archive.c 14.7 KB
Newer Older
1
#include "cache.h"
2
#include "refs.h"
3
#include "commit.h"
4
#include "tree-walk.h"
5
#include "attr.h"
6
#include "archive.h"
7
#include "parse-options.h"
8
#include "unpack-trees.h"
9
#include "dir.h"
10 11

static char const * const archive_usage[] = {
12
	N_("git archive [<options>] <tree-ish> [<path>...]"),
13
	N_("git archive --list"),
14
	N_("git archive --remote <repo> [--exec <cmd>] [<options>] <tree-ish> [<path>...]"),
15
	N_("git archive --remote <repo> [--exec <cmd>] --list"),
16 17
	NULL
};
18

19 20 21
static const struct archiver **archivers;
static int nr_archivers;
static int alloc_archivers;
22
static int remote_allow_unreachable;
23 24 25 26 27 28

void register_archiver(struct archiver *ar)
{
	ALLOC_GROW(archivers, nr_archivers + 1, alloc_archivers);
	archivers[nr_archivers++] = ar;
}
29

30 31 32 33 34
static void format_subst(const struct commit *commit,
                         const char *src, size_t len,
                         struct strbuf *buf)
{
	char *to_free = NULL;
35
	struct strbuf fmt = STRBUF_INIT;
36
	struct pretty_print_context ctx = {0};
37
	ctx.date_mode.type = DATE_NORMAL;
38
	ctx.abbrev = DEFAULT_ABBREV;
39 40 41 42 43 44 45

	if (src == buf->buf)
		to_free = strbuf_detach(buf, NULL);
	for (;;) {
		const char *b, *c;

		b = memmem(src, len, "$Format:", 8);
46
		if (!b)
47
			break;
48
		c = memchr(b + 8, '$', (src + len) - b - 8);
49 50 51 52 53 54 55
		if (!c)
			break;

		strbuf_reset(&fmt);
		strbuf_add(&fmt, b + 8, c - b - 8);

		strbuf_add(buf, src, b - src);
56
		format_commit_message(commit, fmt.buf, buf, &ctx);
57 58 59 60 61 62 63 64
		len -= c + 1 - src;
		src  = c + 1;
	}
	strbuf_add(buf, src, len);
	strbuf_release(&fmt);
	free(to_free);
}

65 66 67 68
void *sha1_file_to_archive(const struct archiver_args *args,
			   const char *path, const unsigned char *sha1,
			   unsigned int mode, enum object_type *type,
			   unsigned long *sizep)
69 70
{
	void *buffer;
71
	const struct commit *commit = args->convert ? args->commit : NULL;
72

73
	path += args->baselen;
74 75
	buffer = read_sha1_file(sha1, type, sizep);
	if (buffer && S_ISREG(mode)) {
76
		struct strbuf buf = STRBUF_INIT;
77 78 79 80
		size_t size = 0;

		strbuf_attach(&buf, buffer, *sizep, *sizep + 1);
		convert_to_working_tree(path, buf.buf, buf.len, &buf);
81 82
		if (commit)
			format_subst(commit, buf.buf, buf.len, &buf);
83 84 85 86 87 88 89
		buffer = strbuf_detach(&buf, &size);
		*sizep = size;
	}

	return buffer;
}

90
static void setup_archive_check(struct git_attr_check *check)
91 92
{
	static struct git_attr *attr_export_ignore;
93
	static struct git_attr *attr_export_subst;
94

95
	if (!attr_export_ignore) {
96 97
		attr_export_ignore = git_attr("export-ignore");
		attr_export_subst = git_attr("export-subst");
98
	}
99
	check[0].attr = attr_export_ignore;
100
	check[1].attr = attr_export_subst;
101
}
102

103 104
struct directory {
	struct directory *up;
105
	struct object_id oid;
106 107 108 109 110 111
	int baselen, len;
	unsigned mode;
	int stage;
	char path[FLEX_ARRAY];
};

