fast-import.c 42.6 KB
Newer Older
1 2 3 4 5 6
/*
Format of STDIN stream:

  stream ::= cmd*;

  cmd ::= new_blob
7
        | new_commit
8
        | new_tag
9
        | reset_branch
10 11
        ;

12 13 14 15
  new_blob ::= 'blob' lf
	mark?
    file_content;
  file_content ::= data;
16

17
  new_commit ::= 'commit' sp ref_str lf
18 19 20 21
    mark?
    ('author' sp name '<' email '>' ts tz lf)?
    'committer' sp name '<' email '>' ts tz lf
    commit_msg
22
    ('from' sp (ref_str | hexsha1 | sha1exp_str | idnum) lf)?
23
    ('merge' sp (ref_str | hexsha1 | sha1exp_str | idnum) lf)*
24 25 26
    file_change*
    lf;
  commit_msg ::= data;
27

28 29
  file_change ::= 'M' sp mode sp (hexsha1 | idnum) sp path_str lf
                | 'D' sp path_str lf
30
                ;
31 32 33 34 35 36 37 38
  mode ::= '644' | '755';

  new_tag ::= 'tag' sp tag_str lf
    'from' sp (ref_str | hexsha1 | sha1exp_str | idnum) lf
	'tagger' sp name '<' email '>' ts tz lf
    tag_msg;
  tag_msg ::= data;

39 40 41
  reset_branch ::= 'reset' sp ref_str lf
    ('from' sp (ref_str | hexsha1 | sha1exp_str | idnum) lf)?
    lf;
42

43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71
     # note: the first idnum in a stream should be 1 and subsequent
     # idnums should not have gaps between values as this will cause
     # the stream parser to reserve space for the gapped values.  An
	 # idnum can be updated in the future to a new object by issuing
     # a new mark directive with the old idnum.
	 #
  mark ::= 'mark' sp idnum lf;

     # note: declen indicates the length of binary_data in bytes.
     # declen does not include the lf preceeding or trailing the
     # binary data.
     #
  data ::= 'data' sp declen lf
    binary_data
	lf;

     # note: quoted strings are C-style quoting supporting \c for
     # common escapes of 'c' (e..g \n, \t, \\, \") or \nnn where nnn
	 # is the signed byte value in octal.  Note that the only
     # characters which must actually be escaped to protect the
     # stream formatting is: \, " and LF.  Otherwise these values
	 # are UTF8.
     #
  ref_str     ::= ref     | '"' quoted(ref)     '"' ;
  sha1exp_str ::= sha1exp | '"' quoted(sha1exp) '"' ;
  tag_str     ::= tag     | '"' quoted(tag)     '"' ;
  path_str    ::= path    | '"' quoted(path)    '"' ;

  declen ::= # unsigned 32 bit value, ascii base10 notation;
72
  binary_data ::= # file content, not interpreted;
73

74 75
  sp ::= # ASCII space character;
  lf ::= # ASCII newline (LF) character;
76 77 78 79 80 81 82 83 84

     # note: a colon (':') must precede the numerical value assigned to
	 # an idnum.  This is to distinguish it from a ref or tag name as
     # GIT does not permit ':' in ref or tag strings.
	 #
  idnum   ::= ':' declen;
  path    ::= # GIT style file path, e.g. "a/b/c";
  ref     ::= # GIT ref name, e.g. "refs/heads/MOZ_GECKO_EXPERIMENT";
  tag     ::= # GIT tag name, e.g. "FIREFOX_1_5";
85 86
  sha1exp ::= # Any valid GIT SHA1 expression;
  hexsha1 ::= # SHA1 in hexadecimal format;
87 88 89 90 91 92

     # note: name and email are UTF8 strings, however name must not
	 # contain '<' or lf and email must not contain any of the
     # following: '<', '>', lf.
	 #
  name  ::= # valid GIT author/committer name;
93
  email ::= # valid GIT author/committer email;
94 95
  ts    ::= # time since the epoch in seconds, ascii base10 notation;
  tz    ::= # GIT style timezone;
96 97
*/

98 99 100 101
#include "builtin.h"
#include "cache.h"
#include "object.h"
#include "blob.h"
102
#include "tree.h"
103 104
#include "delta.h"
#include "pack.h"
105
#include "refs.h"
106
#include "csum-file.h"
107 108
#include "strbuf.h"
#include "quote.h"
109

110 111 112 113
struct object_entry
{
	struct object_entry *next;
	unsigned long offset;
114
	unsigned type : TYPE_BITS;
115 116 117
	unsigned char sha1[20];
};

118
struct object_entry_pool
119
{
120
	struct object_entry_pool *next_pool;
121 122
	struct object_entry *next_free;
	struct object_entry *end;
123
	struct object_entry entries[FLEX_ARRAY]; /* more */
124 125
};

126 127 128 129 130 131 132 133 134
struct mark_set
{
	int shift;
	union {
		struct object_entry *marked[1024];
		struct mark_set *sets[1024];
	} data;
};

135 136 137
struct last_object
{
	void *data;
138
	unsigned long len;
139
	unsigned long offset;
140
	unsigned int depth;
141
	unsigned no_free:1;
142 143
};

144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159
struct mem_pool
{
	struct mem_pool *next_pool;
	char *next_free;
	char *end;
	char space[FLEX_ARRAY]; /* more */
};

struct atom_str
{
	struct atom_str *next_atom;
	int str_len;
	char str_dat[FLEX_ARRAY]; /* more */
};

struct tree_content;
160 161
struct tree_entry
{
162 163
	struct tree_content *tree;
	struct atom_str* name;
164 165 166 167 168
	struct tree_entry_ms
	{
		unsigned int mode;
		unsigned char sha1[20];
	} versions[2];
169 170
};

171
struct tree_content
172
{
173 174
	unsigned int entry_capacity; /* must match avail_tree_content */
	unsigned int entry_count;
175
	unsigned int delta_depth;
176 177 178 179 180 181 182
	struct tree_entry *entries[FLEX_ARRAY]; /* more */
};

struct avail_tree_content
{
	unsigned int entry_capacity; /* must match tree_content */
	struct avail_tree_content *next_avail;
183 184 185 186
};

struct branch
{
187 188
	struct branch *table_next_branch;
	struct branch *active_next_branch;
189
	const char *name;
190 191 192
	unsigned long last_commit;
	struct tree_entry branch_tree;
	unsigned char sha1[20];
193 194
};

195 196 197 198 199 200 201
struct tag
{
	struct tag *next_tag;
	const char *name;
	unsigned char sha1[20];
};

202 203 204 205 206 207
struct dbuf
{
	void *buffer;
	size_t capacity;
};

208 209 210 211 212
struct hash_list
{
	struct hash_list *next;
	unsigned char sha1[20];
};
213 214

/* Stats and misc. counters */
215
static unsigned long max_depth = 10;
216
static unsigned long alloc_count;
217
static unsigned long branch_count;
218
static unsigned long branch_load_count;
219
static unsigned long object_count;
220
static unsigned long duplicate_count;
221
static unsigned long marks_set_count;
222 223 224
static unsigned long object_count_by_type[1 << TYPE_BITS];
static unsigned long duplicate_count_by_type[1 << TYPE_BITS];
static unsigned long delta_count_by_type[1 << TYPE_BITS];
225

226 227 228 229 230
/* Memory pools */
static size_t mem_pool_alloc = 2*1024*1024 - sizeof(struct mem_pool);
static size_t total_allocd;
static struct mem_pool *mem_pool;

231
/* Atom management */
232 233 234 235 236
static unsigned int atom_table_sz = 4451;
static unsigned int atom_cnt;
static struct atom_str **atom_table;

