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

/*
 * Copyright (c) 2005, 2006 Rene Scharfe
 */
#include "git-compat-util.h"
#include "config.h"
#include "gettext.h"
#include "git-zlib.h"
#include "hex.h"
#include "tar.h"
#include "archive.h"
#include "object-store-ll.h"
#include "strbuf.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 (!xstrncmpz(ar->name, 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,
			  const struct config_context *ctx, 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, ctx->kvi);
		}
		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	4	#include "git-compat-util.h"
b2141fc1	5	#include "config.h"
f394e093	6	#include "gettext.h"
d88dbaa7	7	#include "git-zlib.h"
41771fa4	8	#include "hex.h"
3d74982f	9	#include "tar.h"
3d74982f	10	#include "archive.h"
a034e910	11	#include "object-store-ll.h"
c2c4138c	12	#include "strbuf.h"
5544049d	13	#include "streaming.h"
767cf457	14	#include "run-command.h"
d48be35c	15	#include "write-or-die.h"
3d74982f RS	16
	17	#define RECORDSIZE (512)
	18	#define BLOCKSIZE (RECORDSIZE * 20)
	19
	20	static char block[BLOCKSIZE];
	21	static unsigned long offset;
	22
f08b3b0e	23	static int tar_umask = 002;
3d74982f	24
767cf457 JK	25	static int write_tar_filter_archive(const struct archiver *ar,
	26	struct archiver_args *args);
	27
d1657b57 JK	28	/*
	29	* This is the max value that a ustar size header can specify, as it is fixed
	30	* at 11 octal digits. POSIX specifies that we switch to extended headers at
	31	* this size.
6e8e0991 JK	32	*
6e8e0991 JK	33	* Likewise for the mtime (which happens to use a buffer of the same size).
d1657b57	34	*/
29493589 JH	35	#if ULONG_MAX == 0xFFFFFFFF
29493589 JH	36	#define USTAR_MAX_SIZE ULONG_MAX
29493589	37	#else
3f789719	38	#define USTAR_MAX_SIZE 077777777777UL
dddbad72 JS	39	#endif
	40	#if TIME_MAX == 0xFFFFFFFF
	41	#define USTAR_MAX_MTIME TIME_MAX
	42	#else
3f789719	43	#define USTAR_MAX_MTIME 077777777777ULL
29493589	44	#endif
d1657b57	45
76d76026	46	static void tar_write_block(const void *buf)
dfce1186 RS	47	{
	48	write_or_die(1, buf, BLOCKSIZE);
	49	}
	50
76d76026 RS	51	static void (write_block)(const void ) = tar_write_block;
76d76026 RS	52
3d74982f RS	53	/* writes out the whole block, but only if it is full */
	54	static void write_if_needed(void)
	55	{
	56	if (offset == BLOCKSIZE) {
dfce1186	57	write_block(block);
3d74982f RS	58	offset = 0;
	59	}
	60	}
	61
	62	/*
	63	* queues up writes, so that all our write(2) calls write exactly one
	64	* full block; pads writes to RECORDSIZE
	65	*/
5544049d	66	static void do_write_blocked(const void *data, unsigned long size)
3d74982f RS	67	{
3d74982f RS	68	const char *buf = data;
3d74982f RS	69
	70	if (offset) {
	71	unsigned long chunk = BLOCKSIZE - offset;
	72	if (size < chunk)
	73	chunk = size;
	74	memcpy(block + offset, buf, chunk);
	75	size -= chunk;
	76	offset += chunk;
	77	buf += chunk;
	78	write_if_needed();
	79	}
	80	while (size >= BLOCKSIZE) {
dfce1186	81	write_block(buf);
3d74982f RS	82	size -= BLOCKSIZE;
	83	buf += BLOCKSIZE;
	84	}
	85	if (size) {
	86	memcpy(block + offset, buf, size);
	87	offset += size;
	88	}
5544049d NTND	89	}
	90
	91	static void finish_record(void)
	92	{
	93	unsigned long tail;
3d74982f RS	94	tail = offset % RECORDSIZE;
	95	if (tail) {
	96	memset(block + offset, 0, RECORDSIZE - tail);
	97	offset += RECORDSIZE - tail;
	98	}
	99	write_if_needed();
	100	}
	101
5544049d NTND	102	static void write_blocked(const void *data, unsigned long size)
	103	{
	104	do_write_blocked(data, size);
	105	finish_record();
	106	}
	107
3d74982f RS	108	/*
	109	* The end of tar archives is marked by 2*512 nul bytes and after that
	110	* follows the rest of the block (if any).
