1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
3021
3022
3023
3024
3025
3026
3027
3028
3029
3030
3031
3032
3033
3034
3035
3036
3037
3038
3039
3040
3041
3042
3043
3044
3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087
3088
3089
3090
3091
3092
3093
3094
3095
3096
3097
3098
3099
3100
3101
3102
3103
3104
3105
3106
3107
3108
3109
3110
3111
3112
3113
3114
3115
3116
3117
3118
3119
3120
3121
3122
3123
3124
3125
3126
3127
3128
3129
3130
3131
3132
3133
3134
3135
3136
3137
3138
3139
3140
3141
3142
3143
3144
3145
3146
3147
3148
3149
3150
3151
3152
3153
3154
3155
3156
3157
3158
3159
3160
3161
3162
3163
3164
3165
3166
3167
3168
3169
3170
3171
3172
3173
3174
3175
3176
3177
3178
3179
3180
3181
3182
3183
3184
3185
3186
3187
3188
3189
3190
3191
3192
3193
3194
3195
3196
3197
3198
3199
3200
3201
3202
3203
3204
3205
3206
3207
3208
3209
3210
3211
3212
3213
3214
3215
3216
3217
3218
3219
3220
3221
3222
3223
3224
3225
3226
3227
3228
3229
3230
3231
3232
3233
3234
3235
3236
3237
3238
3239
3240
3241
3242
3243
3244
3245
3246
3247
3248
3249
3250
3251
3252
3253
3254
3255
3256
3257
3258
3259
3260
3261
3262
3263
3264
3265
3266
3267
3268
3269
3270
3271
3272
3273
3274
3275
3276
3277
3278
3279
3280
3281
3282
3283
3284
3285
3286
3287
3288
3289
3290
3291
3292
3293
3294
3295
3296
3297
3298
3299
3300
3301
3302
3303
3304
3305
3306
3307
3308
3309
3310
3311
3312
3313
3314
3315
3316
3317
3318
3319
3320
3321
3322
3323
3324
3325
3326
3327
3328
3329
3330
3331
3332
3333
3334
3335
3336
3337
3338
3339
3340
3341
3342
3343
3344
3345
3346
3347
3348
3349
3350
3351
3352
3353
3354
3355
3356
3357
3358
3359
3360
3361
3362
3363
3364
3365
3366
3367
3368
3369
3370
3371
3372
3373
3374
3375
3376
3377
3378
3379
3380
3381
3382
3383
3384
3385
3386
3387
3388
3389
3390
3391
3392
3393
3394
3395
3396
3397
3398
3399
3400
3401
3402
3403
3404
3405
3406
3407
3408
3409
3410
3411
3412
3413
3414
3415
3416
3417
3418
3419
3420
3421
3422
3423
3424
3425
3426
3427
3428
3429
3430
3431
3432
3433
3434
3435
3436
3437
3438
3439
3440
3441
3442
3443
3444
3445
3446
3447
3448
3449
3450
3451
3452
3453
3454
3455
3456
3457
3458
3459
3460
3461
3462
3463
3464
3465
3466
3467
3468
3469
3470
3471
3472
3473
3474
3475
3476
3477
3478
3479
3480
3481
3482
3483
3484
3485
3486
3487
3488
3489
3490
3491
3492
3493
3494
3495
3496
3497
3498
3499
3500
3501
3502
3503
3504
3505
3506
3507
3508
3509
3510
3511
3512
3513
3514
3515
3516
3517
3518
3519
3520
3521
3522
3523
3524
3525
3526
3527
3528
3529
3530
3531
3532
3533
3534
3535
3536
3537
3538
3539
3540
3541
3542
3543
3544
3545
3546
3547
3548
3549
3550
3551
3552
3553
3554
3555
3556
3557
3558
3559
3560
3561
3562
3563
3564
3565
3566
3567
3568
3569
3570
3571
3572
3573
3574
3575
3576
3577
3578
3579
3580
3581
3582
3583
3584
3585
3586
3587
3588
3589
3590
3591
3592
3593
3594
3595
3596
3597
3598
3599
3600
3601
3602
3603
3604
3605
3606
3607
3608
3609
3610
3611
3612
3613
3614
3615
3616
3617
3618
3619
3620
3621
3622
3623
3624
3625
3626
3627
3628
3629
3630
3631
3632
3633
3634
3635
3636
3637
3638
3639
3640
3641
3642
3643
3644
3645
3646
3647
3648
3649
3650
3651
3652
3653
3654
3655
3656
3657
3658
3659
3660
3661
3662
3663
3664
3665
3666
3667
3668
3669
3670
3671
3672
3673
3674
3675
3676
3677
3678
3679
3680
3681
3682
3683
3684
3685
3686
3687
3688
3689
3690
3691
3692
3693
3694
3695
3696
3697
3698
3699
3700
3701
3702
3703
3704
3705
3706
3707
3708
3709
3710
3711
3712
3713
3714
3715
3716
3717
3718
3719
3720
3721
3722
3723
3724
3725
3726
3727
3728
3729
3730
3731
3732
3733
3734
3735
3736
3737
3738
3739
3740
3741
3742
3743
3744
3745
3746
3747
3748
3749
3750
3751
3752
3753
3754
3755
3756
3757
3758
3759
3760
3761
3762
3763
3764
3765
3766
3767
3768
3769
3770
3771
3772
3773
3774
3775
3776
3777
3778
3779
3780
3781
3782
3783
3784
3785
3786
3787
3788
3789
3790
3791
3792
3793
3794
3795
3796
3797
3798
3799
3800
3801
3802
3803
3804
3805
3806
3807
3808
3809
3810
3811
3812
3813
3814
3815
3816
3817
3818
3819
3820
3821
3822
3823
3824
3825
3826
3827
3828
3829
3830
3831
3832
3833
3834
3835
3836
3837
3838
3839
3840
3841
3842
3843
3844
3845
3846
3847
3848
3849
3850
3851
3852
3853
3854
3855
3856
3857
3858
3859
3860
3861
3862
3863
3864
3865
3866
3867
3868
3869
3870
3871
3872
3873
3874
3875
3876
3877
3878
3879
3880
3881
3882
3883
3884
3885
3886
3887
3888
3889
3890
3891
3892
3893
3894
3895
3896
3897
3898
3899
3900
3901
3902
3903
3904
3905
3906
3907
3908
3909
3910
3911
3912
3913
3914
3915
3916
3917
3918
3919
3920
3921
3922
3923
3924
3925
3926
3927
3928
3929
3930
3931
3932
3933
3934
3935
3936
3937
3938
3939
3940
3941
3942
3943
3944
3945
3946
3947
3948
3949
3950
3951
3952
3953
3954
3955
3956
3957
3958
3959
3960
3961
3962
3963
3964
3965
3966
3967
3968
3969
3970
3971
3972
3973
3974
3975
3976
3977
3978
3979
3980
3981
3982
3983
3984
3985
3986
3987
3988
3989
3990
3991
3992
3993
3994
3995
3996
3997
3998
3999
4000
4001
4002
4003
4004
4005
4006
4007
4008
4009
4010
4011
4012
4013
4014
4015
4016
4017
4018
4019
4020
4021
4022
4023
4024
4025
4026
4027
4028
4029
4030
4031
4032
4033
4034
4035
4036
4037
4038
4039
4040
4041
4042
4043
4044
4045
4046
4047
4048
4049
4050
4051
4052
4053
4054
4055
4056
4057
4058
4059
4060
4061
4062
4063
4064
4065
4066
4067
4068
4069
4070
4071
4072
4073
4074
4075
4076
4077
4078
4079
4080
4081
4082
4083
4084
4085
4086
4087
4088
4089
4090
4091
4092
4093
4094
4095
4096
4097
4098
4099
4100
4101
4102
4103
4104
4105
4106
4107
4108
4109
4110
4111
4112
4113
4114
4115
4116
4117
4118
4119
4120
4121
4122
4123
4124
4125
4126
4127
4128
4129
4130
4131
4132
4133
4134
4135
4136
4137
4138
4139
4140
4141
4142
4143
4144
4145
4146
4147
4148
4149
4150
4151
4152
4153
4154
4155
4156
4157
4158
4159
4160
4161
4162
4163
4164
4165
4166
4167
4168
4169
4170
4171
4172
4173
4174
4175
4176
4177
4178
4179
4180
4181
4182
4183
4184
4185
4186
4187
4188
4189
4190
4191
4192
4193
4194
4195
4196
4197
4198
4199
4200
4201
4202
4203
4204
4205
4206
4207
4208
4209
4210
4211
4212
4213
4214
4215
4216
4217
4218
4219
4220
4221
4222
4223
4224
4225
4226
4227
4228
4229
4230
4231
4232
4233
4234
4235
4236
4237
4238
4239
4240
4241
4242
4243
4244
4245
4246
4247
4248
4249
4250
4251
4252
4253
4254
4255
4256
4257
4258
4259
4260
4261
4262
4263
4264
4265
4266
4267
4268
4269
4270
4271
4272
4273
4274
4275
4276
4277
4278
4279
4280
4281
4282
4283
4284
4285
4286
4287
4288
4289
4290
4291
4292
4293
4294
4295
4296
4297
4298
4299
4300
4301
4302
4303
4304
4305
4306
4307
4308
4309
4310
4311
4312
4313
4314
4315
4316
4317
4318
4319
4320
4321
4322
4323
4324
4325
4326
4327
4328
4329
4330
4331
4332
4333
4334
4335
4336
4337
4338
4339
4340
4341
4342
4343
4344
4345
4346
4347
4348
4349
4350
4351
4352
4353
4354
4355
4356
4357
4358
4359
4360
4361
4362
4363
4364
4365
4366
4367
4368
4369
4370
4371
4372
4373
4374
4375
4376
4377
4378
4379
4380
4381
4382
4383
4384
4385
4386
4387
4388
4389
4390
4391
4392
4393
4394
4395
4396
4397
4398
4399
4400
4401
4402
4403
4404
4405
4406
4407
4408
4409
4410
4411
4412
4413
4414
4415
4416
4417
4418
4419
4420
4421
4422
4423
4424
4425
4426
4427
4428
4429
4430
4431
4432
4433
4434
4435
4436
4437
4438
4439
4440
4441
4442
4443
4444
4445
4446
4447
4448
4449
4450
4451
4452
4453
4454
4455
4456
4457
4458
4459
4460
4461
4462
4463
4464
4465
4466
4467
4468
4469
4470
4471
4472
4473
4474
4475
4476
4477
4478
4479
4480
4481
4482
4483
4484
4485
4486
4487
4488
4489
4490
4491
4492
4493
4494
4495
4496
4497
4498
4499
4500
4501
4502
4503
4504
4505
4506
4507
4508
4509
4510
4511
4512
4513
4514
4515
4516
4517
4518
4519
4520
4521
4522
4523
4524
4525
4526
4527
4528
4529
4530
4531
4532
4533
4534
4535
4536
4537
4538
4539
4540
4541
4542
4543
4544
4545
4546
4547
4548
4549
4550
4551
4552
4553
4554
4555
4556
4557
4558
4559
4560
4561
4562
4563
4564
4565
4566
4567
4568
4569
4570
4571
4572
4573
4574
4575
4576
4577
4578
4579
4580
4581
4582
4583
4584
4585
4586
4587
4588
4589
4590
4591
4592
4593
4594
4595
4596
4597
4598
4599
4600
4601
4602
4603
4604
4605
4606
4607
4608
4609
4610
4611
4612
4613
4614
4615
4616
4617
4618
4619
4620
4621
4622
4623
4624
4625
4626
4627
4628
4629
4630
4631
4632
4633
4634
4635
4636
4637
4638
4639
4640
4641
4642
4643
4644
4645
4646
4647
4648
4649
4650
4651
4652
4653
4654
4655
4656
4657
4658
4659
4660
4661
4662
4663
4664
4665
4666
4667
4668
4669
4670
4671
4672
4673
4674
4675
4676
4677
4678
4679
4680
4681
4682
4683
4684
4685
4686
4687
4688
4689
4690
4691
4692
4693
4694
4695
4696
4697
4698
4699
4700
4701
4702
4703
4704
4705
4706
4707
4708
4709
4710
4711
4712
4713
4714
4715
4716
4717
4718
4719
4720
4721
4722
4723
4724
4725
4726
4727
4728
4729
4730
4731
4732
4733
4734
4735
4736
4737
4738
4739
4740
4741
4742
4743
4744
4745
4746
4747
4748
4749
4750
4751
4752
4753
4754
4755
4756
4757
4758
4759
4760
4761
4762
4763
4764
4765
4766
4767
4768
4769
4770
4771
4772
4773
4774
4775
4776
4777
4778
4779
4780
4781
4782
4783
4784
4785
4786
4787
4788
4789
4790
4791
4792
4793
4794
4795
4796
4797
4798
4799
4800
4801
4802
4803
4804
4805
4806
4807
4808
4809
4810
4811
4812
4813
4814
4815
4816
4817
4818
4819
4820
4821
4822
4823
4824
4825
4826
4827
4828
4829
4830
4831
4832
4833
4834
4835
4836
4837
4838
4839
4840
4841
4842
4843
4844
4845
4846
4847
4848
4849
4850
4851
4852
4853
4854
4855
4856
4857
4858
4859
4860
4861
4862
4863
4864
4865
4866
4867
4868
4869
4870
4871
4872
4873
4874
4875
4876
4877
4878
4879
4880
4881
4882
4883
4884
4885
4886
4887
4888
4889
4890
4891
4892
4893
4894
4895
4896
4897
4898
4899
4900
4901
4902
4903
4904
4905
4906
4907
4908
4909
4910
4911
4912
4913
4914
4915
4916
4917
4918
4919
4920
4921
4922
4923
4924
4925
4926
4927
4928
4929
4930
4931
4932
4933
4934
4935
4936
4937
4938
4939
4940
4941
4942
4943
4944
4945
4946
4947
4948
4949
4950
4951
4952
4953
4954
4955
4956
4957
4958
4959
4960
4961
4962
4963
4964
4965
4966
4967
4968
4969
4970
4971
4972
4973
4974
4975
4976
4977
4978
4979
4980
4981
4982
4983
4984
4985
4986
4987
4988
4989
4990
4991
4992
4993
4994
4995
4996
4997
4998
4999
5000
5001
5002
5003
5004
5005
5006
5007
5008
5009
5010
5011
5012
5013
5014
5015
5016
5017
5018
5019
5020
5021
5022
5023
5024
5025
5026
5027
5028
5029
5030
5031
5032
5033
5034
5035
5036
5037
5038
5039
5040
5041
5042
5043
5044
5045
5046
5047
5048
5049
5050
5051
5052
5053
5054
5055
5056
5057
5058
5059
5060
5061
5062
5063
5064
5065
5066
5067
5068
5069
5070
5071
5072
5073
5074
5075
5076
5077
5078
5079
5080
5081
5082
5083
5084
5085
5086
5087
5088
5089
5090
5091
5092
5093
5094
5095
5096
5097
5098
5099
5100
5101
5102
5103
5104
5105
5106
5107
5108
5109
5110
5111
5112
5113
5114
5115
5116
5117
5118
5119
5120
5121
5122
5123
5124
5125
5126
5127
5128
5129
5130
5131
5132
5133
5134
5135
5136
5137
5138
5139
5140
5141
5142
5143
5144
5145
5146
5147
5148
5149
5150
5151
5152
5153
5154
5155
5156
5157
5158
5159
5160
5161
5162
5163
5164
5165
5166
5167
5168
5169
5170
5171
5172
5173
5174
5175
5176
5177
5178
5179
5180
5181
5182
5183
5184
5185
5186
5187
5188
5189
5190
5191
5192
5193
5194
5195
5196
5197
5198
5199
5200
5201
5202
5203
5204
5205
5206
5207
5208
5209
5210
5211
5212
5213
5214
5215
5216
5217
5218
5219
5220
5221
5222
5223
5224
5225
5226
5227
5228
5229
5230
5231
5232
5233
5234
5235
5236
5237
5238
5239
5240
5241
5242
5243
5244
5245
5246
5247
5248
5249
5250
5251
5252
5253
5254
5255
5256
5257
5258
5259
5260
5261
5262
5263
5264
5265
5266
5267
5268
5269
5270
5271
5272
5273
5274
5275
5276
5277
5278
5279
5280
5281
5282
5283
5284
5285
5286
5287
5288
5289
5290
5291
5292
5293
5294
5295
5296
5297
5298
5299
5300
5301
5302
5303
5304
5305
5306
5307
5308
5309
5310
5311
5312
5313
5314
5315
5316
5317
5318
5319
5320
5321
5322
5323
5324
5325
5326
5327
5328
5329
5330
5331
5332
5333
5334
5335
5336
5337
5338
5339
5340
5341
5342
5343
5344
5345
5346
5347
5348
5349
5350
5351
5352
5353
5354
5355
5356
5357
5358
5359
5360
5361
5362
5363
5364
5365
5366
5367
5368
5369
5370
5371
5372
5373
5374
5375
5376
5377
5378
5379
5380
5381
5382
5383
5384
5385
5386
5387
5388
5389
5390
5391
5392
5393
5394
5395
5396
5397
5398
5399
5400
5401
5402
5403
5404
5405
5406
5407
5408
5409
5410
5411
5412
5413
5414
5415
5416
5417
5418
5419
5420
5421
5422
5423
5424
5425
5426
5427
5428
5429
5430
5431
5432
5433
5434
5435
5436
5437
5438
5439
5440
5441
5442
5443
5444
5445
5446
5447
5448
5449
5450
5451
5452
5453
5454
5455
5456
5457
5458
5459
5460
5461
5462
5463
5464
5465
5466
5467
5468
5469
5470
5471
5472
5473
5474
5475
5476
5477
5478
5479
5480
5481
5482
5483
5484
5485
5486
5487
5488
5489
5490
5491
5492
5493
5494
5495
5496
5497
5498
5499
5500
5501
5502
5503
5504
5505
5506
5507
5508
5509
5510
5511
5512
5513
5514
5515
5516
5517
5518
5519
5520
5521
5522
5523
5524
5525
5526
5527
5528
5529
5530
5531
5532
5533
5534
5535
5536
5537
5538
5539
5540
5541
5542
5543
5544
5545
5546
5547
5548
5549
5550
5551
5552
5553
5554
5555
5556
5557
5558
5559
5560
5561
5562
5563
5564
5565
5566
5567
5568
5569
5570
5571
5572
5573
5574
5575
5576
5577
5578
5579
5580
5581
5582
5583
5584
5585
5586
5587
5588
5589
5590
5591
5592
5593
5594
5595
5596
5597
5598
5599
5600
5601
5602
5603
5604
5605
5606
5607
5608
5609
5610
5611
5612
5613
5614
5615
5616
5617
5618
5619
5620
5621
5622
5623
5624
5625
5626
5627
5628
5629
5630
5631
5632
5633
5634
5635
5636
5637
5638
5639
5640
5641
5642
5643
5644
5645
5646
5647
5648
5649
5650
5651
5652
5653
5654
5655
5656
5657
5658
5659
5660
5661
5662
5663
5664
5665
5666
5667
5668
5669
5670
5671
5672
5673
5674
5675
5676
5677
5678
5679
5680
5681
5682
5683
5684
5685
5686
5687
5688
5689
5690
5691
5692
5693
5694
5695
5696
5697
5698
5699
5700
5701
5702
5703
5704
5705
5706
5707
5708
5709
5710
5711
5712
5713
5714
5715
5716
5717
5718
5719
5720
5721
5722
5723
5724
5725
5726
5727
5728
5729
5730
5731
5732
5733
5734
5735
5736
5737
5738
5739
5740
5741
5742
5743
5744
5745
5746
5747
5748
5749
5750
5751
5752
5753
5754
5755
5756
5757
5758
5759
5760
5761
5762
5763
5764
5765
5766
5767
5768
5769
5770
5771
5772
5773
5774
5775
5776
5777
5778
5779
5780
5781
5782
5783
5784
5785
5786
5787
5788
5789
5790
5791
5792
5793
5794
5795
5796
5797
5798
5799
5800
5801
5802
5803
5804
5805
5806
5807
5808
5809
5810
5811
5812
5813
5814
5815
5816
5817
5818
5819
5820
5821
5822
5823
5824
5825
5826
5827
5828
5829
5830
5831
5832
5833
5834
5835
5836
5837
5838
5839
5840
5841
5842
5843
5844
5845
5846
5847
5848
5849
5850
5851
5852
5853
5854
5855
5856
5857
5858
5859
5860
5861
5862
5863
5864
5865
5866
5867
5868
5869
5870
5871
5872
5873
5874
5875
5876
5877
5878
5879
5880
5881
5882
5883
5884
5885
5886
5887
5888
5889
5890
5891
5892
5893
5894
5895
5896
5897
5898
5899
5900
5901
5902
5903
5904
5905
5906
5907
5908
5909
5910
5911
5912
5913
5914
5915
5916
5917
5918
5919
5920
5921
5922
5923
5924
5925
5926
5927
5928
5929
5930
5931
5932
5933
5934
5935
5936
5937
5938
5939
5940
5941
5942
5943
5944
5945
5946
5947
5948
5949
5950
5951
5952
5953
5954
5955
5956
5957
5958
5959
5960
5961
5962
5963
5964
5965
5966
5967
5968
5969
5970
5971
5972
5973
5974
5975
5976
5977
5978
5979
5980
5981
5982
5983
5984
5985
5986
5987
5988
5989
5990
5991
5992
5993
5994
5995
5996
5997
5998
5999
6000
6001
6002
6003
6004
6005
6006
6007
6008
6009
6010
6011
6012
6013
6014
6015
6016
6017
6018
6019
6020
6021
6022
6023
6024
6025
6026
6027
6028
6029
6030
6031
6032
6033
6034
6035
6036
6037
6038
6039
6040
6041
6042
6043
6044
6045
6046
6047
6048
6049
6050
6051
6052
6053
6054
6055
6056
6057
6058
6059
6060
6061
6062
6063
6064
6065
6066
6067
6068
6069
6070
6071
6072
6073
6074
6075
6076
6077
6078
6079
6080
6081
6082
6083
6084
6085
6086
6087
6088
6089
6090
6091
6092
6093
6094
6095
6096
6097
6098
6099
6100
6101
6102
6103
6104
6105
6106
6107
6108
6109
6110
6111
6112
6113
6114
6115
6116
6117
6118
6119
6120
6121
6122
6123
6124
6125
6126
6127
6128
6129
6130
6131
6132
6133
6134
6135
6136
6137
6138
6139
6140
6141
6142
6143
6144
6145
6146
6147
6148
6149
6150
6151
6152
6153
6154
6155
6156
6157
6158
6159
6160
6161
6162
6163
6164
6165
6166
6167
6168
6169
6170
6171
6172
6173
6174
6175
6176
6177
6178
6179
6180
6181
6182
6183
6184
6185
6186
6187
6188
6189
6190
6191
6192
6193
6194
6195
6196
6197
6198
6199
6200
6201
6202
6203
6204
6205
6206
6207
6208
6209
6210
6211
6212
6213
6214
6215
6216
6217
6218
6219
6220
6221
6222
6223
6224
6225
6226
6227
6228
6229
6230
6231
6232
6233
6234
6235
6236
6237
6238
6239
6240
6241
6242
6243
6244
6245
6246
6247
6248
6249
6250
6251
6252
6253
6254
6255
6256
6257
6258
6259
6260
6261
6262
6263
6264
6265
6266
6267
6268
6269
6270
6271
6272
6273
6274
6275
6276
6277
6278
6279
6280
6281
6282
6283
6284
6285
6286
6287
6288
6289
6290
6291
6292
6293
6294
6295
6296
6297
6298
6299
6300
6301
6302
6303
6304
6305
6306
6307
6308
6309
6310
6311
6312
6313
6314
6315
6316
6317
6318
6319
6320
6321
6322
6323
6324
6325
6326
6327
6328
6329
6330
6331
6332
6333
6334
6335
6336
6337
6338
6339
6340
6341
6342
6343
6344
6345
6346
6347
6348
6349
6350
6351
6352
6353
6354
6355
6356
6357
6358
6359
6360
6361
6362
6363
6364
6365
6366
6367
6368
6369
6370
6371
6372
6373
6374
6375
6376
6377
6378
6379
6380
6381
6382
6383
6384
6385
6386
6387
6388
6389
6390
6391
6392
6393
6394
6395
6396
6397
6398
6399
6400
6401
6402
6403
6404
6405
6406
6407
6408
6409
6410
6411
6412
6413
6414
6415
6416
6417
6418
6419
6420
6421
6422
6423
6424
6425
6426
6427
6428
6429
6430
6431
6432
6433
6434
6435
6436
6437
6438
6439
6440
6441
6442
6443
6444
6445
6446
6447
6448
6449
6450
6451
6452
6453
6454
6455
6456
6457
6458
6459
6460
6461
6462
6463
6464
6465
6466
6467
6468
6469
6470
6471
6472
6473
6474
6475
6476
6477
6478
6479
6480
6481
6482
6483
6484
6485
6486
6487
6488
6489
6490
6491
6492
6493
6494
6495
6496
6497
6498
6499
6500
6501
6502
6503
6504
6505
6506
6507
6508
6509
6510
6511
6512
6513
6514
6515
6516
6517
6518
6519
6520
6521
6522
6523
6524
6525
6526
6527
6528
6529
6530
6531
6532
6533
6534
6535
6536
6537
6538
6539
6540
6541
6542
6543
6544
6545
6546
6547
6548
6549
6550
6551
6552
6553
6554
6555
6556
6557
6558
6559
6560
6561
6562
6563
6564
6565
6566
6567
6568
6569
6570
6571
6572
6573
6574
6575
6576
6577
6578
6579
6580
6581
6582
6583
6584
6585
6586
6587
6588
6589
6590
6591
6592
6593
6594
6595
6596
6597
6598
6599
6600
6601
6602
6603
6604
6605
6606
6607
6608
6609
6610
6611
6612
6613
6614
6615
6616
6617
6618
6619
6620
6621
6622
6623
6624
6625
6626
6627
6628
6629
6630
6631
6632
6633
6634
6635
6636
6637
6638
6639
6640
6641
6642
6643
6644
6645
6646
6647
6648
6649
6650
6651
6652
6653
6654
6655
6656
6657
6658
6659
6660
6661
6662
6663
6664
6665
6666
6667
6668
6669
6670
6671
6672
6673
6674
6675
6676
6677
6678
6679
6680
6681
6682
6683
6684
6685
6686
6687
6688
6689
6690
6691
6692
6693
6694
6695
6696
6697
6698
6699
6700
6701
6702
6703
6704
6705
6706
6707
6708
6709
6710
6711
6712
6713
6714
6715
6716
6717
6718
6719
6720
6721
6722
6723
6724
6725
6726
6727
6728
6729
6730
6731
6732
6733
6734
6735
6736
6737
6738
6739
6740
6741
6742
6743
6744
6745
6746
6747
6748
6749
6750
6751
6752
6753
6754
6755
6756
6757
6758
6759
6760
6761
6762
6763
6764
6765
6766
6767
6768
6769
6770
6771
6772
6773
6774
6775
6776
6777
6778
6779
6780
6781
6782
6783
6784
6785
6786
6787
6788
6789
6790
6791
6792
6793
6794
6795
6796
6797
6798
6799
6800
6801
6802
6803
6804
6805
6806
6807
6808
6809
6810
6811
6812
6813
6814
6815
6816
6817
6818
6819
6820
6821
6822
6823
6824
6825
6826
6827
6828
6829
6830
6831
6832
6833
6834
6835
6836
6837
6838
6839
6840
6841
6842
6843
6844
6845
6846
6847
6848
6849
6850
6851
6852
6853
6854
6855
6856
6857
6858
6859
6860
6861
6862
6863
6864
6865
6866
6867
6868
6869
6870
6871
6872
6873
6874
6875
6876
6877
6878
6879
6880
6881
6882
6883
6884
6885
6886
6887
6888
6889
6890
6891
6892
6893
6894
6895
6896
6897
6898
6899
6900
6901
6902
6903
6904
6905
6906
6907
6908
6909
6910
6911
6912
6913
6914
6915
6916
6917
6918
6919
6920
6921
6922
6923
6924
6925
6926
6927
6928
6929
6930
6931
6932
6933
6934
6935
6936
6937
6938
6939
6940
6941
6942
6943
6944
6945
6946
6947
6948
6949
6950
6951
6952
6953
6954
6955
6956
6957
6958
6959
6960
6961
6962
6963
6964
6965
6966
6967
6968
6969
6970
6971
6972
6973
6974
6975
6976
6977
6978
6979
6980
6981
6982
6983
6984
6985
6986
6987
6988
6989
6990
6991
6992
6993
6994
6995
6996
6997
6998
6999
7000
7001
7002
7003
7004
7005
7006
7007
7008
7009
7010
7011
7012
7013
7014
7015
7016
7017
7018
7019
7020
7021
7022
7023
7024
7025
7026
7027
7028
7029
7030
7031
7032
7033
7034
7035
7036
7037
7038
7039
7040
7041
7042
7043
7044
7045
7046
7047
7048
7049
7050
7051
7052
7053
7054
7055
7056
7057
7058
7059
7060
7061
7062
7063
7064
7065
7066
7067
7068
7069
7070
7071
7072
7073
7074
7075
7076
7077
7078
7079
7080
7081
7082
7083
7084
7085
7086
7087
7088
7089
7090
7091
7092
7093
7094
7095
7096
7097
7098
7099
7100
7101
7102
7103
7104
7105
7106
7107
7108
7109
7110
7111
7112
7113
7114
7115
7116
7117
7118
7119
7120
7121
7122
7123
7124
7125
7126
7127
7128
7129
7130
7131
7132
7133
7134
7135
7136
7137
7138
7139
7140
7141
7142
7143
7144
7145
7146
7147
7148
7149
7150
7151
7152
7153
7154
7155
7156
7157
7158
7159
7160
7161
7162
7163
7164
7165
7166
7167
7168
7169
7170
7171
7172
7173
7174
7175
7176
7177
7178
7179
7180
7181
7182
7183
7184
7185
7186
7187
7188
7189
7190
7191
7192
7193
7194
7195
7196
7197
7198
7199
7200
7201
7202
7203
7204
7205
7206
7207
7208
7209
7210
7211
7212
7213
7214
7215
7216
7217
7218
7219
7220
7221
7222
7223
7224
7225
7226
7227
7228
7229
7230
7231
7232
7233
7234
7235
7236
7237
7238
7239
7240
7241
7242
7243
7244
7245
7246
7247
7248
7249
7250
7251
7252
7253
7254
7255
7256
7257
7258
7259
7260
7261
7262
7263
7264
7265
7266
7267
7268
7269
7270
7271
7272
7273
7274
7275
7276
7277
7278
7279
7280
7281
7282
7283
7284
7285
7286
7287
7288
7289
7290
7291
7292
7293
7294
7295
7296
7297
7298
7299
7300
7301
7302
7303
7304
7305
7306
7307
7308
7309
7310
7311
7312
7313
7314
7315
7316
7317
7318
7319
7320
7321
7322
7323
7324
7325
7326
7327
7328
7329
7330
7331
7332
7333
7334
7335
7336
7337
7338
7339
7340
7341
7342
7343
7344
7345
7346
7347
7348
7349
7350
7351
7352
7353
7354
7355
7356
7357
7358
7359
7360
7361
7362
7363
7364
7365
7366
7367
7368
7369
7370
7371
7372
7373
7374
7375
7376
7377
7378
7379
7380
7381
7382
7383
7384
7385
7386
7387
7388
7389
7390
7391
7392
7393
7394
7395
7396
7397
7398
7399
7400
7401
7402
7403
7404
7405
7406
7407
7408
7409
7410
7411
7412
7413
7414
7415
7416
7417
7418
7419
7420
7421
7422
7423
7424
7425
7426
7427
7428
7429
7430
7431
7432
7433
7434
7435
7436
7437
7438
7439
7440
7441
7442
7443
7444
7445
7446
7447
7448
7449
7450
7451
7452
7453
7454
7455
7456
7457
7458
7459
7460
7461
7462
7463
7464
7465
7466
7467
7468
7469
7470
7471
7472
7473
7474
7475
7476
7477
7478
7479
7480
7481
7482
7483
7484
7485
7486
7487
7488
7489
7490
7491
7492
7493
7494
7495
7496
7497
7498
7499
7500
7501
7502
7503
7504
7505
7506
7507
7508
7509
7510
7511
7512
7513
7514
7515
7516
7517
7518
7519
7520
7521
7522
7523
7524
7525
7526
7527
7528
7529
7530
7531
7532
7533
7534
7535
7536
7537
7538
7539
7540
7541
7542
7543
7544
7545
7546
7547
7548
7549
7550
7551
7552
7553
7554
7555
7556
7557
7558
7559
7560
7561
7562
7563
7564
7565
7566
7567
7568
7569
7570
7571
7572
7573
7574
7575
7576
7577
7578
7579
7580
7581
7582
7583
7584
7585
7586
7587
7588
7589
7590
7591
7592
7593
7594
7595
7596
7597
7598
7599
7600
7601
7602
7603
7604
7605
7606
7607
7608
7609
7610
7611
7612
7613
7614
7615
7616
7617
7618
7619
7620
7621
7622
7623
7624
7625
7626
7627
7628
7629
7630
7631
7632
7633
7634
7635
7636
7637
7638
7639
7640
7641
7642
7643
7644
7645
7646
7647
7648
7649
7650
7651
7652
7653
7654
7655
7656
7657
7658
7659
7660
7661
7662
7663
7664
7665
7666
7667
7668
7669
7670
7671
7672
7673
7674
7675
7676
7677
7678
7679
7680
7681
7682
7683
7684
7685
7686
7687
7688
7689
7690
7691
7692
7693
7694
7695
7696
7697
7698
7699
7700
7701
7702
7703
7704
7705
7706
7707
7708
7709
7710
7711
7712
7713
7714
7715
7716
7717
7718
7719
7720
7721
7722
7723
7724
7725
7726
7727
7728
7729
7730
7731
7732
7733
7734
7735
7736
7737
7738
7739
7740
7741
7742
7743
7744
7745
7746
7747
7748
7749
7750
7751
7752
|
/*************************************************
* Perl-Compatible Regular Expressions *
*************************************************/
/* PCRE is a library of functions to support regular expressions whose syntax
and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Copyright (c) 1997-2013 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
* Redistributions of source code must retain the above copyright notice,
this list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above copyright
notice, this list of conditions and the following disclaimer in the
documentation and/or other materials provided with the distribution.
