This file is indexed.

/usr/lib/python2.7/dist-packages/mercurial/patch.py is in mercurial-common 4.5.3-1ubuntu2.

This file is owned by root:root, with mode 0o644.

The actual contents of the file can be viewed below.

   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
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
# patch.py - patch file parsing routines
#
# Copyright 2006 Brendan Cully <brendan@kublai.com>
# Copyright 2007 Chris Mason <chris.mason@oracle.com>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.

from __future__ import absolute_import, print_function

import collections
import copy
import difflib
import email
import email.parser as emailparser
import errno
import hashlib
import os
import posixpath
import re
import shutil
import tempfile
import zlib

from .i18n import _
from .node import (
    hex,
    short,
)
from . import (
    copies,
    encoding,
    error,
    mail,
    mdiff,
    pathutil,
    policy,
    pycompat,
    scmutil,
    similar,
    util,
    vfs as vfsmod,
)

diffhelpers = policy.importmod(r'diffhelpers')
stringio = util.stringio

gitre = re.compile(br'diff --git a/(.*) b/(.*)')
tabsplitter = re.compile(br'(\t+|[^\t]+)')
_nonwordre = re.compile(br'([^a-zA-Z0-9_\x80-\xff])')

PatchError = error.PatchError

# public functions

def split(stream):
    '''return an iterator of individual patches from a stream'''
    def isheader(line, inheader):
        if inheader and line[0] in (' ', '\t'):
            # continuation
            return True
        if line[0] in (' ', '-', '+'):
            # diff line - don't check for header pattern in there
            return False
        l = line.split(': ', 1)
        return len(l) == 2 and ' ' not in l[0]

    def chunk(lines):
        return stringio(''.join(lines))

    def hgsplit(stream, cur):
        inheader = True

        for line in stream:
            if not line.strip():
                inheader = False
            if not inheader and line.startswith('# HG changeset patch'):
                yield chunk(cur)
                cur = []
                inheader = True

            cur.append(line)

        if cur:
            yield chunk(cur)

    def mboxsplit(stream, cur):
        for line in stream:
            if line.startswith('From '):
                for c in split(chunk(cur[1:])):
                    yield c
                cur = []

            cur.append(line)

        if cur:
            for c in split(chunk(cur[1:])):
                yield c

    def mimesplit(stream, cur):
        def msgfp(m):
            fp = stringio()
            g = email.Generator.Generator(fp, mangle_from_=False)
            g.flatten(m)
            fp.seek(0)
            return fp

        for line in stream:
            cur.append(line)
        c = chunk(cur)

        m = emailparser.Parser().parse(c)
        if not m.is_multipart():
            yield msgfp(m)
        else:
            ok_types = ('text/plain', 'text/x-diff', 'text/x-patch')
            for part in m.walk():
                ct = part.get_content_type()
                if ct not in ok_types:
                    continue
                yield msgfp(part)

    def headersplit(stream, cur):
        inheader = False

        for line in stream:
            if not inheader and isheader(line, inheader):
                yield chunk(cur)
                cur = []
                inheader = True
            if inheader and not isheader(line, inheader):
                inheader = False

            cur.append(line)

        if cur:
            yield chunk(cur)

    def remainder(cur):
        yield chunk(cur)

    class fiter(object):
        def __init__(self, fp):
            self.fp = fp

        def __iter__(self):
            return self

        def next(self):
            l = self.fp.readline()
            if not l:
                raise StopIteration
            return l

        __next__ = next

    inheader = False
    cur = []

    mimeheaders = ['content-type']

    if not util.safehasattr(stream, 'next'):
        # http responses, for example, have readline but not next
        stream = fiter(stream)

    for line in stream:
        cur.append(line)
        if line.startswith('# HG changeset patch'):
            return hgsplit(stream, cur)
        elif line.startswith('From '):
            return mboxsplit(stream, cur)
        elif isheader(line, inheader):
            inheader = True
            if line.split(':', 1)[0].lower() in mimeheaders:
                # let email parser handle this
                return mimesplit(stream, cur)
        elif line.startswith('--- ') and inheader:
            # No evil headers seen by diff start, split by hand
            return headersplit(stream, cur)
        # Not enough info, keep reading

    # if we are here, we have a very plain patch
    return remainder(cur)

## Some facility for extensible patch parsing:
# list of pairs ("header to match", "data key")
patchheadermap = [('Date', 'date'),
                  ('Branch', 'branch'),
                  ('Node ID', 'nodeid'),
                 ]

def extract(ui, fileobj):
    '''extract patch from data read from fileobj.

    patch can be a normal patch or contained in an email message.

    return a dictionary. Standard keys are:
      - filename,
      - message,
      - user,
      - date,
      - branch,
      - node,
      - p1,
      - p2.
    Any item can be missing from the dictionary. If filename is missing,
    fileobj did not contain a patch. Caller must unlink filename when done.'''

    # attempt to detect the start of a patch
    # (this heuristic is borrowed from quilt)
    diffre = re.compile(br'^(?:Index:[ \t]|diff[ \t]-|RCS file: |'
                        br'retrieving revision [0-9]+(\.[0-9]+)*$|'
                        br'---[ \t].*?^\+\+\+[ \t]|'
                        br'\*\*\*[ \t].*?^---[ \t])',
                        re.MULTILINE | re.DOTALL)

    data = {}
    fd, tmpname = tempfile.mkstemp(prefix='hg-patch-')
    tmpfp = os.fdopen(fd, pycompat.sysstr('w'))
    try:
        msg = emailparser.Parser().parse(fileobj)

        subject = msg['Subject'] and mail.headdecode(msg['Subject'])
        data['user'] = msg['From'] and mail.headdecode(msg['From'])
        if not subject and not data['user']:
            # Not an email, restore parsed headers if any
            subject = '\n'.join(': '.join(h) for h in msg.items()) + '\n'

        # should try to parse msg['Date']
        parents = []

        if subject:
            if subject.startswith('[PATCH'):
                pend = subject.find(']')
                if pend >= 0:
                    subject = subject[pend + 1:].lstrip()
            subject = re.sub(br'\n[ \t]+', ' ', subject)
            ui.debug('Subject: %s\n' % subject)
        if data['user']:
            ui.debug('From: %s\n' % data['user'])
        diffs_seen = 0
        ok_types = ('text/plain', 'text/x-diff', 'text/x-patch')
        message = ''
        for part in msg.walk():
            content_type = part.get_content_type()
            ui.debug('Content-Type: %s\n' % content_type)
            if content_type not in ok_types:
                continue
            payload = part.get_payload(decode=True)
            m = diffre.search(payload)
            if m:
                hgpatch = False
                hgpatchheader = False
                ignoretext = False

                ui.debug('found patch at byte %d\n' % m.start(0))
                diffs_seen += 1
                cfp = stringio()
                for line in payload[:m.start(0)].splitlines():
                    if line.startswith('# HG changeset patch') and not hgpatch:
                        ui.debug('patch generated by hg export\n')
                        hgpatch = True
                        hgpatchheader = True
                        # drop earlier commit message content
                        cfp.seek(0)
                        cfp.truncate()
                        subject = None
                    elif hgpatchheader:
                        if line.startswith('# User '):
                            data['user'] = line[7:]
                            ui.debug('From: %s\n' % data['user'])
                        elif line.startswith("# Parent "):
                            parents.append(line[9:].lstrip())
                        elif line.startswith("# "):
                            for header, key in patchheadermap:
                                prefix = '# %s ' % header
                                if line.startswith(prefix):
                                    data[key] = line[len(prefix):]
                        else:
                            hgpatchheader = False
                    elif line == '---':
                        ignoretext = True
                    if not hgpatchheader and not ignoretext:
                        cfp.write(line)
                        cfp.write('\n')
                message = cfp.getvalue()
                if tmpfp:
                    tmpfp.write(payload)
                    if not payload.endswith('\n'):
                        tmpfp.write('\n')
            elif not diffs_seen and message and content_type == 'text/plain':
                message += '\n' + payload
    except: # re-raises
        tmpfp.close()
        os.unlink(tmpname)
        raise

    if subject and not message.startswith(subject):
        message = '%s\n%s' % (subject, message)
    data['message'] = message
    tmpfp.close()
    if parents:
        data['p1'] = parents.pop(0)
        if parents:
            data['p2'] = parents.pop(0)

    if diffs_seen:
        data['filename'] = tmpname
    else:
        os.unlink(tmpname)
    return data

class patchmeta(object):
    """Patched file metadata

    'op' is the performed operation within ADD, DELETE, RENAME, MODIFY
    or COPY.  'path' is patched file path. 'oldpath' is set to the
    origin file when 'op' is either COPY or RENAME, None otherwise. If
    file mode is changed, 'mode' is a tuple (islink, isexec) where
    'islink' is True if the file is a symlink and 'isexec' is True if
    the file is executable. Otherwise, 'mode' is None.
    """
    def __init__(self, path):
        self.path = path
        self.oldpath = None
        self.mode = None
        self.op = 'MODIFY'
        self.binary = False

    def setmode(self, mode):
        islink = mode & 0o20000
        isexec = mode & 0o100
        self.mode = (islink, isexec)

    def copy(self):
        other = patchmeta(self.path)
        other.oldpath = self.oldpath
        other.mode = self.mode
        other.op = self.op
        other.binary = self.binary
        return other

    def _ispatchinga(self, afile):
        if afile == '/dev/null':
            return self.op == 'ADD'
        return afile == 'a/' + (self.oldpath or self.path)

    def _ispatchingb(self, bfile):
        if bfile == '/dev/null':
            return self.op == 'DELETE'
        return bfile == 'b/' + self.path

    def ispatching(self, afile, bfile):
        return self._ispatchinga(afile) and self._ispatchingb(bfile)

    def __repr__(self):
        return "<patchmeta %s %r>" % (self.op, self.path)

def readgitpatch(lr):
    """extract git-style metadata about patches from <patchname>"""