/* The .pack file being generated */
237 238 239 240
static const char *base_name;
static unsigned int pack_count;
static char *pack_name;
static char *idx_name;
241
static struct packed_git *pack_data;
242
static int pack_fd;
243
static unsigned long pack_size;
244 245 246
static unsigned char pack_sha1[20];

/* Table of objects we've written. */
247
static unsigned int object_entry_alloc = 5000;
248 249
static struct object_entry_pool *blocks;
static struct object_entry *object_table[1 << 16];
250
static struct mark_set *marks;
251
static const char* mark_file;
252 253

/* Our last blob */
254 255 256 257 258 259 260
static struct last_object last_blob;

/* Tree management */
static unsigned int tree_entry_alloc = 1000;
static void *avail_tree_entry;
static unsigned int avail_tree_table_sz = 100;
static struct avail_tree_content **avail_tree_table;
261 262
static struct dbuf old_tree;
static struct dbuf new_tree;
263

264
/* Branch data */
265 266 267
static unsigned long max_active_branches = 5;
static unsigned long cur_active_branches;
static unsigned long branch_table_sz = 1039;
268 269 270
static struct branch **branch_table;
static struct branch *active_branches;

271 272 273 274
/* Tag data */
static struct tag *first_tag;
static struct tag *last_tag;

275 276
/* Input stream parsing */
static struct strbuf command_buf;
277
static unsigned long next_mark;
278
static struct dbuf new_data;
279
static FILE* branch_log;
280

281

282
static void alloc_objects(unsigned int cnt)
283
{
284
	struct object_entry_pool *b;
285

286
	b = xmalloc(sizeof(struct object_entry_pool)
287
		+ cnt * sizeof(struct object_entry));
288
	b->next_pool = blocks;
289 290 291 292 293
	b->next_free = b->entries;
	b->end = b->entries + cnt;
	blocks = b;
	alloc_count += cnt;
}
294

295
static struct object_entry* new_object(unsigned char *sha1)
296
{
297
	struct object_entry *e;
298

299
	if (blocks->next_free == blocks->end)
300
		alloc_objects(object_entry_alloc);
301

302
	e = blocks->next_free++;
303
	hashcpy(e->sha1, sha1);
304
	return e;
305 306
}

307 308 309 310 311
static struct object_entry* find_object(unsigned char *sha1)
{
	unsigned int h = sha1[0] << 8 | sha1[1];
	struct object_entry *e;
	for (e = object_table[h]; e; e = e->next)
312
		if (!hashcmp(sha1, e->sha1))
313 314 315 316
			return e;
	return NULL;
}

317 318 319
static struct object_entry* insert_object(unsigned char *sha1)
{
	unsigned int h = sha1[0] << 8 | sha1[1];
320
	struct object_entry *e = object_table[h];
321
	struct object_entry *p = NULL;
322 323

	while (e) {
324
		if (!hashcmp(sha1, e->sha1))
325 326 327 328 329 330
			return e;
		p = e;
		e = e->next;
	}

	e = new_object(sha1);
331
	e->next = NULL;
332 333 334 335
	e->offset = 0;
	if (p)
		p->next = e;
	else
336
		object_table[h] = e;
337 338
	return e;
}
339

340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370
static unsigned int hc_str(const char *s, size_t len)
{
	unsigned int r = 0;
	while (len-- > 0)
		r = r * 31 + *s++;
	return r;
}

static void* pool_alloc(size_t len)
{
	struct mem_pool *p;
	void *r;

	for (p = mem_pool; p; p = p->next_pool)
		if ((p->end - p->next_free >= len))
			break;

	if (!p) {
		if (len >= (mem_pool_alloc/2)) {
			total_allocd += len;
			return xmalloc(len);
		}
		total_allocd += sizeof(struct mem_pool) + mem_pool_alloc;
		p = xmalloc(sizeof(struct mem_pool) + mem_pool_alloc);
		p->next_pool = mem_pool;
		p->next_free = p->space;
		p->end = p->next_free + mem_pool_alloc;
		mem_pool = p;
	}

	r = p->next_free;
371 372 373
	/* round out to a pointer alignment */
	if (len & (sizeof(void*) - 1))
		len += sizeof(void*) - (len & (sizeof(void*) - 1));
374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392
	p->next_free += len;
	return r;
}

static void* pool_calloc(size_t count, size_t size)
{
	size_t len = count * size;
	void *r = pool_alloc(len);
	memset(r, 0, len);
	return r;
}

static char* pool_strdup(const char *s)
{
	char *r = pool_alloc(strlen(s) + 1);
	strcpy(r, s);
	return r;
}

393 394 395 396 397 398 399 400 401 402 403
static void size_dbuf(struct dbuf *b, size_t maxlen)
{
	if (b->buffer) {
		if (b->capacity >= maxlen)
			return;
		free(b->buffer);
	}
	b->capacity = ((maxlen / 1024) + 1) * 1024;
	b->buffer = xmalloc(b->capacity);
}

404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445
static void insert_mark(unsigned long idnum, struct object_entry *oe)
{
	struct mark_set *s = marks;
	while ((idnum >> s->shift) >= 1024) {
		s = pool_calloc(1, sizeof(struct mark_set));
		s->shift = marks->shift + 10;
		s->data.sets[0] = marks;
		marks = s;
	}
	while (s->shift) {
		unsigned long i = idnum >> s->shift;
		idnum -= i << s->shift;
		if (!s->data.sets[i]) {
			s->data.sets[i] = pool_calloc(1, sizeof(struct mark_set));
			s->data.sets[i]->shift = s->shift - 10;
		}
		s = s->data.sets[i];
	}
	if (!s->data.marked[idnum])
		marks_set_count++;
	s->data.marked[idnum] = oe;
}

static struct object_entry* find_mark(unsigned long idnum)
{
	unsigned long orig_idnum = idnum;
	struct mark_set *s = marks;
	struct object_entry *oe = NULL;
	if ((idnum >> s->shift) < 1024) {
		while (s && s->shift) {
			unsigned long i = idnum >> s->shift;
			idnum -= i << s->shift;
			s = s->data.sets[i];
		}
		if (s)
			oe = s->data.marked[idnum];
	}
	if (!oe)
		die("mark :%lu not declared", orig_idnum);
	return oe;
}

446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482
static struct atom_str* to_atom(const char *s, size_t len)
{
	unsigned int hc = hc_str(s, len) % atom_table_sz;
	struct atom_str *c;

	for (c = atom_table[hc]; c; c = c->next_atom)
		if (c->str_len == len && !strncmp(s, c->str_dat, len))
			return c;

	c = pool_alloc(sizeof(struct atom_str) + len + 1);
	c->str_len = len;
	strncpy(c->str_dat, s, len);
	c->str_dat[len] = 0;
	c->next_atom = atom_table[hc];
	atom_table[hc] = c;
	atom_cnt++;
	return c;
}

static struct branch* lookup_branch(const char *name)
{
	unsigned int hc = hc_str(name, strlen(name)) % branch_table_sz;
	struct branch *b;

	for (b = branch_table[hc]; b; b = b->table_next_branch)
		if (!strcmp(name, b->name))
			return b;
	return NULL;
}

static struct branch* new_branch(const char *name)
{
	unsigned int hc = hc_str(name, strlen(name)) % branch_table_sz;
	struct branch* b = lookup_branch(name);

	if (b)
		die("Invalid attempt to create duplicate branch: %s", name);
483 484
	if (check_ref_format(name))
		die("Branch name doesn't conform to GIT standards: %s", name);
485 486 487 488

	b = pool_calloc(1, sizeof(struct branch));
	b->name = pool_strdup(name);
	b->table_next_branch = branch_table[hc];
489 490
	b->branch_tree.versions[0].mode = S_IFDIR;
	b->branch_tree.versions[1].mode = S_IFDIR;
491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524
	branch_table[hc] = b;
	branch_count++;
	return b;
}

