about summary refs log tree commit diff
path: root/third_party/git/dir.c
blob: 0ffb1b3302452c2cce0bdaa55e5259d9be168b63 (plain) (blame)
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
/*
 * This handles recursive filename detection with exclude
 * files, index knowledge etc..
 *
 * Copyright (C) Linus Torvalds, 2005-2006
 *		 Junio Hamano, 2005-2006
 */
#include "cache.h"
#include "config.h"
#include "dir.h"
#include "object-store.h"
#include "attr.h"
#include "refs.h"
#include "wildmatch.h"
#include "pathspec.h"
#include "utf8.h"
#include "varint.h"
#include "ewah/ewok.h"
#include "fsmonitor.h"
#include "submodule-config.h"

/*
 * Tells read_directory_recursive how a file or directory should be treated.
 * Values are ordered by significance, e.g. if a directory contains both
 * excluded and untracked files, it is listed as untracked because
 * path_untracked > path_excluded.
 */
enum path_treatment {
	path_none = 0,
	path_recurse,
	path_excluded,
	path_untracked
};

/*
 * Support data structure for our opendir/readdir/closedir wrappers
 */
struct cached_dir {
	DIR *fdir;
	struct untracked_cache_dir *untracked;
	int nr_files;
	int nr_dirs;

	const char *d_name;
	int d_type;
	const char *file;
	struct untracked_cache_dir *ucd;
};

static enum path_treatment read_directory_recursive(struct dir_struct *dir,
	struct index_state *istate, const char *path, int len,
	struct untracked_cache_dir *untracked,
	int check_only, int stop_at_first_file, const struct pathspec *pathspec);
static int resolve_dtype(int dtype, struct index_state *istate,
			 const char *path, int len);

int count_slashes(const char *s)
{
	int cnt = 0;
	while (*s)
		if (*s++ == '/')
			cnt++;
	return cnt;
}

int fspathcmp(const char *a, const char *b)
{
	return ignore_case ? strcasecmp(a, b) : strcmp(a, b);
}

int fspathncmp(const char *a, const char *b, size_t count)
{
	return ignore_case ? strncasecmp(a, b, count) : strncmp(a, b, count);
}

int git_fnmatch(const struct pathspec_item *item,
		const char *pattern, const char *string,
		int prefix)
{
	if (prefix > 0) {
		if (ps_strncmp(item, pattern, string, prefix))
			return WM_NOMATCH;
		pattern += prefix;
		string += prefix;
	}
	if (item->flags & PATHSPEC_ONESTAR) {
		int pattern_len = strlen(++pattern);
		int string_len = strlen(string);
		return string_len < pattern_len ||
			ps_strcmp(item, pattern,
				  string + string_len - pattern_len);
	}
	if (item->magic & PATHSPEC_GLOB)
		return wildmatch(pattern, string,
				 WM_PATHNAME |
				 (item->magic & PATHSPEC_ICASE ? WM_CASEFOLD : 0));
	else
		/* wildmatch has not learned no FNM_PATHNAME mode yet */
		return wildmatch(pattern, string,
				 item->magic & PATHSPEC_ICASE ? WM_CASEFOLD : 0);
}

static int fnmatch_icase_mem(const char *pattern, int patternlen,
			     const char *string, int stringlen,
			     int flags)
{
	int match_status;
	struct strbuf pat_buf = STRBUF_INIT;
	struct strbuf str_buf = STRBUF_INIT;
	const char *use_pat = pattern;
	const char *use_str = string;

	if (pattern[patternlen]) {
		strbuf_add(&pat_buf, pattern, patternlen);
		use_pat = pat_buf.buf;
	}
	if (string[stringlen]) {
		strbuf_add(&str_buf, string, stringlen);
		use_str = str_buf.buf;
	}

	if (ignore_case)
		flags |= WM_CASEFOLD;
	match_status = wildmatch(use_pat, use_str, flags);

	strbuf_release(&pat_buf);
	strbuf_release(&str_buf);

	return match_status;
}

static size_t common_prefix_len(const struct pathspec *pathspec)
{
	int n;
	size_t max = 0;

	/*
	 * ":(icase)path" is treated as a pathspec full of
	 * wildcard. In other words, only prefix is considered common
	 * prefix. If the pathspec is abc/foo abc/bar, running in
	 * subdir xyz, the common prefix is still xyz, not xyz/abc as
	 * in non-:(icase).
	 */
	GUARD_PATHSPEC(pathspec,
		       PATHSPEC_FROMTOP |
		       PATHSPEC_MAXDEPTH |
		       PATHSPEC_LITERAL |
		       PATHSPEC_GLOB |
		       PATHSPEC_ICASE |
		       PATHSPEC_EXCLUDE |
		       PATHSPEC_ATTR);

	for (n = 0; n < pathspec->nr; n++) {
		size_t i = 0, len = 0, item_len;
		if (pathspec->items[n].magic & PATHSPEC_EXCLUDE)
			continue;
		if (pathspec->items[n].magic & PATHSPEC_ICASE)
			item_len = pathspec->items[n].prefix;
		else
			item_len = pathspec->items[n].nowildcard_len;
		while (i < item_len && (n == 0 || i < max)) {
			char c = pathspec->items[n].match[i];
			if (c != pathspec->items[0].match[i])
				break;
			if (c == '/')
				len = i + 1;
			i++;
		}
		if (n == 0 || len < max) {
			max = len;
			if (!max)
				break;
		}
	}
	return max;
}

/*
 * Returns a copy of the longest leading path common among all
 * pathspecs.
 */
char *common_prefix(const struct pathspec *pathspec)
{
	unsigned long len = common_prefix_len(pathspec);

	return len ? xmemdupz(pathspec->items[0].match, len) : NULL;
}

int fill_directory(struct dir_struct *dir,
		   struct index_state *istate,
		   const struct pathspec *pathspec)
{
	const char *prefix;
	size_t prefix_len;

	/*
	 * Calculate common prefix for the pathspec, and
	 * use that to optimize the directory walk
	 */
	prefix_len = common_prefix_len(pathspec);
	prefix = prefix_len ? pathspec->items[0].match : "";

	/* Read the directory and prune it */
	read_directory(dir, istate, prefix, prefix_len, pathspec);

	return prefix_len;
}

int within_depth(const char *name, int namelen,
			int depth, int max_depth)
{
	const char *cp = name, *cpe = name + namelen;

	while (cp < cpe) {
		if (*cp++ != '/')
			continue;
		depth++;
		if (depth > max_depth)
			return 0;
	}
	return 1;
}

/*
 * Read the contents of the blob with the given OID into a buffer.
 * Append a trailing LF to the end if the last line doesn't have one.
 *
 * Returns:
 *    -1 when the OID is invalid or unknown or does not refer to a blob.
 *     0 when the blob is empty.
 *     1 along with { data, size } of the (possibly augmented) buffer
 *       when successful.
 *
 * Optionally updates the given oid_stat with the given OID (when valid).
 */
static int do_read_blob(const struct object_id *oid, struct oid_stat *oid_stat,
			size_t *size_out, char **data_out)
{
	enum object_type type;
	unsigned long sz;
	char *data;

	*size_out = 0;
	*data_out = NULL;

	data = read_object_file(oid, &type, &sz);
	if (!data || type != OBJ_BLOB) {
		free(data);
		return -1;
	}

	if (oid_stat) {
		memset(&oid_stat->stat, 0, sizeof(oid_stat->stat));
		oidcpy(&oid_stat->oid, oid);
	}

	if (sz == 0) {
		free(data);
		return 0;
	}

	if (data[sz - 1] != '\n') {
		data = xrealloc(data, st_add(sz, 1));
		data[sz++] = '\n';
	}

	*size_out = xsize_t(sz);
	*data_out = data;

	return 1;
}

#define DO_MATCH_EXCLUDE   (1<<0)
#define DO_MATCH_DIRECTORY (1<<1)
#define DO_MATCH_LEADING_PATHSPEC (1<<2)

/*
 * Does the given pathspec match the given name?  A match is found if
 *
 * (1) the pathspec string is leading directory of 'name' ("RECURSIVELY"), or
 * (2) the pathspec string has a leading part matching 'name' ("LEADING"), or
 * (3) the pathspec string is a wildcard and matches 'name' ("WILDCARD"), or
 * (4) the pathspec string is exactly the same as 'name' ("EXACT").
 *
 * Return value tells which case it was (1-4), or 0 when there is no match.
 *
 * It may be instructive to look at a small table of concrete examples
 * to understand the differences between 1, 2, and 4:
 *
 *                              Pathspecs
 *                |    a/b    |   a/b/    |   a/b/c
 *          ------+-----------+-----------+------------
 *          a/b   |  EXACT    |  EXACT[1] | LEADING[2]
 *  Names   a/b/  | RECURSIVE |   EXACT   | LEADING[2]
 *          a/b/c | RECURSIVE | RECURSIVE |   EXACT
 *
 * [1] Only if DO_MATCH_DIRECTORY is passed; otherwise, this is NOT a match.
 * [2] Only if DO_MATCH_LEADING_PATHSPEC is passed; otherwise, not a match.
 */
static int match_pathspec_item(const struct index_state *istate,
			       const struct pathspec_item *item, int prefix,
			       const char *name, int namelen, unsigned flags)
{
	/* name/namelen has prefix cut off by caller */
	const char *match = item->match + prefix;
	int matchlen = item->len - prefix;

	/*
	 * The normal call pattern is:
	 * 1. prefix = common_prefix_len(ps);
	 * 2. prune something, or fill_directory
	 * 3. match_pathspec()
	 *
	 * 'prefix' at #1 may be shorter than the command's prefix and
	 * it's ok for #2 to match extra files. Those extras will be
	 * trimmed at #3.
	 *
	 * Suppose the pathspec is 'foo' and '../bar' running from
	 * subdir 'xyz'. The common prefix at #1 will be empty, thanks
	 * to "../". We may have xyz/foo _and_ XYZ/foo after #2. The
	 * user does not want XYZ/foo, only the "foo" part should be
	 * case-insensitive. We need to filter out XYZ/foo here. In
	 * other words, we do not trust the caller on comparing the
	 * prefix part when :(icase) is involved. We do exact
	 * comparison ourselves.
	 *
	 * Normally the caller (common_prefix_len() in fact) does
	 * _exact_ matching on name[-prefix+1..-1] and we do not need
	 * to check that part. Be defensive and check it anyway, in
	 * case common_prefix_len is changed, or a new caller is
	 * introduced that does not use common_prefix_len.
	 *
	 * If the penalty turns out too high when prefix is really
	 * long, maybe change it to
	 * strncmp(match, name, item->prefix - prefix)
	 */
	if (item->prefix && (item->magic & PATHSPEC_ICASE) &&
	    strncmp(item->match, name - prefix, item->prefix))
		return 0;

	if (item->attr_match_nr &&
	    !match_pathspec_attrs(istate, name, namelen, item))
		return 0;

	/* If the match was just the prefix, we matched */
	if (!*match)
		return MATCHED_RECURSIVELY;

	if (matchlen <= namelen && !ps_strncmp(item, match, name, matchlen)) {
		if (matchlen == namelen)
			return MATCHED_EXACTLY;

		if (match[matchlen-1] == '/' || name[matchlen] == '/')
			return MATCHED_RECURSIVELY;
	} else if ((flags & DO_MATCH_DIRECTORY) &&
		   match[matchlen - 1] == '/' &&
		   namelen == matchlen - 1 &&
		   !ps_strncmp(item, match, name, namelen))
		return MATCHED_EXACTLY;

	if (item->nowildcard_len < item->len &&
	    !git_fnmatch(item, match, name,
			 item->nowildcard_len - prefix))
		return MATCHED_FNMATCH;

	/* Perform checks to see if "name" is a leading string of the pathspec */
	if (flags & DO_MATCH_LEADING_PATHSPEC) {
		/* name is a literal prefix of the pathspec */
		int offset = name[namelen-1] == '/' ? 1 : 0;
		if ((namelen < matchlen) &&
		    (match[namelen-offset] == '/') &&
		    !ps_strncmp(item, match, name, namelen))
			return MATCHED_RECURSIVELY_LEADING_PATHSPEC;

		/* name doesn't match up to the first wild character */
		if (item->nowildcard_len < item->len &&
		    ps_strncmp(item, match, name,
			       item->nowildcard_len - prefix))
			return 0;

		/*
		 * name has no wildcard, and it didn't match as a leading
		 * pathspec so return.
		 */
		if (item->nowildcard_len == item->len)
			return 0;

		/*
		 * Here is where we would perform a wildmatch to check if
		 * "name" can be matched as a directory (or a prefix) against
		 * the pathspec.  Since wildmatch doesn't have this capability
		 * at the present we have to punt and say that it is a match,
		 * potentially returning a false positive
		 * The submodules themselves will be able to perform more
		 * accurate matching to determine if the pathspec matches.
		 */
		return MATCHED_RECURSIVELY_LEADING_PATHSPEC;
	}

	return 0;
}

/*
 * Given a name and a list of pathspecs, returns the nature of the
 * closest (i.e. most specific) match of the name to any of the
 * pathspecs.
 *
 * The caller typically calls this multiple times with the same
 * pathspec and seen[] array but with different name/namelen
 * (e.g. entries from the index) and is interested in seeing if and
 * how each pathspec matches all the names it calls this function
 * with.  A mark is left in the seen[] array for each pathspec element
 * indicating the closest type of match that element achieved, so if
 * seen[n] remains zero after multiple invocations, that means the nth
 * pathspec did not match any names, which could indicate that the
 * user mistyped the nth pathspec.
 */
static int do_match_pathspec(const struct index_state *istate,
			     const struct pathspec *ps,
			     const char *name, int namelen,
			     int prefix, char *seen,
			     unsigned flags)
{
	int i, retval = 0, exclude = flags & DO_MATCH_EXCLUDE;