    # Filter patch for git information
    gp = None
    gitpatches = []
    for line in lr:
        line = line.rstrip(' \r\n')
        if line.startswith('diff --git a/'):
            m = gitre.match(line)
            if m:
                if gp:
                    gitpatches.append(gp)
                dst = m.group(2)
                gp = patchmeta(dst)
        elif gp:
            if line.startswith('--- '):
                gitpatches.append(gp)
                gp = None
                continue
            if line.startswith('rename from '):
                gp.op = 'RENAME'
                gp.oldpath = line[12:]
            elif line.startswith('rename to '):
                gp.path = line[10:]
            elif line.startswith('copy from '):
                gp.op = 'COPY'
                gp.oldpath = line[10:]
            elif line.startswith('copy to '):
                gp.path = line[8:]
            elif line.startswith('deleted file'):
                gp.op = 'DELETE'
            elif line.startswith('new file mode '):
                gp.op = 'ADD'
                gp.setmode(int(line[-6:], 8))
            elif line.startswith('new mode '):
                gp.setmode(int(line[-6:], 8))
            elif line.startswith('GIT binary patch'):
                gp.binary = True
    if gp:
        gitpatches.append(gp)

    return gitpatches

class linereader(object):
    # simple class to allow pushing lines back into the input stream
    def __init__(self, fp):
        self.fp = fp
        self.buf = []

    def push(self, line):
        if line is not None:
            self.buf.append(line)

    def readline(self):
        if self.buf:
            l = self.buf[0]
            del self.buf[0]
            return l
        return self.fp.readline()

    def __iter__(self):
        return iter(self.readline, '')

class abstractbackend(object):
    def __init__(self, ui):
        self.ui = ui

    def getfile(self, fname):
        """Return target file data and flags as a (data, (islink,
        isexec)) tuple. Data is None if file is missing/deleted.
        """
        raise NotImplementedError

    def setfile(self, fname, data, mode, copysource):
        """Write data to target file fname and set its mode. mode is a
        (islink, isexec) tuple. If data is None, the file content should
        be left unchanged. If the file is modified after being copied,
        copysource is set to the original file name.
        """
        raise NotImplementedError

    def unlink(self, fname):
        """Unlink target file."""
        raise NotImplementedError

    def writerej(self, fname, failed, total, lines):
        """Write rejected lines for fname. total is the number of hunks
        which failed to apply and total the total number of hunks for this
        files.
        """

    def exists(self, fname):
        raise NotImplementedError

    def close(self):
        raise NotImplementedError

class fsbackend(abstractbackend):
    def __init__(self, ui, basedir):
        super(fsbackend, self).__init__(ui)
        self.opener = vfsmod.vfs(basedir)

    def getfile(self, fname):
        if self.opener.islink(fname):
            return (self.opener.readlink(fname), (True, False))

        isexec = False
        try:
            isexec = self.opener.lstat(fname).st_mode & 0o100 != 0
        except OSError as e:
            if e.errno != errno.ENOENT:
                raise
        try:
            return (self.opener.read(fname), (False, isexec))
        except IOError as e:
            if e.errno != errno.ENOENT:
                raise
            return None, None

    def setfile(self, fname, data, mode, copysource):
        islink, isexec = mode
        if data is None:
            self.opener.setflags(fname, islink, isexec)
            return
        if islink:
            self.opener.symlink(data, fname)
        else:
            self.opener.write(fname, data)
            if isexec:
                self.opener.setflags(fname, False, True)

    def unlink(self, fname):
        self.opener.unlinkpath(fname, ignoremissing=True)

    def writerej(self, fname, failed, total, lines):
        fname = fname + ".rej"
        self.ui.warn(
            _("%d out of %d hunks FAILED -- saving rejects to file %s\n") %
            (failed, total, fname))
        fp = self.opener(fname, 'w')
        fp.writelines(lines)
        fp.close()

    def exists(self, fname):
        return self.opener.lexists(fname)

class workingbackend(fsbackend):
    def __init__(self, ui, repo, similarity):
        super(workingbackend, self).__init__(ui, repo.root)
        self.repo = repo
        self.similarity = similarity
        self.removed = set()
        self.changed = set()
        self.copied = []

    def _checkknown(self, fname):
        if self.repo.dirstate[fname] == '?' and self.exists(fname):
            raise PatchError(_('cannot patch %s: file is not tracked') % fname)

    def setfile(self, fname, data, mode, copysource):
        self._checkknown(fname)
        super(workingbackend, self).setfile(fname, data, mode, copysource)
        if copysource is not None:
            self.copied.append((copysource, fname))
        self.changed.add(fname)

    def unlink(self, fname):
        self._checkknown(fname)
        super(workingbackend, self).unlink(fname)
        self.removed.add(fname)
        self.changed.add(fname)

    def close(self):
        wctx = self.repo[None]
        changed = set(self.changed)
        for src, dst in self.copied:
            scmutil.dirstatecopy(self.ui, self.repo, wctx, src, dst)
        if self.removed:
            wctx.forget(sorted(self.removed))
            for f in self.removed:
                if f not in self.repo.dirstate:
                    # File was deleted and no longer belongs to the
                    # dirstate, it was probably marked added then
                    # deleted, and should not be considered by
                    # marktouched().
                    changed.discard(f)
        if changed:
            scmutil.marktouched(self.repo, changed, self.similarity)
        return sorted(self.changed)

class filestore(object):
    def __init__(self, maxsize=None):
        self.opener = None
        self.files = {}
        self.created = 0
        self.maxsize = maxsize
        if self.maxsize is None:
            self.maxsize = 4*(2**20)
        self.size = 0
        self.data = {}

    def setfile(self, fname, data, mode, copied=None):
        if self.maxsize < 0 or (len(data) + self.size) <= self.maxsize:
            self.data[fname] = (data, mode, copied)
            self.size += len(data)
        else:
            if self.opener is None:
                root = tempfile.mkdtemp(prefix='hg-patch-')
                self.opener = vfsmod.vfs(root)
            # Avoid filename issues with these simple names
            fn = str(self.created)
            self.opener.write(fn, data)
            self.created += 1
            self.files[fname] = (fn, mode, copied)

    def getfile(self, fname):
        if fname in self.data:
            return self.data[fname]
        if not self.opener or fname not in self.files:
            return None, None, None
        fn, mode, copied = self.files[fname]
        return self.opener.read(fn), mode, copied

    def close(self):
        if self.opener:
            shutil.rmtree(self.opener.base)

class repobackend(abstractbackend):
    def __init__(self, ui, repo, ctx, store):
        super(repobackend, self).__init__(ui)
        self.repo = repo
        self.ctx = ctx
        self.store = store
        self.changed = set()
        self.removed = set()
        self.copied = {}

    def _checkknown(self, fname):
        if fname not in self.ctx:
            raise PatchError(_('cannot patch %s: file is not tracked') % fname)

    def getfile(self, fname):
        try:
            fctx = self.ctx[fname]
        except error.LookupError:
            return None, None
        flags = fctx.flags()
        return fctx.data(), ('l' in flags, 'x' in flags)

    def setfile(self, fname, data, mode, copysource):
        if copysource:
            self._checkknown(copysource)
        if data is None:
            data = self.ctx[fname].data()
        self.store.setfile(fname, data, mode, copysource)
        self.changed.add(fname)
        if copysource:
            self.copied[fname] = copysource

    def unlink(self, fname):
        self._checkknown(fname)
        self.removed.add(fname)

    def exists(self, fname):
        return fname in self.ctx

    def close(self):
        return self.changed | self.removed

# @@ -start,len +start,len @@ or @@ -start +start @@ if len is 1
unidesc = re.compile('@@ -(\d+)(?:,(\d+))? \+(\d+)(?:,(\d+))? @@')
contextdesc = re.compile('(?:---|\*\*\*) (\d+)(?:,(\d+))? (?:---|\*\*\*)')
eolmodes = ['strict', 'crlf', 'lf', 'auto']

class patchfile(object):
    def __init__(self, ui, gp, backend, store, eolmode='strict'):
        self.fname = gp.path
        self.eolmode = eolmode
        self.eol = None
        self.backend = backend
        self.ui = ui
        self.lines = []
        self.exists = False
        self.missing = True
        self.mode = gp.mode
        self.copysource = gp.oldpath
        self.create = gp.op in ('ADD', 'COPY', 'RENAME')
        self.remove = gp.op == 'DELETE'
        if self.copysource is None:
            data, mode = backend.getfile(self.fname)
        else:
            data, mode = store.getfile(self.copysource)[:2]
        if data is not None:
            self.exists = self.copysource is None or backend.exists(self.fname)
            self.missing = False
            if data:
                self.lines = mdiff.splitnewlines(data)
            if self.mode is None:
                self.mode = mode
            if self.lines:
                # Normalize line endings
                if self.lines[0].endswith('\r\n'):
                    self.eol = '\r\n'
                elif self.lines[0].endswith('\n'):
                    self.eol = '\n'
                if eolmode != 'strict':
                    nlines = []
                    for l in self.lines:
                        if l.endswith('\r\n'):
                            l = l[:-2] + '\n'
                        nlines.append(l)
                    self.lines = nlines
        else:
            if self.create:
                self.missing = False
            if self.mode is None:
                self.mode = (False, False)
        if self.missing:
            self.ui.warn(_("unable to find '%s' for patching\n") % self.fname)
            self.ui.warn(_("(use '--prefix' to apply patch relative to the "
                           "current directory)\n"))

        self.hash = {}
        self.dirty = 0
        self.offset = 0
        self.skew = 0
        self.rej = []
        self.fileprinted = False
        self.printfile(False)
        self.hunks = 0

    def writelines(self, fname, lines, mode):
        if self.eolmode == 'auto':
            eol = self.eol
        elif self.eolmode == 'crlf':
            eol = '\r\n'
        else:
            eol = '\n'

        if self.eolmode != 'strict' and eol and eol != '\n':
            rawlines = []
            for l in lines:
                if l and l[-1] == '\n':
                    l = l[:-1] + eol
                rawlines.append(l)
            lines = rawlines

        self.backend.setfile(fname, ''.join(lines), mode, self.copysource)

    def printfile(self, warn):
        if self.fileprinted:
            return
        if warn or self.ui.verbose:
            self.fileprinted = True
        s = _("patching file %s\n") % self.fname
        if warn:
            self.ui.warn(s)
        else:
            self.ui.note(s)


    def findlines(self, l, linenum):
        # looks through the hash and finds candidate lines.  The
        # result is a list of line numbers sorted based on distance
        # from linenum

        cand = self.hash.get(l, [])
        if len(cand) > 1:
            # resort our list of potentials forward then back.
            cand.sort(key=lambda x: abs(x - linenum))
        return cand

    def write_rej(self):
        # our rejects are a little different from patch(1).  This always
        # creates rejects in the same form as the original patch.  A file
        # header is inserted so that you can run the reject through patch again
        # without having to type the filename.
        if not self.rej:
            return
        base = os.path.basename(self.fname)
        lines = ["--- %s\n+++ %s\n" % (base, base)]
        for x in self.rej:
            for l in x.hunk:
                lines.append(l)
                if l[-1:] != '\n':
                    lines.append("\n\ No newline at end of file\n")
        self.backend.writerej(self.fname, len(self.rej), self.hunks, lines)

    def apply(self, h):
        if not h.complete():
            raise PatchError(_("bad hunk #%d %s (%d %d %d %d)") %
                            (h.number, h.desc, len(h.a), h.lena, len(h.b),
                            h.lenb))

        self.hunks += 1

        if self.missing:
            self.rej.append(h)
            return -1

        if self.exists and self.create:
            if self.copysource:
                self.ui.warn(_("cannot create %s: destination already "
                               "exists\n") % self.fname)
            else:
                self.ui.warn(_("file %s already exists\n") % self.fname)
            self.rej.append(h)
            return -1

        if isinstance(h, binhunk):
            if self.remove:
                self.backend.unlink(self.fname)
            else:
                l = h.new(self.lines)
                self.lines[:] = l
                self.offset += len(l)
                self.dirty = True
            return 0

        horig = h
        if (self.eolmode in ('crlf', 'lf')
            or self.eolmode == 'auto' and self.eol):
            # If new eols are going to be normalized, then normalize
            # hunk data before patching. Otherwise, preserve input
            # line-endings.
            h = h.getnormalized()

