summaryrefslogtreecommitdiff
path: root/pack-objects.c
blob: af3bdf5d358b8a47ed23bcb7e9721e956eb59d60 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
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
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
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
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
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
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
483
484
485
486
487
488
489
490
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
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
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
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
#include "cache.h"
#include "object.h"
#include "delta.h"
#include "pack.h"
#include "csum-file.h"
#include "diff.h"
#include <sys/time.h>

static const char pack_usage[] = "git-pack-objects [-q] [--no-reuse-delta] [--non-empty] [--local] [--incremental] [--window=N] [--depth=N] {--stdout | base-name} < object-list";

struct object_entry {
	unsigned char sha1[20];
	unsigned long size;	/* uncompressed size */
	unsigned long offset;	/* offset into the final pack file;
				 * nonzero if already written.
				 */
	unsigned int depth;	/* delta depth */
	unsigned int delta_limit;	/* base adjustment for in-pack delta */
	unsigned int hash;	/* name hint hash */
	enum object_type type;
	enum object_type in_pack_type;	/* could be delta */
	unsigned long delta_size;	/* delta data size (uncompressed) */
	struct object_entry *delta;	/* delta base object */
	struct packed_git *in_pack; 	/* already in pack */
	unsigned int in_pack_offset;
	struct object_entry *delta_child; /* delitified objects who bases me */
	struct object_entry *delta_sibling; /* other deltified objects who
					     * uses the same base as me
					     */
	int preferred_base;	/* we do not pack this, but is encouraged to
				 * be used as the base objectto delta huge
				 * objects against.
				 */
	int based_on_preferred;	/* current delta candidate is a preferred
				 * one, or delta against a preferred one.
				 */
};

/*
 * Objects we are going to pack are colected in objects array (dynamically
 * expanded).  nr_objects & nr_alloc controls this array.  They are stored
 * in the order we see -- typically rev-list --objects order that gives us
 * nice "minimum seek" order.
 *
 * sorted-by-sha ans sorted-by-type are arrays of pointers that point at
 * elements in the objects array.  The former is used to build the pack
 * index (lists object names in the ascending order to help offset lookup),
 * and the latter is used to group similar things together by try_delta()
 * heuristics.
 */

static unsigned char object_list_sha1[20];
static int non_empty = 0;
static int no_reuse_delta = 0;
static int local = 0;
static int incremental = 0;
static struct object_entry **sorted_by_sha, **sorted_by_type;
static struct object_entry *objects = NULL;
static int nr_objects = 0, nr_alloc = 0, nr_result = 0;
static const char *base_name;
static unsigned char pack_file_sha1[20];
static int progress = 1;

/*
 * The object names in objects array are hashed with this hashtable,
 * to help looking up the entry by object name.  Binary search from
 * sorted_by_sha is also possible but this was easier to code and faster.
 * This hashtable is built after all the objects are seen.
 */
static int *object_ix = NULL;
static int object_ix_hashsz = 0;

/*
 * Pack index for existing packs give us easy access to the offsets into
 * corresponding pack file where each object's data starts, but the entries
 * do not store the size of the compressed representation (uncompressed
 * size is easily available by examining the pack entry header).  We build
 * a hashtable of existing packs (pack_revindex), and keep reverse index
 * here -- pack index file is sorted by object name mapping to offset; this
 * pack_revindex[].revindex array is an ordered list of offsets, so if you
 * know the offset of an object, next offset is where its packed
 * representation ends.
 */
struct pack_revindex {
	struct packed_git *p;
	unsigned long *revindex;
} *pack_revindex = NULL;
static int pack_revindex_hashsz = 0;