* Neither the name of the University of Cambridge nor the names of its
contributors may be used to endorse or promote products derived from
this software without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
POSSIBILITY OF SUCH DAMAGE.
-----------------------------------------------------------------------------
*/
/* #define ERLANG_DEBUG 1 */
/* This module contains pcre_exec(), the externally visible function that does
pattern matching using an NFA algorithm, trying to mimic Perl as closely as
possible. There are also some static supporting functions. */
/* %ExternalCopyright% */
#ifdef HAVE_CONFIG_H
#include "config.h"
#endif
#define NLBLOCK md /* Block containing newline information */
#define PSSTART start_subject /* Field containing processed string start */
#define PSEND end_subject /* Field containing processed string end */
#include "pcre_internal.h"
/* Undefine some potentially clashing cpp symbols */
#undef min
#undef max
/* The md->capture_last field uses the lower 16 bits for the last captured
substring (which can never be greater than 65535) and a bit in the top half
to mean "capture vector overflowed". This odd way of doing things was
implemented when it was realized that preserving and restoring the overflow bit
whenever the last capture number was saved/restored made for a neater
interface, and doing it this way saved on (a) another variable, which would
have increased the stack frame size (a big NO-NO in PCRE) and (b) another
separate set of save/restore instructions. The following defines are used in
implementing this. */
#define CAPLMASK 0x0000ffff /* The bits used for last_capture */
#define OVFLMASK 0xffff0000 /* The bits used for the overflow flag */
#define OVFLBIT 0x00010000 /* The bit that is set for overflow */
/* Values for setting in md->match_function_type to indicate two special types
of call to match(). We do it this way to save on using another stack variable,
as stack usage is to be discouraged. */
#define MATCH_CONDASSERT 1 /* Called to check a condition assertion */
#define MATCH_CBEGROUP 2 /* Could-be-empty unlimited repeat group */
/* Non-error returns from the match() function. Error returns are externally
defined PCRE_ERROR_xxx codes, which are all negative. */
#define MATCH_MATCH 1
#define MATCH_NOMATCH 0
/* Special internal returns from the match() function. Make them sufficiently
negative to avoid the external error codes. */
#define MATCH_ACCEPT (-999)
#define MATCH_KETRPOS (-998)
#define MATCH_ONCE (-997)
/* The next 5 must be kept together and in sequence so that a test that checks
for any one of them can use a range. */
#define MATCH_COMMIT (-996)
#define MATCH_PRUNE (-995)
#define MATCH_SKIP (-994)
#define MATCH_SKIP_ARG (-993)
#define MATCH_THEN (-992)
#define MATCH_BACKTRACK_MAX MATCH_THEN
#define MATCH_BACKTRACK_MIN MATCH_COMMIT
/* Maximum number of ints of offset to save on the stack for recursive calls.
If the offset vector is bigger, malloc is used. This should be a multiple of 3,
because the offset vector is always a multiple of 3 long. */
#define REC_STACK_SAVE_MAX 30
/* Min and max values for the common repeats; for the maxima, 0 => infinity */
static const char rep_min[] = { 0, 0, 1, 1, 0, 0 };
static const char rep_max[] = { 0, 0, 0, 0, 1, 1 };
#ifdef PCRE_DEBUG
/*************************************************
* Debugging function to print chars *
*************************************************/
/* Print a sequence of chars in printable format, stopping at the end of the
subject if the requested.
Arguments:
p points to characters
length number to print
is_subject TRUE if printing from within md->start_subject
md pointer to matching data block, if is_subject is TRUE
Returns: nothing
*/
static void
pchars(const pcre_uchar *p, int length, BOOL is_subject, match_data *md)
{
pcre_uint32 c;
BOOL utf = md->utf;
if (is_subject && length > md->end_subject - p) length = md->end_subject - p;
while (length-- > 0)
if (isprint(c = RAWUCHARINCTEST(p))) printf("%c", (char)c); else printf("\\x{%02x}", c);
}
#endif
#ifdef ERLANG_INTEGRATION
#ifdef ERLANG_DEBUG
#include <stdarg.h>
static void
edebug_printf(const char *format, ...)
{
va_list args;
va_start(args, format);
fprintf(stderr, "PCRE: ");
vfprintf(stderr, format, args);
va_end(args);
fprintf(stderr, "\r\n");
}
#endif
#endif
/*************************************************
* Match a back-reference *
*************************************************/
/* Normally, if a back reference hasn't been set, the length that is passed is
negative, so the match always fails. However, in JavaScript compatibility mode,
the length passed is zero. Note that in caseless UTF-8 mode, the number of
subject bytes matched may be different to the number of reference bytes.
Arguments:
offset index into the offset vector
eptr pointer into the subject
length length of reference to be matched (number of bytes)
md points to match data block
caseless TRUE if caseless
Returns: >= 0 the number of subject bytes matched
-1 no match
-2 partial match; always given if at end subject
*/
static int
match_ref(int offset, register PCRE_PUCHAR eptr, int length, match_data *md,
BOOL caseless)
{
PCRE_PUCHAR eptr_start = eptr;
register PCRE_PUCHAR p = md->start_subject + md->offset_vector[offset];
#ifdef SUPPORT_UTF
BOOL utf = md->utf;
#endif
#ifdef PCRE_DEBUG
if (eptr >= md->end_subject)
printf("matching subject <null>");
else
{
printf("matching subject ");
pchars(eptr, length, TRUE, md);
}
printf(" against backref ");
pchars(p, length, FALSE, md);
printf("\n");
#endif
/* Always fail if reference not set (and not JavaScript compatible - in that
case the length is passed as zero). */
if (length < 0) return -1;
/* Separate the caseless case for speed. In UTF-8 mode we can only do this
properly if Unicode properties are supported. Otherwise, we can check only
ASCII characters. */
if (caseless)
{
#ifdef SUPPORT_UTF
#ifdef SUPPORT_UCP
if (utf)
{
/* Match characters up to the end of the reference. NOTE: the number of
data units matched may differ, because in UTF-8 there are some characters
whose upper and lower case versions code have different numbers of bytes.
For example, U+023A (2 bytes in UTF-8) is the upper case version of U+2C65
(3 bytes in UTF-8); a sequence of 3 of the former uses 6 bytes, as does a
sequence of two of the latter. It is important, therefore, to check the
length along the reference, not along the subject (earlier code did this
wrong). */
PCRE_PUCHAR endptr = p + length;
while (p < endptr)
{
pcre_uint32 c, d;
const ucd_record *ur;
if (eptr >= md->end_subject) return -2; /* Partial match */
GETCHARINC(c, eptr);
GETCHARINC(d, p);
ur = GET_UCD(d);
if (c != d && c != d + ur->other_case)
{
const pcre_uint32 *pp = PRIV(ucd_caseless_sets) + ur->caseset;
for (;;)
{
if (c < *pp) return -1;
if (c == *pp++) break;
}
}
}
}
else
#endif
#endif
/* The same code works when not in UTF-8 mode and in UTF-8 mode when there
is no UCP support. */
{
while (length-- > 0)
{
pcre_uint32 cc, cp;
if (eptr >= md->end_subject) return -2; /* Partial match */
cc = RAWUCHARTEST(eptr);
cp = RAWUCHARTEST(p);
if (TABLE_GET(cp, md->lcc, cp) != TABLE_GET(cc, md->lcc, cc)) return -1;
p++;
eptr++;
}
}
}
/* In the caseful case, we can just compare the bytes, whether or not we
are in UTF-8 mode. */
else
{
while (length-- > 0)
{
if (eptr >= md->end_subject) return -2; /* Partial match */
if (RAWUCHARINCTEST(p) != RAWUCHARINCTEST(eptr)) return -1;
}
}
return (int)(eptr - eptr_start);
}
/***************************************************************************
****************************************************************************
RECURSION IN THE match() FUNCTION
The match() function is highly recursive, though not every recursive call
increases the recursive depth. Nevertheless, some regular expressions can cause
it to recurse to a great depth. I was writing for Unix, so I just let it call
itself recursively. This uses the stack for saving everything that has to be
saved for a recursive call. On Unix, the stack can be large, and this works
fine.
It turns out that on some non-Unix-like systems there are problems with
programs that use a lot of stack. (This despite the fact that every last chip
has oodles of memory these days, and techniques for extending the stack have
been known for decades.) So....
There is a fudge, triggered by defining NO_RECURSE, which avoids recursive
calls by keeping local variables that need to be preserved in blocks of memory
obtained from malloc() instead instead of on the stack. Macros are used to
achieve this so that the actual code doesn't look very different to what it
always used to.
The original heap-recursive code used longjmp(). However, it seems that this
can be very slow on some operating systems. Following a suggestion from Stan
Switzer, the use of longjmp() has been abolished, at the cost of having to
provide a unique number for each call to RMATCH. There is no way of generating
a sequence of numbers at compile time in C. I have given them names, to make
them stand out more clearly.
Crude tests on x86 Linux show a small speedup of around 5-8%. However, on
FreeBSD, avoiding longjmp() more than halves the time taken to run the standard
tests. Furthermore, not using longjmp() means that local dynamic variables
don't have indeterminate values; this has meant that the frame size can be
reduced because the result can be "passed back" by straight setting of the
variable instead of being passed in the frame.
****************************************************************************
***************************************************************************/
/* Numbers for RMATCH calls. When this list is changed, the code at HEAP_RETURN
below must be updated in sync. */
enum { RM1=1, RM2, RM3, RM4, RM5, RM6, RM7, RM8, RM9, RM10,
RM11, RM12, RM13, RM14, RM15, RM16, RM17, RM18, RM19, RM20,
RM21, RM22, RM23, RM24, RM25, RM26, RM27, RM28, RM29, RM30,
RM31, RM32, RM33, RM34, RM35, RM36, RM37, RM38, RM39, RM40,
RM41, RM42, RM43, RM44, RM45, RM46, RM47, RM48, RM49, RM50,
RM51, RM52, RM53, RM54, RM55, RM56, RM57, RM58, RM59, RM60,
RM61, RM62, RM63, RM64, RM65, RM66, RM67, RM68
};
/* These versions of the macros use the stack, as normal. There are debugging
versions and production versions. Note that the "rw" argument of RMATCH isn't
actually used in this definition. */
#ifndef NO_RECURSE
#ifdef ERLANG_INTEGRATION
#error ERLANG_INTEGRATION only together with NO_RECURSE
#endif
#define REGISTER register
#ifdef PCRE_DEBUG
#define RMATCH(ra,rb,rc,rd,re,rw) \
{ \
printf("match() called in line %d\n", __LINE__); \
rrc = match(ra,rb,mstart,rc,rd,re,rdepth+1); \
printf("to line %d\n", __LINE__); \
}
#define RRETURN(ra) \
{ \
printf("match() returned %d from line %d\n", ra, __LINE__); \
return ra; \
}
#else
#define RMATCH(ra,rb,rc,rd,re,rw) \
rrc = match(ra,rb,mstart,rc,rd,re,rdepth+1)
#define RRETURN(ra) return ra
#endif
#else
/* These versions of the macros manage a private stack on the heap. Note that
the "rd" argument of RMATCH isn't actually used in this definition. It's the md
argument of match(), which never changes. */
#define REGISTER
#define RMATCH(ra,rb,rc,rd,re,rw)\
{\
heapframe *newframe = frame->Xnextframe;\
if (newframe == NULL)\
{\
newframe = (heapframe *)(PUBL(stack_malloc))(sizeof(heapframe));\
if (newframe == NULL) RRETURN(PCRE_ERROR_NOMEMORY);\
newframe->Xnextframe = NULL;\
frame->Xnextframe = newframe;\
}\
frame->Xwhere = rw;\
newframe->Xeptr = ra;\
newframe->Xecode = rb;\
newframe->Xmstart = mstart;\
newframe->Xoffset_top = rc;\
newframe->Xeptrb = re;\
newframe->Xrdepth = frame->Xrdepth + 1;\
newframe->Xprevframe = frame;\
frame = newframe;\
DPRINTF(("restarting from line %d\n", __LINE__));\
goto HEAP_RECURSE;\
L_##rw:\
DPRINTF(("jumped back to line %d\n", __LINE__));\
}
#ifdef ERLANG_INTEGRATION
#define RRETURN(ra)\
{\
heapframe *oldframe = frame;\
frame = oldframe->Xprevframe;\
if (frame != NULL)\
{\
rrc = ra;\
goto HEAP_RETURN;\
}\
if (LOOP_LIMIT != 0) \
{ \
md->loop_limit -= LOOP_COUNT; \
} \
return ra;\
}
#else
#define RRETURN(ra)\
{\
heapframe *oldframe = frame;\
frame = oldframe->Xprevframe;\
if (frame != NULL)\
{\
rrc = ra;\
goto HEAP_RETURN;\
}\
return ra;\
}
#endif
/* Structure for remembering the local variables in a private frame */
typedef struct heapframe {
struct heapframe *Xprevframe;
struct heapframe *Xnextframe;
/* Function arguments that may change */
PCRE_PUCHAR Xeptr;
const pcre_uchar *Xecode;
PCRE_PUCHAR Xmstart;
int Xoffset_top;
eptrblock *Xeptrb;
unsigned int Xrdepth;
/* Function local variables */
PCRE_PUCHAR Xcallpat;
#ifdef SUPPORT_UTF
PCRE_PUCHAR Xcharptr;
#endif
PCRE_PUCHAR Xdata;
PCRE_PUCHAR Xnext;
PCRE_PUCHAR Xpp;
PCRE_PUCHAR Xprev;
PCRE_PUCHAR Xsaved_eptr;
recursion_info Xnew_recursive;
BOOL Xcur_is_word;
BOOL Xcondition;
BOOL Xprev_is_word;
#ifdef SUPPORT_UCP
int Xprop_type;
unsigned int Xprop_value;
int Xprop_fail_result;
int Xoclength;
pcre_uchar Xocchars[6];
#endif
int Xcodelink;
int Xctype;
unsigned int Xfc;
int Xfi;
int Xlength;
int Xmax;
int Xmin;
unsigned int Xnumber;
int Xoffset;
unsigned int Xop;
pcre_int32 Xsave_capture_last;
int Xsave_offset1, Xsave_offset2, Xsave_offset3;
int Xstacksave[REC_STACK_SAVE_MAX];
eptrblock Xnewptrb;
/* Where to jump back to */
int Xwhere;
#if defined(ERLANG_INTEGRATION)
int Xlgb;
int Xrgb;
#endif
} heapframe;
#endif
/***************************************************************************
***************************************************************************/
/*************************************************
* Match from current position *
*************************************************/
/* This function is called recursively in many circumstances. Whenever it
returns a negative (error) response, the outer incarnation must also return the
same response. */
/* These macros pack up tests that are used for partial matching, and which
appear several times in the code. We set the "hit end" flag if the pointer is
at the end of the subject and also past the start of the subject (i.e.
something has been matched). For hard partial matching, we then return
immediately. The second one is used when we already know we are past the end of
the subject. */
#define CHECK_PARTIAL()\
if (md->partial != 0 && eptr >= md->end_subject && \
eptr > md->start_used_ptr) \
{ \
md->hitend = TRUE; \
if (md->partial > 1) RRETURN(PCRE_ERROR_PARTIAL); \
}
#define SCHECK_PARTIAL()\
if (md->partial != 0 && eptr > md->start_used_ptr) \
{ \
md->hitend = TRUE; \
if (md->partial > 1) RRETURN(PCRE_ERROR_PARTIAL); \
}
/* Performance note: It might be tempting to extract commonly used fields from
the md structure (e.g. utf, end_subject) into individual variables to improve
performance. Tests using gcc on a SPARC disproved this; in the first case, it
made performance worse.
Arguments:
eptr pointer to current character in subject
ecode pointer to current position in compiled code
mstart pointer to the current match start position (can be modified
by encountering \K)
offset_top current top pointer
md pointer to "static" info for the match
eptrb pointer to chain of blocks containing eptr at start of
brackets - for testing for empty matches
rdepth the recursion depth
Returns: MATCH_MATCH if matched ) these values are >= 0
MATCH_NOMATCH if failed to match )
a negative MATCH_xxx value for PRUNE, SKIP, etc
a negative PCRE_ERROR_xxx value if aborted by an error condition
(e.g. stopped by repeated call or recursion limit)
*/
static int
match(REGISTER PCRE_PUCHAR eptr, REGISTER const pcre_uchar *ecode,
PCRE_PUCHAR mstart, int offset_top, match_data *md, eptrblock *eptrb,
unsigned int rdepth)
{
/* These variables do not need to be preserved over recursion in this function,
so they can be ordinary variables in all cases. Mark some of them with
"register" because they are used a lot in loops. */
register int rrc; /* Returns from recursive calls */
register int i; /* Used for loops not involving calls to RMATCH() */
register pcre_uint32 c; /* Character values not kept over RMATCH() calls */
register BOOL utf; /* Local copy of UTF flag for speed */
BOOL minimize, possessive; /* Quantifier options */
BOOL caseless;
int condcode;
/* When recursion is not being used, all "local" variables that have to be
preserved over calls to RMATCH() are part of a "frame". We set up the top-level
frame on the stack here; subsequent instantiations are obtained from the heap
whenever RMATCH() does a "recursion". See the macro definitions above. Putting
the top-level on the stack rather than malloc-ing them all gives a performance
boost in many cases where there is not much "recursion". */
#ifdef NO_RECURSE
#ifdef ERLANG_INTEGRATION
#define LOOP_COUNT loop_count
#define LOOP_LIMIT loop_limit
#ifdef ERLANG_DEBUG
#define EDEBUGF(X) edebug_printf X
#else
#define EDEBUGF(X)
#endif
#define COST(N) (LOOP_COUNT += (N))
#define LABEL_XCAT(A,B) A##B
#define LABEL_CAT(A,B) LABEL_XCAT(A,B)
#define COST_CHK(N) \
do { \
LOOP_COUNT += (N); \
if (LOOP_LIMIT != 0) { \
if (LOOP_COUNT > LOOP_LIMIT) { \
frame->Xwhere = __LINE__ + 100; \
goto LOOP_COUNT_BREAK; \
LABEL_CAT(L_LOOP_COUNT_,__LINE__): \
; \
} \
} \
} while (0)
register int loop_count = 0;
register int loop_limit = md->loop_limit;
heapframe *frame;
if (md->state_save) {
frame = md->state_save;
EDEBUGF(("Break restore!"));
goto LOOP_COUNT_RETURN;
}
frame = (heapframe *)md->match_frames_base;
#else
#define COST(N)
#define COST_CHK(N)
heapframe *frame = (heapframe *)md->match_frames_base;
#endif
/* Copy in the original argument variables */
frame->Xeptr = eptr;
frame->Xecode = ecode;
frame->Xmstart = mstart;
frame->Xoffset_top = offset_top;
frame->Xeptrb = eptrb;
frame->Xrdepth = rdepth;
/* This is where control jumps back to to effect "recursion" */
HEAP_RECURSE:
/* Macros make the argument variables come from the current frame */
#define eptr frame->Xeptr
#define ecode frame->Xecode
#define mstart frame->Xmstart
#define offset_top frame->Xoffset_top
#define eptrb frame->Xeptrb
#define rdepth frame->Xrdepth
/* Ditto for the local variables */
#ifdef SUPPORT_UTF
#define charptr frame->Xcharptr
#endif
#define callpat frame->Xcallpat
#define codelink frame->Xcodelink
#define data frame->Xdata
#define next frame->Xnext
#define pp frame->Xpp
#define prev frame->Xprev
#define saved_eptr frame->Xsaved_eptr
#define new_recursive frame->Xnew_recursive
#define cur_is_word frame->Xcur_is_word
#define condition frame->Xcondition
#define prev_is_word frame->Xprev_is_word
#ifdef SUPPORT_UCP
#define prop_type frame->Xprop_type
#define prop_value frame->Xprop_value
#define prop_fail_result frame->Xprop_fail_result
#define oclength frame->Xoclength
#define occhars frame->Xocchars
#endif
#define ctype frame->Xctype
#define fc frame->Xfc
#define fi frame->Xfi
#define length frame->Xlength
#define max frame->Xmax
#define min frame->Xmin
#define number frame->Xnumber
#define offset frame->Xoffset
#define op frame->Xop
#define save_capture_last frame->Xsave_capture_last
#define save_offset1 frame->Xsave_offset1
#define save_offset2 frame->Xsave_offset2
#define save_offset3 frame->Xsave_offset3
#define stacksave frame->Xstacksave
#if defined(ERLANG_INTEGRATION)
#define lgb frame->Xlgb
#define rgb frame->Xrgb
#endif
#define newptrb frame->Xnewptrb
/* When recursion is being used, local variables are allocated on the stack and
get preserved during recursion in the normal way. In this environment, fi and
i, and fc and c, can be the same variables. */
#else /* NO_RECURSE not defined */
#define COST(N)
#define COST_CHK(N)
#define fi i
#define fc c
/* Many of the following variables are used only in small blocks of the code.
My normal style of coding would have declared them within each of those blocks.
However, in order to accommodate the version of this code that uses an external
"stack" implemented on the heap, it is easier to declare them all here, so the
declarations can be cut out in a block. The only declarations within blocks
below are for variables that do not have to be preserved over a recursive call
to RMATCH(). */
#ifdef SUPPORT_UTF
const pcre_uchar *charptr;
#endif
const pcre_uchar *callpat;
const pcre_uchar *data;
const pcre_uchar *next;
PCRE_PUCHAR pp;
const pcre_uchar *prev;
PCRE_PUCHAR saved_eptr;
recursion_info new_recursive;
BOOL cur_is_word;
BOOL condition;
BOOL prev_is_word;
#ifdef SUPPORT_UCP
int prop_type;
unsigned int prop_value;
int prop_fail_result;
int oclength;
pcre_uchar occhars[6];
#endif
int codelink;
int ctype;
int length;
int max;
int min;
unsigned int number;
int offset;
unsigned int op;
pcre_int32 save_capture_last;
int save_offset1, save_offset2, save_offset3;
int stacksave[REC_STACK_SAVE_MAX];
eptrblock newptrb;
/* There is a special fudge for calling match() in a way that causes it to
measure the size of its basic stack frame when the stack is being used for
recursion. The second argument (ecode) being NULL triggers this behaviour. It
cannot normally ever be NULL. The return is the negated value of the frame
size. */
if (ecode == NULL)
{
if (rdepth == 0)
return match((PCRE_PUCHAR)&rdepth, NULL, NULL, 0, NULL, NULL, 1);
else
{
int len = (char *)&rdepth - (char *)eptr;
return (len > 0)? -len : len;
}
}
#endif /* NO_RECURSE */
/* To save space on the stack and in the heap frame, I have doubled up on some
of the local variables that are used only in localised parts of the code, but
still need to be preserved over recursive calls of match(). These macros define
the alternative names that are used. */
#define allow_zero cur_is_word
#define cbegroup condition
#define code_offset codelink
#define condassert condition
#define matched_once prev_is_word
#define foc number
#define save_mark data
/* These statements are here to stop the compiler complaining about unitialized
variables. */
#ifdef SUPPORT_UCP
prop_value = 0;
prop_fail_result = 0;
#endif
/* This label is used for tail recursion, which is used in a few cases even
when NO_RECURSE is not defined, in order to reduce the amount of stack that is
used. Thanks to Ian Taylor for noticing this possibility and sending the
original patch. */
TAIL_RECURSE:
/* OK, now we can get on with the real code of the function. Recursive calls
are specified by the macro RMATCH and RRETURN is used to return. When
NO_RECURSE is *not* defined, these just turn into a recursive call to match()
and a "return", respectively (possibly with some debugging if PCRE_DEBUG is
defined). However, RMATCH isn't like a function call because it's quite a
complicated macro. It has to be used in one particular way. This shouldn't,
however, impact performance when true recursion is being used. */
#ifdef SUPPORT_UTF
utf = md->utf; /* Local copy of the flag */
#else
utf = FALSE;
#endif
/* First check that we haven't called match() too many times, or that we
haven't exceeded the recursive call limit. */
if (md->match_call_count++ >= md->match_limit) RRETURN(PCRE_ERROR_MATCHLIMIT);
if (rdepth >= md->match_limit_recursion) RRETURN(PCRE_ERROR_RECURSIONLIMIT);
/* At the start of a group with an unlimited repeat that may match an empty
string, the variable md->match_function_type is set to MATCH_CBEGROUP. It is
done this way to save having to use another function argument, which would take
up space on the stack. See also MATCH_CONDASSERT below.
When MATCH_CBEGROUP is set, add the current subject pointer to the chain of
such remembered pointers, to be checked when we hit the closing ket, in order
to break infinite loops that match no characters. When match() is called in
other circumstances, don't add to the chain. The MATCH_CBEGROUP feature must
NOT be used with tail recursion, because the memory block that is used is on
the stack, so a new one may be required for each match(). */
if (md->match_function_type == MATCH_CBEGROUP)
{
newptrb.epb_saved_eptr = eptr;
newptrb.epb_prev = eptrb;
eptrb = &newptrb;
md->match_function_type = 0;
}
/* Now start processing the opcodes. */
for (;;)
{
COST_CHK(1);
minimize = possessive = FALSE;
op = *ecode;
EDEBUGF(("Op = %d",op));
switch(op)
{
case OP_MARK:
md->nomatch_mark = ecode + 2;
md->mark = NULL; /* In case previously set by assertion */
RMATCH(eptr, ecode + PRIV(OP_lengths)[*ecode] + ecode[1], offset_top, md,
eptrb, RM55);
if ((rrc == MATCH_MATCH || rrc == MATCH_ACCEPT) &&
md->mark == NULL) md->mark = ecode + 2;
/* A return of MATCH_SKIP_ARG means that matching failed at SKIP with an
argument, and we must check whether that argument matches this MARK's
argument. It is passed back in md->start_match_ptr (an overloading of that
variable). If it does match, we reset that variable to the current subject
position and return MATCH_SKIP. Otherwise, pass back the return code
unaltered. */
else if (rrc == MATCH_SKIP_ARG &&
STRCMP_UC_UC_TEST(ecode + 2, md->start_match_ptr) == 0)
{
md->start_match_ptr = eptr;
RRETURN(MATCH_SKIP);
}
RRETURN(rrc);
case OP_FAIL:
RRETURN(MATCH_NOMATCH);
case OP_COMMIT:
RMATCH(eptr, ecode + PRIV(OP_lengths)[*ecode], offset_top, md,
eptrb, RM52);
if (rrc != MATCH_NOMATCH) RRETURN(rrc);
RRETURN(MATCH_COMMIT);
case OP_PRUNE:
RMATCH(eptr, ecode + PRIV(OP_lengths)[*ecode], offset_top, md,
eptrb, RM51);
if (rrc != MATCH_NOMATCH) RRETURN(rrc);
RRETURN(MATCH_PRUNE);
case OP_PRUNE_ARG:
md->nomatch_mark = ecode + 2;
md->mark = NULL; /* In case previously set by assertion */
RMATCH(eptr, ecode + PRIV(OP_lengths)[*ecode] + ecode[1], offset_top, md,
eptrb, RM56);
if ((rrc == MATCH_MATCH || rrc == MATCH_ACCEPT) &&
md->mark == NULL) md->mark = ecode + 2;
if (rrc != MATCH_NOMATCH) RRETURN(rrc);
RRETURN(MATCH_PRUNE);
case OP_SKIP:
RMATCH(eptr, ecode + PRIV(OP_lengths)[*ecode], offset_top, md,
eptrb, RM53);
if (rrc != MATCH_NOMATCH) RRETURN(rrc);
md->start_match_ptr = eptr; /* Pass back current position */
RRETURN(MATCH_SKIP);
/* Note that, for Perl compatibility, SKIP with an argument does NOT set
nomatch_mark. When a pattern match ends with a SKIP_ARG for which there was
not a matching mark, we have to re-run the match, ignoring the SKIP_ARG
that failed and any that precede it (either they also failed, or were not
triggered). To do this, we maintain a count of executed SKIP_ARGs. If a
SKIP_ARG gets to top level, the match is re-run with md->ignore_skip_arg
set to the count of the one that failed. */
case OP_SKIP_ARG:
md->skip_arg_count++;
if (md->skip_arg_count <= md->ignore_skip_arg)
{
ecode += PRIV(OP_lengths)[*ecode] + ecode[1];
break;
}
RMATCH(eptr, ecode + PRIV(OP_lengths)[*ecode] + ecode[1], offset_top, md,
eptrb, RM57);
if (rrc != MATCH_NOMATCH) RRETURN(rrc);
/* Pass back the current skip name by overloading md->start_match_ptr and
returning the special MATCH_SKIP_ARG return code. This will either be
caught by a matching MARK, or get to the top, where it causes a rematch
with md->ignore_skip_arg set to the value of md->skip_arg_count. */
md->start_match_ptr = ecode + 2;
RRETURN(MATCH_SKIP_ARG);
/* For THEN (and THEN_ARG) we pass back the address of the opcode, so that
the branch in which it occurs can be determined. Overload the start of
match pointer to do this. */
case OP_THEN:
RMATCH(eptr, ecode + PRIV(OP_lengths)[*ecode], offset_top, md,
eptrb, RM54);
if (rrc != MATCH_NOMATCH) RRETURN(rrc);
md->start_match_ptr = ecode;
RRETURN(MATCH_THEN);
case OP_THEN_ARG:
md->nomatch_mark = ecode + 2;
md->mark = NULL; /* In case previously set by assertion */
RMATCH(eptr, ecode + PRIV(OP_lengths)[*ecode] + ecode[1], offset_top,
md, eptrb, RM58);
if ((rrc == MATCH_MATCH || rrc == MATCH_ACCEPT) &&
md->mark == NULL) md->mark = ecode + 2;
if (rrc != MATCH_NOMATCH) RRETURN(rrc);
md->start_match_ptr = ecode;
RRETURN(MATCH_THEN);
/* Handle an atomic group that does not contain any capturing parentheses.