        # fast case first, no offsets, no fuzz
        old, oldstart, new, newstart = h.fuzzit(0, False)
        oldstart += self.offset
        orig_start = oldstart
        # if there's skew we want to emit the "(offset %d lines)" even
        # when the hunk cleanly applies at start + skew, so skip the
        # fast case code
        if (self.skew == 0 and
            diffhelpers.testhunk(old, self.lines, oldstart) == 0):
            if self.remove:
                self.backend.unlink(self.fname)
            else:
                self.lines[oldstart:oldstart + len(old)] = new
                self.offset += len(new) - len(old)
                self.dirty = True
            return 0

        # ok, we couldn't match the hunk. Lets look for offsets and fuzz it
        self.hash = {}
        for x, s in enumerate(self.lines):
            self.hash.setdefault(s, []).append(x)

        for fuzzlen in xrange(self.ui.configint("patch", "fuzz") + 1):
            for toponly in [True, False]:
                old, oldstart, new, newstart = h.fuzzit(fuzzlen, toponly)
                oldstart = oldstart + self.offset + self.skew
                oldstart = min(oldstart, len(self.lines))
                if old:
                    cand = self.findlines(old[0][1:], oldstart)
                else:
                    # Only adding lines with no or fuzzed context, just
                    # take the skew in account
                    cand = [oldstart]

                for l in cand:
                    if not old or diffhelpers.testhunk(old, self.lines, l) == 0:
                        self.lines[l : l + len(old)] = new
                        self.offset += len(new) - len(old)
                        self.skew = l - orig_start
                        self.dirty = True
                        offset = l - orig_start - fuzzlen
                        if fuzzlen:
                            msg = _("Hunk #%d succeeded at %d "
                                    "with fuzz %d "
                                    "(offset %d lines).\n")
                            self.printfile(True)
                            self.ui.warn(msg %
                                (h.number, l + 1, fuzzlen, offset))
                        else:
                            msg = _("Hunk #%d succeeded at %d "
                                    "(offset %d lines).\n")
                            self.ui.note(msg % (h.number, l + 1, offset))
                        return fuzzlen
        self.printfile(True)
        self.ui.warn(_("Hunk #%d FAILED at %d\n") % (h.number, orig_start))
        self.rej.append(horig)
        return -1

    def close(self):
        if self.dirty:
            self.writelines(self.fname, self.lines, self.mode)
        self.write_rej()
        return len(self.rej)

class header(object):
    """patch header
    """
    diffgit_re = re.compile('diff --git a/(.*) b/(.*)$')
    diff_re = re.compile('diff -r .* (.*)$')
    allhunks_re = re.compile('(?:index|deleted file) ')
    pretty_re = re.compile('(?:new file|deleted file) ')
    special_re = re.compile('(?:index|deleted|copy|rename) ')
    newfile_re = re.compile('(?:new file)')

    def __init__(self, header):
        self.header = header
        self.hunks = []

    def binary(self):
        return any(h.startswith('index ') for h in self.header)

    def pretty(self, fp):
        for h in self.header:
            if h.startswith('index '):
                fp.write(_('this modifies a binary file (all or nothing)\n'))
                break
            if self.pretty_re.match(h):
                fp.write(h)
                if self.binary():
                    fp.write(_('this is a binary file\n'))
                break
            if h.startswith('---'):
                fp.write(_('%d hunks, %d lines changed\n') %
                         (len(self.hunks),
                          sum([max(h.added, h.removed) for h in self.hunks])))
                break
            fp.write(h)

    def write(self, fp):
        fp.write(''.join(self.header))

    def allhunks(self):
        return any(self.allhunks_re.match(h) for h in self.header)

    def files(self):
        match = self.diffgit_re.match(self.header[0])
        if match:
            fromfile, tofile = match.groups()
            if fromfile == tofile:
                return [fromfile]
            return [fromfile, tofile]
        else:
            return self.diff_re.match(self.header[0]).groups()

    def filename(self):
        return self.files()[-1]

    def __repr__(self):
        return '<header %s>' % (' '.join(map(repr, self.files())))

    def isnewfile(self):
        return any(self.newfile_re.match(h) for h in self.header)

    def special(self):
        # Special files are shown only at the header level and not at the hunk
        # level for example a file that has been deleted is a special file.
        # The user cannot change the content of the operation, in the case of
        # the deleted file he has to take the deletion or not take it, he
        # cannot take some of it.
        # Newly added files are special if they are empty, they are not special
        # if they have some content as we want to be able to change it
        nocontent = len(self.header) == 2
        emptynewfile = self.isnewfile() and nocontent
        return emptynewfile or \
                any(self.special_re.match(h) for h in self.header)

class recordhunk(object):
    """patch hunk

    XXX shouldn't we merge this with the other hunk class?
    """

    def __init__(self, header, fromline, toline, proc, before, hunk, after,
                 maxcontext=None):
        def trimcontext(lines, reverse=False):
            if maxcontext is not None:
                delta = len(lines) - maxcontext
                if delta > 0:
                    if reverse:
                        return delta, lines[delta:]
                    else:
                        return delta, lines[:maxcontext]
            return 0, lines

        self.header = header
        trimedbefore, self.before = trimcontext(before, True)
        self.fromline = fromline + trimedbefore
        self.toline = toline + trimedbefore
        _trimedafter, self.after = trimcontext(after, False)
        self.proc = proc
        self.hunk = hunk
        self.added, self.removed = self.countchanges(self.hunk)

    def __eq__(self, v):
        if not isinstance(v, recordhunk):
            return False

        return ((v.hunk == self.hunk) and
                (v.proc == self.proc) and
                (self.fromline == v.fromline) and
                (self.header.files() == v.header.files()))

    def __hash__(self):
        return hash((tuple(self.hunk),
            tuple(self.header.files()),
            self.fromline,
            self.proc))

    def countchanges(self, hunk):
        """hunk -> (n+,n-)"""
        add = len([h for h in hunk if h.startswith('+')])
        rem = len([h for h in hunk if h.startswith('-')])
        return add, rem

    def reversehunk(self):
        """return another recordhunk which is the reverse of the hunk

        If this hunk is diff(A, B), the returned hunk is diff(B, A). To do
        that, swap fromline/toline and +/- signs while keep other things
        unchanged.
        """
        m = {'+': '-', '-': '+', '\\': '\\'}
        hunk = ['%s%s' % (m[l[0:1]], l[1:]) for l in self.hunk]
        return recordhunk(self.header, self.toline, self.fromline, self.proc,
                          self.before, hunk, self.after)

    def write(self, fp):
        delta = len(self.before) + len(self.after)
        if self.after and self.after[-1] == '\\ No newline at end of file\n':
            delta -= 1
        fromlen = delta + self.removed
        tolen = delta + self.added
        fp.write('@@ -%d,%d +%d,%d @@%s\n' %
                 (self.fromline, fromlen, self.toline, tolen,
                  self.proc and (' ' + self.proc)))
        fp.write(''.join(self.before + self.hunk + self.after))

    pretty = write

    def filename(self):
        return self.header.filename()

    def __repr__(self):
        return '<hunk %r@%d>' % (self.filename(), self.fromline)

def getmessages():
    return {
        'multiple': {
            'apply': _("apply change %d/%d to '%s'?"),
            'discard': _("discard change %d/%d to '%s'?"),
            'record': _("record change %d/%d to '%s'?"),
        },
        'single': {
            'apply': _("apply this change to '%s'?"),
            'discard': _("discard this change to '%s'?"),
            'record': _("record this change to '%s'?"),
        },
        'help': {
            'apply': _('[Ynesfdaq?]'
                         '$$ &Yes, apply this change'
                         '$$ &No, skip this change'
                         '$$ &Edit this change manually'
                         '$$ &Skip remaining changes to this file'
                         '$$ Apply remaining changes to this &file'
                         '$$ &Done, skip remaining changes and files'
                         '$$ Apply &all changes to all remaining files'
                         '$$ &Quit, applying no changes'
                         '$$ &? (display help)'),
            'discard': _('[Ynesfdaq?]'
                         '$$ &Yes, discard this change'
                         '$$ &No, skip this change'
                         '$$ &Edit this change manually'
                         '$$ &Skip remaining changes to this file'
                         '$$ Discard remaining changes to this &file'
                         '$$ &Done, skip remaining changes and files'
                         '$$ Discard &all changes to all remaining files'
                         '$$ &Quit, discarding no changes'
                         '$$ &? (display help)'),
            'record': _('[Ynesfdaq?]'
                        '$$ &Yes, record this change'
                        '$$ &No, skip this change'
                        '$$ &Edit this change manually'
                        '$$ &Skip remaining changes to this file'
                        '$$ Record remaining changes to this &file'
                        '$$ &Done, skip remaining changes and files'
                        '$$ Record &all changes to all remaining files'
                        '$$ &Quit, recording no changes'
                        '$$ &? (display help)'),
        }
    }

def filterpatch(ui, headers, operation=None):
    """Interactively filter patch chunks into applied-only chunks"""
    messages = getmessages()

    if operation is None:
        operation = 'record'

    def prompt(skipfile, skipall, query, chunk):
        """prompt query, and process base inputs

        - y/n for the rest of file
        - y/n for the rest
        - ? (help)
        - q (quit)

        Return True/False and possibly updated skipfile and skipall.
        """
        newpatches = None
        if skipall is not None:
            return skipall, skipfile, skipall, newpatches
        if skipfile is not None:
            return skipfile, skipfile, skipall, newpatches
        while True:
            resps = messages['help'][operation]
            r = ui.promptchoice("%s %s" % (query, resps))
            ui.write("\n")
            if r == 8: # ?
                for c, t in ui.extractchoices(resps)[1]:
                    ui.write('%s - %s\n' % (c, encoding.lower(t)))
                continue
            elif r == 0: # yes
                ret = True
            elif r == 1: # no
                ret = False
            elif r == 2: # Edit patch
                if chunk is None:
                    ui.write(_('cannot edit patch for whole file'))
                    ui.write("\n")
                    continue
                if chunk.header.binary():
                    ui.write(_('cannot edit patch for binary file'))
                    ui.write("\n")
                    continue
                # Patch comment based on the Git one (based on comment at end of
                # https://mercurial-scm.org/wiki/RecordExtension)
                phelp = '---' + _("""
To remove '-' lines, make them ' ' lines (context).
To remove '+' lines, delete them.
Lines starting with # will be removed from the patch.

