Source

git / builtin-blame.c

   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
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
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
1627
1628
1629
1630
1631
1632
1633
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
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
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
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
/*
 * Pickaxe
 *
 * Copyright (c) 2006, Junio C Hamano
 */

#include "cache.h"
#include "builtin.h"
#include "blob.h"
#include "commit.h"
#include "tag.h"
#include "tree-walk.h"
#include "diff.h"
#include "diffcore.h"
#include "revision.h"
#include "quote.h"
#include "xdiff-interface.h"
#include "cache-tree.h"
#include "string-list.h"
#include "mailmap.h"
#include "parse-options.h"

static char blame_usage[] = "git blame [options] [rev-opts] [rev] [--] file";

static const char *blame_opt_usage[] = {
	blame_usage,
	"",
	"[rev-opts] are documented in git-rev-list(1)",
	NULL
};

static int longest_file;
static int longest_author;
static int max_orig_digits;
static int max_digits;
static int max_score_digits;
static int show_root;
static int reverse;
static int blank_boundary;
static int incremental;
static int xdl_opts = XDF_NEED_MINIMAL;
static struct string_list mailmap;

#ifndef DEBUG
#define DEBUG 0
#endif

/* stats */
static int num_read_blob;
static int num_get_patch;
static int num_commits;

#define PICKAXE_BLAME_MOVE		01
#define PICKAXE_BLAME_COPY		02
#define PICKAXE_BLAME_COPY_HARDER	04
#define PICKAXE_BLAME_COPY_HARDEST	010

/*
 * blame for a blame_entry with score lower than these thresholds
 * is not passed to the parent using move/copy logic.
 */
static unsigned blame_move_score;
static unsigned blame_copy_score;
#define BLAME_DEFAULT_MOVE_SCORE	20
#define BLAME_DEFAULT_COPY_SCORE	40

/* bits #0..7 in revision.h, #8..11 used for merge_bases() in commit.c */
#define METAINFO_SHOWN		(1u<<12)
#define MORE_THAN_ONE_PATH	(1u<<13)

/*
 * One blob in a commit that is being suspected
 */
struct origin {
	int refcnt;
	struct commit *commit;
	mmfile_t file;
	unsigned char blob_sha1[20];
	char path[FLEX_ARRAY];
};

/*
 * Given an origin, prepare mmfile_t structure to be used by the
 * diff machinery
 */
static void fill_origin_blob(struct origin *o, mmfile_t *file)
{
	if (!o->file.ptr) {
		enum object_type type;
		num_read_blob++;
		file->ptr = read_sha1_file(o->blob_sha1, &type,
					   (unsigned long *)(&(file->size)));
		if (!file->ptr)
			die("Cannot read blob %s for path %s",
			    sha1_to_hex(o->blob_sha1),
			    o->path);
		o->file = *file;
	}
	else
		*file = o->file;
}

/*
 * Origin is refcounted and usually we keep the blob contents to be
 * reused.
 */
static inline struct origin *origin_incref(struct origin *o)
{
	if (o)
		o->refcnt++;
	return o;
}

static void origin_decref(struct origin *o)
{
	if (o && --o->refcnt <= 0) {
		free(o->file.ptr);
		free(o);
	}
}

static void drop_origin_blob(struct origin *o)
{
	if (o->file.ptr) {
		free(o->file.ptr);
		o->file.ptr = NULL;
	}
}

/*
 * Each group of lines is described by a blame_entry; it can be split
 * as we pass blame to the parents.  They form a linked list in the
 * scoreboard structure, sorted by the target line number.
 */
struct blame_entry {
	struct blame_entry *prev;
	struct blame_entry *next;

	/* the first line of this group in the final image;
	 * internally all line numbers are 0 based.
	 */
	int lno;

	/* how many lines this group has */
	int num_lines;

	/* the commit that introduced this group into the final image */
	struct origin *suspect;

	/* true if the suspect is truly guilty; false while we have not
	 * checked if the group came from one of its parents.
	 */
	char guilty;

	/* true if the entry has been scanned for copies in the current parent
	 */
	char scanned;

	/* the line number of the first line of this group in the
	 * suspect's file; internally all line numbers are 0 based.
	 */
	int s_lno;

	/* how significant this entry is -- cached to avoid
	 * scanning the lines over and over.
	 */
	unsigned score;
};

/*
 * The current state of the blame assignment.
 */
struct scoreboard {
	/* the final commit (i.e. where we started digging from) */
	struct commit *final;
	struct rev_info *revs;
	const char *path;

	/*
	 * The contents in the final image.
	 * Used by many functions to obtain contents of the nth line,
	 * indexed with scoreboard.lineno[blame_entry.lno].
	 */
	const char *final_buf;
	unsigned long final_buf_size;

	/* linked list of blames */
	struct blame_entry *ent;

	/* look-up a line in the final buffer */
	int num_lines;
	int *lineno;
};

static inline int same_suspect(struct origin *a, struct origin *b)
{
	if (a == b)
		return 1;
	if (a->commit != b->commit)
		return 0;
	return !strcmp(a->path, b->path);
}

static void sanity_check_refcnt(struct scoreboard *);

/*
 * If two blame entries that are next to each other came from
 * contiguous lines in the same origin (i.e. <commit, path> pair),
 * merge them together.
 */
static void coalesce(struct scoreboard *sb)
{
	struct blame_entry *ent, *next;

	for (ent = sb->ent; ent && (next = ent->next); ent = next) {
		if (same_suspect(ent->suspect, next->suspect) &&
		    ent->guilty == next->guilty &&
		    ent->s_lno + ent->num_lines == next->s_lno) {
			ent->num_lines += next->num_lines;
			ent->next = next->next;
			if (ent->next)
				ent->next->prev = ent;
			origin_decref(next->suspect);
			free(next);
			ent->score = 0;
			next = ent; /* again */
		}
	}

	if (DEBUG) /* sanity */
		sanity_check_refcnt(sb);
}

/*
 * Given a commit and a path in it, create a new origin structure.
 * The callers that add blame to the scoreboard should use
 * get_origin() to obtain shared, refcounted copy instead of calling
 * this function directly.
 */
static struct origin *make_origin(struct commit *commit, const char *path)
{
	struct origin *o;
	o = xcalloc(1, sizeof(*o) + strlen(path) + 1);
	o->commit = commit;
	o->refcnt = 1;
	strcpy(o->path, path);
	return o;
}

/*
 * Locate an existing origin or create a new one.
 */
static struct origin *get_origin(struct scoreboard *sb,
				 struct commit *commit,
				 const char *path)
{
	struct blame_entry *e;

	for (e = sb->ent; e; e = e->next) {
		if (e->suspect->commit == commit &&
		    !strcmp(e->suspect->path, path))
			return origin_incref(e->suspect);
	}
	return make_origin(commit, path);
}

/*
 * Fill the blob_sha1 field of an origin if it hasn't, so that later
 * call to fill_origin_blob() can use it to locate the data.  blob_sha1
 * for an origin is also used to pass the blame for the entire file to
 * the parent to detect the case where a child's blob is identical to
 * that of its parent's.
 */
static int fill_blob_sha1(struct origin *origin)
{
	unsigned mode;

	if (!is_null_sha1(origin->blob_sha1))
		return 0;
	if (get_tree_entry(origin->commit->object.sha1,
			   origin->path,
			   origin->blob_sha1, &mode))
		goto error_out;
	if (sha1_object_info(origin->blob_sha1, NULL) != OBJ_BLOB)
		goto error_out;
	return 0;
 error_out:
	hashclr(origin->blob_sha1);
	return -1;
}

/*
 * We have an origin -- check if the same path exists in the
 * parent and return an origin structure to represent it.
 */
static struct origin *find_origin(struct scoreboard *sb,
				  struct commit *parent,
				  struct origin *origin)
{
	struct origin *porigin = NULL;
	struct diff_options diff_opts;
	const char *paths[2];

	if (parent->util) {
		/*
		 * Each commit object can cache one origin in that
		 * commit.  This is a freestanding copy of origin and
		 * not refcounted.
		 */
		struct origin *cached = parent->util;
		if (!strcmp(cached->path, origin->path)) {
			/*
			 * The same path between origin and its parent
			 * without renaming -- the most common case.
			 */
			porigin = get_origin(sb, parent, cached->path);

			/*
			 * If the origin was newly created (i.e. get_origin
			 * would call make_origin if none is found in the
			 * scoreboard), it does not know the blob_sha1,
			 * so copy it.  Otherwise porigin was in the
			 * scoreboard and already knows blob_sha1.
			 */
			if (porigin->refcnt == 1)
				hashcpy(porigin->blob_sha1, cached->blob_sha1);
			return porigin;
		}
		/* otherwise it was not very useful; free it */
		free(parent->util);
		parent->util = NULL;
	}

	/* See if the origin->path is different between parent
	 * and origin first.  Most of the time they are the
	 * same and diff-tree is fairly efficient about this.
	 */
	diff_setup(&diff_opts);
	DIFF_OPT_SET(&diff_opts, RECURSIVE);
	diff_opts.detect_rename = 0;
	diff_opts.output_format = DIFF_FORMAT_NO_OUTPUT;
	paths[0] = origin->path;
	paths[1] = NULL;

	diff_tree_setup_paths(paths, &diff_opts);
	if (diff_setup_done(&diff_opts) < 0)
		die("diff-setup");

	if (is_null_sha1(origin->commit->object.sha1))
		do_diff_cache(parent->tree->object.sha1, &diff_opts);
	else
		diff_tree_sha1(parent->tree->object.sha1,
			       origin->commit->tree->object.sha1,
			       "", &diff_opts);
	diffcore_std(&diff_opts);

