_STREAM_END) {
			write_or_die(1, outbuf, gzstream.next_out - outbuf);
			gzstream.next_out = outbuf;
			gzstream.avail_out = sizeof(outbuf);
			if (status == Z_STREAM_END)
				break;
		}
		if (status != Z_OK && status != Z_BUF_ERROR)
			die(_("deflate error (%d)"), status);
	}
}

static void tgz_write_block(const void *data)
{
	gzstream.next_in = (void *)data;
	gzstream.avail_in = BLOCKSIZE;
	tgz_deflate(Z_NO_FLUSH);
}

static const char internal_gzip_command[] = "git archive gzip";

static int write_tar_filter_archive(const struct archiver *ar,
				    struct archiver_args *args)
{
#if ZLIB_VERNUM >= 0x1221
	struct gz_header_s gzhead = { .os = 3 }; /* Unix, for reproducibility */
#endif
	struct strbuf cmd = STRBUF_INIT;
	struct child_process filter = CHILD_PROCESS_INIT;
	int r;

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

	if (!strcmp(ar->filter_command, internal_gzip_command)) {
		write_block = tgz_write_block;
		git_deflate_init_gzip(&gzstream, args->compression_level);
#if ZLIB_VERNUM >= 0x1221
		if (deflateSetHeader(&gzstream.z, &gzhead) != Z_OK)
			BUG("deflateSetHeader() called too late");
#endif
		gzstream.next_out = outbuf;
		gzstream.avail_out = sizeof(outbuf);

		r = write_tar_archive(ar, args);

		tgz_deflate(Z_FINISH);
		git_deflate_end(&gzstream);
		return r;
	}

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

	strvec_push(&filter.args, cmd.buf);
	filter.use_shell = 1;
	filter.in = -1;
	filter.silent_exec_failure = 1;

	if (start_command(&filter) < 0)
		die_errno(_("unable to start '%s' filter"), cmd.buf);
	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"), cmd.buf);

	strbuf_release(&cmd);
	return r;
}

static struct archiver tar_archiver = {
	.name = "tar",
	.write_archive = write_tar_archive,
	.flags = ARCHIVER_REMOTE,
};

