archive.c 14.7 KB
Newer Older
1
#include "cache.h"
2
#include "config.h"
3
#include "refs.h"
4
#include "object-store.h"
5
#include "commit.h"
6
#include "tree-walk.h"
7
#include "attr.h"
8
#include "archive.h"
9
#include "parse-options.h"
10
#include "unpack-trees.h"
11
#include "dir.h"
12 13

static char const * const archive_usage[] = {
14
	N_("git archive [<options>] <tree-ish> [<path>...]"),
15
	N_("git archive --list"),
16
	N_("git archive --remote <repo> [--exec <cmd>] [<options>] <tree-ish> [<path>...]"),
17
	N_("git archive --remote <repo> [--exec <cmd>] --list"),
18 19
	NULL
};
20

21 22 23
static const struct archiver **archivers;
static int nr_archivers;
static int alloc_archivers;
24
static int remote_allow_unreachable;
25 26 27 28 29 30

void register_archiver(struct archiver *ar)
{
	ALLOC_GROW(archivers, nr_archivers + 1, alloc_archivers);
	archivers[nr_archivers++] = ar;
}
31

32 33 34 35 36
static void format_subst(const struct commit *commit,
                         const char *src, size_t len,
                         struct strbuf *buf)
{
	char *to_free = NULL;
37
	struct strbuf fmt = STRBUF_INIT;
38
	struct pretty_print_context ctx = {0};
39
	ctx.date_mode.type = DATE_NORMAL;
40
	ctx.abbrev = DEFAULT_ABBREV;
41 42 43 44 45 46 47

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

		b = memmem(src, len, "$Format:", 8);
48
		if (!b)
49
			break;
50
		c = memchr(b + 8, '$', (src + len) - b - 8);
51 52 53 54 55 56 57
		if (!c)
			break;

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

		strbuf_add(buf, src, b - src);
58
		format_commit_message(commit, fmt.buf, buf, &ctx);
59 60 61 62 63 64 65 66
		len -= c + 1 - src;
		src  = c + 1;
	}
	strbuf_add(buf, src, len);
	strbuf_release(&fmt);
	free(to_free);
}

67 68 69 70
void *object_file_to_archive(const struct archiver_args *args,
			     const char *path, const struct object_id *oid,
			     unsigned int mode, enum object_type *type,
			     unsigned long *sizep)
71 72
{
	void *buffer;
73
	const struct commit *commit = args->convert ? args->commit : NULL;
74

75
	path += args->baselen;
76
	buffer = read_object_file(oid, type, sizep);
77
	if (buffer && S_ISREG(mode)) {
78
		struct strbuf buf = STRBUF_INIT;
79 80 81 82
		size_t size = 0;

		strbuf_attach(&buf, buffer, *sizep, *sizep + 1);
		convert_to_working_tree(path, buf.buf, buf.len, &buf);
83 84
		if (commit)
			format_subst(commit, buf.buf, buf.len, &buf);
85 86 87 88 89 90 91
		buffer = strbuf_detach(&buf, &size);
		*sizep = size;
	}

	return buffer;
}

92 93
struct directory {
	struct directory *up;
94
	struct object_id oid;
95 96 97 98 99 100
	int baselen, len;
	unsigned mode;
	int stage;
	char path[FLEX_ARRAY];
};

101 102 103
struct archiver_context {
	struct archiver_args *args;
	write_archive_entry_fn_t write_entry;
104
	struct directory *bottom;
105 106
};

107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124
static const struct attr_check *get_archive_attrs(const char *path)
{
	static struct attr_check *check;
	if (!check)
		check = attr_check_initl("export-ignore", "export-subst", NULL);
	return git_check_attr(path, check) ? NULL : check;
}

static int check_attr_export_ignore(const struct attr_check *check)
{
	return check && ATTR_TRUE(check->items[0].value);
}

static int check_attr_export_subst(const struct attr_check *check)
{
	return check && ATTR_TRUE(check->items[1].value);
}

125
static int write_archive_entry(const struct object_id *oid, const char *base,
126 127 128 129 130 131 132 133
		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;
	int err;
134
	const char *path_without_prefix;
135