This can be handled like an assertion. Prior to 8.13, all atomic groups
were handled this way. In 8.13, the code was changed as below for ONCE, so
that backups pass through the group and thereby reset captured values.
However, this uses a lot more stack, so in 8.20, atomic groups that do not
contain any captures generate OP_ONCE_NC, which can be handled in the old,
less stack intensive way.
Check the alternative branches in turn - the matching won't pass the KET
for this kind of subpattern. If any one branch matches, we carry on as at
the end of a normal bracket, leaving the subject pointer, but resetting
the start-of-match value in case it was changed by \K. */
case OP_ONCE_NC:
prev = ecode;
saved_eptr = eptr;
save_mark = md->mark;
do /* LOOP_COUNT: Ok */
{
RMATCH(eptr, ecode + 1 + LINK_SIZE, offset_top, md, eptrb, RM64);
if (rrc == MATCH_MATCH) /* Note: _not_ MATCH_ACCEPT */
{
mstart = md->start_match_ptr;
break;
}
if (rrc == MATCH_THEN)
{
next = ecode + GET(ecode,1);
if (md->start_match_ptr < next &&
(*ecode == OP_ALT || *next == OP_ALT))
rrc = MATCH_NOMATCH;
}
if (rrc != MATCH_NOMATCH) RRETURN(rrc);
ecode += GET(ecode,1);
md->mark = save_mark;
}
while (*ecode == OP_ALT);
/* If hit the end of the group (which could be repeated), fail */
if (*ecode != OP_ONCE_NC && *ecode != OP_ALT) RRETURN(MATCH_NOMATCH);
/* Continue as from after the group, updating the offsets high water
mark, since extracts may have been taken. */
do ecode += GET(ecode, 1); while (*ecode == OP_ALT);
offset_top = md->end_offset_top;
eptr = md->end_match_ptr;
/* For a non-repeating ket, just continue at this level. This also
happens for a repeating ket if no characters were matched in the group.
This is the forcible breaking of infinite loops as implemented in Perl
5.005. */
if (*ecode == OP_KET || eptr == saved_eptr)
{
ecode += 1+LINK_SIZE;
break;
}
/* The repeating kets try the rest of the pattern or restart from the
preceding bracket, in the appropriate order. The second "call" of match()
uses tail recursion, to avoid using another stack frame. */
if (*ecode == OP_KETRMIN)
{
RMATCH(eptr, ecode + 1 + LINK_SIZE, offset_top, md, eptrb, RM65);
if (rrc != MATCH_NOMATCH) RRETURN(rrc);
ecode = prev;
goto TAIL_RECURSE;
}
else /* OP_KETRMAX */
{
RMATCH(eptr, prev, offset_top, md, eptrb, RM66);
if (rrc != MATCH_NOMATCH) RRETURN(rrc);
ecode += 1 + LINK_SIZE;
goto TAIL_RECURSE;
}
/* Control never gets here */
/* Handle a capturing bracket, other than those that are possessive with an
unlimited repeat. If there is space in the offset vector, save the current
subject position in the working slot at the top of the vector. We mustn't
change the current values of the data slot, because they may be set from a
previous iteration of this group, and be referred to by a reference inside
the group. A failure to match might occur after the group has succeeded,
if something later on doesn't match. For this reason, we need to restore
the working value and also the values of the final offsets, in case they
were set by a previous iteration of the same bracket.
If there isn't enough space in the offset vector, treat this as if it were
a non-capturing bracket. Don't worry about setting the flag for the error
case here; that is handled in the code for KET. */
case OP_CBRA:
case OP_SCBRA:
number = GET2(ecode, 1+LINK_SIZE);
offset = number << 1;
#ifdef PCRE_DEBUG
printf("start bracket %d\n", number);
printf("subject=");
pchars(eptr, 16, TRUE, md);
printf("\n");
#endif
if (offset < md->offset_max)
{
save_offset1 = md->offset_vector[offset];
save_offset2 = md->offset_vector[offset+1];
save_offset3 = md->offset_vector[md->offset_end - number];
save_capture_last = md->capture_last;
save_mark = md->mark;
DPRINTF(("saving %d %d %d\n", save_offset1, save_offset2, save_offset3));
md->offset_vector[md->offset_end - number] =
(int)(eptr - md->start_subject);
for (;;) /* LOOP_COUNT: Ok */
{
if (op >= OP_SBRA) md->match_function_type = MATCH_CBEGROUP;
RMATCH(eptr, ecode + PRIV(OP_lengths)[*ecode], offset_top, md,
eptrb, RM1);
if (rrc == MATCH_ONCE) break; /* Backing up through an atomic group */
/* If we backed up to a THEN, check whether it is within the current
branch by comparing the address of the THEN that is passed back with
the end of the branch. If it is within the current branch, and the
branch is one of two or more alternatives (it either starts or ends
with OP_ALT), we have reached the limit of THEN's action, so convert
the return code to NOMATCH, which will cause normal backtracking to
happen from now on. Otherwise, THEN is passed back to an outer
alternative. This implements Perl's treatment of parenthesized groups,
where a group not containing | does not affect the current alternative,
that is, (X) is NOT the same as (X|(*F)). */
if (rrc == MATCH_THEN)
{
next = ecode + GET(ecode,1);
if (md->start_match_ptr < next &&
(*ecode == OP_ALT || *next == OP_ALT))
rrc = MATCH_NOMATCH;
}
/* Anything other than NOMATCH is passed back. */
if (rrc != MATCH_NOMATCH) RRETURN(rrc);
md->capture_last = save_capture_last;
ecode += GET(ecode, 1);
md->mark = save_mark;
if (*ecode != OP_ALT) break;
}
DPRINTF(("bracket %d failed\n", number));
md->offset_vector[offset] = save_offset1;
md->offset_vector[offset+1] = save_offset2;
md->offset_vector[md->offset_end - number] = save_offset3;
/* At this point, rrc will be one of MATCH_ONCE or MATCH_NOMATCH. */
RRETURN(rrc);
}
/* FALL THROUGH ... Insufficient room for saving captured contents. Treat
as a non-capturing bracket. */
/* VVVVVVVVVVVVVVVVVVVVVVVVV */
/* VVVVVVVVVVVVVVVVVVVVVVVVV */
DPRINTF(("insufficient capture room: treat as non-capturing\n"));
/* VVVVVVVVVVVVVVVVVVVVVVVVV */
/* VVVVVVVVVVVVVVVVVVVVVVVVV */
/* Non-capturing or atomic group, except for possessive with unlimited
repeat and ONCE group with no captures. Loop for all the alternatives.
When we get to the final alternative within the brackets, we used to return
the result of a recursive call to match() whatever happened so it was
possible to reduce stack usage by turning this into a tail recursion,
except in the case of a possibly empty group. However, now that there is
the possiblity of (*THEN) occurring in the final alternative, this
optimization is no longer always possible.
We can optimize if we know there are no (*THEN)s in the pattern; at present
this is the best that can be done.
MATCH_ONCE is returned when the end of an atomic group is successfully
reached, but subsequent matching fails. It passes back up the tree (causing
captured values to be reset) until the original atomic group level is
reached. This is tested by comparing md->once_target with the start of the
group. At this point, the return is converted into MATCH_NOMATCH so that
previous backup points can be taken. */
case OP_ONCE:
case OP_BRA:
case OP_SBRA:
DPRINTF(("start non-capturing bracket\n"));
for (;;) /* LOOP_COUNT: Ok */
{
if (op >= OP_SBRA || op == OP_ONCE)
md->match_function_type = MATCH_CBEGROUP;
/* If this is not a possibly empty group, and there are no (*THEN)s in
the pattern, and this is the final alternative, optimize as described
above. */
else if (!md->hasthen && ecode[GET(ecode, 1)] != OP_ALT)
{
ecode += PRIV(OP_lengths)[*ecode];
goto TAIL_RECURSE;
}
/* In all other cases, we have to make another call to match(). */
save_mark = md->mark;
save_capture_last = md->capture_last;
RMATCH(eptr, ecode + PRIV(OP_lengths)[*ecode], offset_top, md, eptrb,
RM2);
/* See comment in the code for capturing groups above about handling
THEN. */
if (rrc == MATCH_THEN)
{
next = ecode + GET(ecode,1);
if (md->start_match_ptr < next &&
(*ecode == OP_ALT || *next == OP_ALT))
rrc = MATCH_NOMATCH;
}
if (rrc != MATCH_NOMATCH)
{
if (rrc == MATCH_ONCE)
{
const pcre_uchar *scode = ecode;
if (*scode != OP_ONCE) /* If not at start, find it */
{
while (*scode == OP_ALT) scode += GET(scode, 1);
scode -= GET(scode, 1);
}
if (md->once_target == scode) rrc = MATCH_NOMATCH;
}
RRETURN(rrc);
}
ecode += GET(ecode, 1);
md->mark = save_mark;
if (*ecode != OP_ALT) break;
md->capture_last = save_capture_last;
}
RRETURN(MATCH_NOMATCH);
/* Handle possessive capturing brackets with an unlimited repeat. We come
here from BRAZERO with allow_zero set TRUE. The offset_vector values are
handled similarly to the normal case above. However, the matching is
different. The end of these brackets will always be OP_KETRPOS, which
returns MATCH_KETRPOS without going further in the pattern. By this means
we can handle the group by iteration rather than recursion, thereby
reducing the amount of stack needed. */
case OP_CBRAPOS:
case OP_SCBRAPOS:
allow_zero = FALSE;
POSSESSIVE_CAPTURE:
number = GET2(ecode, 1+LINK_SIZE);
offset = number << 1;
#ifdef PCRE_DEBUG
printf("start possessive bracket %d\n", number);
printf("subject=");
pchars(eptr, 16, TRUE, md);
printf("\n");
#endif
if (offset < md->offset_max)
{
matched_once = FALSE;
code_offset = (int)(ecode - md->start_code);
save_offset1 = md->offset_vector[offset];
save_offset2 = md->offset_vector[offset+1];
save_offset3 = md->offset_vector[md->offset_end - number];
save_capture_last = md->capture_last;
DPRINTF(("saving %d %d %d\n", save_offset1, save_offset2, save_offset3));
/* Each time round the loop, save the current subject position for use
when the group matches. For MATCH_MATCH, the group has matched, so we
restart it with a new subject starting position, remembering that we had
at least one match. For MATCH_NOMATCH, carry on with the alternatives, as
usual. If we haven't matched any alternatives in any iteration, check to
see if a previous iteration matched. If so, the group has matched;
continue from afterwards. Otherwise it has failed; restore the previous
capture values before returning NOMATCH. */
for (;;) /* LOOP_COUNT: Ok */
{
md->offset_vector[md->offset_end - number] =
(int)(eptr - md->start_subject);
if (op >= OP_SBRA) md->match_function_type = MATCH_CBEGROUP;
RMATCH(eptr, ecode + PRIV(OP_lengths)[*ecode], offset_top, md,
eptrb, RM63);
if (rrc == MATCH_KETRPOS)
{
offset_top = md->end_offset_top;
eptr = md->end_match_ptr;
ecode = md->start_code + code_offset;
save_capture_last = md->capture_last;
matched_once = TRUE;
continue;
}
/* See comment in the code for capturing groups above about handling
THEN. */
if (rrc == MATCH_THEN)
{
next = ecode + GET(ecode,1);
if (md->start_match_ptr < next &&
(*ecode == OP_ALT || *next == OP_ALT))
rrc = MATCH_NOMATCH;
}
if (rrc != MATCH_NOMATCH) RRETURN(rrc);
md->capture_last = save_capture_last;
ecode += GET(ecode, 1);
if (*ecode != OP_ALT) break;
}
if (!matched_once)
{
md->offset_vector[offset] = save_offset1;
md->offset_vector[offset+1] = save_offset2;
md->offset_vector[md->offset_end - number] = save_offset3;
}
if (allow_zero || matched_once)
{
ecode += 1 + LINK_SIZE;
break;
}
RRETURN(MATCH_NOMATCH);
}
/* FALL THROUGH ... Insufficient room for saving captured contents. Treat
as a non-capturing bracket. */
/* VVVVVVVVVVVVVVVVVVVVVVVVV */
/* VVVVVVVVVVVVVVVVVVVVVVVVV */
DPRINTF(("insufficient capture room: treat as non-capturing\n"));
/* VVVVVVVVVVVVVVVVVVVVVVVVV */
/* VVVVVVVVVVVVVVVVVVVVVVVVV */
/* Non-capturing possessive bracket with unlimited repeat. We come here
from BRAZERO with allow_zero = TRUE. The code is similar to the above,
without the capturing complication. It is written out separately for speed
and cleanliness. */
case OP_BRAPOS:
case OP_SBRAPOS:
allow_zero = FALSE;
POSSESSIVE_NON_CAPTURE:
matched_once = FALSE;
code_offset = (int)(ecode - md->start_code);
save_capture_last = md->capture_last;
for (;;) /* LOOP_COUNT: Ok */
{
if (op >= OP_SBRA) md->match_function_type = MATCH_CBEGROUP;
RMATCH(eptr, ecode + PRIV(OP_lengths)[*ecode], offset_top, md,
eptrb, RM48);
if (rrc == MATCH_KETRPOS)
{
offset_top = md->end_offset_top;
eptr = md->end_match_ptr;
ecode = md->start_code + code_offset;
matched_once = TRUE;
continue;
}
/* See comment in the code for capturing groups above about handling
THEN. */
if (rrc == MATCH_THEN)
{
next = ecode + GET(ecode,1);
if (md->start_match_ptr < next &&
(*ecode == OP_ALT || *next == OP_ALT))
rrc = MATCH_NOMATCH;
}
if (rrc != MATCH_NOMATCH) RRETURN(rrc);
ecode += GET(ecode, 1);
if (*ecode != OP_ALT) break;
md->capture_last = save_capture_last;
}
if (matched_once || allow_zero)
{
ecode += 1 + LINK_SIZE;
break;
}
RRETURN(MATCH_NOMATCH);
/* Control never reaches here. */
/* Conditional group: compilation checked that there are no more than
two branches. If the condition is false, skipping the first branch takes us
past the end if there is only one branch, but that's OK because that is
exactly what going to the ket would do. */
case OP_COND:
case OP_SCOND:
codelink = GET(ecode, 1);
/* Because of the way auto-callout works during compile, a callout item is
inserted between OP_COND and an assertion condition. */
if (ecode[LINK_SIZE+1] == OP_CALLOUT)
{
if (PUBL(callout) != NULL)
{
PUBL(callout_block) cb;
cb.version = 2; /* Version 1 of the callout block */
cb.callout_number = ecode[LINK_SIZE+2];
cb.offset_vector = md->offset_vector;
#if defined COMPILE_PCRE8
cb.subject = (PCRE_SPTR)md->start_subject;
#elif defined COMPILE_PCRE16
cb.subject = (PCRE_SPTR16)md->start_subject;
#elif defined COMPILE_PCRE32
cb.subject = (PCRE_SPTR32)md->start_subject;
#endif
cb.subject_length = (int)(md->end_subject - md->start_subject);
cb.start_match = (int)(mstart - md->start_subject);
cb.current_position = (int)(eptr - md->start_subject);
cb.pattern_position = GET(ecode, LINK_SIZE + 3);
cb.next_item_length = GET(ecode, 3 + 2*LINK_SIZE);
cb.capture_top = offset_top/2;
cb.capture_last = md->capture_last & CAPLMASK;
/* Internal change requires this for API compatibility. */
if (cb.capture_last == 0) cb.capture_last = -1;
cb.callout_data = md->callout_data;
cb.mark = md->nomatch_mark;
if ((rrc = (*PUBL(callout))(&cb)) > 0) RRETURN(MATCH_NOMATCH);
if (rrc < 0) RRETURN(rrc);
}
ecode += PRIV(OP_lengths)[OP_CALLOUT];
codelink -= PRIV(OP_lengths)[OP_CALLOUT];
}
condcode = ecode[LINK_SIZE+1];
/* Now see what the actual condition is */
if (condcode == OP_RREF || condcode == OP_NRREF) /* Recursion test */
{
if (md->recursive == NULL) /* Not recursing => FALSE */
{
condition = FALSE;
ecode += GET(ecode, 1);
}
else
{ /* LOOP_COUNT: Warning, No CHK in this block */
unsigned int recno = GET2(ecode, LINK_SIZE + 2); /* Recursion group number*/
condition = (recno == RREF_ANY || recno == md->recursive->group_num);
/* If the test is for recursion into a specific subpattern, and it is
false, but the test was set up by name, scan the table to see if the
name refers to any other numbers, and test them. The condition is true
if any one is set. */
if (!condition && condcode == OP_NRREF)
{
pcre_uchar *slotA = md->name_table;
for (i = 0; i < md->name_count; i++)/* LOOP_COUNT: COST */
{
if (GET2(slotA, 0) == recno) break;
slotA += md->name_entry_size;
COST(1);
}
/* Found a name for the number - there can be only one; duplicate
names for different numbers are allowed, but not vice versa. First
scan down for duplicates. */
if (i < md->name_count)
{
pcre_uchar *slotB = slotA;
while (slotB > md->name_table) /* LOOP_COUNT: COST */
{
slotB -= md->name_entry_size;
if (STRCMP_UC_UC(slotA + IMM2_SIZE, slotB + IMM2_SIZE) == 0)
{
condition = GET2(slotB, 0) == md->recursive->group_num;
if (condition) break;
}
else break;
COST(1);
}
/* Scan up for duplicates */
if (!condition)
{
slotB = slotA;
for (i++; i < md->name_count; i++)/* LOOP_COUNT: COST */
{
slotB += md->name_entry_size;
if (STRCMP_UC_UC(slotA + IMM2_SIZE, slotB + IMM2_SIZE) == 0)
{
condition = GET2(slotB, 0) == md->recursive->group_num;
if (condition) break;
}
else break;
COST(1);
}
}
}
}
/* Chose branch according to the condition */
ecode += condition? 1 + IMM2_SIZE : GET(ecode, 1);
}
}
else if (condcode == OP_CREF || condcode == OP_NCREF) /* Group used test */
{
offset = GET2(ecode, LINK_SIZE+2) << 1; /* Doubled ref number */
condition = offset < offset_top && md->offset_vector[offset] >= 0;
/* If the numbered capture is unset, but the reference was by name,
scan the table to see if the name refers to any other numbers, and test
them. The condition is true if any one is set. This is tediously similar
to the code above, but not close enough to try to amalgamate. */
if (!condition && condcode == OP_NCREF)
{
unsigned int refno = offset >> 1;
pcre_uchar *slotA = md->name_table;/* LOOP_COUNT: Warning, no CHK in this block */
for (i = 0; i < md->name_count; i++) /* LOOP_COUNT: COST */
{
if (GET2(slotA, 0) == refno) break;
slotA += md->name_entry_size;
COST(1);
}
/* Found a name for the number - there can be only one; duplicate names
for different numbers are allowed, but not vice versa. First scan down
for duplicates. */
if (i < md->name_count)
{
pcre_uchar *slotB = slotA;
while (slotB > md->name_table) /* LOOP_COUNT: COST */
{
slotB -= md->name_entry_size;
if (STRCMP_UC_UC(slotA + IMM2_SIZE, slotB + IMM2_SIZE) == 0)
{
offset = GET2(slotB, 0) << 1;
condition = offset < offset_top &&
md->offset_vector[offset] >= 0;
if (condition) break;
}
else break;
COST(1);
}
/* Scan up for duplicates */
if (!condition)
{
slotB = slotA;
for (i++; i < md->name_count; i++) /* LOOP_COUNT: COST */
{
slotB += md->name_entry_size;
if (STRCMP_UC_UC(slotA + IMM2_SIZE, slotB + IMM2_SIZE) == 0)
{
offset = GET2(slotB, 0) << 1;
condition = offset < offset_top &&
md->offset_vector[offset] >= 0;
if (condition) break;
}
else break;
COST(1);
}
}
}
}
/* Chose branch according to the condition */
ecode += condition? 1 + IMM2_SIZE : GET(ecode, 1);
}
else if (condcode == OP_DEF) /* DEFINE - always false */
{
condition = FALSE;
ecode += GET(ecode, 1);
}
/* The condition is an assertion. Call match() to evaluate it - setting
md->match_function_type to MATCH_CONDASSERT causes it to stop at the end of
an assertion. */
else
{
md->match_function_type = MATCH_CONDASSERT;
RMATCH(eptr, ecode + 1 + LINK_SIZE, offset_top, md, NULL, RM3);
if (rrc == MATCH_MATCH)
{
if (md->end_offset_top > offset_top)
offset_top = md->end_offset_top; /* Captures may have happened */
condition = TRUE;
ecode += 1 + LINK_SIZE + GET(ecode, LINK_SIZE + 2);
while (*ecode == OP_ALT) ecode += GET(ecode, 1); /* LOOP_COUNT: Ok */
}
/* PCRE doesn't allow the effect of (*THEN) to escape beyond an
assertion; it is therefore treated as NOMATCH. */
else if (rrc != MATCH_NOMATCH && rrc != MATCH_THEN)
{
RRETURN(rrc); /* Need braces because of following else */
}
else
{
condition = FALSE;
ecode += codelink;
}
}
/* We are now at the branch that is to be obeyed. As there is only one, can
use tail recursion to avoid using another stack frame, except when there is
unlimited repeat of a possibly empty group. In the latter case, a recursive
call to match() is always required, unless the second alternative doesn't
exist, in which case we can just plough on. Note that, for compatibility
with Perl, the | in a conditional group is NOT treated as creating two
alternatives. If a THEN is encountered in the branch, it propagates out to
the enclosing alternative (unless nested in a deeper set of alternatives,
of course). */
if (condition || *ecode == OP_ALT)
{
if (op != OP_SCOND)
{
ecode += 1 + LINK_SIZE;
goto TAIL_RECURSE;
}
md->match_function_type = MATCH_CBEGROUP;
RMATCH(eptr, ecode + 1 + LINK_SIZE, offset_top, md, eptrb, RM49);
RRETURN(rrc);
}
/* Condition false & no alternative; continue after the group. */
else
{
ecode += 1 + LINK_SIZE;
}
break;
/* Before OP_ACCEPT there may be any number of OP_CLOSE opcodes,
to close any currently open capturing brackets. */
case OP_CLOSE:
number = GET2(ecode, 1); /* Must be less than 65536 */
offset = number << 1;
#ifdef PCRE_DEBUG
printf("end bracket %d at *ACCEPT", number);
printf("\n");
#endif
md->capture_last = (md->capture_last & OVFLMASK) | number;
if (offset >= md->offset_max) md->capture_last |= OVFLBIT; else
{
md->offset_vector[offset] =
md->offset_vector[md->offset_end - number];
md->offset_vector[offset+1] = (int)(eptr - md->start_subject);
if (offset_top <= offset) offset_top = offset + 2;
}
ecode += 1 + IMM2_SIZE;
break;
/* End of the pattern, either real or forced. */
case OP_END:
case OP_ACCEPT:
case OP_ASSERT_ACCEPT:
/* If we have matched an empty string, fail if not in an assertion and not
in a recursion if either PCRE_NOTEMPTY is set, or if PCRE_NOTEMPTY_ATSTART
is set and we have matched at the start of the subject. In both cases,
backtracking will then try other alternatives, if any. */
if (eptr == mstart && op != OP_ASSERT_ACCEPT &&
md->recursive == NULL &&
(md->notempty ||
(md->notempty_atstart &&
mstart == md->start_subject + md->start_offset)))
RRETURN(MATCH_NOMATCH);
/* Otherwise, we have a match. */
md->end_match_ptr = eptr; /* Record where we ended */
md->end_offset_top = offset_top; /* and how many extracts were taken */
md->start_match_ptr = mstart; /* and the start (\K can modify) */
/* For some reason, the macros don't work properly if an expression is
given as the argument to RRETURN when the heap is in use. */
rrc = (op == OP_END)? MATCH_MATCH : MATCH_ACCEPT;
RRETURN(rrc);
/* Assertion brackets. Check the alternative branches in turn - the
matching won't pass the KET for an assertion. If any one branch matches,
the assertion is true. Lookbehind assertions have an OP_REVERSE item at the
start of each branch to move the current point backwards, so the code at
this level is identical to the lookahead case. When the assertion is part
of a condition, we want to return immediately afterwards. The caller of
this incarnation of the match() function will have set MATCH_CONDASSERT in
md->match_function type, and one of these opcodes will be the first opcode
that is processed. We use a local variable that is preserved over calls to
match() to remember this case. */
case OP_ASSERT:
case OP_ASSERTBACK:
save_mark = md->mark;
if (md->match_function_type == MATCH_CONDASSERT)
{
condassert = TRUE;
md->match_function_type = 0;
}
else condassert = FALSE;
/* Loop for each branch */
do /* LOOP_COUNT: Ok */
{
RMATCH(eptr, ecode + 1 + LINK_SIZE, offset_top, md, NULL, RM4);
/* A match means that the assertion is true; break out of the loop
that matches its alternatives. */
if (rrc == MATCH_MATCH || rrc == MATCH_ACCEPT)
{
mstart = md->start_match_ptr; /* In case \K reset it */
break;
}
/* If not matched, restore the previous mark setting. */
md->mark = save_mark;
/* See comment in the code for capturing groups above about handling
THEN. */
if (rrc == MATCH_THEN)
{
next = ecode + GET(ecode,1);
if (md->start_match_ptr < next &&
(*ecode == OP_ALT || *next == OP_ALT))
rrc = MATCH_NOMATCH;
}
/* Anything other than NOMATCH causes the entire assertion to fail,
passing back the return code. This includes COMMIT, SKIP, PRUNE and an
uncaptured THEN, which means they take their normal effect. This
consistent approach does not always have exactly the same effect as in
Perl. */
if (rrc != MATCH_NOMATCH) RRETURN(rrc);
ecode += GET(ecode, 1);
}
while (*ecode == OP_ALT); /* Continue for next alternative */ /* LOOP_COUNT: Ok */
/* If we have tried all the alternative branches, the assertion has
failed. If not, we broke out after a match. */
if (*ecode == OP_KET) RRETURN(MATCH_NOMATCH);
/* If checking an assertion for a condition, return MATCH_MATCH. */
if (condassert) RRETURN(MATCH_MATCH);
/* Continue from after a successful assertion, updating the offsets high
water mark, since extracts may have been taken during the assertion. */
do ecode += GET(ecode,1); while (*ecode == OP_ALT); /* LOOP_COUNT: Ok */
ecode += 1 + LINK_SIZE;
offset_top = md->end_offset_top;
continue;
/* Negative assertion: all branches must fail to match for the assertion to
succeed. */
case OP_ASSERT_NOT:
case OP_ASSERTBACK_NOT:
save_mark = md->mark;
if (md->match_function_type == MATCH_CONDASSERT)
{
condassert = TRUE;
md->match_function_type = 0;
}
else condassert = FALSE;
/* Loop for each alternative branch. */
do /* LOOP_COUNT: Ok */
{
RMATCH(eptr, ecode + 1 + LINK_SIZE, offset_top, md, NULL, RM5);
md->mark = save_mark; /* Always restore the mark setting */
switch(rrc)
{
case MATCH_MATCH: /* A successful match means */
case MATCH_ACCEPT: /* the assertion has failed. */
RRETURN(MATCH_NOMATCH);
case MATCH_NOMATCH: /* Carry on with next branch */
break;
/* See comment in the code for capturing groups above about handling
THEN. */
case MATCH_THEN:
next = ecode + GET(ecode,1);
if (md->start_match_ptr < next &&
(*ecode == OP_ALT || *next == OP_ALT))
{
rrc = MATCH_NOMATCH;
break;
}
/* Otherwise fall through. */
/* COMMIT, SKIP, PRUNE, and an uncaptured THEN cause the whole
assertion to fail to match, without considering any more alternatives.
Failing to match means the assertion is true. This is a consistent
approach, but does not always have the same effect as in Perl. */
case MATCH_COMMIT:
case MATCH_SKIP:
case MATCH_SKIP_ARG:
case MATCH_PRUNE:
do ecode += GET(ecode,1); while (*ecode == OP_ALT); /* LOOP_COUNT: Ok */
goto NEG_ASSERT_TRUE; /* Break out of alternation loop */
/* Anything else is an error */
default:
RRETURN(rrc);
}
/* Continue with next branch */
ecode += GET(ecode,1);
}
while (*ecode == OP_ALT);
/* All branches in the assertion failed to match. */
NEG_ASSERT_TRUE:
if (condassert) RRETURN(MATCH_MATCH); /* Condition assertion */
ecode += 1 + LINK_SIZE; /* Continue with current branch */
continue;
/* Move the subject pointer back. This occurs only at the start of
each branch of a lookbehind assertion. If we are too close to the start to
move back, this match function fails. When working with UTF-8 we move
back a number of characters, not bytes. */
case OP_REVERSE:
#ifdef SUPPORT_UTF
if (utf)
{
i = GET(ecode, 1);
COST(i);
while (i-- > 0) /* LOOP_COUNT: COST */
{
eptr--;
if (eptr < md->start_subject) RRETURN(MATCH_NOMATCH);
BACKCHAR(eptr);
}
}
else
#endif
/* No UTF-8 support, or not in UTF-8 mode: count is byte count */
{
eptr -= GET(ecode, 1);
if (eptr < md->start_subject) RRETURN(MATCH_NOMATCH);
}
/* Save the earliest consulted character, then skip to next op code */
if (eptr < md->start_used_ptr) md->start_used_ptr = eptr;
ecode += 1 + LINK_SIZE;
break;
/* The callout item calls an external function, if one is provided, passing
details of the match so far. This is mainly for debugging, though the
function is able to force a failure. */
case OP_CALLOUT:
if (PUBL(callout) != NULL)
{
PUBL(callout_block) cb;
cb.version = 2; /* Version 1 of the callout block */
cb.callout_number = ecode[1];
cb.offset_vector = md->offset_vector;
#if defined COMPILE_PCRE8
cb.subject = (PCRE_SPTR)md->start_subject;
#elif defined COMPILE_PCRE16
cb.subject = (PCRE_SPTR16)md->start_subject;
#elif defined COMPILE_PCRE32
cb.subject = (PCRE_SPTR32)md->start_subject;
#endif
cb.subject_length = (int)(md->end_subject - md->start_subject);
cb.start_match = (int)(mstart - md->start_subject);
cb.current_position = (int)(eptr - md->start_subject);
cb.pattern_position = GET(ecode, 2);
cb.next_item_length = GET(ecode, 2 + LINK_SIZE);
cb.capture_top = offset_top/2;
cb.capture_last = md->capture_last & CAPLMASK;
/* Internal change requires this for API compatibility. */
if (cb.capture_last == 0) cb.capture_last = -1;
cb.callout_data = md->callout_data;
cb.mark = md->nomatch_mark;
if ((rrc = (*PUBL(callout))(&cb)) > 0) RRETURN(MATCH_NOMATCH);
if (rrc < 0) RRETURN(rrc);
}
ecode += 2 + 2*LINK_SIZE;
break;
/* Recursion either matches the current regex, or some subexpression. The
offset data is the offset to the starting bracket from the start of the
whole pattern. (This is so that it works from duplicated subpatterns.)
The state of the capturing groups is preserved over recursion, and
re-instated afterwards. We don't know how many are started and not yet
finished (offset_top records the completed total) so we just have to save
all the potential data. There may be up to 65535 such values, which is too
large to put on the stack, but using malloc for small numbers seems
expensive. As a compromise, the stack is used when there are no more than
REC_STACK_SAVE_MAX values to store; otherwise malloc is used.