/*
 * stats
 */
static int written = 0;
static int written_delta = 0;
static int reused = 0;
static int reused_delta = 0;

static int pack_revindex_ix(struct packed_git *p)
{
	unsigned int ui = (unsigned int) p;
	int i;

	ui = ui ^ (ui >> 16); /* defeat structure alignment */
	i = (int)(ui % pack_revindex_hashsz);
	while (pack_revindex[i].p) {
		if (pack_revindex[i].p == p)
			return i;
		if (++i == pack_revindex_hashsz)
			i = 0;
	}
	return -1 - i;
}

static void prepare_pack_ix(void)
{
	int num;
	struct packed_git *p;
	for (num = 0, p = packed_git; p; p = p->next)
		num++;
	if (!num)
		return;
	pack_revindex_hashsz = num * 11;
	pack_revindex = xcalloc(sizeof(*pack_revindex), pack_revindex_hashsz);
	for (p = packed_git; p; p = p->next) {
		num = pack_revindex_ix(p);
		num = - 1 - num;
		pack_revindex[num].p = p;
	}
	/* revindex elements are lazily initialized */
}

static int cmp_offset(const void *a_, const void *b_)
{
	unsigned long a = *(unsigned long *) a_;
	unsigned long b = *(unsigned long *) b_;
	if (a < b)
		return -1;
	else if (a == b)
		return 0;
	else
		return 1;
}

/*
 * Ordered list of offsets of objects in the pack.
 */
static void prepare_pack_revindex(struct pack_revindex *rix)
{
	struct packed_git *p = rix->p;
	int num_ent = num_packed_objects(p);
	int i;
	void *index = p->index_base + 256;

	rix->revindex = xmalloc(sizeof(unsigned long) * (num_ent + 1));
	for (i = 0; i < num_ent; i++) {
		long hl = *((long *)(index + 24 * i));
		rix->revindex[i] = ntohl(hl);
	}
	/* This knows the pack format -- the 20-byte trailer
	 * follows immediately after the last object data.
	 */
	rix->revindex[num_ent] = p->pack_size - 20;
	qsort(rix->revindex, num_ent, sizeof(unsigned long), cmp_offset);
}

static unsigned long find_packed_object_size(struct packed_git *p,
					     unsigned long ofs)
{
	int num;
	int lo, hi;
	struct pack_revindex *rix;
	unsigned long *revindex;
	num = pack_revindex_ix(p);
	if (num < 0)
		die("internal error: pack revindex uninitialized");
	rix = &pack_revindex[num];
	if (!rix->revindex)
		prepare_pack_revindex(rix);
	revindex = rix->revindex;
	lo = 0;
	hi = num_packed_objects(p) + 1;
	do {
		int mi = (lo + hi) / 2;
		if (revindex[mi] == ofs) {
			return revindex[mi+1] - ofs;
		}
		else if (ofs < revindex[mi])
			hi = mi;
		else
			lo = mi + 1;
	} while (lo < hi);
	die("internal error: pack revindex corrupt");
}

static void *delta_against(void *buf, unsigned long size, struct object_entry *entry)
{
	unsigned long othersize, delta_size;
	char type[10];
	void *otherbuf = read_sha1_file(entry->delta->sha1, type, &othersize);
	void *delta_buf;

	if (!otherbuf)
		die("unable to read %s", sha1_to_hex(entry->delta->sha1));
        delta_buf = diff_delta(otherbuf, othersize,
			       buf, size, &delta_size, 0);
        if (!delta_buf || delta_size != entry->delta_size)
        	die("delta size changed");
        free(buf);
        free(otherbuf);
	return delta_buf;
}

/*
 * The per-object header is a pretty dense thing, which is
 *  - first byte: low four bits are "size", then three bits of "type",
 *    and the high bit is "size continues".
 *  - each byte afterwards: low seven bits are size continuation,
 *    with the high bit being "size continues"
 */
static int encode_header(enum object_type type, unsigned long size, unsigned char *hdr)
{
	int n = 1;
	unsigned char c;

	if (type < OBJ_COMMIT || type > OBJ_DELTA)
		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;
}

static unsigned long write_object(struct sha1file *f,
				  struct object_entry *entry)
{
	unsigned long size;
	char type[10];
	void *buf;
	unsigned char header[10];
	unsigned hdrlen, datalen;
	enum object_type obj_type;
	int to_reuse = 0;

	if (entry->preferred_base)
		return 0;