136
	args->convert = 0;
137 138
	strbuf_reset(&path);
	strbuf_grow(&path, PATH_MAX);
139
	strbuf_add(&path, args->base, args->baselen);
140 141
	strbuf_add(&path, base, baselen);
	strbuf_addstr(&path, filename);
142 143
	if (S_ISDIR(mode) || S_ISGITLINK(mode))
		strbuf_addch(&path, '/');
144
	path_without_prefix = path.buf + args->baselen;
145

146
	if (!S_ISDIR(mode)) {
147 148 149
		const struct attr_check *check;
		check = get_archive_attrs(path_without_prefix);
		if (check_attr_export_ignore(check))
150
			return 0;
151
		args->convert = check_attr_export_subst(check);
152
	}
153 154 155 156

	if (S_ISDIR(mode) || S_ISGITLINK(mode)) {
		if (args->verbose)
			fprintf(stderr, "%.*s\n", (int)path.len, path.buf);
157
		err = write_entry(args, oid, path.buf, path.len, mode);
158 159
		if (err)
			return err;
160
		return (S_ISDIR(mode) ? READ_TREE_RECURSIVE : 0);
161 162 163 164
	}

	if (args->verbose)
		fprintf(stderr, "%.*s\n", (int)path.len, path.buf);
165
	return write_entry(args, oid, path.buf, path.len, mode);
166 167
}

168
static void queue_directory(const unsigned char *sha1,
169
		struct strbuf *base, const char *filename,
170 171 172
		unsigned mode, int stage, struct archiver_context *c)
{
	struct directory *d;
173 174
	size_t len = st_add4(base->len, 1, strlen(filename), 1);
	d = xmalloc(st_add(sizeof(*d), len));
175
	d->up	   = c->bottom;
176
	d->baselen = base->len;
177 178 179
	d->mode	   = mode;
	d->stage   = stage;
	c->bottom  = d;
180
	d->len = xsnprintf(d->path, len, "%.*s%s/", (int)base->len, base->buf, filename);
181
	hashcpy(d->oid.hash, sha1);
182 183 184 185 186 187 188 189 190 191 192 193 194
}

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) ||
195
		write_archive_entry(&d->oid, d->path, d->baselen,
196 197 198 199 200 201
				    d->path + d->baselen, d->mode,
				    d->stage, c) != READ_TREE_RECURSIVE;
	free(d);
	return ret ? -1 : 0;
}

202
static int queue_or_write_archive_entry(const struct object_id *oid,
203
		struct strbuf *base, const char *filename,
204 205 206 207 208
		unsigned mode, int stage, void *context)
{
	struct archiver_context *c = context;

	while (c->bottom &&
209 210
	       !(base->len >= c->bottom->len &&
		 !strncmp(base->buf, c->bottom->path, c->bottom->len))) {
211 212 213 214 215 216
		struct directory *next = c->bottom->up;
		free(c->bottom);
		c->bottom = next;
	}

	if (S_ISDIR(mode)) {
217 218 219 220 221 222 223 224 225 226 227
		size_t baselen = base->len;
		const struct attr_check *check;

		/* Borrow base, but restore its original value when done. */
		strbuf_addstr(base, filename);
		strbuf_addch(base, '/');
		check = get_archive_attrs(base->buf);
		strbuf_setlen(base, baselen);

		if (check_attr_export_ignore(check))
			return 0;
228
		queue_directory(oid->hash, base, filename,
229 230 231 232 233 234
				mode, stage, c);
		return READ_TREE_RECURSIVE;
	}

	if (write_directory(c))
		return -1;
235
	return write_archive_entry(oid, base->buf, base->len, filename, mode,
236 237 238
				   stage, context);
}

239 240 241 242
int write_archive_entries(struct archiver_args *args,
		write_archive_entry_fn_t write_entry)
{
	struct archiver_context context;
243 244
	struct unpack_trees_options opts;
	struct tree_desc t;
245 246 247 248 249 250 251 252 253
	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);
254
		err = write_entry(args, &args->tree->object.oid, args->base,
255
				  len, 040777);
256 257 258 259
		if (err)
			return err;
	}

260
	memset(&context, 0, sizeof(context));
261 262 263
	context.args = args;
	context.write_entry = write_entry;

264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279
	/*
	 * 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);
	}

280
	err = read_tree_recursive(args->tree, "", 0, 0, &args->pathspec,
281
				  queue_or_write_archive_entry,
282
				  &context);
283 284
	if (err == READ_TREE_RECURSIVE)
		err = 0;
285 286 287 288 289
	while (context.bottom) {
		struct directory *next = context.bottom->up;
		free(context.bottom);
		context.bottom = next;
	}
290 291
	return err;
}
292