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

	tar_filter_config("tar.tgz.command", internal_gzip_command, NULL);
	tar_filter_config("tar.tgz.remote", "true", NULL);
	tar_filter_config("tar.tar.gz.command", internal_gzip_command, 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]->filter_command)
			register_archiver(tar_filters[i]);
	}
}
Commit	Line	Data
3d74982f RS	1	/*
	2	* Copyright (c) 2005, 2006 Rene Scharfe
	3	*/
36bf1958 EN	4	#include "git-compat-util.h"
36bf1958 EN	5	#include "alloc.h"
b2141fc1	6	#include "config.h"
f394e093	7	#include "gettext.h"
41771fa4	8	#include "hex.h"
3d74982f	9	#include "tar.h"
3d74982f	10	#include "archive.h"
cbd53a21	11	#include "object-store.h"
5544049d	12	#include "streaming.h"
767cf457	13	#include "run-command.h"
d48be35c	14	#include "write-or-die.h"
3d74982f RS	15
	16	#define RECORDSIZE (512)
	17	#define BLOCKSIZE (RECORDSIZE * 20)
	18
	19	static char block[BLOCKSIZE];
	20	static unsigned long offset;
	21
f08b3b0e	22	static int tar_umask = 002;
3d74982f	23
767cf457 JK	24	static int write_tar_filter_archive(const struct archiver *ar,
	25	struct archiver_args *args);
	26
d1657b57 JK	27	/*
	28	* This is the max value that a ustar size header can specify, as it is fixed
	29	* at 11 octal digits. POSIX specifies that we switch to extended headers at
	30	* this size.
6e8e0991 JK	31	*
6e8e0991 JK	32	* Likewise for the mtime (which happens to use a buffer of the same size).
d1657b57	33	*/
29493589 JH	34	#if ULONG_MAX == 0xFFFFFFFF
29493589 JH	35	#define USTAR_MAX_SIZE ULONG_MAX
29493589	36	#else
3f789719	37	#define USTAR_MAX_SIZE 077777777777UL
dddbad72 JS	38	#endif
	39	#if TIME_MAX == 0xFFFFFFFF
	40	#define USTAR_MAX_MTIME TIME_MAX
	41	#else
3f789719	42	#define USTAR_MAX_MTIME 077777777777ULL
29493589	43	#endif
d1657b57	44
76d76026	45	static void tar_write_block(const void *buf)
dfce1186 RS	46	{
	47	write_or_die(1, buf, BLOCKSIZE);
	48	}
	49
76d76026 RS	50	static void (write_block)(const void ) = tar_write_block;
76d76026 RS	51
3d74982f RS	52	/* writes out the whole block, but only if it is full */
	53	static void write_if_needed(void)
	54	{
	55	if (offset == BLOCKSIZE) {
dfce1186	56	write_block(block);
3d74982f RS	57	offset = 0;
	58	}
	59	}
	60
	61	/*
	62	* queues up writes, so that all our write(2) calls write exactly one
	63	* full block; pads writes to RECORDSIZE
	64	*/
5544049d	65	static void do_write_blocked(const void *data, unsigned long size)
3d74982f RS	66	{
3d74982f RS	67	const char *buf = data;
3d74982f RS	68
	69	if (offset) {
	70	unsigned long chunk = BLOCKSIZE - offset;
	71	if (size < chunk)
	72	chunk = size;
	73	memcpy(block + offset, buf, chunk);
	74	size -= chunk;
	75	offset += chunk;
	76	buf += chunk;
	77	write_if_needed();
	78	}
	79	while (size >= BLOCKSIZE) {
dfce1186	80	write_block(buf);
3d74982f RS	81	size -= BLOCKSIZE;
	82	buf += BLOCKSIZE;
	83	}
	84	if (size) {
	85	memcpy(block + offset, buf, size);
	86	offset += size;
	87	}
5544049d NTND	88	}
	89
	90	static void finish_record(void)
	91	{
	92	unsigned long tail;
3d74982f RS	93	tail = offset % RECORDSIZE;
	94	if (tail) {
	95	memset(block + offset, 0, RECORDSIZE - tail);
	96	offset += RECORDSIZE - tail;
	97	}