	/* It is either one entry that says "modified", or "created",
	 * or nothing.
	 */
	if (!diff_queued_diff.nr) {
		/* The path is the same as parent */
		porigin = get_origin(sb, parent, origin->path);
		hashcpy(porigin->blob_sha1, origin->blob_sha1);
	}
	else if (diff_queued_diff.nr != 1)
		die("internal error in blame::find_origin");
	else {
		struct diff_filepair *p = diff_queued_diff.queue[0];
		switch (p->status) {
		default:
			die("internal error in blame::find_origin (%c)",
			    p->status);
		case 'M':
			porigin = get_origin(sb, parent, origin->path);
			hashcpy(porigin->blob_sha1, p->one->sha1);
			break;
		case 'A':
		case 'T':
			/* Did not exist in parent, or type changed */
			break;
		}
	}
	diff_flush(&diff_opts);
	diff_tree_release_paths(&diff_opts);
	if (porigin) {
		/*
		 * Create a freestanding copy that is not part of
		 * the refcounted origin found in the scoreboard, and
		 * cache it in the commit.
		 */
		struct origin *cached;

		cached = make_origin(porigin->commit, porigin->path);
		hashcpy(cached->blob_sha1, porigin->blob_sha1);
		parent->util = cached;
	}
	return porigin;
}

/*
 * We have an origin -- find the path that corresponds to it in its
 * parent and return an origin structure to represent it.
 */
static struct origin *find_rename(struct scoreboard *sb,
				  struct commit *parent,
				  struct origin *origin)
{
	struct origin *porigin = NULL;
	struct diff_options diff_opts;
	int i;
	const char *paths[2];

	diff_setup(&diff_opts);
	DIFF_OPT_SET(&diff_opts, RECURSIVE);
	diff_opts.detect_rename = DIFF_DETECT_RENAME;
	diff_opts.output_format = DIFF_FORMAT_NO_OUTPUT;
	diff_opts.single_follow = origin->path;
	paths[0] = NULL;
	diff_tree_setup_paths(paths, &diff_opts);
	if (diff_setup_done(&diff_opts) < 0)
		die("diff-setup");

	if (is_null_sha1(origin->commit->object.sha1))
		do_diff_cache(parent->tree->object.sha1, &diff_opts);
	else
		diff_tree_sha1(parent->tree->object.sha1,
			       origin->commit->tree->object.sha1,
			       "", &diff_opts);
	diffcore_std(&diff_opts);

	for (i = 0; i < diff_queued_diff.nr; i++) {
		struct diff_filepair *p = diff_queued_diff.queue[i];
		if ((p->status == 'R' || p->status == 'C') &&
		    !strcmp(p->two->path, origin->path)) {
			porigin = get_origin(sb, parent, p->one->path);
			hashcpy(porigin->blob_sha1, p->one->sha1);
			break;
		}
	}
	diff_flush(&diff_opts);
	diff_tree_release_paths(&diff_opts);
	return porigin;
}

/*
 * Parsing of patch chunks...
 */
struct chunk {
	/* line number in postimage; up to but not including this
	 * line is the same as preimage
	 */
	int same;

	/* preimage line number after this chunk */
	int p_next;

	/* postimage line number after this chunk */
	int t_next;
};

struct patch {
	struct chunk *chunks;
	int num;
};

struct blame_diff_state {
	struct xdiff_emit_state xm;
	struct patch *ret;
	unsigned hunk_post_context;
	unsigned hunk_in_pre_context : 1;
};

static void process_u_diff(void *state_, char *line, unsigned long len)
{
	struct blame_diff_state *state = state_;
	struct chunk *chunk;
	int off1, off2, len1, len2, num;

	num = state->ret->num;
	if (len < 4 || line[0] != '@' || line[1] != '@') {
		if (state->hunk_in_pre_context && line[0] == ' ')
			state->ret->chunks[num - 1].same++;
		else {
			state->hunk_in_pre_context = 0;
			if (line[0] == ' ')
				state->hunk_post_context++;
			else
				state->hunk_post_context = 0;
		}
		return;
	}

	if (num && state->hunk_post_context) {
		chunk = &state->ret->chunks[num - 1];
		chunk->p_next -= state->hunk_post_context;
		chunk->t_next -= state->hunk_post_context;
	}
	state->ret->num = ++num;
	state->ret->chunks = xrealloc(state->ret->chunks,
				      sizeof(struct chunk) * num);
	chunk = &state->ret->chunks[num - 1];
	if (parse_hunk_header(line, len, &off1, &len1, &off2, &len2)) {
		state->ret->num--;
		return;
	}

	/* Line numbers in patch output are one based. */
	off1--;
	off2--;

	chunk->same = len2 ? off2 : (off2 + 1);

	chunk->p_next = off1 + (len1 ? len1 : 1);
	chunk->t_next = chunk->same + len2;
	state->hunk_in_pre_context = 1;
	state->hunk_post_context = 0;
}

static struct patch *compare_buffer(mmfile_t *file_p, mmfile_t *file_o,
				    int context)
{
	struct blame_diff_state state;
	xpparam_t xpp;
	xdemitconf_t xecfg;
	xdemitcb_t ecb;

	xpp.flags = xdl_opts;
	memset(&xecfg, 0, sizeof(xecfg));
	xecfg.ctxlen = context;
	ecb.outf = xdiff_outf;
	ecb.priv = &state;
	memset(&state, 0, sizeof(state));
	state.xm.consume = process_u_diff;
	state.ret = xmalloc(sizeof(struct patch));
	state.ret->chunks = NULL;
	state.ret->num = 0;

	xdi_diff(file_p, file_o, &xpp, &xecfg, &ecb);

	if (state.ret->num) {
		struct chunk *chunk;
		chunk = &state.ret->chunks[state.ret->num - 1];
		chunk->p_next -= state.hunk_post_context;
		chunk->t_next -= state.hunk_post_context;
	}
	return state.ret;
}

/*
 * Run diff between two origins and grab the patch output, so that
 * we can pass blame for lines origin is currently suspected for
 * to its parent.
 */
static struct patch *get_patch(struct origin *parent, struct origin *origin)
{
	mmfile_t file_p, file_o;
	struct patch *patch;

	fill_origin_blob(parent, &file_p);
	fill_origin_blob(origin, &file_o);
	if (!file_p.ptr || !file_o.ptr)
		return NULL;
	patch = compare_buffer(&file_p, &file_o, 0);
	num_get_patch++;
	return patch;
}

static void free_patch(struct patch *p)
{
	free(p->chunks);
	free(p);
}

/*
 * Link in a new blame entry to the scoreboard.  Entries that cover the
 * same line range have been removed from the scoreboard previously.
 */
static void add_blame_entry(struct scoreboard *sb, struct blame_entry *e)
{
	struct blame_entry *ent, *prev = NULL;

	origin_incref(e->suspect);

	for (ent = sb->ent; ent && ent->lno < e->lno; ent = ent->next)
		prev = ent;

	/* prev, if not NULL, is the last one that is below e */
	e->prev = prev;
	if (prev) {
		e->next = prev->next;
		prev->next = e;
	}
	else {
		e->next = sb->ent;
		sb->ent = e;
	}
	if (e->next)
		e->next->prev = e;
}

/*
 * src typically is on-stack; we want to copy the information in it to
 * a malloced blame_entry that is already on the linked list of the
 * scoreboard.  The origin of dst loses a refcnt while the origin of src
 * gains one.
 */
static void dup_entry(struct blame_entry *dst, struct blame_entry *src)
{
	struct blame_entry *p, *n;

	p = dst->prev;
	n = dst->next;
	origin_incref(src->suspect);
	origin_decref(dst->suspect);
	memcpy(dst, src, sizeof(*src));
	dst->prev = p;
	dst->next = n;
	dst->score = 0;
}

static const char *nth_line(struct scoreboard *sb, int lno)
{
	return sb->final_buf + sb->lineno[lno];
}

/*
 * It is known that lines between tlno to same came from parent, and e
 * has an overlap with that range.  it also is known that parent's
 * line plno corresponds to e's line tlno.
 *
 *                <---- e ----->
 *                   <------>
 *                   <------------>
 *             <------------>
 *             <------------------>
 *
 * Split e into potentially three parts; before this chunk, the chunk
 * to be blamed for the parent, and after that portion.
 */
static void split_overlap(struct blame_entry *split,
			  struct blame_entry *e,
			  int tlno, int plno, int same,
			  struct origin *parent)
{
	int chunk_end_lno;
	memset(split, 0, sizeof(struct blame_entry [3]));

	if (e->s_lno < tlno) {
		/* there is a pre-chunk part not blamed on parent */
		split[0].suspect = origin_incref(e->suspect);
		split[0].lno = e->lno;
		split[0].s_lno = e->s_lno;
		split[0].num_lines = tlno - e->s_lno;
		split[1].lno = e->lno + tlno - e->s_lno;
		split[1].s_lno = plno;
	}
	else {
		split[1].lno = e->lno;
		split[1].s_lno = plno + (e->s_lno - tlno);
	}

	if (same < e->s_lno + e->num_lines) {
		/* there is a post-chunk part not blamed on parent */
		split[2].suspect = origin_incref(e->suspect);
		split[2].lno = e->lno + (same - e->s_lno);
		split[2].s_lno = e->s_lno + (same - e->s_lno);
		split[2].num_lines = e->s_lno + e->num_lines - same;
		chunk_end_lno = split[2].lno;
	}
	else
		chunk_end_lno = e->lno + e->num_lines;
	split[1].num_lines = chunk_end_lno - split[1].lno;

	/*
	 * if it turns out there is nothing to blame the parent for,
	 * forget about the splitting.  !split[1].suspect signals this.
	 */
	if (split[1].num_lines < 1)
		return;
	split[1].suspect = origin_incref(parent);
}

