git@vger.kernel.org list mirror (unofficial, one of many)
 help / color / mirror / code / Atom feed
3375e24659ea1a34eca48af6109fa534861c8c7c blob 48782 bytes (raw)

   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
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
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
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
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
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
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
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
 
/*
 *
 * Copyright (C) 2005 Junio C Hamano
 */
#include "cache.h"
#include "diff.h"
#include "diffcore.h"
#include "object-store.h"
#include "hashmap.h"
#include "progress.h"
#include "promisor-remote.h"
#include "strmap.h"

/* Table of rename/copy destinations */

static struct diff_rename_dst {
	struct diff_filepair *p;
	struct diff_filespec *filespec_to_free;
	int is_rename; /* false -> just a create; true -> rename or copy */
} *rename_dst;
static int rename_dst_nr, rename_dst_alloc;
/* Mapping from break source pathname to break destination index */
static struct strintmap *break_idx = NULL;

static struct diff_rename_dst *locate_rename_dst(struct diff_filepair *p)
{
	/* Lookup by p->ONE->path */
	int idx = break_idx ? strintmap_get(break_idx, p->one->path) : -1;
	return (idx == -1) ? NULL : &rename_dst[idx];
}

/*
 * Returns 0 on success, -1 if we found a duplicate.
 */
static int add_rename_dst(struct diff_filepair *p)
{
	ALLOC_GROW(rename_dst, rename_dst_nr + 1, rename_dst_alloc);
	rename_dst[rename_dst_nr].p = p;
	rename_dst[rename_dst_nr].filespec_to_free = NULL;
	rename_dst[rename_dst_nr].is_rename = 0;
	rename_dst_nr++;
	return 0;
}

/* Table of rename/copy src files */
static struct diff_rename_src {
	struct diff_filepair *p;
	unsigned short score; /* to remember the break score */
} *rename_src;
static int rename_src_nr, rename_src_alloc;

static void register_rename_src(struct diff_filepair *p)
{
	if (p->broken_pair) {
		if (!break_idx) {
			break_idx = xmalloc(sizeof(*break_idx));
			strintmap_init(break_idx, -1);
		}
		strintmap_set(break_idx, p->one->path, rename_dst_nr);
	}

	ALLOC_GROW(rename_src, rename_src_nr + 1, rename_src_alloc);
	rename_src[rename_src_nr].p = p;
	rename_src[rename_src_nr].score = p->score;
	rename_src_nr++;
}

static int basename_same(struct diff_filespec *src, struct diff_filespec *dst)
{
	int src_len = strlen(src->path), dst_len = strlen(dst->path);
	while (src_len && dst_len) {
		char c1 = src->path[--src_len];
		char c2 = dst->path[--dst_len];
		if (c1 != c2)
			return 0;
		if (c1 == '/')
			return 1;
	}
	return (!src_len || src->path[src_len - 1] == '/') &&
		(!dst_len || dst->path[dst_len - 1] == '/');
}

struct diff_score {
	int src; /* index in rename_src */
	int dst; /* index in rename_dst */
	unsigned short score;
	short name_score;
};

struct prefetch_options {
	struct repository *repo;
	int skip_unmodified;
};
static void prefetch(void *prefetch_options)
{
	struct prefetch_options *options = prefetch_options;
	int i;
	struct oid_array to_fetch = OID_ARRAY_INIT;

	for (i = 0; i < rename_dst_nr; i++) {
		if (rename_dst[i].p->renamed_pair)
			/*
			 * The loop in diffcore_rename() will not need these
			 * blobs, so skip prefetching.
			 */
			continue; /* already found exact match */
		diff_add_if_missing(options->repo, &to_fetch,
				    rename_dst[i].p->two);
	}
	for (i = 0; i < rename_src_nr; i++) {
		if (options->skip_unmodified &&
		    diff_unmodified_pair(rename_src[i].p))
			/*
			 * The loop in diffcore_rename() will not need these
			 * blobs, so skip prefetching.
			 */
			continue;
		diff_add_if_missing(options->repo, &to_fetch,
				    rename_src[i].p->one);
	}
	promisor_remote_get_direct(options->repo, to_fetch.oid, to_fetch.nr);
	oid_array_clear(&to_fetch);
}

static int estimate_similarity(struct repository *r,
			       struct diff_filespec *src,
			       struct diff_filespec *dst,
			       int minimum_score,
			       int skip_unmodified)
{
	/* src points at a file that existed in the original tree (or
	 * optionally a file in the destination tree) and dst points
	 * at a newly created file.  They may be quite similar, in which
	 * case we want to say src is renamed to dst or src is copied into
	 * dst, and then some edit has been applied to dst.
	 *
	 * Compare them and return how similar they are, representing
	 * the score as an integer between 0 and MAX_SCORE.
	 *
	 * When there is an exact match, it is considered a better
	 * match than anything else; the destination does not even
	 * call into this function in that case.
	 */
	unsigned long max_size, delta_size, base_size, src_copied, literal_added;
	int score;
	struct diff_populate_filespec_options dpf_options = {
		.check_size_only = 1
	};
	struct prefetch_options prefetch_options = {r, skip_unmodified};

	if (r == the_repository && has_promisor_remote()) {
		dpf_options.missing_object_cb = prefetch;
		dpf_options.missing_object_data = &prefetch_options;
	}

	/* We deal only with regular files.  Symlink renames are handled
	 * only when they are exact matches --- in other words, no edits
	 * after renaming.
	 */
	if (!S_ISREG(src->mode) || !S_ISREG(dst->mode))
		return 0;

	/*
	 * Need to check that source and destination sizes are
	 * filled in before comparing them.
	 *
	 * If we already have "cnt_data" filled in, we know it's
	 * all good (avoid checking the size for zero, as that
	 * is a possible size - we really should have a flag to
	 * say whether the size is valid or not!)
	 */
	if (!src->cnt_data &&
	    diff_populate_filespec(r, src, &dpf_options))
		return 0;
	if (!dst->cnt_data &&
	    diff_populate_filespec(r, dst, &dpf_options))
		return 0;

	max_size = ((src->size > dst->size) ? src->size : dst->size);
	base_size = ((src->size < dst->size) ? src->size : dst->size);
	delta_size = max_size - base_size;