There are also other values that have to be saved. We use a chained
sequence of blocks that actually live on the stack. Thanks to Robin Houston
for the original version of this logic. It has, however, been hacked around
a lot, so he is not to blame for the current way it works. */
case OP_RECURSE:
{
recursion_info *ri;
unsigned int recno; /* LOOP_COUNT: Warning, no CHK until after Marker1 */
callpat = md->start_code + GET(ecode, 1);
recno = (callpat == md->start_code)? 0 :
GET2(callpat, 1 + LINK_SIZE);
/* Check for repeating a recursion without advancing the subject pointer.
This should catch convoluted mutual recursions. (Some simple cases are
caught at compile time.) */
for (ri = md->recursive; ri != NULL; ri = ri->prevrec) /* LOOP_COUNT: COST */
{
if (recno == ri->group_num && eptr == ri->subject_position)
RRETURN(PCRE_ERROR_RECURSELOOP);
COST(1);
}
/* Add to "recursing stack" */
new_recursive.group_num = recno; /* LOOP_COUNT: Marker1 */
new_recursive.saved_capture_last = md->capture_last;
new_recursive.subject_position = eptr;
new_recursive.prevrec = md->recursive;
md->recursive = &new_recursive;
/* Where to continue from afterwards */
ecode += 1 + LINK_SIZE;
/* Now save the offset data */
new_recursive.saved_max = md->offset_end;
if (new_recursive.saved_max <= REC_STACK_SAVE_MAX)
new_recursive.offset_save = stacksave;
else
{
new_recursive.offset_save =
(int *)(PUBL(malloc))(new_recursive.saved_max * sizeof(int));
if (new_recursive.offset_save == NULL) RRETURN(PCRE_ERROR_NOMEMORY);
}
memcpy(new_recursive.offset_save, md->offset_vector,
new_recursive.saved_max * sizeof(int));
/* OK, now we can do the recursion. After processing each alternative,
restore the offset data and the last captured value. If there were nested
recursions, md->recursive might be changed, so reset it before looping.
*/
DPRINTF(("Recursing into group %d\n", new_recursive.group_num));
cbegroup = (*callpat >= OP_SBRA);
do /* LOOP_COUNT: Ok */
{
if (cbegroup) md->match_function_type = MATCH_CBEGROUP;
RMATCH(eptr, callpat + PRIV(OP_lengths)[*callpat], offset_top,
md, eptrb, RM6);
memcpy(md->offset_vector, new_recursive.offset_save,
new_recursive.saved_max * sizeof(int));
md->capture_last = new_recursive.saved_capture_last;
md->recursive = new_recursive.prevrec;
if (rrc == MATCH_MATCH || rrc == MATCH_ACCEPT)
{
DPRINTF(("Recursion matched\n"));
if (new_recursive.offset_save != stacksave)
(PUBL(free))(new_recursive.offset_save);
/* Set where we got to in the subject, and reset the start in case
it was changed by \K. This *is* propagated back out of a recursion,
for Perl compatibility. */
eptr = md->end_match_ptr;
mstart = md->start_match_ptr;
goto RECURSION_MATCHED; /* Exit loop; end processing */
}
/* PCRE does not allow THEN, SKIP, PRUNE or COMMIT to escape beyond a
recursion; they cause a NOMATCH for the entire recursion. These codes
are defined in a range that can be tested for. */
if (rrc >= MATCH_BACKTRACK_MIN && rrc <= MATCH_BACKTRACK_MAX)
RRETURN(MATCH_NOMATCH);
/* Any return code other than NOMATCH is an error. */
if (rrc != MATCH_NOMATCH)
{
DPRINTF(("Recursion gave error %d\n", rrc));
if (new_recursive.offset_save != stacksave)
(PUBL(free))(new_recursive.offset_save);
RRETURN(rrc);
}
md->recursive = &new_recursive;
callpat += GET(callpat, 1);
}
while (*callpat == OP_ALT);
DPRINTF(("Recursion didn't match\n"));
md->recursive = new_recursive.prevrec;
if (new_recursive.offset_save != stacksave)
(PUBL(free))(new_recursive.offset_save);
RRETURN(MATCH_NOMATCH);
}
RECURSION_MATCHED:
break;
/* An alternation is the end of a branch; scan along to find the end of the
bracketed group and go to there. */
case OP_ALT:
do ecode += GET(ecode,1); while (*ecode == OP_ALT); /* LOOP_COUNT: Ok */
break;
/* BRAZERO, BRAMINZERO and SKIPZERO occur just before a bracket group,
indicating that it may occur zero times. It may repeat infinitely, or not
at all - i.e. it could be ()* or ()? or even (){0} in the pattern. Brackets
with fixed upper repeat limits are compiled as a number of copies, with the
optional ones preceded by BRAZERO or BRAMINZERO. */
case OP_BRAZERO:
next = ecode + 1;
RMATCH(eptr, next, offset_top, md, eptrb, RM10);
if (rrc != MATCH_NOMATCH) RRETURN(rrc);
do next += GET(next, 1); while (*next == OP_ALT); /* LOOP_COUNT: Ok */
ecode = next + 1 + LINK_SIZE;
break;
case OP_BRAMINZERO:
next = ecode + 1;
do next += GET(next, 1); while (*next == OP_ALT); /* LOOP_COUNT: Ok */
RMATCH(eptr, next + 1+LINK_SIZE, offset_top, md, eptrb, RM11);
if (rrc != MATCH_NOMATCH) RRETURN(rrc);
ecode++;
break;
case OP_SKIPZERO:
next = ecode+1;
do next += GET(next,1); while (*next == OP_ALT); /* LOOP_COUNT: Ok */
ecode = next + 1 + LINK_SIZE;
break;
/* BRAPOSZERO occurs before a possessive bracket group. Don't do anything
here; just jump to the group, with allow_zero set TRUE. */
case OP_BRAPOSZERO:
op = *(++ecode);
allow_zero = TRUE;
if (op == OP_CBRAPOS || op == OP_SCBRAPOS) goto POSSESSIVE_CAPTURE;
goto POSSESSIVE_NON_CAPTURE;
/* End of a group, repeated or non-repeating. */
case OP_KET:
case OP_KETRMIN:
case OP_KETRMAX:
case OP_KETRPOS:
prev = ecode - GET(ecode, 1);
/* If this was a group that remembered the subject start, in order to break
infinite repeats of empty string matches, retrieve the subject start from
the chain. Otherwise, set it NULL. */
if (*prev >= OP_SBRA || *prev == OP_ONCE)
{
saved_eptr = eptrb->epb_saved_eptr; /* Value at start of group */
eptrb = eptrb->epb_prev; /* Backup to previous group */
}
else saved_eptr = NULL;
/* If we are at the end of an assertion group or a non-capturing atomic
group, stop matching and return MATCH_MATCH, but record the current high
water mark for use by positive assertions. We also need to record the match
start in case it was changed by \K. */
if ((*prev >= OP_ASSERT && *prev <= OP_ASSERTBACK_NOT) ||
*prev == OP_ONCE_NC)
{
md->end_match_ptr = eptr; /* For ONCE_NC */
md->end_offset_top = offset_top;
md->start_match_ptr = mstart;
RRETURN(MATCH_MATCH); /* Sets md->mark */
}
/* For capturing groups we have to check the group number back at the start
and if necessary complete handling an extraction by setting the offsets and
bumping the high water mark. Whole-pattern recursion is coded as a recurse
into group 0, so it won't be picked up here. Instead, we catch it when the
OP_END is reached. Other recursion is handled here. We just have to record
the current subject position and start match pointer and give a MATCH
return. */
if (*prev == OP_CBRA || *prev == OP_SCBRA ||
*prev == OP_CBRAPOS || *prev == OP_SCBRAPOS)
{
number = GET2(prev, 1+LINK_SIZE);
offset = number << 1;
#ifdef PCRE_DEBUG
printf("end bracket %d", number);
printf("\n");
#endif
/* Handle a recursively called group. */
if (md->recursive != NULL && md->recursive->group_num == number)
{
md->end_match_ptr = eptr;
md->start_match_ptr = mstart;
RRETURN(MATCH_MATCH);
}
/* Deal with capturing */
md->capture_last = (md->capture_last & OVFLMASK) | number;
if (offset >= md->offset_max) md->capture_last |= OVFLBIT; else
{
/* If offset is greater than offset_top, it means that we are
"skipping" a capturing group, and that group's offsets must be marked
unset. In earlier versions of PCRE, all the offsets were unset at the
start of matching, but this doesn't work because atomic groups and
assertions can cause a value to be set that should later be unset.
Example: matching /(?>(a))b|(a)c/ against "ac". This sets group 1 as
part of the atomic group, but this is not on the final matching path,
so must be unset when 2 is set. (If there is no group 2, there is no
problem, because offset_top will then be 2, indicating no capture.) */
if (offset > offset_top)
{
register int *iptr = md->offset_vector + offset_top;
register int *iend = md->offset_vector + offset;
while (iptr < iend) *iptr++ = -1; /* LOOP_COUNT: CHK */
}
/* Now make the extraction */
md->offset_vector[offset] =
md->offset_vector[md->offset_end - number];
md->offset_vector[offset+1] = (int)(eptr - md->start_subject);
if (offset_top <= offset) offset_top = offset + 2;
}
}
/* For an ordinary non-repeating ket, just continue at this level. This
also happens for a repeating ket if no characters were matched in the
group. This is the forcible breaking of infinite loops as implemented in
Perl 5.005. For a non-repeating atomic group that includes captures,
establish a backup point by processing the rest of the pattern at a lower
level. If this results in a NOMATCH return, pass MATCH_ONCE back to the
original OP_ONCE level, thereby bypassing intermediate backup points, but
resetting any captures that happened along the way. */
if (*ecode == OP_KET || eptr == saved_eptr)
{
if (*prev == OP_ONCE)
{
RMATCH(eptr, ecode + 1 + LINK_SIZE, offset_top, md, eptrb, RM12);
if (rrc != MATCH_NOMATCH) RRETURN(rrc);
md->once_target = prev; /* Level at which to change to MATCH_NOMATCH */
RRETURN(MATCH_ONCE);
}
ecode += 1 + LINK_SIZE; /* Carry on at this level */
break;
}
/* OP_KETRPOS is a possessive repeating ket. Remember the current position,
and return the MATCH_KETRPOS. This makes it possible to do the repeats one
at a time from the outer level, thus saving stack. */
if (*ecode == OP_KETRPOS)
{
md->end_match_ptr = eptr;
md->end_offset_top = offset_top;
RRETURN(MATCH_KETRPOS);
}
/* The normal repeating kets try the rest of the pattern or restart from
the preceding bracket, in the appropriate order. In the second case, we can
use tail recursion to avoid using another stack frame, unless we have an
an atomic group or an unlimited repeat of a group that can match an empty
string. */
if (*ecode == OP_KETRMIN)
{
RMATCH(eptr, ecode + 1 + LINK_SIZE, offset_top, md, eptrb, RM7);
if (rrc != MATCH_NOMATCH) RRETURN(rrc);
if (*prev == OP_ONCE)
{
RMATCH(eptr, prev, offset_top, md, eptrb, RM8);
if (rrc != MATCH_NOMATCH) RRETURN(rrc);
md->once_target = prev; /* Level at which to change to MATCH_NOMATCH */
RRETURN(MATCH_ONCE);
}
if (*prev >= OP_SBRA) /* Could match an empty string */
{
RMATCH(eptr, prev, offset_top, md, eptrb, RM50);
RRETURN(rrc);
}
ecode = prev;
goto TAIL_RECURSE;
}
else /* OP_KETRMAX */
{
RMATCH(eptr, prev, offset_top, md, eptrb, RM13);
if (rrc == MATCH_ONCE && md->once_target == prev) rrc = MATCH_NOMATCH;
if (rrc != MATCH_NOMATCH) RRETURN(rrc);
if (*prev == OP_ONCE)
{
RMATCH(eptr, ecode + 1 + LINK_SIZE, offset_top, md, eptrb, RM9);
if (rrc != MATCH_NOMATCH) RRETURN(rrc);
md->once_target = prev;
RRETURN(MATCH_ONCE);
}
ecode += 1 + LINK_SIZE;
goto TAIL_RECURSE;
}
/* Control never gets here */
/* Not multiline mode: start of subject assertion, unless notbol. */
case OP_CIRC:
if (md->notbol && eptr == md->start_subject) RRETURN(MATCH_NOMATCH);
/* Start of subject assertion */
case OP_SOD:
if (eptr != md->start_subject) RRETURN(MATCH_NOMATCH);
ecode++;
break;
/* Multiline mode: start of subject unless notbol, or after any newline. */
case OP_CIRCM:
if (md->notbol && eptr == md->start_subject) RRETURN(MATCH_NOMATCH);
if (eptr != md->start_subject &&
(eptr == md->end_subject || !WAS_NEWLINE(eptr)))
RRETURN(MATCH_NOMATCH);
ecode++;
break;
/* Start of match assertion */
case OP_SOM:
if (eptr != md->start_subject + md->start_offset) RRETURN(MATCH_NOMATCH);
ecode++;
break;
/* Reset the start of match point */
case OP_SET_SOM:
mstart = eptr;
ecode++;
break;
/* Multiline mode: assert before any newline, or before end of subject
unless noteol is set. */
case OP_DOLLM:
if (eptr < md->end_subject)
{
if (!IS_NEWLINE(eptr))
{
if (md->partial != 0 &&
eptr + 1 >= md->end_subject &&
NLBLOCK->nltype == NLTYPE_FIXED &&
NLBLOCK->nllen == 2 &&
RAWUCHARTEST(eptr) == NLBLOCK->nl[0])
{
md->hitend = TRUE;
if (md->partial > 1) RRETURN(PCRE_ERROR_PARTIAL);
}
RRETURN(MATCH_NOMATCH);
}
}
else
{
if (md->noteol) RRETURN(MATCH_NOMATCH);
SCHECK_PARTIAL();
}
ecode++;
break;
/* Not multiline mode: assert before a terminating newline or before end of
subject unless noteol is set. */
case OP_DOLL:
if (md->noteol) RRETURN(MATCH_NOMATCH);
if (!md->endonly) goto ASSERT_NL_OR_EOS;
/* ... else fall through for endonly */
/* End of subject assertion (\z) */
case OP_EOD:
if (eptr < md->end_subject) RRETURN(MATCH_NOMATCH);
SCHECK_PARTIAL();
ecode++;
break;
/* End of subject or ending \n assertion (\Z) */
case OP_EODN:
ASSERT_NL_OR_EOS:
if (eptr < md->end_subject &&
(!IS_NEWLINE(eptr) || eptr != md->end_subject - md->nllen))
{
if (md->partial != 0 &&
eptr + 1 >= md->end_subject &&
NLBLOCK->nltype == NLTYPE_FIXED &&
NLBLOCK->nllen == 2 &&
RAWUCHARTEST(eptr) == NLBLOCK->nl[0])
{
md->hitend = TRUE;
if (md->partial > 1) RRETURN(PCRE_ERROR_PARTIAL);
}
RRETURN(MATCH_NOMATCH);
}
/* Either at end of string or \n before end. */
SCHECK_PARTIAL();
ecode++;
break;
/* Word boundary assertions */
case OP_NOT_WORD_BOUNDARY:
case OP_WORD_BOUNDARY:
{
/* Find out if the previous and current characters are "word" characters.
It takes a bit more work in UTF-8 mode. Characters > 255 are assumed to
be "non-word" characters. Remember the earliest consulted character for
partial matching. */
#ifdef SUPPORT_UTF
if (utf)
{
/* Get status of previous character */
if (eptr == md->start_subject) prev_is_word = FALSE; else
{
PCRE_PUCHAR lastptr = eptr - 1;
BACKCHAR(lastptr);
if (lastptr < md->start_used_ptr) md->start_used_ptr = lastptr;
GETCHAR(c, lastptr);
#ifdef SUPPORT_UCP
if (md->use_ucp)
{
if (c == '_') prev_is_word = TRUE; else
{
int cat = UCD_CATEGORY(c);
prev_is_word = (cat == ucp_L || cat == ucp_N);
}
}
else
#endif
prev_is_word = c < 256 && (md->ctypes[c] & ctype_word) != 0;
}
/* Get status of next character */
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
cur_is_word = FALSE;
}
else
{
GETCHAR(c, eptr);
#ifdef SUPPORT_UCP
if (md->use_ucp)
{
if (c == '_') cur_is_word = TRUE; else
{
int cat = UCD_CATEGORY(c);
cur_is_word = (cat == ucp_L || cat == ucp_N);
}
}
else
#endif
cur_is_word = c < 256 && (md->ctypes[c] & ctype_word) != 0;
}
}
else
#endif
/* Not in UTF-8 mode, but we may still have PCRE_UCP set, and for
consistency with the behaviour of \w we do use it in this case. */
{
/* Get status of previous character */
if (eptr == md->start_subject) prev_is_word = FALSE; else
{
if (eptr <= md->start_used_ptr) md->start_used_ptr = eptr - 1;
#ifdef SUPPORT_UCP
if (md->use_ucp)
{
c = eptr[-1];
if (c == '_') prev_is_word = TRUE; else
{
int cat = UCD_CATEGORY(c);
prev_is_word = (cat == ucp_L || cat == ucp_N);
}
}
else
#endif
prev_is_word = MAX_255(eptr[-1])
&& ((md->ctypes[eptr[-1]] & ctype_word) != 0);
}
/* Get status of next character */
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
cur_is_word = FALSE;
}
else
#ifdef SUPPORT_UCP
if (md->use_ucp)
{
c = *eptr;
if (c == '_') cur_is_word = TRUE; else
{
int cat = UCD_CATEGORY(c);
cur_is_word = (cat == ucp_L || cat == ucp_N);
}
}
else
#endif
cur_is_word = MAX_255(*eptr)
&& ((md->ctypes[*eptr] & ctype_word) != 0);
}
/* Now see if the situation is what we want */
if ((*ecode++ == OP_WORD_BOUNDARY)?
cur_is_word == prev_is_word : cur_is_word != prev_is_word)
RRETURN(MATCH_NOMATCH);
}
break;
/* Match any single character type except newline; have to take care with
CRLF newlines and partial matching. */
case OP_ANY:
if (IS_NEWLINE(eptr)) RRETURN(MATCH_NOMATCH);
if (md->partial != 0 &&
eptr + 1 >= md->end_subject &&
NLBLOCK->nltype == NLTYPE_FIXED &&
NLBLOCK->nllen == 2 &&
RAWUCHARTEST(eptr) == NLBLOCK->nl[0])
{
md->hitend = TRUE;
if (md->partial > 1) RRETURN(PCRE_ERROR_PARTIAL);
}
/* Fall through */
/* Match any single character whatsoever. */
case OP_ALLANY:
if (eptr >= md->end_subject) /* DO NOT merge the eptr++ here; it must */
{ /* not be updated before SCHECK_PARTIAL. */
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
eptr++;
#ifdef SUPPORT_UTF
if (utf) ACROSSCHAR(eptr < md->end_subject, *eptr, eptr++);
#endif
ecode++;
break;
/* Match a single byte, even in UTF-8 mode. This opcode really does match
any byte, even newline, independent of the setting of PCRE_DOTALL. */
case OP_ANYBYTE:
if (eptr >= md->end_subject) /* DO NOT merge the eptr++ here; it must */
{ /* not be updated before SCHECK_PARTIAL. */
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
eptr++;
ecode++;
break;
case OP_NOT_DIGIT:
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
GETCHARINCTEST(c, eptr);
if (
#if defined SUPPORT_UTF || !(defined COMPILE_PCRE8)
c < 256 &&
#endif
(md->ctypes[c] & ctype_digit) != 0
)
RRETURN(MATCH_NOMATCH);
ecode++;
break;
case OP_DIGIT:
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
GETCHARINCTEST(c, eptr);
if (
#if defined SUPPORT_UTF || !(defined COMPILE_PCRE8)
c > 255 ||
#endif
(md->ctypes[c] & ctype_digit) == 0
)
RRETURN(MATCH_NOMATCH);
ecode++;
break;
case OP_NOT_WHITESPACE:
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
GETCHARINCTEST(c, eptr);
if (
#if defined SUPPORT_UTF || !(defined COMPILE_PCRE8)
c < 256 &&
#endif
(md->ctypes[c] & ctype_space) != 0
)
RRETURN(MATCH_NOMATCH);
ecode++;
break;
case OP_WHITESPACE:
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
GETCHARINCTEST(c, eptr);
if (
#if defined SUPPORT_UTF || !(defined COMPILE_PCRE8)
c > 255 ||
#endif
(md->ctypes[c] & ctype_space) == 0
)
RRETURN(MATCH_NOMATCH);
ecode++;
break;
case OP_NOT_WORDCHAR:
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
GETCHARINCTEST(c, eptr);
if (
#if defined SUPPORT_UTF || !(defined COMPILE_PCRE8)
c < 256 &&
#endif
(md->ctypes[c] & ctype_word) != 0
)
RRETURN(MATCH_NOMATCH);
ecode++;
break;
case OP_WORDCHAR:
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
GETCHARINCTEST(c, eptr);
if (
#if defined SUPPORT_UTF || !(defined COMPILE_PCRE8)
c > 255 ||
#endif
(md->ctypes[c] & ctype_word) == 0
)
RRETURN(MATCH_NOMATCH);
ecode++;
break;
case OP_ANYNL:
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
GETCHARINCTEST(c, eptr);
switch(c)
{
default: RRETURN(MATCH_NOMATCH);
case CHAR_CR:
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
}
else if (RAWUCHARTEST(eptr) == CHAR_LF) eptr++;
break;
case CHAR_LF:
break;
case CHAR_VT:
case CHAR_FF:
case CHAR_NEL:
#ifndef EBCDIC
case 0x2028:
case 0x2029:
#endif /* Not EBCDIC */
if (md->bsr_anycrlf) RRETURN(MATCH_NOMATCH);
break;
}
ecode++;
break;
case OP_NOT_HSPACE:
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
GETCHARINCTEST(c, eptr);
switch(c)
{
HSPACE_CASES: RRETURN(MATCH_NOMATCH); /* Byte and multibyte cases */
default: break;
}
ecode++;
break;
case OP_HSPACE:
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
GETCHARINCTEST(c, eptr);
switch(c)
{
HSPACE_CASES: break; /* Byte and multibyte cases */
default: RRETURN(MATCH_NOMATCH);
}
ecode++;
break;
case OP_NOT_VSPACE:
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
GETCHARINCTEST(c, eptr);
switch(c)
{
VSPACE_CASES: RRETURN(MATCH_NOMATCH);
default: break;
}
ecode++;
break;
case OP_VSPACE:
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
GETCHARINCTEST(c, eptr);
switch(c)
{
VSPACE_CASES: break;
default: RRETURN(MATCH_NOMATCH);
}
ecode++;
break;
#ifdef SUPPORT_UCP
/* Check the next character by Unicode property. We will get here only
if the support is in the binary; otherwise a compile-time error occurs. */
case OP_PROP:
case OP_NOTPROP:
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
GETCHARINCTEST(c, eptr);
{
const pcre_uint32 *cp;
const ucd_record *prop = GET_UCD(c); /* LOOP_COUNT: Warning, no CHK in this block! */
switch(ecode[1])
{
case PT_ANY:
if (op == OP_NOTPROP) RRETURN(MATCH_NOMATCH);
break;
case PT_LAMP:
if ((prop->chartype == ucp_Lu ||
prop->chartype == ucp_Ll ||
prop->chartype == ucp_Lt) == (op == OP_NOTPROP))
RRETURN(MATCH_NOMATCH);
break;
case PT_GC:
if ((ecode[2] != PRIV(ucp_gentype)[prop->chartype]) == (op == OP_PROP))
RRETURN(MATCH_NOMATCH);
break;
case PT_PC:
if ((ecode[2] != prop->chartype) == (op == OP_PROP))
RRETURN(MATCH_NOMATCH);
break;
case PT_SC:
if ((ecode[2] != prop->script) == (op == OP_PROP))
RRETURN(MATCH_NOMATCH);
break;
/* These are specials */
case PT_ALNUM:
if ((PRIV(ucp_gentype)[prop->chartype] == ucp_L ||
PRIV(ucp_gentype)[prop->chartype] == ucp_N) == (op == OP_NOTPROP))
RRETURN(MATCH_NOMATCH);
break;
case PT_SPACE: /* Perl space */
if ((PRIV(ucp_gentype)[prop->chartype] == ucp_Z ||
c == CHAR_HT || c == CHAR_NL || c == CHAR_FF || c == CHAR_CR)
== (op == OP_NOTPROP))
RRETURN(MATCH_NOMATCH);
break;
case PT_PXSPACE: /* POSIX space */
if ((PRIV(ucp_gentype)[prop->chartype] == ucp_Z ||
c == CHAR_HT || c == CHAR_NL || c == CHAR_VT ||
c == CHAR_FF || c == CHAR_CR)
== (op == OP_NOTPROP))
RRETURN(MATCH_NOMATCH);
break;
case PT_WORD:
if ((PRIV(ucp_gentype)[prop->chartype] == ucp_L ||
PRIV(ucp_gentype)[prop->chartype] == ucp_N ||
c == CHAR_UNDERSCORE) == (op == OP_NOTPROP))
RRETURN(MATCH_NOMATCH);
break;
case PT_CLIST:
cp = PRIV(ucd_caseless_sets) + ecode[2];
for (;;) /* LOOP_COUNT: COST */
{
if (c < *cp)
{ if (op == OP_PROP) { RRETURN(MATCH_NOMATCH); } else break; }
if (c == *cp++)
{ if (op == OP_PROP) break; else { RRETURN(MATCH_NOMATCH); } }
COST(1);
}
break;
case PT_UCNC:
if ((c == CHAR_DOLLAR_SIGN || c == CHAR_COMMERCIAL_AT ||
c == CHAR_GRAVE_ACCENT || (c >= 0xa0 && c <= 0xd7ff) ||
c >= 0xe000) == (op == OP_NOTPROP))
RRETURN(MATCH_NOMATCH);
break;
/* This should never occur */
default:
RRETURN(PCRE_ERROR_INTERNAL);
}
ecode += 3;
}
break;
/* Match an extended Unicode sequence. We will get here only if the support
is in the binary; otherwise a compile-time error occurs. */
case OP_EXTUNI:
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
else
{
#ifndef ERLANG_INTEGRATION
int lgb, rgb;
#endif
GETCHARINCTEST(c, eptr);
lgb = UCD_GRAPHBREAK(c);
while (eptr < md->end_subject) /* LOOP_COUNT: CHK */
{
int len = 1;
if (!utf) c = *eptr; else { GETCHARLEN(c, eptr, len); }
rgb = UCD_GRAPHBREAK(c);
if ((PRIV(ucp_gbtable)[lgb] & (1 << rgb)) == 0) break;
lgb = rgb;
eptr += len;
COST_CHK(1);
}
}
CHECK_PARTIAL();
ecode++;
break;
#endif /* SUPPORT_UCP */
/* Match a back reference, possibly repeatedly. Look past the end of the
item to see if there is repeat information following. The code is similar
to that for character classes, but repeated for efficiency. Then obey
similar code to character type repeats - written out again for speed.
However, if the referenced string is the empty string, always treat
it as matched, any number of times (otherwise there could be infinite
loops). */
case OP_REF:
case OP_REFI:
caseless = op == OP_REFI;
offset = GET2(ecode, 1) << 1; /* Doubled ref number */
ecode += 1 + IMM2_SIZE;
/* If the reference is unset, there are two possibilities:
(a) In the default, Perl-compatible state, set the length negative;
this ensures that every attempt at a match fails. We can't just fail
here, because of the possibility of quantifiers with zero minima.
(b) If the JavaScript compatibility flag is set, set the length to zero
so that the back reference matches an empty string.
Otherwise, set the length to the length of what was matched by the
referenced subpattern. */
if (offset >= offset_top || md->offset_vector[offset] < 0)
length = (md->jscript_compat)? 0 : -1;
else
length = md->offset_vector[offset+1] - md->offset_vector[offset];
/* Set up for repetition, or handle the non-repeated case */
switch (*ecode)
{
case OP_CRSTAR:
case OP_CRMINSTAR:
case OP_CRPLUS:
case OP_CRMINPLUS:
case OP_CRQUERY:
case OP_CRMINQUERY:
c = *ecode++ - OP_CRSTAR;
minimize = (c & 1) != 0;
min = rep_min[c]; /* Pick up values from tables; */
max = rep_max[c]; /* zero for max => infinity */
if (max == 0) max = INT_MAX;
break;
case OP_CRRANGE:
case OP_CRMINRANGE:
minimize = (*ecode == OP_CRMINRANGE);
min = GET2(ecode, 1);
max = GET2(ecode, 1 + IMM2_SIZE);
if (max == 0) max = INT_MAX;
ecode += 1 + 2 * IMM2_SIZE;
break;
default: /* No repeat follows */
if ((length = match_ref(offset, eptr, length, md, caseless)) < 0)
{
if (length == -2) eptr = md->end_subject; /* Partial match */
CHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
eptr += length;
continue; /* With the main loop */
}
/* Handle repeated back references. If the length of the reference is
zero, just continue with the main loop. If the length is negative, it
means the reference is unset in non-Java-compatible mode. If the minimum is
zero, we can continue at the same level without recursion. For any other
minimum, carrying on will result in NOMATCH. */
if (length == 0) continue;
if (length < 0 && min == 0) continue;
/* First, ensure the minimum number of matches are present. We get back
the length of the reference string explicitly rather than passing the
address of eptr, so that eptr can be a register variable. */
COST(min);
for (i = 1; i <= min; i++) /* LOOP_COUNT: COST */
{
int slength;
if ((slength = match_ref(offset, eptr, length, md, caseless)) < 0)
{
if (slength == -2) eptr = md->end_subject; /* Partial match */
CHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
eptr += slength;
}
/* If min = max, continue at the same level without recursion.
They are not both allowed to be zero. */
if (min == max) continue;
/* If minimizing, keep trying and advancing the pointer */
if (minimize)
{
for (fi = min;; fi++) /* LOOP_COUNT: Ok */
{
int slength;
RMATCH(eptr, ecode, offset_top, md, eptrb, RM14);
if (rrc != MATCH_NOMATCH) RRETURN(rrc);
if (fi >= max) RRETURN(MATCH_NOMATCH);
if ((slength = match_ref(offset, eptr, length, md, caseless)) < 0)
{
if (slength == -2) eptr = md->end_subject; /* Partial match */
CHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
eptr += slength;
}
/* Control never gets here */
}
/* If maximizing, find the longest string and work backwards */
else
{
pp = eptr;
for (i = min; i < max; i++)
{
int slength;
if ((slength = match_ref(offset, eptr, length, md, caseless)) < 0) /* LOOP_COUNT: CHK */
{
/* Can't use CHECK_PARTIAL because we don't want to update eptr in
the soft partial matching case. */
if (slength == -2 && md->partial != 0 &&
md->end_subject > md->start_used_ptr)
{
md->hitend = TRUE;
if (md->partial > 1) RRETURN(PCRE_ERROR_PARTIAL);
}
break;
}
eptr += slength;
COST_CHK(1);
}
while (eptr >= pp) /* LOOP_COUNT: Ok */
{
RMATCH(eptr, ecode, offset_top, md, eptrb, RM15);
if (rrc != MATCH_NOMATCH) RRETURN(rrc);
eptr -= length;
}
RRETURN(MATCH_NOMATCH);
}
/* Control never gets here */
/* Match a bit-mapped character class, possibly repeatedly. This op code is
used when all the characters in the class have values in the range 0-255,
and either the matching is caseful, or the characters are in the range
0-127 when UTF-8 processing is enabled. The only difference between
OP_CLASS and OP_NCLASS occurs when a data character outside the range is
encountered.