112 113 114
struct archiver_context {
	struct archiver_args *args;
	write_archive_entry_fn_t write_entry;
115
	struct directory *bottom;
116 117 118 119 120 121 122 123 124 125
};

static int write_archive_entry(const unsigned char *sha1, const char *base,
		int baselen, const char *filename, unsigned mode, int stage,
		void *context)
{
	static struct strbuf path = STRBUF_INIT;
	struct archiver_context *c = context;
	struct archiver_args *args = c->args;
	write_archive_entry_fn_t write_entry = c->write_entry;
126 127
	struct git_attr_check check[2];
	const char *path_without_prefix;
128 129
	int err;

130
	args->convert = 0;
131 132
	strbuf_reset(&path);
	strbuf_grow(&path, PATH_MAX);
133
	strbuf_add(&path, args->base, args->baselen);
134 135
	strbuf_add(&path, base, baselen);
	strbuf_addstr(&path, filename);
136 137
	if (S_ISDIR(mode) || S_ISGITLINK(mode))
		strbuf_addch(&path, '/');
138
	path_without_prefix = path.buf + args->baselen;
139

140
	setup_archive_check(check);
141
	if (!git_check_attr(path_without_prefix, ARRAY_SIZE(check), check)) {
142 143
		if (ATTR_TRUE(check[0].value))
			return 0;
144
		args->convert = ATTR_TRUE(check[1].value);
145
	}
146 147 148 149

	if (S_ISDIR(mode) || S_ISGITLINK(mode)) {
		if (args->verbose)
			fprintf(stderr, "%.*s\n", (int)path.len, path.buf);
150
		err = write_entry(args, sha1, path.buf, path.len, mode);
151 152
		if (err)
			return err;
153
		return (S_ISDIR(mode) ? READ_TREE_RECURSIVE : 0);
154 155 156 157
	}

	if (args->verbose)
		fprintf(stderr, "%.*s\n", (int)path.len, path.buf);
158
	return write_entry(args, sha1, path.buf, path.len, mode);
159 160
}

161 162 163 164 165 166 167 168
static int write_archive_entry_buf(const unsigned char *sha1, struct strbuf *base,
		const char *filename, unsigned mode, int stage,
		void *context)
{
	return write_archive_entry(sha1, base->buf, base->len,
				     filename, mode, stage, context);
}

169
static void queue_directory(const unsigned char *sha1,
170
		struct strbuf *base, const char *filename,
171 172 173
		unsigned mode, int stage, struct archiver_context *c)
{
	struct directory *d;
174 175
	size_t len = st_add4(base->len, 1, strlen(filename), 1);
	d = xmalloc(st_add(sizeof(*d), len));
176
	d->up	   = c->bottom;
177
	d->baselen = base->len;
178 179 180
	d->mode	   = mode;
	d->stage   = stage;
	c->bottom  = d;
181
	d->len = xsnprintf(d->path, len, "%.*s%s/", (int)base->len, base->buf, filename);
182
	hashcpy(d->oid.hash, sha1);
183 184 185 186 187 188 189 190 191 192 193 194 195
}

static int write_directory(struct archiver_context *c)
{
	struct directory *d = c->bottom;
	int ret;

	if (!d)
		return 0;
	c->bottom = d->up;
	d->path[d->len - 1] = '\0'; /* no trailing slash */
	ret =
		write_directory(c) ||
196
		write_archive_entry(d->oid.hash, d->path, d->baselen,
197 198 199 200 201 202 203
				    d->path + d->baselen, d->mode,
				    d->stage, c) != READ_TREE_RECURSIVE;
	free(d);
	return ret ? -1 : 0;
}

static int queue_or_write_archive_entry(const unsigned char *sha1,
204
		struct strbuf *base, const char *filename,
205 206 207 208 209
		unsigned mode, int stage, void *context)
{
	struct archiver_context *c = context;

	while (c->bottom &&
210 211
	       !(base->len >= c->bottom->len &&
		 !strncmp(base->buf, c->bottom->path, c->bottom->len))) {
212 213 214 215 216 217
		struct directory *next = c->bottom->up;
		free(c->bottom);
		c->bottom = next;
	}

	if (S_ISDIR(mode)) {
218
		queue_directory(sha1, base, filename,
219 220 221 222 223 224
				mode, stage, c);
		return READ_TREE_RECURSIVE;
	}

	if (write_directory(c))
		return -1;
225
	return write_archive_entry(sha1, base->buf, base->len, filename, mode,
226 227 228
				   stage, context);
}