	/* We would not consider edits that change the file size so
	 * drastically.  delta_size must be smaller than
	 * (MAX_SCORE-minimum_score)/MAX_SCORE * min(src->size, dst->size).
	 *
	 * Note that base_size == 0 case is handled here already
	 * and the final score computation below would not have a
	 * divide-by-zero issue.
	 */
	if (max_size * (MAX_SCORE-minimum_score) < delta_size * MAX_SCORE)
		return 0;

	dpf_options.check_size_only = 0;

	if (!src->cnt_data && diff_populate_filespec(r, src, &dpf_options))
		return 0;
	if (!dst->cnt_data && diff_populate_filespec(r, dst, &dpf_options))
		return 0;

	if (diffcore_count_changes(r, src, dst,
				   &src->cnt_data, &dst->cnt_data,
				   &src_copied, &literal_added))
		return 0;

	/* How similar are they?
	 * what percentage of material in dst are from source?
	 */
	if (!dst->size)
		score = 0; /* should not happen */
	else
		score = (int)(src_copied * MAX_SCORE / max_size);
	return score;
}

static void record_rename_pair(int dst_index, int src_index, int score)
{
	struct diff_filepair *src = rename_src[src_index].p;
	struct diff_filepair *dst = rename_dst[dst_index].p;

	if (dst->renamed_pair)
		die("internal error: dst already matched.");

	src->one->rename_used++;
	src->one->count++;

	rename_dst[dst_index].filespec_to_free = dst->one;
	rename_dst[dst_index].is_rename = 1;

	dst->one = src->one;
	dst->renamed_pair = 1;
	if (!strcmp(dst->one->path, dst->two->path))
		dst->score = rename_src[src_index].score;
	else
		dst->score = score;
}

/*
 * We sort the rename similarity matrix with the score, in descending
 * order (the most similar first).
 */
static int score_compare(const void *a_, const void *b_)
{
	const struct diff_score *a = a_, *b = b_;

	/* sink the unused ones to the bottom */
	if (a->dst < 0)
		return (0 <= b->dst);
	else if (b->dst < 0)
		return -1;

	if (a->score == b->score)
		return b->name_score - a->name_score;

	return b->score - a->score;
}

struct file_similarity {
	struct hashmap_entry entry;
	int index;
	struct diff_filespec *filespec;
};

static unsigned int hash_filespec(struct repository *r,
				  struct diff_filespec *filespec)
{
	if (!filespec->oid_valid) {
		if (diff_populate_filespec(r, filespec, NULL))
			return 0;
		hash_object_file(r->hash_algo, filespec->data, filespec->size,
				 "blob", &filespec->oid);
	}
	return oidhash(&filespec->oid);
}

static int find_identical_files(struct hashmap *srcs,
				int dst_index,
				struct diff_options *options)
{
	int renames = 0;
	struct diff_filespec *target = rename_dst[dst_index].p->two;
	struct file_similarity *p, *best = NULL;
	int i = 100, best_score = -1;
	unsigned int hash = hash_filespec(options->repo, target);

	/*
	 * Find the best source match for specified destination.
	 */
	p = hashmap_get_entry_from_hash(srcs, hash, NULL,
					struct file_similarity, entry);
	hashmap_for_each_entry_from(srcs, p, entry) {
		int score;
		struct diff_filespec *source = p->filespec;

		/* False hash collision? */
		if (!oideq(&source->oid, &target->oid))
			continue;
		/* Non-regular files? If so, the modes must match! */
		if (!S_ISREG(source->mode) || !S_ISREG(target->mode)) {
			if (source->mode != target->mode)
				continue;
		}
		/* Give higher scores to sources that haven't been used already */
		score = !source->rename_used;
		if (source->rename_used && options->detect_rename != DIFF_DETECT_COPY)
			continue;
		score += basename_same(source, target);
		if (score > best_score) {
			best = p;
			best_score = score;
			if (score == 2)
				break;
		}

		/* Too many identical alternatives? Pick one */
		if (!--i)
			break;
	}
	if (best) {
		record_rename_pair(dst_index, best->index, MAX_SCORE);
		renames++;
	}
	return renames;
}

static void insert_file_table(struct repository *r,
			      struct hashmap *table, int index,
			      struct diff_filespec *filespec)
{
	struct file_similarity *entry = xmalloc(sizeof(*entry));

	entry->index = index;
	entry->filespec = filespec;

	hashmap_entry_init(&entry->entry, hash_filespec(r, filespec));
	hashmap_add(table, &entry->entry);
}

/*
 * Find exact renames first.
 *
 * The first round matches up the up-to-date entries,
 * and then during the second round we try to match
 * cache-dirty entries as well.
 */
static int find_exact_renames(struct diff_options *options)
{
	int i, renames = 0;
	struct hashmap file_table;

	/* Add all sources to the hash table in reverse order, because
	 * later on they will be retrieved in LIFO order.
	 */
	hashmap_init(&file_table, NULL, NULL, rename_src_nr);
	for (i = rename_src_nr-1; i >= 0; i--)
		insert_file_table(options->repo,
				  &file_table, i,
				  rename_src[i].p->one);

	/* Walk the destinations and find best source match */
	for (i = 0; i < rename_dst_nr; i++)
		renames += find_identical_files(&file_table, i, options);

	/* Free the hash data structure and entries */
	hashmap_clear_and_free(&file_table, struct file_similarity, entry);

	return renames;
}

struct dir_rename_info {
	struct strintmap idx_map;
	struct strmap dir_rename_guess;
	struct strmap *dir_rename_count;
	struct strintmap *relevant_source_dirs;
	unsigned setup;
};

static char *get_dirname(const char *filename)
{
	char *slash = strrchr(filename, '/');
	return slash ? xstrndup(filename, slash - filename) : xstrdup("");
}

static void dirname_munge(char *filename)
{
	char *slash = strrchr(filename, '/');
	if (!slash)
		slash = filename;
	*slash = '\0';
}

static const char *get_highest_rename_path(struct strintmap *counts)
{
	int highest_count = 0;
	const char *highest_destination_dir = NULL;
	struct hashmap_iter iter;
	struct strmap_entry *entry;

	strintmap_for_each_entry(counts, &iter, entry) {
		const char *destination_dir = entry->key;
		intptr_t count = (intptr_t)entry->value;
		if (count > highest_count) {
			highest_count = count;
			highest_destination_dir = destination_dir;
		}
	}
	return highest_destination_dir;
}

static char *UNKNOWN_DIR = "/";  /* placeholder -- short, illegal directory */

static int dir_rename_already_determinable(struct strintmap *counts)
{
	struct hashmap_iter iter;
	struct strmap_entry *entry;
	int first = 0, second = 0, unknown = 0;
	strintmap_for_each_entry(counts, &iter, entry) {
		const char *destination_dir = entry->key;
		intptr_t count = (intptr_t)entry->value;
		if (!strcmp(destination_dir, UNKNOWN_DIR)) {
			unknown = count;
		} else if (count >= first) {
			second = first;
			first = count;
		} else if (count >= second) {
			second = count;
		}
	}
	return first > second + unknown;
}

static void increment_count(struct dir_rename_info *info,
			    char *old_dir,
			    char *new_dir)
{
	struct strintmap *counts;
	struct strmap_entry *e;