	obj_type = entry->type;
	if (! entry->in_pack)
		to_reuse = 0;	/* can't reuse what we don't have */
	else if (obj_type == OBJ_DELTA)
		to_reuse = 1;	/* check_object() decided it for us */
	else if (obj_type != entry->in_pack_type)
		to_reuse = 0;	/* pack has delta which is unusable */
	else if (entry->delta)
		to_reuse = 0;	/* we want to pack afresh */
	else
		to_reuse = 1;	/* we have it in-pack undeltified,
				 * and we do not need to deltify it.
				 */

	if (! to_reuse) {
		buf = read_sha1_file(entry->sha1, type, &size);
		if (!buf)
			die("unable to read %s", sha1_to_hex(entry->sha1));
		if (size != entry->size)
			die("object %s size inconsistency (%lu vs %lu)",
			    sha1_to_hex(entry->sha1), size, entry->size);
		if (entry->delta) {
			buf = delta_against(buf, size, entry);
			size = entry->delta_size;
			obj_type = OBJ_DELTA;
		}
		/*
		 * The object header is a byte of 'type' followed by zero or
		 * more bytes of length.  For deltas, the 20 bytes of delta
		 * sha1 follows that.
		 */
		hdrlen = encode_header(obj_type, size, header);
		sha1write(f, header, hdrlen);

		if (entry->delta) {
			sha1write(f, entry->delta, 20);
			hdrlen += 20;
		}
		datalen = sha1write_compressed(f, buf, size);
		free(buf);
	}
	else {
		struct packed_git *p = entry->in_pack;
		use_packed_git(p);

		datalen = find_packed_object_size(p, entry->in_pack_offset);
		buf = p->pack_base + entry->in_pack_offset;
		sha1write(f, buf, datalen);
		unuse_packed_git(p);
		hdrlen = 0; /* not really */
		if (obj_type == OBJ_DELTA)
			reused_delta++;
		reused++;
	}
	if (obj_type == OBJ_DELTA)
		written_delta++;
	written++;
	return hdrlen + datalen;
}

static unsigned long write_one(struct sha1file *f,
			       struct object_entry *e,
			       unsigned long offset)
{
	if (e->offset)
		/* offset starts from header size and cannot be zero
		 * if it is written already.
		 */
		return offset;
	e->offset = offset;
	offset += write_object(f, e);
	/* if we are deltified, write out its base object. */
	if (e->delta)
		offset = write_one(f, e->delta, offset);
	return offset;
}

static void write_pack_file(void)
{
	int i;
	struct sha1file *f;
	unsigned long offset;
	struct pack_header hdr;

	if (!base_name)
		f = sha1fd(1, "<stdout>");
	else
		f = sha1create("%s-%s.%s", base_name,
			       sha1_to_hex(object_list_sha1), "pack");
	hdr.hdr_signature = htonl(PACK_SIGNATURE);
	hdr.hdr_version = htonl(PACK_VERSION);
	hdr.hdr_entries = htonl(nr_result);
	sha1write(f, &hdr, sizeof(hdr));
	offset = sizeof(hdr);
	for (i = 0; i < nr_objects; i++)
		offset = write_one(f, objects + i, offset);

	sha1close(f, pack_file_sha1, 1);
}

static void write_index_file(void)
{
	int i;
	struct sha1file *f = sha1create("%s-%s.%s", base_name,
					sha1_to_hex(object_list_sha1), "idx");
	struct object_entry **list = sorted_by_sha;
	struct object_entry **last = list + nr_result;
	unsigned int array[256];

	/*
	 * Write the first-level table (the list is sorted,
	 * but we use a 256-entry lookup to be able to avoid
	 * having to do eight extra binary search iterations).
	 */
	for (i = 0; i < 256; i++) {
		struct object_entry **next = list;
		while (next < last) {
			struct object_entry *entry = *next;
			if (entry->sha1[0] != i)
				break;
			next++;
		}
		array[i] = htonl(next - sorted_by_sha);
		list = next;
	}
	sha1write(f, array, 256 * sizeof(int));