229 230 231 232
int write_archive_entries(struct archiver_args *args,
		write_archive_entry_fn_t write_entry)
{
	struct archiver_context context;
233 234
	struct unpack_trees_options opts;
	struct tree_desc t;
235 236 237 238 239 240 241 242 243
	int err;

	if (args->baselen > 0 && args->base[args->baselen - 1] == '/') {
		size_t len = args->baselen;

		while (len > 1 && args->base[len - 2] == '/')
			len--;
		if (args->verbose)
			fprintf(stderr, "%.*s\n", (int)len, args->base);
244
		err = write_entry(args, args->tree->object.oid.hash, args->base,
245
				  len, 040777);
246 247 248 249
		if (err)
			return err;
	}

250
	memset(&context, 0, sizeof(context));
251 252 253
	context.args = args;
	context.write_entry = write_entry;

254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269
	/*
	 * Setup index and instruct attr to read index only
	 */
	if (!args->worktree_attributes) {
		memset(&opts, 0, sizeof(opts));
		opts.index_only = 1;
		opts.head_idx = -1;
		opts.src_index = &the_index;
		opts.dst_index = &the_index;
		opts.fn = oneway_merge;
		init_tree_desc(&t, args->tree->buffer, args->tree->size);
		if (unpack_trees(1, &t, &opts))
			return -1;
		git_attr_set_direction(GIT_ATTR_INDEX, &the_index);
	}

270
	err = read_tree_recursive(args->tree, "", 0, 0, &args->pathspec,
271 272
				  args->pathspec.has_wildcard ?
				  queue_or_write_archive_entry :
273
				  write_archive_entry_buf,
274
				  &context);
275 276
	if (err == READ_TREE_RECURSIVE)
		err = 0;
277 278 279 280 281
	while (context.bottom) {
		struct directory *next = context.bottom->up;
		free(context.bottom);
		context.bottom = next;
	}
282 283
	return err;
}
284

285 286 287 288
static const struct archiver *lookup_archiver(const char *name)
{
	int i;

289 290 291
	if (!name)
		return NULL;

292 293 294
	for (i = 0; i < nr_archivers; i++) {
		if (!strcmp(name, archivers[i]->name))
			return archivers[i];
295 296 297 298
	}
	return NULL;
}

299 300
static int reject_entry(const unsigned char *sha1, struct strbuf *base,
			const char *filename, unsigned mode,
301 302
			int stage, void *context)
{
303 304 305
	int ret = -1;
	if (S_ISDIR(mode)) {
		struct strbuf sb = STRBUF_INIT;
306
		strbuf_addbuf(&sb, base);
307 308 309 310 311 312
		strbuf_addstr(&sb, filename);
		if (!match_pathspec(context, sb.buf, sb.len, 0, NULL, 1))
			ret = READ_TREE_RECURSIVE;
		strbuf_release(&sb);
	}
	return ret;
313 314 315 316
}

static int path_exists(struct tree *tree, const char *path)
{
317 318 319 320
	const char *paths[] = { path, NULL };
	struct pathspec pathspec;
	int ret;

321
	parse_pathspec(&pathspec, 0, 0, "", paths);
322 323 324
	pathspec.recursive = 1;
	ret = read_tree_recursive(tree, "", 0, 0, &pathspec,
				  reject_entry, &pathspec);
325 326
	free_pathspec(&pathspec);
	return ret != 0;
327 328
}

329 330 331
static void parse_pathspec_arg(const char **pathspec,
		struct archiver_args *ar_args)
{
332 333 334 335 336 337 338 339
	/*
	 * must be consistent with parse_pathspec in path_exists()
	 * Also if pathspec patterns are dependent, we're in big
	 * trouble as we test each one separately
	 */
	parse_pathspec(&ar_args->pathspec, 0,
		       PATHSPEC_PREFER_FULL,
		       "", pathspec);
340
	ar_args->pathspec.recursive = 1;
341 342
	if (pathspec) {
		while (*pathspec) {
343
			if (**pathspec && !path_exists(ar_args->tree, *pathspec))
344
				die(_("pathspec '%s' did not match any files"), *pathspec);
345 346 347
			pathspec++;
		}
	}
348 349 350
}

static void parse_treeish_arg(const char **argv,
351 352
		struct archiver_args *ar_args, const char *prefix,
		int remote)
353 354 355 356 357 358
{
	const char *name = argv[0];
	const unsigned char *commit_sha1;
	time_t archive_time;
	struct tree *tree;
	const struct commit *commit;
359
	struct object_id oid;
360