	GUARD_PATHSPEC(ps,
		       PATHSPEC_FROMTOP |
		       PATHSPEC_MAXDEPTH |
		       PATHSPEC_LITERAL |
		       PATHSPEC_GLOB |
		       PATHSPEC_ICASE |
		       PATHSPEC_EXCLUDE |
		       PATHSPEC_ATTR);

	if (!ps->nr) {
		if (!ps->recursive ||
		    !(ps->magic & PATHSPEC_MAXDEPTH) ||
		    ps->max_depth == -1)
			return MATCHED_RECURSIVELY;

		if (within_depth(name, namelen, 0, ps->max_depth))
			return MATCHED_EXACTLY;
		else
			return 0;
	}

	name += prefix;
	namelen -= prefix;

	for (i = ps->nr - 1; i >= 0; i--) {
		int how;

		if ((!exclude &&   ps->items[i].magic & PATHSPEC_EXCLUDE) ||
		    ( exclude && !(ps->items[i].magic & PATHSPEC_EXCLUDE)))
			continue;

		if (seen && seen[i] == MATCHED_EXACTLY)
			continue;
		/*
		 * Make exclude patterns optional and never report
		 * "pathspec ':(exclude)foo' matches no files"
		 */
		if (seen && ps->items[i].magic & PATHSPEC_EXCLUDE)
			seen[i] = MATCHED_FNMATCH;
		how = match_pathspec_item(istate, ps->items+i, prefix, name,
					  namelen, flags);
		if (ps->recursive &&
		    (ps->magic & PATHSPEC_MAXDEPTH) &&
		    ps->max_depth != -1 &&
		    how && how != MATCHED_FNMATCH) {
			int len = ps->items[i].len;
			if (name[len] == '/')
				len++;
			if (within_depth(name+len, namelen-len, 0, ps->max_depth))
				how = MATCHED_EXACTLY;
			else
				how = 0;
		}
		if (how) {
			if (retval < how)
				retval = how;
			if (seen && seen[i] < how)
				seen[i] = how;
		}
	}
	return retval;
}

int match_pathspec(const struct index_state *istate,
		   const struct pathspec *ps,
		   const char *name, int namelen,
		   int prefix, char *seen, int is_dir)
{
	int positive, negative;
	unsigned flags = is_dir ? DO_MATCH_DIRECTORY : 0;
	positive = do_match_pathspec(istate, ps, name, namelen,
				     prefix, seen, flags);
	if (!(ps->magic & PATHSPEC_EXCLUDE) || !positive)
		return positive;
	negative = do_match_pathspec(istate, ps, name, namelen,
				     prefix, seen,
				     flags | DO_MATCH_EXCLUDE);
	return negative ? 0 : positive;
}

/**
 * Check if a submodule is a superset of the pathspec
 */
int submodule_path_match(const struct index_state *istate,
			 const struct pathspec *ps,
			 const char *submodule_name,
			 char *seen)
{
	int matched = do_match_pathspec(istate, ps, submodule_name,
					strlen(submodule_name),
					0, seen,
					DO_MATCH_DIRECTORY |
					DO_MATCH_LEADING_PATHSPEC);
	return matched;
}

int report_path_error(const char *ps_matched,
		      const struct pathspec *pathspec)
{
	/*
	 * Make sure all pathspec matched; otherwise it is an error.
	 */
	int num, errors = 0;
	for (num = 0; num < pathspec->nr; num++) {
		int other, found_dup;

		if (ps_matched[num])
			continue;
		/*
		 * The caller might have fed identical pathspec
		 * twice.  Do not barf on such a mistake.
		 * FIXME: parse_pathspec should have eliminated
		 * duplicate pathspec.
		 */
		for (found_dup = other = 0;
		     !found_dup && other < pathspec->nr;
		     other++) {
			if (other == num || !ps_matched[other])
				continue;
			if (!strcmp(pathspec->items[other].original,
				    pathspec->items[num].original))
				/*
				 * Ok, we have a match already.
				 */
				found_dup = 1;
		}
		if (found_dup)
			continue;

		error(_("pathspec '%s' did not match any file(s) known to git"),
		      pathspec->items[num].original);
		errors++;
	}
	return errors;
}

/*
 * Return the length of the "simple" part of a path match limiter.
 */
int simple_length(const char *match)
{
	int len = -1;

	for (;;) {
		unsigned char c = *match++;
		len++;
		if (c == '\0' || is_glob_special(c))
			return len;
	}
}

int no_wildcard(const char *string)
{
	return string[simple_length(string)] == '\0';
}

void parse_path_pattern(const char **pattern,
			   int *patternlen,
			   unsigned *flags,
			   int *nowildcardlen)
{
	const char *p = *pattern;
	size_t i, len;

	*flags = 0;
	if (*p == '!') {
		*flags |= PATTERN_FLAG_NEGATIVE;
		p++;
	}
	len = strlen(p);
	if (len && p[len - 1] == '/') {
		len--;
		*flags |= PATTERN_FLAG_MUSTBEDIR;
	}
	for (i = 0; i < len; i++) {
		if (p[i] == '/')
			break;
	}
	if (i == len)
		*flags |= PATTERN_FLAG_NODIR;
	*nowildcardlen = simple_length(p);
	/*
	 * we should have excluded the trailing slash from 'p' too,
	 * but that's one more allocation. Instead just make sure
	 * nowildcardlen does not exceed real patternlen
	 */
	if (*nowildcardlen > len)
		*nowildcardlen = len;
	if (*p == '*' && no_wildcard(p + 1))
		*flags |= PATTERN_FLAG_ENDSWITH;
	*pattern = p;
	*patternlen = len;
}

int pl_hashmap_cmp(const void *unused_cmp_data,
		   const struct hashmap_entry *a,
		   const struct hashmap_entry *b,
		   const void *key)
{
	const struct pattern_entry *ee1 =
			container_of(a, struct pattern_entry, ent);
	const struct pattern_entry *ee2 =
			container_of(b, struct pattern_entry, ent);

	size_t min_len = ee1->patternlen <= ee2->patternlen
			 ? ee1->patternlen
			 : ee2->patternlen;

	if (ignore_case)
		return strncasecmp(ee1->pattern, ee2->pattern, min_len);
	return strncmp(ee1->pattern, ee2->pattern, min_len);
}

static char *dup_and_filter_pattern(const char *pattern)
{
	char *set, *read;
	size_t count  = 0;
	char *result = xstrdup(pattern);

	set = result;
	read = result;

	while (*read) {
		/* skip escape characters (once) */
		if (*read == '\\')
			read++;

		*set = *read;

		set++;
		read++;
		count++;
	}
	*set = 0;

	if (count > 2 &&
	    *(set - 1) == '*' &&
	    *(set - 2) == '/')
		*(set - 2) = 0;

	return result;
}

static void add_pattern_to_hashsets(struct pattern_list *pl, struct path_pattern *given)
{
	struct pattern_entry *translated;
	char *truncated;
	char *data = NULL;
	const char *prev, *cur, *next;

	if (!pl->use_cone_patterns)
		return;

	if (given->flags & PATTERN_FLAG_NEGATIVE &&
	    given->flags & PATTERN_FLAG_MUSTBEDIR &&
	    !strcmp(given->pattern, "/*")) {
		pl->full_cone = 0;
		return;
	}

	if (!given->flags && !strcmp(given->pattern, "/*")) {
		pl->full_cone = 1;
		return;
	}

	if (given->patternlen < 2 ||
	    *given->pattern == '*' ||
	    strstr(given->pattern, "**")) {
		/* Not a cone pattern. */
		warning(_("unrecognized pattern: '%s'"), given->pattern);
		goto clear_hashmaps;
	}

	prev = given->pattern;
	cur = given->pattern + 1;
	next = given->pattern + 2;

	while (*cur) {
		/* Watch for glob characters '*', '\', '[', '?' */
		if (!is_glob_special(*cur))
			goto increment;

		/* But only if *prev != '\\' */
		if (*prev == '\\')
			goto increment;

		/* But allow the initial '\' */
		if (*cur == '\\' &&
		    is_glob_special(*next))
			goto increment;

		/* But a trailing '/' then '*' is fine */
		if (*prev == '/' &&
		    *cur == '*' &&
		    *next == 0)
			goto increment;

		/* Not a cone pattern. */
		warning(_("unrecognized pattern: '%s'"), given->pattern);
		goto clear_hashmaps;

	increment:
		prev++;
		cur++;
		next++;
	}

	if (given->patternlen > 2 &&
	    !strcmp(given->pattern + given->patternlen - 2, "/*")) {
		if (!(given->flags & PATTERN_FLAG_NEGATIVE)) {
			/* Not a cone pattern. */
			warning(_("unrecognized pattern: '%s'"), given->pattern);
			goto clear_hashmaps;
		}

		truncated = dup_and_filter_pattern(given->pattern);

		translated = xmalloc(sizeof(struct pattern_entry));
		translated->pattern = truncated;
		translated->patternlen = given->patternlen - 2;
		hashmap_entry_init(&translated->ent,
				   ignore_case ?
				   strihash(translated->pattern) :
				   strhash(translated->pattern));

		if (!hashmap_get_entry(&pl->recursive_hashmap,
				       translated, ent, NULL)) {
			/* We did not see the "parent" included */
			warning(_("unrecognized negative pattern: '%s'"),
				given->pattern);
			free(truncated);
			free(translated);
			goto clear_hashmaps;
		}

		hashmap_add(&pl->parent_hashmap, &translated->ent);
		hashmap_remove(&pl->recursive_hashmap, &translated->ent, &data);
		free(data);
		return;
	}

	if (given->flags & PATTERN_FLAG_NEGATIVE) {
		warning(_("unrecognized negative pattern: '%s'"),
			given->pattern);
		goto clear_hashmaps;
	}

	translated = xmalloc(sizeof(struct pattern_entry));

	translated->pattern = dup_and_filter_pattern(given->pattern);
	translated->patternlen = given->patternlen;
	hashmap_entry_init(&translated->ent,
			   ignore_case ?
			   strihash(translated->pattern) :
			   strhash(translated->pattern));

	hashmap_add(&pl->recursive_hashmap, &translated->ent);

	if (hashmap_get_entry(&pl->parent_hashmap, translated, ent, NULL)) {
		/* we already included this at the parent level */
		warning(_("your sparse-checkout file may have issues: pattern '%s' is repeated"),
			given->pattern);
		hashmap_remove(&pl->parent_hashmap, &translated->ent, &data);
		free(data);
		free(translated);
	}

	return;

clear_hashmaps:
	warning(_("disabling cone pattern matching"));
	hashmap_free_entries(&pl->parent_hashmap, struct pattern_entry, ent);
	hashmap_free_entries(&pl->recursive_hashmap, struct pattern_entry, ent);
	pl->use_cone_patterns = 0;
}

static int hashmap_contains_path(struct hashmap *map,
				 struct strbuf *pattern)
{
	struct pattern_entry p;

	/* Check straight mapping */
	p.pattern = pattern->buf;
	p.patternlen = pattern->len;
	hashmap_entry_init(&p.ent,
			   ignore_case ?
			   strihash(p.pattern) :
			   strhash(p.pattern));
	return !!hashmap_get_entry(map, &p, ent, NULL);
}

int hashmap_contains_parent(struct hashmap *map,
			    const char *path,
			    struct strbuf *buffer)
{
	char *slash_pos;

	strbuf_setlen(buffer, 0);

	if (path[0] != '/')
		strbuf_addch(buffer, '/');

	strbuf_addstr(buffer, path);

	slash_pos = strrchr(buffer->buf, '/');

	while (slash_pos > buffer->buf) {
		strbuf_setlen(buffer, slash_pos - buffer->buf);

		if (hashmap_contains_path(map, buffer))
			return 1;

		slash_pos = strrchr(buffer->buf, '/');
	}

	return 0;
}

void add_pattern(const char *string, const char *base,
		 int baselen, struct pattern_list *pl, int srcpos)
{
	struct path_pattern *pattern;
	int patternlen;
	unsigned flags;
	int nowildcardlen;

	parse_path_pattern(&string, &patternlen, &flags, &nowildcardlen);
	if (flags & PATTERN_FLAG_MUSTBEDIR) {
		FLEXPTR_ALLOC_MEM(pattern, pattern, string, patternlen);
	} else {
		pattern = xmalloc(sizeof(*pattern));
		pattern->pattern = string;
	}
	pattern->patternlen = patternlen;
	pattern->nowildcardlen = nowildcardlen;
	pattern->base = base;
	pattern->baselen = baselen;
	pattern->flags = flags;
	pattern->srcpos = srcpos;
	ALLOC_GROW(pl->patterns, pl->nr + 1, pl->alloc);
	pl->patterns[pl->nr++] = pattern;
	pattern->pl = pl;

	add_pattern_to_hashsets(pl, pattern);
}

static int read_skip_worktree_file_from_index(const struct index_state *istate,
					      const char *path,
					      size_t *size_out, char **data_out,
					      struct oid_stat *oid_stat)
{
	int pos, len;

	len = strlen(path);
	pos = index_name_pos(istate, path, len);
	if (pos < 0)
		return -1;
	if (!ce_skip_worktree(istate->cache[pos]))
		return -1;

	return do_read_blob(&istate->cache[pos]->oid, oid_stat, size_out, data_out);
}

/*
 * Frees memory within pl which was allocated for exclude patterns and
 * the file buffer.  Does not free pl itself.
 */
void clear_pattern_list(struct pattern_list *pl)
{
	int i;

	for (i = 0; i < pl->nr; i++)
		free(pl->patterns[i]);
	free(pl->patterns);
	free(pl->filebuf);

	memset(pl, 0, sizeof(*pl));
}

static void trim_trailing_spaces(char *buf)
{
	char *p, *last_space = NULL;

	for (p = buf; *p; p++)
		switch (*p) {
		case ' ':
			if (!last_space)
				last_space = p;
			break;
		case '\\':
			p++;
			if (!*p)
				return;
			/* fallthrough */
		default:
			last_space = NULL;
		}

	if (last_space)
		*last_space = '\0';
}

/*
 * Given a subdirectory name and "dir" of the current directory,
 * search the subdir in "dir" and return it, or create a new one if it
 * does not exist in "dir".
 *
 * If "name" has the trailing slash, it'll be excluded in the search.
 */
static struct untracked_cache_dir *lookup_untracked(struct untracked_cache *uc,
						    struct untracked_cache_dir *dir,
						    const char *name, int len)
{
	int first, last;
	struct untracked_cache_dir *d;
	if (!dir)
		return NULL;
	if (len && name[len - 1] == '/')
		len--;
	first = 0;
	last = dir->dirs_nr;
	while (last > first) {
		int cmp, next = first + ((last - first) >> 1);
		d = dir->dirs[next];
		cmp = strncmp(name, d->name, len);
		if (!cmp && strlen(d->name) > len)
			cmp = -1;
		if (!cmp)
			return d;
		if (cmp < 0) {
			last = next;
			continue;
		}
		first = next+1;
	}

	uc->dir_created++;
	FLEX_ALLOC_MEM(d, name, name, len);