	98	write_if_needed();
	99	}
	100
5544049d NTND	101	static void write_blocked(const void *data, unsigned long size)
	102	{
	103	do_write_blocked(data, size);
	104	finish_record();
	105	}
	106
3d74982f RS	107	/*
	108	* The end of tar archives is marked by 2*512 nul bytes and after that
	109	* follows the rest of the block (if any).
	110	*/
	111	static void write_trailer(void)
	112	{
	113	int tail = BLOCKSIZE - offset;
	114	memset(block + offset, 0, tail);
dfce1186	115	write_block(block);
3d74982f RS	116	if (tail < 2 * RECORDSIZE) {
3d74982f RS	117	memset(block, 0, offset);
dfce1186	118	write_block(block);
3d74982f RS	119	}
	120	}
	121
5544049d NTND	122	/*
	123	* queues up writes, so that all our write(2) calls write exactly one
	124	* full block; pads writes to RECORDSIZE
	125	*/
c8123e72	126	static int stream_blocked(struct repository r, const struct object_id oid)
5544049d NTND	127	{
	128	struct git_istream *st;
	129	enum object_type type;
	130	unsigned long sz;
	131	char buf[BLOCKSIZE];
	132	ssize_t readlen;
	133
c8123e72	134	st = open_istream(r, oid, &type, &sz, NULL);
5544049d	135	if (!st)
d0482e69	136	return error(_("cannot stream blob %s"), oid_to_hex(oid));
5544049d NTND	137	for (;;) {
	138	readlen = read_istream(st, buf, sizeof(buf));
	139	if (readlen <= 0)
	140	break;
	141	do_write_blocked(buf, readlen);
	142	}
	143	close_istream(st);
	144	if (!readlen)
	145	finish_record();
	146	return readlen;
	147	}
	148
3d74982f RS	149	/*
	150	* pax extended header records have the format "%u %s=%s\n". %u contains
	151	* the size of the whole string (including the %u), the first %s is the
	152	* keyword, the second one is the value. This function constructs such a
	153	* string and appends it to a struct strbuf.
	154	*/
	155	static void strbuf_append_ext_header(struct strbuf sb, const char keyword,
17e9ef00	156	const char *value, size_t valuelen)
3d74982f	157	{
4060c199	158	size_t orig_len = sb->len;
17e9ef00	159	size_t len, tmp;
3d74982f RS	160
	161	/* "%u %s=%s\n" */
	162	len = 1 + 1 + strlen(keyword) + 1 + valuelen + 1;
82a46af1	163	for (tmp = 1; len / 10 >= tmp; tmp *= 10)
3d74982f RS	164	len++;
3d74982f RS	165
7a604f16	166	strbuf_grow(sb, len);
17e9ef00	167	strbuf_addf(sb, "%"PRIuMAX" %s=", (uintmax_t)len, keyword);
7a604f16 PH	168	strbuf_add(sb, value, valuelen);
7a604f16 PH	169	strbuf_addch(sb, '\n');
4060c199 RS	170
4060c199 RS	171	if (len != sb->len - orig_len)
71d41ff6 RS	172	BUG("pax extended header length miscalculated as %"PRIuMAX
	173	", should be %"PRIuMAX,
	174	(uintmax_t)len, (uintmax_t)(sb->len - orig_len));
3d74982f RS	175	}
3d74982f RS	176
d1657b57 JK	177	/*
	178	* Like strbuf_append_ext_header, but for numeric values.
	179	*/
	180	static void strbuf_append_ext_header_uint(struct strbuf *sb,
	181	const char *keyword,
	182	uintmax_t value)
	183	{
	184	char buf[40]; /* big enough for 2^128 in decimal, plus NUL */
	185	int len;
	186
	187	len = xsnprintf(buf, sizeof(buf), "%"PRIuMAX, value);
	188	strbuf_append_ext_header(sb, keyword, buf, len);
	189	}
	190
3d74982f RS	191	static unsigned int ustar_header_chksum(const struct ustar_header *header)
3d74982f RS	192	{
a5a46eb9	193	const unsigned char p = (const unsigned char )header;