361
	/* Remotes are only allowed to fetch actual refs */
362
	if (remote && !remote_allow_unreachable) {
363
		char *ref = NULL;
364 365
		const char *colon = strchrnul(name, ':');
		int refnamelen = colon - name;
366

367
		if (!dwim_ref(name, refnamelen, oid.hash, &ref))
368
			die("no such ref: %.*s", refnamelen, name);
369 370
		free(ref);
	}
371

372
	if (get_sha1(name, oid.hash))
373
		die("Not a valid object name");
374

375
	commit = lookup_commit_reference_gently(oid.hash, 1);
376
	if (commit) {
377
		commit_sha1 = commit->object.oid.hash;
378 379 380 381 382 383
		archive_time = commit->date;
	} else {
		commit_sha1 = NULL;
		archive_time = time(NULL);
	}

384
	tree = parse_tree_indirect(oid.hash);
385 386 387 388
	if (tree == NULL)
		die("not a tree object");

	if (prefix) {
389
		struct object_id tree_oid;
390 391 392
		unsigned int mode;
		int err;

393
		err = get_tree_entry(tree->object.oid.hash, prefix,
394
				     tree_oid.hash, &mode);
395 396 397
		if (err || !S_ISDIR(mode))
			die("current working directory is untracked");

398
		tree = parse_tree_indirect(tree_oid.hash);
399 400 401 402 403 404 405
	}
	ar_args->tree = tree;
	ar_args->commit_sha1 = commit_sha1;
	ar_args->commit = commit;
	ar_args->time = archive_time;
}

406 407 408 409 410 411 412
#define OPT__COMPR(s, v, h, p) \
	{ OPTION_SET_INT, (s), NULL, (v), NULL, (h), \
	  PARSE_OPT_NOARG | PARSE_OPT_NONEG, NULL, (p) }
#define OPT__COMPR_HIDDEN(s, v, p) \
	{ OPTION_SET_INT, (s), NULL, (v), NULL, "", \
	  PARSE_OPT_NOARG | PARSE_OPT_NONEG | PARSE_OPT_HIDDEN, NULL, (p) }

413
static int parse_archive_args(int argc, const char **argv,
414
		const struct archiver **ar, struct archiver_args *args,
415
		const char *name_hint, int is_remote)
416
{
417
	const char *format = NULL;
418 419 420
	const char *base = NULL;
	const char *remote = NULL;
	const char *exec = NULL;
421
	const char *output = NULL;
422 423 424
	int compression_level = -1;
	int verbose = 0;
	int i;
425
	int list = 0;
426
	int worktree_attributes = 0;
427 428
	struct option opts[] = {
		OPT_GROUP(""),
429 430 431 432 433
		OPT_STRING(0, "format", &format, N_("fmt"), N_("archive format")),
		OPT_STRING(0, "prefix", &base, N_("prefix"),
			N_("prepend prefix to each pathname in the archive")),
		OPT_STRING('o', "output", &output, N_("file"),
			N_("write the archive to this file")),
434
		OPT_BOOL(0, "worktree-attributes", &worktree_attributes,
435 436 437 438
			N_("read .gitattributes in working directory")),
		OPT__VERBOSE(&verbose, N_("report archived files on stderr")),
		OPT__COMPR('0', &compression_level, N_("store only"), 0),
		OPT__COMPR('1', &compression_level, N_("compress faster"), 1),
439 440 441 442 443 444 445
		OPT__COMPR_HIDDEN('2', &compression_level, 2),
		OPT__COMPR_HIDDEN('3', &compression_level, 3),
		OPT__COMPR_HIDDEN('4', &compression_level, 4),
		OPT__COMPR_HIDDEN('5', &compression_level, 5),
		OPT__COMPR_HIDDEN('6', &compression_level, 6),
		OPT__COMPR_HIDDEN('7', &compression_level, 7),
		OPT__COMPR_HIDDEN('8', &compression_level, 8),
446
		OPT__COMPR('9', &compression_level, N_("compress better"), 9),
447
		OPT_GROUP(""),
448
		OPT_BOOL('l', "list", &list,
449
			N_("list supported archive formats")),
450
		OPT_GROUP(""),
451 452
		OPT_STRING(0, "remote", &remote, N_("repo"),
			N_("retrieve the archive from remote repository <repo>")),
453
		OPT_STRING(0, "exec", &exec, N_("command"),
454
			N_("path to the remote git-upload-archive command")),
455 456 457
		OPT_END()
	};