If the patch applies cleanly, the edited hunk will immediately be
added to the record list. If it does not apply cleanly, a rejects
file will be generated: you can use that when you try again. If
all lines of the hunk are removed, then the edit is aborted and
the hunk is left unchanged.
""")
                (patchfd, patchfn) = tempfile.mkstemp(prefix="hg-editor-",
                        suffix=".diff", text=True)
                ncpatchfp = None
                try:
                    # Write the initial patch
                    f = os.fdopen(patchfd, pycompat.sysstr("w"))
                    chunk.header.write(f)
                    chunk.write(f)
                    f.write('\n'.join(['# ' + i for i in phelp.splitlines()]))
                    f.close()
                    # Start the editor and wait for it to complete
                    editor = ui.geteditor()
                    ret = ui.system("%s \"%s\"" % (editor, patchfn),
                                    environ={'HGUSER': ui.username()},
                                    blockedtag='filterpatch')
                    if ret != 0:
                        ui.warn(_("editor exited with exit code %d\n") % ret)
                        continue
                    # Remove comment lines
                    patchfp = open(patchfn)
                    ncpatchfp = stringio()
                    for line in util.iterfile(patchfp):
                        if not line.startswith('#'):
                            ncpatchfp.write(line)
                    patchfp.close()
                    ncpatchfp.seek(0)
                    newpatches = parsepatch(ncpatchfp)
                finally:
                    os.unlink(patchfn)
                    del ncpatchfp
                # Signal that the chunk shouldn't be applied as-is, but
                # provide the new patch to be used instead.
                ret = False
            elif r == 3: # Skip
                ret = skipfile = False
            elif r == 4: # file (Record remaining)
                ret = skipfile = True
            elif r == 5: # done, skip remaining
                ret = skipall = False
            elif r == 6: # all
                ret = skipall = True
            elif r == 7: # quit
                raise error.Abort(_('user quit'))
            return ret, skipfile, skipall, newpatches

    seen = set()
    applied = {}        # 'filename' -> [] of chunks
    skipfile, skipall = None, None
    pos, total = 1, sum(len(h.hunks) for h in headers)
    for h in headers:
        pos += len(h.hunks)
        skipfile = None
        fixoffset = 0
        hdr = ''.join(h.header)
        if hdr in seen:
            continue
        seen.add(hdr)
        if skipall is None:
            h.pretty(ui)
        msg = (_('examine changes to %s?') %
               _(' and ').join("'%s'" % f for f in h.files()))
        r, skipfile, skipall, np = prompt(skipfile, skipall, msg, None)
        if not r:
            continue
        applied[h.filename()] = [h]
        if h.allhunks():
            applied[h.filename()] += h.hunks
            continue
        for i, chunk in enumerate(h.hunks):
            if skipfile is None and skipall is None:
                chunk.pretty(ui)
            if total == 1:
                msg = messages['single'][operation] % chunk.filename()
            else:
                idx = pos - len(h.hunks) + i
                msg = messages['multiple'][operation] % (idx, total,
                                                         chunk.filename())
            r, skipfile, skipall, newpatches = prompt(skipfile,
                    skipall, msg, chunk)
            if r:
                if fixoffset:
                    chunk = copy.copy(chunk)
                    chunk.toline += fixoffset
                applied[chunk.filename()].append(chunk)
            elif newpatches is not None:
                for newpatch in newpatches:
                    for newhunk in newpatch.hunks:
                        if fixoffset:
                            newhunk.toline += fixoffset
                        applied[newhunk.filename()].append(newhunk)
            else:
                fixoffset += chunk.removed - chunk.added
    return (sum([h for h in applied.itervalues()
               if h[0].special() or len(h) > 1], []), {})
class hunk(object):
    def __init__(self, desc, num, lr, context):
        self.number = num
        self.desc = desc
        self.hunk = [desc]
        self.a = []
        self.b = []
        self.starta = self.lena = None
        self.startb = self.lenb = None
        if lr is not None:
            if context:
                self.read_context_hunk(lr)
            else:
                self.read_unified_hunk(lr)

    def getnormalized(self):
        """Return a copy with line endings normalized to LF."""

        def normalize(lines):
            nlines = []
            for line in lines:
                if line.endswith('\r\n'):
                    line = line[:-2] + '\n'
                nlines.append(line)
            return nlines

        # Dummy object, it is rebuilt manually
        nh = hunk(self.desc, self.number, None, None)
        nh.number = self.number
        nh.desc = self.desc
        nh.hunk = self.hunk
        nh.a = normalize(self.a)
        nh.b = normalize(self.b)
        nh.starta = self.starta
        nh.startb = self.startb
        nh.lena = self.lena
        nh.lenb = self.lenb
        return nh

    def read_unified_hunk(self, lr):
        m = unidesc.match(self.desc)
        if not m:
            raise PatchError(_("bad hunk #%d") % self.number)
        self.starta, self.lena, self.startb, self.lenb = m.groups()
        if self.lena is None:
            self.lena = 1
        else:
            self.lena = int(self.lena)
        if self.lenb is None:
            self.lenb = 1
        else:
            self.lenb = int(self.lenb)
        self.starta = int(self.starta)
        self.startb = int(self.startb)
        diffhelpers.addlines(lr, self.hunk, self.lena, self.lenb, self.a,
                             self.b)
        # if we hit eof before finishing out the hunk, the last line will
        # be zero length.  Lets try to fix it up.
        while len(self.hunk[-1]) == 0:
            del self.hunk[-1]
            del self.a[-1]
            del self.b[-1]
            self.lena -= 1
            self.lenb -= 1
        self._fixnewline(lr)

    def read_context_hunk(self, lr):
        self.desc = lr.readline()
        m = contextdesc.match(self.desc)
        if not m:
            raise PatchError(_("bad hunk #%d") % self.number)
        self.starta, aend = m.groups()
        self.starta = int(self.starta)
        if aend is None:
            aend = self.starta
        self.lena = int(aend) - self.starta
        if self.starta:
            self.lena += 1
        for x in xrange(self.lena):
            l = lr.readline()
            if l.startswith('---'):
                # lines addition, old block is empty
                lr.push(l)
                break
            s = l[2:]
            if l.startswith('- ') or l.startswith('! '):
                u = '-' + s
            elif l.startswith('  '):
                u = ' ' + s
            else:
                raise PatchError(_("bad hunk #%d old text line %d") %
                                 (self.number, x))
            self.a.append(u)
            self.hunk.append(u)

        l = lr.readline()
        if l.startswith('\ '):
            s = self.a[-1][:-1]
            self.a[-1] = s
            self.hunk[-1] = s
            l = lr.readline()
        m = contextdesc.match(l)
        if not m:
            raise PatchError(_("bad hunk #%d") % self.number)
        self.startb, bend = m.groups()
        self.startb = int(self.startb)
        if bend is None:
            bend = self.startb
        self.lenb = int(bend) - self.startb
        if self.startb:
            self.lenb += 1
        hunki = 1
        for x in xrange(self.lenb):
            l = lr.readline()
            if l.startswith('\ '):
                # XXX: the only way to hit this is with an invalid line range.
                # The no-eol marker is not counted in the line range, but I
                # guess there are diff(1) out there which behave differently.
                s = self.b[-1][:-1]
                self.b[-1] = s
                self.hunk[hunki - 1] = s
                continue
            if not l:
                # line deletions, new block is empty and we hit EOF
                lr.push(l)
                break
            s = l[2:]
            if l.startswith('+ ') or l.startswith('! '):
                u = '+' + s
            elif l.startswith('  '):
                u = ' ' + s
            elif len(self.b) == 0:
                # line deletions, new block is empty
                lr.push(l)
                break
            else:
                raise PatchError(_("bad hunk #%d old text line %d") %
                                 (self.number, x))
            self.b.append(s)
            while True:
                if hunki >= len(self.hunk):
                    h = ""
                else:
                    h = self.hunk[hunki]
                hunki += 1
                if h == u:
                    break
                elif h.startswith('-'):
                    continue
                else:
                    self.hunk.insert(hunki - 1, u)
                    break

        if not self.a:
            # this happens when lines were only added to the hunk
            for x in self.hunk:
                if x.startswith('-') or x.startswith(' '):
                    self.a.append(x)
        if not self.b:
            # this happens when lines were only deleted from the hunk
            for x in self.hunk:
                if x.startswith('+') or x.startswith(' '):
                    self.b.append(x[1:])
        # @@ -start,len +start,len @@
        self.desc = "@@ -%d,%d +%d,%d @@\n" % (self.starta, self.lena,
                                             self.startb, self.lenb)
        self.hunk[0] = self.desc
        self._fixnewline(lr)

    def _fixnewline(self, lr):
        l = lr.readline()
        if l.startswith('\ '):
            diffhelpers.fix_newline(self.hunk, self.a, self.b)
        else:
            lr.push(l)

    def complete(self):
        return len(self.a) == self.lena and len(self.b) == self.lenb

    def _fuzzit(self, old, new, fuzz, toponly):
        # this removes context lines from the top and bottom of list 'l'.  It
        # checks the hunk to make sure only context lines are removed, and then
        # returns a new shortened list of lines.
        fuzz = min(fuzz, len(old))
        if fuzz:
            top = 0
            bot = 0
            hlen = len(self.hunk)
            for x in xrange(hlen - 1):
                # the hunk starts with the @@ line, so use x+1
                if self.hunk[x + 1][0] == ' ':
                    top += 1
                else:
                    break
            if not toponly:
                for x in xrange(hlen - 1):
                    if self.hunk[hlen - bot - 1][0] == ' ':
                        bot += 1
                    else:
                        break

            bot = min(fuzz, bot)
            top = min(fuzz, top)
            return old[top:len(old) - bot], new[top:len(new) - bot], top
        return old, new, 0

    def fuzzit(self, fuzz, toponly):
        old, new, top = self._fuzzit(self.a, self.b, fuzz, toponly)
        oldstart = self.starta + top
        newstart = self.startb + top
        # zero length hunk ranges already have their start decremented
        if self.lena and oldstart > 0:
            oldstart -= 1
        if self.lenb and newstart > 0:
            newstart -= 1
        return old, oldstart, new, newstart

class binhunk(object):
    'A binary patch file.'
    def __init__(self, lr, fname):
        self.text = None
        self.delta = False
        self.hunk = ['GIT binary patch\n']
        self._fname = fname
        self._read(lr)

    def complete(self):
        return self.text is not None

    def new(self, lines):
        if self.delta:
            return [applybindelta(self.text, ''.join(lines))]
        return [self.text]

    def _read(self, lr):
        def getline(lr, hunk):
            l = lr.readline()
            hunk.append(l)
            return l.rstrip('\r\n')

        size = 0
        while True:
            line = getline(lr, self.hunk)
            if not line:
                raise PatchError(_('could not extract "%s" binary data')
                                 % self._fname)
            if line.startswith('literal '):
                size = int(line[8:].rstrip())
                break
            if line.startswith('delta '):
                size = int(line[6:].rstrip())
                self.delta = True
                break
        dec = []
        line = getline(lr, self.hunk)
        while len(line) > 1:
            l = line[0]
            if l <= 'Z' and l >= 'A':
                l = ord(l) - ord('A') + 1
            else:
                l = ord(l) - ord('a') + 27
            try:
                dec.append(util.b85decode(line[1:])[:l])
            except ValueError as e:
                raise PatchError(_('could not decode "%s" binary patch: %s')
                                 % (self._fname, str(e)))
            line = getline(lr, self.hunk)
        text = zlib.decompress(''.join(dec))
        if len(text) != size:
            raise PatchError(_('"%s" length is %d bytes, should be %d')
                             % (self._fname, len(text), size))
        self.text = text

def parsefilename(str):
    # --- filename \t|space stuff
    s = str[4:].rstrip('\r\n')
    i = s.find('\t')
    if i < 0:
        i = s.find(' ')
        if i < 0:
            return s
    return s[:i]

def reversehunks(hunks):
    '''reverse the signs in the hunks given as argument

    This function operates on hunks coming out of patch.filterpatch, that is
    a list of the form: [header1, hunk1, hunk2, header2...]. Example usage:

    >>> rawpatch = b"""diff --git a/folder1/g b/folder1/g
    ... --- a/folder1/g
    ... +++ b/folder1/g
    ... @@ -1,7 +1,7 @@
    ... +firstline
    ...  c
    ...  1
    ...  2
    ... + 3
    ... -4
    ...  5
    ...  d
    ... +lastline"""
    >>> hunks = parsepatch([rawpatch])
    >>> hunkscomingfromfilterpatch = []
    >>> for h in hunks:
    ...     hunkscomingfromfilterpatch.append(h)
    ...     hunkscomingfromfilterpatch.extend(h.hunks)

    >>> reversedhunks = reversehunks(hunkscomingfromfilterpatch)
    >>> from . import util
    >>> fp = util.stringio()
    >>> for c in reversedhunks:
    ...      c.write(fp)
    >>> fp.seek(0) or None
    >>> reversedpatch = fp.read()
    >>> print(pycompat.sysstr(reversedpatch))
    diff --git a/folder1/g b/folder1/g
    --- a/folder1/g
    +++ b/folder1/g
    @@ -1,4 +1,3 @@
    -firstline
     c
     1
     2
    @@ -2,6 +1,6 @@
     c
     1
     2
    - 3
    +4
     5
     d
    @@ -6,3 +5,2 @@
     5
     d
    -lastline

    '''

    newhunks = []
    for c in hunks:
        if util.safehasattr(c, 'reversehunk'):
            c = c.reversehunk()
        newhunks.append(c)
    return newhunks

def parsepatch(originalchunks, maxcontext=None):
    """patch -> [] of headers -> [] of hunks

    If maxcontext is not None, trim context lines if necessary.