First, look past the end of the item to see if there is repeat information
following. Then obey similar code to character type repeats - written out
again for speed. */
case OP_NCLASS:
case OP_CLASS:
{
/* The data variable is saved across frames, so the byte map needs to
be stored there. */
#define BYTE_MAP ((pcre_uint8 *)data)
data = ecode + 1; /* Save for matching */
ecode += 1 + (32 / sizeof(pcre_uchar)); /* Advance past the item */
#ifdef ERLANG_INTEGRATION
EDEBUGF(("OP_(N)CLASS (%d)...",*ecode));
#endif
switch (*ecode)
{
case OP_CRSTAR:
case OP_CRMINSTAR:
case OP_CRPLUS:
case OP_CRMINPLUS:
case OP_CRQUERY:
case OP_CRMINQUERY:
c = *ecode++ - OP_CRSTAR;
minimize = (c & 1) != 0;
min = rep_min[c]; /* Pick up values from tables; */
max = rep_max[c]; /* zero for max => infinity */
if (max == 0) max = INT_MAX;
break;
case OP_CRRANGE:
case OP_CRMINRANGE:
minimize = (*ecode == OP_CRMINRANGE);
min = GET2(ecode, 1);
max = GET2(ecode, 1 + IMM2_SIZE);
if (max == 0) max = INT_MAX;
ecode += 1 + 2 * IMM2_SIZE;
break;
default: /* No repeat follows */
min = max = 1;
break;
}
/* First, ensure the minimum number of matches are present. */
#ifdef SUPPORT_UTF
if (utf)
{
COST(min);
for (i = 1; i <= min; i++) /* LOOP_COUNT: COST */
{
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
GETCHARINC(c, eptr);
if (c > 255)
{
if (op == OP_CLASS) RRETURN(MATCH_NOMATCH);
}
else
if ((BYTE_MAP[c/8] & (1 << (c&7))) == 0) RRETURN(MATCH_NOMATCH);
}
}
else
#endif
/* Not UTF mode */
{
COST(min);
for (i = 1; i <= min; i++) /* LOOP_COUNT: COST */
{
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
c = *eptr++;
#ifndef COMPILE_PCRE8
if (c > 255)
{
if (op == OP_CLASS) RRETURN(MATCH_NOMATCH);
}
else
#endif
if ((BYTE_MAP[c/8] & (1 << (c&7))) == 0) RRETURN(MATCH_NOMATCH);
}
}
/* If max == min we can continue with the main loop without the
need to recurse. */
if (min == max) continue;
/* If minimizing, keep testing the rest of the expression and advancing
the pointer while it matches the class. */
if (minimize)
{
#ifdef SUPPORT_UTF
if (utf)
{
for (fi = min;; fi++) /* LOOP_COUNT: Ok */
{
RMATCH(eptr, ecode, offset_top, md, eptrb, RM16);
if (rrc != MATCH_NOMATCH) RRETURN(rrc);
if (fi >= max) RRETURN(MATCH_NOMATCH);
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
GETCHARINC(c, eptr);
if (c > 255)
{
if (op == OP_CLASS) RRETURN(MATCH_NOMATCH);
}
else
if ((BYTE_MAP[c/8] & (1 << (c&7))) == 0) RRETURN(MATCH_NOMATCH);
}
}
else
#endif
/* Not UTF mode */
{
for (fi = min;; fi++) /* LOOP_COUNT: Ok */
{
RMATCH(eptr, ecode, offset_top, md, eptrb, RM17);
if (rrc != MATCH_NOMATCH) RRETURN(rrc);
if (fi >= max) RRETURN(MATCH_NOMATCH);
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
c = *eptr++;
#ifndef COMPILE_PCRE8
if (c > 255)
{
if (op == OP_CLASS) RRETURN(MATCH_NOMATCH);
}
else
#endif
if ((BYTE_MAP[c/8] & (1 << (c&7))) == 0) RRETURN(MATCH_NOMATCH);
}
}
/* Control never gets here */
}
/* If maximizing, find the longest possible run, then work backwards. */
else
{
pp = eptr;
#ifdef SUPPORT_UTF
if (utf)
{
for (i = min; i < max; i++) /* LOOP_COUNT: CHK */
{
int len = 1;
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
break;
}
GETCHARLEN(c, eptr, len);
if (c > 255)
{
if (op == OP_CLASS) break;
}
else
if ((BYTE_MAP[c/8] & (1 << (c&7))) == 0) break;
eptr += len;
COST_CHK(1);
}
for (;;) /* LOOP_COUNT: Ok */
{
RMATCH(eptr, ecode, offset_top, md, eptrb, RM18);
if (rrc != MATCH_NOMATCH) RRETURN(rrc);
if (eptr-- == pp) break; /* Stop if tried at original pos */
BACKCHAR(eptr);
}
}
else
#endif
/* Not UTF mode */
{
for (i = min; i < max; i++) /* LOOP_COUNT: CHK */
{
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
break;
}
c = *eptr;
#ifndef COMPILE_PCRE8
if (c > 255)
{
if (op == OP_CLASS) break;
}
else
#endif
if ((BYTE_MAP[c/8] & (1 << (c&7))) == 0) break;
COST_CHK(1);
eptr++;
}
while (eptr >= pp) /* LOOP_COUNT: Ok */
{
RMATCH(eptr, ecode, offset_top, md, eptrb, RM19);
if (rrc != MATCH_NOMATCH) RRETURN(rrc);
eptr--;
}
}
RRETURN(MATCH_NOMATCH);
}
#undef BYTE_MAP
}
/* Control never gets here */
/* Match an extended character class. This opcode is encountered only
when UTF-8 mode mode is supported. Nevertheless, we may not be in UTF-8
mode, because Unicode properties are supported in non-UTF-8 mode. */
#if defined SUPPORT_UTF || !defined COMPILE_PCRE8
case OP_XCLASS:
{
data = ecode + 1 + LINK_SIZE; /* Save for matching */
ecode += GET(ecode, 1); /* Advance past the item */
switch (*ecode)
{
case OP_CRSTAR:
case OP_CRMINSTAR:
case OP_CRPLUS:
case OP_CRMINPLUS:
case OP_CRQUERY:
case OP_CRMINQUERY:
c = *ecode++ - OP_CRSTAR;
minimize = (c & 1) != 0;
min = rep_min[c]; /* Pick up values from tables; */
max = rep_max[c]; /* zero for max => infinity */
if (max == 0) max = INT_MAX;
break;
case OP_CRRANGE:
case OP_CRMINRANGE:
minimize = (*ecode == OP_CRMINRANGE);
min = GET2(ecode, 1);
max = GET2(ecode, 1 + IMM2_SIZE);
if (max == 0) max = INT_MAX;
ecode += 1 + 2 * IMM2_SIZE;
break;
default: /* No repeat follows */
min = max = 1;
break;
}
/* First, ensure the minimum number of matches are present. */
COST(min);
for (i = 1; i <= min; i++) /* LOOP_COUNT: COST */
{
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
GETCHARINCTEST(c, eptr);
if (!PRIV(xclass)(c, data, utf)) RRETURN(MATCH_NOMATCH);
}
/* If max == min we can continue with the main loop without the
need to recurse. */
if (min == max) continue;
/* If minimizing, keep testing the rest of the expression and advancing
the pointer while it matches the class. */
if (minimize)
{
for (fi = min;; fi++) /* LOOP_COUNT: Ok */
{
RMATCH(eptr, ecode, offset_top, md, eptrb, RM20);
if (rrc != MATCH_NOMATCH) RRETURN(rrc);
if (fi >= max) RRETURN(MATCH_NOMATCH);
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
GETCHARINCTEST(c, eptr);
if (!PRIV(xclass)(c, data, utf)) RRETURN(MATCH_NOMATCH);
}
/* Control never gets here */
}
/* If maximizing, find the longest possible run, then work backwards. */
else
{
pp = eptr;
for (i = min; i < max; i++) /* LOOP_COUNT: CHK */
{
int len = 1;
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
break;
}
#ifdef SUPPORT_UTF
GETCHARLENTEST(c, eptr, len);
#else
c = *eptr;
#endif
if (!PRIV(xclass)(c, data, utf)) break;
eptr += len;
COST_CHK(1);
}
for(;;) /* LOOP_COUNT: Ok */
{
RMATCH(eptr, ecode, offset_top, md, eptrb, RM21);
if (rrc != MATCH_NOMATCH) RRETURN(rrc);
if (eptr-- == pp) break; /* Stop if tried at original pos */
#ifdef SUPPORT_UTF
if (utf) BACKCHAR(eptr);
#endif
}
RRETURN(MATCH_NOMATCH);
}
/* Control never gets here */
}
#endif /* End of XCLASS */
/* Match a single character, casefully */
case OP_CHAR:
#ifdef SUPPORT_UTF
if (utf)
{
length = 1;
ecode++;
GETCHARLEN(fc, ecode, length);
if (length > md->end_subject - eptr)
{
CHECK_PARTIAL(); /* Not SCHECK_PARTIAL() */
RRETURN(MATCH_NOMATCH);
}
while (length-- > 0) if (*ecode++ != RAWUCHARINC(eptr)) RRETURN(MATCH_NOMATCH); /* LOOP_COUNT: Ok */
}
else
#endif
/* Not UTF mode */
{
if (md->end_subject - eptr < 1)
{
SCHECK_PARTIAL(); /* This one can use SCHECK_PARTIAL() */
RRETURN(MATCH_NOMATCH);
}
EDEBUGF(("code to match:%d, code is:%d",ecode[1],*eptr));
if (ecode[1] != *eptr++) RRETURN(MATCH_NOMATCH);
ecode += 2;
}
break;
/* Match a single character, caselessly. If we are at the end of the
subject, give up immediately. */
case OP_CHARI:
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
#ifdef SUPPORT_UTF
if (utf)
{
length = 1;
ecode++;
GETCHARLEN(fc, ecode, length);
/* If the pattern character's value is < 128, we have only one byte, and
we know that its other case must also be one byte long, so we can use the
fast lookup table. We know that there is at least one byte left in the
subject. */
if (fc < 128)
{
pcre_uint32 cc = RAWUCHAR(eptr);
if (md->lcc[fc] != TABLE_GET(cc, md->lcc, cc)) RRETURN(MATCH_NOMATCH);
ecode++;
eptr++;
}
/* Otherwise we must pick up the subject character. Note that we cannot
use the value of "length" to check for sufficient bytes left, because the
other case of the character may have more or fewer bytes. */
else
{
pcre_uint32 dc;
GETCHARINC(dc, eptr);
ecode += length;
/* If we have Unicode property support, we can use it to test the other
case of the character, if there is one. */
if (fc != dc)
{
#ifdef SUPPORT_UCP
if (dc != UCD_OTHERCASE(fc))
#endif
RRETURN(MATCH_NOMATCH);
}
}
}
else
#endif /* SUPPORT_UTF */
/* Not UTF mode */
{
if (TABLE_GET(ecode[1], md->lcc, ecode[1])
!= TABLE_GET(*eptr, md->lcc, *eptr)) RRETURN(MATCH_NOMATCH);
eptr++;
ecode += 2;
}
break;
/* Match a single character repeatedly. */
case OP_EXACT:
case OP_EXACTI:
min = max = GET2(ecode, 1);
ecode += 1 + IMM2_SIZE;
goto REPEATCHAR;
case OP_POSUPTO:
case OP_POSUPTOI:
possessive = TRUE;
/* Fall through */
case OP_UPTO:
case OP_UPTOI:
case OP_MINUPTO:
case OP_MINUPTOI:
min = 0;
max = GET2(ecode, 1);
minimize = *ecode == OP_MINUPTO || *ecode == OP_MINUPTOI;
ecode += 1 + IMM2_SIZE;
goto REPEATCHAR;
case OP_POSSTAR:
case OP_POSSTARI:
possessive = TRUE;
min = 0;
max = INT_MAX;
ecode++;
goto REPEATCHAR;
case OP_POSPLUS:
case OP_POSPLUSI:
possessive = TRUE;
min = 1;
max = INT_MAX;
ecode++;
goto REPEATCHAR;
case OP_POSQUERY:
case OP_POSQUERYI:
possessive = TRUE;
min = 0;
max = 1;
ecode++;
goto REPEATCHAR;
case OP_STAR:
case OP_STARI:
case OP_MINSTAR:
case OP_MINSTARI:
case OP_PLUS:
case OP_PLUSI:
case OP_MINPLUS:
case OP_MINPLUSI:
case OP_QUERY:
case OP_QUERYI:
case OP_MINQUERY:
case OP_MINQUERYI:
c = *ecode++ - ((op < OP_STARI)? OP_STAR : OP_STARI);
minimize = (c & 1) != 0;
min = rep_min[c]; /* Pick up values from tables; */
max = rep_max[c]; /* zero for max => infinity */
if (max == 0) max = INT_MAX;
/* Common code for all repeated single-character matches. We first check
for the minimum number of characters. If the minimum equals the maximum, we
are done. Otherwise, if minimizing, check the rest of the pattern for a
match; if there isn't one, advance up to the maximum, one character at a
time.
If maximizing, advance up to the maximum number of matching characters,
until eptr is past the end of the maximum run. If possessive, we are
then done (no backing up). Otherwise, match at this position; anything
other than no match is immediately returned. For nomatch, back up one
character, unless we are matching \R and the last thing matched was
\r\n, in which case, back up two bytes. When we reach the first optional
character position, we can save stack by doing a tail recurse.
The various UTF/non-UTF and caseful/caseless cases are handled separately,
for speed. */
REPEATCHAR:
#ifdef SUPPORT_UTF
if (utf)
{
length = 1;
charptr = ecode;
GETCHARLEN(fc, ecode, length);
ecode += length;
/* Handle multibyte character matching specially here. There is
support for caseless matching if UCP support is present. */
if (length > 1)
{
#ifdef SUPPORT_UCP
pcre_uint32 othercase;
if (op >= OP_STARI && /* Caseless */
(othercase = UCD_OTHERCASE(fc)) != fc)
oclength = PRIV(ord2utf)(othercase, occhars);
else oclength = 0;
#endif /* SUPPORT_UCP */
COST(min);
for (i = 1; i <= min; i++) /* LOOP_COUNT: COST */
{
if (eptr <= md->end_subject - length &&
memcmp(eptr, charptr, IN_UCHARS(length)) == 0) eptr += length;
#ifdef SUPPORT_UCP
else if (oclength > 0 &&
eptr <= md->end_subject - oclength &&
memcmp(eptr, occhars, IN_UCHARS(oclength)) == 0) eptr += oclength;
#endif /* SUPPORT_UCP */
else
{
CHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
}
if (min == max) continue;
if (minimize)
{
for (fi = min;; fi++) /* LOOP_COUNT: Ok */
{
RMATCH(eptr, ecode, offset_top, md, eptrb, RM22);
if (rrc != MATCH_NOMATCH) RRETURN(rrc);
if (fi >= max) RRETURN(MATCH_NOMATCH);
if (eptr <= md->end_subject - length &&
memcmp(eptr, charptr, IN_UCHARS(length)) == 0) eptr += length;
#ifdef SUPPORT_UCP
else if (oclength > 0 &&
eptr <= md->end_subject - oclength &&
memcmp(eptr, occhars, IN_UCHARS(oclength)) == 0) eptr += oclength;
#endif /* SUPPORT_UCP */
else
{
CHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
}
/* Control never gets here */
}
else /* Maximize */
{
pp = eptr;
for (i = min; i < max; i++) /* LOOP_COUNT: CHK */
{
if (eptr <= md->end_subject - length &&
memcmp(eptr, charptr, IN_UCHARS(length)) == 0) eptr += length;
#ifdef SUPPORT_UCP
else if (oclength > 0 &&
eptr <= md->end_subject - oclength &&
memcmp(eptr, occhars, IN_UCHARS(oclength)) == 0) eptr += oclength;
#endif /* SUPPORT_UCP */
else
{
CHECK_PARTIAL();
break;
}
COST_CHK(1);
}
if (possessive) continue; /* No backtracking */
for(;;) /* LOOP_COUNT: Ok */
{
if (eptr == pp) goto TAIL_RECURSE;
RMATCH(eptr, ecode, offset_top, md, eptrb, RM23);
if (rrc != MATCH_NOMATCH) RRETURN(rrc);
#ifdef SUPPORT_UCP
eptr--;
BACKCHAR(eptr);
#else /* without SUPPORT_UCP */
eptr -= length;
#endif /* SUPPORT_UCP */
}
}
/* Control never gets here */
}
/* If the length of a UTF-8 character is 1, we fall through here, and
obey the code as for non-UTF-8 characters below, though in this case the
value of fc will always be < 128. */
}
else
#endif /* SUPPORT_UTF */
/* When not in UTF-8 mode, load a single-byte character. */
fc = *ecode++;
/* The value of fc at this point is always one character, though we may
or may not be in UTF mode. The code is duplicated for the caseless and
caseful cases, for speed, since matching characters is likely to be quite
common. First, ensure the minimum number of matches are present. If min =
max, continue at the same level without recursing. Otherwise, if
minimizing, keep trying the rest of the expression and advancing one
matching character if failing, up to the maximum. Alternatively, if
maximizing, find the maximum number of characters and work backwards. */
DPRINTF(("matching %c{%d,%d} against subject %.*s\n", fc, min, max,
max, (char *)eptr));
if (op >= OP_STARI) /* Caseless */
{
#ifdef COMPILE_PCRE8
/* fc must be < 128 if UTF is enabled. */
foc = md->fcc[fc];
#else
#ifdef SUPPORT_UTF
#ifdef SUPPORT_UCP
if (utf && fc > 127)
foc = UCD_OTHERCASE(fc);
#else
if (utf && fc > 127)
foc = fc;
#endif /* SUPPORT_UCP */
else
#endif /* SUPPORT_UTF */
foc = TABLE_GET(fc, md->fcc, fc);
#endif /* COMPILE_PCRE8 */
for (i = 1; i <= min; i++) /* LOOP_COUNT: CHK */
{
pcre_uint32 cc; /* Faster than pcre_uchar */
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
cc = RAWUCHARTEST(eptr);
if (fc != cc && foc != cc) RRETURN(MATCH_NOMATCH);
eptr++;
COST_CHK(1);
}
if (min == max) continue;
if (minimize)
{
for (fi = min;; fi++) /* LOOP_COUNT: Ok */
{
pcre_uint32 cc; /* Faster than pcre_uchar */
RMATCH(eptr, ecode, offset_top, md, eptrb, RM24);
if (rrc != MATCH_NOMATCH) RRETURN(rrc);
if (fi >= max) RRETURN(MATCH_NOMATCH);
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
cc = RAWUCHARTEST(eptr);
if (fc != cc && foc != cc) RRETURN(MATCH_NOMATCH);
eptr++;
}
/* Control never gets here */
}
else /* Maximize */
{
pp = eptr;
for (i = min; i < max; i++) /* LOOP_COUNT: CHK */
{
pcre_uint32 cc; /* Faster than pcre_uchar */
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
break;
}
cc = RAWUCHARTEST(eptr);
if (fc != cc && foc != cc) break;
eptr++;
COST_CHK(1);
}
if (possessive) continue; /* No backtracking */
for (;;) /* LOOP_COUNT: Ok */
{
if (eptr == pp) goto TAIL_RECURSE;
RMATCH(eptr, ecode, offset_top, md, eptrb, RM25);
eptr--;
if (rrc != MATCH_NOMATCH) RRETURN(rrc);
}
RRETURN(MATCH_NOMATCH);
}
/* Control never gets here */
}
/* Caseful comparisons (includes all multi-byte characters) */
else
{
COST(min);
for (i = 1; i <= min; i++) /* LOOP_COUNT: COST */
{
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
if (fc != RAWUCHARINCTEST(eptr)) RRETURN(MATCH_NOMATCH);
}
if (min == max) continue;
if (minimize)
{
for (fi = min;; fi++) /* LOOP_COUNT: Ok */
{
RMATCH(eptr, ecode, offset_top, md, eptrb, RM26);
if (rrc != MATCH_NOMATCH) RRETURN(rrc);
if (fi >= max) RRETURN(MATCH_NOMATCH);
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
if (fc != RAWUCHARINCTEST(eptr)) RRETURN(MATCH_NOMATCH);
}
/* Control never gets here */
}
else /* Maximize */
{
pp = eptr;
for (i = min; i < max; i++) /* LOOP_COUNT: CHK */
{
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
break;
}
if (fc != RAWUCHARTEST(eptr)) break;
eptr++;
COST_CHK(1);
}
if (possessive) continue; /* No backtracking */
for (;;) /* LOOP_COUNT: Ok */
{
if (eptr == pp) goto TAIL_RECURSE;
RMATCH(eptr, ecode, offset_top, md, eptrb, RM27);
eptr--;
if (rrc != MATCH_NOMATCH) RRETURN(rrc);
}
RRETURN(MATCH_NOMATCH);
}
}
/* Control never gets here */
/* Match a negated single one-byte character. The character we are
checking can be multibyte. */
case OP_NOT:
case OP_NOTI:
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
#ifdef SUPPORT_UTF
if (utf)
{
register pcre_uint32 ch, och;
ecode++;
GETCHARINC(ch, ecode);
GETCHARINC(c, eptr);
if (op == OP_NOT)
{
if (ch == c) RRETURN(MATCH_NOMATCH);
}
else
{
#ifdef SUPPORT_UCP
if (ch > 127)
och = UCD_OTHERCASE(ch);
#else
if (ch > 127)
och = ch;
#endif /* SUPPORT_UCP */
else
och = TABLE_GET(ch, md->fcc, ch);
if (ch == c || och == c) RRETURN(MATCH_NOMATCH);
}
}
else
#endif
{
register pcre_uint32 ch = ecode[1];
c = *eptr++;
if (ch == c || (op == OP_NOTI && TABLE_GET(ch, md->fcc, ch) == c))
RRETURN(MATCH_NOMATCH);
ecode += 2;
}
break;
/* Match a negated single one-byte character repeatedly. This is almost a
repeat of the code for a repeated single character, but I haven't found a
nice way of commoning these up that doesn't require a test of the
positive/negative option for each character match. Maybe that wouldn't add
very much to the time taken, but character matching *is* what this is all
about... */
case OP_NOTEXACT:
case OP_NOTEXACTI:
min = max = GET2(ecode, 1);
ecode += 1 + IMM2_SIZE;
goto REPEATNOTCHAR;
case OP_NOTUPTO:
case OP_NOTUPTOI:
case OP_NOTMINUPTO:
case OP_NOTMINUPTOI:
min = 0;
max = GET2(ecode, 1);
minimize = *ecode == OP_NOTMINUPTO || *ecode == OP_NOTMINUPTOI;
ecode += 1 + IMM2_SIZE;
goto REPEATNOTCHAR;
case OP_NOTPOSSTAR:
case OP_NOTPOSSTARI:
possessive = TRUE;
min = 0;
max = INT_MAX;
ecode++;
goto REPEATNOTCHAR;
case OP_NOTPOSPLUS:
case OP_NOTPOSPLUSI:
possessive = TRUE;
min = 1;
max = INT_MAX;
ecode++;
goto REPEATNOTCHAR;
case OP_NOTPOSQUERY:
case OP_NOTPOSQUERYI:
possessive = TRUE;
min = 0;
max = 1;
ecode++;
goto REPEATNOTCHAR;
case OP_NOTPOSUPTO:
case OP_NOTPOSUPTOI:
possessive = TRUE;
min = 0;
max = GET2(ecode, 1);
ecode += 1 + IMM2_SIZE;
goto REPEATNOTCHAR;
case OP_NOTSTAR:
case OP_NOTSTARI:
case OP_NOTMINSTAR:
case OP_NOTMINSTARI:
case OP_NOTPLUS:
case OP_NOTPLUSI:
case OP_NOTMINPLUS:
case OP_NOTMINPLUSI:
case OP_NOTQUERY:
case OP_NOTQUERYI:
case OP_NOTMINQUERY:
case OP_NOTMINQUERYI:
c = *ecode++ - ((op >= OP_NOTSTARI)? OP_NOTSTARI: OP_NOTSTAR);
minimize = (c & 1) != 0;
min = rep_min[c]; /* Pick up values from tables; */
max = rep_max[c]; /* zero for max => infinity */
if (max == 0) max = INT_MAX;
/* Common code for all repeated single-byte matches. */
REPEATNOTCHAR:
GETCHARINCTEST(fc, ecode);
/* The code is duplicated for the caseless and caseful cases, for speed,
since matching characters is likely to be quite common. First, ensure the
minimum number of matches are present. If min = max, continue at the same
level without recursing. Otherwise, if minimizing, keep trying the rest of
the expression and advancing one matching character if failing, up to the
maximum. Alternatively, if maximizing, find the maximum number of
characters and work backwards. */
DPRINTF(("negative matching %c{%d,%d} against subject %.*s\n", fc, min, max,
max, (char *)eptr));
if (op >= OP_NOTSTARI) /* Caseless */
{
#ifdef SUPPORT_UTF
#ifdef SUPPORT_UCP
if (utf && fc > 127)
foc = UCD_OTHERCASE(fc);
#else
if (utf && fc > 127)
foc = fc;
#endif /* SUPPORT_UCP */
else
#endif /* SUPPORT_UTF */
foc = TABLE_GET(fc, md->fcc, fc);
#ifdef SUPPORT_UTF
if (utf)
{
register pcre_uint32 d;
COST(min);
for (i = 1; i <= min; i++) /* LOOP_COUNT: COST */
{
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
GETCHARINC(d, eptr);
if (fc == d || (unsigned int)foc == d) RRETURN(MATCH_NOMATCH);
}
}
else
#endif /* SUPPORT_UTF */
/* Not UTF mode */
{
COST(min);
for (i = 1; i <= min; i++) /* LOOP_COUNT: COST */
{
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
if (fc == *eptr || foc == *eptr) RRETURN(MATCH_NOMATCH);
eptr++;
}
}
if (min == max) continue;
if (minimize)
{
#ifdef SUPPORT_UTF
if (utf)
{
register pcre_uint32 d;
for (fi = min;; fi++) /* LOOP_COUNT: Ok */
{
RMATCH(eptr, ecode, offset_top, md, eptrb, RM28);
if (rrc != MATCH_NOMATCH) RRETURN(rrc);
if (fi >= max) RRETURN(MATCH_NOMATCH);
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
GETCHARINC(d, eptr);
if (fc == d || (unsigned int)foc == d) RRETURN(MATCH_NOMATCH);
}
}
else
#endif /*SUPPORT_UTF */
/* Not UTF mode */
{
for (fi = min;; fi++) /* LOOP_COUNT: Ok */
{
RMATCH(eptr, ecode, offset_top, md, eptrb, RM29);
if (rrc != MATCH_NOMATCH) RRETURN(rrc);
if (fi >= max) RRETURN(MATCH_NOMATCH);
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
if (fc == *eptr || foc == *eptr) RRETURN(MATCH_NOMATCH);
eptr++;
}
}
/* Control never gets here */
}
/* Maximize case */
else
{
pp = eptr;
#ifdef SUPPORT_UTF
if (utf)
{
register pcre_uint32 d;
for (i = min; i < max; i++) /* LOOP_COUNT: CHK */
{
int len = 1;
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
break;
}
GETCHARLEN(d, eptr, len);
if (fc == d || (unsigned int)foc == d) break;
eptr += len;
COST_CHK(1); /* 'd' is not alive */
}
if (possessive) continue; /* No backtracking */
for(;;) /* LOOP_COUNT: Ok */
{
if (eptr == pp) goto TAIL_RECURSE;
RMATCH(eptr, ecode, offset_top, md, eptrb, RM30);
if (rrc != MATCH_NOMATCH) RRETURN(rrc);
eptr--;
BACKCHAR(eptr);
}
}
else
#endif /* SUPPORT_UTF */
/* Not UTF mode */
{
for (i = min; i < max; i++) /* LOOP_COUNT: CHK */
{
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
break;
}
if (fc == *eptr || foc == *eptr) break;
eptr++;
COST_CHK(1);
}
if (possessive) continue; /* No backtracking */
for (;;) /* LOOP_COUNT: Ok */
{
if (eptr == pp) goto TAIL_RECURSE;
RMATCH(eptr, ecode, offset_top, md, eptrb, RM31);
if (rrc != MATCH_NOMATCH) RRETURN(rrc);
eptr--;
}
}
RRETURN(MATCH_NOMATCH);
}
/* Control never gets here */
}
/* Caseful comparisons */
else
{
#ifdef SUPPORT_UTF
if (utf)
{
register pcre_uint32 d;
for (i = 1; i <= min; i++) /* LOOP_COUNT: CHK */
{
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
GETCHARINC(d, eptr);
if (fc == d) RRETURN(MATCH_NOMATCH);
COST_CHK(1);
}
}
else
#endif
/* Not UTF mode */
{
COST(min);
for (i = 1; i <= min; i++) /* LOOP_COUNT: Ok */
{
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
if (fc == *eptr++) RRETURN(MATCH_NOMATCH);
}
}
if (min == max) continue;
if (minimize)
{
#ifdef SUPPORT_UTF
if (utf)
{
register pcre_uint32 d;
for (fi = min;; fi++) /* LOOP_COUNT: Ok */
{
RMATCH(eptr, ecode, offset_top, md, eptrb, RM32);
if (rrc != MATCH_NOMATCH) RRETURN(rrc);
if (fi >= max) RRETURN(MATCH_NOMATCH);
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
GETCHARINC(d, eptr);
if (fc == d) RRETURN(MATCH_NOMATCH);
}
}
else
#endif
/* Not UTF mode */
{
for (fi = min;; fi++) /* LOOP_COUNT: Ok */
{
RMATCH(eptr, ecode, offset_top, md, eptrb, RM33);
if (rrc != MATCH_NOMATCH) RRETURN(rrc);
if (fi >= max) RRETURN(MATCH_NOMATCH);
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
if (fc == *eptr++) RRETURN(MATCH_NOMATCH);
}
}
/* Control never gets here */
}
/* Maximize case */
else
{
pp = eptr;
#ifdef SUPPORT_UTF
if (utf)
{
register pcre_uint32 d;
for (i = min; i < max; i++) /* LOOP_COUNT: CHK */
{
int len = 1;
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
break;
}
GETCHARLEN(d, eptr, len);
if (fc == d) break;
eptr += len;
COST_CHK(1);
}
if (possessive) continue; /* No backtracking */
for(;;) /* LOOP_COUNT: Ok */
{
if (eptr == pp) goto TAIL_RECURSE;
RMATCH(eptr, ecode, offset_top, md, eptrb, RM34);
if (rrc != MATCH_NOMATCH) RRETURN(rrc);
eptr--;
BACKCHAR(eptr);
}
}
else
#endif
/* Not UTF mode */
{
for (i = min; i < max; i++) /* LOOP_COUNT: CHK */
{
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
break;
}
if (fc == *eptr) break;
eptr++;
COST_CHK(1);
}
if (possessive) continue; /* No backtracking */
for (;;) /* LOOP_COUNT: Ok */
{
if (eptr == pp) goto TAIL_RECURSE;
RMATCH(eptr, ecode, offset_top, md, eptrb, RM35);
if (rrc != MATCH_NOMATCH) RRETURN(rrc);
eptr--;
}
}
RRETURN(MATCH_NOMATCH);
}
}
/* Control never gets here */
/* Match a single character type repeatedly; several different opcodes
share code. This is very similar to the code for single characters, but we
repeat it in the interests of efficiency. */
case OP_TYPEEXACT:
min = max = GET2(ecode, 1);
minimize = TRUE;
ecode += 1 + IMM2_SIZE;
goto REPEATTYPE;
case OP_TYPEUPTO:
case OP_TYPEMINUPTO:
min = 0;
max = GET2(ecode, 1);
minimize = *ecode == OP_TYPEMINUPTO;
ecode += 1 + IMM2_SIZE;
goto REPEATTYPE;
case OP_TYPEPOSSTAR:
possessive = TRUE;
min = 0;
max = INT_MAX;
ecode++;
goto REPEATTYPE;
case OP_TYPEPOSPLUS:
possessive = TRUE;
min = 1;
max = INT_MAX;
ecode++;
goto REPEATTYPE;
case OP_TYPEPOSQUERY:
possessive = TRUE;
min = 0;
max = 1;
ecode++;
goto REPEATTYPE;
case OP_TYPEPOSUPTO:
possessive = TRUE;
min = 0;
max = GET2(ecode, 1);
ecode += 1 + IMM2_SIZE;
goto REPEATTYPE;
case OP_TYPESTAR:
case OP_TYPEMINSTAR:
case OP_TYPEPLUS:
case OP_TYPEMINPLUS:
case OP_TYPEQUERY:
case OP_TYPEMINQUERY:
c = *ecode++ - OP_TYPESTAR;
minimize = (c & 1) != 0;
min = rep_min[c]; /* Pick up values from tables; */
max = rep_max[c]; /* zero for max => infinity */
if (max == 0) max = INT_MAX;
/* Common code for all repeated single character type matches. Note that
in UTF-8 mode, '.' matches a character of any length, but for the other
character types, the valid characters are all one-byte long. */
REPEATTYPE:
ctype = *ecode++; /* Code for the character type */
#ifdef SUPPORT_UCP
if (ctype == OP_PROP || ctype == OP_NOTPROP)
{
prop_fail_result = ctype == OP_NOTPROP;