	ALLOC_GROW(dir->dirs, dir->dirs_nr + 1, dir->dirs_alloc);
	MOVE_ARRAY(dir->dirs + first + 1, dir->dirs + first,
		   dir->dirs_nr - first);
	dir->dirs_nr++;
	dir->dirs[first] = d;
	return d;
}

static void do_invalidate_gitignore(struct untracked_cache_dir *dir)
{
	int i;
	dir->valid = 0;
	dir->untracked_nr = 0;
	for (i = 0; i < dir->dirs_nr; i++)
		do_invalidate_gitignore(dir->dirs[i]);
}

static void invalidate_gitignore(struct untracked_cache *uc,
				 struct untracked_cache_dir *dir)
{
	uc->gitignore_invalidated++;
	do_invalidate_gitignore(dir);
}

static void invalidate_directory(struct untracked_cache *uc,
				 struct untracked_cache_dir *dir)
{
	int i;

	/*
	 * Invalidation increment here is just roughly correct. If
	 * untracked_nr or any of dirs[].recurse is non-zero, we
	 * should increment dir_invalidated too. But that's more
	 * expensive to do.
	 */
	if (dir->valid)
		uc->dir_invalidated++;

	dir->valid = 0;
	dir->untracked_nr = 0;
	for (i = 0; i < dir->dirs_nr; i++)
		dir->dirs[i]->recurse = 0;
}

static int add_patterns_from_buffer(char *buf, size_t size,
				    const char *base, int baselen,
				    struct pattern_list *pl);

/*
 * Given a file with name "fname", read it (either from disk, or from
 * an index if 'istate' is non-null), parse it and store the
 * exclude rules in "pl".
 *
 * If "ss" is not NULL, compute SHA-1 of the exclude file and fill
 * stat data from disk (only valid if add_patterns returns zero). If
 * ss_valid is non-zero, "ss" must contain good value as input.
 */
static int add_patterns(const char *fname, const char *base, int baselen,
			struct pattern_list *pl, struct index_state *istate,
			struct oid_stat *oid_stat)
{
	struct stat st;
	int r;
	int fd;
	size_t size = 0;
	char *buf;

	fd = open(fname, O_RDONLY);
	if (fd < 0 || fstat(fd, &st) < 0) {
		if (fd < 0)
			warn_on_fopen_errors(fname);
		else
			close(fd);
		if (!istate)
			return -1;
		r = read_skip_worktree_file_from_index(istate, fname,
						       &size, &buf,
						       oid_stat);
		if (r != 1)
			return r;
	} else {
		size = xsize_t(st.st_size);
		if (size == 0) {
			if (oid_stat) {
				fill_stat_data(&oid_stat->stat, &st);
				oidcpy(&oid_stat->oid, the_hash_algo->empty_blob);
				oid_stat->valid = 1;
			}
			close(fd);
			return 0;
		}
		buf = xmallocz(size);
		if (read_in_full(fd, buf, size) != size) {
			free(buf);
			close(fd);
			return -1;
		}
		buf[size++] = '\n';
		close(fd);
		if (oid_stat) {
			int pos;
			if (oid_stat->valid &&
			    !match_stat_data_racy(istate, &oid_stat->stat, &st))
				; /* no content change, ss->sha1 still good */
			else if (istate &&
				 (pos = index_name_pos(istate, fname, strlen(fname))) >= 0 &&
				 !ce_stage(istate->cache[pos]) &&
				 ce_uptodate(istate->cache[pos]) &&
				 !would_convert_to_git(istate, fname))
				oidcpy(&oid_stat->oid,
				       &istate->cache[pos]->oid);
			else
				hash_object_file(the_hash_algo, buf, size,
						 "blob", &oid_stat->oid);
			fill_stat_data(&oid_stat->stat, &st);
			oid_stat->valid = 1;
		}
	}

	add_patterns_from_buffer(buf, size, base, baselen, pl);
	return 0;
}

static int add_patterns_from_buffer(char *buf, size_t size,
				    const char *base, int baselen,
				    struct pattern_list *pl)
{
	int i, lineno = 1;
	char *entry;

	hashmap_init(&pl->recursive_hashmap, pl_hashmap_cmp, NULL, 0);
	hashmap_init(&pl->parent_hashmap, pl_hashmap_cmp, NULL, 0);

	pl->filebuf = buf;

	if (skip_utf8_bom(&buf, size))
		size -= buf - pl->filebuf;

	entry = buf;

	for (i = 0; i < size; i++) {
		if (buf[i] == '\n') {
			if (entry != buf + i && entry[0] != '#') {
				buf[i - (i && buf[i-1] == '\r')] = 0;
				trim_trailing_spaces(entry);
				add_pattern(entry, base, baselen, pl, lineno);
			}
			lineno++;
			entry = buf + i + 1;
		}
	}
	return 0;
}

int add_patterns_from_file_to_list(const char *fname, const char *base,
				   int baselen, struct pattern_list *pl,
				   struct index_state *istate)
{
	return add_patterns(fname, base, baselen, pl, istate, NULL);
}

int add_patterns_from_blob_to_list(
	struct object_id *oid,
	const char *base, int baselen,
	struct pattern_list *pl)
{
	char *buf;
	size_t size;
	int r;

	r = do_read_blob(oid, NULL, &size, &buf);
	if (r != 1)
		return r;

	add_patterns_from_buffer(buf, size, base, baselen, pl);
	return 0;
}

struct pattern_list *add_pattern_list(struct dir_struct *dir,
				      int group_type, const char *src)
{
	struct pattern_list *pl;
	struct exclude_list_group *group;

	group = &dir->exclude_list_group[group_type];
	ALLOC_GROW(group->pl, group->nr + 1, group->alloc);
	pl = &group->pl[group->nr++];
	memset(pl, 0, sizeof(*pl));
	pl->src = src;
	return pl;
}

/*
 * Used to set up core.excludesfile and .git/info/exclude lists.
 */
static void add_patterns_from_file_1(struct dir_struct *dir, const char *fname,
				     struct oid_stat *oid_stat)
{
	struct pattern_list *pl;
	/*
	 * catch setup_standard_excludes() that's called before
	 * dir->untracked is assigned. That function behaves
	 * differently when dir->untracked is non-NULL.
	 */
	if (!dir->untracked)
		dir->unmanaged_exclude_files++;
	pl = add_pattern_list(dir, EXC_FILE, fname);
	if (add_patterns(fname, "", 0, pl, NULL, oid_stat) < 0)
		die(_("cannot use %s as an exclude file"), fname);
}

void add_patterns_from_file(struct dir_struct *dir, const char *fname)
{
	dir->unmanaged_exclude_files++; /* see validate_untracked_cache() */
	add_patterns_from_file_1(dir, fname, NULL);
}

int match_basename(const char *basename, int basenamelen,
		   const char *pattern, int prefix, int patternlen,
		   unsigned flags)
{
	if (prefix == patternlen) {
		if (patternlen == basenamelen &&
		    !fspathncmp(pattern, basename, basenamelen))
			return 1;
	} else if (flags & PATTERN_FLAG_ENDSWITH) {
		/* "*literal" matching against "fooliteral" */
		if (patternlen - 1 <= basenamelen &&
		    !fspathncmp(pattern + 1,
				   basename + basenamelen - (patternlen - 1),
				   patternlen - 1))
			return 1;
	} else {
		if (fnmatch_icase_mem(pattern, patternlen,
				      basename, basenamelen,
				      0) == 0)
			return 1;
	}
	return 0;
}

int match_pathname(const char *pathname, int pathlen,
		   const char *base, int baselen,
		   const char *pattern, int prefix, int patternlen,
		   unsigned flags)
{
	const char *name;
	int namelen;

	/*
	 * match with FNM_PATHNAME; the pattern has base implicitly
	 * in front of it.
	 */
	if (*pattern == '/') {
		pattern++;
		patternlen--;
		prefix--;
	}

	/*
	 * baselen does not count the trailing slash. base[] may or
	 * may not end with a trailing slash though.
	 */
	if (pathlen < baselen + 1 ||
	    (baselen && pathname[baselen] != '/') ||
	    fspathncmp(pathname, base, baselen))
		return 0;

	namelen = baselen ? pathlen - baselen - 1 : pathlen;
	name = pathname + pathlen - namelen;

	if (prefix) {
		/*
		 * if the non-wildcard part is longer than the
		 * remaining pathname, surely it cannot match.
		 */
		if (prefix > namelen)
			return 0;

		if (fspathncmp(pattern, name, prefix))
			return 0;
		pattern += prefix;
		patternlen -= prefix;
		name    += prefix;
		namelen -= prefix;

		/*
		 * If the whole pattern did not have a wildcard,
		 * then our prefix match is all we need; we
		 * do not need to call fnmatch at all.
		 */
		if (!patternlen && !namelen)
			return 1;
	}

	return fnmatch_icase_mem(pattern, patternlen,
				 name, namelen,
				 WM_PATHNAME) == 0;
}

/*
 * Scan the given exclude list in reverse to see whether pathname
 * should be ignored.  The first match (i.e. the last on the list), if
 * any, determines the fate.  Returns the exclude_list element which
 * matched, or NULL for undecided.
 */
static struct path_pattern *last_matching_pattern_from_list(const char *pathname,
						       int pathlen,
						       const char *basename,
						       int *dtype,
						       struct pattern_list *pl,
						       struct index_state *istate)
{
	struct path_pattern *res = NULL; /* undecided */
	int i;

	if (!pl->nr)
		return NULL;	/* undefined */

	for (i = pl->nr - 1; 0 <= i; i--) {
		struct path_pattern *pattern = pl->patterns[i];
		const char *exclude = pattern->pattern;
		int prefix = pattern->nowildcardlen;

		if (pattern->flags & PATTERN_FLAG_MUSTBEDIR) {
			*dtype = resolve_dtype(*dtype, istate, pathname, pathlen);
			if (*dtype != DT_DIR)
				continue;
		}

		if (pattern->flags & PATTERN_FLAG_NODIR) {
			if (match_basename(basename,
					   pathlen - (basename - pathname),
					   exclude, prefix, pattern->patternlen,
					   pattern->flags)) {
				res = pattern;
				break;
			}
			continue;
		}

		assert(pattern->baselen == 0 ||
		       pattern->base[pattern->baselen - 1] == '/');
		if (match_pathname(pathname, pathlen,
				   pattern->base,
				   pattern->baselen ? pattern->baselen - 1 : 0,
				   exclude, prefix, pattern->patternlen,
				   pattern->flags)) {
			res = pattern;
			break;
		}
	}
	return res;
}

/*
 * Scan the list of patterns to determine if the ordered list
 * of patterns matches on 'pathname'.
 *
 * Return 1 for a match, 0 for not matched and -1 for undecided.
 */
enum pattern_match_result path_matches_pattern_list(
				const char *pathname, int pathlen,
				const char *basename, int *dtype,
				struct pattern_list *pl,
				struct index_state *istate)
{
	struct path_pattern *pattern;
	struct strbuf parent_pathname = STRBUF_INIT;
	int result = NOT_MATCHED;
	const char *slash_pos;

	if (!pl->use_cone_patterns) {
		pattern = last_matching_pattern_from_list(pathname, pathlen, basename,
							dtype, pl, istate);
		if (pattern) {
			if (pattern->flags & PATTERN_FLAG_NEGATIVE)
				return NOT_MATCHED;
			else
				return MATCHED;
		}

		return UNDECIDED;
	}

	if (pl->full_cone)
		return MATCHED;

	strbuf_addch(&parent_pathname, '/');
	strbuf_add(&parent_pathname, pathname, pathlen);

	if (hashmap_contains_path(&pl->recursive_hashmap,
				  &parent_pathname)) {
		result = MATCHED_RECURSIVE;
		goto done;
	}

	slash_pos = strrchr(parent_pathname.buf, '/');

	if (slash_pos == parent_pathname.buf) {
		/* include every file in root */
		result = MATCHED;
		goto done;
	}

	strbuf_setlen(&parent_pathname, slash_pos - parent_pathname.buf);

	if (hashmap_contains_path(&pl->parent_hashmap, &parent_pathname)) {
		result = MATCHED;
		goto done;
	}

	if (hashmap_contains_parent(&pl->recursive_hashmap,
				    pathname,
				    &parent_pathname))
		result = MATCHED_RECURSIVE;

done:
	strbuf_release(&parent_pathname);
	return result;
}

static struct path_pattern *last_matching_pattern_from_lists(
		struct dir_struct *dir, struct index_state *istate,
		const char *pathname, int pathlen,
		const char *basename, int *dtype_p)
{
	int i, j;
	struct exclude_list_group *group;
	struct path_pattern *pattern;
	for (i = EXC_CMDL; i <= EXC_FILE; i++) {
		group = &dir->exclude_list_group[i];
		for (j = group->nr - 1; j >= 0; j--) {
			pattern = last_matching_pattern_from_list(
				pathname, pathlen, basename, dtype_p,
				&group->pl[j], istate);
			if (pattern)
				return pattern;
		}
	}
	return NULL;
}