    >>> rawpatch = b'''diff --git a/folder1/g b/folder1/g
    ... --- a/folder1/g
    ... +++ b/folder1/g
    ... @@ -1,8 +1,10 @@
    ...  1
    ...  2
    ... -3
    ...  4
    ...  5
    ...  6
    ... +6.1
    ... +6.2
    ...  7
    ...  8
    ... +9'''
    >>> out = util.stringio()
    >>> headers = parsepatch([rawpatch], maxcontext=1)
    >>> for header in headers:
    ...     header.write(out)
    ...     for hunk in header.hunks:
    ...         hunk.write(out)
    >>> print(pycompat.sysstr(out.getvalue()))
    diff --git a/folder1/g b/folder1/g
    --- a/folder1/g
    +++ b/folder1/g
    @@ -2,3 +2,2 @@
     2
    -3
     4
    @@ -6,2 +5,4 @@
     6
    +6.1
    +6.2
     7
    @@ -8,1 +9,2 @@
     8
    +9
    """
    class parser(object):
        """patch parsing state machine"""
        def __init__(self):
            self.fromline = 0
            self.toline = 0
            self.proc = ''
            self.header = None
            self.context = []
            self.before = []
            self.hunk = []
            self.headers = []

        def addrange(self, limits):
            fromstart, fromend, tostart, toend, proc = limits
            self.fromline = int(fromstart)
            self.toline = int(tostart)
            self.proc = proc

        def addcontext(self, context):
            if self.hunk:
                h = recordhunk(self.header, self.fromline, self.toline,
                        self.proc, self.before, self.hunk, context, maxcontext)
                self.header.hunks.append(h)
                self.fromline += len(self.before) + h.removed
                self.toline += len(self.before) + h.added
                self.before = []
                self.hunk = []
            self.context = context

        def addhunk(self, hunk):
            if self.context:
                self.before = self.context
                self.context = []
            self.hunk = hunk

        def newfile(self, hdr):
            self.addcontext([])
            h = header(hdr)
            self.headers.append(h)
            self.header = h

        def addother(self, line):
            pass # 'other' lines are ignored

        def finished(self):
            self.addcontext([])
            return self.headers

        transitions = {
            'file': {'context': addcontext,
                     'file': newfile,
                     'hunk': addhunk,
                     'range': addrange},
            'context': {'file': newfile,
                        'hunk': addhunk,
                        'range': addrange,
                        'other': addother},
            'hunk': {'context': addcontext,
                     'file': newfile,
                     'range': addrange},
            'range': {'context': addcontext,
                      'hunk': addhunk},
            'other': {'other': addother},
            }

    p = parser()
    fp = stringio()
    fp.write(''.join(originalchunks))
    fp.seek(0)

    state = 'context'
    for newstate, data in scanpatch(fp):
        try:
            p.transitions[state][newstate](p, data)
        except KeyError:
            raise PatchError('unhandled transition: %s -> %s' %
                                   (state, newstate))
        state = newstate
    del fp
    return p.finished()

def pathtransform(path, strip, prefix):
    '''turn a path from a patch into a path suitable for the repository

    prefix, if not empty, is expected to be normalized with a / at the end.

    Returns (stripped components, path in repository).

    >>> pathtransform(b'a/b/c', 0, b'')
    ('', 'a/b/c')
    >>> pathtransform(b'   a/b/c   ', 0, b'')
    ('', '   a/b/c')
    >>> pathtransform(b'   a/b/c   ', 2, b'')
    ('a/b/', 'c')
    >>> pathtransform(b'a/b/c', 0, b'd/e/')
    ('', 'd/e/a/b/c')
    >>> pathtransform(b'   a//b/c   ', 2, b'd/e/')
    ('a//b/', 'd/e/c')
    >>> pathtransform(b'a/b/c', 3, b'')
    Traceback (most recent call last):
    PatchError: unable to strip away 1 of 3 dirs from a/b/c
    '''
    pathlen = len(path)
    i = 0
    if strip == 0:
        return '', prefix + path.rstrip()
    count = strip
    while count > 0:
        i = path.find('/', i)
        if i == -1:
            raise PatchError(_("unable to strip away %d of %d dirs from %s") %
                             (count, strip, path))
        i += 1
        # consume '//' in the path
        while i < pathlen - 1 and path[i:i + 1] == '/':
            i += 1
        count -= 1
    return path[:i].lstrip(), prefix + path[i:].rstrip()

def makepatchmeta(backend, afile_orig, bfile_orig, hunk, strip, prefix):
    nulla = afile_orig == "/dev/null"
    nullb = bfile_orig == "/dev/null"
    create = nulla and hunk.starta == 0 and hunk.lena == 0
    remove = nullb and hunk.startb == 0 and hunk.lenb == 0
    abase, afile = pathtransform(afile_orig, strip, prefix)
    gooda = not nulla and backend.exists(afile)
    bbase, bfile = pathtransform(bfile_orig, strip, prefix)
    if afile == bfile:
        goodb = gooda
    else:
        goodb = not nullb and backend.exists(bfile)
    missing = not goodb and not gooda and not create

    # some diff programs apparently produce patches where the afile is
    # not /dev/null, but afile starts with bfile
    abasedir = afile[:afile.rfind('/') + 1]
    bbasedir = bfile[:bfile.rfind('/') + 1]
    if (missing and abasedir == bbasedir and afile.startswith(bfile)
        and hunk.starta == 0 and hunk.lena == 0):
        create = True
        missing = False

    # If afile is "a/b/foo" and bfile is "a/b/foo.orig" we assume the
    # diff is between a file and its backup. In this case, the original
    # file should be patched (see original mpatch code).
    isbackup = (abase == bbase and bfile.startswith(afile))
    fname = None
    if not missing:
        if gooda and goodb:
            if isbackup:
                fname = afile
            else:
                fname = bfile
        elif gooda:
            fname = afile

    if not fname:
        if not nullb:
            if isbackup:
                fname = afile
            else:
                fname = bfile
        elif not nulla:
            fname = afile
        else:
            raise PatchError(_("undefined source and destination files"))

    gp = patchmeta(fname)
    if create:
        gp.op = 'ADD'
    elif remove:
        gp.op = 'DELETE'
    return gp

def scanpatch(fp):
    """like patch.iterhunks, but yield different events

    - ('file',    [header_lines + fromfile + tofile])
    - ('context', [context_lines])
    - ('hunk',    [hunk_lines])
    - ('range',   (-start,len, +start,len, proc))
    """
    lines_re = re.compile(br'@@ -(\d+),(\d+) \+(\d+),(\d+) @@\s*(.*)')
    lr = linereader(fp)

    def scanwhile(first, p):
        """scan lr while predicate holds"""
        lines = [first]
        for line in iter(lr.readline, ''):
            if p(line):
                lines.append(line)
            else:
                lr.push(line)
                break
        return lines

    for line in iter(lr.readline, ''):
        if line.startswith('diff --git a/') or line.startswith('diff -r '):
            def notheader(line):
                s = line.split(None, 1)
                return not s or s[0] not in ('---', 'diff')
            header = scanwhile(line, notheader)
            fromfile = lr.readline()
            if fromfile.startswith('---'):
                tofile = lr.readline()
                header += [fromfile, tofile]
            else:
                lr.push(fromfile)
            yield 'file', header
        elif line[0:1] == ' ':
            yield 'context', scanwhile(line, lambda l: l[0] in ' \\')
        elif line[0] in '-+':
            yield 'hunk', scanwhile(line, lambda l: l[0] in '-+\\')
        else:
            m = lines_re.match(line)
            if m:
                yield 'range', m.groups()
            else:
                yield 'other', line

def scangitpatch(lr, firstline):
    """
    Git patches can emit:
    - rename a to b
    - change b
    - copy a to c
    - change c

    We cannot apply this sequence as-is, the renamed 'a' could not be
    found for it would have been renamed already. And we cannot copy
    from 'b' instead because 'b' would have been changed already. So
    we scan the git patch for copy and rename commands so we can
    perform the copies ahead of time.
    """
    pos = 0
    try:
        pos = lr.fp.tell()
        fp = lr.fp
    except IOError:
        fp = stringio(lr.fp.read())
    gitlr = linereader(fp)
    gitlr.push(firstline)
    gitpatches = readgitpatch(gitlr)
    fp.seek(pos)
    return gitpatches

def iterhunks(fp):
    """Read a patch and yield the following events:
    - ("file", afile, bfile, firsthunk): select a new target file.
    - ("hunk", hunk): a new hunk is ready to be applied, follows a
    "file" event.
    - ("git", gitchanges): current diff is in git format, gitchanges
    maps filenames to gitpatch records. Unique event.
    """
    afile = ""
    bfile = ""
    state = None
    hunknum = 0
    emitfile = newfile = False
    gitpatches = None