	/* Get the {new_dirs -> counts} mapping using old_dir */
	e = strmap_get_entry(info->dir_rename_count, old_dir);
	if (e) {
		counts = e->value;
	} else {
		counts = xmalloc(sizeof(*counts));
		strintmap_init_with_options(counts, 0, NULL, 1);
		strmap_put(info->dir_rename_count, old_dir, counts);
	}

	/* Increment the count for new_dir */
	strintmap_incr(counts, new_dir, 1);
}

static void update_dir_rename_counts(struct dir_rename_info *info,
				     struct strintmap *dirs_removed,
				     const char *oldname,
				     const char *newname)
{
	char *old_dir = xstrdup(oldname);
	char *new_dir = xstrdup(newname);
	char new_dir_first_char = new_dir[0];
	int first_time_in_loop = 1;

	if (!info->setup)
		/*
		 * info->setup is 0 here in two cases: (1) all auxiliary
		 * vars (like dirs_removed) were NULL so
		 * initialize_dir_rename_info() returned early, or (2)
		 * either break detection or copy detection are active so
		 * that we never called initialize_dir_rename_info().  In
		 * the former case, we don't have enough info to know if
		 * directories were renamed (because dirs_removed lets us
		 * know about a necessary prerequisite, namely if they were
		 * removed), and in the latter, we don't care about
		 * directory renames or find_basename_matches.
		 *
		 * This matters because both basename and inexact matching
		 * will also call update_dir_rename_counts().  In either of
		 * the above two cases info->dir_rename_counts will not
		 * have been properly initialized which prevents us from
		 * updating it, but in these two cases we don't care about
		 * dir_rename_counts anyway, so we can just exit early.
		 */
		return;

	while (1) {
		int drd_flag = NOT_RELEVANT;

		/* Get old_dir, skip if its directory isn't relevant. */
		dirname_munge(old_dir);
		if (info->relevant_source_dirs &&
		    !strintmap_contains(info->relevant_source_dirs, old_dir))
			break;

		/* Get new_dir */
		dirname_munge(new_dir);

		/*
		 * When renaming
		 *   "a/b/c/d/e/foo.c" -> "a/b/some/thing/else/e/foo.c"
		 * then this suggests that both
		 *   a/b/c/d/e/ => a/b/some/thing/else/e/
		 *   a/b/c/d/   => a/b/some/thing/else/
		 * so we want to increment counters for both.  We do NOT,
		 * however, also want to suggest that there was the following
		 * rename:
		 *   a/b/c/ => a/b/some/thing/
		 * so we need to quit at that point.
		 *
		 * Note the when first_time_in_loop, we only strip off the
		 * basename, and we don't care if that's different.
		 */
		if (!first_time_in_loop) {
			char *old_sub_dir = strchr(old_dir, '\0')+1;
			char *new_sub_dir = strchr(new_dir, '\0')+1;
			if (!*new_dir) {
				/*
				 * Special case when renaming to root directory,
				 * i.e. when new_dir == "".  In this case, we had
				 * something like
				 *    a/b/subdir => subdir
				 * and so dirname_munge() sets things up so that
				 *    old_dir = "a/b\0subdir\0"
				 *    new_dir = "\0ubdir\0"
				 * We didn't have a '/' to overwrite a '\0' onto
				 * in new_dir, so we have to compare differently.
				 */
				if (new_dir_first_char != old_sub_dir[0] ||
				    strcmp(old_sub_dir+1, new_sub_dir))
					break;
			} else {
				if (strcmp(old_sub_dir, new_sub_dir))
					break;
			}
		}

		/*
		 * Above we suggested that we'd keep recording renames for
		 * all ancestor directories where the trailing directories
		 * matched, i.e. for
		 *   "a/b/c/d/e/foo.c" -> "a/b/some/thing/else/e/foo.c"
		 * we'd increment rename counts for each of
		 *   a/b/c/d/e/ => a/b/some/thing/else/e/
		 *   a/b/c/d/   => a/b/some/thing/else/
		 * However, we only need the rename counts for directories
		 * in dirs_removed whose value is RELEVANT_FOR_SELF.
		 * However, we add one special case of also recording it for
		 * first_time_in_loop because find_basename_matches() can
		 * use that as a hint to find a good pairing.
		 */
		if (dirs_removed)
			drd_flag = strintmap_get(dirs_removed, old_dir);
		if (drd_flag == RELEVANT_FOR_SELF || first_time_in_loop)
			increment_count(info, old_dir, new_dir);

		first_time_in_loop = 0;
		if (drd_flag == NOT_RELEVANT)
			break;
		/* If we hit toplevel directory ("") for old or new dir, quit */
		if (!*old_dir || !*new_dir)
			break;
	}

	/* Free resources we don't need anymore */
	free(old_dir);
	free(new_dir);
}

static void initialize_dir_rename_info(struct dir_rename_info *info,
				       struct strintmap *relevant_sources,
				       struct strintmap *dirs_removed,
				       struct strmap *dir_rename_count,
				       struct strmap *cached_pairs)
{
	struct hashmap_iter iter;
	struct strmap_entry *entry;
	int i;

	if (!dirs_removed && !relevant_sources) {
		info->setup = 0;
		return;
	}
	info->setup = 1;

	info->dir_rename_count = dir_rename_count;
	if (!info->dir_rename_count) {
		info->dir_rename_count = xmalloc(sizeof(*dir_rename_count));
		strmap_init(info->dir_rename_count);
	}
	strintmap_init_with_options(&info->idx_map, -1, NULL, 0);
	strmap_init_with_options(&info->dir_rename_guess, NULL, 0);

	/* Setup info->relevant_source_dirs */
	info->relevant_source_dirs = NULL;
	if (dirs_removed || !relevant_sources) {
		info->relevant_source_dirs = dirs_removed; /* might be NULL */
	} else {
		info->relevant_source_dirs = xmalloc(sizeof(struct strintmap));
		strintmap_init(info->relevant_source_dirs, 0 /* unused */);
		strintmap_for_each_entry(relevant_sources, &iter, entry) {
			char *dirname = get_dirname(entry->key);
			if (!dirs_removed ||
			    strintmap_contains(dirs_removed, dirname))
				strintmap_set(info->relevant_source_dirs,
					      dirname, 0 /* value irrelevant */);
			free(dirname);
		}
	}