/*
 * Loads the per-directory exclude list for the substring of base
 * which has a char length of baselen.
 */
static void prep_exclude(struct dir_struct *dir,
			 struct index_state *istate,
			 const char *base, int baselen)
{
	struct exclude_list_group *group;
	struct pattern_list *pl;
	struct exclude_stack *stk = NULL;
	struct untracked_cache_dir *untracked;
	int current;

	group = &dir->exclude_list_group[EXC_DIRS];

	/*
	 * Pop the exclude lists from the EXCL_DIRS exclude_list_group
	 * which originate from directories not in the prefix of the
	 * path being checked.
	 */
	while ((stk = dir->exclude_stack) != NULL) {
		if (stk->baselen <= baselen &&
		    !strncmp(dir->basebuf.buf, base, stk->baselen))
			break;
		pl = &group->pl[dir->exclude_stack->exclude_ix];
		dir->exclude_stack = stk->prev;
		dir->pattern = NULL;
		free((char *)pl->src); /* see strbuf_detach() below */
		clear_pattern_list(pl);
		free(stk);
		group->nr--;
	}

	/* Skip traversing into sub directories if the parent is excluded */
	if (dir->pattern)
		return;

	/*
	 * Lazy initialization. All call sites currently just
	 * memset(dir, 0, sizeof(*dir)) before use. Changing all of
	 * them seems lots of work for little benefit.
	 */
	if (!dir->basebuf.buf)
		strbuf_init(&dir->basebuf, PATH_MAX);

	/* Read from the parent directories and push them down. */
	current = stk ? stk->baselen : -1;
	strbuf_setlen(&dir->basebuf, current < 0 ? 0 : current);
	if (dir->untracked)
		untracked = stk ? stk->ucd : dir->untracked->root;
	else
		untracked = NULL;

	while (current < baselen) {
		const char *cp;
		struct oid_stat oid_stat;

		stk = xcalloc(1, sizeof(*stk));
		if (current < 0) {
			cp = base;
			current = 0;
		} else {
			cp = strchr(base + current + 1, '/');
			if (!cp)
				die("oops in prep_exclude");
			cp++;
			untracked =
				lookup_untracked(dir->untracked, untracked,
						 base + current,
						 cp - base - current);
		}
		stk->prev = dir->exclude_stack;
		stk->baselen = cp - base;
		stk->exclude_ix = group->nr;
		stk->ucd = untracked;
		pl = add_pattern_list(dir, EXC_DIRS, NULL);
		strbuf_add(&dir->basebuf, base + current, stk->baselen - current);
		assert(stk->baselen == dir->basebuf.len);

		/* Abort if the directory is excluded */
		if (stk->baselen) {
			int dt = DT_DIR;
			dir->basebuf.buf[stk->baselen - 1] = 0;
			dir->pattern = last_matching_pattern_from_lists(dir,
									istate,
				dir->basebuf.buf, stk->baselen - 1,
				dir->basebuf.buf + current, &dt);
			dir->basebuf.buf[stk->baselen - 1] = '/';
			if (dir->pattern &&
			    dir->pattern->flags & PATTERN_FLAG_NEGATIVE)
				dir->pattern = NULL;
			if (dir->pattern) {
				dir->exclude_stack = stk;
				return;
			}
		}

		/* Try to read per-directory file */
		oidclr(&oid_stat.oid);
		oid_stat.valid = 0;
		if (dir->exclude_per_dir &&
		    /*
		     * If we know that no files have been added in
		     * this directory (i.e. valid_cached_dir() has
		     * been executed and set untracked->valid) ..
		     */
		    (!untracked || !untracked->valid ||
		     /*
		      * .. and .gitignore does not exist before
		      * (i.e. null exclude_oid). Then we can skip
		      * loading .gitignore, which would result in
		      * ENOENT anyway.
		      */
		     !is_null_oid(&untracked->exclude_oid))) {
			/*
			 * dir->basebuf gets reused by the traversal, but we
			 * need fname to remain unchanged to ensure the src
			 * member of each struct path_pattern correctly
			 * back-references its source file.  Other invocations
			 * of add_pattern_list provide stable strings, so we
			 * strbuf_detach() and free() here in the caller.
			 */
			struct strbuf sb = STRBUF_INIT;
			strbuf_addbuf(&sb, &dir->basebuf);
			strbuf_addstr(&sb, dir->exclude_per_dir);
			pl->src = strbuf_detach(&sb, NULL);
			add_patterns(pl->src, pl->src, stk->baselen, pl, istate,
				     untracked ? &oid_stat : NULL);
		}
		/*
		 * NEEDSWORK: when untracked cache is enabled, prep_exclude()
		 * will first be called in valid_cached_dir() then maybe many
		 * times more in last_matching_pattern(). When the cache is
		 * used, last_matching_pattern() will not be called and
		 * reading .gitignore content will be a waste.
		 *
		 * So when it's called by valid_cached_dir() and we can get
		 * .gitignore SHA-1 from the index (i.e. .gitignore is not
		 * modified on work tree), we could delay reading the
		 * .gitignore content until we absolutely need it in
		 * last_matching_pattern(). Be careful about ignore rule
		 * order, though, if you do that.
		 */
		if (untracked &&
		    !oideq(&oid_stat.oid, &untracked->exclude_oid)) {
			invalidate_gitignore(dir->untracked, untracked);
			oidcpy(&untracked->exclude_oid, &oid_stat.oid);
		}
		dir->exclude_stack = stk;
		current = stk->baselen;
	}
	strbuf_setlen(&dir->basebuf, baselen);
}

/*
 * Loads the exclude lists for the directory containing pathname, then
 * scans all exclude lists to determine whether pathname is excluded.
 * Returns the exclude_list element which matched, or NULL for
 * undecided.
 */
struct path_pattern *last_matching_pattern(struct dir_struct *dir,
				      struct index_state *istate,
				      const char *pathname,
				      int *dtype_p)
{
	int pathlen = strlen(pathname);
	const char *basename = strrchr(pathname, '/');
	basename = (basename) ? basename+1 : pathname;

	prep_exclude(dir, istate, pathname, basename-pathname);

	if (dir->pattern)
		return dir->pattern;

	return last_matching_pattern_from_lists(dir, istate, pathname, pathlen,
			basename, dtype_p);
}

/*
 * Loads the exclude lists for the directory containing pathname, then
 * scans all exclude lists to determine whether pathname is excluded.
 * Returns 1 if true, otherwise 0.
 */
int is_excluded(struct dir_struct *dir, struct index_state *istate,
		const char *pathname, int *dtype_p)
{
	struct path_pattern *pattern =
		last_matching_pattern(dir, istate, pathname, dtype_p);
	if (pattern)
		return pattern->flags & PATTERN_FLAG_NEGATIVE ? 0 : 1;
	return 0;
}

static struct dir_entry *dir_entry_new(const char *pathname, int len)
{
	struct dir_entry *ent;

	FLEX_ALLOC_MEM(ent, name, pathname, len);
	ent->len = len;
	return ent;
}

static struct dir_entry *dir_add_name(struct dir_struct *dir,
				      struct index_state *istate,
				      const char *pathname, int len)
{
	if (index_file_exists(istate, pathname, len, ignore_case))
		return NULL;

	ALLOC_GROW(dir->entries, dir->nr+1, dir->alloc);
	return dir->entries[dir->nr++] = dir_entry_new(pathname, len);
}

struct dir_entry *dir_add_ignored(struct dir_struct *dir,
				  struct index_state *istate,
				  const char *pathname, int len)
{
	if (!index_name_is_other(istate, pathname, len))
		return NULL;

	ALLOC_GROW(dir->ignored, dir->ignored_nr+1, dir->ignored_alloc);
	return dir->ignored[dir->ignored_nr++] = dir_entry_new(pathname, len);
}

enum exist_status {
	index_nonexistent = 0,
	index_directory,
	index_gitdir
};

/*
 * Do not use the alphabetically sorted index to look up
 * the directory name; instead, use the case insensitive
 * directory hash.
 */
static enum exist_status directory_exists_in_index_icase(struct index_state *istate,
							 const char *dirname, int len)
{
	struct cache_entry *ce;

	if (index_dir_exists(istate, dirname, len))
		return index_directory;

	ce = index_file_exists(istate, dirname, len, ignore_case);
	if (ce && S_ISGITLINK(ce->ce_mode))
		return index_gitdir;

	return index_nonexistent;
}

/*
 * The index sorts alphabetically by entry name, which
 * means that a gitlink sorts as '\0' at the end, while
 * a directory (which is defined not as an entry, but as
 * the files it contains) will sort with the '/' at the
 * end.
 */
static enum exist_status directory_exists_in_index(struct index_state *istate,
						   const char *dirname, int len)
{
	int pos;

	if (ignore_case)
		return directory_exists_in_index_icase(istate, dirname, len);

	pos = index_name_pos(istate, dirname, len);
	if (pos < 0)
		pos = -pos-1;
	while (pos < istate->cache_nr) {
		const struct cache_entry *ce = istate->cache[pos++];
		unsigned char endchar;

		if (strncmp(ce->name, dirname, len))
			break;
		endchar = ce->name[len];
		if (endchar > '/')
			break;
		if (endchar == '/')
			return index_directory;
		if (!endchar && S_ISGITLINK(ce->ce_mode))
			return index_gitdir;
	}
	return index_nonexistent;
}

/*
 * When we find a directory when traversing the filesystem, we
 * have three distinct cases:
 *
 *  - ignore it
 *  - see it as a directory
 *  - recurse into it
 *
 * and which one we choose depends on a combination of existing
 * git index contents and the flags passed into the directory
 * traversal routine.
 *
 * Case 1: If we *already* have entries in the index under that
 * directory name, we always recurse into the directory to see
 * all the files.
 *
 * Case 2: If we *already* have that directory name as a gitlink,
 * we always continue to see it as a gitlink, regardless of whether
 * there is an actual git directory there or not (it might not
 * be checked out as a subproject!)
 *
 * Case 3: if we didn't have it in the index previously, we
 * have a few sub-cases:
 *
 *  (a) if "show_other_directories" is true, we show it as
 *      just a directory, unless "hide_empty_directories" is
 *      also true, in which case we need to check if it contains any
 *      untracked and / or ignored files.
 *  (b) if it looks like a git directory, and we don't have
 *      'no_gitlinks' set we treat it as a gitlink, and show it
 *      as a directory.
 *  (c) otherwise, we recurse into it.
 */
static enum path_treatment treat_directory(struct dir_struct *dir,
	struct index_state *istate,
	struct untracked_cache_dir *untracked,
	const char *dirname, int len, int baselen, int exclude,
	const struct pathspec *pathspec)
{
	int nested_repo = 0;

	/* The "len-1" is to strip the final '/' */
	switch (directory_exists_in_index(istate, dirname, len-1)) {
	case index_directory:
		return path_recurse;

	case index_gitdir:
		return path_none;

	case index_nonexistent:
		if ((dir->flags & DIR_SKIP_NESTED_GIT) ||
		    !(dir->flags & DIR_NO_GITLINKS)) {
			struct strbuf sb = STRBUF_INIT;
			strbuf_addstr(&sb, dirname);
			nested_repo = is_nonbare_repository_dir(&sb);
			strbuf_release(&sb);
		}
		if (nested_repo)
			return ((dir->flags & DIR_SKIP_NESTED_GIT) ? path_none :
				(exclude ? path_excluded : path_untracked));

		if (dir->flags & DIR_SHOW_OTHER_DIRECTORIES)
			break;
		if (exclude &&
			(dir->flags & DIR_SHOW_IGNORED_TOO) &&
			(dir->flags & DIR_SHOW_IGNORED_TOO_MODE_MATCHING)) {

			/*
			 * This is an excluded directory and we are
			 * showing ignored paths that match an exclude
			 * pattern.  (e.g. show directory as ignored
			 * only if it matches an exclude pattern).
			 * This path will either be 'path_excluded`
			 * (if we are showing empty directories or if
			 * the directory is not empty), or will be
			 * 'path_none' (empty directory, and we are
			 * not showing empty directories).
			 */
			if (!(dir->flags & DIR_HIDE_EMPTY_DIRECTORIES))
				return path_excluded;

			if (read_directory_recursive(dir, istate, dirname, len,
						     untracked, 1, 1, pathspec) == path_excluded)
				return path_excluded;

			return path_none;
		}
		return path_recurse;
	}

	/* This is the "show_other_directories" case */

	if (!(dir->flags & DIR_HIDE_EMPTY_DIRECTORIES))
		return exclude ? path_excluded : path_untracked;

	untracked = lookup_untracked(dir->untracked, untracked,
				     dirname + baselen, len - baselen);

	/*
	 * If this is an excluded directory, then we only need to check if
	 * the directory contains any files.
	 */
	return read_directory_recursive(dir, istate, dirname, len,
					untracked, 1, exclude, pathspec);
}

/*
 * This is an inexact early pruning of any recursive directory
 * reading - if the path cannot possibly be in the pathspec,
 * return true, and we'll skip it early.
 */
static int simplify_away(const char *path, int pathlen,
			 const struct pathspec *pathspec)
{
	int i;

	if (!pathspec || !pathspec->nr)
		return 0;