	/*
	 * Write the actual SHA1 entries..
	 */
	list = sorted_by_sha;
	for (i = 0; i < nr_result; i++) {
		struct object_entry *entry = *list++;
		unsigned int offset = htonl(entry->offset);
		sha1write(f, &offset, 4);
		sha1write(f, entry->sha1, 20);
	}
	sha1write(f, pack_file_sha1, 20);
	sha1close(f, NULL, 1);
}

static int locate_object_entry_hash(const unsigned char *sha1)
{
	int i;
	unsigned int ui;
	memcpy(&ui, sha1, sizeof(unsigned int));
	i = ui % object_ix_hashsz;
	while (0 < object_ix[i]) {
		if (!memcmp(sha1, objects[object_ix[i]-1].sha1, 20))
			return i;
		if (++i == object_ix_hashsz)
			i = 0;
	}
	return -1 - i;
}

static struct object_entry *locate_object_entry(const unsigned char *sha1)
{
	int i;

	if (!object_ix_hashsz)
		return NULL;

	i = locate_object_entry_hash(sha1);
	if (0 <= i)
		return &objects[object_ix[i]-1];
	return NULL;
}

static void rehash_objects(void)
{
	int i;
	struct object_entry *oe;

	object_ix_hashsz = nr_objects * 3;
	if (object_ix_hashsz < 1024)
		object_ix_hashsz = 1024;
	object_ix = xrealloc(object_ix, sizeof(int) * object_ix_hashsz);
	object_ix = memset(object_ix, 0, sizeof(int) * object_ix_hashsz);
	for (i = 0, oe = objects; i < nr_objects; i++, oe++) {
		int ix = locate_object_entry_hash(oe->sha1);
		if (0 <= ix)
			continue;
		ix = -1 - ix;
		object_ix[ix] = i + 1;
	}
}

static int add_object_entry(const unsigned char *sha1, const char *name, int exclude)
{
	unsigned int hash = 0;
	unsigned int idx = nr_objects;
	struct object_entry *entry;
	struct packed_git *p;
	unsigned int found_offset = 0;
	struct packed_git *found_pack = NULL;
	int ix, status = 0;

	if (!exclude) {
		for (p = packed_git; p; p = p->next) {
			struct pack_entry e;
			if (find_pack_entry_one(sha1, &e, p)) {
				if (incremental)
					return 0;
				if (local && !p->pack_local)
					return 0;
				if (!found_pack) {
					found_offset = e.offset;
					found_pack = e.p;
				}
			}
		}
	}
	if ((entry = locate_object_entry(sha1)) != NULL)
		goto already_added;

	while (*name) {
		unsigned char c = *name++;
		if (isspace(c))
			continue;
		hash = hash * 11 + c;
	}

	if (idx >= nr_alloc) {
		unsigned int needed = (idx + 1024) * 3 / 2;
		objects = xrealloc(objects, needed * sizeof(*entry));
		nr_alloc = needed;
	}
	entry = objects + idx;
	nr_objects = idx + 1;
	memset(entry, 0, sizeof(*entry));
	memcpy(entry->sha1, sha1, 20);
	entry->hash = hash;

	if (object_ix_hashsz * 3 <= nr_objects * 4)
		rehash_objects();
	else {
		ix = locate_object_entry_hash(entry->sha1);
		if (0 <= ix)
			die("internal error in object hashing.");
		object_ix[-1 - ix] = idx + 1;
	}
	status = 1;

 already_added:
	if (exclude)
		entry->preferred_base = 1;
	else {
		if (found_pack) {
			entry->in_pack = found_pack;
			entry->in_pack_offset = found_offset;
		}
	}
	return status;
}

static void add_pbase_tree(struct tree_desc *tree)
{
	while (tree->size) {
		const unsigned char *sha1;
		const char *name;
		unsigned mode;
		unsigned long size;
		char type[20];

		sha1 = tree_entry_extract(tree, &name, &mode);
		update_tree_entry(tree);
		if (!has_sha1_file(sha1))
			continue;
		if (sha1_object_info(sha1, type, &size))
			continue;

