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
|
<?php
/**
* @defgroup Parser Parser
*
* @file
* @ingroup Parser
* File for Parser and related classes
*/
/**
* PHP Parser - Processes wiki markup (which uses a more user-friendly
* syntax, such as "[[link]]" for making links), and provides a one-way
* transformation of that wiki markup it into XHTML output / markup
* (which in turn the browser understands, and can display).
*
* <pre>
* There are five main entry points into the Parser class:
* parse()
* produces HTML output
* preSaveTransform().
* produces altered wiki markup.
* preprocess()
* removes HTML comments and expands templates
* cleanSig()
* Cleans a signature before saving it to preferences
* extractSections()
* Extracts sections from an article for section editing
*
* Globals used:
* objects: $wgLang, $wgContLang
*
* NOT $wgArticle, $wgUser or $wgTitle. Keep them away!
*
* settings:
* $wgUseTex*, $wgUseDynamicDates*, $wgInterwikiMagic*,
* $wgNamespacesWithSubpages, $wgAllowExternalImages*,
* $wgLocaltimezone, $wgAllowSpecialInclusion*,
* $wgMaxArticleSize*
*
* * only within ParserOptions
* </pre>
*
* @ingroup Parser
*/
class Parser
{
/**
* Update this version number when the ParserOutput format
* changes in an incompatible way, so the parser cache
* can automatically discard old data.
*/
const VERSION = '1.6.4';
# Flags for Parser::setFunctionHook
# Also available as global constants from Defines.php
const SFH_NO_HASH = 1;
const SFH_OBJECT_ARGS = 2;
# Constants needed for external link processing
# Everything except bracket, space, or control characters
const EXT_LINK_URL_CLASS = '[^][<>"\\x00-\\x20\\x7F]';
const EXT_IMAGE_REGEX = '/^(http:\/\/|https:\/\/)([^][<>"\\x00-\\x20\\x7F]+)
\\/([A-Za-z0-9_.,~%\\-+&;#*?!=()@\\x80-\\xFF]+)\\.((?i)gif|png|jpg|jpeg)$/Sx';
// State constants for the definition list colon extraction
const COLON_STATE_TEXT = 0;
const COLON_STATE_TAG = 1;
const COLON_STATE_TAGSTART = 2;
const COLON_STATE_CLOSETAG = 3;
const COLON_STATE_TAGSLASH = 4;
const COLON_STATE_COMMENT = 5;
const COLON_STATE_COMMENTDASH = 6;
const COLON_STATE_COMMENTDASHDASH = 7;
// Flags for preprocessToDom
const PTD_FOR_INCLUSION = 1;
// Allowed values for $this->mOutputType
// Parameter to startExternalParse().
const OT_HTML = 1;
const OT_WIKI = 2;
const OT_PREPROCESS = 3;
const OT_MSG = 3;
// Marker Suffix needs to be accessible staticly.
const MARKER_SUFFIX = "-QINU\x7f";
/**#@+
* @private
*/
# Persistent:
var $mTagHooks, $mTransparentTagHooks, $mFunctionHooks, $mFunctionSynonyms, $mVariables,
$mSubstWords, $mImageParams, $mImageParamsMagicArray, $mStripList, $mMarkerIndex,
$mPreprocessor, $mExtLinkBracketedRegex, $mUrlProtocols, $mDefaultStripList,
$mVarCache, $mConf, $mFunctionTagHooks;
# Cleared with clearState():
var $mOutput, $mAutonumber, $mDTopen, $mStripState;
var $mIncludeCount, $mArgStack, $mLastSection, $mInPre;
var $mLinkHolders, $mLinkID;
var $mIncludeSizes, $mPPNodeCount, $mDefaultSort;
var $mTplExpandCache; // empty-frame expansion cache
var $mTplRedirCache, $mTplDomCache, $mHeadings, $mDoubleUnderscores;
var $mExpensiveFunctionCount; // number of expensive parser function calls
# Temporary
# These are variables reset at least once per parse regardless of $clearState
var $mOptions, // ParserOptions object
$mTitle, // Title context, used for self-link rendering and similar things
$mOutputType, // Output type, one of the OT_xxx constants
$ot, // Shortcut alias, see setOutputType()
$mRevisionId, // ID to display in {{REVISIONID}} tags
$mRevisionTimestamp, // The timestamp of the specified revision ID
$mRevIdForTs; // The revision ID which was used to fetch the timestamp
/**#@-*/
/**
* Constructor
*
* @public
*/
function __construct( $conf = array() ) {
$this->mConf = $conf;
$this->mTagHooks = array();
$this->mTransparentTagHooks = array();
$this->mFunctionHooks = array();
$this->mFunctionTagHooks = array();
$this->mFunctionSynonyms = array( 0 => array(), 1 => array() );
$this->mDefaultStripList = $this->mStripList = array();
$this->mUrlProtocols = wfUrlProtocols();
$this->mExtLinkBracketedRegex = '/\[(\b(' . wfUrlProtocols() . ')'.