/*
 * split_overlap() divided an existing blame e into up to three parts
 * in split.  Adjust the linked list of blames in the scoreboard to
 * reflect the split.
 */
static void split_blame(struct scoreboard *sb,
			struct blame_entry *split,
			struct blame_entry *e)
{
	struct blame_entry *new_entry;

	if (split[0].suspect && split[2].suspect) {
		/* The first part (reuse storage for the existing entry e) */
		dup_entry(e, &split[0]);

		/* The last part -- me */
		new_entry = xmalloc(sizeof(*new_entry));
		memcpy(new_entry, &(split[2]), sizeof(struct blame_entry));
		add_blame_entry(sb, new_entry);

		/* ... and the middle part -- parent */
		new_entry = xmalloc(sizeof(*new_entry));
		memcpy(new_entry, &(split[1]), sizeof(struct blame_entry));
		add_blame_entry(sb, new_entry);
	}
	else if (!split[0].suspect && !split[2].suspect)
		/*
		 * The parent covers the entire area; reuse storage for
		 * e and replace it with the parent.
		 */
		dup_entry(e, &split[1]);
	else if (split[0].suspect) {
		/* me and then parent */
		dup_entry(e, &split[0]);

		new_entry = xmalloc(sizeof(*new_entry));
		memcpy(new_entry, &(split[1]), sizeof(struct blame_entry));
		add_blame_entry(sb, new_entry);
	}
	else {
		/* parent and then me */
		dup_entry(e, &split[1]);

		new_entry = xmalloc(sizeof(*new_entry));
		memcpy(new_entry, &(split[2]), sizeof(struct blame_entry));
		add_blame_entry(sb, new_entry);
	}

	if (DEBUG) { /* sanity */
		struct blame_entry *ent;
		int lno = sb->ent->lno, corrupt = 0;

		for (ent = sb->ent; ent; ent = ent->next) {
			if (lno != ent->lno)
				corrupt = 1;
			if (ent->s_lno < 0)
				corrupt = 1;
			lno += ent->num_lines;
		}
		if (corrupt) {
			lno = sb->ent->lno;
			for (ent = sb->ent; ent; ent = ent->next) {
				printf("L %8d l %8d n %8d\n",
				       lno, ent->lno, ent->num_lines);
				lno = ent->lno + ent->num_lines;
			}
			die("oops");
		}
	}
}

/*
 * After splitting the blame, the origins used by the
 * on-stack blame_entry should lose one refcnt each.
 */
static void decref_split(struct blame_entry *split)
{
	int i;

	for (i = 0; i < 3; i++)
		origin_decref(split[i].suspect);
}

/*
 * Helper for blame_chunk().  blame_entry e is known to overlap with
 * the patch hunk; split it and pass blame to the parent.
 */
static void blame_overlap(struct scoreboard *sb, struct blame_entry *e,
			  int tlno, int plno, int same,
			  struct origin *parent)
{
	struct blame_entry split[3];

	split_overlap(split, e, tlno, plno, same, parent);
	if (split[1].suspect)
		split_blame(sb, split, e);
	decref_split(split);
}

/*
 * Find the line number of the last line the target is suspected for.
 */
static int find_last_in_target(struct scoreboard *sb, struct origin *target)
{
	struct blame_entry *e;
	int last_in_target = -1;

	for (e = sb->ent; e; e = e->next) {
		if (e->guilty || !same_suspect(e->suspect, target))
			continue;
		if (last_in_target < e->s_lno + e->num_lines)
			last_in_target = e->s_lno + e->num_lines;
	}
	return last_in_target;
}

/*
 * Process one hunk from the patch between the current suspect for
 * blame_entry e and its parent.  Find and split the overlap, and
 * pass blame to the overlapping part to the parent.
 */
static void blame_chunk(struct scoreboard *sb,
			int tlno, int plno, int same,
			struct origin *target, struct origin *parent)
{
	struct blame_entry *e;

	for (e = sb->ent; e; e = e->next) {
		if (e->guilty || !same_suspect(e->suspect, target))
			continue;
		if (same <= e->s_lno)
			continue;
		if (tlno < e->s_lno + e->num_lines)
			blame_overlap(sb, e, tlno, plno, same, parent);
	}
}

/*
 * We are looking at the origin 'target' and aiming to pass blame
 * for the lines it is suspected to its parent.  Run diff to find
 * which lines came from parent and pass blame for them.
 */
static int pass_blame_to_parent(struct scoreboard *sb,
				struct origin *target,
				struct origin *parent)
{
	int i, last_in_target, plno, tlno;
	struct patch *patch;

	last_in_target = find_last_in_target(sb, target);
	if (last_in_target < 0)
		return 1; /* nothing remains for this target */

	patch = get_patch(parent, target);
	plno = tlno = 0;
	for (i = 0; i < patch->num; i++) {
		struct chunk *chunk = &patch->chunks[i];

		blame_chunk(sb, tlno, plno, chunk->same, target, parent);
		plno = chunk->p_next;
		tlno = chunk->t_next;
	}
	/* The rest (i.e. anything after tlno) are the same as the parent */
	blame_chunk(sb, tlno, plno, last_in_target, target, parent);

	free_patch(patch);
	return 0;
}

/*
 * The lines in blame_entry after splitting blames many times can become
 * very small and trivial, and at some point it becomes pointless to
 * blame the parents.  E.g. "\t\t}\n\t}\n\n" appears everywhere in any
 * ordinary C program, and it is not worth to say it was copied from
 * totally unrelated file in the parent.
 *
 * Compute how trivial the lines in the blame_entry are.
 */
static unsigned ent_score(struct scoreboard *sb, struct blame_entry *e)
{
	unsigned score;
	const char *cp, *ep;

	if (e->score)
		return e->score;

	score = 1;
	cp = nth_line(sb, e->lno);
	ep = nth_line(sb, e->lno + e->num_lines);
	while (cp < ep) {
		unsigned ch = *((unsigned char *)cp);
		if (isalnum(ch))
			score++;
		cp++;
	}
	e->score = score;
	return score;
}

/*
 * best_so_far[] and this[] are both a split of an existing blame_entry
 * that passes blame to the parent.  Maintain best_so_far the best split
 * so far, by comparing this and best_so_far and copying this into
 * bst_so_far as needed.
 */
static void copy_split_if_better(struct scoreboard *sb,
				 struct blame_entry *best_so_far,
				 struct blame_entry *this)
{
	int i;

	if (!this[1].suspect)
		return;
	if (best_so_far[1].suspect) {
		if (ent_score(sb, &this[1]) < ent_score(sb, &best_so_far[1]))
			return;
	}

	for (i = 0; i < 3; i++)
		origin_incref(this[i].suspect);
	decref_split(best_so_far);
	memcpy(best_so_far, this, sizeof(struct blame_entry [3]));
}

/*
 * We are looking at a part of the final image represented by
 * ent (tlno and same are offset by ent->s_lno).
 * tlno is where we are looking at in the final image.
 * up to (but not including) same match preimage.
 * plno is where we are looking at in the preimage.
 *
 * <-------------- final image ---------------------->
 *       <------ent------>
 *         ^tlno ^same
 *    <---------preimage----->
 *         ^plno
 *
 * All line numbers are 0-based.
 */
static void handle_split(struct scoreboard *sb,
			 struct blame_entry *ent,
			 int tlno, int plno, int same,
			 struct origin *parent,
			 struct blame_entry *split)
{
	if (ent->num_lines <= tlno)
		return;
	if (tlno < same) {
		struct blame_entry this[3];
		tlno += ent->s_lno;
		same += ent->s_lno;
		split_overlap(this, ent, tlno, plno, same, parent);
		copy_split_if_better(sb, split, this);
		decref_split(this);
	}
}

/*
 * Find the lines from parent that are the same as ent so that
 * we can pass blames to it.  file_p has the blob contents for
 * the parent.
 */
static void find_copy_in_blob(struct scoreboard *sb,
			      struct blame_entry *ent,
			      struct origin *parent,
			      struct blame_entry *split,
			      mmfile_t *file_p)
{
	const char *cp;
	int cnt;
	mmfile_t file_o;
	struct patch *patch;
	int i, plno, tlno;

	/*
	 * Prepare mmfile that contains only the lines in ent.
	 */
	cp = nth_line(sb, ent->lno);
	file_o.ptr = (char*) cp;
	cnt = ent->num_lines;

	while (cnt && cp < sb->final_buf + sb->final_buf_size) {
		if (*cp++ == '\n')
			cnt--;
	}
	file_o.size = cp - file_o.ptr;

	patch = compare_buffer(file_p, &file_o, 1);

	/*
	 * file_o is a part of final image we are annotating.
	 * file_p partially may match that image.
	 */
	memset(split, 0, sizeof(struct blame_entry [3]));
	plno = tlno = 0;
	for (i = 0; i < patch->num; i++) {
		struct chunk *chunk = &patch->chunks[i];

		handle_split(sb, ent, tlno, plno, chunk->same, parent, split);
		plno = chunk->p_next;
		tlno = chunk->t_next;
	}
	/* remainder, if any, all match the preimage */
	handle_split(sb, ent, tlno, plno, ent->num_lines, parent, split);
	free_patch(patch);
}

/*
 * See if lines currently target is suspected for can be attributed to
 * parent.
 */
static int find_move_in_parent(struct scoreboard *sb,
			       struct origin *target,
			       struct origin *parent)
{
	int last_in_target, made_progress;
	struct blame_entry *e, split[3];
	mmfile_t file_p;

	last_in_target = find_last_in_target(sb, target);
	if (last_in_target < 0)
		return 1; /* nothing remains for this target */

	fill_origin_blob(parent, &file_p);
	if (!file_p.ptr)
		return 0;

	made_progress = 1;
	while (made_progress) {
		made_progress = 0;
		for (e = sb->ent; e; e = e->next) {
			if (e->guilty || !same_suspect(e->suspect, target) ||
			    ent_score(sb, e) < blame_move_score)
				continue;
			find_copy_in_blob(sb, e, parent, split, &file_p);
			if (split[1].suspect &&
			    blame_move_score < ent_score(sb, &split[1])) {
				split_blame(sb, split, e);
				made_progress = 1;
			}
			decref_split(split);
		}
	}
	return 0;
}

struct blame_list {
	struct blame_entry *ent;
	struct blame_entry split[3];
};