		if (!add_object_entry(sha1, name, 1))
			continue;

		if (!strcmp(type, "tree")) {
			struct tree_desc sub;
			void *elem;
			elem = read_sha1_file(sha1, type, &sub.size);
			sub.buf = elem;
			if (sub.buf) {
				add_pbase_tree(&sub);
				free(elem);
			}
		}
	}
}

static void add_preferred_base(unsigned char *sha1)
{
	struct tree_desc tree;
	void *elem;
	elem = read_object_with_reference(sha1, "tree", &tree.size, NULL);
	tree.buf = elem;
	if (!tree.buf)
		return;
	if (add_object_entry(sha1, "", 1))
		add_pbase_tree(&tree);
	free(elem);
}

static void check_object(struct object_entry *entry)
{
	char type[20];

	if (entry->in_pack && !entry->preferred_base) {
		unsigned char base[20];
		unsigned long size;
		struct object_entry *base_entry;

		/* We want in_pack_type even if we do not reuse delta.
		 * There is no point not reusing non-delta representations.
		 */
		check_reuse_pack_delta(entry->in_pack,
				       entry->in_pack_offset,
				       base, &size,
				       &entry->in_pack_type);

		/* Check if it is delta, and the base is also an object
		 * we are going to pack.  If so we will reuse the existing
		 * delta.
		 */
		if (!no_reuse_delta &&
		    entry->in_pack_type == OBJ_DELTA &&
		    (base_entry = locate_object_entry(base)) &&
		    (!base_entry->preferred_base)) {

			/* Depth value does not matter - find_deltas()
			 * will never consider reused delta as the
			 * base object to deltify other objects
			 * against, in order to avoid circular deltas.
			 */

			/* uncompressed size of the delta data */
			entry->size = entry->delta_size = size;
			entry->delta = base_entry;
			entry->type = OBJ_DELTA;

			entry->delta_sibling = base_entry->delta_child;
			base_entry->delta_child = entry;

			return;
		}
		/* Otherwise we would do the usual */
	}

	if (sha1_object_info(entry->sha1, type, &entry->size))
		die("unable to get type of object %s",
		    sha1_to_hex(entry->sha1));

	if (!strcmp(type, "commit")) {
		entry->type = OBJ_COMMIT;
	} else if (!strcmp(type, "tree")) {
		entry->type = OBJ_TREE;
	} else if (!strcmp(type, "blob")) {
		entry->type = OBJ_BLOB;
	} else if (!strcmp(type, "tag")) {
		entry->type = OBJ_TAG;
	} else
		die("unable to pack object %s of type %s",
		    sha1_to_hex(entry->sha1), type);
}

static unsigned int check_delta_limit(struct object_entry *me, unsigned int n)
{
	struct object_entry *child = me->delta_child;
	unsigned int m = n;
	while (child) {
		unsigned int c = check_delta_limit(child, n + 1);
		if (m < c)
			m = c;
		child = child->delta_sibling;
	}
	return m;
}

static void get_object_details(void)
{
	int i;
	struct object_entry *entry;

	prepare_pack_ix();
	for (i = 0, entry = objects; i < nr_objects; i++, entry++)
		check_object(entry);
	for (i = 0, entry = objects; i < nr_objects; i++, entry++)
		if (!entry->delta && entry->delta_child)
			entry->delta_limit =
				check_delta_limit(entry, 1);
}

typedef int (*entry_sort_t)(const struct object_entry *, const struct object_entry *);

static entry_sort_t current_sort;

static int sort_comparator(const void *_a, const void *_b)
{
	struct object_entry *a = *(struct object_entry **)_a;
	struct object_entry *b = *(struct object_entry **)_b;
	return current_sort(a,b);
}

static struct object_entry **create_sorted_list(entry_sort_t sort)
{
	struct object_entry **list = xmalloc(nr_objects * sizeof(struct object_entry *));
	int i;