293 294 295 296
static const struct archiver *lookup_archiver(const char *name)
{
	int i;

297 298 299
	if (!name)
		return NULL;

300 301 302
	for (i = 0; i < nr_archivers; i++) {
		if (!strcmp(name, archivers[i]->name))
			return archivers[i];
303 304 305 306
	}
	return NULL;
}

307
static int reject_entry(const struct object_id *oid, struct strbuf *base,
308
			const char *filename, unsigned mode,
309 310
			int stage, void *context)
{
311 312 313
	int ret = -1;
	if (S_ISDIR(mode)) {
		struct strbuf sb = STRBUF_INIT;
314
		strbuf_addbuf(&sb, base);
315 316 317 318 319 320
		strbuf_addstr(&sb, filename);
		if (!match_pathspec(context, sb.buf, sb.len, 0, NULL, 1))
			ret = READ_TREE_RECURSIVE;
		strbuf_release(&sb);
	}
	return ret;
321 322 323 324
}

static int path_exists(struct tree *tree, const char *path)
{
325 326 327 328
	const char *paths[] = { path, NULL };
	struct pathspec pathspec;
	int ret;

329
	parse_pathspec(&pathspec, 0, 0, "", paths);
330 331 332
	pathspec.recursive = 1;
	ret = read_tree_recursive(tree, "", 0, 0, &pathspec,
				  reject_entry, &pathspec);
333
	clear_pathspec(&pathspec);
334
	return ret != 0;
335 336
}

337 338 339
static void parse_pathspec_arg(const char **pathspec,
		struct archiver_args *ar_args)
{
340 341 342 343 344 345 346 347
	/*
	 * 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);
348
	ar_args->pathspec.recursive = 1;
349 350
	if (pathspec) {
		while (*pathspec) {
351
			if (**pathspec && !path_exists(ar_args->tree, *pathspec))
352
				die(_("pathspec '%s' did not match any files"), *pathspec);
353 354 355
			pathspec++;
		}
	}
356 357 358
}

static void parse_treeish_arg(const char **argv,
359 360
		struct archiver_args *ar_args, const char *prefix,
		int remote)
361 362 363 364 365 366
{
	const char *name = argv[0];
	const unsigned char *commit_sha1;
	time_t archive_time;
	struct tree *tree;
	const struct commit *commit;
367
	struct object_id oid;
368

369
	/* Remotes are only allowed to fetch actual refs */
370
	if (remote && !remote_allow_unreachable) {
371
		char *ref = NULL;
372 373
		const char *colon = strchrnul(name, ':');
		int refnamelen = colon - name;
374

375
		if (!dwim_ref(name, refnamelen, &oid, &ref))
376
			die("no such ref: %.*s", refnamelen, name);
377 378
		free(ref);
	}
379

380
	if (get_oid(name, &oid))
381
		die("Not a valid object name");
382

383
	commit = lookup_commit_reference_gently(&oid, 1);
384
	if (commit) {
385
		commit_sha1 = commit->object.oid.hash;
386 387 388 389 390 391
		archive_time = commit->date;
	} else {
		commit_sha1 = NULL;
		archive_time = time(NULL);
	}

392
	tree = parse_tree_indirect(&oid);
393 394 395 396
	if (tree == NULL)
		die("not a tree object");

	if (prefix) {
397
		struct object_id tree_oid;
398 399 400
		unsigned int mode;
		int err;

401 402
		err = get_tree_entry(&tree->object.oid, prefix, &tree_oid,
				     &mode);
403 404 405
		if (err || !S_ISDIR(mode))
			die("current working directory is untracked");

406
		tree = parse_tree_indirect(&tree_oid);
407 408 409 410 411 412 413
	}
	ar_args->tree = tree;
	ar_args->commit_sha1 = commit_sha1;
	ar_args->commit = commit;
	ar_args->time = archive_time;
}

414
#define OPT__COMPR(s, v, h, p) \
415
	OPT_SET_INT_F(s, NULL, v, h, p, PARSE_OPT_NONEG)
416
#define OPT__COMPR_HIDDEN(s, v, p) \
417
	OPT_SET_INT_F(s, NULL, v, "", p, PARSE_OPT_NONEG | PARSE_OPT_HIDDEN)
418