458
	argc = parse_options(argc, argv, NULL, opts, archive_usage, 0);
459 460 461 462 463

	if (remote)
		die("Unexpected option --remote");
	if (exec)
		die("Option --exec can only be used together with --remote");
464 465
	if (output)
		die("Unexpected option --output");
466 467 468 469 470

	if (!base)
		base = "";

	if (list) {
471
		for (i = 0; i < nr_archivers; i++)
472 473
			if (!is_remote || archivers[i]->flags & ARCHIVER_REMOTE)
				printf("%s\n", archivers[i]->name);
474
		exit(0);
475 476
	}

477 478 479 480 481
	if (!format && name_hint)
		format = archive_format_from_filename(name_hint);
	if (!format)
		format = "tar";

482
	/* We need at least one parameter -- tree-ish */
483 484
	if (argc < 1)
		usage_with_options(archive_usage, opts);
485
	*ar = lookup_archiver(format);
486
	if (!*ar || (is_remote && !((*ar)->flags & ARCHIVER_REMOTE)))
487 488 489 490
		die("Unknown archive format '%s'", format);

	args->compression_level = Z_DEFAULT_COMPRESSION;
	if (compression_level != -1) {
491
		if ((*ar)->flags & ARCHIVER_WANT_COMPRESSION_LEVELS)
492 493 494 495 496 497 498 499 500
			args->compression_level = compression_level;
		else {
			die("Argument not supported for format '%s': -%d",
					format, compression_level);
		}
	}
	args->verbose = verbose;
	args->base = base;
	args->baselen = strlen(base);
501
	args->worktree_attributes = worktree_attributes;
502

503
	return argc;
504 505
}

506
int write_archive(int argc, const char **argv, const char *prefix,
507
		  int setup_prefix, const char *name_hint, int remote)
508
{
509
	int nongit = 0;
510 511 512 513
	const struct archiver *ar = NULL;
	struct archiver_args args;

	if (setup_prefix && prefix == NULL)
514 515
		prefix = setup_git_directory_gently(&nongit);

516 517 518
	git_config_get_bool("uploadarchive.allowunreachable", &remote_allow_unreachable);
	git_config(git_default_config, NULL);

519 520
	init_tar_archiver();
	init_zip_archiver();
521

522
	argc = parse_archive_args(argc, argv, &ar, &args, name_hint, remote);
523 524 525 526 527 528 529 530
	if (nongit) {
		/*
		 * We know this will die() with an error, so we could just
		 * die ourselves; but its error message will be more specific
		 * than what we could write here.
		 */
		setup_git_directory();
	}
531

532
	parse_treeish_arg(argv, &args, prefix, remote);
533 534
	parse_pathspec_arg(argv + 1, &args);

535
	return ar->write_archive(ar, &args);
536
}
537

538 539 540 541 542 543 544 545 546
static int match_extension(const char *filename, const char *ext)
{
	int prefixlen = strlen(filename) - strlen(ext);

	/*
	 * We need 1 character for the '.', and 1 character to ensure that the
	 * prefix is non-empty (k.e., we don't match .tar.gz with no actual
	 * filename).
	 */
547
	if (prefixlen < 2 || filename[prefixlen - 1] != '.')
548 549 550 551
		return 0;
	return !strcmp(filename + prefixlen, ext);
}

552 553
const char *archive_format_from_filename(const char *filename)
{
554 555 556 557 558
	int i;

	for (i = 0; i < nr_archivers; i++)
		if (match_extension(filename, archivers[i]->name))
			return archivers[i]->name;
559 560
	return NULL;
}