	111	*/
	112	static void write_trailer(void)
	113	{
	114	int tail = BLOCKSIZE - offset;
	115	memset(block + offset, 0, tail);
dfce1186	116	write_block(block);
3d74982f RS	117	if (tail < 2 * RECORDSIZE) {
3d74982f RS	118	memset(block, 0, offset);
dfce1186	119	write_block(block);
3d74982f RS	120	}
	121	}
	122
5544049d NTND	123	/*
	124	* queues up writes, so that all our write(2) calls write exactly one
	125	* full block; pads writes to RECORDSIZE
	126	*/
c8123e72	127	static int stream_blocked(struct repository r, const struct object_id oid)
5544049d NTND	128	{
	129	struct git_istream *st;
	130	enum object_type type;
	131	unsigned long sz;
	132	char buf[BLOCKSIZE];
	133	ssize_t readlen;
	134
c8123e72	135	st = open_istream(r, oid, &type, &sz, NULL);
5544049d	136	if (!st)
d0482e69	137	return error(_("cannot stream blob %s"), oid_to_hex(oid));
5544049d NTND	138	for (;;) {
	139	readlen = read_istream(st, buf, sizeof(buf));
	140	if (readlen <= 0)
	141	break;
	142	do_write_blocked(buf, readlen);
	143	}
	144	close_istream(st);
	145	if (!readlen)
	146	finish_record();
	147	return readlen;
	148	}
	149
3d74982f RS	150	/*
	151	* pax extended header records have the format "%u %s=%s\n". %u contains
	152	* the size of the whole string (including the %u), the first %s is the
	153	* keyword, the second one is the value. This function constructs such a
	154	* string and appends it to a struct strbuf.
	155	*/
	156	static void strbuf_append_ext_header(struct strbuf sb, const char keyword,
17e9ef00	157	const char *value, size_t valuelen)
3d74982f	158	{
4060c199	159	size_t orig_len = sb->len;
17e9ef00	160	size_t len, tmp;
3d74982f RS	161
	162	/* "%u %s=%s\n" */
	163	len = 1 + 1 + strlen(keyword) + 1 + valuelen + 1;
82a46af1	164	for (tmp = 1; len / 10 >= tmp; tmp *= 10)
3d74982f RS	165	len++;
3d74982f RS	166
7a604f16	167	strbuf_grow(sb, len);
17e9ef00	168	strbuf_addf(sb, "%"PRIuMAX" %s=", (uintmax_t)len, keyword);
7a604f16 PH	169	strbuf_add(sb, value, valuelen);
7a604f16 PH	170	strbuf_addch(sb, '\n');
4060c199 RS	171
4060c199 RS	172	if (len != sb->len - orig_len)
71d41ff6 RS	173	BUG("pax extended header length miscalculated as %"PRIuMAX
	174	", should be %"PRIuMAX,
	175	(uintmax_t)len, (uintmax_t)(sb->len - orig_len));
3d74982f RS	176	}
3d74982f RS	177
d1657b57 JK	178	/*
	179	* Like strbuf_append_ext_header, but for numeric values.