/*
 * Count the number of entries the target is suspected for,
 * and prepare a list of entry and the best split.
 */
static struct blame_list *setup_blame_list(struct scoreboard *sb,
					   struct origin *target,
					   int min_score,
					   int *num_ents_p)
{
	struct blame_entry *e;
	int num_ents, i;
	struct blame_list *blame_list = NULL;

	for (e = sb->ent, num_ents = 0; e; e = e->next)
		if (!e->scanned && !e->guilty &&
		    same_suspect(e->suspect, target) &&
		    min_score < ent_score(sb, e))
			num_ents++;
	if (num_ents) {
		blame_list = xcalloc(num_ents, sizeof(struct blame_list));
		for (e = sb->ent, i = 0; e; e = e->next)
			if (!e->scanned && !e->guilty &&
			    same_suspect(e->suspect, target) &&
			    min_score < ent_score(sb, e))
				blame_list[i++].ent = e;
	}
	*num_ents_p = num_ents;
	return blame_list;
}

/*
 * Reset the scanned status on all entries.
 */
static void reset_scanned_flag(struct scoreboard *sb)
{
	struct blame_entry *e;
	for (e = sb->ent; e; e = e->next)
		e->scanned = 0;
}

/*
 * For lines target is suspected for, see if we can find code movement
 * across file boundary from the parent commit.  porigin is the path
 * in the parent we already tried.
 */
static int find_copy_in_parent(struct scoreboard *sb,
			       struct origin *target,
			       struct commit *parent,
			       struct origin *porigin,
			       int opt)
{
	struct diff_options diff_opts;
	const char *paths[1];
	int i, j;
	int retval;
	struct blame_list *blame_list;
	int num_ents;

	blame_list = setup_blame_list(sb, target, blame_copy_score, &num_ents);
	if (!blame_list)
		return 1; /* nothing remains for this target */

	diff_setup(&diff_opts);
	DIFF_OPT_SET(&diff_opts, RECURSIVE);
	diff_opts.output_format = DIFF_FORMAT_NO_OUTPUT;

	paths[0] = NULL;
	diff_tree_setup_paths(paths, &diff_opts);
	if (diff_setup_done(&diff_opts) < 0)
		die("diff-setup");

	/* Try "find copies harder" on new path if requested;
	 * we do not want to use diffcore_rename() actually to
	 * match things up; find_copies_harder is set only to
	 * force diff_tree_sha1() to feed all filepairs to diff_queue,
	 * and this code needs to be after diff_setup_done(), which
	 * usually makes find-copies-harder imply copy detection.
	 */
	if ((opt & PICKAXE_BLAME_COPY_HARDEST)
	    || ((opt & PICKAXE_BLAME_COPY_HARDER)
		&& (!porigin || strcmp(target->path, porigin->path))))
		DIFF_OPT_SET(&diff_opts, FIND_COPIES_HARDER);

	if (is_null_sha1(target->commit->object.sha1))
		do_diff_cache(parent->tree->object.sha1, &diff_opts);
	else
		diff_tree_sha1(parent->tree->object.sha1,
			       target->commit->tree->object.sha1,
			       "", &diff_opts);

	if (!DIFF_OPT_TST(&diff_opts, FIND_COPIES_HARDER))
		diffcore_std(&diff_opts);

	retval = 0;
	while (1) {
		int made_progress = 0;

		for (i = 0; i < diff_queued_diff.nr; i++) {
			struct diff_filepair *p = diff_queued_diff.queue[i];
			struct origin *norigin;
			mmfile_t file_p;
			struct blame_entry this[3];

			if (!DIFF_FILE_VALID(p->one))
				continue; /* does not exist in parent */
			if (S_ISGITLINK(p->one->mode))
				continue; /* ignore git links */
			if (porigin && !strcmp(p->one->path, porigin->path))
				/* find_move already dealt with this path */
				continue;

			norigin = get_origin(sb, parent, p->one->path);
			hashcpy(norigin->blob_sha1, p->one->sha1);
			fill_origin_blob(norigin, &file_p);
			if (!file_p.ptr)
				continue;

			for (j = 0; j < num_ents; j++) {
				find_copy_in_blob(sb, blame_list[j].ent,
						  norigin, this, &file_p);
				copy_split_if_better(sb, blame_list[j].split,
						     this);
				decref_split(this);
			}
			origin_decref(norigin);
		}

		for (j = 0; j < num_ents; j++) {
			struct blame_entry *split = blame_list[j].split;
			if (split[1].suspect &&
			    blame_copy_score < ent_score(sb, &split[1])) {
				split_blame(sb, split, blame_list[j].ent);
				made_progress = 1;
			}
			else
				blame_list[j].ent->scanned = 1;
			decref_split(split);
		}
		free(blame_list);

		if (!made_progress)
			break;
		blame_list = setup_blame_list(sb, target, blame_copy_score, &num_ents);
		if (!blame_list) {
			retval = 1;
			break;
		}
	}
	reset_scanned_flag(sb);
	diff_flush(&diff_opts);
	diff_tree_release_paths(&diff_opts);
	return retval;
}

/*
 * The blobs of origin and porigin exactly match, so everything
 * origin is suspected for can be blamed on the parent.
 */
static void pass_whole_blame(struct scoreboard *sb,
			     struct origin *origin, struct origin *porigin)
{
	struct blame_entry *e;

	if (!porigin->file.ptr && origin->file.ptr) {
		/* Steal its file */
		porigin->file = origin->file;
		origin->file.ptr = NULL;
	}
	for (e = sb->ent; e; e = e->next) {
		if (!same_suspect(e->suspect, origin))
			continue;
		origin_incref(porigin);
		origin_decref(e->suspect);
		e->suspect = porigin;
	}
}

/*
 * We pass blame from the current commit to its parents.  We keep saying
 * "parent" (and "porigin"), but what we mean is to find scapegoat to
 * exonerate ourselves.
 */
static struct commit_list *first_scapegoat(struct rev_info *revs, struct commit *commit)
{
	if (!reverse)
		return commit->parents;
	return lookup_decoration(&revs->children, &commit->object);
}

static int num_scapegoats(struct rev_info *revs, struct commit *commit)
{
	int cnt;
	struct commit_list *l = first_scapegoat(revs, commit);
	for (cnt = 0; l; l = l->next)
		cnt++;
	return cnt;
}

#define MAXSG 16

static void pass_blame(struct scoreboard *sb, struct origin *origin, int opt)
{
	struct rev_info *revs = sb->revs;
	int i, pass, num_sg;
	struct commit *commit = origin->commit;
	struct commit_list *sg;
	struct origin *sg_buf[MAXSG];
	struct origin *porigin, **sg_origin = sg_buf;

	num_sg = num_scapegoats(revs, commit);
	if (!num_sg)
		goto finish;
	else if (num_sg < ARRAY_SIZE(sg_buf))
		memset(sg_buf, 0, sizeof(sg_buf));
	else
		sg_origin = xcalloc(num_sg, sizeof(*sg_origin));

	/*
	 * The first pass looks for unrenamed path to optimize for
	 * common cases, then we look for renames in the second pass.
	 */
	for (pass = 0; pass < 2; pass++) {
		struct origin *(*find)(struct scoreboard *,
				       struct commit *, struct origin *);
		find = pass ? find_rename : find_origin;

		for (i = 0, sg = first_scapegoat(revs, commit);
		     i < num_sg && sg;
		     sg = sg->next, i++) {
			struct commit *p = sg->item;
			int j, same;

			if (sg_origin[i])
				continue;
			if (parse_commit(p))
				continue;
			porigin = find(sb, p, origin);
			if (!porigin)
				continue;
			if (!hashcmp(porigin->blob_sha1, origin->blob_sha1)) {
				pass_whole_blame(sb, origin, porigin);
				origin_decref(porigin);
				goto finish;
			}
			for (j = same = 0; j < i; j++)
				if (sg_origin[j] &&
				    !hashcmp(sg_origin[j]->blob_sha1,
					     porigin->blob_sha1)) {
					same = 1;
					break;
				}
			if (!same)
				sg_origin[i] = porigin;
			else
				origin_decref(porigin);
		}
	}

	num_commits++;
	for (i = 0, sg = first_scapegoat(revs, commit);
	     i < num_sg && sg;
	     sg = sg->next, i++) {
		struct origin *porigin = sg_origin[i];
		if (!porigin)
			continue;
		if (pass_blame_to_parent(sb, origin, porigin))
			goto finish;
	}

	/*
	 * Optionally find moves in parents' files.
	 */
	if (opt & PICKAXE_BLAME_MOVE)
		for (i = 0, sg = first_scapegoat(revs, commit);
		     i < num_sg && sg;
		     sg = sg->next, i++) {
			struct origin *porigin = sg_origin[i];
			if (!porigin)
				continue;
			if (find_move_in_parent(sb, origin, porigin))
				goto finish;
		}

	/*
	 * Optionally find copies from parents' files.
	 */
	if (opt & PICKAXE_BLAME_COPY)
		for (i = 0, sg = first_scapegoat(revs, commit);
		     i < num_sg && sg;
		     sg = sg->next, i++) {
			struct origin *porigin = sg_origin[i];
			if (find_copy_in_parent(sb, origin, sg->item,
						porigin, opt))
				goto finish;
		}

 finish:
	for (i = 0; i < num_sg; i++) {
		if (sg_origin[i]) {
			drop_origin_blob(sg_origin[i]);
			origin_decref(sg_origin[i]);
		}
	}
	drop_origin_blob(origin);
	if (sg_buf != sg_origin)
		free(sg_origin);
}