	GUARD_PATHSPEC(pathspec,
		       PATHSPEC_FROMTOP |
		       PATHSPEC_MAXDEPTH |
		       PATHSPEC_LITERAL |
		       PATHSPEC_GLOB |
		       PATHSPEC_ICASE |
		       PATHSPEC_EXCLUDE |
		       PATHSPEC_ATTR);

	for (i = 0; i < pathspec->nr; i++) {
		const struct pathspec_item *item = &pathspec->items[i];
		int len = item->nowildcard_len;

		if (len > pathlen)
			len = pathlen;
		if (!ps_strncmp(item, item->match, path, len))
			return 0;
	}

	return 1;
}

/*
 * This function tells us whether an excluded path matches a
 * list of "interesting" pathspecs. That is, whether a path matched
 * by any of the pathspecs could possibly be ignored by excluding
 * the specified path. This can happen if:
 *
 *   1. the path is mentioned explicitly in the pathspec
 *
 *   2. the path is a directory prefix of some element in the
 *      pathspec
 */
static int exclude_matches_pathspec(const char *path, int pathlen,
				    const struct pathspec *pathspec)
{
	int i;

	if (!pathspec || !pathspec->nr)
		return 0;

	GUARD_PATHSPEC(pathspec,
		       PATHSPEC_FROMTOP |
		       PATHSPEC_MAXDEPTH |
		       PATHSPEC_LITERAL |
		       PATHSPEC_GLOB |
		       PATHSPEC_ICASE |
		       PATHSPEC_EXCLUDE);

	for (i = 0; i < pathspec->nr; i++) {
		const struct pathspec_item *item = &pathspec->items[i];
		int len = item->nowildcard_len;

		if (len == pathlen &&
		    !ps_strncmp(item, item->match, path, pathlen))
			return 1;
		if (len > pathlen &&
		    item->match[pathlen] == '/' &&
		    !ps_strncmp(item, item->match, path, pathlen))
			return 1;
	}
	return 0;
}

static int get_index_dtype(struct index_state *istate,
			   const char *path, int len)
{
	int pos;
	const struct cache_entry *ce;

	ce = index_file_exists(istate, path, len, 0);
	if (ce) {
		if (!ce_uptodate(ce))
			return DT_UNKNOWN;
		if (S_ISGITLINK(ce->ce_mode))
			return DT_DIR;
		/*
		 * Nobody actually cares about the
		 * difference between DT_LNK and DT_REG
		 */
		return DT_REG;
	}

	/* Try to look it up as a directory */
	pos = index_name_pos(istate, path, len);
	if (pos >= 0)
		return DT_UNKNOWN;
	pos = -pos-1;
	while (pos < istate->cache_nr) {
		ce = istate->cache[pos++];
		if (strncmp(ce->name, path, len))
			break;
		if (ce->name[len] > '/')
			break;
		if (ce->name[len] < '/')
			continue;
		if (!ce_uptodate(ce))
			break;	/* continue? */
		return DT_DIR;
	}
	return DT_UNKNOWN;
}

static int resolve_dtype(int dtype, struct index_state *istate,
			 const char *path, int len)
{
	struct stat st;

	if (dtype != DT_UNKNOWN)
		return dtype;
	dtype = get_index_dtype(istate, path, len);
	if (dtype != DT_UNKNOWN)
		return dtype;
	if (lstat(path, &st))
		return dtype;
	if (S_ISREG(st.st_mode))
		return DT_REG;
	if (S_ISDIR(st.st_mode))
		return DT_DIR;
	if (S_ISLNK(st.st_mode))
		return DT_LNK;
	return dtype;
}

static enum path_treatment treat_one_path(struct dir_struct *dir,
					  struct untracked_cache_dir *untracked,
					  struct index_state *istate,
					  struct strbuf *path,
					  int baselen,
					  const struct pathspec *pathspec,
					  int dtype)
{
	int exclude;
	int has_path_in_index = !!index_file_exists(istate, path->buf, path->len, ignore_case);
	enum path_treatment path_treatment;

	dtype = resolve_dtype(dtype, istate, path->buf, path->len);

	/* Always exclude indexed files */
	if (dtype != DT_DIR && has_path_in_index)
		return path_none;

	/*
	 * When we are looking at a directory P in the working tree,
	 * there are three cases:
	 *
	 * (1) P exists in the index.  Everything inside the directory P in
	 * the working tree needs to go when P is checked out from the
	 * index.
	 *
	 * (2) P does not exist in the index, but there is P/Q in the index.
	 * We know P will stay a directory when we check out the contents
	 * of the index, but we do not know yet if there is a directory
	 * P/Q in the working tree to be killed, so we need to recurse.
	 *
	 * (3) P does not exist in the index, and there is no P/Q in the index
	 * to require P to be a directory, either.  Only in this case, we
	 * know that everything inside P will not be killed without
	 * recursing.
	 */
	if ((dir->flags & DIR_COLLECT_KILLED_ONLY) &&
	    (dtype == DT_DIR) &&
	    !has_path_in_index &&
	    (directory_exists_in_index(istate, path->buf, path->len) == index_nonexistent))
		return path_none;

	exclude = is_excluded(dir, istate, path->buf, &dtype);

	/*
	 * Excluded? If we don't explicitly want to show
	 * ignored files, ignore it
	 */
	if (exclude && !(dir->flags & (DIR_SHOW_IGNORED|DIR_SHOW_IGNORED_TOO)))
		return path_excluded;

	switch (dtype) {
	default:
		return path_none;
	case DT_DIR:
		strbuf_addch(path, '/');
		path_treatment = treat_directory(dir, istate, untracked,
						 path->buf, path->len,
						 baselen, exclude, pathspec);
		/*
		 * If 1) we only want to return directories that
		 * match an exclude pattern and 2) this directory does
		 * not match an exclude pattern but all of its
		 * contents are excluded, then indicate that we should
		 * recurse into this directory (instead of marking the
		 * directory itself as an ignored path).
		 */
		if (!exclude &&
		    path_treatment == path_excluded &&
		    (dir->flags & DIR_SHOW_IGNORED_TOO) &&
		    (dir->flags & DIR_SHOW_IGNORED_TOO_MODE_MATCHING))
			return path_recurse;
		return path_treatment;
	case DT_REG:
	case DT_LNK:
		return exclude ? path_excluded : path_untracked;
	}
}

static enum path_treatment treat_path_fast(struct dir_struct *dir,
					   struct untracked_cache_dir *untracked,
					   struct cached_dir *cdir,
					   struct index_state *istate,
					   struct strbuf *path,
					   int baselen,
					   const struct pathspec *pathspec)
{
	strbuf_setlen(path, baselen);
	if (!cdir->ucd) {
		strbuf_addstr(path, cdir->file);
		return path_untracked;
	}
	strbuf_addstr(path, cdir->ucd->name);
	/* treat_one_path() does this before it calls treat_directory() */
	strbuf_complete(path, '/');
	if (cdir->ucd->check_only)
		/*
		 * check_only is set as a result of treat_directory() getting
		 * to its bottom. Verify again the same set of directories
		 * with check_only set.
		 */
		return read_directory_recursive(dir, istate, path->buf, path->len,
						cdir->ucd, 1, 0, pathspec);
	/*
	 * We get path_recurse in the first run when
	 * directory_exists_in_index() returns index_nonexistent. We
	 * are sure that new changes in the index does not impact the
	 * outcome. Return now.
	 */
	return path_recurse;
}

static enum path_treatment treat_path(struct dir_struct *dir,
				      struct untracked_cache_dir *untracked,
				      struct cached_dir *cdir,
				      struct index_state *istate,
				      struct strbuf *path,
				      int baselen,
				      const struct pathspec *pathspec)
{
	if (!cdir->d_name)
		return treat_path_fast(dir, untracked, cdir, istate, path,
				       baselen, pathspec);
	if (is_dot_or_dotdot(cdir->d_name) || !fspathcmp(cdir->d_name, ".git"))
		return path_none;
	strbuf_setlen(path, baselen);
	strbuf_addstr(path, cdir->d_name);
	if (simplify_away(path->buf, path->len, pathspec))
		return path_none;

	return treat_one_path(dir, untracked, istate, path, baselen, pathspec,
			      cdir->d_type);
}

static void add_untracked(struct untracked_cache_dir *dir, const char *name)
{
	if (!dir)
		return;
	ALLOC_GROW(dir->untracked, dir->untracked_nr + 1,
		   dir->untracked_alloc);
	dir->untracked[dir->untracked_nr++] = xstrdup(name);
}

static int valid_cached_dir(struct dir_struct *dir,
			    struct untracked_cache_dir *untracked,
			    struct index_state *istate,
			    struct strbuf *path,
			    int check_only)
{
	struct stat st;

	if (!untracked)
		return 0;

	/*
	 * With fsmonitor, we can trust the untracked cache's valid field.
	 */
	refresh_fsmonitor(istate);
	if (!(dir->untracked->use_fsmonitor && untracked->valid)) {
		if (lstat(path->len ? path->buf : ".", &st)) {
			memset(&untracked->stat_data, 0, sizeof(untracked->stat_data));
			return 0;
		}
		if (!untracked->valid ||
			match_stat_data_racy(istate, &untracked->stat_data, &st)) {
			fill_stat_data(&untracked->stat_data, &st);
			return 0;
		}
	}

	if (untracked->check_only != !!check_only)
		return 0;

	/*
	 * prep_exclude will be called eventually on this directory,
	 * but it's called much later in last_matching_pattern(). We
	 * need it now to determine the validity of the cache for this
	 * path. The next calls will be nearly no-op, the way
	 * prep_exclude() is designed.
	 */
	if (path->len && path->buf[path->len - 1] != '/') {
		strbuf_addch(path, '/');
		prep_exclude(dir, istate, path->buf, path->len);
		strbuf_setlen(path, path->len - 1);
	} else
		prep_exclude(dir, istate, path->buf, path->len);

	/* hopefully prep_exclude() haven't invalidated this entry... */
	return untracked->valid;
}

static int open_cached_dir(struct cached_dir *cdir,
			   struct dir_struct *dir,
			   struct untracked_cache_dir *untracked,
			   struct index_state *istate,
			   struct strbuf *path,
			   int check_only)
{
	const char *c_path;

	memset(cdir, 0, sizeof(*cdir));
	cdir->untracked = untracked;
	if (valid_cached_dir(dir, untracked, istate, path, check_only))
		return 0;
	c_path = path->len ? path->buf : ".";
	cdir->fdir = opendir(c_path);
	if (!cdir->fdir)
		warning_errno(_("could not open directory '%s'"), c_path);
	if (dir->untracked) {
		invalidate_directory(dir->untracked, untracked);
		dir->untracked->dir_opened++;
	}
	if (!cdir->fdir)
		return -1;
	return 0;
}

static int read_cached_dir(struct cached_dir *cdir)
{
	struct dirent *de;

	if (cdir->fdir) {
		de = readdir(cdir->fdir);
		if (!de) {
			cdir->d_name = NULL;
			cdir->d_type = DT_UNKNOWN;
			return -1;
		}
		cdir->d_name = de->d_name;
		cdir->d_type = DTYPE(de);
		return 0;
	}
	while (cdir->nr_dirs < cdir->untracked->dirs_nr) {
		struct untracked_cache_dir *d = cdir->untracked->dirs[cdir->nr_dirs];
		if (!d->recurse) {
			cdir->nr_dirs++;
			continue;
		}
		cdir->ucd = d;
		cdir->nr_dirs++;
		return 0;
	}
	cdir->ucd = NULL;
	if (cdir->nr_files < cdir->untracked->untracked_nr) {
		struct untracked_cache_dir *d = cdir->untracked;
		cdir->file = d->untracked[cdir->nr_files++];
		return 0;
	}
	return -1;
}

static void close_cached_dir(struct cached_dir *cdir)
{
	if (cdir->fdir)
		closedir(cdir->fdir);
	/*
	 * We have gone through this directory and found no untracked
	 * entries. Mark it valid.
	 */
	if (cdir->untracked) {
		cdir->untracked->valid = 1;
		cdir->untracked->recurse = 1;
	}
}

static void add_path_to_appropriate_result_list(struct dir_struct *dir,
	struct untracked_cache_dir *untracked,
	struct cached_dir *cdir,
	struct index_state *istate,
	struct strbuf *path,
	int baselen,
	const struct pathspec *pathspec,
	enum path_treatment state)
{
	/* add the path to the appropriate result list */
	switch (state) {
	case path_excluded:
		if (dir->flags & DIR_SHOW_IGNORED)
			dir_add_name(dir, istate, path->buf, path->len);
		else if ((dir->flags & DIR_SHOW_IGNORED_TOO) ||
			((dir->flags & DIR_COLLECT_IGNORED) &&
			exclude_matches_pathspec(path->buf, path->len,
						 pathspec)))
			dir_add_ignored(dir, istate, path->buf, path->len);
		break;

	case path_untracked:
		if (dir->flags & DIR_SHOW_IGNORED)
			break;
		dir_add_name(dir, istate, path->buf, path->len);
		if (cdir->fdir)
			add_untracked(untracked, path->buf + baselen);
		break;

	default:
		break;
	}
}

/*
 * Read a directory tree. We currently ignore anything but
 * directories, regular files and symlinks. That's because git
 * doesn't handle them at all yet. Maybe that will change some
 * day.
 *
 * Also, we ignore the name ".git" (even if it is not a directory).
 * That likely will not change.
 *
 * If 'stop_at_first_file' is specified, 'path_excluded' is returned
 * to signal that a file was found. This is the least significant value that
 * indicates that a file was encountered that does not depend on the order of
 * whether an untracked or exluded path was encountered first.
 *
 * Returns the most significant path_treatment value encountered in the scan.
 * If 'stop_at_first_file' is specified, `path_excluded` is the most
 * significant path_treatment value that will be returned.
 */

static enum path_treatment read_directory_recursive(struct dir_struct *dir,
	struct index_state *istate, const char *base, int baselen,
	struct untracked_cache_dir *untracked, int check_only,
	int stop_at_first_file, const struct pathspec *pathspec)
{
	/*
	 * WARNING WARNING WARNING:
	 *
	 * Any updates to the traversal logic here may need corresponding
	 * updates in treat_leading_path().  See the commit message for the
	 * commit adding this warning as well as the commit preceding it
	 * for details.
	 */

	struct cached_dir cdir;
	enum path_treatment state, subdir_state, dir_state = path_none;
	struct strbuf path = STRBUF_INIT;

	strbuf_add(&path, base, baselen);

	if (open_cached_dir(&cdir, dir, untracked, istate, &path, check_only))
		goto out;

	if (untracked)
		untracked->check_only = !!check_only;

	while (!read_cached_dir(&cdir)) {
		/* check how the file or directory should be treated */
		state = treat_path(dir, untracked, &cdir, istate, &path,
				   baselen, pathspec);

		if (state > dir_state)
			dir_state = state;