3d74982f	194	unsigned int chksum = 0;
a5a46eb9	195	while (p < (const unsigned char *)header->chksum)
3d74982f RS	196	chksum += *p++;
	197	chksum += sizeof(header->chksum) * ' ';
	198	p += sizeof(header->chksum);
a5a46eb9	199	while (p < (const unsigned char *)header + sizeof(struct ustar_header))
3d74982f RS	200	chksum += *p++;
	201	return chksum;
	202	}
	203
562e25ab	204	static size_t get_path_prefix(const char *path, size_t pathlen, size_t maxlen)
3d74982f	205	{
562e25ab	206	size_t i = pathlen;
22f0dcd9 RS	207	if (i > 1 && path[i - 1] == '/')
22f0dcd9 RS	208	i--;
3d74982f RS	209	if (i > maxlen)
	210	i = maxlen;
	211	do {
	212	i--;
562e25ab	213	} while (i > 0 && path[i] != '/');
3d74982f RS	214	return i;
	215	}
	216
d240d410 NTND	217	static void prepare_header(struct archiver_args *args,
	218	struct ustar_header *header,
	219	unsigned int mode, unsigned long size)
	220	{
f2f02675	221	xsnprintf(header->mode, sizeof(header->mode), "%07o", mode & 07777);
ca473cef	222	xsnprintf(header->size, sizeof(header->size), "%011"PRIoMAX , S_ISREG(mode) ? (uintmax_t)size : (uintmax_t)0);
f2f02675	223	xsnprintf(header->mtime, sizeof(header->mtime), "%011lo", (unsigned long) args->time);
d240d410	224
f2f02675 JK	225	xsnprintf(header->uid, sizeof(header->uid), "%07o", 0);
f2f02675 JK	226	xsnprintf(header->gid, sizeof(header->gid), "%07o", 0);
d240d410 NTND	227	strlcpy(header->uname, "root", sizeof(header->uname));
d240d410 NTND	228	strlcpy(header->gname, "root", sizeof(header->gname));
f2f02675 JK	229	xsnprintf(header->devmajor, sizeof(header->devmajor), "%07o", 0);
f2f02675 JK	230	xsnprintf(header->devminor, sizeof(header->devminor), "%07o", 0);
d240d410 NTND	231
	232	memcpy(header->magic, "ustar", 6);
	233	memcpy(header->version, "00", 2);
	234
9e6c1e91	235	xsnprintf(header->chksum, sizeof(header->chksum), "%07o", ustar_header_chksum(header));
d240d410 NTND	236	}
d240d410 NTND	237
560b0e8f	238	static void write_extended_header(struct archiver_args *args,
015ff4f8	239	const struct object_id *oid,
560b0e8f	240	const void *buffer, unsigned long size)
d240d410 NTND	241	{
	242	struct ustar_header header;
	243	unsigned int mode;
	244	memset(&header, 0, sizeof(header));
	245	*header.typeflag = TYPEFLAG_EXT_HEADER;
15c6ef7b	246	mode = 0100666;
015ff4f8	247	xsnprintf(header.name, sizeof(header.name), "%s.paxheader", oid_to_hex(oid));
d240d410 NTND	248	prepare_header(args, &header, mode, size);
	249	write_blocked(&header, sizeof(header));
	250	write_blocked(buffer, size);
d240d410 NTND	251	}
d240d410 NTND	252
562e25ab	253	static int write_tar_entry(struct archiver_args *args,
015ff4f8	254	const struct object_id *oid,
9cb513b7	255	const char *path, size_t pathlen,
200589ab RS	256	unsigned int mode,
200589ab RS	257	void *buffer, unsigned long size)
3d74982f RS	258	{
3d74982f RS	259	struct ustar_header header;
f285a2d7	260	struct strbuf ext_header = STRBUF_INIT;
200589ab	261	unsigned long size_in_header;
562e25ab	262	int err = 0;
3d74982f RS	263
3d74982f RS	264	memset(&header, 0, sizeof(header));
3d74982f	265
85390709 NTND	266	if (S_ISDIR(mode) \|\| S_ISGITLINK(mode)) {
	267	*header.typeflag = TYPEFLAG_DIR;
	268	mode = (mode \| 0777) & ~tar_umask;