'[^][<>"\\x00-\\x20\\x7F]+) *([^\]\\x0a\\x0d]*?)\]/S';
$this->mVarCache = array();
if ( isset( $conf['preprocessorClass'] ) ) {
$this->mPreprocessorClass = $conf['preprocessorClass'];
} elseif ( extension_loaded( 'domxml' ) ) {
// PECL extension that conflicts with the core DOM extension (bug 13770)
wfDebug( "Warning: you have the obsolete domxml extension for PHP. Please remove it!\n" );
$this->mPreprocessorClass = 'Preprocessor_Hash';
} elseif ( extension_loaded( 'dom' ) ) {
$this->mPreprocessorClass = 'Preprocessor_DOM';
} else {
$this->mPreprocessorClass = 'Preprocessor_Hash';
}
$this->mMarkerIndex = 0;
$this->mFirstCall = true;
}
/**
* Reduce memory usage to reduce the impact of circular references
*/
function __destruct() {
if ( isset( $this->mLinkHolders ) ) {
$this->mLinkHolders->__destruct();
}
foreach ( $this as $name => $value ) {
unset( $this->$name );
}
}
/**
* Do various kinds of initialisation on the first call of the parser
*/
function firstCallInit() {
if ( !$this->mFirstCall ) {
return;
}
$this->mFirstCall = false;
wfProfileIn( __METHOD__ );
CoreParserFunctions::register( $this );
CoreTagHooks::register( $this );
$this->initialiseVariables();
wfRunHooks( 'ParserFirstCallInit', array( &$this ) );
wfProfileOut( __METHOD__ );
}
/**
* Clear Parser state
*
* @private
*/
function clearState() {
wfProfileIn( __METHOD__ );
if ( $this->mFirstCall ) {
$this->firstCallInit();
}
$this->mOutput = new ParserOutput;
$this->mAutonumber = 0;
$this->mLastSection = '';
$this->mDTopen = false;
$this->mIncludeCount = array();
$this->mStripState = new StripState;
$this->mArgStack = false;
$this->mInPre = false;
$this->mLinkHolders = new LinkHolderArray( $this );
$this->mLinkID = 0;
$this->mRevisionTimestamp = $this->mRevisionId = null;
$this->mVarCache = array();
/**
* Prefix for temporary replacement strings for the multipass parser.
* \x07 should never appear in input as it's disallowed in XML.
* Using it at the front also gives us a little extra robustness
* since it shouldn't match when butted up against identifier-like
* string constructs.
*
* Must not consist of all title characters, or else it will change
* the behaviour of <nowiki> in a link.
*/
#$this->mUniqPrefix = "\x07UNIQ" . Parser::getRandomString();
# Changed to \x7f to allow XML double-parsing -- TS
$this->mUniqPrefix = "\x7fUNIQ" . self::getRandomString();
# Clear these on every parse, bug 4549
$this->mTplExpandCache = $this->mTplRedirCache = $this->mTplDomCache = array();
$this->mShowToc = true;
$this->mForceTocPosition = false;
$this->mIncludeSizes = array(
'post-expand' => 0,
'arg' => 0,
);
$this->mPPNodeCount = 0;
$this->mDefaultSort = false;
$this->mHeadings = array();
$this->mDoubleUnderscores = array();
$this->mExpensiveFunctionCount = 0;
# Fix cloning
if ( isset( $this->mPreprocessor ) && $this->mPreprocessor->parser !== $this ) {
$this->mPreprocessor = null;
}
wfRunHooks( 'ParserClearState', array( &$this ) );
wfProfileOut( __METHOD__ );
}
function setOutputType( $ot ) {
$this->mOutputType = $ot;
// Shortcut alias
$this->ot = array(
'html' => $ot == self::OT_HTML,
'wiki' => $ot == self::OT_WIKI,
'pre' => $ot == self::OT_PREPROCESS,
);
}
/**
* Set the context title
*/
function setTitle( $t ) {
if ( !$t || $t instanceof FakeTitle ) {
$t = Title::newFromText( 'NO TITLE' );
}
if ( strval( $t->getFragment() ) !== '' ) {
# Strip the fragment to avoid various odd effects
$this->mTitle = clone $t;
$this->mTitle->setFragment( '' );
} else {
$this->mTitle = $t;
}
}
/**
* Accessor for mUniqPrefix.