		/* recurse into subdir if instructed by treat_path */
		if ((state == path_recurse) ||
			((state == path_untracked) &&
			 (resolve_dtype(cdir.d_type, istate, path.buf, path.len) == DT_DIR) &&
			 ((dir->flags & DIR_SHOW_IGNORED_TOO) ||
			  (pathspec &&
			   do_match_pathspec(istate, pathspec, path.buf, path.len,
					     baselen, NULL, DO_MATCH_LEADING_PATHSPEC) == MATCHED_RECURSIVELY_LEADING_PATHSPEC)))) {
			struct untracked_cache_dir *ud;
			ud = lookup_untracked(dir->untracked, untracked,
					      path.buf + baselen,
					      path.len - baselen);
			subdir_state =
				read_directory_recursive(dir, istate, path.buf,
							 path.len, ud,
							 check_only, stop_at_first_file, pathspec);
			if (subdir_state > dir_state)
				dir_state = subdir_state;

			if (pathspec &&
			    !match_pathspec(istate, pathspec, path.buf, path.len,
					    0 /* prefix */, NULL,
					    0 /* do NOT special case dirs */))
				state = path_none;
		}

		if (check_only) {
			if (stop_at_first_file) {
				/*
				 * If stopping at first file, then
				 * signal that a file was found by
				 * returning `path_excluded`. This is
				 * to return a consistent value
				 * regardless of whether an ignored or
				 * excluded file happened to be
				 * encountered 1st.
				 *
				 * In current usage, the
				 * `stop_at_first_file` is passed when
				 * an ancestor directory has matched
				 * an exclude pattern, so any found
				 * files will be excluded.
				 */
				if (dir_state >= path_excluded) {
					dir_state = path_excluded;
					break;
				}
			}

			/* abort early if maximum state has been reached */
			if (dir_state == path_untracked) {
				if (cdir.fdir)
					add_untracked(untracked, path.buf + baselen);
				break;
			}
			/* skip the dir_add_* part */
			continue;
		}

		add_path_to_appropriate_result_list(dir, untracked, &cdir,
						    istate, &path, baselen,
						    pathspec, state);
	}
	close_cached_dir(&cdir);
 out:
	strbuf_release(&path);

	return dir_state;
}

int cmp_dir_entry(const void *p1, const void *p2)
{
	const struct dir_entry *e1 = *(const struct dir_entry **)p1;
	const struct dir_entry *e2 = *(const struct dir_entry **)p2;

	return name_compare(e1->name, e1->len, e2->name, e2->len);
}

/* check if *out lexically strictly contains *in */
int check_dir_entry_contains(const struct dir_entry *out, const struct dir_entry *in)
{
	return (out->len < in->len) &&
		(out->name[out->len - 1] == '/') &&
		!memcmp(out->name, in->name, out->len);
}

static int treat_leading_path(struct dir_struct *dir,
			      struct index_state *istate,
			      const char *path, int len,
			      const struct pathspec *pathspec)
{
	/*
	 * WARNING WARNING WARNING:
	 *
	 * Any updates to the traversal logic here may need corresponding
	 * updates in read_directory_recursive().  See 777b420347 (dir:
	 * synchronize treat_leading_path() and read_directory_recursive(),
	 * 2019-12-19) and its parent commit for details.
	 */

	struct strbuf sb = STRBUF_INIT;
	struct strbuf subdir = STRBUF_INIT;
	int prevlen, baselen;
	const char *cp;
	struct cached_dir cdir;
	enum path_treatment state = path_none;

	/*
	 * For each directory component of path, we are going to check whether
	 * that path is relevant given the pathspec.  For example, if path is
	 *    foo/bar/baz/
	 * then we will ask treat_path() whether we should go into foo, then
	 * whether we should go into bar, then whether baz is relevant.
	 * Checking each is important because e.g. if path is
	 *    .git/info/
	 * then we need to check .git to know we shouldn't traverse it.
	 * If the return from treat_path() is:
	 *    * path_none, for any path, we return false.
	 *    * path_recurse, for all path components, we return true
	 *    * <anything else> for some intermediate component, we make sure
	 *        to add that path to the relevant list but return false
	 *        signifying that we shouldn't recurse into it.
	 */

	while (len && path[len - 1] == '/')
		len--;
	if (!len)
		return 1;

	memset(&cdir, 0, sizeof(cdir));
	cdir.d_type = DT_DIR;
	baselen = 0;
	prevlen = 0;
	while (1) {
		prevlen = baselen + !!baselen;
		cp = path + prevlen;
		cp = memchr(cp, '/', path + len - cp);
		if (!cp)
			baselen = len;
		else
			baselen = cp - path;
		strbuf_reset(&sb);
		strbuf_add(&sb, path, baselen);
		if (!is_directory(sb.buf))
			break;
		strbuf_reset(&sb);
		strbuf_add(&sb, path, prevlen);
		strbuf_reset(&subdir);
		strbuf_add(&subdir, path+prevlen, baselen-prevlen);
		cdir.d_name = subdir.buf;
		state = treat_path(dir, NULL, &cdir, istate, &sb, prevlen,
				    pathspec);
		if (state == path_untracked &&
		    resolve_dtype(cdir.d_type, istate, sb.buf, sb.len) == DT_DIR &&
		    (dir->flags & DIR_SHOW_IGNORED_TOO ||
		     do_match_pathspec(istate, pathspec, sb.buf, sb.len,
				       baselen, NULL, DO_MATCH_LEADING_PATHSPEC) == MATCHED_RECURSIVELY_LEADING_PATHSPEC)) {
			if (!match_pathspec(istate, pathspec, sb.buf, sb.len,
					    0 /* prefix */, NULL,
					    0 /* do NOT special case dirs */))
				state = path_none;
			add_path_to_appropriate_result_list(dir, NULL, &cdir,
							    istate,
							    &sb, baselen,
							    pathspec, state);
			state = path_recurse;
		}

		if (state != path_recurse)
			break; /* do not recurse into it */
		if (len <= baselen)
			break; /* finished checking */
	}
	add_path_to_appropriate_result_list(dir, NULL, &cdir, istate,
					    &sb, baselen, pathspec,
					    state);

	strbuf_release(&subdir);
	strbuf_release(&sb);
	return state == path_recurse;
}

static const char *get_ident_string(void)
{
	static struct strbuf sb = STRBUF_INIT;
	struct utsname uts;

	if (sb.len)
		return sb.buf;
	if (uname(&uts) < 0)
		die_errno(_("failed to get kernel name and information"));
	strbuf_addf(&sb, "Location %s, system %s", get_git_work_tree(),
		    uts.sysname);
	return sb.buf;
}

static int ident_in_untracked(const struct untracked_cache *uc)
{
	/*
	 * Previous git versions may have saved many NUL separated
	 * strings in the "ident" field, but it is insane to manage
	 * many locations, so just take care of the first one.
	 */

	return !strcmp(uc->ident.buf, get_ident_string());
}

static void set_untracked_ident(struct untracked_cache *uc)
{
	strbuf_reset(&uc->ident);
	strbuf_addstr(&uc->ident, get_ident_string());

	/*
	 * This strbuf used to contain a list of NUL separated
	 * strings, so save NUL too for backward compatibility.
	 */
	strbuf_addch(&uc->ident, 0);
}

static void new_untracked_cache(struct index_state *istate)
{
	struct untracked_cache *uc = xcalloc(1, sizeof(*uc));
	strbuf_init(&uc->ident, 100);
	uc->exclude_per_dir = ".gitignore";
	/* should be the same flags used by git-status */
	uc->dir_flags = DIR_SHOW_OTHER_DIRECTORIES | DIR_HIDE_EMPTY_DIRECTORIES;
	set_untracked_ident(uc);
	istate->untracked = uc;
	istate->cache_changed |= UNTRACKED_CHANGED;
}

void add_untracked_cache(struct index_state *istate)
{
	if (!istate->untracked) {
		new_untracked_cache(istate);
	} else {
		if (!ident_in_untracked(istate->untracked)) {
			free_untracked_cache(istate->untracked);
			new_untracked_cache(istate);
		}
	}
}

void remove_untracked_cache(struct index_state *istate)
{
	if (istate->untracked) {
		free_untracked_cache(istate->untracked);
		istate->untracked = NULL;
		istate->cache_changed |= UNTRACKED_CHANGED;
	}
}

static struct untracked_cache_dir *validate_untracked_cache(struct dir_struct *dir,
						      int base_len,
						      const struct pathspec *pathspec)
{
	struct untracked_cache_dir *root;
	static int untracked_cache_disabled = -1;

	if (!dir->untracked)
		return NULL;
	if (untracked_cache_disabled < 0)
		untracked_cache_disabled = git_env_bool("GIT_DISABLE_UNTRACKED_CACHE", 0);
	if (untracked_cache_disabled)
		return NULL;

	/*
	 * We only support $GIT_DIR/info/exclude and core.excludesfile
	 * as the global ignore rule files. Any other additions
	 * (e.g. from command line) invalidate the cache. This
	 * condition also catches running setup_standard_excludes()
	 * before setting dir->untracked!
	 */
	if (dir->unmanaged_exclude_files)
		return NULL;

	/*
	 * Optimize for the main use case only: whole-tree git
	 * status. More work involved in treat_leading_path() if we
	 * use cache on just a subset of the worktree. pathspec
	 * support could make the matter even worse.
	 */
	if (base_len || (pathspec && pathspec->nr))
		return NULL;

	/* Different set of flags may produce different results */
	if (dir->flags != dir->untracked->dir_flags ||
	    /*
	     * See treat_directory(), case index_nonexistent. Without
	     * this flag, we may need to also cache .git file content
	     * for the resolve_gitlink_ref() call, which we don't.
	     */
	    !(dir->flags & DIR_SHOW_OTHER_DIRECTORIES) ||
	    /* We don't support collecting ignore files */
	    (dir->flags & (DIR_SHOW_IGNORED | DIR_SHOW_IGNORED_TOO |
			   DIR_COLLECT_IGNORED)))
		return NULL;

	/*
	 * If we use .gitignore in the cache and now you change it to
	 * .gitexclude, everything will go wrong.
	 */
	if (dir->exclude_per_dir != dir->untracked->exclude_per_dir &&
	    strcmp(dir->exclude_per_dir, dir->untracked->exclude_per_dir))
		return NULL;

	/*
	 * EXC_CMDL is not considered in the cache. If people set it,
	 * skip the cache.
	 */
	if (dir->exclude_list_group[EXC_CMDL].nr)
		return NULL;

	if (!ident_in_untracked(dir->untracked)) {
		warning(_("untracked cache is disabled on this system or location"));
		return NULL;
	}

	if (!dir->untracked->root) {
		const int len = sizeof(*dir->untracked->root);
		dir->untracked->root = xmalloc(len);
		memset(dir->untracked->root, 0, len);
	}

	/* Validate $GIT_DIR/info/exclude and core.excludesfile */
	root = dir->untracked->root;
	if (!oideq(&dir->ss_info_exclude.oid,
		   &dir->untracked->ss_info_exclude.oid)) {
		invalidate_gitignore(dir->untracked, root);
		dir->untracked->ss_info_exclude = dir->ss_info_exclude;
	}
	if (!oideq(&dir->ss_excludes_file.oid,
		   &dir->untracked->ss_excludes_file.oid)) {
		invalidate_gitignore(dir->untracked, root);
		dir->untracked->ss_excludes_file = dir->ss_excludes_file;
	}

	/* Make sure this directory is not dropped out at saving phase */
	root->recurse = 1;
	return root;
}

int read_directory(struct dir_struct *dir, struct index_state *istate,
		   const char *path, int len, const struct pathspec *pathspec)
{
	struct untracked_cache_dir *untracked;

	trace_performance_enter();

	if (has_symlink_leading_path(path, len)) {
		trace_performance_leave("read directory %.*s", len, path);
		return dir->nr;
	}

	untracked = validate_untracked_cache(dir, len, pathspec);
	if (!untracked)
		/*
		 * make sure untracked cache code path is disabled,
		 * e.g. prep_exclude()
		 */
		dir->untracked = NULL;
	if (!len || treat_leading_path(dir, istate, path, len, pathspec))
		read_directory_recursive(dir, istate, path, len, untracked, 0, 0, pathspec);
	QSORT(dir->entries, dir->nr, cmp_dir_entry);
	QSORT(dir->ignored, dir->ignored_nr, cmp_dir_entry);