	269	} else if (S_ISLNK(mode)) {
	270	*header.typeflag = TYPEFLAG_LNK;
	271	mode \|= 0777;
	272	} else if (S_ISREG(mode)) {
	273	*header.typeflag = TYPEFLAG_REG;
	274	mode = (mode \| ((mode & 0100) ? 0777 : 0666)) & ~tar_umask;
3d74982f	275	} else {
d0482e69	276	return error(_("unsupported file mode: 0%o (SHA1: %s)"),
015ff4f8	277	mode, oid_to_hex(oid));
85390709 NTND	278	}
	279	if (pathlen > sizeof(header.name)) {
	280	size_t plen = get_path_prefix(path, pathlen,
	281	sizeof(header.prefix));
	282	size_t rest = pathlen - plen - 1;
	283	if (plen > 0 && rest <= sizeof(header.name)) {
	284	memcpy(header.prefix, path, plen);
108332c7	285	memcpy(header.name, path + plen + 1, rest);
3d74982f	286	} else {
f2f02675	287	xsnprintf(header.name, sizeof(header.name), "%s.data",
015ff4f8	288	oid_to_hex(oid));
85390709 NTND	289	strbuf_append_ext_header(&ext_header, "path",
85390709 NTND	290	path, pathlen);
3d74982f	291	}
85390709 NTND	292	} else
85390709 NTND	293	memcpy(header.name, path, pathlen);
3d74982f	294
9cb513b7	295	if (S_ISLNK(mode)) {
3d74982f	296	if (size > sizeof(header.linkname)) {
f2f02675	297	xsnprintf(header.linkname, sizeof(header.linkname),
015ff4f8	298	"see %s.paxheader", oid_to_hex(oid));
3d74982f RS	299	strbuf_append_ext_header(&ext_header, "linkpath",
	300	buffer, size);
	301	} else
	302	memcpy(header.linkname, buffer, size);
	303	}
	304
d1657b57 JK	305	size_in_header = size;
	306	if (S_ISREG(mode) && size > USTAR_MAX_SIZE) {
	307	size_in_header = 0;
	308	strbuf_append_ext_header_uint(&ext_header, "size", size);
	309	}
	310
	311	prepare_header(args, &header, mode, size_in_header);
3d74982f RS	312
3d74982f RS	313	if (ext_header.len > 0) {
015ff4f8	314	write_extended_header(args, oid, ext_header.buf,
560b0e8f	315	ext_header.len);
3d74982f	316	}
7a604f16	317	strbuf_release(&ext_header);
3d74982f	318	write_blocked(&header, sizeof(header));
5544049d NTND	319	if (S_ISREG(mode) && size > 0) {
	320	if (buffer)
	321	write_blocked(buffer, size);
	322	else
c8123e72	323	err = stream_blocked(args->repo, oid);
5544049d	324	}
562e25ab	325	return err;
3d74982f RS	326	}
3d74982f RS	327
5caeeb83	328	static void write_global_extended_header(struct archiver_args *args)
3d74982f	329	{
bbf05cf7	330	const struct object_id *oid = args->commit_oid;
f285a2d7	331	struct strbuf ext_header = STRBUF_INIT;
d240d410 NTND	332	struct ustar_header header;
d240d410 NTND	333	unsigned int mode;
7a604f16	334
bbf05cf7	335	if (oid)
6e8e0991	336	strbuf_append_ext_header(&ext_header, "comment",
bbf05cf7	337	oid_to_hex(oid),
bbf05cf7	338	the_hash_algo->hexsz);
6e8e0991 JK	339	if (args->time > USTAR_MAX_MTIME) {
	340	strbuf_append_ext_header_uint(&ext_header, "mtime",
	341	args->time);
	342	args->time = USTAR_MAX_MTIME;
	343	}
	344
	345	if (!ext_header.len)
5caeeb83	346	return;
6e8e0991	347
d240d410 NTND	348	memset(&header, 0, sizeof(header));
d240d410 NTND	349	*header.typeflag = TYPEFLAG_GLOBAL_HEADER;
15c6ef7b	350	mode = 0100666;
5096d490	351	xsnprintf(header.name, sizeof(header.name), "pax_global_header");
d240d410 NTND	352	prepare_header(args, &header, mode, ext_header.len);
	353	write_blocked(&header, sizeof(header));
	354	write_blocked(ext_header.buf, ext_header.len);