*
* @public
*/
function uniqPrefix() {
if( !isset( $this->mUniqPrefix ) ) {
// @todo Fixme: this is probably *horribly wrong*
// LanguageConverter seems to want $wgParser's uniqPrefix, however
// if this is called for a parser cache hit, the parser may not
// have ever been initialized in the first place.
// Not really sure what the heck is supposed to be going on here.
return '';
//throw new MWException( "Accessing uninitialized mUniqPrefix" );
}
return $this->mUniqPrefix;
}
/**
* Convert wikitext to HTML
* Do not call this function recursively.
*
* @param $text String: text we want to parse
* @param $title A title object
* @param $options ParserOptions
* @param $linestart boolean
* @param $clearState boolean
* @param $revid Int: number to pass in {{REVISIONID}}
* @return ParserOutput a ParserOutput
*/
public function parse( $text, Title $title, ParserOptions $options, $linestart = true, $clearState = true, $revid = null ) {
/**
* First pass--just handle <nowiki> sections, pass the rest off
* to internalParse() which does all the real work.
*/
global $wgUseTidy, $wgAlwaysUseTidy, $wgContLang, $wgDisableLangConversion, $wgDisableTitleConversion;
$fname = __METHOD__.'-' . wfGetCaller();
wfProfileIn( __METHOD__ );
wfProfileIn( $fname );
if ( $clearState ) {
$this->clearState();
}
$this->mOptions = $options;
$this->setTitle( $title ); // Page title has to be set for the pre-processor
$oldRevisionId = $this->mRevisionId;
$oldRevisionTimestamp = $this->mRevisionTimestamp;
if( $revid !== null ) {
$this->mRevisionId = $revid;
$this->mRevisionTimestamp = null;
}
$this->setOutputType( self::OT_HTML );
wfRunHooks( 'ParserBeforeStrip', array( &$this, &$text, &$this->mStripState ) );
# No more strip!
wfRunHooks( 'ParserAfterStrip', array( &$this, &$text, &$this->mStripState ) );
$text = $this->internalParse( $text );
$text = $this->mStripState->unstripGeneral( $text );
# Clean up special characters, only run once, next-to-last before doBlockLevels
$fixtags = array(
# french spaces, last one Guillemet-left
# only if there is something before the space
'/(.) (?=\\?|:|;|!|%|\\302\\273)/' => '\\1 \\2',
# french spaces, Guillemet-right
'/(\\302\\253) /' => '\\1 ',
'/ (!\s*important)/' => ' \\1', #Beware of CSS magic word !important, bug #11874.
);
$text = preg_replace( array_keys($fixtags), array_values($fixtags), $text );
$text = $this->doBlockLevels( $text, $linestart );
$this->replaceLinkHolders( $text );
/**
* The page doesn't get language converted if
* a) It's disabled
* b) Content isn't converted
* c) It's a conversion table
*/
if ( !( $wgDisableLangConversion
|| isset( $this->mDoubleUnderscores['nocontentconvert'] )
|| $this->mTitle->isConversionTable() ) ) {
# The position of the convert() call should not be changed. it
# assumes that the links are all replaced and the only thing left
# is the <nowiki> mark.
$text = $wgContLang->convert( $text );
}
/**
* A page get its title converted except:
* a) Language conversion is globally disabled
* b) Title convert is globally disabled
* c) The page is a redirect page
* d) User request with a "linkconvert" set to "no"
* e) A "nocontentconvert" magic word has been set
* f) A "notitleconvert" magic word has been set
* g) User sets "noconvertlink" in his/her preference
*
* Note that if a user tries to set a title in a conversion
* rule but content conversion was not done, then the parser
* won't pick it up. This is probably expected behavior.