static unsigned int hc_entries(unsigned int cnt)
{
	cnt = cnt & 7 ? (cnt / 8) + 1 : cnt / 8;
	return cnt < avail_tree_table_sz ? cnt : avail_tree_table_sz - 1;
}

static struct tree_content* new_tree_content(unsigned int cnt)
{
	struct avail_tree_content *f, *l = NULL;
	struct tree_content *t;
	unsigned int hc = hc_entries(cnt);

	for (f = avail_tree_table[hc]; f; l = f, f = f->next_avail)
		if (f->entry_capacity >= cnt)
			break;

	if (f) {
		if (l)
			l->next_avail = f->next_avail;
		else
			avail_tree_table[hc] = f->next_avail;
	} else {
		cnt = cnt & 7 ? ((cnt / 8) + 1) * 8 : cnt;
		f = pool_alloc(sizeof(*t) + sizeof(t->entries[0]) * cnt);
		f->entry_capacity = cnt;
	}

	t = (struct tree_content*)f;
	t->entry_count = 0;
525
	t->delta_depth = 0;
526 527 528 529 530 531 532 533
	return t;
}

static void release_tree_entry(struct tree_entry *e);
static void release_tree_content(struct tree_content *t)
{
	struct avail_tree_content *f = (struct avail_tree_content*)t;
	unsigned int hc = hc_entries(f->entry_capacity);
534 535 536 537 538 539
	f->next_avail = avail_tree_table[hc];
	avail_tree_table[hc] = f;
}

static void release_tree_content_recursive(struct tree_content *t)
{
540 541 542
	unsigned int i;
	for (i = 0; i < t->entry_count; i++)
		release_tree_entry(t->entries[i]);
543
	release_tree_content(t);
544 545 546 547 548 549 550 551
}

static struct tree_content* grow_tree_content(
	struct tree_content *t,
	int amt)
{
	struct tree_content *r = new_tree_content(t->entry_count + amt);
	r->entry_count = t->entry_count;
552
	r->delta_depth = t->delta_depth;
553 554 555 556 557 558 559 560 561 562 563
	memcpy(r->entries,t->entries,t->entry_count*sizeof(t->entries[0]));
	release_tree_content(t);
	return r;
}

static struct tree_entry* new_tree_entry()
{
	struct tree_entry *e;

	if (!avail_tree_entry) {
		unsigned int n = tree_entry_alloc;
564
		total_allocd += n * sizeof(struct tree_entry);
565
		avail_tree_entry = e = xmalloc(n * sizeof(struct tree_entry));
566
		while (n-- > 1) {
567 568 569
			*((void**)e) = e + 1;
			e++;
		}
570
		*((void**)e) = NULL;
571 572 573 574 575 576 577 578 579 580
	}

	e = avail_tree_entry;
	avail_tree_entry = *((void**)e);
	return e;
}

static void release_tree_entry(struct tree_entry *e)
{
	if (e->tree)
581
		release_tree_content_recursive(e->tree);
582 583 584 585 586
	*((void**)e) = avail_tree_entry;
	avail_tree_entry = e;
}

static void yread(int fd, void *buffer, size_t length)
587 588 589 590
{
	ssize_t ret = 0;
	while (ret < length) {
		ssize_t size = xread(fd, (char *) buffer + ret, length - ret);
591 592 593 594 595 596 597 598
		if (!size)
			die("Read from descriptor %i: end of stream", fd);
		if (size < 0)
			die("Read from descriptor %i: %s", fd, strerror(errno));
		ret += size;
	}
}

599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716
static void start_packfile()
{
	struct pack_header hdr;

	pack_count++;
	pack_name = xmalloc(strlen(base_name) + 11);
	idx_name = xmalloc(strlen(base_name) + 11);
	sprintf(pack_name, "%s%5.5i.pack", base_name, pack_count);
	sprintf(idx_name, "%s%5.5i.idx", base_name, pack_count);

	pack_fd = open(pack_name, O_RDWR|O_CREAT|O_EXCL, 0666);
	if (pack_fd < 0)
		die("Can't create %s: %s", pack_name, strerror(errno));

	pack_data = xcalloc(1, sizeof(*pack_data) + strlen(pack_name) + 2);
	strcpy(pack_data->pack_name, pack_name);
	pack_data->pack_fd = pack_fd;

	hdr.hdr_signature = htonl(PACK_SIGNATURE);
	hdr.hdr_version = htonl(2);
	hdr.hdr_entries = 0;

	write_or_die(pack_fd, &hdr, sizeof(hdr));
	pack_size = sizeof(hdr);
	object_count = 0;
}

static void fixup_header_footer()
{
	SHA_CTX c;
	char hdr[8];
	unsigned long cnt;
	char *buf;

	if (lseek(pack_fd, 0, SEEK_SET) != 0)
		die("Failed seeking to start: %s", strerror(errno));

	SHA1_Init(&c);
	yread(pack_fd, hdr, 8);
	SHA1_Update(&c, hdr, 8);

	cnt = htonl(object_count);
	SHA1_Update(&c, &cnt, 4);
	write_or_die(pack_fd, &cnt, 4);

	buf = xmalloc(128 * 1024);
	for (;;) {
		size_t n = xread(pack_fd, buf, 128 * 1024);
		if (n <= 0)
			break;
		SHA1_Update(&c, buf, n);
	}
	free(buf);

	SHA1_Final(pack_sha1, &c);
	write_or_die(pack_fd, pack_sha1, sizeof(pack_sha1));
}

static int oecmp (const void *a_, const void *b_)
{
	struct object_entry *a = *((struct object_entry**)a_);
	struct object_entry *b = *((struct object_entry**)b_);
	return hashcmp(a->sha1, b->sha1);
}

static void write_index(const char *idx_name)
{
	struct sha1file *f;
	struct object_entry **idx, **c, **last, *e;
	struct object_entry_pool *o;
	unsigned int array[256];
	int i;

	/* Build the sorted table of object IDs. */
	idx = xmalloc(object_count * sizeof(struct object_entry*));
	c = idx;
	for (o = blocks; o; o = o->next_pool)
		for (e = o->entries; e != o->next_free; e++)
			*c++ = e;
	last = idx + object_count;
	qsort(idx, object_count, sizeof(struct object_entry*), oecmp);

	/* Generate the fan-out array. */
	c = idx;
	for (i = 0; i < 256; i++) {
		struct object_entry **next = c;;
		while (next < last) {
			if ((*next)->sha1[0] != i)
				break;
			next++;
		}
		array[i] = htonl(next - idx);
		c = next;
	}

	f = sha1create("%s", idx_name);
	sha1write(f, array, 256 * sizeof(int));
	for (c = idx; c != last; c++) {
		unsigned int offset = htonl((*c)->offset);
		sha1write(f, &offset, 4);
		sha1write(f, (*c)->sha1, sizeof((*c)->sha1));
	}
	sha1write(f, pack_sha1, sizeof(pack_sha1));
	sha1close(f, NULL, 1);
	free(idx);
}

static void end_packfile()
{
	fixup_header_footer();
	close(pack_fd);
	write_index(idx_name);

	free(pack_name);
	free(idx_name);
	free(pack_data);
}

717
static size_t encode_header(
718
	enum object_type type,
719
	size_t size,
720
	unsigned char *hdr)
721 722 723 724
{
	int n = 1;
	unsigned char c;

725
	if (type < OBJ_COMMIT || type > OBJ_REF_DELTA)
726 727 728 729 730 731 732 733 734 735 736 737 738 739
		die("bad type %d", type);

	c = (type << 4) | (size & 15);
	size >>= 4;
	while (size) {
		*hdr++ = c | 0x80;
		c = size & 0x7f;
		size >>= 7;
		n++;
	}
	*hdr = c;
	return n;
}