	/*
	 * Loop setting up both info->idx_map, and doing setup of
	 * info->dir_rename_count.
	 */
	for (i = 0; i < rename_dst_nr; ++i) {
		/*
		 * For non-renamed files, make idx_map contain mapping of
		 *   filename -> index (index within rename_dst, that is)
		 */
		if (!rename_dst[i].is_rename) {
			char *filename = rename_dst[i].p->two->path;
			strintmap_set(&info->idx_map, filename, i);
			continue;
		}

		/*
		 * For everything else (i.e. renamed files), make
		 * dir_rename_count contain a map of a map:
		 *   old_directory -> {new_directory -> count}
		 * In other words, for every pair look at the directories for
		 * the old filename and the new filename and count how many
		 * times that pairing occurs.
		 */
		update_dir_rename_counts(info, dirs_removed,
					 rename_dst[i].p->one->path,
					 rename_dst[i].p->two->path);
	}

	/* Add cached_pairs to counts */
	strmap_for_each_entry(cached_pairs, &iter, entry) {
		const char *old_name = entry->key;
		const char *new_name = entry->value;
		if (!new_name)
			/* known delete; ignore it */
			continue;

		update_dir_rename_counts(info, dirs_removed, old_name, new_name);
	}

	/*
	 * Now we collapse
	 *    dir_rename_count: old_directory -> {new_directory -> count}
	 * down to
	 *    dir_rename_guess: old_directory -> best_new_directory
	 * where best_new_directory is the one with the highest count.
	 */
	strmap_for_each_entry(info->dir_rename_count, &iter, entry) {
		/* entry->key is source_dir */
		struct strintmap *counts = entry->value;
		char *best_newdir;

		best_newdir = xstrdup(get_highest_rename_path(counts));
		strmap_put(&info->dir_rename_guess, entry->key,
			   best_newdir);
	}
}

void partial_clear_dir_rename_count(struct strmap *dir_rename_count)
{
	struct hashmap_iter iter;
	struct strmap_entry *entry;

	strmap_for_each_entry(dir_rename_count, &iter, entry) {
		struct strintmap *counts = entry->value;
		strintmap_clear(counts);
	}
	strmap_partial_clear(dir_rename_count, 1);
}

static void cleanup_dir_rename_info(struct dir_rename_info *info,
				    struct strintmap *dirs_removed,
				    int keep_dir_rename_count)
{
	struct hashmap_iter iter;
	struct strmap_entry *entry;
	struct string_list to_remove = STRING_LIST_INIT_NODUP;
	int i;

	if (!info->setup)
		return;

	/* idx_map */
	strintmap_clear(&info->idx_map);

	/* dir_rename_guess */
	strmap_clear(&info->dir_rename_guess, 1);

	/* relevant_source_dirs */
	if (info->relevant_source_dirs &&
	    info->relevant_source_dirs != dirs_removed) {
		strintmap_clear(info->relevant_source_dirs);
		FREE_AND_NULL(info->relevant_source_dirs);
	}

	/* dir_rename_count */
	if (!keep_dir_rename_count) {
		partial_clear_dir_rename_count(info->dir_rename_count);
		strmap_clear(info->dir_rename_count, 1);
		FREE_AND_NULL(info->dir_rename_count);
		return;
	}

	/*
	 * Although dir_rename_count was passed in
	 * diffcore_rename_extended() and we want to keep it around and
	 * return it to that caller, we first want to remove any counts in
	 * the maps associated with UNKNOWN_DIR entries and any data
	 * associated with directories that weren't renamed.
	 */
	strmap_for_each_entry(info->dir_rename_count, &iter, entry) {
		const char *source_dir = entry->key;
		struct strintmap *counts = entry->value;

		if (!strintmap_get(dirs_removed, source_dir)) {
			string_list_append(&to_remove, source_dir);
			strintmap_clear(counts);
			continue;
		}

		if (strintmap_contains(counts, UNKNOWN_DIR))
			strintmap_remove(counts, UNKNOWN_DIR);
	}
	for (i = 0; i < to_remove.nr; ++i)
		strmap_remove(info->dir_rename_count,
			      to_remove.items[i].string, 1);
	string_list_clear(&to_remove, 0);
}

static const char *get_basename(const char *filename)
{
	/*
	 * gitbasename() has to worry about special drives, multiple
	 * directory separator characters, trailing slashes, NULL or
	 * empty strings, etc.  We only work on filenames as stored in
	 * git, and thus get to ignore all those complications.
	 */
	const char *base = strrchr(filename, '/');
	return base ? base + 1 : filename;
}

static int idx_possible_rename(char *filename, struct dir_rename_info *info)
{
	/*
	 * Our comparison of files with the same basename (see
	 * find_basename_matches() below), is only helpful when after exact
	 * rename detection we have exactly one file with a given basename
	 * among the rename sources and also only exactly one file with
	 * that basename among the rename destinations.  When we have
	 * multiple files with the same basename in either set, we do not
	 * know which to compare against.  However, there are some
	 * filenames that occur in large numbers (particularly
	 * build-related filenames such as 'Makefile', '.gitignore', or
	 * 'build.gradle' that potentially exist within every single
	 * subdirectory), and for performance we want to be able to quickly
	 * find renames for these files too.
	 *
	 * The reason basename comparisons are a useful heuristic was that it
	 * is common for people to move files across directories while keeping
	 * their filename the same.  If we had a way of determining or even
	 * making a good educated guess about which directory these non-unique
	 * basename files had moved the file to, we could check it.
	 * Luckily...
	 *
	 * When an entire directory is in fact renamed, we have two factors
	 * helping us out:
	 *   (a) the original directory disappeared giving us a hint
	 *       about when we can apply an extra heuristic.
	 *   (a) we often have several files within that directory and
	 *       subdirectories that are renamed without changes
	 * So, rules for a heuristic:
	 *   (0) If there basename matches are non-unique (the condition under
	 *       which this function is called) AND
	 *   (1) the directory in which the file was found has disappeared
	 *       (i.e. dirs_removed is non-NULL and has a relevant entry) THEN
	 *   (2) use exact renames of files within the directory to determine
	 *       where the directory is likely to have been renamed to.  IF
	 *       there is at least one exact rename from within that
	 *       directory, we can proceed.
	 *   (3) If there are multiple places the directory could have been
	 *       renamed to based on exact renames, ignore all but one of them.
	 *       Just use the destination with the most renames going to it.
	 *   (4) Check if applying that directory rename to the original file
	 *       would result in a destination filename that is in the
	 *       potential rename set.  If so, return the index of the
	 *       destination file (the index within rename_dst).
	 *   (5) Compare the original file and returned destination for
	 *       similarity, and if they are sufficiently similar, record the
	 *       rename.
	 *
	 * This function, idx_possible_rename(), is only responsible for (4).
	 * The conditions/steps in (1)-(3) are handled via setting up
	 * dir_rename_count and dir_rename_guess in
	 * initialize_dir_rename_info().  Steps (0) and (5) are handled by
	 * the caller of this function.
	 */
	char *old_dir, *new_dir;
	struct strbuf new_path = STRBUF_INIT;
	int idx;