*/
if ( !( $wgDisableLangConversion
|| $wgDisableTitleConversion
|| isset( $this->mDoubleUnderscores['nocontentconvert'] )
|| isset( $this->mDoubleUnderscores['notitleconvert'] )
|| $this->mOutput->getDisplayTitle() !== false ) )
{
$convruletitle = $wgContLang->getConvRuleTitle();
if ( $convruletitle ) {
$this->mOutput->setTitleText( $convruletitle );
} else {
$titleText = $wgContLang->convertTitle( $title );
$this->mOutput->setTitleText( $titleText );
}
}
$text = $this->mStripState->unstripNoWiki( $text );
wfRunHooks( 'ParserBeforeTidy', array( &$this, &$text ) );
//!JF Move to its own function
$uniq_prefix = $this->mUniqPrefix;
$matches = array();
$elements = array_keys( $this->mTransparentTagHooks );
$text = self::extractTagsAndParams( $elements, $text, $matches, $uniq_prefix );
foreach( $matches as $marker => $data ) {
list( $element, $content, $params, $tag ) = $data;
$tagName = strtolower( $element );
if( isset( $this->mTransparentTagHooks[$tagName] ) ) {
$output = call_user_func_array( $this->mTransparentTagHooks[$tagName],
array( $content, $params, $this ) );
} else {
$output = $tag;
}
$this->mStripState->general->setPair( $marker, $output );
}
$text = $this->mStripState->unstripGeneral( $text );
$text = Sanitizer::normalizeCharReferences( $text );
if ( ( $wgUseTidy && $this->mOptions->mTidy ) || $wgAlwaysUseTidy ) {
$text = MWTidy::tidy( $text );
} else {
# attempt to sanitize at least some nesting problems
# (bug #2702 and quite a few others)
$tidyregs = array(
# ''Something [http://www.cool.com cool''] -->
# <i>Something</i><a href="http://www.cool.com"..><i>cool></i></a>
'/(<([bi])>)(<([bi])>)?([^<]*)(<\/?a[^<]*>)([^<]*)(<\/\\4>)?(<\/\\2>)/' =>
'\\1\\3\\5\\8\\9\\6\\1\\3\\7\\8\\9',
# fix up an anchor inside another anchor, only
# at least for a single single nested link (bug 3695)
'/(<a[^>]+>)([^<]*)(<a[^>]+>[^<]*)<\/a>(.*)<\/a>/' =>
'\\1\\2</a>\\3</a>\\1\\4</a>',
# fix div inside inline elements- doBlockLevels won't wrap a line which
# contains a div, so fix it up here; replace
# div with escaped text
'/(<([aib]) [^>]+>)([^<]*)(<div([^>]*)>)(.*)(<\/div>)([^<]*)(<\/\\2>)/' =>
'\\1\\3<div\\5>\\6</div>\\8\\9',
# remove empty italic or bold tag pairs, some
# introduced by rules above
'/<([bi])><\/\\1>/' => '',
);
$text = preg_replace(
array_keys( $tidyregs ),
array_values( $tidyregs ),
$text );
}
global $wgExpensiveParserFunctionLimit;
if ( $this->mExpensiveFunctionCount > $wgExpensiveParserFunctionLimit ) {
$this->limitationWarn( 'expensive-parserfunction', $this->mExpensiveFunctionCount, $wgExpensiveParserFunctionLimit );
}
wfRunHooks( 'ParserAfterTidy', array( &$this, &$text ) );
# Information on include size limits, for the benefit of users who try to skirt them
if ( $this->mOptions->getEnableLimitReport() ) {
$max = $this->mOptions->getMaxIncludeSize();
$PFreport = "Expensive parser function count: {$this->mExpensiveFunctionCount}/$wgExpensiveParserFunctionLimit\n";
$limitReport =
"NewPP limit report\n" .
"Preprocessor node count: {$this->mPPNodeCount}/{$this->mOptions->mMaxPPNodeCount}\n" .
"Post-expand include size: {$this->mIncludeSizes['post-expand']}/$max bytes\n" .
"Template argument size: {$this->mIncludeSizes['arg']}/$max bytes\n".