740 741 742
static int store_object(
	enum object_type type,
	void *dat,
743
	size_t datlen,
744
	struct last_object *last,
745 746
	unsigned char *sha1out,
	unsigned long mark)
747 748
{
	void *out, *delta;
749 750 751
	struct object_entry *e;
	unsigned char hdr[96];
	unsigned char sha1[20];
752
	unsigned long hdrlen, deltalen;
753 754 755 756 757 758 759 760
	SHA_CTX c;
	z_stream s;

	hdrlen = sprintf((char*)hdr,"%s %lu",type_names[type],datlen) + 1;
	SHA1_Init(&c);
	SHA1_Update(&c, hdr, hdrlen);
	SHA1_Update(&c, dat, datlen);
	SHA1_Final(sha1, &c);
761
	if (sha1out)
762
		hashcpy(sha1out, sha1);
763 764

	e = insert_object(sha1);
765 766
	if (mark)
		insert_mark(mark, e);
767 768
	if (e->offset) {
		duplicate_count++;
769
		duplicate_count_by_type[type]++;
770
		return 1;
771
	}
772
	e->type = type;
773
	e->offset = pack_size;
774
	object_count++;
775
	object_count_by_type[type]++;
776

777
	if (last && last->data && last->depth < max_depth)
778
		delta = diff_delta(last->data, last->len,
779 780
			dat, datlen,
			&deltalen, 0);
781
	else
782 783 784 785 786 787
		delta = 0;

	memset(&s, 0, sizeof(s));
	deflateInit(&s, zlib_compression_level);

	if (delta) {
788 789 790
		unsigned long ofs = e->offset - last->offset;
		unsigned pos = sizeof(hdr) - 1;

791
		delta_count_by_type[type]++;
792
		last->depth++;
793 794
		s.next_in = delta;
		s.avail_in = deltalen;
795 796

		hdrlen = encode_header(OBJ_OFS_DELTA, deltalen, hdr);
797
		write_or_die(pack_fd, hdr, hdrlen);
798 799 800 801 802 803 804
		pack_size += hdrlen;

		hdr[pos] = ofs & 127;
		while (ofs >>= 7)
			hdr[--pos] = 128 | (--ofs & 127);
		write_or_die(pack_fd, hdr + pos, sizeof(hdr) - pos);
		pack_size += sizeof(hdr) - pos;
805
	} else {
806 807
		if (last)
			last->depth = 0;
808 809
		s.next_in = dat;
		s.avail_in = datlen;
810
		hdrlen = encode_header(type, datlen, hdr);
811
		write_or_die(pack_fd, hdr, hdrlen);
812
		pack_size += hdrlen;
813 814 815 816 817 818 819 820
	}

	s.avail_out = deflateBound(&s, s.avail_in);
	s.next_out = out = xmalloc(s.avail_out);
	while (deflate(&s, Z_FINISH) == Z_OK)
		/* nothing */;
	deflateEnd(&s);

821
	write_or_die(pack_fd, out, s.total_out);
822
	pack_size += s.total_out;
823 824 825 826

	free(out);
	if (delta)
		free(delta);
827
	if (last) {
828
		if (last->data && !last->no_free)
829 830
			free(last->data);
		last->data = dat;
831
		last->offset = e->offset;
832 833 834 835 836
		last->len = datlen;
	}
	return 0;
}

837
static void *gfi_unpack_entry(unsigned long ofs, unsigned long *sizep)
838
{
839 840 841
	char type[20];
	pack_data->pack_size = pack_size + 20;
	return unpack_entry(pack_data, ofs, type, sizep);
842 843
}

844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859
static const char *get_mode(const char *str, unsigned int *modep)
{
	unsigned char c;
	unsigned int mode = 0;

	while ((c = *str++) != ' ') {
		if (c < '0' || c > '7')
			return NULL;
		mode = (mode << 3) + (c - '0');
	}
	*modep = mode;
	return str;
}

static void load_tree(struct tree_entry *root)
{
860
	unsigned char* sha1 = root->versions[1].sha1;
861 862 863 864 865 866 867
	struct object_entry *myoe;
	struct tree_content *t;
	unsigned long size;
	char *buf;
	const char *c;

	root->tree = t = new_tree_content(8);
868
	if (is_null_sha1(sha1))
869 870
		return;

871
	myoe = find_object(sha1);
872
	if (myoe) {
873
		if (myoe->type != OBJ_TREE)
874
			die("Not a tree: %s", sha1_to_hex(sha1));
875 876
		t->delta_depth = 0;
		buf = gfi_unpack_entry(myoe->offset, &size);
877
	} else {
878
		char type[20];
879
		buf = read_sha1_file(sha1, type, &size);
880
		if (!buf || strcmp(type, tree_type))
881
			die("Can't load tree %s", sha1_to_hex(sha1));
882 883 884 885 886 887 888 889 890 891 892
	}

	c = buf;
	while (c != (buf + size)) {
		struct tree_entry *e = new_tree_entry();

		if (t->entry_count == t->entry_capacity)
			root->tree = t = grow_tree_content(t, 8);
		t->entries[t->entry_count++] = e;

		e->tree = NULL;
893
		c = get_mode(c, &e->versions[1].mode);
894
		if (!c)
895 896
			die("Corrupt mode in %s", sha1_to_hex(sha1));
		e->versions[0].mode = e->versions[1].mode;
897 898
		e->name = to_atom(c, strlen(c));
		c += e->name->str_len + 1;
899 900
		hashcpy(e->versions[0].sha1, (unsigned char*)c);
		hashcpy(e->versions[1].sha1, (unsigned char*)c);
901 902 903 904 905
		c += 20;
	}
	free(buf);
}

906
static int tecmp0 (const void *_a, const void *_b)
907 908 909 910
{
	struct tree_entry *a = *((struct tree_entry**)_a);
	struct tree_entry *b = *((struct tree_entry**)_b);
	return base_name_compare(
911 912
		a->name->str_dat, a->name->str_len, a->versions[0].mode,
		b->name->str_dat, b->name->str_len, b->versions[0].mode);
913 914
}

915
static int tecmp1 (const void *_a, const void *_b)
916
{
917 918 919 920 921 922 923
	struct tree_entry *a = *((struct tree_entry**)_a);
	struct tree_entry *b = *((struct tree_entry**)_b);
	return base_name_compare(
		a->name->str_dat, a->name->str_len, a->versions[1].mode,
		b->name->str_dat, b->name->str_len, b->versions[1].mode);
}

924 925 926 927
static void mktree(struct tree_content *t,
	int v,
	unsigned long *szp,
	struct dbuf *b)
928 929
{
	size_t maxlen = 0;
930
	unsigned int i;
931
	char *c;
932

933 934 935 936
	if (!v)
		qsort(t->entries,t->entry_count,sizeof(t->entries[0]),tecmp0);
	else
		qsort(t->entries,t->entry_count,sizeof(t->entries[0]),tecmp1);
937 938

	for (i = 0; i < t->entry_count; i++) {
939 940
		if (t->entries[i]->versions[v].mode)
			maxlen += t->entries[i]->name->str_len + 34;
941 942
	}