	/*
	 * If DIR_SHOW_IGNORED_TOO is set, read_directory_recursive() will
	 * also pick up untracked contents of untracked dirs; by default
	 * we discard these, but given DIR_KEEP_UNTRACKED_CONTENTS we do not.
	 */
	if ((dir->flags & DIR_SHOW_IGNORED_TOO) &&
		     !(dir->flags & DIR_KEEP_UNTRACKED_CONTENTS)) {
		int i, j;

		/* remove from dir->entries untracked contents of untracked dirs */
		for (i = j = 0; j < dir->nr; j++) {
			if (i &&
			    check_dir_entry_contains(dir->entries[i - 1], dir->entries[j])) {
				FREE_AND_NULL(dir->entries[j]);
			} else {
				dir->entries[i++] = dir->entries[j];
			}
		}

		dir->nr = i;
	}

	trace_performance_leave("read directory %.*s", len, path);
	if (dir->untracked) {
		static int force_untracked_cache = -1;
		static struct trace_key trace_untracked_stats = TRACE_KEY_INIT(UNTRACKED_STATS);

		if (force_untracked_cache < 0)
			force_untracked_cache =
				git_env_bool("GIT_FORCE_UNTRACKED_CACHE", 0);
		trace_printf_key(&trace_untracked_stats,
				 "node creation: %u\n"
				 "gitignore invalidation: %u\n"
				 "directory invalidation: %u\n"
				 "opendir: %u\n",
				 dir->untracked->dir_created,
				 dir->untracked->gitignore_invalidated,
				 dir->untracked->dir_invalidated,
				 dir->untracked->dir_opened);
		if (force_untracked_cache &&
			dir->untracked == istate->untracked &&
		    (dir->untracked->dir_opened ||
		     dir->untracked->gitignore_invalidated ||
		     dir->untracked->dir_invalidated))
			istate->cache_changed |= UNTRACKED_CHANGED;
		if (dir->untracked != istate->untracked) {
			FREE_AND_NULL(dir->untracked);
		}
	}
	return dir->nr;
}

int file_exists(const char *f)
{
	struct stat sb;
	return lstat(f, &sb) == 0;
}

int repo_file_exists(struct repository *repo, const char *path)
{
	if (repo != the_repository)
		BUG("do not know how to check file existence in arbitrary repo");

	return file_exists(path);
}

static int cmp_icase(char a, char b)
{
	if (a == b)
		return 0;
	if (ignore_case)
		return toupper(a) - toupper(b);
	return a - b;
}

/*
 * Given two normalized paths (a trailing slash is ok), if subdir is
 * outside dir, return -1.  Otherwise return the offset in subdir that
 * can be used as relative path to dir.
 */
int dir_inside_of(const char *subdir, const char *dir)
{
	int offset = 0;

	assert(dir && subdir && *dir && *subdir);

	while (*dir && *subdir && !cmp_icase(*dir, *subdir)) {
		dir++;
		subdir++;
		offset++;
	}

	/* hel[p]/me vs hel[l]/yeah */
	if (*dir && *subdir)
		return -1;

	if (!*subdir)
		return !*dir ? offset : -1; /* same dir */

	/* foo/[b]ar vs foo/[] */
	if (is_dir_sep(dir[-1]))
		return is_dir_sep(subdir[-1]) ? offset : -1;

	/* foo[/]bar vs foo[] */
	return is_dir_sep(*subdir) ? offset + 1 : -1;
}

int is_inside_dir(const char *dir)
{
	char *cwd;
	int rc;

	if (!dir)
		return 0;

	cwd = xgetcwd();
	rc = (dir_inside_of(cwd, dir) >= 0);
	free(cwd);
	return rc;
}

int is_empty_dir(const char *path)
{
	DIR *dir = opendir(path);
	struct dirent *e;
	int ret = 1;

	if (!dir)
		return 0;

	while ((e = readdir(dir)) != NULL)
		if (!is_dot_or_dotdot(e->d_name)) {
			ret = 0;
			break;
		}

	closedir(dir);
	return ret;
}

static int remove_dir_recurse(struct strbuf *path, int flag, int *kept_up)
{
	DIR *dir;
	struct dirent *e;
	int ret = 0, original_len = path->len, len, kept_down = 0;
	int only_empty = (flag & REMOVE_DIR_EMPTY_ONLY);
	int keep_toplevel = (flag & REMOVE_DIR_KEEP_TOPLEVEL);
	struct object_id submodule_head;

	if ((flag & REMOVE_DIR_KEEP_NESTED_GIT) &&
	    !resolve_gitlink_ref(path->buf, "HEAD", &submodule_head)) {
		/* Do not descend and nuke a nested git work tree. */
		if (kept_up)
			*kept_up = 1;
		return 0;
	}

	flag &= ~REMOVE_DIR_KEEP_TOPLEVEL;
	dir = opendir(path->buf);
	if (!dir) {
		if (errno == ENOENT)
			return keep_toplevel ? -1 : 0;
		else if (errno == EACCES && !keep_toplevel)
			/*
			 * An empty dir could be removable even if it
			 * is unreadable:
			 */
			return rmdir(path->buf);
		else
			return -1;
	}
	strbuf_complete(path, '/');

	len = path->len;
	while ((e = readdir(dir)) != NULL) {
		struct stat st;
		if (is_dot_or_dotdot(e->d_name))
			continue;

		strbuf_setlen(path, len);
		strbuf_addstr(path, e->d_name);
		if (lstat(path->buf, &st)) {
			if (errno == ENOENT)
				/*
				 * file disappeared, which is what we
				 * wanted anyway
				 */
				continue;
			/* fall through */
		} else if (S_ISDIR(st.st_mode)) {
			if (!remove_dir_recurse(path, flag, &kept_down))
				continue; /* happy */
		} else if (!only_empty &&
			   (!unlink(path->buf) || errno == ENOENT)) {
			continue; /* happy, too */
		}

		/* path too long, stat fails, or non-directory still exists */
		ret = -1;
		break;
	}
	closedir(dir);

	strbuf_setlen(path, original_len);
	if (!ret && !keep_toplevel && !kept_down)
		ret = (!rmdir(path->buf) || errno == ENOENT) ? 0 : -1;
	else if (kept_up)
		/*
		 * report the uplevel that it is not an error that we
		 * did not rmdir() our directory.
		 */
		*kept_up = !ret;
	return ret;
}

int remove_dir_recursively(struct strbuf *path, int flag)
{
	return remove_dir_recurse(path, flag, NULL);
}

static GIT_PATH_FUNC(git_path_info_exclude, "info/exclude")

void setup_standard_excludes(struct dir_struct *dir)
{
	dir->exclude_per_dir = ".gitignore";

	/* core.excludesfile defaulting to $XDG_CONFIG_HOME/git/ignore */
	if (!excludes_file)
		excludes_file = xdg_config_home("ignore");
	if (excludes_file && !access_or_warn(excludes_file, R_OK, 0))
		add_patterns_from_file_1(dir, excludes_file,
					 dir->untracked ? &dir->ss_excludes_file : NULL);

	/* per repository user preference */
	if (startup_info->have_repository) {
		const char *path = git_path_info_exclude();
		if (!access_or_warn(path, R_OK, 0))
			add_patterns_from_file_1(dir, path,
						 dir->untracked ? &dir->ss_info_exclude : NULL);
	}
}

int remove_path(const char *name)
{
	char *slash;

	if (unlink(name) && !is_missing_file_error(errno))
		return -1;

	slash = strrchr(name, '/');
	if (slash) {
		char *dirs = xstrdup(name);
		slash = dirs + (slash - name);
		do {
			*slash = '\0';
		} while (rmdir(dirs) == 0 && (slash = strrchr(dirs, '/')));
		free(dirs);
	}
	return 0;
}

/*
 * Frees memory within dir which was allocated for exclude lists and
 * the exclude_stack.  Does not free dir itself.
 */
void clear_directory(struct dir_struct *dir)
{
	int i, j;
	struct exclude_list_group *group;
	struct pattern_list *pl;
	struct exclude_stack *stk;

	for (i = EXC_CMDL; i <= EXC_FILE; i++) {
		group = &dir->exclude_list_group[i];
		for (j = 0; j < group->nr; j++) {
			pl = &group->pl[j];
			if (i == EXC_DIRS)
				free((char *)pl->src);
			clear_pattern_list(pl);
		}
		free(group->pl);
	}

	stk = dir->exclude_stack;
	while (stk) {
		struct exclude_stack *prev = stk->prev;
		free(stk);
		stk = prev;
	}
	strbuf_release(&dir->basebuf);
}

struct ondisk_untracked_cache {
	struct stat_data info_exclude_stat;
	struct stat_data excludes_file_stat;
	uint32_t dir_flags;
};

#define ouc_offset(x) offsetof(struct ondisk_untracked_cache, x)

struct write_data {
	int index;	   /* number of written untracked_cache_dir */
	struct ewah_bitmap *check_only; /* from untracked_cache_dir */
	struct ewah_bitmap *valid;	/* from untracked_cache_dir */
	struct ewah_bitmap *sha1_valid; /* set if exclude_sha1 is not null */
	struct strbuf out;
	struct strbuf sb_stat;
	struct strbuf sb_sha1;
};

static void stat_data_to_disk(struct stat_data *to, const struct stat_data *from)
{
	to->sd_ctime.sec  = htonl(from->sd_ctime.sec);
	to->sd_ctime.nsec = htonl(from->sd_ctime.nsec);
	to->sd_mtime.sec  = htonl(from->sd_mtime.sec);
	to->sd_mtime.nsec = htonl(from->sd_mtime.nsec);
	to->sd_dev	  = htonl(from->sd_dev);
	to->sd_ino	  = htonl(from->sd_ino);
	to->sd_uid	  = htonl(from->sd_uid);
	to->sd_gid	  = htonl(from->sd_gid);
	to->sd_size	  = htonl(from->sd_size);
}

static void write_one_dir(struct untracked_cache_dir *untracked,
			  struct write_data *wd)
{
	struct stat_data stat_data;
	struct strbuf *out = &wd->out;
	unsigned char intbuf[16];
	unsigned int intlen, value;
	int i = wd->index++;

	/*
	 * untracked_nr should be reset whenever valid is clear, but
	 * for safety..
	 */
	if (!untracked->valid) {
		untracked->untracked_nr = 0;
		untracked->check_only = 0;
	}

	if (untracked->check_only)
		ewah_set(wd->check_only, i);
	if (untracked->valid) {
		ewah_set(wd->valid, i);
		stat_data_to_disk(&stat_data, &untracked->stat_data);
		strbuf_add(&wd->sb_stat, &stat_data, sizeof(stat_data));
	}
	if (!is_null_oid(&untracked->exclude_oid)) {
		ewah_set(wd->sha1_valid, i);
		strbuf_add(&wd->sb_sha1, untracked->exclude_oid.hash,
			   the_hash_algo->rawsz);
	}

	intlen = encode_varint(untracked->untracked_nr, intbuf);
	strbuf_add(out, intbuf, intlen);

	/* skip non-recurse directories */
	for (i = 0, value = 0; i < untracked->dirs_nr; i++)
		if (untracked->dirs[i]->recurse)
			value++;
	intlen = encode_varint(value, intbuf);
	strbuf_add(out, intbuf, intlen);

	strbuf_add(out, untracked->name, strlen(untracked->name) + 1);

	for (i = 0; i < untracked->untracked_nr; i++)
		strbuf_add(out, untracked->untracked[i],
			   strlen(untracked->untracked[i]) + 1);

	for (i = 0; i < untracked->dirs_nr; i++)
		if (untracked->dirs[i]->recurse)
			write_one_dir(untracked->dirs[i], wd);
}

void write_untracked_extension(struct strbuf *out, struct untracked_cache *untracked)
{
	struct ondisk_untracked_cache *ouc;
	struct write_data wd;
	unsigned char varbuf[16];
	int varint_len;
	const unsigned hashsz = the_hash_algo->rawsz;

	ouc = xcalloc(1, sizeof(*ouc));
	stat_data_to_disk(&ouc->info_exclude_stat, &untracked->ss_info_exclude.stat);
	stat_data_to_disk(&ouc->excludes_file_stat, &untracked->ss_excludes_file.stat);
	ouc->dir_flags = htonl(untracked->dir_flags);

	varint_len = encode_varint(untracked->ident.len, varbuf);
	strbuf_add(out, varbuf, varint_len);
	strbuf_addbuf(out, &untracked->ident);

	strbuf_add(out, ouc, sizeof(*ouc));
	strbuf_add(out, untracked->ss_info_exclude.oid.hash, hashsz);
	strbuf_add(out, untracked->ss_excludes_file.oid.hash, hashsz);
	strbuf_add(out, untracked->exclude_per_dir, strlen(untracked->exclude_per_dir) + 1);
	FREE_AND_NULL(ouc);

	if (!untracked->root) {
		varint_len = encode_varint(0, varbuf);
		strbuf_add(out, varbuf, varint_len);
		return;
	}

	wd.index      = 0;
	wd.check_only = ewah_new();
	wd.valid      = ewah_new();
	wd.sha1_valid = ewah_new();
	strbuf_init(&wd.out, 1024);
	strbuf_init(&wd.sb_stat, 1024);
	strbuf_init(&wd.sb_sha1, 1024);
	write_one_dir(untracked->root, &wd);

	varint_len = encode_varint(wd.index, varbuf);
	strbuf_add(out, varbuf, varint_len);
	strbuf_addbuf(out, &wd.out);
	ewah_serialize_strbuf(wd.valid, out);
	ewah_serialize_strbuf(wd.check_only, out);
	ewah_serialize_strbuf(wd.sha1_valid, out);
	strbuf_addbuf(out, &wd.sb_stat);
	strbuf_addbuf(out, &wd.sb_sha1);
	strbuf_addch(out, '\0'); /* safe guard for string lists */

	ewah_free(wd.valid);
	ewah_free(wd.check_only);
	ewah_free(wd.sha1_valid);
	strbuf_release(&wd.out);
	strbuf_release(&wd.sb_stat);
	strbuf_release(&wd.sb_sha1);
}