prop_type = *ecode++;
prop_value = *ecode++;
}
else prop_type = -1;
#endif
/* First, ensure the minimum number of matches are present. Use inline
code for maximizing the speed, and do the type test once at the start
(i.e. keep it out of the loop). Separate the UTF-8 code completely as that
is tidier. Also separate the UCP code, which can be the same for both UTF-8
and single-bytes. */
if (min > 0)
{
#ifdef SUPPORT_UCP
if (prop_type >= 0)
{
COST(min);
switch(prop_type)
{
case PT_ANY:
if (prop_fail_result) RRETURN(MATCH_NOMATCH);
for (i = 1; i <= min; i++) /* LOOP_COUNT: COST (above) */
{
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
GETCHARINCTEST(c, eptr);
}
break;
case PT_LAMP:
for (i = 1; i <= min; i++) /* LOOP_COUNT: COST (above) */
{
int chartype;
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
GETCHARINCTEST(c, eptr);
chartype = UCD_CHARTYPE(c);
if ((chartype == ucp_Lu ||
chartype == ucp_Ll ||
chartype == ucp_Lt) == prop_fail_result)
RRETURN(MATCH_NOMATCH);
}
break;
case PT_GC:
for (i = 1; i <= min; i++) /* LOOP_COUNT: COST (above) */
{
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
GETCHARINCTEST(c, eptr);
if ((UCD_CATEGORY(c) == prop_value) == prop_fail_result)
RRETURN(MATCH_NOMATCH);
}
break;
case PT_PC:
for (i = 1; i <= min; i++) /* LOOP_COUNT: COST (above) */
{
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
GETCHARINCTEST(c, eptr);
if ((UCD_CHARTYPE(c) == prop_value) == prop_fail_result)
RRETURN(MATCH_NOMATCH);
}
break;
case PT_SC:
for (i = 1; i <= min; i++) /* LOOP_COUNT: COST (above) */
{
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
GETCHARINCTEST(c, eptr);
if ((UCD_SCRIPT(c) == prop_value) == prop_fail_result)
RRETURN(MATCH_NOMATCH);
}
break;
case PT_ALNUM: /* LOOP_COUNT: COST (above) */
for (i = 1; i <= min; i++)
{
int category;
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
GETCHARINCTEST(c, eptr);
category = UCD_CATEGORY(c);
if ((category == ucp_L || category == ucp_N) == prop_fail_result)
RRETURN(MATCH_NOMATCH);
}
break;
case PT_SPACE: /* Perl space */
for (i = 1; i <= min; i++) /* LOOP_COUNT: COST (above) */
{
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
GETCHARINCTEST(c, eptr);
if ((UCD_CATEGORY(c) == ucp_Z || c == CHAR_HT || c == CHAR_NL ||
c == CHAR_FF || c == CHAR_CR)
== prop_fail_result)
RRETURN(MATCH_NOMATCH);
}
break;
case PT_PXSPACE: /* POSIX space */
for (i = 1; i <= min; i++) /* LOOP_COUNT: COST (above) */
{
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
GETCHARINCTEST(c, eptr);
if ((UCD_CATEGORY(c) == ucp_Z || c == CHAR_HT || c == CHAR_NL ||
c == CHAR_VT || c == CHAR_FF || c == CHAR_CR)
== prop_fail_result)
RRETURN(MATCH_NOMATCH);
}
break;
case PT_WORD:
for (i = 1; i <= min; i++) /* LOOP_COUNT: COST (above) */
{
int category;
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
GETCHARINCTEST(c, eptr);
category = UCD_CATEGORY(c);
if ((category == ucp_L || category == ucp_N || c == CHAR_UNDERSCORE)
== prop_fail_result)
RRETURN(MATCH_NOMATCH);
}
break;
case PT_CLIST:
for (i = 1; i <= min; i++) /* LOOP_COUNT: COST (above) */
{
const pcre_uint32 *cp;
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
GETCHARINCTEST(c, eptr);
cp = PRIV(ucd_caseless_sets) + prop_value;
for (;;) /* LOOP_COUNT: COST */
{
if (c < *cp)
{ if (prop_fail_result) break; else { RRETURN(MATCH_NOMATCH); } }
if (c == *cp++)
{ if (prop_fail_result) { RRETURN(MATCH_NOMATCH); } else break; }
COST(1);
}
}
break;
case PT_UCNC:
for (i = 1; i <= min; i++) /* LOOP_COUNT: COST (above) */
{
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
GETCHARINCTEST(c, eptr);
if ((c == CHAR_DOLLAR_SIGN || c == CHAR_COMMERCIAL_AT ||
c == CHAR_GRAVE_ACCENT || (c >= 0xa0 && c <= 0xd7ff) ||
c >= 0xe000) == prop_fail_result)
RRETURN(MATCH_NOMATCH);
}
break;
/* This should not occur */
default:
RRETURN(PCRE_ERROR_INTERNAL);
}
}
/* Match extended Unicode sequences. We will get here only if the
support is in the binary; otherwise a compile-time error occurs. */
else if (ctype == OP_EXTUNI)
{
COST(min);
for (i = 1; i <= min; i++) /* LOOP_COUNT: COST */
{
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
else
{
#ifndef ERLANG_INTEGRATION
int lgb, rgb;
#endif
GETCHARINCTEST(c, eptr);
lgb = UCD_GRAPHBREAK(c);
while (eptr < md->end_subject) /* LOOP_COUNT: CHK */
{
int len = 1;
if (!utf) c = *eptr; else { GETCHARLEN(c, eptr, len); }
rgb = UCD_GRAPHBREAK(c);
if ((PRIV(ucp_gbtable)[lgb] & (1 << rgb)) == 0) break;
lgb = rgb;
eptr += len;
COST_CHK(1);
}
}
CHECK_PARTIAL();
}
}
else
#endif /* SUPPORT_UCP */
/* Handle all other cases when the coding is UTF-8 */
#ifdef SUPPORT_UTF
if (utf) switch(ctype)
{
case OP_ANY:
COST(min);
for (i = 1; i <= min; i++) /* LOOP_COUNT: COST */
{
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
if (IS_NEWLINE(eptr)) RRETURN(MATCH_NOMATCH);
if (md->partial != 0 &&
eptr + 1 >= md->end_subject &&
NLBLOCK->nltype == NLTYPE_FIXED &&
NLBLOCK->nllen == 2 &&
RAWUCHAR(eptr) == NLBLOCK->nl[0])
{
md->hitend = TRUE;
if (md->partial > 1) RRETURN(PCRE_ERROR_PARTIAL);
}
eptr++;
ACROSSCHAR(eptr < md->end_subject, *eptr, eptr++);
}
break;
case OP_ALLANY:
COST(min);
for (i = 1; i <= min; i++) /* LOOP_COUNT: COST */
{
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
eptr++;
ACROSSCHAR(eptr < md->end_subject, *eptr, eptr++);
}
break;
case OP_ANYBYTE:
if (eptr > md->end_subject - min) RRETURN(MATCH_NOMATCH);
eptr += min;
break;
case OP_ANYNL:
COST(min);
for (i = 1; i <= min; i++) /* LOOP_COUNT: COST */
{
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
GETCHARINC(c, eptr);
switch(c)
{
default: RRETURN(MATCH_NOMATCH);
case CHAR_CR:
if (eptr < md->end_subject && RAWUCHAR(eptr) == CHAR_LF) eptr++;
break;
case CHAR_LF:
break;
case CHAR_VT:
case CHAR_FF:
case CHAR_NEL:
#ifndef EBCDIC
case 0x2028:
case 0x2029:
#endif /* Not EBCDIC */
if (md->bsr_anycrlf) RRETURN(MATCH_NOMATCH);
break;
}
}
break;
case OP_NOT_HSPACE:
COST(min);
for (i = 1; i <= min; i++) /* LOOP_COUNT: COST */
{
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
GETCHARINC(c, eptr);
switch(c)
{
HSPACE_CASES: RRETURN(MATCH_NOMATCH); /* Byte and multibyte cases */
default: break;
}
}
break;
case OP_HSPACE:
COST(min);
for (i = 1; i <= min; i++) /* LOOP_COUNT: COST */
{
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
GETCHARINC(c, eptr);
switch(c)
{
HSPACE_CASES: break; /* Byte and multibyte cases */
default: RRETURN(MATCH_NOMATCH);
}
}
break;
case OP_NOT_VSPACE:
COST(min);
for (i = 1; i <= min; i++) /* LOOP_COUNT: COST */
{
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
GETCHARINC(c, eptr);
switch(c)
{
VSPACE_CASES: RRETURN(MATCH_NOMATCH);
default: break;
}
}
break;
case OP_VSPACE:
COST(min);
for (i = 1; i <= min; i++) /* LOOP_COUNT: COST */
{
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
GETCHARINC(c, eptr);
switch(c)
{
VSPACE_CASES: break;
default: RRETURN(MATCH_NOMATCH);
}
}
break;
case OP_NOT_DIGIT:
COST(min);
for (i = 1; i <= min; i++) /* LOOP_COUNT: COST */
{
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
GETCHARINC(c, eptr);
if (c < 128 && (md->ctypes[c] & ctype_digit) != 0)
RRETURN(MATCH_NOMATCH);
}
break;
case OP_DIGIT:
COST(min);
for (i = 1; i <= min; i++) /* LOOP_COUNT: COST */
{
pcre_uint32 cc;
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
cc = RAWUCHAR(eptr);
if (cc >= 128 || (md->ctypes[cc] & ctype_digit) == 0)
RRETURN(MATCH_NOMATCH);
eptr++;
/* No need to skip more bytes - we know it's a 1-byte character */
}
break;
case OP_NOT_WHITESPACE:
COST(min);
for (i = 1; i <= min; i++) /* LOOP_COUNT: COST */
{
pcre_uint32 cc;
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
cc = RAWUCHAR(eptr);
if (cc < 128 && (md->ctypes[cc] & ctype_space) != 0)
RRETURN(MATCH_NOMATCH);
eptr++;
ACROSSCHAR(eptr < md->end_subject, *eptr, eptr++);
}
break;
case OP_WHITESPACE:
COST(min);
for (i = 1; i <= min; i++) /* LOOP_COUNT: COST */
{
pcre_uint32 cc;
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
cc = RAWUCHAR(eptr);
if (cc >= 128 || (md->ctypes[cc] & ctype_space) == 0)
RRETURN(MATCH_NOMATCH);
eptr++;
/* No need to skip more bytes - we know it's a 1-byte character */
}
break;
case OP_NOT_WORDCHAR:
COST(min);
for (i = 1; i <= min; i++) /* LOOP_COUNT: COST */
{
pcre_uint32 cc;
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
cc = RAWUCHAR(eptr);
if (cc < 128 && (md->ctypes[cc] & ctype_word) != 0)
RRETURN(MATCH_NOMATCH);
eptr++;
ACROSSCHAR(eptr < md->end_subject, *eptr, eptr++);
}
break;
case OP_WORDCHAR:
COST(min);
for (i = 1; i <= min; i++) /* LOOP_COUNT: COST */
{
pcre_uint32 cc;
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
cc = RAWUCHAR(eptr);
if (cc >= 128 || (md->ctypes[cc] & ctype_word) == 0)
RRETURN(MATCH_NOMATCH);
eptr++;
/* No need to skip more bytes - we know it's a 1-byte character */
}
break;
default:
RRETURN(PCRE_ERROR_INTERNAL);
} /* End switch(ctype) */
else
#endif /* SUPPORT_UTF */
/* Code for the non-UTF-8 case for minimum matching of operators other
than OP_PROP and OP_NOTPROP. */
switch(ctype)
{
case OP_ANY:
COST(min);
for (i = 1; i <= min; i++) /* LOOP_COUNT: COST */
{
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
if (IS_NEWLINE(eptr)) RRETURN(MATCH_NOMATCH);
if (md->partial != 0 &&
eptr + 1 >= md->end_subject &&
NLBLOCK->nltype == NLTYPE_FIXED &&
NLBLOCK->nllen == 2 &&
*eptr == NLBLOCK->nl[0])
{
md->hitend = TRUE;
if (md->partial > 1) RRETURN(PCRE_ERROR_PARTIAL);
}
eptr++;
}
break;
case OP_ALLANY:
if (eptr > md->end_subject - min)
{
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
eptr += min;
break;
case OP_ANYBYTE:
if (eptr > md->end_subject - min)
{
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
eptr += min;
break;
case OP_ANYNL:
COST(min);
for (i = 1; i <= min; i++) /* LOOP_COUNT: COST */
{
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
switch(*eptr++)
{
default: RRETURN(MATCH_NOMATCH);
case CHAR_CR:
if (eptr < md->end_subject && *eptr == CHAR_LF) eptr++;
break;
case CHAR_LF:
break;
case CHAR_VT:
case CHAR_FF:
case CHAR_NEL:
#if defined COMPILE_PCRE16 || defined COMPILE_PCRE32
case 0x2028:
case 0x2029:
#endif
if (md->bsr_anycrlf) RRETURN(MATCH_NOMATCH);
break;
}
}
break;
case OP_NOT_HSPACE:
COST(min);
for (i = 1; i <= min; i++) /* LOOP_COUNT: COST */
{
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
switch(*eptr++)
{
default: break;
HSPACE_BYTE_CASES:
#if defined COMPILE_PCRE16 || defined COMPILE_PCRE32
HSPACE_MULTIBYTE_CASES:
#endif
RRETURN(MATCH_NOMATCH);
}
}
break;
case OP_HSPACE:
COST(min);
for (i = 1; i <= min; i++) /* LOOP_COUNT: COST */
{
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
switch(*eptr++)
{
default: RRETURN(MATCH_NOMATCH);
HSPACE_BYTE_CASES:
#if defined COMPILE_PCRE16 || defined COMPILE_PCRE32
HSPACE_MULTIBYTE_CASES:
#endif
break;
}
}
break;
case OP_NOT_VSPACE:
COST(min);
for (i = 1; i <= min; i++) /* LOOP_COUNT: COST */
{
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
switch(*eptr++)
{
VSPACE_BYTE_CASES:
#if defined COMPILE_PCRE16 || defined COMPILE_PCRE32
VSPACE_MULTIBYTE_CASES:
#endif
RRETURN(MATCH_NOMATCH);
default: break;
}
}
break;
case OP_VSPACE:
COST(min);
for (i = 1; i <= min; i++) /* LOOP_COUNT: COST */
{
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
switch(*eptr++)
{
default: RRETURN(MATCH_NOMATCH);
VSPACE_BYTE_CASES:
#if defined COMPILE_PCRE16 || defined COMPILE_PCRE32
VSPACE_MULTIBYTE_CASES:
#endif
break;
}
}
break;
case OP_NOT_DIGIT:
COST(min);
for (i = 1; i <= min; i++) /* LOOP_COUNT: COST */
{
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
if (MAX_255(*eptr) && (md->ctypes[*eptr] & ctype_digit) != 0)
RRETURN(MATCH_NOMATCH);
eptr++;
}
break;
case OP_DIGIT:
COST(min);
for (i = 1; i <= min; i++) /* LOOP_COUNT: COST */
{
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
if (!MAX_255(*eptr) || (md->ctypes[*eptr] & ctype_digit) == 0)
RRETURN(MATCH_NOMATCH);
eptr++;
}
break;
case OP_NOT_WHITESPACE:
COST(min);
for (i = 1; i <= min; i++) /* LOOP_COUNT: COST */
{
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
if (MAX_255(*eptr) && (md->ctypes[*eptr] & ctype_space) != 0)
RRETURN(MATCH_NOMATCH);
eptr++;
}
break;
case OP_WHITESPACE:
COST(min);
for (i = 1; i <= min; i++) /* LOOP_COUNT: COST */
{
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
if (!MAX_255(*eptr) || (md->ctypes[*eptr] & ctype_space) == 0)
RRETURN(MATCH_NOMATCH);
eptr++;
}
break;
case OP_NOT_WORDCHAR:
COST(min);
for (i = 1; i <= min; i++) /* LOOP_COUNT: COST */
{
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
if (MAX_255(*eptr) && (md->ctypes[*eptr] & ctype_word) != 0)
RRETURN(MATCH_NOMATCH);
eptr++;
}
break;
case OP_WORDCHAR:
COST(min);
for (i = 1; i <= min; i++) /* LOOP_COUNT: COST */
{
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
if (!MAX_255(*eptr) || (md->ctypes[*eptr] & ctype_word) == 0)
RRETURN(MATCH_NOMATCH);
eptr++;
}
break;
default:
RRETURN(PCRE_ERROR_INTERNAL);
}
}
/* If min = max, continue at the same level without recursing */
if (min == max) continue;
/* If minimizing, we have to test the rest of the pattern before each
subsequent match. Again, separate the UTF-8 case for speed, and also
separate the UCP cases. */
if (minimize)
{
#ifdef SUPPORT_UCP
if (prop_type >= 0)
{
switch(prop_type)
{
case PT_ANY:
for (fi = min;; fi++) /* LOOP_COUNT: Ok */
{
RMATCH(eptr, ecode, offset_top, md, eptrb, RM36);
if (rrc != MATCH_NOMATCH) RRETURN(rrc);
if (fi >= max) RRETURN(MATCH_NOMATCH);
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
GETCHARINCTEST(c, eptr);
if (prop_fail_result) RRETURN(MATCH_NOMATCH);
}
/* Control never gets here */
case PT_LAMP:
for (fi = min;; fi++) /* LOOP_COUNT: Ok */
{
int chartype;
RMATCH(eptr, ecode, offset_top, md, eptrb, RM37);
if (rrc != MATCH_NOMATCH) RRETURN(rrc);
if (fi >= max) RRETURN(MATCH_NOMATCH);
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
GETCHARINCTEST(c, eptr);
chartype = UCD_CHARTYPE(c);
if ((chartype == ucp_Lu ||
chartype == ucp_Ll ||
chartype == ucp_Lt) == prop_fail_result)
RRETURN(MATCH_NOMATCH);
}
/* Control never gets here */
case PT_GC:
for (fi = min;; fi++) /* LOOP_COUNT: Ok */
{
RMATCH(eptr, ecode, offset_top, md, eptrb, RM38);
if (rrc != MATCH_NOMATCH) RRETURN(rrc);
if (fi >= max) RRETURN(MATCH_NOMATCH);
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
GETCHARINCTEST(c, eptr);
if ((UCD_CATEGORY(c) == prop_value) == prop_fail_result)
RRETURN(MATCH_NOMATCH);
}
/* Control never gets here */
case PT_PC:
for (fi = min;; fi++) /* LOOP_COUNT: Ok */
{
RMATCH(eptr, ecode, offset_top, md, eptrb, RM39);
if (rrc != MATCH_NOMATCH) RRETURN(rrc);
if (fi >= max) RRETURN(MATCH_NOMATCH);
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
GETCHARINCTEST(c, eptr);
if ((UCD_CHARTYPE(c) == prop_value) == prop_fail_result)
RRETURN(MATCH_NOMATCH);
}
/* Control never gets here */
case PT_SC:
for (fi = min;; fi++) /* LOOP_COUNT: Ok */
{
RMATCH(eptr, ecode, offset_top, md, eptrb, RM40);
if (rrc != MATCH_NOMATCH) RRETURN(rrc);
if (fi >= max) RRETURN(MATCH_NOMATCH);
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
GETCHARINCTEST(c, eptr);
if ((UCD_SCRIPT(c) == prop_value) == prop_fail_result)
RRETURN(MATCH_NOMATCH);
}
/* Control never gets here */
case PT_ALNUM:
for (fi = min;; fi++) /* LOOP_COUNT: Ok */
{
int category;
RMATCH(eptr, ecode, offset_top, md, eptrb, RM59);
if (rrc != MATCH_NOMATCH) RRETURN(rrc);
if (fi >= max) RRETURN(MATCH_NOMATCH);
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
GETCHARINCTEST(c, eptr);
category = UCD_CATEGORY(c);
if ((category == ucp_L || category == ucp_N) == prop_fail_result)
RRETURN(MATCH_NOMATCH);
}
/* Control never gets here */
case PT_SPACE: /* Perl space */
for (fi = min;; fi++) /* LOOP_COUNT: Ok */
{
RMATCH(eptr, ecode, offset_top, md, eptrb, RM60);
if (rrc != MATCH_NOMATCH) RRETURN(rrc);
if (fi >= max) RRETURN(MATCH_NOMATCH);
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
GETCHARINCTEST(c, eptr);
if ((UCD_CATEGORY(c) == ucp_Z || c == CHAR_HT || c == CHAR_NL ||
c == CHAR_FF || c == CHAR_CR)
== prop_fail_result)
RRETURN(MATCH_NOMATCH);
}
/* Control never gets here */
case PT_PXSPACE: /* POSIX space */
for (fi = min;; fi++) /* LOOP_COUNT: Ok */
{
RMATCH(eptr, ecode, offset_top, md, eptrb, RM61);
if (rrc != MATCH_NOMATCH) RRETURN(rrc);
if (fi >= max) RRETURN(MATCH_NOMATCH);
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
GETCHARINCTEST(c, eptr);
if ((UCD_CATEGORY(c) == ucp_Z || c == CHAR_HT || c == CHAR_NL ||
c == CHAR_VT || c == CHAR_FF || c == CHAR_CR)
== prop_fail_result)
RRETURN(MATCH_NOMATCH);
}
/* Control never gets here */
case PT_WORD:
for (fi = min;; fi++) /* LOOP_COUNT: Ok */
{
int category;
RMATCH(eptr, ecode, offset_top, md, eptrb, RM62);
if (rrc != MATCH_NOMATCH) RRETURN(rrc);
if (fi >= max) RRETURN(MATCH_NOMATCH);
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
GETCHARINCTEST(c, eptr);
category = UCD_CATEGORY(c);
if ((category == ucp_L ||
category == ucp_N ||
c == CHAR_UNDERSCORE)
== prop_fail_result)
RRETURN(MATCH_NOMATCH);
}
/* Control never gets here */
case PT_CLIST:
for (fi = min;; fi++) /* LOOP_COUNT: Ok */
{
const pcre_uint32 *cp;
RMATCH(eptr, ecode, offset_top, md, eptrb, RM67);
if (rrc != MATCH_NOMATCH) RRETURN(rrc);
if (fi >= max) RRETURN(MATCH_NOMATCH);
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
GETCHARINCTEST(c, eptr);
cp = PRIV(ucd_caseless_sets) + prop_value;
for (;;) /* LOOP_COUNT: COST */
{
if (c < *cp)
{ if (prop_fail_result) break; else { RRETURN(MATCH_NOMATCH); } }
if (c == *cp++)
{ if (prop_fail_result) { RRETURN(MATCH_NOMATCH); } else break; }
COST(1);
}
}
/* Control never gets here */
case PT_UCNC:
for (fi = min;; fi++) /* LOOP_COUNT: Ok */
{
RMATCH(eptr, ecode, offset_top, md, eptrb, RM68);
if (rrc != MATCH_NOMATCH) RRETURN(rrc);
if (fi >= max) RRETURN(MATCH_NOMATCH);
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
GETCHARINCTEST(c, eptr);
if ((c == CHAR_DOLLAR_SIGN || c == CHAR_COMMERCIAL_AT ||
c == CHAR_GRAVE_ACCENT || (c >= 0xa0 && c <= 0xd7ff) ||
c >= 0xe000) == prop_fail_result)
RRETURN(MATCH_NOMATCH);
}
/* Control never gets here */
/* This should never occur */
default:
RRETURN(PCRE_ERROR_INTERNAL);
}
}
/* Match extended Unicode sequences. We will get here only if the
support is in the binary; otherwise a compile-time error occurs. */
else if (ctype == OP_EXTUNI)
{
for (fi = min;; fi++) /* LOOP_COUNT: Ok */
{
RMATCH(eptr, ecode, offset_top, md, eptrb, RM41);
if (rrc != MATCH_NOMATCH) RRETURN(rrc);
if (fi >= max) RRETURN(MATCH_NOMATCH);
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
else
{
#ifndef ERLANG_INTEGRATION
int lgb, rgb;
#endif
GETCHARINCTEST(c, eptr);
lgb = UCD_GRAPHBREAK(c);
while (eptr < md->end_subject) /* LOOP_COUNT: CHK */
{
int len = 1;
if (!utf) c = *eptr; else { GETCHARLEN(c, eptr, len); }
rgb = UCD_GRAPHBREAK(c);
if ((PRIV(ucp_gbtable)[lgb] & (1 << rgb)) == 0) break;
lgb = rgb;
eptr += len;
COST_CHK(1);
}
}
CHECK_PARTIAL();
}
}
else
#endif /* SUPPORT_UCP */
#ifdef SUPPORT_UTF
if (utf)
{
for (fi = min;; fi++) /* LOOP_COUNT: Ok */
{
RMATCH(eptr, ecode, offset_top, md, eptrb, RM42);
if (rrc != MATCH_NOMATCH) RRETURN(rrc);
if (fi >= max) RRETURN(MATCH_NOMATCH);
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
if (ctype == OP_ANY && IS_NEWLINE(eptr))
RRETURN(MATCH_NOMATCH);
GETCHARINC(c, eptr);
switch(ctype)
{
case OP_ANY: /* This is the non-NL case */
if (md->partial != 0 && /* Take care with CRLF partial */
eptr >= md->end_subject &&
NLBLOCK->nltype == NLTYPE_FIXED &&
NLBLOCK->nllen == 2 &&
c == NLBLOCK->nl[0])
{
md->hitend = TRUE;
if (md->partial > 1) RRETURN(PCRE_ERROR_PARTIAL);
}
break;
case OP_ALLANY:
case OP_ANYBYTE:
break;
case OP_ANYNL:
switch(c)
{
default: RRETURN(MATCH_NOMATCH);
case CHAR_CR:
if (eptr < md->end_subject && RAWUCHAR(eptr) == CHAR_LF) eptr++;
break;
case CHAR_LF:
break;
case CHAR_VT:
case CHAR_FF:
case CHAR_NEL:
#ifndef EBCDIC
case 0x2028:
case 0x2029:
#endif /* Not EBCDIC */
if (md->bsr_anycrlf) RRETURN(MATCH_NOMATCH);
break;
}
break;
case OP_NOT_HSPACE:
switch(c)
{
HSPACE_CASES: RRETURN(MATCH_NOMATCH);
default: break;
}
break;
case OP_HSPACE:
switch(c)
{
HSPACE_CASES: break;
default: RRETURN(MATCH_NOMATCH);
}
break;
case OP_NOT_VSPACE:
switch(c)
{
VSPACE_CASES: RRETURN(MATCH_NOMATCH);
default: break;
}
break;
case OP_VSPACE:
switch(c)
{
VSPACE_CASES: break;
default: RRETURN(MATCH_NOMATCH);
}
break;
case OP_NOT_DIGIT:
if (c < 256 && (md->ctypes[c] & ctype_digit) != 0)
RRETURN(MATCH_NOMATCH);
break;
case OP_DIGIT:
if (c >= 256 || (md->ctypes[c] & ctype_digit) == 0)
RRETURN(MATCH_NOMATCH);
break;
case OP_NOT_WHITESPACE:
if (c < 256 && (md->ctypes[c] & ctype_space) != 0)
RRETURN(MATCH_NOMATCH);
break;
case OP_WHITESPACE:
if (c >= 256 || (md->ctypes[c] & ctype_space) == 0)
RRETURN(MATCH_NOMATCH);
break;
case OP_NOT_WORDCHAR:
if (c < 256 && (md->ctypes[c] & ctype_word) != 0)
RRETURN(MATCH_NOMATCH);
break;
case OP_WORDCHAR:
if (c >= 256 || (md->ctypes[c] & ctype_word) == 0)
RRETURN(MATCH_NOMATCH);
break;
default:
RRETURN(PCRE_ERROR_INTERNAL);
}
}
}
else
#endif
/* Not UTF mode */
{
for (fi = min;; fi++) /* LOOP_COUNT: Ok */
{
RMATCH(eptr, ecode, offset_top, md, eptrb, RM43);
if (rrc != MATCH_NOMATCH) RRETURN(rrc);
if (fi >= max) RRETURN(MATCH_NOMATCH);
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
RRETURN(MATCH_NOMATCH);
}
if (ctype == OP_ANY && IS_NEWLINE(eptr))
RRETURN(MATCH_NOMATCH);
c = *eptr++;
switch(ctype)
{
case OP_ANY: /* This is the non-NL case */
if (md->partial != 0 && /* Take care with CRLF partial */
eptr >= md->end_subject &&
NLBLOCK->nltype == NLTYPE_FIXED &&
NLBLOCK->nllen == 2 &&
c == NLBLOCK->nl[0])
{
md->hitend = TRUE;
if (md->partial > 1) RRETURN(PCRE_ERROR_PARTIAL);
}
break;
case OP_ALLANY:
case OP_ANYBYTE:
break;
case OP_ANYNL:
switch(c)
{
default: RRETURN(MATCH_NOMATCH);
case CHAR_CR:
if (eptr < md->end_subject && *eptr == CHAR_LF) eptr++;
break;
case CHAR_LF:
break;
case CHAR_VT:
case CHAR_FF:
case CHAR_NEL:
#if defined COMPILE_PCRE16 || defined COMPILE_PCRE32
case 0x2028:
case 0x2029:
#endif
if (md->bsr_anycrlf) RRETURN(MATCH_NOMATCH);
break;
}
break;
case OP_NOT_HSPACE:
switch(c)
{
default: break;
HSPACE_BYTE_CASES:
#if defined COMPILE_PCRE16 || defined COMPILE_PCRE32
HSPACE_MULTIBYTE_CASES:
#endif
RRETURN(MATCH_NOMATCH);
}
break;
case OP_HSPACE:
switch(c)
{
default: RRETURN(MATCH_NOMATCH);
HSPACE_BYTE_CASES:
#if defined COMPILE_PCRE16 || defined COMPILE_PCRE32
HSPACE_MULTIBYTE_CASES:
#endif
break;
}
break;
case OP_NOT_VSPACE:
switch(c)
{
default: break;
VSPACE_BYTE_CASES:
#if defined COMPILE_PCRE16 || defined COMPILE_PCRE32
VSPACE_MULTIBYTE_CASES:
#endif
RRETURN(MATCH_NOMATCH);
}
break;
case OP_VSPACE:
switch(c)
{
default: RRETURN(MATCH_NOMATCH);
VSPACE_BYTE_CASES:
#if defined COMPILE_PCRE16 || defined COMPILE_PCRE32
VSPACE_MULTIBYTE_CASES:
#endif
break;
}
break;
case OP_NOT_DIGIT:
if (MAX_255(c) && (md->ctypes[c] & ctype_digit) != 0) RRETURN(MATCH_NOMATCH);
break;
case OP_DIGIT:
if (!MAX_255(c) || (md->ctypes[c] & ctype_digit) == 0) RRETURN(MATCH_NOMATCH);
break;
case OP_NOT_WHITESPACE:
if (MAX_255(c) && (md->ctypes[c] & ctype_space) != 0) RRETURN(MATCH_NOMATCH);
break;
case OP_WHITESPACE:
if (!MAX_255(c) || (md->ctypes[c] & ctype_space) == 0) RRETURN(MATCH_NOMATCH);
break;
case OP_NOT_WORDCHAR:
if (MAX_255(c) && (md->ctypes[c] & ctype_word) != 0) RRETURN(MATCH_NOMATCH);
break;
case OP_WORDCHAR:
if (!MAX_255(c) || (md->ctypes[c] & ctype_word) == 0) RRETURN(MATCH_NOMATCH);
break;
default:
RRETURN(PCRE_ERROR_INTERNAL);
}
}
}
/* Control never gets here */
}
/* If maximizing, it is worth using inline code for speed, doing the type
test once at the start (i.e. keep it out of the loop). Again, keep the
UTF-8 and UCP stuff separate. */
else
{
pp = eptr; /* Remember where we started */
#ifdef SUPPORT_UCP
if (prop_type >= 0)
{
switch(prop_type)
{
case PT_ANY:
for (i = min; i < max; i++) /* LOOP_COUNT: CHK */
{
int len = 1;
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
break;
}
GETCHARLENTEST(c, eptr, len);
if (prop_fail_result) break;
eptr+= len;
COST_CHK(1);
}
break;
case PT_LAMP:
for (i = min; i < max; i++) /* LOOP_COUNT: CHK */
{
int chartype;
int len = 1;
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
break;
}
GETCHARLENTEST(c, eptr, len);
chartype = UCD_CHARTYPE(c);
if ((chartype == ucp_Lu ||
chartype == ucp_Ll ||
chartype == ucp_Lt) == prop_fail_result)
break;
eptr+= len;
COST_CHK(1);
}
break;
case PT_GC:
for (i = min; i < max; i++) /* LOOP_COUNT: CHK */
{
int len = 1;
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
break;
}
GETCHARLENTEST(c, eptr, len);
if ((UCD_CATEGORY(c) == prop_value) == prop_fail_result) break;
eptr+= len;
COST_CHK(1);
}
break;
case PT_PC:
for (i = min; i < max; i++) /* LOOP_COUNT: CHK */
{
int len = 1;
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
break;
}
GETCHARLENTEST(c, eptr, len);
if ((UCD_CHARTYPE(c) == prop_value) == prop_fail_result) break;
eptr+= len;
COST_CHK(1);
}
break;
case PT_SC:
for (i = min; i < max; i++) /* LOOP_COUNT: CHK */
{
int len = 1;
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
break;
}
GETCHARLENTEST(c, eptr, len);
if ((UCD_SCRIPT(c) == prop_value) == prop_fail_result) break;
eptr+= len;
COST_CHK(1);
}
break;
case PT_ALNUM:
for (i = min; i < max; i++) /* LOOP_COUNT: CHK */
{
int category;
int len = 1;
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
break;
}
GETCHARLENTEST(c, eptr, len);
category = UCD_CATEGORY(c);
if ((category == ucp_L || category == ucp_N) == prop_fail_result)
break;
eptr+= len;
COST_CHK(1);
}
break;
case PT_SPACE: /* Perl space */
for (i = min; i < max; i++) /* LOOP_COUNT: CHK */
{
int len = 1;
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
break;
}
GETCHARLENTEST(c, eptr, len);
if ((UCD_CATEGORY(c) == ucp_Z || c == CHAR_HT || c == CHAR_NL ||
c == CHAR_FF || c == CHAR_CR)
== prop_fail_result)