419
static int parse_archive_args(int argc, const char **argv,
420
		const struct archiver **ar, struct archiver_args *args,
421
		const char *name_hint, int is_remote)
422
{
423
	const char *format = NULL;
424 425 426
	const char *base = NULL;
	const char *remote = NULL;
	const char *exec = NULL;
427
	const char *output = NULL;
428 429 430
	int compression_level = -1;
	int verbose = 0;
	int i;
431
	int list = 0;
432
	int worktree_attributes = 0;
433 434
	struct option opts[] = {
		OPT_GROUP(""),
435 436 437 438 439
		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")),
440
		OPT_BOOL(0, "worktree-attributes", &worktree_attributes,
441 442 443 444
			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),
445 446 447 448 449 450 451
		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),
452
		OPT__COMPR('9', &compression_level, N_("compress better"), 9),
453
		OPT_GROUP(""),
454
		OPT_BOOL('l', "list", &list,
455
			N_("list supported archive formats")),
456
		OPT_GROUP(""),
457 458
		OPT_STRING(0, "remote", &remote, N_("repo"),
			N_("retrieve the archive from remote repository <repo>")),
459
		OPT_STRING(0, "exec", &exec, N_("command"),
460
			N_("path to the remote git-upload-archive command")),
461 462 463
		OPT_END()
	};

464
	argc = parse_options(argc, argv, NULL, opts, archive_usage, 0);
465 466

	if (remote)
467
		die(_("Unexpected option --remote"));
468
	if (exec)
469
		die(_("Option --exec can only be used together with --remote"));
470
	if (output)
471
		die(_("Unexpected option --output"));
472 473 474 475 476

	if (!base)
		base = "";

	if (list) {
477
		for (i = 0; i < nr_archivers; i++)
478 479
			if (!is_remote || archivers[i]->flags & ARCHIVER_REMOTE)
				printf("%s\n", archivers[i]->name);
480
		exit(0);
481 482
	}

483 484 485 486 487
	if (!format && name_hint)
		format = archive_format_from_filename(name_hint);
	if (!format)
		format = "tar";

488
	/* We need at least one parameter -- tree-ish */
489 490
	if (argc < 1)
		usage_with_options(archive_usage, opts);
491
	*ar = lookup_archiver(format);
492
	if (!*ar || (is_remote && !((*ar)->flags & ARCHIVER_REMOTE)))
493
		die(_("Unknown archive format '%s'"), format);
494 495 496

	args->compression_level = Z_DEFAULT_COMPRESSION;
	if (compression_level != -1) {
497
		if ((*ar)->flags & ARCHIVER_WANT_COMPRESSION_LEVELS)
498 499
			args->compression_level = compression_level;
		else {
500
			die(_("Argument not supported for format '%s': -%d"),
501 502 503 504 505 506
					format, compression_level);
		}
	}
	args->verbose = verbose;
	args->base = base;
	args->baselen = strlen(base);
507
	args->worktree_attributes = worktree_attributes;
508

509
	return argc;
510 511
}

512
int write_archive(int argc, const char **argv, const char *prefix,
513
		  const char *name_hint, int remote)
514 515 516 517
{
	const struct archiver *ar = NULL;
	struct archiver_args args;

518 519 520
	git_config_get_bool("uploadarchive.allowunreachable", &remote_allow_unreachable);
	git_config(git_default_config, NULL);

521 522
	init_tar_archiver();
	init_zip_archiver();
523

524
	argc = parse_archive_args(argc, argv, &ar, &args, name_hint, remote);
525
	if (!startup_info->have_repository) {
526 527 528 529 530 531 532
		/*
		 * 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();
	}
533

534
	parse_treeish_arg(argv, &args, prefix, remote);
535 536
	parse_pathspec_arg(argv + 1, &args);

537
	return ar->write_archive(ar, &args);
538
}
539

540 541 542 543 544 545 546 547 548
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).
	 */
549
	if (prefixlen < 2 || filename[prefixlen - 1] != '.')
550 551 552 553
		return 0;
	return !strcmp(filename + prefixlen, ext);
}

554 555
const char *archive_format_from_filename(const char *filename)
{
556 557 558 559 560
	int i;

	for (i = 0; i < nr_archivers; i++)
		if (match_extension(filename, archivers[i]->name))
			return archivers[i]->name;
561 562
	return NULL;
}