/*
 * Information on commits, used for output.
 */
struct commit_info
{
	const char *author;
	const char *author_mail;
	unsigned long author_time;
	const char *author_tz;

	/* filled only when asked for details */
	const char *committer;
	const char *committer_mail;
	unsigned long committer_time;
	const char *committer_tz;

	const char *summary;
};

/*
 * Parse author/committer line in the commit object buffer
 */
static void get_ac_line(const char *inbuf, const char *what,
			int bufsz, char *person, const char **mail,
			unsigned long *time, const char **tz)
{
	int len, tzlen, maillen;
	char *tmp, *endp, *timepos;

	tmp = strstr(inbuf, what);
	if (!tmp)
		goto error_out;
	tmp += strlen(what);
	endp = strchr(tmp, '\n');
	if (!endp)
		len = strlen(tmp);
	else
		len = endp - tmp;
	if (bufsz <= len) {
	error_out:
		/* Ugh */
		*mail = *tz = "(unknown)";
		*time = 0;
		return;
	}
	memcpy(person, tmp, len);

	tmp = person;
	tmp += len;
	*tmp = 0;
	while (*tmp != ' ')
		tmp--;
	*tz = tmp+1;
	tzlen = (person+len)-(tmp+1);

	*tmp = 0;
	while (*tmp != ' ')
		tmp--;
	*time = strtoul(tmp, NULL, 10);
	timepos = tmp;

	*tmp = 0;
	while (*tmp != ' ')
		tmp--;
	*mail = tmp + 1;
	*tmp = 0;
	maillen = timepos - tmp;

	if (!mailmap.nr)
		return;

	/*
	 * mailmap expansion may make the name longer.
	 * make room by pushing stuff down.
	 */
	tmp = person + bufsz - (tzlen + 1);
	memmove(tmp, *tz, tzlen);
	tmp[tzlen] = 0;
	*tz = tmp;

	tmp = tmp - (maillen + 1);
	memmove(tmp, *mail, maillen);
	tmp[maillen] = 0;
	*mail = tmp;

	/*
	 * Now, convert e-mail using mailmap
	 */
	map_email(&mailmap, tmp + 1, person, tmp-person-1);
}

static void get_commit_info(struct commit *commit,
			    struct commit_info *ret,
			    int detailed)
{
	int len;
	char *tmp, *endp;
	static char author_buf[1024];
	static char committer_buf[1024];
	static char summary_buf[1024];

	/*
	 * We've operated without save_commit_buffer, so
	 * we now need to populate them for output.
	 */
	if (!commit->buffer) {
		enum object_type type;
		unsigned long size;
		commit->buffer =
			read_sha1_file(commit->object.sha1, &type, &size);
		if (!commit->buffer)
			die("Cannot read commit %s",
			    sha1_to_hex(commit->object.sha1));
	}
	ret->author = author_buf;
	get_ac_line(commit->buffer, "\nauthor ",
		    sizeof(author_buf), author_buf, &ret->author_mail,
		    &ret->author_time, &ret->author_tz);

	if (!detailed)
		return;

	ret->committer = committer_buf;
	get_ac_line(commit->buffer, "\ncommitter ",
		    sizeof(committer_buf), committer_buf, &ret->committer_mail,
		    &ret->committer_time, &ret->committer_tz);

	ret->summary = summary_buf;
	tmp = strstr(commit->buffer, "\n\n");
	if (!tmp) {
	error_out:
		sprintf(summary_buf, "(%s)", sha1_to_hex(commit->object.sha1));
		return;
	}
	tmp += 2;
	endp = strchr(tmp, '\n');
	if (!endp)
		endp = tmp + strlen(tmp);
	len = endp - tmp;
	if (len >= sizeof(summary_buf) || len == 0)
		goto error_out;
	memcpy(summary_buf, tmp, len);
	summary_buf[len] = 0;
}

/*
 * To allow LF and other nonportable characters in pathnames,
 * they are c-style quoted as needed.
 */
static void write_filename_info(const char *path)
{
	printf("filename ");
	write_name_quoted(path, stdout, '\n');
}

/*
 * The blame_entry is found to be guilty for the range.  Mark it
 * as such, and show it in incremental output.
 */
static void found_guilty_entry(struct blame_entry *ent)
{
	if (ent->guilty)
		return;
	ent->guilty = 1;
	if (incremental) {
		struct origin *suspect = ent->suspect;

		printf("%s %d %d %d\n",
		       sha1_to_hex(suspect->commit->object.sha1),
		       ent->s_lno + 1, ent->lno + 1, ent->num_lines);
		if (!(suspect->commit->object.flags & METAINFO_SHOWN)) {
			struct commit_info ci;
			suspect->commit->object.flags |= METAINFO_SHOWN;
			get_commit_info(suspect->commit, &ci, 1);
			printf("author %s\n", ci.author);
			printf("author-mail %s\n", ci.author_mail);
			printf("author-time %lu\n", ci.author_time);
			printf("author-tz %s\n", ci.author_tz);
			printf("committer %s\n", ci.committer);
			printf("committer-mail %s\n", ci.committer_mail);
			printf("committer-time %lu\n", ci.committer_time);
			printf("committer-tz %s\n", ci.committer_tz);
			printf("summary %s\n", ci.summary);
			if (suspect->commit->object.flags & UNINTERESTING)
				printf("boundary\n");
		}
		write_filename_info(suspect->path);
		maybe_flush_or_die(stdout, "stdout");
	}
}

/*
 * The main loop -- while the scoreboard has lines whose true origin
 * is still unknown, pick one blame_entry, and allow its current
 * suspect to pass blames to its parents.
 */
static void assign_blame(struct scoreboard *sb, int opt)
{
	struct rev_info *revs = sb->revs;

	while (1) {
		struct blame_entry *ent;
		struct commit *commit;
		struct origin *suspect = NULL;

		/* find one suspect to break down */
		for (ent = sb->ent; !suspect && ent; ent = ent->next)
			if (!ent->guilty)
				suspect = ent->suspect;
		if (!suspect)
			return; /* all done */

		/*
		 * We will use this suspect later in the loop,
		 * so hold onto it in the meantime.
		 */
		origin_incref(suspect);
		commit = suspect->commit;
		if (!commit->object.parsed)
			parse_commit(commit);
		if (reverse ||
		    (!(commit->object.flags & UNINTERESTING) &&
		     !(revs->max_age != -1 && commit->date < revs->max_age)))
			pass_blame(sb, suspect, opt);
		else {
			commit->object.flags |= UNINTERESTING;
			if (commit->object.parsed)
				mark_parents_uninteresting(commit);
		}
		/* treat root commit as boundary */
		if (!commit->parents && !show_root)
			commit->object.flags |= UNINTERESTING;

		/* Take responsibility for the remaining entries */
		for (ent = sb->ent; ent; ent = ent->next)
			if (same_suspect(ent->suspect, suspect))
				found_guilty_entry(ent);
		origin_decref(suspect);

		if (DEBUG) /* sanity */
			sanity_check_refcnt(sb);
	}
}

static const char *format_time(unsigned long time, const char *tz_str,
			       int show_raw_time)
{
	static char time_buf[128];
	time_t t = time;
	int minutes, tz;
	struct tm *tm;

	if (show_raw_time) {
		sprintf(time_buf, "%lu %s", time, tz_str);
		return time_buf;
	}

	tz = atoi(tz_str);
	minutes = tz < 0 ? -tz : tz;
	minutes = (minutes / 100)*60 + (minutes % 100);
	minutes = tz < 0 ? -minutes : minutes;
	t = time + minutes * 60;
	tm = gmtime(&t);

	strftime(time_buf, sizeof(time_buf), "%Y-%m-%d %H:%M:%S ", tm);
	strcat(time_buf, tz_str);
	return time_buf;
}

#define OUTPUT_ANNOTATE_COMPAT	001
#define OUTPUT_LONG_OBJECT_NAME	002
#define OUTPUT_RAW_TIMESTAMP	004
#define OUTPUT_PORCELAIN	010
#define OUTPUT_SHOW_NAME	020
#define OUTPUT_SHOW_NUMBER	040
#define OUTPUT_SHOW_SCORE      0100
#define OUTPUT_NO_AUTHOR       0200

static void emit_porcelain(struct scoreboard *sb, struct blame_entry *ent)
{
	int cnt;
	const char *cp;
	struct origin *suspect = ent->suspect;
	char hex[41];

	strcpy(hex, sha1_to_hex(suspect->commit->object.sha1));
	printf("%s%c%d %d %d\n",
	       hex,
	       ent->guilty ? ' ' : '*', // purely for debugging
	       ent->s_lno + 1,
	       ent->lno + 1,
	       ent->num_lines);
	if (!(suspect->commit->object.flags & METAINFO_SHOWN)) {
		struct commit_info ci;
		suspect->commit->object.flags |= METAINFO_SHOWN;
		get_commit_info(suspect->commit, &ci, 1);
		printf("author %s\n", ci.author);
		printf("author-mail %s\n", ci.author_mail);
		printf("author-time %lu\n", ci.author_time);
		printf("author-tz %s\n", ci.author_tz);
		printf("committer %s\n", ci.committer);
		printf("committer-mail %s\n", ci.committer_mail);
		printf("committer-time %lu\n", ci.committer_time);
		printf("committer-tz %s\n", ci.committer_tz);
		write_filename_info(suspect->path);
		printf("summary %s\n", ci.summary);
		if (suspect->commit->object.flags & UNINTERESTING)
			printf("boundary\n");
	}
	else if (suspect->commit->object.flags & MORE_THAN_ONE_PATH)
		write_filename_info(suspect->path);