    # our states
    BFILE = 1
    context = None
    lr = linereader(fp)

    for x in iter(lr.readline, ''):
        if state == BFILE and (
            (not context and x[0] == '@')
            or (context is not False and x.startswith('***************'))
            or x.startswith('GIT binary patch')):
            gp = None
            if (gitpatches and
                gitpatches[-1].ispatching(afile, bfile)):
                gp = gitpatches.pop()
            if x.startswith('GIT binary patch'):
                h = binhunk(lr, gp.path)
            else:
                if context is None and x.startswith('***************'):
                    context = True
                h = hunk(x, hunknum + 1, lr, context)
            hunknum += 1
            if emitfile:
                emitfile = False
                yield 'file', (afile, bfile, h, gp and gp.copy() or None)
            yield 'hunk', h
        elif x.startswith('diff --git a/'):
            m = gitre.match(x.rstrip(' \r\n'))
            if not m:
                continue
            if gitpatches is None:
                # scan whole input for git metadata
                gitpatches = scangitpatch(lr, x)
                yield 'git', [g.copy() for g in gitpatches
                              if g.op in ('COPY', 'RENAME')]
                gitpatches.reverse()
            afile = 'a/' + m.group(1)
            bfile = 'b/' + m.group(2)
            while gitpatches and not gitpatches[-1].ispatching(afile, bfile):
                gp = gitpatches.pop()
                yield 'file', ('a/' + gp.path, 'b/' + gp.path, None, gp.copy())
            if not gitpatches:
                raise PatchError(_('failed to synchronize metadata for "%s"')
                                 % afile[2:])
            gp = gitpatches[-1]
            newfile = True
        elif x.startswith('---'):
            # check for a unified diff
            l2 = lr.readline()
            if not l2.startswith('+++'):
                lr.push(l2)
                continue
            newfile = True
            context = False
            afile = parsefilename(x)
            bfile = parsefilename(l2)
        elif x.startswith('***'):
            # check for a context diff
            l2 = lr.readline()
            if not l2.startswith('---'):
                lr.push(l2)
                continue
            l3 = lr.readline()
            lr.push(l3)
            if not l3.startswith("***************"):
                lr.push(l2)
                continue
            newfile = True
            context = True
            afile = parsefilename(x)
            bfile = parsefilename(l2)

        if newfile:
            newfile = False
            emitfile = True
            state = BFILE
            hunknum = 0

    while gitpatches:
        gp = gitpatches.pop()
        yield 'file', ('a/' + gp.path, 'b/' + gp.path, None, gp.copy())

def applybindelta(binchunk, data):
    """Apply a binary delta hunk
    The algorithm used is the algorithm from git's patch-delta.c
    """
    def deltahead(binchunk):
        i = 0
        for c in binchunk:
            i += 1
            if not (ord(c) & 0x80):
                return i
        return i
    out = ""
    s = deltahead(binchunk)
    binchunk = binchunk[s:]
    s = deltahead(binchunk)
    binchunk = binchunk[s:]
    i = 0
    while i < len(binchunk):
        cmd = ord(binchunk[i])
        i += 1
        if (cmd & 0x80):
            offset = 0
            size = 0
            if (cmd & 0x01):
                offset = ord(binchunk[i])
                i += 1
            if (cmd & 0x02):
                offset |= ord(binchunk[i]) << 8
                i += 1
            if (cmd & 0x04):
                offset |= ord(binchunk[i]) << 16
                i += 1
            if (cmd & 0x08):
                offset |= ord(binchunk[i]) << 24
                i += 1
            if (cmd & 0x10):
                size = ord(binchunk[i])
                i += 1
            if (cmd & 0x20):
                size |= ord(binchunk[i]) << 8
                i += 1
            if (cmd & 0x40):
                size |= ord(binchunk[i]) << 16
                i += 1
            if size == 0:
                size = 0x10000
            offset_end = offset + size
            out += data[offset:offset_end]
        elif cmd != 0:
            offset_end = i + cmd
            out += binchunk[i:offset_end]
            i += cmd
        else:
            raise PatchError(_('unexpected delta opcode 0'))
    return out

def applydiff(ui, fp, backend, store, strip=1, prefix='', eolmode='strict'):
    """Reads a patch from fp and tries to apply it.

    Returns 0 for a clean patch, -1 if any rejects were found and 1 if
    there was any fuzz.

    If 'eolmode' is 'strict', the patch content and patched file are
    read in binary mode. Otherwise, line endings are ignored when
    patching then normalized according to 'eolmode'.
    """
    return _applydiff(ui, fp, patchfile, backend, store, strip=strip,
                      prefix=prefix, eolmode=eolmode)

def _canonprefix(repo, prefix):
    if prefix:
        prefix = pathutil.canonpath(repo.root, repo.getcwd(), prefix)
        if prefix != '':
            prefix += '/'
    return prefix

def _applydiff(ui, fp, patcher, backend, store, strip=1, prefix='',
               eolmode='strict'):
    prefix = _canonprefix(backend.repo, prefix)
    def pstrip(p):
        return pathtransform(p, strip - 1, prefix)[1]

    rejects = 0
    err = 0
    current_file = None

    for state, values in iterhunks(fp):
        if state == 'hunk':
            if not current_file:
                continue
            ret = current_file.apply(values)
            if ret > 0:
                err = 1
        elif state == 'file':
            if current_file:
                rejects += current_file.close()
                current_file = None
            afile, bfile, first_hunk, gp = values
            if gp:
                gp.path = pstrip(gp.path)
                if gp.oldpath:
                    gp.oldpath = pstrip(gp.oldpath)
            else:
                gp = makepatchmeta(backend, afile, bfile, first_hunk, strip,
                                   prefix)
            if gp.op == 'RENAME':
                backend.unlink(gp.oldpath)
            if not first_hunk:
                if gp.op == 'DELETE':
                    backend.unlink(gp.path)
                    continue
                data, mode = None, None
                if gp.op in ('RENAME', 'COPY'):
                    data, mode = store.getfile(gp.oldpath)[:2]
                    if data is None:
                        # This means that the old path does not exist
                        raise PatchError(_("source file '%s' does not exist")
                                           % gp.oldpath)
                if gp.mode:
                    mode = gp.mode
                    if gp.op == 'ADD':
                        # Added files without content have no hunk and
                        # must be created
                        data = ''
                if data or mode:
                    if (gp.op in ('ADD', 'RENAME', 'COPY')
                        and backend.exists(gp.path)):
                        raise PatchError(_("cannot create %s: destination "
                                           "already exists") % gp.path)
                    backend.setfile(gp.path, data, mode, gp.oldpath)
                continue
            try:
                current_file = patcher(ui, gp, backend, store,
                                       eolmode=eolmode)
            except PatchError as inst:
                ui.warn(str(inst) + '\n')
                current_file = None
                rejects += 1
                continue
        elif state == 'git':
            for gp in values:
                path = pstrip(gp.oldpath)
                data, mode = backend.getfile(path)
                if data is None:
                    # The error ignored here will trigger a getfile()
                    # error in a place more appropriate for error
                    # handling, and will not interrupt the patching
                    # process.
                    pass
                else:
                    store.setfile(path, data, mode)
        else:
            raise error.Abort(_('unsupported parser state: %s') % state)

    if current_file:
        rejects += current_file.close()

    if rejects:
        return -1
    return err

def _externalpatch(ui, repo, patcher, patchname, strip, files,
                   similarity):
    """use <patcher> to apply <patchname> to the working directory.
    returns whether patch was applied with fuzz factor."""

    fuzz = False
    args = []
    cwd = repo.root
    if cwd:
        args.append('-d %s' % util.shellquote(cwd))
    fp = util.popen('%s %s -p%d < %s' % (patcher, ' '.join(args), strip,
                                       util.shellquote(patchname)))
    try:
        for line in util.iterfile(fp):
            line = line.rstrip()
            ui.note(line + '\n')
            if line.startswith('patching file '):
                pf = util.parsepatchoutput(line)
                printed_file = False
                files.add(pf)
            elif line.find('with fuzz') >= 0:
                fuzz = True
                if not printed_file:
                    ui.warn(pf + '\n')
                    printed_file = True
                ui.warn(line + '\n')
            elif line.find('saving rejects to file') >= 0:
                ui.warn(line + '\n')
            elif line.find('FAILED') >= 0:
                if not printed_file:
                    ui.warn(pf + '\n')
                    printed_file = True
                ui.warn(line + '\n')
    finally:
        if files:
            scmutil.marktouched(repo, files, similarity)
    code = fp.close()
    if code:
        raise PatchError(_("patch command failed: %s") %
                         util.explainexit(code)[0])
    return fuzz

def patchbackend(ui, backend, patchobj, strip, prefix, files=None,
                 eolmode='strict'):
    if files is None:
        files = set()
    if eolmode is None:
        eolmode = ui.config('patch', 'eol')
    if eolmode.lower() not in eolmodes:
        raise error.Abort(_('unsupported line endings type: %s') % eolmode)
    eolmode = eolmode.lower()

    store = filestore()
    try:
        fp = open(patchobj, 'rb')
    except TypeError:
        fp = patchobj
    try:
        ret = applydiff(ui, fp, backend, store, strip=strip, prefix=prefix,
                        eolmode=eolmode)
    finally:
        if fp != patchobj:
            fp.close()
        files.update(backend.close())
        store.close()
    if ret < 0:
        raise PatchError(_('patch failed to apply'))
    return ret > 0

def internalpatch(ui, repo, patchobj, strip, prefix='', files=None,
                  eolmode='strict', similarity=0):
    """use builtin patch to apply <patchobj> to the working directory.
    returns whether patch was applied with fuzz factor."""
    backend = workingbackend(ui, repo, similarity)
    return patchbackend(ui, backend, patchobj, strip, prefix, files, eolmode)

def patchrepo(ui, repo, ctx, store, patchobj, strip, prefix, files=None,
              eolmode='strict'):
    backend = repobackend(ui, repo, ctx, store)
    return patchbackend(ui, backend, patchobj, strip, prefix, files, eolmode)

def patch(ui, repo, patchname, strip=1, prefix='', files=None, eolmode='strict',
          similarity=0):
    """Apply <patchname> to the working directory.

    'eolmode' specifies how end of lines should be handled. It can be:
    - 'strict': inputs are read in binary mode, EOLs are preserved
    - 'crlf': EOLs are ignored when patching and reset to CRLF
    - 'lf': EOLs are ignored when patching and reset to LF
    - None: get it from user settings, default to 'strict'
    'eolmode' is ignored when using an external patcher program.

    Returns whether patch was applied with fuzz factor.
    """
    patcher = ui.config('ui', 'patch')
    if files is None:
        files = set()
    if patcher:
        return _externalpatch(ui, repo, patcher, patchname, strip,
                              files, similarity)
    return internalpatch(ui, repo, patchname, strip, prefix, files, eolmode,
                         similarity)

def changedfiles(ui, repo, patchpath, strip=1, prefix=''):
    backend = fsbackend(ui, repo.root)
    prefix = _canonprefix(repo, prefix)
    with open(patchpath, 'rb') as fp:
        changed = set()
        for state, values in iterhunks(fp):
            if state == 'file':
                afile, bfile, first_hunk, gp = values
                if gp:
                    gp.path = pathtransform(gp.path, strip - 1, prefix)[1]
                    if gp.oldpath:
                        gp.oldpath = pathtransform(gp.oldpath, strip - 1,
                                                   prefix)[1]
                else:
                    gp = makepatchmeta(backend, afile, bfile, first_hunk, strip,
                                       prefix)
                changed.add(gp.path)
                if gp.op == 'RENAME':
                    changed.add(gp.oldpath)
            elif state not in ('hunk', 'git'):
                raise error.Abort(_('unsupported parser state: %s') % state)
        return changed

class GitDiffRequired(Exception):
    pass

def diffallopts(ui, opts=None, untrusted=False, section='diff'):
    '''return diffopts with all features supported and parsed'''
    return difffeatureopts(ui, opts=opts, untrusted=untrusted, section=section,
                           git=True, whitespace=True, formatchanging=True)

diffopts = diffallopts

def difffeatureopts(ui, opts=None, untrusted=False, section='diff', git=False,
                    whitespace=False, formatchanging=False):
    '''return diffopts with only opted-in features parsed