	if (!info->setup)
		return -1;

	old_dir = get_dirname(filename);
	new_dir = strmap_get(&info->dir_rename_guess, old_dir);
	free(old_dir);
	if (!new_dir)
		return -1;

	strbuf_addstr(&new_path, new_dir);
	strbuf_addch(&new_path, '/');
	strbuf_addstr(&new_path, get_basename(filename));

	idx = strintmap_get(&info->idx_map, new_path.buf);
	strbuf_release(&new_path);
	return idx;
}

static int find_basename_matches(struct diff_options *options,
				 int minimum_score,
				 struct dir_rename_info *info,
				 struct strintmap *relevant_sources,
				 struct strintmap *dirs_removed)
{
	/*
	 * When I checked in early 2020, over 76% of file renames in linux
	 * just moved files to a different directory but kept the same
	 * basename.  gcc did that with over 64% of renames, gecko did it
	 * with over 79%, and WebKit did it with over 89%.
	 *
	 * Therefore we can bypass the normal exhaustive NxM matrix
	 * comparison of similarities between all potential rename sources
	 * and destinations by instead using file basename as a hint (i.e.
	 * the portion of the filename after the last '/'), checking for
	 * similarity between files with the same basename, and if we find
	 * a pair that are sufficiently similar, record the rename pair and
	 * exclude those two from the NxM matrix.
	 *
	 * This *might* cause us to find a less than optimal pairing (if
	 * there is another file that we are even more similar to but has a
	 * different basename).  Given the huge performance advantage
	 * basename matching provides, and given the frequency with which
	 * people use the same basename in real world projects, that's a
	 * trade-off we are willing to accept when doing just rename
	 * detection.
	 *
	 * If someone wants copy detection that implies they are willing to
	 * spend more cycles to find similarities between files, so it may
	 * be less likely that this heuristic is wanted.  If someone is
	 * doing break detection, that means they do not want filename
	 * similarity to imply any form of content similiarity, and thus
	 * this heuristic would definitely be incompatible.
	 */

	int i, renames = 0;
	struct strintmap sources;
	struct strintmap dests;

	/*
	 * The prefeteching stuff wants to know if it can skip prefetching
	 * blobs that are unmodified...and will then do a little extra work
	 * to verify that the oids are indeed different before prefetching.
	 * Unmodified blobs are only relevant when doing copy detection;
	 * when limiting to rename detection, diffcore_rename[_extended]()
	 * will never be called with unmodified source paths fed to us, so
	 * the extra work necessary to check if rename_src entries are
	 * unmodified would be a small waste.
	 */
	int skip_unmodified = 0;

	/*
	 * Create maps of basename -> fullname(s) for remaining sources and
	 * dests.
	 */
	strintmap_init_with_options(&sources, -1, NULL, 0);
	strintmap_init_with_options(&dests, -1, NULL, 0);
	for (i = 0; i < rename_src_nr; ++i) {
		char *filename = rename_src[i].p->one->path;
		const char *base;

		/* exact renames removed in remove_unneeded_paths_from_src() */
		assert(!rename_src[i].p->one->rename_used);

		/* Record index within rename_src (i) if basename is unique */
		base = get_basename(filename);
		if (strintmap_contains(&sources, base))
			strintmap_set(&sources, base, -1);
		else
			strintmap_set(&sources, base, i);
	}
	for (i = 0; i < rename_dst_nr; ++i) {
		char *filename = rename_dst[i].p->two->path;
		const char *base;

		if (rename_dst[i].is_rename)
			continue; /* involved in exact match already. */

		/* Record index within rename_dst (i) if basename is unique */
		base = get_basename(filename);
		if (strintmap_contains(&dests, base))
			strintmap_set(&dests, base, -1);
		else
			strintmap_set(&dests, base, i);
	}

	/* Now look for basename matchups and do similarity estimation */
	for (i = 0; i < rename_src_nr; ++i) {
		char *filename = rename_src[i].p->one->path;
		const char *base = NULL;
		intptr_t src_index;
		intptr_t dst_index;

		/* Skip irrelevant sources */
		if (relevant_sources &&
		    !strintmap_contains(relevant_sources, filename))
			continue;

		/*
		 * If the basename is unique among remaining sources, then
		 * src_index will equal 'i' and we can attempt to match it
		 * to a unique basename in the destinations.  Otherwise,
		 * use directory rename heuristics, if possible.
		 */
		base = get_basename(filename);
		src_index = strintmap_get(&sources, base);
		assert(src_index == -1 || src_index == i);

		if (strintmap_contains(&dests, base)) {
			struct diff_filespec *one, *two;
			int score;

			/* Find a matching destination, if possible */
			dst_index = strintmap_get(&dests, base);
			if (src_index == -1 || dst_index == -1) {
				src_index = i;
				dst_index = idx_possible_rename(filename, info);
			}
			if (dst_index == -1)
				continue;

			/* Ignore this dest if already used in a rename */
			if (rename_dst[dst_index].is_rename)
				continue; /* already used previously */

			/* Estimate the similarity */
			one = rename_src[src_index].p->one;
			two = rename_dst[dst_index].p->two;
			score = estimate_similarity(options->repo, one, two,
						    minimum_score, skip_unmodified);

			/* If sufficiently similar, record as rename pair */
			if (score < minimum_score)
				continue;
			record_rename_pair(dst_index, src_index, score);
			renames++;
			update_dir_rename_counts(info, dirs_removed,
						 one->path, two->path);

			/*
			 * Found a rename so don't need text anymore; if we
			 * didn't find a rename, the filespec_blob would get
			 * re-used when doing the matrix of comparisons.
			 */
			diff_free_filespec_blob(one);
			diff_free_filespec_blob(two);
		}
	}

	strintmap_clear(&sources);
	strintmap_clear(&dests);

	return renames;
}

#define NUM_CANDIDATE_PER_DST 4
static void record_if_better(struct diff_score m[], struct diff_score *o)
{
	int i, worst;

	/* find the worst one */
	worst = 0;
	for (i = 1; i < NUM_CANDIDATE_PER_DST; i++)
		if (score_compare(&m[i], &m[worst]) > 0)
			worst = i;

	/* is it better than the worst one? */
	if (score_compare(&m[worst], o) > 0)
		m[worst] = *o;
}