	cp = nth_line(sb, ent->lno);
	for (cnt = 0; cnt < ent->num_lines; cnt++) {
		char ch;
		if (cnt)
			printf("%s %d %d\n", hex,
			       ent->s_lno + 1 + cnt,
			       ent->lno + 1 + cnt);
		putchar('\t');
		do {
			ch = *cp++;
			putchar(ch);
		} while (ch != '\n' &&
			 cp < sb->final_buf + sb->final_buf_size);
	}
}

static void emit_other(struct scoreboard *sb, struct blame_entry *ent, int opt)
{
	int cnt;
	const char *cp;
	struct origin *suspect = ent->suspect;
	struct commit_info ci;
	char hex[41];
	int show_raw_time = !!(opt & OUTPUT_RAW_TIMESTAMP);

	get_commit_info(suspect->commit, &ci, 1);
	strcpy(hex, sha1_to_hex(suspect->commit->object.sha1));

	cp = nth_line(sb, ent->lno);
	for (cnt = 0; cnt < ent->num_lines; cnt++) {
		char ch;
		int length = (opt & OUTPUT_LONG_OBJECT_NAME) ? 40 : 8;

		if (suspect->commit->object.flags & UNINTERESTING) {
			if (blank_boundary)
				memset(hex, ' ', length);
			else if (!(opt & OUTPUT_ANNOTATE_COMPAT)) {
				length--;
				putchar('^');
			}
		}

		printf("%.*s", length, hex);
		if (opt & OUTPUT_ANNOTATE_COMPAT)
			printf("\t(%10s\t%10s\t%d)", ci.author,
			       format_time(ci.author_time, ci.author_tz,
					   show_raw_time),
			       ent->lno + 1 + cnt);
		else {
			if (opt & OUTPUT_SHOW_SCORE)
				printf(" %*d %02d",
				       max_score_digits, ent->score,
				       ent->suspect->refcnt);
			if (opt & OUTPUT_SHOW_NAME)
				printf(" %-*.*s", longest_file, longest_file,
				       suspect->path);
			if (opt & OUTPUT_SHOW_NUMBER)
				printf(" %*d", max_orig_digits,
				       ent->s_lno + 1 + cnt);

			if (!(opt & OUTPUT_NO_AUTHOR))
				printf(" (%-*.*s %10s",
				       longest_author, longest_author,
				       ci.author,
				       format_time(ci.author_time,
						   ci.author_tz,
						   show_raw_time));
			printf(" %*d) ",
			       max_digits, ent->lno + 1 + cnt);
		}
		do {
			ch = *cp++;
			putchar(ch);
		} while (ch != '\n' &&
			 cp < sb->final_buf + sb->final_buf_size);
	}
}

static void output(struct scoreboard *sb, int option)
{
	struct blame_entry *ent;

	if (option & OUTPUT_PORCELAIN) {
		for (ent = sb->ent; ent; ent = ent->next) {
			struct blame_entry *oth;
			struct origin *suspect = ent->suspect;
			struct commit *commit = suspect->commit;
			if (commit->object.flags & MORE_THAN_ONE_PATH)
				continue;
			for (oth = ent->next; oth; oth = oth->next) {
				if ((oth->suspect->commit != commit) ||
				    !strcmp(oth->suspect->path, suspect->path))
					continue;
				commit->object.flags |= MORE_THAN_ONE_PATH;
				break;
			}
		}
	}

	for (ent = sb->ent; ent; ent = ent->next) {
		if (option & OUTPUT_PORCELAIN)
			emit_porcelain(sb, ent);
		else {
			emit_other(sb, ent, option);
		}
	}
}

/*
 * To allow quick access to the contents of nth line in the
 * final image, prepare an index in the scoreboard.
 */
static int prepare_lines(struct scoreboard *sb)
{
	const char *buf = sb->final_buf;
	unsigned long len = sb->final_buf_size;
	int num = 0, incomplete = 0, bol = 1;

	if (len && buf[len-1] != '\n')
		incomplete++; /* incomplete line at the end */
	while (len--) {
		if (bol) {
			sb->lineno = xrealloc(sb->lineno,
					      sizeof(int* ) * (num + 1));
			sb->lineno[num] = buf - sb->final_buf;
			bol = 0;
		}
		if (*buf++ == '\n') {
			num++;
			bol = 1;
		}
	}
	sb->lineno = xrealloc(sb->lineno,
			      sizeof(int* ) * (num + incomplete + 1));
	sb->lineno[num + incomplete] = buf - sb->final_buf;
	sb->num_lines = num + incomplete;
	return sb->num_lines;
}

/*
 * Add phony grafts for use with -S; this is primarily to
 * support git's cvsserver that wants to give a linear history
 * to its clients.
 */
static int read_ancestry(const char *graft_file)
{
	FILE *fp = fopen(graft_file, "r");
	char buf[1024];
	if (!fp)
		return -1;
	while (fgets(buf, sizeof(buf), fp)) {
		/* The format is just "Commit Parent1 Parent2 ...\n" */
		int len = strlen(buf);
		struct commit_graft *graft = read_graft_line(buf, len);
		if (graft)
			register_commit_graft(graft, 0);
	}
	fclose(fp);
	return 0;
}

/*
 * How many columns do we need to show line numbers in decimal?
 */
static int lineno_width(int lines)
{
	int i, width;

	for (width = 1, i = 10; i <= lines + 1; width++)
		i *= 10;
	return width;
}

/*
 * How many columns do we need to show line numbers, authors,
 * and filenames?
 */
static void find_alignment(struct scoreboard *sb, int *option)
{
	int longest_src_lines = 0;
	int longest_dst_lines = 0;
	unsigned largest_score = 0;
	struct blame_entry *e;

	for (e = sb->ent; e; e = e->next) {
		struct origin *suspect = e->suspect;
		struct commit_info ci;
		int num;

		if (strcmp(suspect->path, sb->path))
			*option |= OUTPUT_SHOW_NAME;
		num = strlen(suspect->path);
		if (longest_file < num)
			longest_file = num;
		if (!(suspect->commit->object.flags & METAINFO_SHOWN)) {
			suspect->commit->object.flags |= METAINFO_SHOWN;
			get_commit_info(suspect->commit, &ci, 1);
			num = strlen(ci.author);
			if (longest_author < num)
				longest_author = num;
		}
		num = e->s_lno + e->num_lines;
		if (longest_src_lines < num)
			longest_src_lines = num;
		num = e->lno + e->num_lines;
		if (longest_dst_lines < num)
			longest_dst_lines = num;
		if (largest_score < ent_score(sb, e))
			largest_score = ent_score(sb, e);
	}
	max_orig_digits = lineno_width(longest_src_lines);
	max_digits = lineno_width(longest_dst_lines);
	max_score_digits = lineno_width(largest_score);
}

/*
 * For debugging -- origin is refcounted, and this asserts that
 * we do not underflow.
 */
static void sanity_check_refcnt(struct scoreboard *sb)
{
	int baa = 0;
	struct blame_entry *ent;

	for (ent = sb->ent; ent; ent = ent->next) {
		/* Nobody should have zero or negative refcnt */
		if (ent->suspect->refcnt <= 0) {
			fprintf(stderr, "%s in %s has negative refcnt %d\n",
				ent->suspect->path,
				sha1_to_hex(ent->suspect->commit->object.sha1),
				ent->suspect->refcnt);
			baa = 1;
		}
	}
	for (ent = sb->ent; ent; ent = ent->next) {
		/* Mark the ones that haven't been checked */
		if (0 < ent->suspect->refcnt)
			ent->suspect->refcnt = -ent->suspect->refcnt;
	}
	for (ent = sb->ent; ent; ent = ent->next) {
		/*
		 * ... then pick each and see if they have the the
		 * correct refcnt.
		 */
		int found;
		struct blame_entry *e;
		struct origin *suspect = ent->suspect;

		if (0 < suspect->refcnt)
			continue;
		suspect->refcnt = -suspect->refcnt; /* Unmark */
		for (found = 0, e = sb->ent; e; e = e->next) {
			if (e->suspect != suspect)
				continue;
			found++;
		}
		if (suspect->refcnt != found) {
			fprintf(stderr, "%s in %s has refcnt %d, not %d\n",
				ent->suspect->path,
				sha1_to_hex(ent->suspect->commit->object.sha1),
				ent->suspect->refcnt, found);
			baa = 2;
		}
	}
	if (baa) {
		int opt = 0160;
		find_alignment(sb, &opt);
		output(sb, opt);
		die("Baa %d!", baa);
	}
}

/*
 * Used for the command line parsing; check if the path exists
 * in the working tree.
 */
static int has_string_in_work_tree(const char *path)
{
	struct stat st;
	return !lstat(path, &st);
}

static unsigned parse_score(const char *arg)
{
	char *end;
	unsigned long score = strtoul(arg, &end, 10);
	if (*end)
		return 0;
	return score;
}

static const char *add_prefix(const char *prefix, const char *path)
{
	return prefix_path(prefix, prefix ? strlen(prefix) : 0, path);
}

/*
 * Parsing of (comma separated) one item in the -L option
 */
static const char *parse_loc(const char *spec,
			     struct scoreboard *sb, long lno,
			     long begin, long *ret)
{
	char *term;
	const char *line;
	long num;
	int reg_error;
	regex_t regexp;
	regmatch_t match[1];