break;
eptr+= len;
COST_CHK(1);
}
break;
case PT_PXSPACE: /* POSIX space */
for (i = min; i < max; i++) /* LOOP_COUNT: CHK */
{
int len = 1;
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
break;
}
GETCHARLENTEST(c, eptr, len);
if ((UCD_CATEGORY(c) == ucp_Z || c == CHAR_HT || c == CHAR_NL ||
c == CHAR_VT || c == CHAR_FF || c == CHAR_CR)
== prop_fail_result)
break;
eptr+= len;
COST_CHK(1);
}
break;
case PT_WORD:
for (i = min; i < max; i++) /* LOOP_COUNT: CHK */
{
int category;
int len = 1;
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
break;
}
GETCHARLENTEST(c, eptr, len);
category = UCD_CATEGORY(c);
if ((category == ucp_L || category == ucp_N ||
c == CHAR_UNDERSCORE) == prop_fail_result)
break;
eptr+= len;
COST_CHK(1);
}
break;
case PT_CLIST:
for (i = min; i < max; i++) /* LOOP_COUNT: CHK */
{
const pcre_uint32 *cp;
int len = 1;
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
break;
}
GETCHARLENTEST(c, eptr, len);
cp = PRIV(ucd_caseless_sets) + prop_value;
for (;;) /* LOOP_COUNT: COST */
{
if (c < *cp)
{ if (prop_fail_result) break; else goto GOT_MAX; }
if (c == *cp++)
{ if (prop_fail_result) goto GOT_MAX; else break; }
COST(1);
}
eptr += len;
COST_CHK(1);
}
GOT_MAX:
break;
case PT_UCNC:
for (i = min; i < max; i++) /* LOOP_COUNT: CHK */
{
int len = 1;
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
break;
}
GETCHARLENTEST(c, eptr, len);
if ((c == CHAR_DOLLAR_SIGN || c == CHAR_COMMERCIAL_AT ||
c == CHAR_GRAVE_ACCENT || (c >= 0xa0 && c <= 0xd7ff) ||
c >= 0xe000) == prop_fail_result)
break;
eptr += len;
COST_CHK(1);
}
break;
default:
RRETURN(PCRE_ERROR_INTERNAL);
}
/* eptr is now past the end of the maximum run */
if (possessive) continue; /* No backtracking */
for(;;) /* LOOP_COUNT: Ok */
{
if (eptr == pp) goto TAIL_RECURSE;
RMATCH(eptr, ecode, offset_top, md, eptrb, RM44);
if (rrc != MATCH_NOMATCH) RRETURN(rrc);
eptr--;
if (utf) BACKCHAR(eptr);
}
}
/* Match extended Unicode grapheme clusters. We will get here only if the
support is in the binary; otherwise a compile-time error occurs. */
else if (ctype == OP_EXTUNI)
{
for (i = min; i < max; i++) /* LOOP_COUNT: CHK */
{
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
break;
}
else
{
#ifndef ERLANG_INTEGRATION
int lgb, rgb;
#endif
GETCHARINCTEST(c, eptr);
lgb = UCD_GRAPHBREAK(c);
while (eptr < md->end_subject) /* LOOP_COUNT: CHK */
{
int len = 1;
if (!utf) c = *eptr; else { GETCHARLEN(c, eptr, len); }
rgb = UCD_GRAPHBREAK(c);
if ((PRIV(ucp_gbtable)[lgb] & (1 << rgb)) == 0) break;
lgb = rgb;
eptr += len;
COST_CHK(1);
}
COST_CHK(1);
}
CHECK_PARTIAL();
}
/* eptr is now past the end of the maximum run */
if (possessive) continue; /* No backtracking */
for(;;) /* LOOP_COUNT: Ok */
{
#ifndef ERLANG_INTEGRATION
int lgb, rgb;
#endif
PCRE_PUCHAR fptr;
if (eptr == pp) goto TAIL_RECURSE; /* At start of char run */
RMATCH(eptr, ecode, offset_top, md, eptrb, RM45);
if (rrc != MATCH_NOMATCH) RRETURN(rrc);
/* Backtracking over an extended grapheme cluster involves inspecting
the previous two characters (if present) to see if a break is
permitted between them. */
eptr--;
if (!utf) c = *eptr; else
{
BACKCHAR(eptr);
GETCHAR(c, eptr);
}
rgb = UCD_GRAPHBREAK(c);
for (;;) /* LOOP_COUNT: COST */
{
if (eptr == pp) goto TAIL_RECURSE; /* At start of char run */
fptr = eptr - 1;
if (!utf) c = *fptr; else
{
BACKCHAR(fptr);
GETCHAR(c, fptr);
}
lgb = UCD_GRAPHBREAK(c);
if ((PRIV(ucp_gbtable)[lgb] & (1 << rgb)) == 0) break;
eptr = fptr;
rgb = lgb;
COST(1);
}
}
}
else
#endif /* SUPPORT_UCP */
#ifdef SUPPORT_UTF
if (utf)
{
switch(ctype)
{
case OP_ANY:
if (max < INT_MAX)
{
for (i = min; i < max; i++) /* LOOP_COUNT: CHK */
{
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
break;
}
if (IS_NEWLINE(eptr)) break;
if (md->partial != 0 && /* Take care with CRLF partial */
eptr + 1 >= md->end_subject &&
NLBLOCK->nltype == NLTYPE_FIXED &&
NLBLOCK->nllen == 2 &&
RAWUCHAR(eptr) == NLBLOCK->nl[0])
{
md->hitend = TRUE;
if (md->partial > 1) RRETURN(PCRE_ERROR_PARTIAL);
}
eptr++;
ACROSSCHAR(eptr < md->end_subject, *eptr, eptr++);
COST_CHK(1);
}
}
/* Handle unlimited UTF-8 repeat */
else
{
for (i = min; i < max; i++) /* LOOP_COUNT: CHK */
{
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
break;
}
if (IS_NEWLINE(eptr)) break;
if (md->partial != 0 && /* Take care with CRLF partial */
eptr + 1 >= md->end_subject &&
NLBLOCK->nltype == NLTYPE_FIXED &&
NLBLOCK->nllen == 2 &&
RAWUCHAR(eptr) == NLBLOCK->nl[0])
{
md->hitend = TRUE;
if (md->partial > 1) RRETURN(PCRE_ERROR_PARTIAL);
}
eptr++;
ACROSSCHAR(eptr < md->end_subject, *eptr, eptr++);
COST_CHK(1);
}
}
break;
case OP_ALLANY:
if (max < INT_MAX)
{
for (i = min; i < max; i++) /* LOOP_COUNT: CHK */
{
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
break;
}
eptr++;
ACROSSCHAR(eptr < md->end_subject, *eptr, eptr++);
COST_CHK(1);
}
}
else
{
eptr = md->end_subject; /* Unlimited UTF-8 repeat */
SCHECK_PARTIAL();
}
break;
/* The byte case is the same as non-UTF8 */
case OP_ANYBYTE:
c = max - min;
if (c > (unsigned int)(md->end_subject - eptr))
{
eptr = md->end_subject;
SCHECK_PARTIAL();
}
else eptr += c;
break;
case OP_ANYNL:
for (i = min; i < max; i++) /* LOOP_COUNT: CHK */
{
int len = 1;
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
break;
}
GETCHARLEN(c, eptr, len);
if (c == CHAR_CR)
{
if (++eptr >= md->end_subject) break;
if (RAWUCHAR(eptr) == CHAR_LF) eptr++;
}
else
{
if (c != CHAR_LF &&
(md->bsr_anycrlf ||
(c != CHAR_VT && c != CHAR_FF && c != CHAR_NEL
#ifndef EBCDIC
&& c != 0x2028 && c != 0x2029
#endif /* Not EBCDIC */
)))
break;
eptr += len;
}
COST_CHK(1);
}
break;
case OP_NOT_HSPACE:
case OP_HSPACE:
for (i = min; i < max; i++) /* LOOP_COUNT: CHK */
{
BOOL gotspace;
int len = 1;
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
break;
}
GETCHARLEN(c, eptr, len);
switch(c)
{
HSPACE_CASES: gotspace = TRUE; break;
default: gotspace = FALSE; break;
}
if (gotspace == (ctype == OP_NOT_HSPACE)) break;
eptr += len;
COST_CHK(1);
}
break;
case OP_NOT_VSPACE:
case OP_VSPACE:
for (i = min; i < max; i++) /* LOOP_COUNT: CHK */
{
BOOL gotspace;
int len = 1;
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
break;
}
GETCHARLEN(c, eptr, len);
switch(c)
{
VSPACE_CASES: gotspace = TRUE; break;
default: gotspace = FALSE; break;
}
if (gotspace == (ctype == OP_NOT_VSPACE)) break;
eptr += len;
COST_CHK(1);
}
break;
case OP_NOT_DIGIT:
for (i = min; i < max; i++) /* LOOP_COUNT: CHK */
{
int len = 1;
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
break;
}
GETCHARLEN(c, eptr, len);
if (c < 256 && (md->ctypes[c] & ctype_digit) != 0) break;
eptr+= len;
COST_CHK(1);
}
break;
case OP_DIGIT:
for (i = min; i < max; i++) /* LOOP_COUNT: CHK */
{
int len = 1;
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
break;
}
GETCHARLEN(c, eptr, len);
if (c >= 256 ||(md->ctypes[c] & ctype_digit) == 0) break;
eptr+= len;
COST_CHK(1);
}
break;
case OP_NOT_WHITESPACE:
for (i = min; i < max; i++) /* LOOP_COUNT: CHK */
{
int len = 1;
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
break;
}
GETCHARLEN(c, eptr, len);
if (c < 256 && (md->ctypes[c] & ctype_space) != 0) break;
eptr+= len;
COST_CHK(1);
}
break;
case OP_WHITESPACE:
for (i = min; i < max; i++) /* LOOP_COUNT: CHK */
{
int len = 1;
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
break;
}
GETCHARLEN(c, eptr, len);
if (c >= 256 ||(md->ctypes[c] & ctype_space) == 0) break;
eptr+= len;
COST_CHK(1);
}
break;
case OP_NOT_WORDCHAR:
for (i = min; i < max; i++) /* LOOP_COUNT: CHK */
{
int len = 1;
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
break;
}
GETCHARLEN(c, eptr, len);
if (c < 256 && (md->ctypes[c] & ctype_word) != 0) break;
eptr+= len;
COST_CHK(1);
}
break;
case OP_WORDCHAR:
for (i = min; i < max; i++) /* LOOP_COUNT: CHK */
{
int len = 1;
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
break;
}
GETCHARLEN(c, eptr, len);
if (c >= 256 || (md->ctypes[c] & ctype_word) == 0) break;
eptr+= len;
COST_CHK(1);
}
break;
default:
RRETURN(PCRE_ERROR_INTERNAL);
}
if (possessive) continue; /* No backtracking */
for(;;) /* LOOP_COUNT: Ok */
{
if (eptr == pp) goto TAIL_RECURSE;
RMATCH(eptr, ecode, offset_top, md, eptrb, RM46);
if (rrc != MATCH_NOMATCH) RRETURN(rrc);
eptr--;
BACKCHAR(eptr);
if (ctype == OP_ANYNL && eptr > pp && RAWUCHAR(eptr) == CHAR_NL &&
RAWUCHAR(eptr - 1) == CHAR_CR) eptr--;
}
}
else
#endif /* SUPPORT_UTF */
/* Not UTF mode */
{
switch(ctype)
{
case OP_ANY:
for (i = min; i < max; i++) /* LOOP_COUNT: CHK */
{
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
break;
}
if (IS_NEWLINE(eptr)) break;
if (md->partial != 0 && /* Take care with CRLF partial */
eptr + 1 >= md->end_subject &&
NLBLOCK->nltype == NLTYPE_FIXED &&
NLBLOCK->nllen == 2 &&
*eptr == NLBLOCK->nl[0])
{
md->hitend = TRUE;
if (md->partial > 1) RRETURN(PCRE_ERROR_PARTIAL);
}
eptr++;
COST_CHK(1);
}
break;
case OP_ALLANY:
case OP_ANYBYTE:
c = max - min;
if (c > (unsigned int)(md->end_subject - eptr))
{
eptr = md->end_subject;
SCHECK_PARTIAL();
}
else eptr += c;
break;
case OP_ANYNL:
for (i = min; i < max; i++) /* LOOP_COUNT: CHK */
{
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
break;
}
c = *eptr;
if (c == CHAR_CR)
{
if (++eptr >= md->end_subject) break;
if (*eptr == CHAR_LF) eptr++;
}
else
{
if (c != CHAR_LF && (md->bsr_anycrlf ||
(c != CHAR_VT && c != CHAR_FF && c != CHAR_NEL
#if defined COMPILE_PCRE16 || defined COMPILE_PCRE32
&& c != 0x2028 && c != 0x2029
#endif
))) break;
eptr++;
}
COST_CHK(1);
}
break;
case OP_NOT_HSPACE:
for (i = min; i < max; i++) /* LOOP_COUNT: CHK */
{
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
break;
}
switch(*eptr)
{
default: eptr++; break;
HSPACE_BYTE_CASES:
#if defined COMPILE_PCRE16 || defined COMPILE_PCRE32
HSPACE_MULTIBYTE_CASES:
#endif
goto ENDLOOP00;
}
COST_CHK(1);
}
ENDLOOP00:
break;
case OP_HSPACE:
for (i = min; i < max; i++) /* LOOP_COUNT: CHK */
{
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
break;
}
switch(*eptr)
{
default: goto ENDLOOP01;
HSPACE_BYTE_CASES:
#if defined COMPILE_PCRE16 || defined COMPILE_PCRE32
HSPACE_MULTIBYTE_CASES:
#endif
eptr++; break;
}
COST_CHK(1);
}
ENDLOOP01:
break;
case OP_NOT_VSPACE:
for (i = min; i < max; i++) /* LOOP_COUNT: CHK */
{
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
break;
}
switch(*eptr)
{
default: eptr++; break;
VSPACE_BYTE_CASES:
#if defined COMPILE_PCRE16 || defined COMPILE_PCRE32
VSPACE_MULTIBYTE_CASES:
#endif
goto ENDLOOP02;
}
COST_CHK(1);
}
ENDLOOP02:
break;
case OP_VSPACE:
for (i = min; i < max; i++) /* LOOP_COUNT: CHK */
{
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
break;
}
switch(*eptr)
{
default: goto ENDLOOP03;
VSPACE_BYTE_CASES:
#if defined COMPILE_PCRE16 || defined COMPILE_PCRE32
VSPACE_MULTIBYTE_CASES:
#endif
eptr++; break;
}
COST_CHK(1);
}
ENDLOOP03:
break;
case OP_NOT_DIGIT:
for (i = min; i < max; i++) /* LOOP_COUNT: CHK */
{
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
break;
}
if (MAX_255(*eptr) && (md->ctypes[*eptr] & ctype_digit) != 0) break;
eptr++;
COST_CHK(1);
}
break;
case OP_DIGIT:
for (i = min; i < max; i++) /* LOOP_COUNT: CHK */
{
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
break;
}
if (!MAX_255(*eptr) || (md->ctypes[*eptr] & ctype_digit) == 0) break;
eptr++;
COST_CHK(1);
}
break;
case OP_NOT_WHITESPACE:
for (i = min; i < max; i++) /* LOOP_COUNT: CHK */
{
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
break;
}
if (MAX_255(*eptr) && (md->ctypes[*eptr] & ctype_space) != 0) break;
eptr++;
COST_CHK(1);
}
break;
case OP_WHITESPACE:
for (i = min; i < max; i++) /* LOOP_COUNT: CHK */
{
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
break;
}
if (!MAX_255(*eptr) || (md->ctypes[*eptr] & ctype_space) == 0) break;
eptr++;
COST_CHK(1);
}
break;
case OP_NOT_WORDCHAR:
for (i = min; i < max; i++) /* LOOP_COUNT: CHK */
{
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
break;
}
if (MAX_255(*eptr) && (md->ctypes[*eptr] & ctype_word) != 0) break;
eptr++;
COST_CHK(1);
}
break;
case OP_WORDCHAR:
for (i = min; i < max; i++) /* LOOP_COUNT: CHK */
{
if (eptr >= md->end_subject)
{
SCHECK_PARTIAL();
break;
}
if (!MAX_255(*eptr) || (md->ctypes[*eptr] & ctype_word) == 0) break;
eptr++;
COST_CHK(1);
}
break;
default:
RRETURN(PCRE_ERROR_INTERNAL);
}
if (possessive) continue; /* No backtracking */
for (;;) /* LOOP_COUNT: Ok */
{
if (eptr == pp) goto TAIL_RECURSE;
RMATCH(eptr, ecode, offset_top, md, eptrb, RM47);
if (rrc != MATCH_NOMATCH) RRETURN(rrc);
eptr--;
if (ctype == OP_ANYNL && eptr > pp && *eptr == CHAR_LF &&
eptr[-1] == CHAR_CR) eptr--;
}
}
/* Get here if we can't make it match with any permitted repetitions */
RRETURN(MATCH_NOMATCH);
}
/* Control never gets here */
/* There's been some horrible disaster. Arrival here can only mean there is
something seriously wrong in the code above or the OP_xxx definitions. */
default:
DPRINTF(("Unknown opcode %d\n", *ecode));
RRETURN(PCRE_ERROR_UNKNOWN_OPCODE);
}
/* Do not stick any code in here without much thought; it is assumed
that "continue" in the code above comes out to here to repeat the main
loop. */
} /* End of main loop */
/* Control never reaches here */
/* When compiling to use the heap rather than the stack for recursive calls to
match(), the RRETURN() macro jumps here. The number that is saved in
frame->Xwhere indicates which label we actually want to return to. */
#ifdef NO_RECURSE
#define LBL(val) case val: goto L_RM##val;
HEAP_RETURN:
switch (frame->Xwhere)
{
LBL( 1) LBL( 2) LBL( 3) LBL( 4) LBL( 5) LBL( 6) LBL( 7) LBL( 8)
LBL( 9) LBL(10) LBL(11) LBL(12) LBL(13) LBL(14) LBL(15) LBL(17)
LBL(19) LBL(24) LBL(25) LBL(26) LBL(27) LBL(29) LBL(31) LBL(33)
LBL(35) LBL(43) LBL(47) LBL(48) LBL(49) LBL(50) LBL(51) LBL(52)
LBL(53) LBL(54) LBL(55) LBL(56) LBL(57) LBL(58) LBL(63) LBL(64)
LBL(65) LBL(66)
#if defined SUPPORT_UTF || !defined COMPILE_PCRE8
LBL(21)
#endif
#ifdef SUPPORT_UTF
LBL(16) LBL(18) LBL(20)
LBL(22) LBL(23) LBL(28) LBL(30)
LBL(32) LBL(34) LBL(42) LBL(46)
#ifdef SUPPORT_UCP
LBL(36) LBL(37) LBL(38) LBL(39) LBL(40) LBL(41) LBL(44) LBL(45)
LBL(59) LBL(60) LBL(61) LBL(62) LBL(67) LBL(68)
#endif /* SUPPORT_UCP */
#endif /* SUPPORT_UTF */
default:
DPRINTF(("jump error in pcre match: label %d non-existent\n", frame->Xwhere));
return PCRE_ERROR_INTERNAL;
}
#undef LBL
#ifdef ERLANG_INTEGRATION
LOOP_COUNT_RETURN:
/* Restore the saved register variables in the upper dummy frame, description below */
{
heapframe *newframe = frame;
frame = newframe->Xprevframe;
rrc = newframe->Xop;
i = newframe->Xfi;
c = (pcre_uint32) newframe->Xfc;
utf = newframe->Xcur_is_word;
minimize = newframe->Xcondition;
possessive = newframe->Xprev_is_word;
caseless = (BOOL) newframe->Xcodelink;
condcode = newframe->Xctype;
/* Note, the frame is not freed until the whole match is done,
the function release_match_heapframes takes care of that */
EDEBUGF(("LOOP_COUNT_RETURN: %d",frame->Xwhere));
switch (frame->Xwhere)
{
#include "pcre_exec_loop_break_cases.inc"
default:
DPRINTF(("jump error in pcre match: label %d non-existent\n", frame->Xwhere));
return PCRE_ERROR_INTERNAL;
}
}
LOOP_COUNT_BREAK:
/* Save the local register variables in a dummy frame, to keep the
* every frame of equal size rule */
/*
* Store Local in
* ------------------------------ --------------
* rrc Xop
* i Xfi
* c Xfc (cast)
* utf Xcur_is_word
* minimize Xcondition
* possessive Xprev_is_word
* caseless Xcodelink (cast)
* condcode Xctype
*/
{
heapframe *newframe = frame->Xnextframe;
if (newframe == NULL)
{
newframe = (heapframe *)(PUBL(stack_malloc))(sizeof(heapframe));
if (newframe == NULL) RRETURN(PCRE_ERROR_NOMEMORY);
newframe->Xnextframe = NULL;
frame->Xnextframe = newframe;
}
newframe->Xprevframe = frame;
newframe->Xop = rrc;
newframe->Xfi = i;
newframe->Xfc = (unsigned int) c;
newframe->Xcur_is_word = utf;
newframe->Xcondition = minimize;
newframe->Xprev_is_word = possessive;
newframe->Xcodelink = (int) caseless;
newframe->Xctype = condcode;
md->state_save = newframe;
md->loop_limit = 0;
EDEBUGF(("Break loop!"));
return PCRE_ERROR_LOOP_LIMIT;
}
#endif
#endif /* NO_RECURSE */
}
/***************************************************************************
****************************************************************************
RECURSION IN THE match() FUNCTION
Undefine all the macros that were defined above to handle this. */
#ifdef NO_RECURSE
#undef eptr
#undef ecode
#undef mstart
#undef offset_top
#undef eptrb
#undef flags
#undef callpat
#undef charptr
#undef data
#undef next
#undef pp
#undef prev
#undef saved_eptr
#undef new_recursive
#undef cur_is_word
#undef condition
#undef prev_is_word
#undef ctype
#undef length
#undef max
#undef min
#undef number
#undef offset
#undef op
#undef save_capture_last
#undef save_offset1
#undef save_offset2
#undef save_offset3
#undef stacksave
#undef newptrb
#endif
/* These two are defined as macros in both cases */
#undef fc
#undef fi
/***************************************************************************
***************************************************************************/
#ifdef NO_RECURSE
/*************************************************
* Release allocated heap frames *
*************************************************/
/* This function releases all the allocated frames. The base frame is on the
machine stack, and so must not be freed.
Argument: the address of the base frame
Returns: nothing
*/
static void
release_match_heapframes (heapframe *frame_base)
{
heapframe *nextframe = frame_base->Xnextframe;
#ifdef ERLANG_INTEGRATION
frame_base->Xnextframe = NULL; /* Protect against multiple free */
#endif
while (nextframe != NULL)
{
heapframe *oldframe = nextframe;
nextframe = nextframe->Xnextframe;
(PUBL(stack_free))(oldframe);
}
}
#endif
/*************************************************
* Execute a Regular Expression *
*************************************************/
/* This function applies a compiled re to a subject string and picks out
portions of the string if it matches. Two elements in the vector are set for
each substring: the offsets to the start and end of the substring.
Arguments:
argument_re points to the compiled expression
extra_data points to extra data or is NULL
subject points to the subject string
length length of subject string (may contain binary zeros)
start_offset where to start in the subject string
options option bits
offsets points to a vector of ints to be filled in with offsets
offsetcount the number of elements in the vector
Returns: > 0 => success; value is the number of elements filled in
= 0 => success, but offsets is not big enough
-1 => failed to match
< -1 => some kind of unexpected problem
*/
#ifdef ERLANG_INTEGRATION
typedef struct {
int Xarg_offset_max;
BOOL Xusing_temporary_offsets;
BOOL Xanchored;
BOOL Xstartline;
BOOL Xfirstline;
BOOL Xutf;
BOOL Xhas_first_char;
BOOL Xhas_req_char;
pcre_uchar Xfirst_char;
pcre_uchar Xfirst_char2;
pcre_uchar Xreq_char;
pcre_uchar Xreq_char2;
match_data Xmatch_block;
match_data *Xmd;
const pcre_uint8 *Xtables;
const pcre_uint8 *Xstart_bits;
PCRE_PUCHAR Xstart_match;
PCRE_PUCHAR Xend_subject;
PCRE_PUCHAR Xstart_partial;
PCRE_PUCHAR Xmatch_partial;
PCRE_PUCHAR Xreq_char_ptr;
const pcre_study_data *Xstudy;
REAL_PCRE *Xre;
heapframe Xframe_zero; /* Always NO_RECURSE */
/* Original function parameters that need be saved */
int Xstart_offset;
int Xoffsetcount;
int *Xoffsets;
} PcreExecContext;
#endif
#if defined COMPILE_PCRE8
#if defined(ERLANG_INTEGRATION)
PCRE_EXP_DEFN int PCRE_CALL_CONVENTION
erts_pcre_exec(const pcre *argument_re, const erts_pcre_extra *extra_data,
PCRE_SPTR subject, int length, int start_offset, int options, int *offsets,
int offsetcount)
#else
PCRE_EXP_DEFN int PCRE_CALL_CONVENTION
pcre_exec(const pcre *argument_re, const pcre_extra *extra_data,
PCRE_SPTR subject, int length, int start_offset, int options, int *offsets,
int offsetcount)
#endif
#elif defined COMPILE_PCRE16
PCRE_EXP_DEFN int PCRE_CALL_CONVENTION
pcre16_exec(const pcre16 *argument_re, const pcre16_extra *extra_data,
PCRE_SPTR16 subject, int length, int start_offset, int options, int *offsets,
int offsetcount)
#elif defined COMPILE_PCRE32
PCRE_EXP_DEFN int PCRE_CALL_CONVENTION
pcre32_exec(const pcre32 *argument_re, const pcre32_extra *extra_data,
PCRE_SPTR32 subject, int length, int start_offset, int options, int *offsets,
int offsetcount)
#endif
{
#ifndef ERLANG_INTEGRATION
int rc, ocount, arg_offset_max;
int newline;
BOOL using_temporary_offsets = FALSE;
BOOL anchored;
BOOL startline;
BOOL firstline;
BOOL utf;
BOOL has_first_char = FALSE;
BOOL has_req_char = FALSE;
pcre_uchar first_char = 0;
pcre_uchar first_char2 = 0;
pcre_uchar req_char = 0;
pcre_uchar req_char2 = 0;
match_data match_block;
match_data *md = &match_block;
const pcre_uint8 *tables;
const pcre_uint8 *start_bits = NULL;
PCRE_PUCHAR start_match = (PCRE_PUCHAR)subject + start_offset;
PCRE_PUCHAR end_subject;
PCRE_PUCHAR start_partial = NULL;
PCRE_PUCHAR match_partial;
PCRE_PUCHAR req_char_ptr = start_match - 1;
const pcre_study_data *study;
const REAL_PCRE *re = (const REAL_PCRE *)argument_re;
#ifdef NO_RECURSE
heapframe frame_zero;
#endif
#else
/* "local" variables in faked stackframe instead */
#define arg_offset_max (exec_context->Xarg_offset_max)
#define using_temporary_offsets (exec_context->Xusing_temporary_offsets)
#define anchored (exec_context->Xanchored)
#define startline (exec_context->Xstartline)
#define firstline (exec_context->Xfirstline)
#define has_first_char (exec_context->Xhas_first_char)
#define has_req_char (exec_context->Xhas_req_char)
#define first_char2 (exec_context->Xfirst_char2)
#define req_char2 (exec_context->Xreq_char2)
#define match_block (exec_context->Xmatch_block)
#define md (exec_context->Xmd)
#define start_match (exec_context->Xstart_match)
#define start_partial (exec_context->Xstart_partial)
#define match_partial (exec_context->Xmatch_partial)
#define study (exec_context->Xstudy)
#define re (exec_context->Xre)
#define frame_zero (exec_context->Xframe_zero)
#define SWAPIN() do { \
utf = exec_context->Xutf; \
first_char = exec_context->Xfirst_char; \
tables = exec_context->Xtables; \
start_bits = exec_context->Xstart_bits; \
end_subject = exec_context->Xend_subject; \
req_char_ptr = exec_context->Xreq_char_ptr; \
req_char = exec_context->Xreq_char; \
/* Parameters */ \
start_offset = exec_context->Xstart_offset; \
offsetcount = exec_context->Xoffsetcount; \
offsets = exec_context->Xoffsets; \
} while (0)
#define SWAPOUT() do { \
exec_context->Xutf = utf; \
exec_context->Xfirst_char = first_char; \
exec_context->Xtables = tables; \
exec_context->Xstart_bits = start_bits; \
exec_context->Xend_subject = end_subject; \
exec_context->Xreq_char_ptr = req_char_ptr; \
exec_context->Xreq_char = req_char; \
/* Parameters */ \
exec_context->Xstart_offset = start_offset; \
exec_context->Xoffsetcount = offsetcount; \
exec_context->Xoffsets = offsets; \
} while (0)
PcreExecContext *exec_context;
PcreExecContext internal_context;
/* Locals that need never be saved */
int rc, ocount;
int newline;
/* Variables that we swap in and out */
BOOL utf;
pcre_uchar first_char;
const pcre_uint8 *tables;
const pcre_uint8 *start_bits;
PCRE_PUCHAR end_subject;
PCRE_PUCHAR req_char_ptr;
pcre_uchar req_char;
/* End special swapped variables */
if (extra_data != NULL &&
(extra_data->flags & PCRE_EXTRA_LOOP_LIMIT) &&
*(extra_data->restart_data) != NULL) {
/* we are restarting, every initialization is skipped and we jump directly into the loop */
exec_context = (PcreExecContext *) *(extra_data->restart_data);
SWAPIN();
goto RESTART_INTERRUPTED;
} else {
if (extra_data != NULL &&
(extra_data->flags & PCRE_EXTRA_LOOP_LIMIT)) {
exec_context = (PcreExecContext *) (erts_pcre_malloc)(sizeof(PcreExecContext));
*(extra_data->restart_data) = (void *) exec_context;
/* need freeing by special routine from client */
} else {
exec_context = &internal_context;
}
/* OK, no restart here, initialize variables instead */
using_temporary_offsets = FALSE;
has_first_char = FALSE;
has_req_char = FALSE;
first_char = 0;
first_char2 = 0;
req_char = 0;
req_char2 = 0;
md = &match_block;
start_bits = NULL;
start_match = (PCRE_PUCHAR)subject + start_offset;
start_partial = NULL;
req_char_ptr = start_match - 1;
re = (REAL_PCRE *)argument_re;
md->state_save = NULL;
}
#endif /* ERLANG_INTEGRATION */
#ifdef NO_RECURSE
frame_zero.Xprevframe = NULL; /* Marks the top level */
frame_zero.Xnextframe = NULL; /* None are allocated yet */
md->match_frames_base = &frame_zero;
#endif
/* Check for the special magic call that measures the size of the stack used
per recursive call of match(). Without the funny casting for sizeof, a Windows
compiler gave this error: "unary minus operator applied to unsigned type,
result still unsigned". Hopefully the cast fixes that. */
if (re == NULL && extra_data == NULL && subject == NULL && length == -999 &&
start_offset == -999)
#ifdef NO_RECURSE
return -((int)sizeof(heapframe));
#else
return match(NULL, NULL, NULL, 0, NULL, NULL, 0);
#endif
/* Plausibility checks */
if ((options & ~PUBLIC_EXEC_OPTIONS) != 0) return PCRE_ERROR_BADOPTION;
if (re == NULL || subject == NULL || (offsets == NULL && offsetcount > 0))
return PCRE_ERROR_NULL;
if (offsetcount < 0) return PCRE_ERROR_BADCOUNT;
if (length < 0) return PCRE_ERROR_BADLENGTH;
if (start_offset < 0 || start_offset > length) return PCRE_ERROR_BADOFFSET;
/* Check that the first field in the block is the magic number. If it is not,
return with PCRE_ERROR_BADMAGIC. However, if the magic number is equal to
REVERSED_MAGIC_NUMBER we return with PCRE_ERROR_BADENDIANNESS, which
means that the pattern is likely compiled with different endianness. */
if (re->magic_number != MAGIC_NUMBER)
return re->magic_number == REVERSED_MAGIC_NUMBER?