    Features:
    - git: git-style diffs
    - whitespace: whitespace options like ignoreblanklines and ignorews
    - formatchanging: options that will likely break or cause correctness issues
      with most diff parsers
    '''
    def get(key, name=None, getter=ui.configbool, forceplain=None):
        if opts:
            v = opts.get(key)
            # diffopts flags are either None-default (which is passed
            # through unchanged, so we can identify unset values), or
            # some other falsey default (eg --unified, which defaults
            # to an empty string). We only want to override the config
            # entries from hgrc with command line values if they
            # appear to have been set, which is any truthy value,
            # True, or False.
            if v or isinstance(v, bool):
                return v
        if forceplain is not None and ui.plain():
            return forceplain
        return getter(section, name or key, untrusted=untrusted)

    # core options, expected to be understood by every diff parser
    buildopts = {
        'nodates': get('nodates'),
        'showfunc': get('show_function', 'showfunc'),
        'context': get('unified', getter=ui.config),
    }
    buildopts['worddiff'] = ui.configbool('experimental', 'worddiff')

    if git:
        buildopts['git'] = get('git')

        # since this is in the experimental section, we need to call
        # ui.configbool directory
        buildopts['showsimilarity'] = ui.configbool('experimental',
                                                    'extendedheader.similarity')

        # need to inspect the ui object instead of using get() since we want to
        # test for an int
        hconf = ui.config('experimental', 'extendedheader.index')
        if hconf is not None:
            hlen = None
            try:
                # the hash config could be an integer (for length of hash) or a
                # word (e.g. short, full, none)
                hlen = int(hconf)
                if hlen < 0 or hlen > 40:
                    msg = _("invalid length for extendedheader.index: '%d'\n")
                    ui.warn(msg % hlen)
            except ValueError:
                # default value
                if hconf == 'short' or hconf == '':
                    hlen = 12
                elif hconf == 'full':
                    hlen = 40
                elif hconf != 'none':
                    msg = _("invalid value for extendedheader.index: '%s'\n")
                    ui.warn(msg % hconf)
            finally:
                buildopts['index'] = hlen

    if whitespace:
        buildopts['ignorews'] = get('ignore_all_space', 'ignorews')
        buildopts['ignorewsamount'] = get('ignore_space_change',
                                          'ignorewsamount')
        buildopts['ignoreblanklines'] = get('ignore_blank_lines',
                                            'ignoreblanklines')
        buildopts['ignorewseol'] = get('ignore_space_at_eol', 'ignorewseol')
    if formatchanging:
        buildopts['text'] = opts and opts.get('text')
        binary = None if opts is None else opts.get('binary')
        buildopts['nobinary'] = (not binary if binary is not None
                                 else get('nobinary', forceplain=False))
        buildopts['noprefix'] = get('noprefix', forceplain=False)

    return mdiff.diffopts(**pycompat.strkwargs(buildopts))

def diff(repo, node1=None, node2=None, match=None, changes=None,
         opts=None, losedatafn=None, prefix='', relroot='', copy=None,
         hunksfilterfn=None):
    '''yields diff of changes to files between two nodes, or node and
    working directory.

    if node1 is None, use first dirstate parent instead.
    if node2 is None, compare node1 with working directory.

    losedatafn(**kwarg) is a callable run when opts.upgrade=True and
    every time some change cannot be represented with the current
    patch format. Return False to upgrade to git patch format, True to
    accept the loss or raise an exception to abort the diff. It is
    called with the name of current file being diffed as 'fn'. If set
    to None, patches will always be upgraded to git format when
    necessary.

    prefix is a filename prefix that is prepended to all filenames on
    display (used for subrepos).

    relroot, if not empty, must be normalized with a trailing /. Any match
    patterns that fall outside it will be ignored.

    copy, if not empty, should contain mappings {dst@y: src@x} of copy
    information.

    hunksfilterfn, if not None, should be a function taking a filectx and
    hunks generator that may yield filtered hunks.
    '''
    for fctx1, fctx2, hdr, hunks in diffhunks(
            repo, node1=node1, node2=node2,
            match=match, changes=changes, opts=opts,
            losedatafn=losedatafn, prefix=prefix, relroot=relroot, copy=copy,
    ):
        if hunksfilterfn is not None:
            # If the file has been removed, fctx2 is None; but this should
            # not occur here since we catch removed files early in
            # cmdutil.getloglinerangerevs() for 'hg log -L'.
            assert fctx2 is not None, \
                'fctx2 unexpectly None in diff hunks filtering'
            hunks = hunksfilterfn(fctx2, hunks)
        text = ''.join(sum((list(hlines) for hrange, hlines in hunks), []))
        if hdr and (text or len(hdr) > 1):
            yield '\n'.join(hdr) + '\n'
        if text:
            yield text

def diffhunks(repo, node1=None, node2=None, match=None, changes=None,
              opts=None, losedatafn=None, prefix='', relroot='', copy=None):
    """Yield diff of changes to files in the form of (`header`, `hunks`) tuples
    where `header` is a list of diff headers and `hunks` is an iterable of
    (`hunkrange`, `hunklines`) tuples.

    See diff() for the meaning of parameters.
    """

    if opts is None:
        opts = mdiff.defaultopts

    if not node1 and not node2:
        node1 = repo.dirstate.p1()

    def lrugetfilectx():
        cache = {}
        order = collections.deque()
        def getfilectx(f, ctx):
            fctx = ctx.filectx(f, filelog=cache.get(f))
            if f not in cache:
                if len(cache) > 20:
                    del cache[order.popleft()]
                cache[f] = fctx.filelog()
            else:
                order.remove(f)
            order.append(f)
            return fctx
        return getfilectx
    getfilectx = lrugetfilectx()

    ctx1 = repo[node1]
    ctx2 = repo[node2]

    relfiltered = False
    if relroot != '' and match.always():
        # as a special case, create a new matcher with just the relroot
        pats = [relroot]
        match = scmutil.match(ctx2, pats, default='path')
        relfiltered = True

    if not changes:
        changes = repo.status(ctx1, ctx2, match=match)
    modified, added, removed = changes[:3]

    if not modified and not added and not removed:
        return []

    if repo.ui.debugflag:
        hexfunc = hex
    else:
        hexfunc = short
    revs = [hexfunc(node) for node in [ctx1.node(), ctx2.node()] if node]

    if copy is None:
        copy = {}
        if opts.git or opts.upgrade:
            copy = copies.pathcopies(ctx1, ctx2, match=match)

    if relroot is not None:
        if not relfiltered:
            # XXX this would ideally be done in the matcher, but that is
            # generally meant to 'or' patterns, not 'and' them. In this case we
            # need to 'and' all the patterns from the matcher with relroot.
            def filterrel(l):
                return [f for f in l if f.startswith(relroot)]
            modified = filterrel(modified)
            added = filterrel(added)
            removed = filterrel(removed)
            relfiltered = True
        # filter out copies where either side isn't inside the relative root
        copy = dict(((dst, src) for (dst, src) in copy.iteritems()
                     if dst.startswith(relroot)
                     and src.startswith(relroot)))

    modifiedset = set(modified)
    addedset = set(added)
    removedset = set(removed)
    for f in modified:
        if f not in ctx1:
            # Fix up added, since merged-in additions appear as
            # modifications during merges
            modifiedset.remove(f)
            addedset.add(f)
    for f in removed:
        if f not in ctx1:
            # Merged-in additions that are then removed are reported as removed.
            # They are not in ctx1, so We don't want to show them in the diff.
            removedset.remove(f)
    modified = sorted(modifiedset)
    added = sorted(addedset)
    removed = sorted(removedset)
    for dst, src in list(copy.items()):
        if src not in ctx1:
            # Files merged in during a merge and then copied/renamed are
            # reported as copies. We want to show them in the diff as additions.
            del copy[dst]

    def difffn(opts, losedata):
        return trydiff(repo, revs, ctx1, ctx2, modified, added, removed,
                       copy, getfilectx, opts, losedata, prefix, relroot)
    if opts.upgrade and not opts.git:
        try:
            def losedata(fn):
                if not losedatafn or not losedatafn(fn=fn):
                    raise GitDiffRequired
            # Buffer the whole output until we are sure it can be generated
            return list(difffn(opts.copy(git=False), losedata))
        except GitDiffRequired:
            return difffn(opts.copy(git=True), None)
    else:
        return difffn(opts, None)

def difflabel(func, *args, **kw):
    '''yields 2-tuples of (output, label) based on the output of func()'''
    inlinecolor = False
    if kw.get(r'opts'):
        inlinecolor = kw[r'opts'].worddiff
    headprefixes = [('diff', 'diff.diffline'),
                    ('copy', 'diff.extended'),
                    ('rename', 'diff.extended'),
                    ('old', 'diff.extended'),
                    ('new', 'diff.extended'),
                    ('deleted', 'diff.extended'),
                    ('index', 'diff.extended'),
                    ('similarity', 'diff.extended'),
                    ('---', 'diff.file_a'),
                    ('+++', 'diff.file_b')]
    textprefixes = [('@', 'diff.hunk'),
                    ('-', 'diff.deleted'),
                    ('+', 'diff.inserted')]
    head = False
    for chunk in func(*args, **kw):
        lines = chunk.split('\n')
        matches = {}
        if inlinecolor:
            matches = _findmatches(lines)
        for i, line in enumerate(lines):
            if i != 0:
                yield ('\n', '')
            if head:
                if line.startswith('@'):
                    head = False
            else:
                if line and line[0] not in ' +-@\\':
                    head = True
            stripline = line
            diffline = False
            if not head and line and line[0] in '+-':
                # highlight tabs and trailing whitespace, but only in
                # changed lines
                stripline = line.rstrip()
                diffline = True

            prefixes = textprefixes
            if head:
                prefixes = headprefixes
            for prefix, label in prefixes:
                if stripline.startswith(prefix):
                    if diffline:
                        if i in matches:
                            for t, l in _inlinediff(lines[i].rstrip(),
                                                    lines[matches[i]].rstrip(),
                                                    label):
                                yield (t, l)
                        else:
                            for token in tabsplitter.findall(stripline):
                                if '\t' == token[0]:
                                    yield (token, 'diff.tab')
                                else:
                                    yield (token, label)
                    else:
                        yield (stripline, label)
                    break
            else:
                yield (line, '')
            if line != stripline:
                yield (line[len(stripline):], 'diff.trailingwhitespace')

def _findmatches(slist):
    '''Look for insertion matches to deletion and returns a dict of
    correspondences.
    '''
    lastmatch = 0
    matches = {}
    for i, line in enumerate(slist):
        if line == '':
            continue
        if line[0] == '-':
            lastmatch = max(lastmatch, i)
            newgroup = False
            for j, newline in enumerate(slist[lastmatch + 1:]):
                if newline == '':
                    continue
                if newline[0] == '-' and newgroup: # too far, no match
                    break
                if newline[0] == '+': # potential match
                    newgroup = True
                    sim = difflib.SequenceMatcher(None, line, newline).ratio()
                    if sim > 0.7:
                        lastmatch = lastmatch + 1 + j
                        matches[i] = lastmatch
                        matches[lastmatch] = i
                        break
    return matches