	for (i = 0; i < nr_objects; i++)
		list[i] = objects + i;
	current_sort = sort;
	qsort(list, nr_objects, sizeof(struct object_entry *), sort_comparator);
	return list;
}

static int sha1_sort(const struct object_entry *a, const struct object_entry *b)
{
	return memcmp(a->sha1, b->sha1, 20);
}

static struct object_entry **create_final_object_list()
{
	struct object_entry **list;
	int i, j;

	for (i = nr_result = 0; i < nr_objects; i++)
		if (!objects[i].preferred_base)
			nr_result++;
	list = xmalloc(nr_result * sizeof(struct object_entry *));
	for (i = j = 0; i < nr_objects; i++) {
		if (!objects[i].preferred_base)
			list[j++] = objects + i;
	}
	current_sort = sha1_sort;
	qsort(list, nr_result, sizeof(struct object_entry *), sort_comparator);
	return list;
}

static int type_size_sort(const struct object_entry *a, const struct object_entry *b)
{
	if (a->type < b->type)
		return -1;
	if (a->type > b->type)
		return 1;
	if (a->hash < b->hash)
		return -1;
	if (a->hash > b->hash)
		return 1;
	if (a->preferred_base < b->preferred_base)
		return -1;
	if (a->preferred_base > b->preferred_base)
		return 1;
	if (a->size < b->size)
		return -1;
	if (a->size > b->size)
		return 1;
	return a < b ? -1 : (a > b);
}

struct unpacked {
	struct object_entry *entry;
	void *data;
};

/*
 * We search for deltas _backwards_ in a list sorted by type and
 * by size, so that we see progressively smaller and smaller files.
 * That's because we prefer deltas to be from the bigger file
 * to the smaller - deletes are potentially cheaper, but perhaps
 * more importantly, the bigger file is likely the more recent
 * one.
 */
static int try_delta(struct unpacked *cur, struct unpacked *old, unsigned max_depth)
{
	struct object_entry *cur_entry = cur->entry;
	struct object_entry *old_entry = old->entry;
	int old_preferred = (old_entry->preferred_base ||
			     old_entry->based_on_preferred);
	unsigned long size, oldsize, delta_size, sizediff;
	long max_size;
	void *delta_buf;

	/* Don't bother doing diffs between different types */
	if (cur_entry->type != old_entry->type)
		return -1;

	/* We do not compute delta to *create* objects we are not
	 * going to pack.
	 */
	if (cur_entry->preferred_base)
		return -1;

	/* If the current object is at pack edge, take the depth the
	 * objects that depend on the current object into account --
	 * otherwise they would become too deep.
	 */
	if (cur_entry->delta_child) {
		if (max_depth <= cur_entry->delta_limit)
			return 0;
		max_depth -= cur_entry->delta_limit;
	}

	size = cur_entry->size;
	if (size < 50)
		return -1;
	oldsize = old_entry->size;
	sizediff = oldsize > size ? oldsize - size : size - oldsize;
	if (sizediff > size / 8)
		return -1;
	if (old_entry->depth >= max_depth)
		return 0;

	/*
	 * NOTE!
	 *
	 * We always delta from the bigger to the smaller, since that's
	 * more space-efficient (deletes don't have to say _what_ they
	 * delete).
	 */
	max_size = size / 2 - 20;
	if (cur_entry->delta) {
		if (cur_entry->based_on_preferred) {
			if (old_preferred)
				max_size = cur_entry->delta_size-1;
			else
				/* trying with non-preferred one when we
				 * already have a delta based on preferred
				 * one is pointless.
				 */
				return -1;
		}
		else if (!old_preferred)
			max_size = cur_entry->delta_size-1;
		else
			/* otherwise...  even if delta with a
			 * preferred one produces a bigger result than
			 * what we currently have, which is based on a
			 * non-preferred one, it is OK.
			 */
			;
	}
	if (sizediff >= max_size)
		return -1;
	delta_buf = diff_delta(old->data, oldsize,
			       cur->data, size, &delta_size, max_size);
	if (!delta_buf)
		return 0;
	cur_entry->delta = old_entry;
	cur_entry->delta_size = delta_size;
	cur_entry->depth = old_entry->depth + 1;
	cur_entry->based_on_preferred = old_preferred;
	free(delta_buf);
	return 0;
}