/*
 * Returns:
 * 0 if we are under the limit;
 * 1 if we need to disable inexact rename detection;
 * 2 if we would be under the limit if we were given -C instead of -C -C.
 */
static int too_many_rename_candidates(int num_destinations, int num_sources,
				      struct diff_options *options)
{
	int rename_limit = options->rename_limit;
	int i, limited_sources;

	options->needed_rename_limit = 0;

	/*
	 * This basically does a test for the rename matrix not
	 * growing larger than a "rename_limit" square matrix, ie:
	 *
	 *    num_destinations * num_sources > rename_limit * rename_limit
	 *
	 * We use st_mult() to check overflow conditions; in the
	 * exceptional circumstance that size_t isn't large enough to hold
	 * the multiplication, the system won't be able to allocate enough
	 * memory for the matrix anyway.
	 */
	if (rename_limit <= 0)
		rename_limit = 32767;
	if (st_mult(num_destinations, num_sources)
	    <= st_mult(rename_limit, rename_limit))
		return 0;

	options->needed_rename_limit =
		num_sources > num_destinations ? num_sources : num_destinations;

	/* Are we running under -C -C? */
	if (!options->flags.find_copies_harder)
		return 1;

	/* Would we bust the limit if we were running under -C? */
	for (limited_sources = i = 0; i < num_sources; i++) {
		if (diff_unmodified_pair(rename_src[i].p))
			continue;
		limited_sources++;
	}
	if (st_mult(num_destinations, limited_sources)
	    <= st_mult(rename_limit, rename_limit))
		return 2;
	return 1;
}

static int find_renames(struct diff_score *mx,
			int dst_cnt,
			int minimum_score,
			int copies,
			struct dir_rename_info *info,
			struct strintmap *dirs_removed)
{
	int count = 0, i;

	for (i = 0; i < dst_cnt * NUM_CANDIDATE_PER_DST; i++) {
		struct diff_rename_dst *dst;

		if ((mx[i].dst < 0) ||
		    (mx[i].score < minimum_score))
			break; /* there is no more usable pair. */
		dst = &rename_dst[mx[i].dst];
		if (dst->is_rename)
			continue; /* already done, either exact or fuzzy. */
		if (!copies && rename_src[mx[i].src].p->one->rename_used)
			continue;
		record_rename_pair(mx[i].dst, mx[i].src, mx[i].score);
		count++;
		update_dir_rename_counts(info, dirs_removed,
					 rename_src[mx[i].src].p->one->path,
					 rename_dst[mx[i].dst].p->two->path);
	}
	return count;
}

static void remove_unneeded_paths_from_src(int detecting_copies,
					   struct strintmap *interesting)
{
	int i, new_num_src;

	if (detecting_copies && !interesting)
		return; /* nothing to remove */
	if (break_idx)
		return; /* culling incompatible with break detection */

	/*
	 * Note on reasons why we cull unneeded sources but not destinations:
	 *   1) Pairings are stored in rename_dst (not rename_src), which we
	 *      need to keep around.  So, we just can't cull rename_dst even
	 *      if we wanted to.  But doing so wouldn't help because...
	 *
	 *   2) There is a matrix pairwise comparison that follows the
	 *      "Performing inexact rename detection" progress message.
	 *      Iterating over the destinations is done in the outer loop,
	 *      hence we only iterate over each of those once and we can
	 *      easily skip the outer loop early if the destination isn't
	 *      relevant.  That's only one check per destination path to
	 *      skip.
	 *
	 *      By contrast, the sources are iterated in the inner loop; if
	 *      we check whether a source can be skipped, then we'll be
	 *      checking it N separate times, once for each destination.
	 *      We don't want to have to iterate over known-not-needed
	 *      sources N times each, so avoid that by removing the sources
	 *      from rename_src here.
	 */
	for (i = 0, new_num_src = 0; i < rename_src_nr; i++) {
		struct diff_filespec *one = rename_src[i].p->one;

		/*
		 * renames are stored in rename_dst, so if a rename has
		 * already been detected using this source, we can just
		 * remove the source knowing rename_dst has its info.
		 */
		if (!detecting_copies && one->rename_used)
			continue;

		/* If we don't care about the source path, skip it */
		if (interesting && !strintmap_contains(interesting, one->path))
			continue;

		if (new_num_src < i)
			memcpy(&rename_src[new_num_src], &rename_src[i],
			       sizeof(struct diff_rename_src));
		new_num_src++;
	}

	rename_src_nr = new_num_src;
}

static void handle_early_known_dir_renames(struct dir_rename_info *info,
					   struct strintmap *relevant_sources,
					   struct strintmap *dirs_removed)
{
	/*
	 * Directory renames are determined via an aggregate of all renames
	 * under them and using a "majority wins" rule.  The fact that
	 * "majority wins", though, means we don't need all the renames
	 * under the given directory, we only need enough to ensure we have
	 * a majority.
	 */

	int i, new_num_src;
	struct hashmap_iter iter;
	struct strmap_entry *entry;

	if (!dirs_removed || !relevant_sources)
		return; /* nothing to cull */
	if (break_idx)
		return; /* culling incompatbile with break detection */

	/*
	 * Supplement dir_rename_count with number of potential renames,
	 * marking all potential rename sources as mapping to UNKNOWN_DIR.
	 */
	for (i = 0; i < rename_src_nr; i++) {
		char *old_dir;
		struct diff_filespec *one = rename_src[i].p->one;

		/*
		 * sources that are part of a rename will have already been
		 * removed by a prior call to remove_unneeded_paths_from_src()
		 */
		assert(!one->rename_used);

		old_dir = get_dirname(one->path);
		while (*old_dir != '\0' &&
		       NOT_RELEVANT != strintmap_get(dirs_removed, old_dir)) {
			char *freeme = old_dir;

			increment_count(info, old_dir, UNKNOWN_DIR);
			old_dir = get_dirname(old_dir);

			/* Free resources we don't need anymore */
			free(freeme);
		}
		/*
		 * old_dir and new_dir free'd in increment_count, but
		 * get_dirname() gives us a new pointer we need to free for
		 * old_dir.  Also, if the loop runs 0 times we need old_dir
		 * to be freed.
		 */
		free(old_dir);
	}