7a604f16	355	strbuf_release(&ext_header);
3d74982f RS	356	}
3d74982f RS	357
767cf457 JK	358	static struct archiver **tar_filters;
	359	static int nr_tar_filters;
	360	static int alloc_tar_filters;
	361
f5914f4b	362	static struct archiver find_tar_filter(const char name, size_t len)
767cf457 JK	363	{
	364	int i;
	365	for (i = 0; i < nr_tar_filters; i++) {
	366	struct archiver *ar = tar_filters[i];
	367	if (!strncmp(ar->name, name, len) && !ar->name[len])
	368	return ar;
	369	}
	370	return NULL;
	371	}
	372
783a86c1	373	static int tar_filter_config(const char var, const char value,
5cf88fd8	374	void *data UNUSED)
767cf457 JK	375	{
767cf457 JK	376	struct archiver *ar;
767cf457 JK	377	const char *name;
767cf457 JK	378	const char *type;
f5914f4b	379	size_t namelen;
767cf457	380
785a0429	381	if (parse_config_key(var, "tar", &name, &namelen, &type) < 0 \|\| !name)
767cf457	382	return 0;
767cf457 JK	383
	384	ar = find_tar_filter(name, namelen);
	385	if (!ar) {
ca56dadb	386	CALLOC_ARRAY(ar, 1);
767cf457 JK	387	ar->name = xmemdupz(name, namelen);
767cf457 JK	388	ar->write_archive = write_tar_filter_archive;
cde8ea9c RS	389	ar->flags = ARCHIVER_WANT_COMPRESSION_LEVELS \|
cde8ea9c RS	390	ARCHIVER_HIGH_COMPRESSION_LEVELS;
767cf457 JK	391	ALLOC_GROW(tar_filters, nr_tar_filters + 1, alloc_tar_filters);
	392	tar_filters[nr_tar_filters++] = ar;
	393	}
	394
	395	if (!strcmp(type, "command")) {
	396	if (!value)
	397	return config_error_nonbool(var);
96b9e515 RS	398	free(ar->filter_command);
96b9e515 RS	399	ar->filter_command = xstrdup(value);
767cf457 JK	400	return 0;
767cf457 JK	401	}
7b97730b JK	402	if (!strcmp(type, "remote")) {
	403	if (git_config_bool(var, value))
	404	ar->flags \|= ARCHIVER_REMOTE;
	405	else
	406	ar->flags &= ~ARCHIVER_REMOTE;
	407	return 0;
	408	}
767cf457 JK	409
	410	return 0;
	411	}
	412
ef90d6d4	413	static int git_tar_config(const char var, const char value, void *cb)
3d74982f RS	414	{
3d74982f RS	415	if (!strcmp(var, "tar.umask")) {
cc1816b0	416	if (value && !strcmp(value, "user")) {
3d74982f RS	417	tar_umask = umask(0);
	418	umask(tar_umask);
	419	} else {
	420	tar_umask = git_config_int(var, value);
	421	}
	422	return 0;
	423	}
767cf457 JK	424
767cf457 JK	425	return tar_filter_config(var, value, cb);
3d74982f RS	426	}
3d74982f RS	427
5cf88fd8	428	static int write_tar_archive(const struct archiver *ar UNUSED,
4d7c9898	429	struct archiver_args *args)
3d74982f	430	{
562e25ab	431	int err = 0;
3d74982f	432
5caeeb83 JK	433	write_global_extended_header(args);
5caeeb83 JK	434	err = write_archive_entries(args, write_tar_entry);
562e25ab RS	435	if (!err)
	436	write_trailer();
	437	return err;
3d74982f	438	}
13e0f88d	439
76d76026 RS	440	static git_zstream gzstream;
	441	static unsigned char outbuf[16384];
	442
	443	static void tgz_deflate(int flush)
	444	{
	445	while (gzstream.avail_in \|\| flush == Z_FINISH) {
	446	int status = git_deflate(&gzstream, flush);
	447	if (!gzstream.avail_out \|\| status == Z_STREAM_END) {
	448	write_or_die(1, outbuf, gzstream.next_out - outbuf);
	449	gzstream.next_out = outbuf;
	450	gzstream.avail_out = sizeof(outbuf);
	451	if (status == Z_STREAM_END)
	452	break;
	453	}