	/* Allow "-L <something>,+20" to mean starting at <something>
	 * for 20 lines, or "-L <something>,-5" for 5 lines ending at
	 * <something>.
	 */
	if (1 < begin && (spec[0] == '+' || spec[0] == '-')) {
		num = strtol(spec + 1, &term, 10);
		if (term != spec + 1) {
			if (spec[0] == '-')
				num = 0 - num;
			if (0 < num)
				*ret = begin + num - 2;
			else if (!num)
				*ret = begin;
			else
				*ret = begin + num;
			return term;
		}
		return spec;
	}
	num = strtol(spec, &term, 10);
	if (term != spec) {
		*ret = num;
		return term;
	}
	if (spec[0] != '/')
		return spec;

	/* it could be a regexp of form /.../ */
	for (term = (char*) spec + 1; *term && *term != '/'; term++) {
		if (*term == '\\')
			term++;
	}
	if (*term != '/')
		return spec;

	/* try [spec+1 .. term-1] as regexp */
	*term = 0;
	begin--; /* input is in human terms */
	line = nth_line(sb, begin);

	if (!(reg_error = regcomp(&regexp, spec + 1, REG_NEWLINE)) &&
	    !(reg_error = regexec(&regexp, line, 1, match, 0))) {
		const char *cp = line + match[0].rm_so;
		const char *nline;

		while (begin++ < lno) {
			nline = nth_line(sb, begin);
			if (line <= cp && cp < nline)
				break;
			line = nline;
		}
		*ret = begin;
		regfree(&regexp);
		*term++ = '/';
		return term;
	}
	else {
		char errbuf[1024];
		regerror(reg_error, &regexp, errbuf, 1024);
		die("-L parameter '%s': %s", spec + 1, errbuf);
	}
}

/*
 * Parsing of -L option
 */
static void prepare_blame_range(struct scoreboard *sb,
				const char *bottomtop,
				long lno,
				long *bottom, long *top)
{
	const char *term;

	term = parse_loc(bottomtop, sb, lno, 1, bottom);
	if (*term == ',') {
		term = parse_loc(term + 1, sb, lno, *bottom + 1, top);
		if (*term)
			usage(blame_usage);
	}
	if (*term)
		usage(blame_usage);
}

static int git_blame_config(const char *var, const char *value, void *cb)
{
	if (!strcmp(var, "blame.showroot")) {
		show_root = git_config_bool(var, value);
		return 0;
	}
	if (!strcmp(var, "blame.blankboundary")) {
		blank_boundary = git_config_bool(var, value);
		return 0;
	}
	return git_default_config(var, value, cb);
}

/*
 * Prepare a dummy commit that represents the work tree (or staged) item.
 * Note that annotating work tree item never works in the reverse.
 */
static struct commit *fake_working_tree_commit(const char *path, const char *contents_from)
{
	struct commit *commit;
	struct origin *origin;
	unsigned char head_sha1[20];
	struct strbuf buf;
	const char *ident;
	time_t now;
	int size, len;
	struct cache_entry *ce;
	unsigned mode;

	if (get_sha1("HEAD", head_sha1))
		die("No such ref: HEAD");

	time(&now);
	commit = xcalloc(1, sizeof(*commit));
	commit->parents = xcalloc(1, sizeof(*commit->parents));
	commit->parents->item = lookup_commit_reference(head_sha1);
	commit->object.parsed = 1;
	commit->date = now;
	commit->object.type = OBJ_COMMIT;

	origin = make_origin(commit, path);

	strbuf_init(&buf, 0);
	if (!contents_from || strcmp("-", contents_from)) {
		struct stat st;
		const char *read_from;
		unsigned long fin_size;

		if (contents_from) {
			if (stat(contents_from, &st) < 0)
				die("Cannot stat %s", contents_from);
			read_from = contents_from;
		}
		else {
			if (lstat(path, &st) < 0)
				die("Cannot lstat %s", path);
			read_from = path;
		}
		fin_size = xsize_t(st.st_size);
		mode = canon_mode(st.st_mode);
		switch (st.st_mode & S_IFMT) {
		case S_IFREG:
			if (strbuf_read_file(&buf, read_from, st.st_size) != st.st_size)
				die("cannot open or read %s", read_from);
			break;
		case S_IFLNK:
			if (readlink(read_from, buf.buf, buf.alloc) != fin_size)
				die("cannot readlink %s", read_from);
			buf.len = fin_size;
			break;
		default:
			die("unsupported file type %s", read_from);
		}
	}
	else {
		/* Reading from stdin */
		contents_from = "standard input";
		mode = 0;
		if (strbuf_read(&buf, 0, 0) < 0)
			die("read error %s from stdin", strerror(errno));
	}
	convert_to_git(path, buf.buf, buf.len, &buf, 0);
	origin->file.ptr = buf.buf;
	origin->file.size = buf.len;
	pretend_sha1_file(buf.buf, buf.len, OBJ_BLOB, origin->blob_sha1);
	commit->util = origin;

	/*
	 * Read the current index, replace the path entry with
	 * origin->blob_sha1 without mucking with its mode or type
	 * bits; we are not going to write this index out -- we just
	 * want to run "diff-index --cached".
	 */
	discard_cache();
	read_cache();

	len = strlen(path);
	if (!mode) {
		int pos = cache_name_pos(path, len);
		if (0 <= pos)
			mode = active_cache[pos]->ce_mode;
		else
			/* Let's not bother reading from HEAD tree */
			mode = S_IFREG | 0644;
	}
	size = cache_entry_size(len);
	ce = xcalloc(1, size);
	hashcpy(ce->sha1, origin->blob_sha1);
	memcpy(ce->name, path, len);
	ce->ce_flags = create_ce_flags(len, 0);
	ce->ce_mode = create_ce_mode(mode);
	add_cache_entry(ce, ADD_CACHE_OK_TO_ADD|ADD_CACHE_OK_TO_REPLACE);

	/*
	 * We are not going to write this out, so this does not matter
	 * right now, but someday we might optimize diff-index --cached
	 * with cache-tree information.
	 */
	cache_tree_invalidate_path(active_cache_tree, path);

	commit->buffer = xmalloc(400);
	ident = fmt_ident("Not Committed Yet", "not.committed.yet", NULL, 0);
	snprintf(commit->buffer, 400,
		"tree 0000000000000000000000000000000000000000\n"
		"parent %s\n"
		"author %s\n"
		"committer %s\n\n"
		"Version of %s from %s\n",
		sha1_to_hex(head_sha1),
		ident, ident, path, contents_from ? contents_from : path);
	return commit;
}

static const char *prepare_final(struct scoreboard *sb)
{
	int i;
	const char *final_commit_name = NULL;
	struct rev_info *revs = sb->revs;

	/*
	 * There must be one and only one positive commit in the
	 * revs->pending array.
	 */
	for (i = 0; i < revs->pending.nr; i++) {
		struct object *obj = revs->pending.objects[i].item;
		if (obj->flags & UNINTERESTING)
			continue;
		while (obj->type == OBJ_TAG)
			obj = deref_tag(obj, NULL, 0);
		if (obj->type != OBJ_COMMIT)
			die("Non commit %s?", revs->pending.objects[i].name);
		if (sb->final)
			die("More than one commit to dig from %s and %s?",
			    revs->pending.objects[i].name,
			    final_commit_name);
		sb->final = (struct commit *) obj;
		final_commit_name = revs->pending.objects[i].name;
	}
	return final_commit_name;
}

static const char *prepare_initial(struct scoreboard *sb)
{
	int i;
	const char *final_commit_name = NULL;
	struct rev_info *revs = sb->revs;

	/*
	 * There must be one and only one negative commit, and it must be
	 * the boundary.
	 */
	for (i = 0; i < revs->pending.nr; i++) {
		struct object *obj = revs->pending.objects[i].item;
		if (!(obj->flags & UNINTERESTING))
			continue;
		while (obj->type == OBJ_TAG)
			obj = deref_tag(obj, NULL, 0);
		if (obj->type != OBJ_COMMIT)
			die("Non commit %s?", revs->pending.objects[i].name);
		if (sb->final)
			die("More than one commit to dig down to %s and %s?",
			    revs->pending.objects[i].name,
			    final_commit_name);
		sb->final = (struct commit *) obj;
		final_commit_name = revs->pending.objects[i].name;
	}
	if (!final_commit_name)
		die("No commit to dig down to?");
	return final_commit_name;
}

static int blame_copy_callback(const struct option *option, const char *arg, int unset)
{
	int *opt = option->value;

	/*
	 * -C enables copy from removed files;
	 * -C -C enables copy from existing files, but only
	 *       when blaming a new file;
	 * -C -C -C enables copy from existing files for
	 *          everybody
	 */
	if (*opt & PICKAXE_BLAME_COPY_HARDER)
		*opt |= PICKAXE_BLAME_COPY_HARDEST;
	if (*opt & PICKAXE_BLAME_COPY)
		*opt |= PICKAXE_BLAME_COPY_HARDER;
	*opt |= PICKAXE_BLAME_COPY | PICKAXE_BLAME_MOVE;

	if (arg)
		blame_copy_score = parse_score(arg);
	return 0;
}

static int blame_move_callback(const struct option *option, const char *arg, int unset)
{
	int *opt = option->value;