943
	size_dbuf(b, maxlen);
944
	c = b->buffer;
945 946
	for (i = 0; i < t->entry_count; i++) {
		struct tree_entry *e = t->entries[i];
947 948 949
		if (!e->versions[v].mode)
			continue;
		c += sprintf(c, "%o", e->versions[v].mode);
950 951 952
		*c++ = ' ';
		strcpy(c, e->name->str_dat);
		c += e->name->str_len + 1;
953
		hashcpy((unsigned char*)c, e->versions[v].sha1);
954 955
		c += 20;
	}
956
	*szp = c - (char*)b->buffer;
957 958 959 960 961 962
}

static void store_tree(struct tree_entry *root)
{
	struct tree_content *t = root->tree;
	unsigned int i, j, del;
963
	unsigned long new_len;
964
	struct last_object lo;
965
	struct object_entry *le;
966 967 968 969 970 971 972 973 974

	if (!is_null_sha1(root->versions[1].sha1))
		return;

	for (i = 0; i < t->entry_count; i++) {
		if (t->entries[i]->tree)
			store_tree(t->entries[i]);
	}

975 976
	le = find_object(root->versions[0].sha1);
	if (!S_ISDIR(root->versions[0].mode) || !le) {
977 978 979
		lo.data = NULL;
		lo.depth = 0;
	} else {
980 981
		mktree(t, 0, &lo.len, &old_tree);
		lo.data = old_tree.buffer;
982
		lo.offset = le->offset;
983
		lo.depth = t->delta_depth;
984
		lo.no_free = 1;
985 986
	}

987
	mktree(t, 1, &new_len, &new_tree);
988
	store_object(OBJ_TREE, new_tree.buffer, new_len,
989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003
		&lo, root->versions[1].sha1, 0);

	t->delta_depth = lo.depth;
	for (i = 0, j = 0, del = 0; i < t->entry_count; i++) {
		struct tree_entry *e = t->entries[i];
		if (e->versions[1].mode) {
			e->versions[0].mode = e->versions[1].mode;
			hashcpy(e->versions[0].sha1, e->versions[1].sha1);
			t->entries[j++] = e;
		} else {
			release_tree_entry(e);
			del++;
		}
	}
	t->entry_count -= del;
1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026
}

static int tree_content_set(
	struct tree_entry *root,
	const char *p,
	const unsigned char *sha1,
	const unsigned int mode)
{
	struct tree_content *t = root->tree;
	const char *slash1;
	unsigned int i, n;
	struct tree_entry *e;

	slash1 = strchr(p, '/');
	if (slash1)
		n = slash1 - p;
	else
		n = strlen(p);

	for (i = 0; i < t->entry_count; i++) {
		e = t->entries[i];
		if (e->name->str_len == n && !strncmp(p, e->name->str_dat, n)) {
			if (!slash1) {
1027 1028
				if (e->versions[1].mode == mode
						&& !hashcmp(e->versions[1].sha1, sha1))
1029
					return 0;
1030 1031
				e->versions[1].mode = mode;
				hashcpy(e->versions[1].sha1, sha1);
1032
				if (e->tree) {
1033
					release_tree_content_recursive(e->tree);
1034 1035
					e->tree = NULL;
				}
1036
				hashclr(root->versions[1].sha1);
1037 1038
				return 1;
			}
1039
			if (!S_ISDIR(e->versions[1].mode)) {
1040
				e->tree = new_tree_content(8);
1041
				e->versions[1].mode = S_IFDIR;
1042 1043 1044 1045
			}
			if (!e->tree)
				load_tree(e);
			if (tree_content_set(e, slash1 + 1, sha1, mode)) {
1046
				hashclr(root->versions[1].sha1);
1047 1048 1049 1050 1051 1052 1053 1054 1055 1056
				return 1;
			}
			return 0;
		}
	}

	if (t->entry_count == t->entry_capacity)
		root->tree = t = grow_tree_content(t, 8);
	e = new_tree_entry();
	e->name = to_atom(p, n);
1057 1058
	e->versions[0].mode = 0;
	hashclr(e->versions[0].sha1);
1059 1060 1061
	t->entries[t->entry_count++] = e;
	if (slash1) {
		e->tree = new_tree_content(8);
1062
		e->versions[1].mode = S_IFDIR;
1063 1064 1065
		tree_content_set(e, slash1 + 1, sha1, mode);
	} else {
		e->tree = NULL;
1066 1067
		e->versions[1].mode = mode;
		hashcpy(e->versions[1].sha1, sha1);
1068
	}
1069
	hashclr(root->versions[1].sha1);
1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088
	return 1;
}

static int tree_content_remove(struct tree_entry *root, const char *p)
{
	struct tree_content *t = root->tree;
	const char *slash1;
	unsigned int i, n;
	struct tree_entry *e;

	slash1 = strchr(p, '/');
	if (slash1)
		n = slash1 - p;
	else
		n = strlen(p);

	for (i = 0; i < t->entry_count; i++) {
		e = t->entries[i];
		if (e->name->str_len == n && !strncmp(p, e->name->str_dat, n)) {
1089
			if (!slash1 || !S_ISDIR(e->versions[1].mode))
1090 1091 1092 1093
				goto del_entry;
			if (!e->tree)
				load_tree(e);
			if (tree_content_remove(e, slash1 + 1)) {
1094 1095 1096 1097 1098 1099 1100
				for (n = 0; n < e->tree->entry_count; n++) {
					if (e->tree->entries[n]->versions[1].mode) {
						hashclr(root->versions[1].sha1);
						return 1;
					}
				}
				goto del_entry;
1101 1102 1103 1104 1105 1106 1107
			}
			return 0;
		}
	}
	return 0;

del_entry:
1108 1109 1110 1111 1112 1113 1114
	if (e->tree) {
		release_tree_content_recursive(e->tree);
		e->tree = NULL;
	}
	e->versions[1].mode = 0;
	hashclr(e->versions[1].sha1);
	hashclr(root->versions[1].sha1);
1115
	return 1;
1116 1117
}

1118 1119 1120 1121 1122 1123 1124 1125 1126
static void dump_branches()
{
	static const char *msg = "fast-import";
	unsigned int i;
	struct branch *b;
	struct ref_lock *lock;

	for (i = 0; i < branch_table_sz; i++) {
		for (b = branch_table[i]; b; b = b->table_next_branch) {
1127
			lock = lock_any_ref_for_update(b->name, NULL);
1128 1129 1130 1131 1132 1133
			if (!lock || write_ref_sha1(lock, b->sha1, msg) < 0)
				die("Can't write %s", b->name);
		}
	}
}

1134 1135 1136 1137 1138 1139 1140 1141 1142
static void dump_tags()
{
	static const char *msg = "fast-import";
	struct tag *t;
	struct ref_lock *lock;
	char path[PATH_MAX];

	for (t = first_tag; t; t = t->next_tag) {
		sprintf(path, "refs/tags/%s", t->name);
1143
		lock = lock_any_ref_for_update(path, NULL);
1144 1145 1146 1147 1148
		if (!lock || write_ref_sha1(lock, t->sha1, msg) < 0)
			die("Can't write %s", path);
	}
}

1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162
static void dump_marks_helper(FILE *f,
	unsigned long base,
	struct mark_set *m)
{
	int k;
	if (m->shift) {
		for (k = 0; k < 1024; k++) {
			if (m->data.sets[k])
				dump_marks_helper(f, (base + k) << m->shift,
					m->data.sets[k]);
		}
	} else {
		for (k = 0; k < 1024; k++) {
			if (m->data.marked[k])
1163
				fprintf(f, ":%lu %s\n", base + k,
1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178
					sha1_to_hex(m->data.marked[k]->sha1));
		}
	}
}

static void dump_marks()
{
	if (mark_file)
	{
		FILE *f = fopen(mark_file, "w");
		dump_marks_helper(f, 0, marks);
		fclose(f);
	}
}