	180	*/
	181	static void strbuf_append_ext_header_uint(struct strbuf *sb,
	182	const char *keyword,
	183	uintmax_t value)
	184	{
	185	char buf[40]; /* big enough for 2^128 in decimal, plus NUL */
	186	int len;
	187
	188	len = xsnprintf(buf, sizeof(buf), "%"PRIuMAX, value);
	189	strbuf_append_ext_header(sb, keyword, buf, len);
	190	}
	191
3d74982f RS	192	static unsigned int ustar_header_chksum(const struct ustar_header *header)
3d74982f RS	193	{
a5a46eb9	194	const unsigned char p = (const unsigned char )header;
3d74982f	195	unsigned int chksum = 0;
a5a46eb9	196	while (p < (const unsigned char *)header->chksum)
3d74982f RS	197	chksum += *p++;
	198	chksum += sizeof(header->chksum) * ' ';
	199	p += sizeof(header->chksum);
a5a46eb9	200	while (p < (const unsigned char *)header + sizeof(struct ustar_header))
3d74982f RS	201	chksum += *p++;
	202	return chksum;
	203	}
	204
562e25ab	205	static size_t get_path_prefix(const char *path, size_t pathlen, size_t maxlen)
3d74982f	206	{
562e25ab	207	size_t i = pathlen;
22f0dcd9 RS	208	if (i > 1 && path[i - 1] == '/')
22f0dcd9 RS	209	i--;
3d74982f RS	210	if (i > maxlen)
	211	i = maxlen;
	212	do {
	213	i--;
562e25ab	214	} while (i > 0 && path[i] != '/');
3d74982f RS	215	return i;
	216	}
	217
d240d410 NTND	218	static void prepare_header(struct archiver_args *args,
	219	struct ustar_header *header,
	220	unsigned int mode, unsigned long size)
	221	{
f2f02675	222	xsnprintf(header->mode, sizeof(header->mode), "%07o", mode & 07777);
ca473cef	223	xsnprintf(header->size, sizeof(header->size), "%011"PRIoMAX , S_ISREG(mode) ? (uintmax_t)size : (uintmax_t)0);
f2f02675	224	xsnprintf(header->mtime, sizeof(header->mtime), "%011lo", (unsigned long) args->time);
d240d410	225
f2f02675 JK	226	xsnprintf(header->uid, sizeof(header->uid), "%07o", 0);
f2f02675 JK	227	xsnprintf(header->gid, sizeof(header->gid), "%07o", 0);
d240d410 NTND	228	strlcpy(header->uname, "root", sizeof(header->uname));
d240d410 NTND	229	strlcpy(header->gname, "root", sizeof(header->gname));
f2f02675 JK	230	xsnprintf(header->devmajor, sizeof(header->devmajor), "%07o", 0);
f2f02675 JK	231	xsnprintf(header->devminor, sizeof(header->devminor), "%07o", 0);
d240d410 NTND	232
	233	memcpy(header->magic, "ustar", 6);
	234	memcpy(header->version, "00", 2);
	235
9e6c1e91	236	xsnprintf(header->chksum, sizeof(header->chksum), "%07o", ustar_header_chksum(header));
d240d410 NTND	237	}
d240d410 NTND	238
560b0e8f	239	static void write_extended_header(struct archiver_args *args,
015ff4f8	240	const struct object_id *oid,
560b0e8f	241	const void *buffer, unsigned long size)
d240d410 NTND	242	{
	243	struct ustar_header header;
	244	unsigned int mode;
	245	memset(&header, 0, sizeof(header));
	246	*header.typeflag = TYPEFLAG_EXT_HEADER;
15c6ef7b	247	mode = 0100666;
015ff4f8	248	xsnprintf(header.name, sizeof(header.name), "%s.paxheader", oid_to_hex(oid));
d240d410 NTND	249	prepare_header(args, &header, mode, size);
	250	write_blocked(&header, sizeof(header));
	251	write_blocked(buffer, size);
d240d410 NTND	252	}
d240d410 NTND	253
562e25ab	254	static int write_tar_entry(struct archiver_args *args,
015ff4f8	255	const struct object_id *oid,
9cb513b7	256	const char *path, size_t pathlen,
200589ab RS	257	unsigned int mode,
200589ab RS	258	void *buffer, unsigned long size)
3d74982f RS	259	{
3d74982f RS	260	struct ustar_header header;