static void free_untracked(struct untracked_cache_dir *ucd)
{
	int i;
	if (!ucd)
		return;
	for (i = 0; i < ucd->dirs_nr; i++)
		free_untracked(ucd->dirs[i]);
	for (i = 0; i < ucd->untracked_nr; i++)
		free(ucd->untracked[i]);
	free(ucd->untracked);
	free(ucd->dirs);
	free(ucd);
}

void free_untracked_cache(struct untracked_cache *uc)
{
	if (uc)
		free_untracked(uc->root);
	free(uc);
}

struct read_data {
	int index;
	struct untracked_cache_dir **ucd;
	struct ewah_bitmap *check_only;
	struct ewah_bitmap *valid;
	struct ewah_bitmap *sha1_valid;
	const unsigned char *data;
	const unsigned char *end;
};

static void stat_data_from_disk(struct stat_data *to, const unsigned char *data)
{
	memcpy(to, data, sizeof(*to));
	to->sd_ctime.sec  = ntohl(to->sd_ctime.sec);
	to->sd_ctime.nsec = ntohl(to->sd_ctime.nsec);
	to->sd_mtime.sec  = ntohl(to->sd_mtime.sec);
	to->sd_mtime.nsec = ntohl(to->sd_mtime.nsec);
	to->sd_dev	  = ntohl(to->sd_dev);
	to->sd_ino	  = ntohl(to->sd_ino);
	to->sd_uid	  = ntohl(to->sd_uid);
	to->sd_gid	  = ntohl(to->sd_gid);
	to->sd_size	  = ntohl(to->sd_size);
}

static int read_one_dir(struct untracked_cache_dir **untracked_,
			struct read_data *rd)
{
	struct untracked_cache_dir ud, *untracked;
	const unsigned char *data = rd->data, *end = rd->end;
	const unsigned char *eos;
	unsigned int value;
	int i;

	memset(&ud, 0, sizeof(ud));

	value = decode_varint(&data);
	if (data > end)
		return -1;
	ud.recurse	   = 1;
	ud.untracked_alloc = value;
	ud.untracked_nr	   = value;
	if (ud.untracked_nr)
		ALLOC_ARRAY(ud.untracked, ud.untracked_nr);

	ud.dirs_alloc = ud.dirs_nr = decode_varint(&data);
	if (data > end)
		return -1;
	ALLOC_ARRAY(ud.dirs, ud.dirs_nr);

	eos = memchr(data, '\0', end - data);
	if (!eos || eos == end)
		return -1;

	*untracked_ = untracked = xmalloc(st_add3(sizeof(*untracked), eos - data, 1));
	memcpy(untracked, &ud, sizeof(ud));
	memcpy(untracked->name, data, eos - data + 1);
	data = eos + 1;

	for (i = 0; i < untracked->untracked_nr; i++) {
		eos = memchr(data, '\0', end - data);
		if (!eos || eos == end)
			return -1;
		untracked->untracked[i] = xmemdupz(data, eos - data);
		data = eos + 1;
	}

	rd->ucd[rd->index++] = untracked;
	rd->data = data;

	for (i = 0; i < untracked->dirs_nr; i++) {
		if (read_one_dir(untracked->dirs + i, rd) < 0)
			return -1;
	}
	return 0;
}

static void set_check_only(size_t pos, void *cb)
{
	struct read_data *rd = cb;
	struct untracked_cache_dir *ud = rd->ucd[pos];
	ud->check_only = 1;
}

static void read_stat(size_t pos, void *cb)
{
	struct read_data *rd = cb;
	struct untracked_cache_dir *ud = rd->ucd[pos];
	if (rd->data + sizeof(struct stat_data) > rd->end) {
		rd->data = rd->end + 1;
		return;
	}
	stat_data_from_disk(&ud->stat_data, rd->data);
	rd->data += sizeof(struct stat_data);
	ud->valid = 1;
}

static void read_oid(size_t pos, void *cb)
{
	struct read_data *rd = cb;
	struct untracked_cache_dir *ud = rd->ucd[pos];
	if (rd->data + the_hash_algo->rawsz > rd->end) {
		rd->data = rd->end + 1;
		return;
	}
	hashcpy(ud->exclude_oid.hash, rd->data);
	rd->data += the_hash_algo->rawsz;
}

static void load_oid_stat(struct oid_stat *oid_stat, const unsigned char *data,
			  const unsigned char *sha1)
{
	stat_data_from_disk(&oid_stat->stat, data);
	hashcpy(oid_stat->oid.hash, sha1);
	oid_stat->valid = 1;
}

struct untracked_cache *read_untracked_extension(const void *data, unsigned long sz)
{
	struct untracked_cache *uc;
	struct read_data rd;
	const unsigned char *next = data, *end = (const unsigned char *)data + sz;
	const char *ident;
	int ident_len;
	ssize_t len;
	const char *exclude_per_dir;
	const unsigned hashsz = the_hash_algo->rawsz;
	const unsigned offset = sizeof(struct ondisk_untracked_cache);
	const unsigned exclude_per_dir_offset = offset + 2 * hashsz;

	if (sz <= 1 || end[-1] != '\0')
		return NULL;
	end--;

	ident_len = decode_varint(&next);
	if (next + ident_len > end)
		return NULL;
	ident = (const char *)next;
	next += ident_len;

	if (next + exclude_per_dir_offset + 1 > end)
		return NULL;

	uc = xcalloc(1, sizeof(*uc));
	strbuf_init(&uc->ident, ident_len);
	strbuf_add(&uc->ident, ident, ident_len);
	load_oid_stat(&uc->ss_info_exclude,
		      next + ouc_offset(info_exclude_stat),
		      next + offset);
	load_oid_stat(&uc->ss_excludes_file,
		      next + ouc_offset(excludes_file_stat),
		      next + offset + hashsz);
	uc->dir_flags = get_be32(next + ouc_offset(dir_flags));
	exclude_per_dir = (const char *)next + exclude_per_dir_offset;
	uc->exclude_per_dir = xstrdup(exclude_per_dir);
	/* NUL after exclude_per_dir is covered by sizeof(*ouc) */
	next += exclude_per_dir_offset + strlen(exclude_per_dir) + 1;
	if (next >= end)
		goto done2;

	len = decode_varint(&next);
	if (next > end || len == 0)
		goto done2;

	rd.valid      = ewah_new();
	rd.check_only = ewah_new();
	rd.sha1_valid = ewah_new();
	rd.data	      = next;
	rd.end	      = end;
	rd.index      = 0;
	ALLOC_ARRAY(rd.ucd, len);

	if (read_one_dir(&uc->root, &rd) || rd.index != len)
		goto done;

	next = rd.data;
	len = ewah_read_mmap(rd.valid, next, end - next);
	if (len < 0)
		goto done;

	next += len;
	len = ewah_read_mmap(rd.check_only, next, end - next);
	if (len < 0)
		goto done;

	next += len;
	len = ewah_read_mmap(rd.sha1_valid, next, end - next);
	if (len < 0)
		goto done;

	ewah_each_bit(rd.check_only, set_check_only, &rd);
	rd.data = next + len;
	ewah_each_bit(rd.valid, read_stat, &rd);
	ewah_each_bit(rd.sha1_valid, read_oid, &rd);
	next = rd.data;

done:
	free(rd.ucd);
	ewah_free(rd.valid);
	ewah_free(rd.check_only);
	ewah_free(rd.sha1_valid);
done2:
	if (next != end) {
		free_untracked_cache(uc);
		uc = NULL;
	}
	return uc;
}

static void invalidate_one_directory(struct untracked_cache *uc,
				     struct untracked_cache_dir *ucd)
{
	uc->dir_invalidated++;
	ucd->valid = 0;
	ucd->untracked_nr = 0;
}

/*
 * Normally when an entry is added or removed from a directory,
 * invalidating that directory is enough. No need to touch its
 * ancestors. When a directory is shown as "foo/bar/" in git-status
 * however, deleting or adding an entry may have cascading effect.
 *
 * Say the "foo/bar/file" has become untracked, we need to tell the
 * untracked_cache_dir of "foo" that "bar/" is not an untracked
 * directory any more (because "bar" is managed by foo as an untracked
 * "file").
 *
 * Similarly, if "foo/bar/file" moves from untracked to tracked and it
 * was the last untracked entry in the entire "foo", we should show
 * "foo/" instead. Which means we have to invalidate past "bar" up to
 * "foo".
 *
 * This function traverses all directories from root to leaf. If there
 * is a chance of one of the above cases happening, we invalidate back
 * to root. Otherwise we just invalidate the leaf. There may be a more
 * sophisticated way than checking for SHOW_OTHER_DIRECTORIES to
 * detect these cases and avoid unnecessary invalidation, for example,
 * checking for the untracked entry named "bar/" in "foo", but for now
 * stick to something safe and simple.
 */
static int invalidate_one_component(struct untracked_cache *uc,
				    struct untracked_cache_dir *dir,
				    const char *path, int len)
{
	const char *rest = strchr(path, '/');

	if (rest) {
		int component_len = rest - path;
		struct untracked_cache_dir *d =
			lookup_untracked(uc, dir, path, component_len);
		int ret =
			invalidate_one_component(uc, d, rest + 1,
						 len - (component_len + 1));
		if (ret)
			invalidate_one_directory(uc, dir);
		return ret;
	}

	invalidate_one_directory(uc, dir);
	return uc->dir_flags & DIR_SHOW_OTHER_DIRECTORIES;
}

void untracked_cache_invalidate_path(struct index_state *istate,
				     const char *path, int safe_path)
{
	if (!istate->untracked || !istate->untracked->root)
		return;
	if (!safe_path && !verify_path(path, 0))
		return;
	invalidate_one_component(istate->untracked, istate->untracked->root,
				 path, strlen(path));
}

void untracked_cache_remove_from_index(struct index_state *istate,
				       const char *path)
{
	untracked_cache_invalidate_path(istate, path, 1);
}

void untracked_cache_add_to_index(struct index_state *istate,
				  const char *path)
{
	untracked_cache_invalidate_path(istate, path, 1);
}

static void connect_wt_gitdir_in_nested(const char *sub_worktree,
					const char *sub_gitdir)
{
	int i;
	struct repository subrepo;
	struct strbuf sub_wt = STRBUF_INIT;
	struct strbuf sub_gd = STRBUF_INIT;

	const struct submodule *sub;

	/* If the submodule has no working tree, we can ignore it. */
	if (repo_init(&subrepo, sub_gitdir, sub_worktree))
		return;

	if (repo_read_index(&subrepo) < 0)
		die(_("index file corrupt in repo %s"), subrepo.gitdir);

	for (i = 0; i < subrepo.index->cache_nr; i++) {
		const struct cache_entry *ce = subrepo.index->cache[i];

		if (!S_ISGITLINK(ce->ce_mode))
			continue;

		while (i + 1 < subrepo.index->cache_nr &&
		       !strcmp(ce->name, subrepo.index->cache[i + 1]->name))
			/*
			 * Skip entries with the same name in different stages
			 * to make sure an entry is returned only once.
			 */
			i++;

		sub = submodule_from_path(&subrepo, &null_oid, ce->name);
		if (!sub || !is_submodule_active(&subrepo, ce->name))
			/* .gitmodules broken or inactive sub */
			continue;

		strbuf_reset(&sub_wt);
		strbuf_reset(&sub_gd);
		strbuf_addf(&sub_wt, "%s/%s", sub_worktree, sub->path);
		strbuf_addf(&sub_gd, "%s/modules/%s", sub_gitdir, sub->name);

		connect_work_tree_and_git_dir(sub_wt.buf, sub_gd.buf, 1);
	}
	strbuf_release(&sub_wt);
	strbuf_release(&sub_gd);
	repo_clear(&subrepo);
}

void connect_work_tree_and_git_dir(const char *work_tree_,
				   const char *git_dir_,
				   int recurse_into_nested)
{
	struct strbuf gitfile_sb = STRBUF_INIT;
	struct strbuf cfg_sb = STRBUF_INIT;
	struct strbuf rel_path = STRBUF_INIT;
	char *git_dir, *work_tree;

	/* Prepare .git file */
	strbuf_addf(&gitfile_sb, "%s/.git", work_tree_);
	if (safe_create_leading_directories_const(gitfile_sb.buf))
		die(_("could not create directories for %s"), gitfile_sb.buf);

	/* Prepare config file */
	strbuf_addf(&cfg_sb, "%s/config", git_dir_);
	if (safe_create_leading_directories_const(cfg_sb.buf))
		die(_("could not create directories for %s"), cfg_sb.buf);

	git_dir = real_pathdup(git_dir_, 1);
	work_tree = real_pathdup(work_tree_, 1);

	/* Write .git file */
	write_file(gitfile_sb.buf, "gitdir: %s",
		   relative_path(git_dir, work_tree, &rel_path));
	/* Update core.worktree setting */
	git_config_set_in_file(cfg_sb.buf, "core.worktree",
			       relative_path(work_tree, git_dir, &rel_path));

	strbuf_release(&gitfile_sb);
	strbuf_release(&cfg_sb);
	strbuf_release(&rel_path);

	if (recurse_into_nested)
		connect_wt_gitdir_in_nested(work_tree, git_dir);

	free(work_tree);
	free(git_dir);
}

/*
 * Migrate the git directory of the given path from old_git_dir to new_git_dir.
 */
void relocate_gitdir(const char *path, const char *old_git_dir, const char *new_git_dir)
{
	if (rename(old_git_dir, new_git_dir) < 0)
		die_errno(_("could not migrate git directory from '%s' to '%s'"),
			old_git_dir, new_git_dir);

	connect_work_tree_and_git_dir(path, new_git_dir, 0);
}