1179 1180 1181 1182 1183 1184 1185 1186
static void read_next_command()
{
	read_line(&command_buf, stdin, '\n');
}

static void cmd_mark()
{
	if (!strncmp("mark :", command_buf.buf, 6)) {
1187
		next_mark = strtoul(command_buf.buf + 6, NULL, 10);
1188 1189 1190
		read_next_command();
	}
	else
1191
		next_mark = 0;
1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219
}

static void* cmd_data (size_t *size)
{
	size_t n = 0;
	void *buffer;
	size_t length;

	if (strncmp("data ", command_buf.buf, 5))
		die("Expected 'data n' command, found: %s", command_buf.buf);

	length = strtoul(command_buf.buf + 5, NULL, 10);
	buffer = xmalloc(length);

	while (n < length) {
		size_t s = fread((char*)buffer + n, 1, length - n, stdin);
		if (!s && feof(stdin))
			die("EOF in data (%lu bytes remaining)", length - n);
		n += s;
	}

	if (fgetc(stdin) != '\n')
		die("An lf did not trail the binary data as expected.");

	*size = length;
	return buffer;
}

1220
static void cmd_new_blob()
1221
{
1222 1223
	size_t l;
	void *d;
1224 1225 1226

	read_next_command();
	cmd_mark();
1227
	d = cmd_data(&l);
1228

1229 1230
	if (store_object(OBJ_BLOB, d, l, &last_blob, NULL, next_mark))
		free(d);
1231 1232
}

1233
static void unload_one_branch()
1234
{
1235 1236
	while (cur_active_branches
		&& cur_active_branches >= max_active_branches) {
1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256
		unsigned long min_commit = ULONG_MAX;
		struct branch *e, *l = NULL, *p = NULL;

		for (e = active_branches; e; e = e->active_next_branch) {
			if (e->last_commit < min_commit) {
				p = l;
				min_commit = e->last_commit;
			}
			l = e;
		}

		if (p) {
			e = p->active_next_branch;
			p->active_next_branch = e->active_next_branch;
		} else {
			e = active_branches;
			active_branches = e->active_next_branch;
		}
		e->active_next_branch = NULL;
		if (e->branch_tree.tree) {
1257
			release_tree_content_recursive(e->branch_tree.tree);
1258 1259 1260
			e->branch_tree.tree = NULL;
		}
		cur_active_branches--;
1261 1262 1263
	}
}

1264
static void load_branch(struct branch *b)
1265
{
1266 1267 1268 1269
	load_tree(&b->branch_tree);
	b->active_next_branch = active_branches;
	active_branches = b;
	cur_active_branches++;
1270
	branch_load_count++;
1271 1272
}

1273
static void file_change_m(struct branch *b)
1274
{
1275 1276 1277
	const char *p = command_buf.buf + 2;
	char *p_uq;
	const char *endp;
1278
	struct object_entry *oe;
1279
	unsigned char sha1[20];
1280
	unsigned int mode;
1281
	char type[20];
1282

1283 1284 1285 1286 1287 1288
	p = get_mode(p, &mode);
	if (!p)
		die("Corrupt mode: %s", command_buf.buf);
	switch (mode) {
	case S_IFREG | 0644:
	case S_IFREG | 0755:
1289
	case S_IFLNK:
1290 1291 1292 1293 1294 1295 1296 1297
	case 0644:
	case 0755:
		/* ok */
		break;
	default:
		die("Corrupt mode: %s", command_buf.buf);
	}

1298 1299 1300
	if (*p == ':') {
		char *x;
		oe = find_mark(strtoul(p + 1, &x, 10));
1301
		hashcpy(sha1, oe->sha1);
1302 1303 1304 1305 1306 1307 1308
		p = x;
	} else {
		if (get_sha1_hex(p, sha1))
			die("Invalid SHA1: %s", command_buf.buf);
		oe = find_object(sha1);
		p += 40;
	}
1309 1310 1311 1312 1313 1314 1315 1316 1317
	if (*p++ != ' ')
		die("Missing space after SHA1: %s", command_buf.buf);

	p_uq = unquote_c_style(p, &endp);
	if (p_uq) {
		if (*endp)
			die("Garbage after path in: %s", command_buf.buf);
		p = p_uq;
	}
1318

1319 1320
	if (oe) {
		if (oe->type != OBJ_BLOB)
1321 1322
			die("Not a blob (actually a %s): %s",
				command_buf.buf, type_names[oe->type]);
1323 1324
	} else {
		if (sha1_object_info(sha1, type, NULL))
1325
			die("Blob not found: %s", command_buf.buf);
1326
		if (strcmp(blob_type, type))
1327 1328
			die("Not a blob (actually a %s): %s",
				command_buf.buf, type);
1329
	}
1330

1331 1332 1333 1334
	tree_content_set(&b->branch_tree, p, sha1, S_IFREG | mode);

	if (p_uq)
		free(p_uq);
1335
}
1336

1337 1338
static void file_change_d(struct branch *b)
{
1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351
	const char *p = command_buf.buf + 2;
	char *p_uq;
	const char *endp;

	p_uq = unquote_c_style(p, &endp);
	if (p_uq) {
		if (*endp)
			die("Garbage after path in: %s", command_buf.buf);
		p = p_uq;
	}
	tree_content_remove(&b->branch_tree, p);
	if (p_uq)
		free(p_uq);
1352 1353
}

1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377
static void cmd_from(struct branch *b)
{
	const char *from, *endp;
	char *str_uq;
	struct branch *s;

	if (strncmp("from ", command_buf.buf, 5))
		return;

	if (b->last_commit)
		die("Can't reinitailize branch %s", b->name);

	from = strchr(command_buf.buf, ' ') + 1;
	str_uq = unquote_c_style(from, &endp);
	if (str_uq) {
		if (*endp)
			die("Garbage after string in: %s", command_buf.buf);
		from = str_uq;
	}

	s = lookup_branch(from);
	if (b == s)
		die("Can't create a branch from itself: %s", b->name);
	else if (s) {
1378
		unsigned char *t = s->branch_tree.versions[1].sha1;
1379
		hashcpy(b->sha1, s->sha1);
1380 1381
		hashcpy(b->branch_tree.versions[0].sha1, t);
		hashcpy(b->branch_tree.versions[1].sha1, t);
1382 1383 1384 1385 1386 1387 1388
	} else if (*from == ':') {
		unsigned long idnum = strtoul(from + 1, NULL, 10);
		struct object_entry *oe = find_mark(idnum);
		unsigned long size;
		char *buf;
		if (oe->type != OBJ_COMMIT)
			die("Mark :%lu not a commit", idnum);
1389
		hashcpy(b->sha1, oe->sha1);
1390
		buf = gfi_unpack_entry(oe->offset, &size);
1391 1392 1393
		if (!buf || size < 46)
			die("Not a valid commit: %s", from);
		if (memcmp("tree ", buf, 5)
1394
			|| get_sha1_hex(buf + 5, b->branch_tree.versions[1].sha1))
1395 1396
			die("The commit %s is corrupt", sha1_to_hex(b->sha1));
		free(buf);
1397 1398
		hashcpy(b->branch_tree.versions[0].sha1,
			b->branch_tree.versions[1].sha1);
1399
	} else if (!get_sha1(from, b->sha1)) {
1400 1401 1402 1403
		if (is_null_sha1(b->sha1)) {
			hashclr(b->branch_tree.versions[0].sha1);
			hashclr(b->branch_tree.versions[1].sha1);
		} else {
1404 1405 1406 1407 1408 1409 1410 1411
			unsigned long size;
			char *buf;

			buf = read_object_with_reference(b->sha1,
				type_names[OBJ_COMMIT], &size, b->sha1);
			if (!buf || size < 46)
				die("Not a valid commit: %s", from);
			if (memcmp("tree ", buf, 5)
1412
				|| get_sha1_hex(buf + 5, b->branch_tree.versions[1].sha1))
1413 1414
				die("The commit %s is corrupt", sha1_to_hex(b->sha1));
			free(buf);
1415 1416
			hashcpy(b->branch_tree.versions[0].sha1,
				b->branch_tree.versions[1].sha1);
1417 1418 1419 1420 1421 1422 1423
		}
	} else
		die("Invalid ref name or SHA1 expression: %s", from);

	read_next_command();
}

1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465
static struct hash_list* cmd_merge(unsigned int *count)
{
	struct hash_list *list = NULL, *n, *e;
	const char *from, *endp;
	char *str_uq;
	struct branch *s;