$PFreport;
wfRunHooks( 'ParserLimitReport', array( $this, &$limitReport ) );
$text .= "\n<!-- \n$limitReport-->\n";
}
$this->mOutput->setText( $text );
$this->mRevisionId = $oldRevisionId;
$this->mRevisionTimestamp = $oldRevisionTimestamp;
wfProfileOut( $fname );
wfProfileOut( __METHOD__ );
return $this->mOutput;
}
/**
* Recursive parser entry point that can be called from an extension tag
* hook.
*
* If $frame is not provided, then template variables (e.g., {{{1}}}) within $text are not expanded
*
* @param $text String: text extension wants to have parsed
* @param PPFrame $frame: The frame to use for expanding any template variables
*/
function recursiveTagParse( $text, $frame=false ) {
wfProfileIn( __METHOD__ );
wfRunHooks( 'ParserBeforeStrip', array( &$this, &$text, &$this->mStripState ) );
wfRunHooks( 'ParserAfterStrip', array( &$this, &$text, &$this->mStripState ) );
$text = $this->internalParse( $text, false, $frame );
wfProfileOut( __METHOD__ );
return $text;
}
/**
* Expand templates and variables in the text, producing valid, static wikitext.
* Also removes comments.
*/
function preprocess( $text, $title, $options, $revid = null ) {
wfProfileIn( __METHOD__ );
$this->clearState();
$this->setOutputType( self::OT_PREPROCESS );
$this->mOptions = $options;
$this->setTitle( $title );
if( $revid !== null ) {
$this->mRevisionId = $revid;
}
wfRunHooks( 'ParserBeforeStrip', array( &$this, &$text, &$this->mStripState ) );
wfRunHooks( 'ParserAfterStrip', array( &$this, &$text, &$this->mStripState ) );
$text = $this->replaceVariables( $text );
$text = $this->mStripState->unstripBoth( $text );
wfProfileOut( __METHOD__ );
return $text;
}
/**
* Get a random string
*
* @private
* @static
*/
function getRandomString() {
return dechex(mt_rand(0, 0x7fffffff)) . dechex(mt_rand(0, 0x7fffffff));
}
function &getTitle() { return $this->mTitle; }
function getOptions() { return $this->mOptions; }
function getRevisionId() { return $this->mRevisionId; }
function getOutput() { return $this->mOutput; }
function nextLinkID() { return $this->mLinkID++; }
function getFunctionLang() {
global $wgLang, $wgContLang;
$target = $this->mOptions->getTargetLanguage();
if ( $target !== null ) {
return $target;
} else {
return $this->mOptions->getInterfaceMessage() ? $wgLang : $wgContLang;
}
}
/**
* Get a preprocessor object
*/
function getPreprocessor() {
if ( !isset( $this->mPreprocessor ) ) {
$class = $this->mPreprocessorClass;
$this->mPreprocessor = new $class( $this );
}
return $this->mPreprocessor;
}
/**
* Replaces all occurrences of HTML-style comments and the given tags
* in the text with a random marker and returns the next text. The output
* parameter $matches will be an associative array filled with data in
* the form:
* 'UNIQ-xxxxx' => array(
* 'element',
* 'tag content',
* array( 'param' => 'x' ),
* '<element param="x">tag content</element>' ) )
*
* @param $elements list of element names. Comments are always extracted.
* @param $text Source text string.
* @param $uniq_prefix
*
* @public
* @static
*/
function extractTagsAndParams($elements, $text, &$matches, $uniq_prefix = ''){
static $n = 1;
$stripped = '';
$matches = array();
$taglist = implode( '|', $elements );
$start = "/<($taglist)(\\s+[^>]*?|\\s*?)(\/?" . ">)|<(!--)/i";
while ( $text != '' ) {
$p = preg_split( $start, $text, 2, PREG_SPLIT_DELIM_CAPTURE );
$stripped .= $p[0];
if( count( $p ) < 5 ) {
break;
}
if( count( $p ) > 5 ) {
// comment
$element = $p[4];
$attributes = '';
$close = '';
$inside = $p[5];
} else {
// tag
$element = $p[1];
$attributes = $p[2];
$close = $p[3];
$inside = $p[4];
}
$marker = "$uniq_prefix-$element-" . sprintf('%08X', $n++) . self::MARKER_SUFFIX;
$stripped .= $marker;
if ( $close === '/>' ) {
// Empty element tag, <tag />
$content = null;
$text = $inside;
$tail = null;
} else {
if( $element === '!--' ) {
$end = '/(-->)/';
} else {
$end = "/(<\\/$element\\s*>)/i";
}
$q = preg_split( $end, $inside, 2, PREG_SPLIT_DELIM_CAPTURE );
$content = $q[0];