f285a2d7	261	struct strbuf ext_header = STRBUF_INIT;
200589ab	262	unsigned long size_in_header;
562e25ab	263	int err = 0;
3d74982f RS	264
3d74982f RS	265	memset(&header, 0, sizeof(header));
3d74982f	266
85390709 NTND	267	if (S_ISDIR(mode) \|\| S_ISGITLINK(mode)) {
	268	*header.typeflag = TYPEFLAG_DIR;
	269	mode = (mode \| 0777) & ~tar_umask;
	270	} else if (S_ISLNK(mode)) {
	271	*header.typeflag = TYPEFLAG_LNK;
	272	mode \|= 0777;
	273	} else if (S_ISREG(mode)) {
	274	*header.typeflag = TYPEFLAG_REG;
	275	mode = (mode \| ((mode & 0100) ? 0777 : 0666)) & ~tar_umask;
3d74982f	276	} else {
d0482e69	277	return error(_("unsupported file mode: 0%o (SHA1: %s)"),
015ff4f8	278	mode, oid_to_hex(oid));
85390709 NTND	279	}
	280	if (pathlen > sizeof(header.name)) {
	281	size_t plen = get_path_prefix(path, pathlen,
	282	sizeof(header.prefix));
	283	size_t rest = pathlen - plen - 1;
	284	if (plen > 0 && rest <= sizeof(header.name)) {
	285	memcpy(header.prefix, path, plen);
108332c7	286	memcpy(header.name, path + plen + 1, rest);
3d74982f	287	} else {
f2f02675	288	xsnprintf(header.name, sizeof(header.name), "%s.data",
015ff4f8	289	oid_to_hex(oid));
85390709 NTND	290	strbuf_append_ext_header(&ext_header, "path",
85390709 NTND	291	path, pathlen);
3d74982f	292	}
85390709 NTND	293	} else
85390709 NTND	294	memcpy(header.name, path, pathlen);
3d74982f	295
9cb513b7	296	if (S_ISLNK(mode)) {
3d74982f	297	if (size > sizeof(header.linkname)) {
f2f02675	298	xsnprintf(header.linkname, sizeof(header.linkname),
015ff4f8	299	"see %s.paxheader", oid_to_hex(oid));
3d74982f RS	300	strbuf_append_ext_header(&ext_header, "linkpath",
	301	buffer, size);
	302	} else
	303	memcpy(header.linkname, buffer, size);
	304	}
	305
d1657b57 JK	306	size_in_header = size;
	307	if (S_ISREG(mode) && size > USTAR_MAX_SIZE) {
	308	size_in_header = 0;
	309	strbuf_append_ext_header_uint(&ext_header, "size", size);
	310	}
	311
	312	prepare_header(args, &header, mode, size_in_header);
3d74982f RS	313
3d74982f RS	314	if (ext_header.len > 0) {
015ff4f8	315	write_extended_header(args, oid, ext_header.buf,
560b0e8f	316	ext_header.len);
3d74982f	317	}
7a604f16	318	strbuf_release(&ext_header);
3d74982f	319	write_blocked(&header, sizeof(header));
5544049d NTND	320	if (S_ISREG(mode) && size > 0) {
	321	if (buffer)
	322	write_blocked(buffer, size);
	323	else
c8123e72	324	err = stream_blocked(args->repo, oid);
5544049d	325	}
562e25ab	326	return err;
3d74982f RS	327	}
3d74982f RS	328
5caeeb83	329	static void write_global_extended_header(struct archiver_args *args)
3d74982f	330	{
bbf05cf7	331	const struct object_id *oid = args->commit_oid;
f285a2d7	332	struct strbuf ext_header = STRBUF_INIT;
d240d410 NTND	333	struct ustar_header header;
d240d410 NTND	334	unsigned int mode;
7a604f16	335
bbf05cf7	336	if (oid)
6e8e0991	337	strbuf_append_ext_header(&ext_header, "comment",
bbf05cf7	338	oid_to_hex(oid),
bbf05cf7	339	the_hash_algo->hexsz);
6e8e0991 JK	340	if (args->time > USTAR_MAX_MTIME) {
	341	strbuf_append_ext_header_uint(&ext_header, "mtime",
	342	args->time);
	343	args->time = USTAR_MAX_MTIME;
	344	}
	345
	346	if (!ext_header.len)
5caeeb83	347	return;
6e8e0991	348
d240d410 NTND	349	memset(&header, 0, sizeof(header));
d240d410 NTND	350	*header.typeflag = TYPEFLAG_GLOBAL_HEADER;
15c6ef7b	351	mode = 0100666;