	/*
	 * For any directory which we need a potential rename detected for
	 * (i.e. those marked as RELEVANT_FOR_SELF in dirs_removed), check
	 * whether we have enough renames to satisfy the "majority rules"
	 * requirement such that detecting any more renames of files under
	 * it won't change the result.  For any such directory, mark that
	 * we no longer need to detect a rename for it.  However, since we
	 * might need to still detect renames for an ancestor of that
	 * directory, use RELEVANT_FOR_ANCESTOR.
	 */
	strmap_for_each_entry(info->dir_rename_count, &iter, entry) {
		/* entry->key is source_dir */
		struct strintmap *counts = entry->value;

		if (strintmap_get(dirs_removed, entry->key) ==
		    RELEVANT_FOR_SELF &&
		    dir_rename_already_determinable(counts)) {
			strintmap_set(dirs_removed, entry->key,
				      RELEVANT_FOR_ANCESTOR);
		}
	}

	for (i = 0, new_num_src = 0; i < rename_src_nr; i++) {
		struct diff_filespec *one = rename_src[i].p->one;
		int val;

		val = strintmap_get(relevant_sources, one->path);

		/*
		 * sources that were not found in relevant_sources should
		 * have already been removed by a prior call to
		 * remove_unneeded_paths_from_src()
		 */
		assert(val != -1);

		if (val == RELEVANT_LOCATION) {
			int removable = 1;
			char *dir = get_dirname(one->path);
			while (1) {
				char *freeme = dir;
				int res = strintmap_get(dirs_removed, dir);

				/* Quit if not found or irrelevant */
				if (res == NOT_RELEVANT)
					break;
				/* If RELEVANT_FOR_SELF, can't remove */
				if (res == RELEVANT_FOR_SELF) {
					removable = 0;
					break;
				}
				/* Else continue searching upwards */
				assert(res == RELEVANT_FOR_ANCESTOR);
				dir = get_dirname(dir);
				free(freeme);
			}
			free(dir);
			if (removable) {
				strintmap_set(relevant_sources, one->path,
					      RELEVANT_NO_MORE);
				continue;
			}
		}

		if (new_num_src < i)
			memcpy(&rename_src[new_num_src], &rename_src[i],
			       sizeof(struct diff_rename_src));
		new_num_src++;
	}

	rename_src_nr = new_num_src;
}

void diffcore_rename_extended(struct diff_options *options,
			      struct strintmap *relevant_sources,
			      struct strintmap *dirs_removed,
			      struct strmap *dir_rename_count,
			      struct strmap *cached_pairs)
{
	int detect_rename = options->detect_rename;
	int minimum_score = options->rename_score;
	struct diff_queue_struct *q = &diff_queued_diff;
	struct diff_queue_struct outq;
	struct diff_score *mx;
	int i, j, rename_count, skip_unmodified = 0;
	int num_destinations, dst_cnt;
	int num_sources, want_copies;
	struct progress *progress = NULL;
	struct dir_rename_info info;

	trace2_region_enter("diff", "setup", options->repo);
	info.setup = 0;
	assert(!dir_rename_count || strmap_empty(dir_rename_count));
	want_copies = (detect_rename == DIFF_DETECT_COPY);
	if (dirs_removed && (break_idx || want_copies))
		BUG("dirs_removed incompatible with break/copy detection");
	if (break_idx && relevant_sources)
		BUG("break detection incompatible with source specification");
	if (!minimum_score)
		minimum_score = DEFAULT_RENAME_SCORE;

	for (i = 0; i < q->nr; i++) {
		struct diff_filepair *p = q->queue[i];
		if (!DIFF_FILE_VALID(p->one)) {
			if (!DIFF_FILE_VALID(p->two))
				continue; /* unmerged */
			else if (options->single_follow &&
				 strcmp(options->single_follow, p->two->path))
				continue; /* not interested */
			else if (!options->flags.rename_empty &&
				 is_empty_blob_oid(&p->two->oid))
				continue;
			else if (add_rename_dst(p) < 0) {
				warning("skipping rename detection, detected"
					" duplicate destination '%s'",
					p->two->path);
				goto cleanup;
			}
		}
		else if (!options->flags.rename_empty &&
			 is_empty_blob_oid(&p->one->oid))
			continue;
		else if (!DIFF_PAIR_UNMERGED(p) && !DIFF_FILE_VALID(p->two)) {
			/*
			 * If the source is a broken "delete", and
			 * they did not really want to get broken,
			 * that means the source actually stays.
			 * So we increment the "rename_used" score
			 * by one, to indicate ourselves as a user
			 */
			if (p->broken_pair && !p->score)
				p->one->rename_used++;
			register_rename_src(p);
		}
		else if (want_copies) {
			/*
			 * Increment the "rename_used" score by
			 * one, to indicate ourselves as a user.
			 */
			p->one->rename_used++;
			register_rename_src(p);
		}
	}
	trace2_region_leave("diff", "setup", options->repo);
	if (rename_dst_nr == 0 || rename_src_nr == 0)
		goto cleanup; /* nothing to do */

	trace2_region_enter("diff", "exact renames", options->repo);
	/*
	 * We really want to cull the candidates list early
	 * with cheap tests in order to avoid doing deltas.
	 */
	rename_count = find_exact_renames(options);
	trace2_region_leave("diff", "exact renames", options->repo);

	/* Did we only want exact renames? */
	if (minimum_score == MAX_SCORE)
		goto cleanup;

	num_sources = rename_src_nr;

	if (want_copies || break_idx) {
		/*
		 * Cull sources:
		 *   - remove ones corresponding to exact renames
		 *   - remove ones not found in relevant_sources
		 */
		trace2_region_enter("diff", "cull after exact", options->repo);
		remove_unneeded_paths_from_src(want_copies, relevant_sources);
		trace2_region_leave("diff", "cull after exact", options->repo);
	} else {
		/* Determine minimum score to match basenames */
		double factor = 0.5;
		char *basename_factor = getenv("GIT_BASENAME_FACTOR");
		int min_basename_score;

		if (basename_factor)
			factor = strtol(basename_factor, NULL, 10)/100.0;
		assert(factor >= 0.0 && factor <= 1.0);
		min_basename_score = minimum_score +
			(int)(factor * (MAX_SCORE - minimum_score));

		/*
		 * Cull sources:
		 *   - remove ones involved in renames (found via exact match)
		 */
		trace2_region_enter("diff", "cull after exact", options->repo);
		remove_unneeded_paths_from_src(want_copies, NULL);
		trace2_region_leave("diff", "cull after exact", options->repo);

		/* Preparation for basename-driven matching. */
		trace2_region_enter("diff", "dir rename setup", options->repo);
		initialize_dir_rename_info(&info, relevant_sources,
					   dirs_removed, dir_rename_count,
					   cached_pairs);
		trace2_region_leave("diff", "dir rename setup", options->repo);

		/* Utilize file basenames to quickly find renames. */
		trace2_region_enter("diff", "basename matches", options->repo);
		rename_count += find_basename_matches(options,
						      min_basename_score,
						      &info,
						      relevant_sources,
						      dirs_removed);
		trace2_region_leave("diff", "basename matches", options->repo);