def _inlinediff(s1, s2, operation):
    '''Perform string diff to highlight specific changes.'''
    operation_skip = '+?' if operation == 'diff.deleted' else '-?'
    if operation == 'diff.deleted':
        s2, s1 = s1, s2

    buff = []
    # we never want to higlight the leading +-
    if operation == 'diff.deleted' and s2.startswith('-'):
        label = operation
        token = '-'
        s2 = s2[1:]
        s1 = s1[1:]
    elif operation == 'diff.inserted' and s1.startswith('+'):
        label = operation
        token = '+'
        s2 = s2[1:]
        s1 = s1[1:]
    else:
        raise error.ProgrammingError("Case not expected, operation = %s" %
                                     operation)

    s = difflib.ndiff(_nonwordre.split(s2), _nonwordre.split(s1))
    for part in s:
        if part[0] in operation_skip or len(part) == 2:
            continue
        l = operation + '.highlight'
        if part[0] in ' ':
            l = operation
        if part[2:] == '\t':
            l = 'diff.tab'
        if l == label: # contiguous token with same label
            token += part[2:]
            continue
        else:
            buff.append((token, label))
            label = l
            token = part[2:]
    buff.append((token, label))

    return buff

def diffui(*args, **kw):
    '''like diff(), but yields 2-tuples of (output, label) for ui.write()'''
    return difflabel(diff, *args, **kw)

def _filepairs(modified, added, removed, copy, opts):
    '''generates tuples (f1, f2, copyop), where f1 is the name of the file
    before and f2 is the the name after. For added files, f1 will be None,
    and for removed files, f2 will be None. copyop may be set to None, 'copy'
    or 'rename' (the latter two only if opts.git is set).'''
    gone = set()

    copyto = dict([(v, k) for k, v in copy.items()])

    addedset, removedset = set(added), set(removed)

    for f in sorted(modified + added + removed):
        copyop = None
        f1, f2 = f, f
        if f in addedset:
            f1 = None
            if f in copy:
                if opts.git:
                    f1 = copy[f]
                    if f1 in removedset and f1 not in gone:
                        copyop = 'rename'
                        gone.add(f1)
                    else:
                        copyop = 'copy'
        elif f in removedset:
            f2 = None
            if opts.git:
                # have we already reported a copy above?
                if (f in copyto and copyto[f] in addedset
                    and copy[copyto[f]] == f):
                    continue
        yield f1, f2, copyop

def trydiff(repo, revs, ctx1, ctx2, modified, added, removed,
            copy, getfilectx, opts, losedatafn, prefix, relroot):
    '''given input data, generate a diff and yield it in blocks

    If generating a diff would lose data like flags or binary data and
    losedatafn is not None, it will be called.

    relroot is removed and prefix is added to every path in the diff output.

    If relroot is not empty, this function expects every path in modified,
    added, removed and copy to start with it.'''

    def gitindex(text):
        if not text:
            text = ""
        l = len(text)
        s = hashlib.sha1('blob %d\0' % l)
        s.update(text)
        return hex(s.digest())

    if opts.noprefix:
        aprefix = bprefix = ''
    else:
        aprefix = 'a/'
        bprefix = 'b/'

    def diffline(f, revs):
        revinfo = ' '.join(["-r %s" % rev for rev in revs])
        return 'diff %s %s' % (revinfo, f)

    def isempty(fctx):
        return fctx is None or fctx.size() == 0

    date1 = util.datestr(ctx1.date())
    date2 = util.datestr(ctx2.date())

    gitmode = {'l': '120000', 'x': '100755', '': '100644'}

    if relroot != '' and (repo.ui.configbool('devel', 'all-warnings')
                          or repo.ui.configbool('devel', 'check-relroot')):
        for f in modified + added + removed + list(copy) + list(copy.values()):
            if f is not None and not f.startswith(relroot):
                raise AssertionError(
                    "file %s doesn't start with relroot %s" % (f, relroot))

    for f1, f2, copyop in _filepairs(modified, added, removed, copy, opts):
        content1 = None
        content2 = None
        fctx1 = None
        fctx2 = None
        flag1 = None
        flag2 = None
        if f1:
            fctx1 = getfilectx(f1, ctx1)
            if opts.git or losedatafn:
                flag1 = ctx1.flags(f1)
        if f2:
            fctx2 = getfilectx(f2, ctx2)
            if opts.git or losedatafn:
                flag2 = ctx2.flags(f2)
        # if binary is True, output "summary" or "base85", but not "text diff"
        binary = not opts.text and any(f.isbinary()
                                       for f in [fctx1, fctx2] if f is not None)

        if losedatafn and not opts.git:
            if (binary or
                # copy/rename
                f2 in copy or
                # empty file creation
                (not f1 and isempty(fctx2)) or
                # empty file deletion
                (isempty(fctx1) and not f2) or
                # create with flags
                (not f1 and flag2) or
                # change flags
                (f1 and f2 and flag1 != flag2)):
                losedatafn(f2 or f1)

        path1 = f1 or f2
        path2 = f2 or f1
        path1 = posixpath.join(prefix, path1[len(relroot):])
        path2 = posixpath.join(prefix, path2[len(relroot):])
        header = []
        if opts.git:
            header.append('diff --git %s%s %s%s' %
                          (aprefix, path1, bprefix, path2))
            if not f1: # added
                header.append('new file mode %s' % gitmode[flag2])
            elif not f2: # removed
                header.append('deleted file mode %s' % gitmode[flag1])
            else:  # modified/copied/renamed
                mode1, mode2 = gitmode[flag1], gitmode[flag2]
                if mode1 != mode2:
                    header.append('old mode %s' % mode1)
                    header.append('new mode %s' % mode2)
                if copyop is not None:
                    if opts.showsimilarity:
                        sim = similar.score(ctx1[path1], ctx2[path2]) * 100
                        header.append('similarity index %d%%' % sim)
                    header.append('%s from %s' % (copyop, path1))
                    header.append('%s to %s' % (copyop, path2))
        elif revs and not repo.ui.quiet:
            header.append(diffline(path1, revs))

        #  fctx.is  | diffopts                | what to   | is fctx.data()
        #  binary() | text nobinary git index | output?   | outputted?
        # ------------------------------------|----------------------------
        #  yes      | no   no       no  *     | summary   | no
        #  yes      | no   no       yes *     | base85    | yes
        #  yes      | no   yes      no  *     | summary   | no
        #  yes      | no   yes      yes 0     | summary   | no
        #  yes      | no   yes      yes >0    | summary   | semi [1]
        #  yes      | yes  *        *   *     | text diff | yes
        #  no       | *    *        *   *     | text diff | yes
        # [1]: hash(fctx.data()) is outputted. so fctx.data() cannot be faked
        if binary and (not opts.git or (opts.git and opts.nobinary and not
                                        opts.index)):
            # fast path: no binary content will be displayed, content1 and
            # content2 are only used for equivalent test. cmp() could have a
            # fast path.
            if fctx1 is not None:
                content1 = b'\0'
            if fctx2 is not None:
                if fctx1 is not None and not fctx1.cmp(fctx2):
                    content2 = b'\0' # not different
                else:
                    content2 = b'\0\0'
        else:
            # normal path: load contents
            if fctx1 is not None:
                content1 = fctx1.data()
            if fctx2 is not None:
                content2 = fctx2.data()

        if binary and opts.git and not opts.nobinary:
            text = mdiff.b85diff(content1, content2)
            if text:
                header.append('index %s..%s' %
                              (gitindex(content1), gitindex(content2)))
            hunks = (None, [text]),
        else:
            if opts.git and opts.index > 0:
                flag = flag1
                if flag is None:
                    flag = flag2
                header.append('index %s..%s %s' %
                              (gitindex(content1)[0:opts.index],
                               gitindex(content2)[0:opts.index],
                               gitmode[flag]))

            uheaders, hunks = mdiff.unidiff(content1, date1,
                                            content2, date2,
                                            path1, path2, opts=opts)
            header.extend(uheaders)
        yield fctx1, fctx2, header, hunks

def diffstatsum(stats):
    maxfile, maxtotal, addtotal, removetotal, binary = 0, 0, 0, 0, False
    for f, a, r, b in stats:
        maxfile = max(maxfile, encoding.colwidth(f))
        maxtotal = max(maxtotal, a + r)
        addtotal += a
        removetotal += r
        binary = binary or b

    return maxfile, maxtotal, addtotal, removetotal, binary

def diffstatdata(lines):
    diffre = re.compile('^diff .*-r [a-z0-9]+\s(.*)$')

    results = []
    filename, adds, removes, isbinary = None, 0, 0, False

    def addresult():
        if filename:
            results.append((filename, adds, removes, isbinary))

    # inheader is used to track if a line is in the
    # header portion of the diff.  This helps properly account
    # for lines that start with '--' or '++'
    inheader = False

    for line in lines:
        if line.startswith('diff'):
            addresult()
            # starting a new file diff
            # set numbers to 0 and reset inheader
            inheader = True
            adds, removes, isbinary = 0, 0, False
            if line.startswith('diff --git a/'):
                filename = gitre.search(line).group(2)
            elif line.startswith('diff -r'):
                # format: "diff -r ... -r ... filename"
                filename = diffre.search(line).group(1)
        elif line.startswith('@@'):
            inheader = False
        elif line.startswith('+') and not inheader:
            adds += 1
        elif line.startswith('-') and not inheader:
            removes += 1
        elif (line.startswith('GIT binary patch') or
              line.startswith('Binary file')):
            isbinary = True
    addresult()
    return results

def diffstat(lines, width=80):
    output = []
    stats = diffstatdata(lines)
    maxname, maxtotal, totaladds, totalremoves, hasbinary = diffstatsum(stats)

    countwidth = len(str(maxtotal))
    if hasbinary and countwidth < 3:
        countwidth = 3
    graphwidth = width - countwidth - maxname - 6
    if graphwidth < 10:
        graphwidth = 10

    def scale(i):
        if maxtotal <= graphwidth:
            return i
        # If diffstat runs out of room it doesn't print anything,
        # which isn't very useful, so always print at least one + or -
        # if there were at least some changes.
        return max(i * graphwidth // maxtotal, int(bool(i)))

    for filename, adds, removes, isbinary in stats:
        if isbinary:
            count = 'Bin'
        else:
            count = '%d' % (adds + removes)
        pluses = '+' * scale(adds)
        minuses = '-' * scale(removes)
        output.append(' %s%s |  %*s %s%s\n' %
                      (filename, ' ' * (maxname - encoding.colwidth(filename)),
                       countwidth, count, pluses, minuses))

    if stats:
        output.append(_(' %d files changed, %d insertions(+), '
                        '%d deletions(-)\n')
                      % (len(stats), totaladds, totalremoves))

    return ''.join(output)

def diffstatui(*args, **kw):
    '''like diffstat(), but yields 2-tuples of (output, label) for
    ui.write()
    '''

    for line in diffstat(*args, **kw).splitlines():
        if line and line[-1] in '+-':
            name, graph = line.rsplit(' ', 1)
            yield (name + ' ', '')
            m = re.search(br'\++', graph)
            if m:
                yield (m.group(0), 'diffstat.inserted')
            m = re.search(br'-+', graph)
            if m:
                yield (m.group(0), 'diffstat.deleted')
        else:
            yield (line, '')
        yield ('\n', '')