5096d490	352	xsnprintf(header.name, sizeof(header.name), "pax_global_header");
d240d410 NTND	353	prepare_header(args, &header, mode, ext_header.len);
	354	write_blocked(&header, sizeof(header));
	355	write_blocked(ext_header.buf, ext_header.len);
7a604f16	356	strbuf_release(&ext_header);
3d74982f RS	357	}
3d74982f RS	358
767cf457 JK	359	static struct archiver **tar_filters;
	360	static int nr_tar_filters;
	361	static int alloc_tar_filters;
	362
f5914f4b	363	static struct archiver find_tar_filter(const char name, size_t len)
767cf457 JK	364	{
	365	int i;
	366	for (i = 0; i < nr_tar_filters; i++) {
	367	struct archiver *ar = tar_filters[i];
f0e578c6	368	if (!xstrncmpz(ar->name, name, len))
767cf457 JK	369	return ar;
	370	}
	371	return NULL;
	372	}
	373
783a86c1	374	static int tar_filter_config(const char var, const char value,
5cf88fd8	375	void *data UNUSED)
767cf457 JK	376	{
767cf457 JK	377	struct archiver *ar;
767cf457 JK	378	const char *name;
767cf457 JK	379	const char *type;
f5914f4b	380	size_t namelen;
767cf457	381
785a0429	382	if (parse_config_key(var, "tar", &name, &namelen, &type) < 0 \|\| !name)
767cf457	383	return 0;
767cf457 JK	384
	385	ar = find_tar_filter(name, namelen);
	386	if (!ar) {
ca56dadb	387	CALLOC_ARRAY(ar, 1);
767cf457 JK	388	ar->name = xmemdupz(name, namelen);
767cf457 JK	389	ar->write_archive = write_tar_filter_archive;
cde8ea9c RS	390	ar->flags = ARCHIVER_WANT_COMPRESSION_LEVELS \|
cde8ea9c RS	391	ARCHIVER_HIGH_COMPRESSION_LEVELS;
767cf457 JK	392	ALLOC_GROW(tar_filters, nr_tar_filters + 1, alloc_tar_filters);
	393	tar_filters[nr_tar_filters++] = ar;
	394	}
	395
	396	if (!strcmp(type, "command")) {
	397	if (!value)
	398	return config_error_nonbool(var);
96b9e515 RS	399	free(ar->filter_command);
96b9e515 RS	400	ar->filter_command = xstrdup(value);
767cf457 JK	401	return 0;
767cf457 JK	402	}
7b97730b JK	403	if (!strcmp(type, "remote")) {
	404	if (git_config_bool(var, value))
	405	ar->flags \|= ARCHIVER_REMOTE;
	406	else
	407	ar->flags &= ~ARCHIVER_REMOTE;
	408	return 0;
	409	}
767cf457 JK	410
	411	return 0;
	412	}
	413
a4e7e317	414	static int git_tar_config(const char var, const char value,
8868b1eb	415	const struct config_context ctx, void cb)
3d74982f RS	416	{
3d74982f RS	417	if (!strcmp(var, "tar.umask")) {
cc1816b0	418	if (value && !strcmp(value, "user")) {
3d74982f RS	419	tar_umask = umask(0);
	420	umask(tar_umask);
	421	} else {
8868b1eb	422	tar_umask = git_config_int(var, value, ctx->kvi);
3d74982f RS	423	}
	424	return 0;
	425	}
767cf457 JK	426
767cf457 JK	427	return tar_filter_config(var, value, cb);
3d74982f RS	428	}
3d74982f RS	429
5cf88fd8	430	static int write_tar_archive(const struct archiver *ar UNUSED,
4d7c9898	431	struct archiver_args *args)
3d74982f	432	{
562e25ab	433	int err = 0;
3d74982f	434
5caeeb83 JK	435	write_global_extended_header(args);
5caeeb83 JK	436	err = write_archive_entries(args, write_tar_entry);
562e25ab RS	437	if (!err)
	438	write_trailer();
	439	return err;
3d74982f	440	}
13e0f88d	441
76d76026 RS	442	static git_zstream gzstream;
	443	static unsigned char outbuf[16384];
	444
	445	static void tgz_deflate(int flush)
	446	{
	447	while (gzstream.avail_in \|\| flush == Z_FINISH) {
	448	int status = git_deflate(&gzstream, flush);
	449	if (!gzstream.avail_out \|\| status == Z_STREAM_END) {
	450	write_or_die(1, outbuf, gzstream.next_out - outbuf);