static void find_deltas(struct object_entry **list, int window, int depth)
{
	int i, idx;
	unsigned int array_size = window * sizeof(struct unpacked);
	struct unpacked *array = xmalloc(array_size);
	int eye_candy;

	memset(array, 0, array_size);
	i = nr_objects;
	idx = 0;
	eye_candy = i - (nr_objects / 20);

	while (--i >= 0) {
		struct object_entry *entry = list[i];
		struct unpacked *n = array + idx;
		unsigned long size;
		char type[10];
		int j;

		if (progress && i <= eye_candy) {
			eye_candy -= nr_objects / 20;
			fputc('.', stderr);
		}

		if (entry->delta)
			/* This happens if we decided to reuse existing
			 * delta from a pack.  "!no_reuse_delta &&" is implied.
			 */
			continue;

		free(n->data);
		n->entry = entry;
		n->data = read_sha1_file(entry->sha1, type, &size);
		if (size != entry->size)
			die("object %s inconsistent object length (%lu vs %lu)", sha1_to_hex(entry->sha1), size, entry->size);

		j = window;
		while (--j > 0) {
			unsigned int other_idx = idx + j;
			struct unpacked *m;
			if (other_idx >= window)
				other_idx -= window;
			m = array + other_idx;
			if (!m->entry)
				break;
			if (try_delta(n, m, depth) < 0)
				break;
		}
		idx++;
		if (idx >= window)
			idx = 0;
	}

	for (i = 0; i < window; ++i)
		free(array[i].data);
	free(array);
}

static void prepare_pack(int window, int depth)
{
	if (progress)
		fprintf(stderr, "Packing %d objects", nr_result);
	get_object_details();
	if (progress)
		fputc('.', stderr);

	sorted_by_type = create_sorted_list(type_size_sort);
	if (window && depth)
		find_deltas(sorted_by_type, window+1, depth);
	if (progress)
		fputc('\n', stderr);
	write_pack_file();
}

static int reuse_cached_pack(unsigned char *sha1, int pack_to_stdout)
{
	static const char cache[] = "pack-cache/pack-%s.%s";
	char *cached_pack, *cached_idx;
	int ifd, ofd, ifd_ix = -1;

	cached_pack = git_path(cache, sha1_to_hex(sha1), "pack");
	ifd = open(cached_pack, O_RDONLY);
	if (ifd < 0)
		return 0;

	if (!pack_to_stdout) {
		cached_idx = git_path(cache, sha1_to_hex(sha1), "idx");
		ifd_ix = open(cached_idx, O_RDONLY);
		if (ifd_ix < 0) {
			close(ifd);
			return 0;
		}
	}

	if (progress)
		fprintf(stderr, "Reusing %d objects pack %s\n", nr_objects,
			sha1_to_hex(sha1));

	if (pack_to_stdout) {
		if (copy_fd(ifd, 1))
			exit(1);
		close(ifd);
	}
	else {
		char name[PATH_MAX];
		snprintf(name, sizeof(name),
			 "%s-%s.%s", base_name, sha1_to_hex(sha1), "pack");
		ofd = open(name, O_CREAT | O_EXCL | O_WRONLY, 0666);
		if (ofd < 0)
			die("unable to open %s (%s)", name, strerror(errno));
		if (copy_fd(ifd, ofd))
			exit(1);
		close(ifd);

		snprintf(name, sizeof(name),
			 "%s-%s.%s", base_name, sha1_to_hex(sha1), "idx");
		ofd = open(name, O_CREAT | O_EXCL | O_WRONLY, 0666);
		if (ofd < 0)
			die("unable to open %s (%s)", name, strerror(errno));
		if (copy_fd(ifd_ix, ofd))
			exit(1);
		close(ifd_ix);
		puts(sha1_to_hex(sha1));
	}