if( count( $q ) < 3 ) {
# No end tag -- let it run out to the end of the text.
$tail = '';
$text = '';
} else {
$tail = $q[1];
$text = $q[2];
}
}
$matches[$marker] = array( $element,
$content,
Sanitizer::decodeTagAttributes( $attributes ),
"<$element$attributes$close$content$tail" );
}
return $stripped;
}
/**
* Get a list of strippable XML-like elements
*/
function getStripList() {
return $this->mStripList;
}
/**
* @deprecated use replaceVariables
*/
function strip( $text, $state, $stripcomments = false , $dontstrip = array () ) {
return $text;
}
/**
* Restores pre, math, and other extensions removed by strip()
*
* always call unstripNoWiki() after this one
* @private
* @deprecated use $this->mStripState->unstrip()
*/
function unstrip( $text, $state ) {
return $state->unstripGeneral( $text );
}
/**
* Always call this after unstrip() to preserve the order
*
* @private
* @deprecated use $this->mStripState->unstrip()
*/
function unstripNoWiki( $text, $state ) {
return $state->unstripNoWiki( $text );
}
/**
* @deprecated use $this->mStripState->unstripBoth()
*/
function unstripForHTML( $text ) {
return $this->mStripState->unstripBoth( $text );
}
/**
* Add an item to the strip state
* Returns the unique tag which must be inserted into the stripped text
* The tag will be replaced with the original text in unstrip()
*
* @private
*/
function insertStripItem( $text ) {
$rnd = "{$this->mUniqPrefix}-item-{$this->mMarkerIndex}-" . self::MARKER_SUFFIX;
$this->mMarkerIndex++;
$this->mStripState->general->setPair( $rnd, $text );
return $rnd;
}
/**
* Interface with html tidy
* @deprecated Use MWTidy::tidy()
*/
public static function tidy( $text ) {
wfDeprecated( __METHOD__ );
return MWTidy::tidy( $text );
}
/**
* parse the wiki syntax used to render tables
*
* @private
*/
function doTableStuff ( $text ) {
wfProfileIn( __METHOD__ );
$lines = StringUtils::explode( "\n", $text );
$out = '';
$td_history = array (); // Is currently a td tag open?
$last_tag_history = array (); // Save history of last lag activated (td, th or caption)
$tr_history = array (); // Is currently a tr tag open?
$tr_attributes = array (); // history of tr attributes
$has_opened_tr = array(); // Did this table open a <tr> element?
$indent_level = 0; // indent level of the table
foreach ( $lines as $outLine ) {
$line = trim( $outLine );
if( $line == '' ) { // empty line, go to next line
$out .= $outLine."\n";
continue;
}
$first_character = $line[0];
$matches = array();
if ( preg_match( '/^(:*)\{\|(.*)$/', $line , $matches ) ) {
// First check if we are starting a new table
$indent_level = strlen( $matches[1] );
$attributes = $this->mStripState->unstripBoth( $matches[2] );
$attributes = Sanitizer::fixTagAttributes ( $attributes , 'table' );
$outLine = str_repeat( '<dl><dd>' , $indent_level ) . "<table{$attributes}>";
array_push( $td_history , false );
array_push( $last_tag_history , '' );
array_push( $tr_history , false );
array_push( $tr_attributes , '' );
array_push( $has_opened_tr , false );
} else if ( count ( $td_history ) == 0 ) {
// Don't do any of the following
$out .= $outLine."\n";
continue;
} else if ( substr ( $line , 0 , 2 ) === '|}' ) {
// We are ending a table
$line = '</table>' . substr ( $line , 2 );
$last_tag = array_pop ( $last_tag_history );
if ( !array_pop ( $has_opened_tr ) ) {
$line = "<tr><td></td></tr>{$line}";
}
if ( array_pop ( $tr_history ) ) {
$line = "</tr>{$line}";
}
if ( array_pop ( $td_history ) ) {
$line = "</{$last_tag}>{$line}";