	454	if (status != Z_OK && status != Z_BUF_ERROR)
	455	die(_("deflate error (%d)"), status);
	456	}
	457	}
	458
	459	static void tgz_write_block(const void *data)
	460	{
	461	gzstream.next_in = (void *)data;
	462	gzstream.avail_in = BLOCKSIZE;
	463	tgz_deflate(Z_NO_FLUSH);
	464	}
	465
	466	static const char internal_gzip_command[] = "git archive gzip";
	467
767cf457 JK	468	static int write_tar_filter_archive(const struct archiver *ar,
	469	struct archiver_args *args)
	470	{
23fcf8b0 RS	471	#if ZLIB_VERNUM >= 0x1221
	472	struct gz_header_s gzhead = { .os = 3 }; /* Unix, for reproducibility */
	473	#endif
767cf457	474	struct strbuf cmd = STRBUF_INIT;
d3180279	475	struct child_process filter = CHILD_PROCESS_INIT;
767cf457 JK	476	int r;
767cf457 JK	477
96b9e515	478	if (!ar->filter_command)
033abf97	479	BUG("tar-filter archiver called with no filter defined");
767cf457	480
76d76026 RS	481	if (!strcmp(ar->filter_command, internal_gzip_command)) {
	482	write_block = tgz_write_block;
	483	git_deflate_init_gzip(&gzstream, args->compression_level);
23fcf8b0 RS	484	#if ZLIB_VERNUM >= 0x1221
	485	if (deflateSetHeader(&gzstream.z, &gzhead) != Z_OK)
	486	BUG("deflateSetHeader() called too late");
	487	#endif
76d76026 RS	488	gzstream.next_out = outbuf;
	489	gzstream.avail_out = sizeof(outbuf);
	490
	491	r = write_tar_archive(ar, args);
	492
	493	tgz_deflate(Z_FINISH);
	494	git_deflate_end(&gzstream);
	495	return r;
	496	}
	497
96b9e515	498	strbuf_addstr(&cmd, ar->filter_command);
767cf457 JK	499	if (args->compression_level >= 0)
	500	strbuf_addf(&cmd, " -%d", args->compression_level);
	501
7f14609e	502	strvec_push(&filter.args, cmd.buf);
767cf457 JK	503	filter.use_shell = 1;
767cf457 JK	504	filter.in = -1;
1e4ea950	505	filter.silent_exec_failure = 1;
767cf457 JK	506
767cf457 JK	507	if (start_command(&filter) < 0)
7f14609e	508	die_errno(_("unable to start '%s' filter"), cmd.buf);
767cf457 JK	509	close(1);
767cf457 JK	510	if (dup2(filter.in, 1) < 0)
d0482e69	511	die_errno(_("unable to redirect descriptor"));
767cf457 JK	512	close(filter.in);
	513
	514	r = write_tar_archive(ar, args);
	515
	516	close(1);
	517	if (finish_command(&filter) != 0)
7f14609e	518	die(_("'%s' filter reported error"), cmd.buf);
767cf457 JK	519
	520	strbuf_release(&cmd);
	521	return r;
	522	}
	523
13e0f88d	524	static struct archiver tar_archiver = {
4fbedd4d ÆAB	525	.name = "tar",
	526	.write_archive = write_tar_archive,
	527	.flags = ARCHIVER_REMOTE,
13e0f88d JK	528	};
	529
	530	void init_tar_archiver(void)
	531	{
767cf457	532	int i;
13e0f88d	533	register_archiver(&tar_archiver);
767cf457	534
4f4be00d	535	tar_filter_config("tar.tgz.command", internal_gzip_command, NULL);
7b97730b	536	tar_filter_config("tar.tgz.remote", "true", NULL);
4f4be00d	537	tar_filter_config("tar.tar.gz.command", internal_gzip_command, NULL);
7b97730b	538	tar_filter_config("tar.tar.gz.remote", "true", NULL);
13e0f88d	539	git_config(git_tar_config, NULL);
767cf457 JK	540	for (i = 0; i < nr_tar_filters; i++) {
767cf457 JK	541	/* omit any filters that never had a command configured */
96b9e515	542	if (tar_filters[i]->filter_command)
767cf457 JK	543	register_archiver(tar_filters[i]);
767cf457 JK	544	}
13e0f88d	545	}