	*count = 0;
	while (!strncmp("merge ", command_buf.buf, 6)) {
		from = strchr(command_buf.buf, ' ') + 1;
		str_uq = unquote_c_style(from, &endp);
		if (str_uq) {
			if (*endp)
				die("Garbage after string in: %s", command_buf.buf);
			from = str_uq;
		}

		n = xmalloc(sizeof(*n));
		s = lookup_branch(from);
		if (s)
			hashcpy(n->sha1, s->sha1);
		else if (*from == ':') {
			unsigned long idnum = strtoul(from + 1, NULL, 10);
			struct object_entry *oe = find_mark(idnum);
			if (oe->type != OBJ_COMMIT)
				die("Mark :%lu not a commit", idnum);
			hashcpy(n->sha1, oe->sha1);
		} else if (get_sha1(from, n->sha1))
			die("Invalid ref name or SHA1 expression: %s", from);

		n->next = NULL;
		if (list)
			e->next = n;
		else
			list = n;
		e = n;
		*count++;
		read_next_command();
	}
	return list;
}

1466
static void cmd_new_commit()
1467
{
1468 1469 1470 1471 1472 1473 1474 1475
	struct branch *b;
	void *msg;
	size_t msglen;
	char *str_uq;
	const char *endp;
	char *sp;
	char *author = NULL;
	char *committer = NULL;
1476 1477
	struct hash_list *merge_list = NULL;
	unsigned int merge_count;
1478 1479 1480 1481 1482 1483 1484 1485 1486 1487

	/* Obtain the branch name from the rest of our command */
	sp = strchr(command_buf.buf, ' ') + 1;
	str_uq = unquote_c_style(sp, &endp);
	if (str_uq) {
		if (*endp)
			die("Garbage after ref in: %s", command_buf.buf);
		sp = str_uq;
	}
	b = lookup_branch(sp);
1488
	if (!b)
1489
		b = new_branch(sp);
1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505
	if (str_uq)
		free(str_uq);

	read_next_command();
	cmd_mark();
	if (!strncmp("author ", command_buf.buf, 7)) {
		author = strdup(command_buf.buf);
		read_next_command();
	}
	if (!strncmp("committer ", command_buf.buf, 10)) {
		committer = strdup(command_buf.buf);
		read_next_command();
	}
	if (!committer)
		die("Expected committer but didn't get one");
	msg = cmd_data(&msglen);
1506 1507
	read_next_command();
	cmd_from(b);
1508
	merge_list = cmd_merge(&merge_count);
1509 1510

	/* ensure the branch is active/loaded */
1511
	if (!b->branch_tree.tree || !max_active_branches) {
1512 1513 1514
		unload_one_branch();
		load_branch(b);
	}
1515

1516 1517
	/* file_change* */
	for (;;) {
1518
		if (1 == command_buf.len)
1519
			break;
1520
		else if (!strncmp("M ", command_buf.buf, 2))
1521
			file_change_m(b);
1522
		else if (!strncmp("D ", command_buf.buf, 2))
1523 1524
			file_change_d(b);
		else
1525
			die("Unsupported file_change: %s", command_buf.buf);
1526
		read_next_command();
1527 1528
	}

1529
	/* build the tree and the commit */
1530
	store_tree(&b->branch_tree);
1531 1532
	hashcpy(b->branch_tree.versions[0].sha1,
		b->branch_tree.versions[1].sha1);
1533
	size_dbuf(&new_data, 97 + msglen
1534
		+ merge_count * 49
1535 1536 1537
		+ (author
			? strlen(author) + strlen(committer)
			: 2 * strlen(committer)));
1538
	sp = new_data.buffer;
1539 1540
	sp += sprintf(sp, "tree %s\n",
		sha1_to_hex(b->branch_tree.versions[1].sha1));
1541
	if (!is_null_sha1(b->sha1))
1542
		sp += sprintf(sp, "parent %s\n", sha1_to_hex(b->sha1));
1543 1544 1545 1546 1547 1548
	while (merge_list) {
		struct hash_list *next = merge_list->next;
		sp += sprintf(sp, "parent %s\n", sha1_to_hex(merge_list->sha1));
		free(merge_list);
		merge_list = next;
	}
1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560
	if (author)
		sp += sprintf(sp, "%s\n", author);
	else
		sp += sprintf(sp, "author %s\n", committer + 10);
	sp += sprintf(sp, "%s\n\n", committer);
	memcpy(sp, msg, msglen);
	sp += msglen;
	if (author)
		free(author);
	free(committer);
	free(msg);

1561 1562 1563
	store_object(OBJ_COMMIT,
		new_data.buffer, sp - (char*)new_data.buffer,
		NULL, b->sha1, next_mark);
1564
	b->last_commit = object_count_by_type[OBJ_COMMIT];
1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576

	if (branch_log) {
		int need_dq = quote_c_style(b->name, NULL, NULL, 0);
		fprintf(branch_log, "commit ");
		if (need_dq) {
			fputc('"', branch_log);
			quote_c_style(b->name, NULL, branch_log, 0);
			fputc('"', branch_log);
		} else
			fprintf(branch_log, "%s", b->name);
		fprintf(branch_log," :%lu %s\n",next_mark,sha1_to_hex(b->sha1));
	}
1577 1578
}

1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589
static void cmd_new_tag()
{
	char *str_uq;
	const char *endp;
	char *sp;
	const char *from;
	char *tagger;
	struct branch *s;
	void *msg;
	size_t msglen;
	struct tag *t;
1590
	unsigned long from_mark = 0;
1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626
	unsigned char sha1[20];

	/* Obtain the new tag name from the rest of our command */
	sp = strchr(command_buf.buf, ' ') + 1;
	str_uq = unquote_c_style(sp, &endp);
	if (str_uq) {
		if (*endp)
			die("Garbage after tag name in: %s", command_buf.buf);
		sp = str_uq;
	}
	t = pool_alloc(sizeof(struct tag));
	t->next_tag = NULL;
	t->name = pool_strdup(sp);
	if (last_tag)
		last_tag->next_tag = t;
	else
		first_tag = t;
	last_tag = t;
	if (str_uq)
		free(str_uq);
	read_next_command();

	/* from ... */
	if (strncmp("from ", command_buf.buf, 5))
		die("Expected from command, got %s", command_buf.buf);

	from = strchr(command_buf.buf, ' ') + 1;
	str_uq = unquote_c_style(from, &endp);
	if (str_uq) {
		if (*endp)
			die("Garbage after string in: %s", command_buf.buf);
		from = str_uq;
	}

	s = lookup_branch(from);
	if (s) {
1627
		hashcpy(sha1, s->sha1);
1628
	} else if (*from == ':') {
1629 1630
		from_mark = strtoul(from + 1, NULL, 10);
		struct object_entry *oe = find_mark(from_mark);
1631
		if (oe->type != OBJ_COMMIT)
1632
			die("Mark :%lu not a commit", from_mark);
1633
		hashcpy(sha1, oe->sha1);
1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659
	} else if (!get_sha1(from, sha1)) {
		unsigned long size;
		char *buf;

		buf = read_object_with_reference(sha1,
			type_names[OBJ_COMMIT], &size, sha1);
		if (!buf || size < 46)
			die("Not a valid commit: %s", from);
		free(buf);
	} else
		die("Invalid ref name or SHA1 expression: %s", from);

	if (str_uq)
		free(str_uq);
	read_next_command();