	return 1;
}

int main(int argc, char **argv)
{
	SHA_CTX ctx;
	char line[PATH_MAX + 20];
	int window = 10, depth = 10, pack_to_stdout = 0;
	struct object_entry **list;
	int i;
	struct timeval prev_tv;
	int eye_candy = 0;
	int eye_candy_incr = 500;


	setup_git_directory();

	for (i = 1; i < argc; i++) {
		const char *arg = argv[i];

		if (*arg == '-') {
			if (!strcmp("--non-empty", arg)) {
				non_empty = 1;
				continue;
			}
			if (!strcmp("--local", arg)) {
				local = 1;
				continue;
			}
			if (!strcmp("--incremental", arg)) {
				incremental = 1;
				continue;
			}
			if (!strncmp("--window=", arg, 9)) {
				char *end;
				window = strtoul(arg+9, &end, 0);
				if (!arg[9] || *end)
					usage(pack_usage);
				continue;
			}
			if (!strncmp("--depth=", arg, 8)) {
				char *end;
				depth = strtoul(arg+8, &end, 0);
				if (!arg[8] || *end)
					usage(pack_usage);
				continue;
			}
			if (!strcmp("-q", arg)) {
				progress = 0;
				continue;
			}
			if (!strcmp("--no-reuse-delta", arg)) {
				no_reuse_delta = 1;
				continue;
			}
			if (!strcmp("--stdout", arg)) {
				pack_to_stdout = 1;
				continue;
			}
			usage(pack_usage);
		}
		if (base_name)
			usage(pack_usage);
		base_name = arg;
	}

	if (pack_to_stdout != !base_name)
		usage(pack_usage);

	prepare_packed_git();
	if (progress) {
		fprintf(stderr, "Generating pack...\n");
		gettimeofday(&prev_tv, NULL);
	}
	while (fgets(line, sizeof(line), stdin) != NULL) {
		unsigned char sha1[20];

		if (progress && (eye_candy <= nr_objects)) {
			fprintf(stderr, "Counting objects...%d\r", nr_objects);
			if (eye_candy && (50 <= eye_candy_incr)) {
				struct timeval tv;
				int time_diff;
				gettimeofday(&tv, NULL);
				time_diff = (tv.tv_sec - prev_tv.tv_sec);
				time_diff <<= 10;
				time_diff += (tv.tv_usec - prev_tv.tv_usec);
				if ((1 << 9) < time_diff)
					eye_candy_incr += 50;
				else if (50 < eye_candy_incr)
					eye_candy_incr -= 50;
			}
			eye_candy += eye_candy_incr;
		}
		if (line[0] == '-') {
			if (get_sha1_hex(line+1, sha1))
				die("expected edge sha1, got garbage:\n %s",
				    line+1);
			add_preferred_base(sha1);
			continue;
		}
		if (get_sha1_hex(line, sha1))
			die("expected sha1, got garbage:\n %s", line);
		add_object_entry(sha1, line+40, 0);
	}
	if (progress)
		fprintf(stderr, "Done counting %d objects.\n", nr_objects);
	if (non_empty && !nr_objects)
		return 0;

	sorted_by_sha = create_final_object_list();
	SHA1_Init(&ctx);
	list = sorted_by_sha;
	for (i = 0; i < nr_result; i++) {
		struct object_entry *entry = *list++;
		SHA1_Update(&ctx, entry->sha1, 20);
	}
	SHA1_Final(object_list_sha1, &ctx);
	if (progress && (nr_objects != nr_result))
		fprintf(stderr, "Result has %d objects.\n", nr_result);

	if (reuse_cached_pack(object_list_sha1, pack_to_stdout))
		;
	else {
		prepare_pack(window, depth);
		if (!pack_to_stdout) {
			write_index_file();
			puts(sha1_to_hex(object_list_sha1));
		}
	}
	if (progress)
		fprintf(stderr, "Total %d, written %d (delta %d), reused %d (delta %d)\n",
			nr_result, written, written_delta, reused, reused_delta);
	return 0;
}