		/*
		 * Cull sources, again:
		 *   - remove ones involved in renames (found via basenames)
		 *   - remove ones not found in relevant_sources
		 * and
		 *   - remove ones in relevant_sources which are needed only
		 *     for directory renames IF no ancestory directory
		 *     actually needs to know any more individual path
		 *     renames under them
		 */
		trace2_region_enter("diff", "cull basename", options->repo);
		remove_unneeded_paths_from_src(want_copies, relevant_sources);
		handle_early_known_dir_renames(&info, relevant_sources,
					       dirs_removed);
		trace2_region_leave("diff", "cull basename", options->repo);
	}

	/* Calculate how many rename destinations are left */
	num_destinations = (rename_dst_nr - rename_count);
	num_sources = rename_src_nr; /* rename_src_nr reflects lower number */

	/* All done? */
	if (!num_destinations || !num_sources)
		goto cleanup;

	switch (too_many_rename_candidates(num_destinations, num_sources,
					   options)) {
	case 1:
		goto cleanup;
	case 2:
		options->degraded_cc_to_c = 1;
		skip_unmodified = 1;
		break;
	default:
		break;
	}

	trace2_region_enter("diff", "inexact renames", options->repo);
	if (options->show_rename_progress) {
		progress = start_delayed_progress(
				_("Performing inexact rename detection"),
				(uint64_t)num_destinations * (uint64_t)num_sources);
	}

	CALLOC_ARRAY(mx, st_mult(NUM_CANDIDATE_PER_DST, num_destinations));
	for (dst_cnt = i = 0; i < rename_dst_nr; i++) {
		struct diff_filespec *two = rename_dst[i].p->two;
		struct diff_score *m;

		if (rename_dst[i].is_rename)
			continue; /* exact or basename match already handled */

		m = &mx[dst_cnt * NUM_CANDIDATE_PER_DST];
		for (j = 0; j < NUM_CANDIDATE_PER_DST; j++)
			m[j].dst = -1;

		for (j = 0; j < rename_src_nr; j++) {
			struct diff_filespec *one = rename_src[j].p->one;
			struct diff_score this_src;

			assert(!one->rename_used || want_copies || break_idx);

			if (skip_unmodified &&
			    diff_unmodified_pair(rename_src[j].p))
				continue;

			this_src.score = estimate_similarity(options->repo,
							     one, two,
							     minimum_score,
							     skip_unmodified);
			this_src.name_score = basename_same(one, two);
			this_src.dst = i;
			this_src.src = j;
			record_if_better(m, &this_src);
			/*
			 * Once we run estimate_similarity,
			 * We do not need the text anymore.
			 */
			diff_free_filespec_blob(one);
			diff_free_filespec_blob(two);
		}
		dst_cnt++;
		display_progress(progress,
				 (uint64_t)dst_cnt * (uint64_t)num_sources);
	}
	stop_progress(&progress);

	/* cost matrix sorted by most to least similar pair */
	STABLE_QSORT(mx, dst_cnt * NUM_CANDIDATE_PER_DST, score_compare);

	rename_count += find_renames(mx, dst_cnt, minimum_score, 0,
				     &info, dirs_removed);
	if (want_copies)
		rename_count += find_renames(mx, dst_cnt, minimum_score, 1,
					     &info, dirs_removed);
	free(mx);
	trace2_region_leave("diff", "inexact renames", options->repo);

 cleanup:
	/* At this point, we have found some renames and copies and they
	 * are recorded in rename_dst.  The original list is still in *q.
	 */
	trace2_region_enter("diff", "write back to queue", options->repo);
	DIFF_QUEUE_CLEAR(&outq);
	for (i = 0; i < q->nr; i++) {
		struct diff_filepair *p = q->queue[i];
		struct diff_filepair *pair_to_free = NULL;

		if (DIFF_PAIR_UNMERGED(p)) {
			diff_q(&outq, p);
		}
		else if (!DIFF_FILE_VALID(p->one) && DIFF_FILE_VALID(p->two)) {
			/* Creation */
			diff_q(&outq, p);
		}
		else if (DIFF_FILE_VALID(p->one) && !DIFF_FILE_VALID(p->two)) {
			/*
			 * Deletion
			 *
			 * We would output this delete record if:
			 *
			 * (1) this is a broken delete and the counterpart
			 *     broken create remains in the output; or
			 * (2) this is not a broken delete, and rename_dst
			 *     does not have a rename/copy to move p->one->path
			 *     out of existence.
			 *
			 * Otherwise, the counterpart broken create
			 * has been turned into a rename-edit; or
			 * delete did not have a matching create to
			 * begin with.
			 */
			if (DIFF_PAIR_BROKEN(p)) {
				/* broken delete */
				struct diff_rename_dst *dst = locate_rename_dst(p);
				if (!dst)
					BUG("tracking failed somehow; failed to find associated dst for broken pair");
				if (dst->is_rename)
					/* counterpart is now rename/copy */
					pair_to_free = p;
			}
			else {
				if (p->one->rename_used)
					/* this path remains */
					pair_to_free = p;
			}

			if (!pair_to_free)
				diff_q(&outq, p);
		}
		else if (!diff_unmodified_pair(p))
			/* all the usual ones need to be kept */
			diff_q(&outq, p);
		else
			/* no need to keep unmodified pairs; FIXME: remove earlier? */
			pair_to_free = p;

		if (pair_to_free)
			diff_free_filepair(pair_to_free);
	}
	diff_debug_queue("done copying original", &outq);

	free(q->queue);
	*q = outq;
	diff_debug_queue("done collapsing", q);

	for (i = 0; i < rename_dst_nr; i++)
		if (rename_dst[i].filespec_to_free)
			free_filespec(rename_dst[i].filespec_to_free);

	cleanup_dir_rename_info(&info, dirs_removed, dir_rename_count != NULL);
	FREE_AND_NULL(rename_dst);
	rename_dst_nr = rename_dst_alloc = 0;
	FREE_AND_NULL(rename_src);
	rename_src_nr = rename_src_alloc = 0;
	if (break_idx) {
		strintmap_clear(break_idx);
		FREE_AND_NULL(break_idx);
	}
	trace2_region_leave("diff", "write back to queue", options->repo);
	return;
}

void diffcore_rename(struct diff_options *options)
{
	diffcore_rename_extended(options, NULL, NULL, NULL, NULL);
}
debug log:

solving 3375e24659ea ...
found 3375e24659ea in https://80x24.org/mirrors/git.git

Code repositories for project(s) associated with this inbox:

	https://80x24.org/mirrors/git.git

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).