	/* tagger ... */
	if (strncmp("tagger ", command_buf.buf, 7))
		die("Expected tagger command, got %s", command_buf.buf);
	tagger = strdup(command_buf.buf);

	/* tag payload/message */
	read_next_command();
	msg = cmd_data(&msglen);

	/* build the tag object */
1660 1661
	size_dbuf(&new_data, 67+strlen(t->name)+strlen(tagger)+msglen);
	sp = new_data.buffer;
1662 1663 1664 1665 1666 1667 1668 1669 1670
	sp += sprintf(sp, "object %s\n", sha1_to_hex(sha1));
	sp += sprintf(sp, "type %s\n", type_names[OBJ_COMMIT]);
	sp += sprintf(sp, "tag %s\n", t->name);
	sp += sprintf(sp, "%s\n\n", tagger);
	memcpy(sp, msg, msglen);
	sp += msglen;
	free(tagger);
	free(msg);

1671 1672
	store_object(OBJ_TAG, new_data.buffer, sp - (char*)new_data.buffer,
		NULL, t->sha1, 0);
1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684

	if (branch_log) {
		int need_dq = quote_c_style(t->name, NULL, NULL, 0);
		fprintf(branch_log, "tag ");
		if (need_dq) {
			fputc('"', branch_log);
			quote_c_style(t->name, NULL, branch_log, 0);
			fputc('"', branch_log);
		} else
			fprintf(branch_log, "%s", t->name);
		fprintf(branch_log," :%lu %s\n",from_mark,sha1_to_hex(t->sha1));
	}
1685 1686
}

1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709
static void cmd_reset_branch()
{
	struct branch *b;
	char *str_uq;
	const char *endp;
	char *sp;

	/* Obtain the branch name from the rest of our command */
	sp = strchr(command_buf.buf, ' ') + 1;
	str_uq = unquote_c_style(sp, &endp);
	if (str_uq) {
		if (*endp)
			die("Garbage after ref in: %s", command_buf.buf);
		sp = str_uq;
	}
	b = lookup_branch(sp);
	if (b) {
		b->last_commit = 0;
		if (b->branch_tree.tree) {
			release_tree_content_recursive(b->branch_tree.tree);
			b->branch_tree.tree = NULL;
		}
	}
1710 1711
	else
		b = new_branch(sp);
1712 1713
	if (str_uq)
		free(str_uq);
1714 1715
	read_next_command();
	cmd_from(b);
1716 1717
}

1718
static const char fast_import_usage[] =
1719
"git-fast-import [--objects=n] [--depth=n] [--active-branches=n] [--export-marks=marks.file] [--branch-log=log] temp.pack";
1720

1721 1722
int main(int argc, const char **argv)
{
1723
	int i;
1724
	unsigned long est_obj_cnt = object_entry_alloc;
1725
	struct stat sb;
1726

1727 1728 1729
	setup_ident();
	git_config(git_default_config);

1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740
	for (i = 1; i < argc; i++) {
		const char *a = argv[i];

		if (*a != '-' || !strcmp(a, "--"))
			break;
		else if (!strncmp(a, "--objects=", 10))
			est_obj_cnt = strtoul(a + 10, NULL, 0);
		else if (!strncmp(a, "--depth=", 8))
			max_depth = strtoul(a + 8, NULL, 0);
		else if (!strncmp(a, "--active-branches=", 18))
			max_active_branches = strtoul(a + 18, NULL, 0);
1741 1742
		else if (!strncmp(a, "--export-marks=", 15))
			mark_file = a + 15;
1743 1744 1745 1746 1747
		else if (!strncmp(a, "--branch-log=", 13)) {
			branch_log = fopen(a + 13, "w");
			if (!branch_log)
				die("Can't create %s: %s", a + 13, strerror(errno));
		}
1748 1749 1750 1751 1752 1753 1754
		else
			die("unknown option %s", a);
	}
	if ((i+1) != argc)
		usage(fast_import_usage);
	base_name = argv[i];

1755
	alloc_objects(est_obj_cnt);
1756
	strbuf_init(&command_buf);
1757 1758 1759 1760

	atom_table = xcalloc(atom_table_sz, sizeof(struct atom_str*));
	branch_table = xcalloc(branch_table_sz, sizeof(struct branch*));
	avail_tree_table = xcalloc(avail_tree_table_sz, sizeof(struct avail_tree_content*));
1761
	marks = pool_calloc(1, sizeof(struct mark_set));
1762

1763
	start_packfile();
1764
	for (;;) {
1765 1766
		read_next_command();
		if (command_buf.eof)
1767
			break;
1768 1769 1770 1771
		else if (!strcmp("blob", command_buf.buf))
			cmd_new_blob();
		else if (!strncmp("commit ", command_buf.buf, 7))
			cmd_new_commit();
1772 1773
		else if (!strncmp("tag ", command_buf.buf, 4))
			cmd_new_tag();
1774 1775
		else if (!strncmp("reset ", command_buf.buf, 6))
			cmd_reset_branch();
1776 1777
		else
			die("Unsupported command: %s", command_buf.buf);
1778
	}
1779
	end_packfile();
1780

1781
	dump_branches();
1782
	dump_tags();
1783
	dump_marks();
1784 1785
	if (branch_log)
		fclose(branch_log);
1786

1787
	fprintf(stderr, "%s statistics:\n", argv[0]);
1788
	fprintf(stderr, "---------------------------------------------------------------------\n");
1789
	fprintf(stderr, "Alloc'd objects: %10lu (%10lu overflow  )\n", alloc_count, alloc_count - est_obj_cnt);
1790
	fprintf(stderr, "Total objects:   %10lu (%10lu duplicates                  )\n", object_count, duplicate_count);
1791 1792 1793 1794
	fprintf(stderr, "      blobs  :   %10lu (%10lu duplicates %10lu deltas)\n", object_count_by_type[OBJ_BLOB], duplicate_count_by_type[OBJ_BLOB], delta_count_by_type[OBJ_BLOB]);
	fprintf(stderr, "      trees  :   %10lu (%10lu duplicates %10lu deltas)\n", object_count_by_type[OBJ_TREE], duplicate_count_by_type[OBJ_TREE], delta_count_by_type[OBJ_TREE]);
	fprintf(stderr, "      commits:   %10lu (%10lu duplicates %10lu deltas)\n", object_count_by_type[OBJ_COMMIT], duplicate_count_by_type[OBJ_COMMIT], delta_count_by_type[OBJ_COMMIT]);
	fprintf(stderr, "      tags   :   %10lu (%10lu duplicates %10lu deltas)\n", object_count_by_type[OBJ_TAG], duplicate_count_by_type[OBJ_TAG], delta_count_by_type[OBJ_TAG]);
1795
	fprintf(stderr, "Total branches:  %10lu (%10lu loads     )\n", branch_count, branch_load_count);
1796
	fprintf(stderr, "      marks:     %10u (%10lu unique    )\n", (1 << marks->shift) * 1024, marks_set_count);
1797
	fprintf(stderr, "      atoms:     %10u\n", atom_cnt);
1798 1799 1800
	fprintf(stderr, "Memory total:    %10lu KiB\n", (total_allocd + alloc_count*sizeof(struct object_entry))/1024);
	fprintf(stderr, "       pools:    %10lu KiB\n", total_allocd/1024);
	fprintf(stderr, "     objects:    %10lu KiB\n", (alloc_count*sizeof(struct object_entry))/1024);
1801
	fprintf(stderr, "---------------------------------------------------------------------\n");
1802
	fprintf(stderr, "\n");
1803 1804 1805

	return 0;
}