	451	gzstream.next_out = outbuf;
	452	gzstream.avail_out = sizeof(outbuf);
	453	if (status == Z_STREAM_END)
	454	break;
	455	}
	456	if (status != Z_OK && status != Z_BUF_ERROR)
	457	die(_("deflate error (%d)"), status);
	458	}
	459	}
	460
	461	static void tgz_write_block(const void *data)
	462	{
	463	gzstream.next_in = (void *)data;
	464	gzstream.avail_in = BLOCKSIZE;
	465	tgz_deflate(Z_NO_FLUSH);
	466	}
	467
	468	static const char internal_gzip_command[] = "git archive gzip";
	469
767cf457 JK	470	static int write_tar_filter_archive(const struct archiver *ar,
	471	struct archiver_args *args)
	472	{
23fcf8b0 RS	473	#if ZLIB_VERNUM >= 0x1221
	474	struct gz_header_s gzhead = { .os = 3 }; /* Unix, for reproducibility */
	475	#endif
767cf457	476	struct strbuf cmd = STRBUF_INIT;
d3180279	477	struct child_process filter = CHILD_PROCESS_INIT;
767cf457 JK	478	int r;
767cf457 JK	479
96b9e515	480	if (!ar->filter_command)
033abf97	481	BUG("tar-filter archiver called with no filter defined");
767cf457	482
76d76026 RS	483	if (!strcmp(ar->filter_command, internal_gzip_command)) {
	484	write_block = tgz_write_block;
	485	git_deflate_init_gzip(&gzstream, args->compression_level);
23fcf8b0 RS	486	#if ZLIB_VERNUM >= 0x1221
	487	if (deflateSetHeader(&gzstream.z, &gzhead) != Z_OK)
	488	BUG("deflateSetHeader() called too late");
	489	#endif
76d76026 RS	490	gzstream.next_out = outbuf;
	491	gzstream.avail_out = sizeof(outbuf);
	492
	493	r = write_tar_archive(ar, args);
	494
	495	tgz_deflate(Z_FINISH);
	496	git_deflate_end(&gzstream);
	497	return r;
	498	}
	499
96b9e515	500	strbuf_addstr(&cmd, ar->filter_command);
767cf457 JK	501	if (args->compression_level >= 0)
	502	strbuf_addf(&cmd, " -%d", args->compression_level);
	503
7f14609e	504	strvec_push(&filter.args, cmd.buf);
767cf457 JK	505	filter.use_shell = 1;
767cf457 JK	506	filter.in = -1;
1e4ea950	507	filter.silent_exec_failure = 1;
767cf457 JK	508
767cf457 JK	509	if (start_command(&filter) < 0)
7f14609e	510	die_errno(_("unable to start '%s' filter"), cmd.buf);
767cf457 JK	511	close(1);
767cf457 JK	512	if (dup2(filter.in, 1) < 0)
d0482e69	513	die_errno(_("unable to redirect descriptor"));
767cf457 JK	514	close(filter.in);
	515
	516	r = write_tar_archive(ar, args);
	517
	518	close(1);
	519	if (finish_command(&filter) != 0)
7f14609e	520	die(_("'%s' filter reported error"), cmd.buf);
767cf457 JK	521
	522	strbuf_release(&cmd);
	523	return r;
	524	}
	525
13e0f88d	526	static struct archiver tar_archiver = {
4fbedd4d ÆAB	527	.name = "tar",
	528	.write_archive = write_tar_archive,
	529	.flags = ARCHIVER_REMOTE,
13e0f88d JK	530	};
	531
	532	void init_tar_archiver(void)
	533	{
767cf457	534	int i;
13e0f88d	535	register_archiver(&tar_archiver);
767cf457	536
4f4be00d	537	tar_filter_config("tar.tgz.command", internal_gzip_command, NULL);
7b97730b	538	tar_filter_config("tar.tgz.remote", "true", NULL);
4f4be00d	539	tar_filter_config("tar.tar.gz.command", internal_gzip_command, NULL);
7b97730b	540	tar_filter_config("tar.tar.gz.remote", "true", NULL);
13e0f88d	541	git_config(git_tar_config, NULL);
767cf457 JK	542	for (i = 0; i < nr_tar_filters; i++) {
767cf457 JK	543	/* omit any filters that never had a command configured */
96b9e515	544	if (tar_filters[i]->filter_command)
767cf457 JK	545	register_archiver(tar_filters[i]);
767cf457 JK	546	}
13e0f88d	547	}