PCRE_ERROR_BADENDIANNESS:PCRE_ERROR_BADMAGIC;
if ((re->flags & PCRE_MODE) == 0) return PCRE_ERROR_BADMODE;
/* These two settings are used in the code for checking a UTF-8 string that
follows immediately afterwards. Other values in the md block are used only
during "normal" pcre_exec() processing, not when the JIT support is in use,
so they are set up later. */
/* PCRE_UTF16 has the same value as PCRE_UTF8. */
utf = md->utf = (re->options & PCRE_UTF8) != 0;
md->partial = ((options & PCRE_PARTIAL_HARD) != 0)? 2 :
((options & PCRE_PARTIAL_SOFT) != 0)? 1 : 0;
/* Check a UTF-8 string if required. Pass back the character offset and error
code for an invalid string if a results vector is available. */
#ifdef SUPPORT_UTF
if (utf && (options & PCRE_NO_UTF8_CHECK) == 0)
{
int erroroffset;
int errorcode = PRIV(valid_utf)((PCRE_PUCHAR)subject, length, &erroroffset);
if (errorcode != 0)
{
if (offsetcount >= 2)
{
offsets[0] = erroroffset;
offsets[1] = errorcode;
}
#if defined COMPILE_PCRE8
return (errorcode <= PCRE_UTF8_ERR5 && md->partial > 1)?
PCRE_ERROR_SHORTUTF8 : PCRE_ERROR_BADUTF8;
#elif defined COMPILE_PCRE16
return (errorcode <= PCRE_UTF16_ERR1 && md->partial > 1)?
PCRE_ERROR_SHORTUTF16 : PCRE_ERROR_BADUTF16;
#elif defined COMPILE_PCRE32
return PCRE_ERROR_BADUTF32;
#endif
}
#if defined COMPILE_PCRE8 || defined COMPILE_PCRE16
/* Check that a start_offset points to the start of a UTF character. */
if (start_offset > 0 && start_offset < length &&
NOT_FIRSTCHAR(((PCRE_PUCHAR)subject)[start_offset]))
return PCRE_ERROR_BADUTF8_OFFSET;
#endif
}
#endif
/* If the pattern was successfully studied with JIT support, run the JIT
executable instead of the rest of this function. Most options must be set at
compile time for the JIT code to be usable. Fallback to the normal code path if
an unsupported flag is set. */
#ifdef SUPPORT_JIT
if (extra_data != NULL
&& (extra_data->flags & (PCRE_EXTRA_EXECUTABLE_JIT |
PCRE_EXTRA_TABLES)) == PCRE_EXTRA_EXECUTABLE_JIT
&& extra_data->executable_jit != NULL
&& (options & ~PUBLIC_JIT_EXEC_OPTIONS) == 0)
{
rc = PRIV(jit_exec)(extra_data, (const pcre_uchar *)subject, length,
start_offset, options, offsets, offsetcount);
/* PCRE_ERROR_NULL means that the selected normal or partial matching
mode is not compiled. In this case we simply fallback to interpreter. */
if (rc != PCRE_ERROR_JIT_BADOPTION) return rc;
}
#endif
/* Carry on with non-JIT matching. This information is for finding all the
numbers associated with a given name, for condition testing. */
md->name_table = (pcre_uchar *)re + re->name_table_offset;
md->name_count = re->name_count;
md->name_entry_size = re->name_entry_size;
/* Fish out the optional data from the extra_data structure, first setting
the default values. */
study = NULL;
md->match_limit = MATCH_LIMIT;
md->match_limit_recursion = MATCH_LIMIT_RECURSION;
md->callout_data = NULL;
/* The table pointer is always in native byte order. */
tables = re->tables;
/* The two limit values override the defaults, whatever their value. */
if (extra_data != NULL)
{
register unsigned int flags = extra_data->flags;
if ((flags & PCRE_EXTRA_STUDY_DATA) != 0)
study = (const pcre_study_data *)extra_data->study_data;
if ((flags & PCRE_EXTRA_MATCH_LIMIT) != 0)
md->match_limit = extra_data->match_limit;
if ((flags & PCRE_EXTRA_MATCH_LIMIT_RECURSION) != 0)
md->match_limit_recursion = extra_data->match_limit_recursion;
if ((flags & PCRE_EXTRA_CALLOUT_DATA) != 0)
md->callout_data = extra_data->callout_data;
if ((flags & PCRE_EXTRA_TABLES) != 0) tables = extra_data->tables;
#ifdef ERLANG_INTEGRATION
if ((flags & PCRE_EXTRA_LOOP_LIMIT) != 0)
{
md->loop_limit = extra_data->loop_limit;
}
#endif
}
/* Limits in the regex override only if they are smaller. */
if ((re->flags & PCRE_MLSET) != 0 && re->limit_match < md->match_limit)
md->match_limit = re->limit_match;
if ((re->flags & PCRE_RLSET) != 0 &&
re->limit_recursion < md->match_limit_recursion)
md->match_limit_recursion = re->limit_recursion;
/* If the exec call supplied NULL for tables, use the inbuilt ones. This
is a feature that makes it possible to save compiled regex and re-use them
in other programs later. */
if (tables == NULL) tables = PRIV(default_tables);
/* Set up other data */
anchored = ((re->options | options) & PCRE_ANCHORED) != 0;
startline = (re->flags & PCRE_STARTLINE) != 0;
firstline = (re->options & PCRE_FIRSTLINE) != 0;
/* The code starts after the real_pcre block and the capture name table. */
md->start_code = (const pcre_uchar *)re + re->name_table_offset +
re->name_count * re->name_entry_size;
md->start_subject = (PCRE_PUCHAR)subject;
md->start_offset = start_offset;
md->end_subject = md->start_subject + length;
end_subject = md->end_subject;
md->endonly = (re->options & PCRE_DOLLAR_ENDONLY) != 0;
md->use_ucp = (re->options & PCRE_UCP) != 0;
md->jscript_compat = (re->options & PCRE_JAVASCRIPT_COMPAT) != 0;
md->ignore_skip_arg = 0;
/* Some options are unpacked into BOOL variables in the hope that testing
them will be faster than individual option bits. */
md->notbol = (options & PCRE_NOTBOL) != 0;
md->noteol = (options & PCRE_NOTEOL) != 0;
md->notempty = (options & PCRE_NOTEMPTY) != 0;
md->notempty_atstart = (options & PCRE_NOTEMPTY_ATSTART) != 0;
md->hitend = FALSE;
md->mark = md->nomatch_mark = NULL; /* In case never set */
md->recursive = NULL; /* No recursion at top level */
md->hasthen = (re->flags & PCRE_HASTHEN) != 0;
md->lcc = tables + lcc_offset;
md->fcc = tables + fcc_offset;
md->ctypes = tables + ctypes_offset;
/* Handle different \R options. */
switch (options & (PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE))
{
case 0:
if ((re->options & (PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE)) != 0)
md->bsr_anycrlf = (re->options & PCRE_BSR_ANYCRLF) != 0;
else
#ifdef BSR_ANYCRLF
md->bsr_anycrlf = TRUE;
#else
md->bsr_anycrlf = FALSE;
#endif
break;
case PCRE_BSR_ANYCRLF:
md->bsr_anycrlf = TRUE;
break;
case PCRE_BSR_UNICODE:
md->bsr_anycrlf = FALSE;
break;
default: return PCRE_ERROR_BADNEWLINE;
}
/* Handle different types of newline. The three bits give eight cases. If
nothing is set at run time, whatever was used at compile time applies. */
switch ((((options & PCRE_NEWLINE_BITS) == 0)? re->options :
(pcre_uint32)options) & PCRE_NEWLINE_BITS)
{
case 0: newline = NEWLINE; break; /* Compile-time default */
case PCRE_NEWLINE_CR: newline = CHAR_CR; break;
case PCRE_NEWLINE_LF: newline = CHAR_NL; break;
case PCRE_NEWLINE_CR+
PCRE_NEWLINE_LF: newline = (CHAR_CR << 8) | CHAR_NL; break;
case PCRE_NEWLINE_ANY: newline = -1; break;
case PCRE_NEWLINE_ANYCRLF: newline = -2; break;
default: return PCRE_ERROR_BADNEWLINE;
}
if (newline == -2)
{
md->nltype = NLTYPE_ANYCRLF;
}
else if (newline < 0)
{
md->nltype = NLTYPE_ANY;
}
else
{
md->nltype = NLTYPE_FIXED;
if (newline > 255)
{
md->nllen = 2;
md->nl[0] = (newline >> 8) & 255;
md->nl[1] = newline & 255;
}
else
{
md->nllen = 1;
md->nl[0] = newline;
}
}
/* Partial matching was originally supported only for a restricted set of
regexes; from release 8.00 there are no restrictions, but the bits are still
defined (though never set). So there's no harm in leaving this code. */
if (md->partial && (re->flags & PCRE_NOPARTIAL) != 0)
return PCRE_ERROR_BADPARTIAL;
/* If the expression has got more back references than the offsets supplied can
hold, we get a temporary chunk of working store to use during the matching.
Otherwise, we can use the vector supplied, rounding down its size to a multiple
of 3. */
ocount = offsetcount - (offsetcount % 3);
arg_offset_max = (2*ocount)/3;
if (re->top_backref > 0 && re->top_backref >= ocount/3)
{
ocount = re->top_backref * 3 + 3;
md->offset_vector = (int *)(PUBL(malloc))(ocount * sizeof(int));
if (md->offset_vector == NULL) return PCRE_ERROR_NOMEMORY;
using_temporary_offsets = TRUE;
DPRINTF(("Got memory to hold back references\n"));
}
else md->offset_vector = offsets;
md->offset_end = ocount;
md->offset_max = (2*ocount)/3;
md->capture_last = 0;
/* Reset the working variable associated with each extraction. These should
never be used unless previously set, but they get saved and restored, and so we
initialize them to avoid reading uninitialized locations. Also, unset the
offsets for the matched string. This is really just for tidiness with callouts,
in case they inspect these fields. */
if (md->offset_vector != NULL)
{
register int *iptr = md->offset_vector + ocount;
register int *iend = iptr - re->top_bracket;
if (iend < md->offset_vector + 2) iend = md->offset_vector + 2;
while (--iptr >= iend) *iptr = -1;
md->offset_vector[0] = md->offset_vector[1] = -1;
}
/* Set up the first character to match, if available. The first_char value is
never set for an anchored regular expression, but the anchoring may be forced
at run time, so we have to test for anchoring. The first char may be unset for
an unanchored pattern, of course. If there's no first char and the pattern was
studied, there may be a bitmap of possible first characters. */
if (!anchored)
{
if ((re->flags & PCRE_FIRSTSET) != 0)
{
has_first_char = TRUE;
first_char = first_char2 = (pcre_uchar)(re->first_char);
if ((re->flags & PCRE_FCH_CASELESS) != 0)
{
first_char2 = TABLE_GET(first_char, md->fcc, first_char);
#if defined SUPPORT_UCP && !(defined COMPILE_PCRE8)
if (utf && first_char > 127)
first_char2 = UCD_OTHERCASE(first_char);
#endif
}
}
else
if (!startline && study != NULL &&
(study->flags & PCRE_STUDY_MAPPED) != 0)
start_bits = study->start_bits;
}
/* For anchored or unanchored matches, there may be a "last known required
character" set. */
if ((re->flags & PCRE_REQCHSET) != 0)
{
has_req_char = TRUE;
req_char = req_char2 = (pcre_uchar)(re->req_char);
if ((re->flags & PCRE_RCH_CASELESS) != 0)
{
req_char2 = TABLE_GET(req_char, md->fcc, req_char);
#if defined SUPPORT_UCP && !(defined COMPILE_PCRE8)
if (utf && req_char > 127)
req_char2 = UCD_OTHERCASE(req_char);
#endif
}
}
/* ==========================================================================*/
/* Loop for handling unanchored repeated matching attempts; for anchored regexs
the loop runs just once. */
for(;;)
{
PCRE_PUCHAR save_end_subject = end_subject;
PCRE_PUCHAR new_start_match;
/* If firstline is TRUE, the start of the match is constrained to the first
line of a multiline string. That is, the match must be before or at the first
newline. Implement this by temporarily adjusting end_subject so that we stop
scanning at a newline. If the match fails at the newline, later code breaks
this loop. */
if (firstline)
{
PCRE_PUCHAR t = start_match;
#ifdef SUPPORT_UTF
if (utf)
{
while (t < md->end_subject && !IS_NEWLINE(t))
{
t++;
ACROSSCHAR(t < end_subject, *t, t++);
}
}
else
#endif
while (t < md->end_subject && !IS_NEWLINE(t)) t++;
end_subject = t;
}
/* There are some optimizations that avoid running the match if a known
starting point is not found, or if a known later character is not present.
However, there is an option that disables these, for testing and for ensuring
that all callouts do actually occur. The option can be set in the regex by
(*NO_START_OPT) or passed in match-time options. */
if (((options | re->options) & PCRE_NO_START_OPTIMIZE) == 0)
{
/* Advance to a unique first char if there is one. */
if (has_first_char)
{
pcre_uchar smc;
if (first_char != first_char2)
while (start_match < end_subject &&
(smc = RAWUCHARTEST(start_match)) != first_char && smc != first_char2)
start_match++;
else
while (start_match < end_subject && RAWUCHARTEST(start_match) != first_char)
start_match++;
}
/* Or to just after a linebreak for a multiline match */
else if (startline)
{
if (start_match > md->start_subject + start_offset)
{
#ifdef SUPPORT_UTF
if (utf)
{
while (start_match < end_subject && !WAS_NEWLINE(start_match))
{
start_match++;
ACROSSCHAR(start_match < end_subject, *start_match,
start_match++);
}
}
else
#endif
while (start_match < end_subject && !WAS_NEWLINE(start_match))
start_match++;
/* If we have just passed a CR and the newline option is ANY or ANYCRLF,
and we are now at a LF, advance the match position by one more character.
*/
if (start_match[-1] == CHAR_CR &&
(md->nltype == NLTYPE_ANY || md->nltype == NLTYPE_ANYCRLF) &&
start_match < end_subject &&
RAWUCHARTEST(start_match) == CHAR_NL)
start_match++;
}
}
/* Or to a non-unique first byte after study */
else if (start_bits != NULL)
{
while (start_match < end_subject)
{
register pcre_uint32 c = RAWUCHARTEST(start_match);
#ifndef COMPILE_PCRE8
if (c > 255) c = 255;
#endif
if ((start_bits[c/8] & (1 << (c&7))) == 0)
{
start_match++;
#if defined SUPPORT_UTF && defined COMPILE_PCRE8
/* In non 8-bit mode, the iteration will stop for
characters > 255 at the beginning or not stop at all. */
if (utf)
ACROSSCHAR(start_match < end_subject, *start_match,
start_match++);
#endif
}
#ifdef ERLANG_INTEGRATION
else {
if ((extra_data->flags & PCRE_EXTRA_LOOP_LIMIT) != 0)
{
*extra_data->loop_counter_return =
(extra_data->loop_limit - md->loop_limit);
}
break;
}
#else
else break;
#endif
}
}
} /* Starting optimizations */
/* Restore fudged end_subject */
end_subject = save_end_subject;
/* The following two optimizations are disabled for partial matching or if
disabling is explicitly requested. */
if (((options | re->options) & PCRE_NO_START_OPTIMIZE) == 0 && !md->partial)
{
/* If the pattern was studied, a minimum subject length may be set. This is
a lower bound; no actual string of that length may actually match the
pattern. Although the value is, strictly, in characters, we treat it as
bytes to avoid spending too much time in this optimization. */
if (study != NULL && (study->flags & PCRE_STUDY_MINLEN) != 0 &&
(pcre_uint32)(end_subject - start_match) < study->minlength)
{
rc = MATCH_NOMATCH;
#ifdef ERLANG_INTEGRATION
if ((extra_data->flags & PCRE_EXTRA_LOOP_LIMIT) != 0)
{
*extra_data->loop_counter_return =
(extra_data->loop_limit - md->loop_limit);
}
#endif
break;
}
/* If req_char is set, we know that that character must appear in the
subject for the match to succeed. If the first character is set, req_char
must be later in the subject; otherwise the test starts at the match point.
This optimization can save a huge amount of backtracking in patterns with
nested unlimited repeats that aren't going to match. Writing separate code
for cased/caseless versions makes it go faster, as does using an
autoincrement and backing off on a match.
HOWEVER: when the subject string is very, very long, searching to its end
can take a long time, and give bad performance on quite ordinary patterns.
This showed up when somebody was matching something like /^\d+C/ on a
32-megabyte string... so we don't do this when the string is sufficiently
long. */
if (has_req_char && end_subject - start_match < REQ_BYTE_MAX)
{
register PCRE_PUCHAR p = start_match + (has_first_char? 1:0);
/* We don't need to repeat the search if we haven't yet reached the
place we found it at last time. */
if (p > req_char_ptr)
{
if (req_char != req_char2)
{
while (p < end_subject)
{
register pcre_uint32 pp = RAWUCHARINCTEST(p);
if (pp == req_char || pp == req_char2) { p--; break; }
}
}
else
{
while (p < end_subject)
{
if (RAWUCHARINCTEST(p) == req_char) { p--; break; }
}
}
/* If we can't find the required character, break the matching loop,
forcing a match failure. */
if (p >= end_subject)
{
rc = MATCH_NOMATCH;
#ifdef ERLANG_INTEGRATION
if ((extra_data->flags & PCRE_EXTRA_LOOP_LIMIT) != 0)
{
*extra_data->loop_counter_return =
(extra_data->loop_limit - md->loop_limit);
}
#endif
break;
}
/* If we have found the required character, save the point where we
found it, so that we don't search again next time round the loop if
the start hasn't passed this character yet. */
req_char_ptr = p;
}
}
}
#ifdef PCRE_DEBUG /* Sigh. Some compilers never learn. */
printf(">>>> Match against: ");
pchars(start_match, end_subject - start_match, TRUE, md);
printf("\n");
#endif
/* OK, we can now run the match. If "hitend" is set afterwards, remember the
first starting point for which a partial match was found. */
md->start_match_ptr = start_match;
md->start_used_ptr = start_match;
md->match_call_count = 0;
md->match_function_type = 0;
md->end_offset_top = 0;
md->skip_arg_count = 0;
EDEBUGF(("Calling match..."));
rc = match(start_match, md->start_code, start_match, 2, md, NULL, 0);
#ifdef ERLANG_INTEGRATION
if ((extra_data->flags & PCRE_EXTRA_LOOP_LIMIT) != 0)
{
*extra_data->loop_counter_return =
(extra_data->loop_limit - md->loop_limit);
}
SWAPOUT();
while(rc == PCRE_ERROR_LOOP_LIMIT) {
EDEBUGF(("Loop limit break detected"));
return PCRE_ERROR_LOOP_LIMIT;
RESTART_INTERRUPTED:
md->loop_limit = extra_data->loop_limit;
rc = match(NULL,NULL,NULL,0,md,NULL,0);
*extra_data->loop_counter_return =
(extra_data->loop_limit - md->loop_limit);
}
md->state_save = NULL; /* So that next call to free_saved... does not crash */
#endif
if (md->hitend && start_partial == NULL)
{
start_partial = md->start_used_ptr;
match_partial = start_match;
}
switch(rc)
{
/* If MATCH_SKIP_ARG reaches this level it means that a MARK that matched
the SKIP's arg was not found. In this circumstance, Perl ignores the SKIP
entirely. The only way we can do that is to re-do the match at the same
point, with a flag to force SKIP with an argument to be ignored. Just
treating this case as NOMATCH does not work because it does not check other
alternatives in patterns such as A(*SKIP:A)B|AC when the subject is AC. */
case MATCH_SKIP_ARG:
new_start_match = start_match;
md->ignore_skip_arg = md->skip_arg_count;
break;
/* SKIP passes back the next starting point explicitly, but if it is no
greater than the match we have just done, treat it as NOMATCH. */
case MATCH_SKIP:
if (md->start_match_ptr > start_match)
{
new_start_match = md->start_match_ptr;
break;
}
/* Fall through */
/* NOMATCH and PRUNE advance by one character. THEN at this level acts
exactly like PRUNE. Unset ignore SKIP-with-argument. */
case MATCH_NOMATCH:
case MATCH_PRUNE:
case MATCH_THEN:
md->ignore_skip_arg = 0;
new_start_match = start_match + 1;
#ifdef SUPPORT_UTF
if (utf)
ACROSSCHAR(new_start_match < end_subject, *new_start_match,
new_start_match++);
#endif
break;
/* COMMIT disables the bumpalong, but otherwise behaves as NOMATCH. */
case MATCH_COMMIT:
rc = MATCH_NOMATCH;
goto ENDLOOP;
/* Any other return is either a match, or some kind of error. */
default:
goto ENDLOOP;
}
/* Control reaches here for the various types of "no match at this point"
result. Reset the code to MATCH_NOMATCH for subsequent checking. */
rc = MATCH_NOMATCH;
/* If PCRE_FIRSTLINE is set, the match must happen before or at the first
newline in the subject (though it may continue over the newline). Therefore,
if we have just failed to match, starting at a newline, do not continue. */
if (firstline && IS_NEWLINE(start_match)) break;
/* Advance to new matching position */
start_match = new_start_match;
/* Break the loop if the pattern is anchored or if we have passed the end of
the subject. */
if (anchored || start_match > end_subject) break;
/* If we have just passed a CR and we are now at a LF, and the pattern does
not contain any explicit matches for \r or \n, and the newline option is CRLF
or ANY or ANYCRLF, advance the match position by one more character. In
normal matching start_match will aways be greater than the first position at
this stage, but a failed *SKIP can cause a return at the same point, which is
why the first test exists. */
if (start_match > (PCRE_PUCHAR)subject + start_offset &&
start_match[-1] == CHAR_CR &&
start_match < end_subject &&
*start_match == CHAR_NL &&
(re->flags & PCRE_HASCRORLF) == 0 &&
(md->nltype == NLTYPE_ANY ||
md->nltype == NLTYPE_ANYCRLF ||
md->nllen == 2))
start_match++;
md->mark = NULL; /* Reset for start of next match attempt */
} /* End of for(;;) "bumpalong" loop */
/* ==========================================================================*/
/* We reach here when rc is not MATCH_NOMATCH, or if one of the stopping
conditions is true:
(1) The pattern is anchored or the match was failed by (*COMMIT);
(2) We are past the end of the subject;
(3) PCRE_FIRSTLINE is set and we have failed to match at a newline, because
this option requests that a match occur at or before the first newline in
the subject.
When we have a match and the offset vector is big enough to deal with any
backreferences, captured substring offsets will already be set up. In the case
where we had to get some local store to hold offsets for backreference
processing, copy those that we can. In this case there need not be overflow if
certain parts of the pattern were not used, even though there are more
capturing parentheses than vector slots. */
ENDLOOP:
if (rc == MATCH_MATCH || rc == MATCH_ACCEPT)
{
if (using_temporary_offsets)
{
if (arg_offset_max >= 4)
{
memcpy(offsets + 2, md->offset_vector + 2,
(arg_offset_max - 2) * sizeof(int));
DPRINTF(("Copied offsets from temporary memory\n"));
}
if (md->end_offset_top > arg_offset_max) md->capture_last |= OVFLBIT;
DPRINTF(("Freeing temporary memory\n"));
(PUBL(free))(md->offset_vector);
#ifdef ERLANG_INTEGRATION
md->offset_vector = NULL;
#endif
}
/* Set the return code to the number of captured strings, or 0 if there were
too many to fit into the vector. */
rc = ((md->capture_last & OVFLBIT) != 0 &&
md->end_offset_top >= arg_offset_max)?
0 : md->end_offset_top/2;
/* If there is space in the offset vector, set any unused pairs at the end of
the pattern to -1 for backwards compatibility. It is documented that this
happens. In earlier versions, the whole set of potential capturing offsets
was set to -1 each time round the loop, but this is handled differently now.
"Gaps" are set to -1 dynamically instead (this fixes a bug). Thus, it is only
those at the end that need unsetting here. We can't just unset them all at
the start of the whole thing because they may get set in one branch that is
not the final matching branch. */
if (md->end_offset_top/2 <= re->top_bracket && offsets != NULL)
{
register int *iptr, *iend;
int resetcount = 2 + re->top_bracket * 2;
if (resetcount > offsetcount) resetcount = offsetcount;
iptr = offsets + md->end_offset_top;
iend = offsets + resetcount;
while (iptr < iend) *iptr++ = -1;
}
/* If there is space, set up the whole thing as substring 0. The value of
md->start_match_ptr might be modified if \K was encountered on the success
matching path. */
if (offsetcount < 2) rc = 0; else
{
offsets[0] = (int)(md->start_match_ptr - md->start_subject);
offsets[1] = (int)(md->end_match_ptr - md->start_subject);
}
/* Return MARK data if requested */
if (extra_data != NULL && (extra_data->flags & PCRE_EXTRA_MARK) != 0)
*(extra_data->mark) = (pcre_uchar *)md->mark;
DPRINTF((">>>> returning %d\n", rc));
#ifdef NO_RECURSE
release_match_heapframes(&frame_zero);
#endif
return rc;
}
/* Control gets here if there has been an error, or if the overall match
attempt has failed at all permitted starting positions. */
if (using_temporary_offsets)
{
DPRINTF(("Freeing temporary memory\n"));
#ifdef ERLANG_INTEGRATION
if (extra_data == NULL ||
!(extra_data->flags & PCRE_EXTRA_LOOP_LIMIT))
{
(PUBL(free))(md->offset_vector);
md->offset_vector = NULL;
}
#else
(PUBL(free))(md->offset_vector);
#endif
}
/* For anything other than nomatch or partial match, just return the code. */
if (rc != MATCH_NOMATCH && rc != PCRE_ERROR_PARTIAL)
{
DPRINTF((">>>> error: returning %d\n", rc));
#ifdef NO_RECURSE
release_match_heapframes(&frame_zero);
#endif
return rc;
}
/* Handle partial matches - disable any mark data */
if (start_partial != NULL)
{
DPRINTF((">>>> returning PCRE_ERROR_PARTIAL\n"));
md->mark = NULL;
if (offsetcount > 1)
{
offsets[0] = (int)(start_partial - (PCRE_PUCHAR)subject);
offsets[1] = (int)(end_subject - (PCRE_PUCHAR)subject);
if (offsetcount > 2)
offsets[2] = (int)(match_partial - (PCRE_PUCHAR)subject);
}
rc = PCRE_ERROR_PARTIAL;
}
/* This is the classic nomatch case */
else
{
DPRINTF((">>>> returning PCRE_ERROR_NOMATCH\n"));
rc = PCRE_ERROR_NOMATCH;
}
/* Return the MARK data if it has been requested. */
if (extra_data != NULL && (extra_data->flags & PCRE_EXTRA_MARK) != 0)
*(extra_data->mark) = (pcre_uchar *)md->nomatch_mark;
#ifdef NO_RECURSE
release_match_heapframes(&frame_zero);
#endif
return rc;
}
#if defined(ERLANG_INTEGRATION)
#undef arg_offset_max
#undef using_temporary_offsets
#undef anchored
#undef startline
#undef firstline
#undef has_first_char
#undef has_req_char
#undef first_char2
#undef req_char
#undef req_char2
#undef match_block
#undef md
#undef start_match
#undef start_partial
#undef match_partial
#undef study
#undef re
#undef frame_zero
void erts_pcre_free_restart_data(void *restart_data) {
PcreExecContext *top = (PcreExecContext *) restart_data;
/* We might be done, or we might not, so there might be some saved match_states here */
if (top != NULL) {
match_data *md = top->Xmd;
if (top->Xusing_temporary_offsets && md->offset_vector != NULL) {
(PUBL(free))(md->offset_vector);
}
release_match_heapframes(&(top->Xframe_zero));
(PUBL(free))(top);
}
}
#endif
/* End of pcre_exec.c */
|