	*opt |= PICKAXE_BLAME_MOVE;

	if (arg)
		blame_move_score = parse_score(arg);
	return 0;
}

static int blame_bottomtop_callback(const struct option *option, const char *arg, int unset)
{
	const char **bottomtop = option->value;
	if (!arg)
		return -1;
	if (*bottomtop)
		die("More than one '-L n,m' option given");
	*bottomtop = arg;
	return 0;
}

int cmd_blame(int argc, const char **argv, const char *prefix)
{
	struct rev_info revs;
	const char *path;
	struct scoreboard sb;
	struct origin *o;
	struct blame_entry *ent;
	long dashdash_pos, bottom, top, lno;
	const char *final_commit_name = NULL;
	enum object_type type;

	static const char *bottomtop = NULL;
	static int output_option = 0, opt = 0;
	static int show_stats = 0;
	static const char *revs_file = NULL;
	static const char *contents_from = NULL;
	static const struct option options[] = {
		OPT_BOOLEAN(0, "incremental", &incremental, "Show blame entries as we find them, incrementally"),
		OPT_BOOLEAN('b', NULL, &blank_boundary, "Show blank SHA-1 for boundary commits (Default: off)"),
		OPT_BOOLEAN(0, "root", &show_root, "Do not treat root commits as boundaries (Default: off)"),
		OPT_BOOLEAN(0, "show-stats", &show_stats, "Show work cost statistics"),
		OPT_BIT(0, "score-debug", &output_option, "Show output score for blame entries", OUTPUT_SHOW_SCORE),
		OPT_BIT('f', "show-name", &output_option, "Show original filename (Default: auto)", OUTPUT_SHOW_NAME),
		OPT_BIT('n', "show-number", &output_option, "Show original linenumber (Default: off)", OUTPUT_SHOW_NUMBER),
		OPT_BIT('p', "porcelain", &output_option, "Show in a format designed for machine consumption", OUTPUT_PORCELAIN),
		OPT_BIT('c', NULL, &output_option, "Use the same output mode as git-annotate (Default: off)", OUTPUT_ANNOTATE_COMPAT),
		OPT_BIT('t', NULL, &output_option, "Show raw timestamp (Default: off)", OUTPUT_RAW_TIMESTAMP),
		OPT_BIT('l', NULL, &output_option, "Show long commit SHA1 (Default: off)", OUTPUT_LONG_OBJECT_NAME),
		OPT_BIT('s', NULL, &output_option, "Suppress author name and timestamp (Default: off)", OUTPUT_NO_AUTHOR),
		OPT_BIT('w', NULL, &xdl_opts, "Ignore whitespace differences", XDF_IGNORE_WHITESPACE),
		OPT_STRING('S', NULL, &revs_file, "file", "Use revisions from <file> instead of calling git-rev-list"),
		OPT_STRING(0, "contents", &contents_from, "file", "Use <file>'s contents as the final image"),
		{ OPTION_CALLBACK, 'C', NULL, &opt, "score", "Find line copies within and across files", PARSE_OPT_OPTARG, blame_copy_callback },
		{ OPTION_CALLBACK, 'M', NULL, &opt, "score", "Find line movements within and across files", PARSE_OPT_OPTARG, blame_move_callback },
		OPT_CALLBACK('L', NULL, &bottomtop, "n,m", "Process only line range n,m, counting from 1", blame_bottomtop_callback),
		OPT_END()
	};

	struct parse_opt_ctx_t ctx;
	int cmd_is_annotate = !strcmp(argv[0], "annotate");

	git_config(git_blame_config, NULL);
	init_revisions(&revs, NULL);
	save_commit_buffer = 0;
	dashdash_pos = 0;

	parse_options_start(&ctx, argc, argv, PARSE_OPT_KEEP_DASHDASH |
			    PARSE_OPT_KEEP_ARGV0);
	for (;;) {
		switch (parse_options_step(&ctx, options, blame_opt_usage)) {
		case PARSE_OPT_HELP:
			exit(129);
		case PARSE_OPT_DONE:
			if (ctx.argv[0])
				dashdash_pos = ctx.cpidx;
			goto parse_done;
		}

		if (!strcmp(ctx.argv[0], "--reverse")) {
			ctx.argv[0] = "--children";
			reverse = 1;
		}
		parse_revision_opt(&revs, &ctx, options, blame_opt_usage);
	}
parse_done:
	argc = parse_options_end(&ctx);

	if (cmd_is_annotate)
		output_option |= OUTPUT_ANNOTATE_COMPAT;

	if (DIFF_OPT_TST(&revs.diffopt, FIND_COPIES_HARDER))
		opt |= (PICKAXE_BLAME_COPY | PICKAXE_BLAME_MOVE |
			PICKAXE_BLAME_COPY_HARDER);

	if (!blame_move_score)
		blame_move_score = BLAME_DEFAULT_MOVE_SCORE;
	if (!blame_copy_score)
		blame_copy_score = BLAME_DEFAULT_COPY_SCORE;

	/*
	 * We have collected options unknown to us in argv[1..unk]
	 * which are to be passed to revision machinery if we are
	 * going to do the "bottom" processing.
	 *
	 * The remaining are:
	 *
	 * (1) if dashdash_pos != 0, its either
	 *     "blame [revisions] -- <path>" or
	 *     "blame -- <path> <rev>"
	 *
	 * (2) otherwise, its one of the two:
	 *     "blame [revisions] <path>"
	 *     "blame <path> <rev>"
	 *
	 * Note that we must strip out <path> from the arguments: we do not
	 * want the path pruning but we may want "bottom" processing.
	 */
	if (dashdash_pos) {
		switch (argc - dashdash_pos - 1) {
		case 2: /* (1b) */
			if (argc != 4)
				usage_with_options(blame_opt_usage, options);
			/* reorder for the new way: <rev> -- <path> */
			argv[1] = argv[3];
			argv[3] = argv[2];
			argv[2] = "--";
			/* FALLTHROUGH */
		case 1: /* (1a) */
			path = add_prefix(prefix, argv[--argc]);
			argv[argc] = NULL;
			break;
		default:
			usage_with_options(blame_opt_usage, options);
		}
	} else {
		if (argc < 2)
			usage_with_options(blame_opt_usage, options);
		path = add_prefix(prefix, argv[argc - 1]);
		if (argc == 3 && !has_string_in_work_tree(path)) { /* (2b) */
			path = add_prefix(prefix, argv[1]);
			argv[1] = argv[2];
		}
		argv[argc - 1] = "--";

		setup_work_tree();
		if (!has_string_in_work_tree(path))
			die("cannot stat path %s: %s", path, strerror(errno));
	}

	setup_revisions(argc, argv, &revs, NULL);
	memset(&sb, 0, sizeof(sb));

	sb.revs = &revs;
	if (!reverse)
		final_commit_name = prepare_final(&sb);
	else if (contents_from)
		die("--contents and --children do not blend well.");
	else
		final_commit_name = prepare_initial(&sb);

	if (!sb.final) {
		/*
		 * "--not A B -- path" without anything positive;
		 * do not default to HEAD, but use the working tree
		 * or "--contents".
		 */
		setup_work_tree();
		sb.final = fake_working_tree_commit(path, contents_from);
		add_pending_object(&revs, &(sb.final->object), ":");
	}
	else if (contents_from)
		die("Cannot use --contents with final commit object name");

	/*
	 * If we have bottom, this will mark the ancestors of the
	 * bottom commits we would reach while traversing as
	 * uninteresting.
	 */
	if (prepare_revision_walk(&revs))
		die("revision walk setup failed");

	if (is_null_sha1(sb.final->object.sha1)) {
		char *buf;
		o = sb.final->util;
		buf = xmalloc(o->file.size + 1);
		memcpy(buf, o->file.ptr, o->file.size + 1);
		sb.final_buf = buf;
		sb.final_buf_size = o->file.size;
	}
	else {
		o = get_origin(&sb, sb.final, path);
		if (fill_blob_sha1(o))
			die("no such path %s in %s", path, final_commit_name);

		sb.final_buf = read_sha1_file(o->blob_sha1, &type,
					      &sb.final_buf_size);
		if (!sb.final_buf)
			die("Cannot read blob %s for path %s",
			    sha1_to_hex(o->blob_sha1),
			    path);
	}
	num_read_blob++;
	lno = prepare_lines(&sb);

	bottom = top = 0;
	if (bottomtop)
		prepare_blame_range(&sb, bottomtop, lno, &bottom, &top);
	if (bottom && top && top < bottom) {
		long tmp;
		tmp = top; top = bottom; bottom = tmp;
	}
	if (bottom < 1)
		bottom = 1;
	if (top < 1)
		top = lno;
	bottom--;
	if (lno < top)
		die("file %s has only %lu lines", path, lno);

	ent = xcalloc(1, sizeof(*ent));
	ent->lno = bottom;
	ent->num_lines = top - bottom;
	ent->suspect = o;
	ent->s_lno = bottom;

	sb.ent = ent;
	sb.path = path;

	if (revs_file && read_ancestry(revs_file))
		die("reading graft file %s failed: %s",
		    revs_file, strerror(errno));

	read_mailmap(&mailmap, ".mailmap", NULL);

	if (!incremental)
		setup_pager();

	assign_blame(&sb, opt);

	if (incremental)
		return 0;

	coalesce(&sb);

	if (!(output_option & OUTPUT_PORCELAIN))
		find_alignment(&sb, &output_option);

	output(&sb, output_option);
	free((void *)sb.final_buf);
	for (ent = sb.ent; ent; ) {
		struct blame_entry *e = ent->next;
		free(ent);
		ent = e;
	}

	if (show_stats) {
		printf("num read blob: %d\n", num_read_blob);
		printf("num get patch: %d\n", num_get_patch);
		printf("num commits: %d\n", num_commits);
	}
	return 0;
}
Tip: Filter by directory path e.g. /media app.js to search for public/media/app.js.
Tip: Use camelCasing e.g. ProjME to search for ProjectModifiedEvent.java.
Tip: Filter by extension type e.g. /repo .js to search for all .js files in the /repo directory.
Tip: Separate your search with spaces e.g. /ssh pom.xml to search for src/ssh/pom.xml.
Tip: Use ↑ and ↓ arrow keys to navigate and return to view the file.
Tip: You can also navigate files with Ctrl+j (next) and Ctrl+k (previous) and view the file with Ctrl+o.
Tip: You can also navigate files with Alt+j (next) and Alt+k (previous) and view the file with Alt+o.