}
array_pop ( $tr_attributes );
$outLine = $line . str_repeat( '</dd></dl>' , $indent_level );
} else if ( substr ( $line , 0 , 2 ) === '|-' ) {
// Now we have a table row
$line = preg_replace( '#^\|-+#', '', $line );
// Whats after the tag is now only attributes
$attributes = $this->mStripState->unstripBoth( $line );
$attributes = Sanitizer::fixTagAttributes( $attributes, 'tr' );
array_pop( $tr_attributes );
array_push( $tr_attributes, $attributes );
$line = '';
$last_tag = array_pop ( $last_tag_history );
array_pop ( $has_opened_tr );
array_push ( $has_opened_tr , true );
if ( array_pop ( $tr_history ) ) {
$line = '</tr>';
}
if ( array_pop ( $td_history ) ) {
$line = "</{$last_tag}>{$line}";
}
$outLine = $line;
array_push ( $tr_history , false );
array_push ( $td_history , false );
array_push ( $last_tag_history , '' );
}
else if ( $first_character === '|' || $first_character === '!' || substr ( $line , 0 , 2 ) === '|+' ) {
// This might be cell elements, td, th or captions
if ( substr ( $line , 0 , 2 ) === '|+' ) {
$first_character = '+';
$line = substr ( $line , 1 );
}
$line = substr ( $line , 1 );
if ( $first_character === '!' ) {
$line = str_replace ( '!!' , '||' , $line );
}
// Split up multiple cells on the same line.
// FIXME : This can result in improper nesting of tags processed
// by earlier parser steps, but should avoid splitting up eg
// attribute values containing literal "||".
$cells = StringUtils::explodeMarkup( '||' , $line );
$outLine = '';
// Loop through each table cell
foreach ( $cells as $cell )
{
$previous = '';
if ( $first_character !== '+' )
{
$tr_after = array_pop ( $tr_attributes );
if ( !array_pop ( $tr_history ) ) {
$previous = "<tr{$tr_after}>\n";
}
array_push ( $tr_history , true );
array_push ( $tr_attributes , '' );
array_pop ( $has_opened_tr );
array_push ( $has_opened_tr , true );
}
$last_tag = array_pop ( $last_tag_history );
if ( array_pop ( $td_history ) ) {
$previous = "</{$last_tag}>{$previous}";
}
if ( $first_character === '|' ) {
$last_tag = 'td';
} else if ( $first_character === '!' ) {
$last_tag = 'th';
} else if ( $first_character === '+' ) {
$last_tag = 'caption';
} else {
$last_tag = '';
}
array_push ( $last_tag_history , $last_tag );
// A cell could contain both parameters and data
$cell_data = explode ( '|' , $cell , 2 );
// Bug 553: Note that a '|' inside an invalid link should not
// be mistaken as delimiting cell parameters
if ( strpos( $cell_data[0], '[[' ) !== false ) {
$cell = "{$previous}<{$last_tag}>{$cell}";
} else if ( count ( $cell_data ) == 1 )
$cell = "{$previous}<{$last_tag}>{$cell_data[0]}";
else {
$attributes = $this->mStripState->unstripBoth( $cell_data[0] );
$attributes = Sanitizer::fixTagAttributes( $attributes , $last_tag );
$cell = "{$previous}<{$last_tag}{$attributes}>{$cell_data[1]}";
}
$outLine .= $cell;
array_push ( $td_history , true );
}
}
$out .= $outLine . "\n";
}
// Closing open td, tr && table
while ( count ( $td_history ) > 0 )
{
if ( array_pop ( $td_history ) ) {
$out .= "</td>\n";
}
if ( array_pop ( $tr_history ) ) {
$out .= "</tr>\n";
}
if ( !array_pop ( $has_opened_tr ) ) {
$out .= "<tr><td></td></tr>\n" ;
}
$out .= "</table>\n";
}
// Remove trailing line-ending (b/c)
if ( substr( $out, -1 ) === "\n" ) {
$out = substr( $out, 0, -1 );
}
// special case: don't return empty table
if( $out === "<table>\n<tr><td></td></tr>\n</table>" ) {
$out = '';
}
wfProfileOut( __METHOD__ );
return $out;
}
/**
* Helper function for parse() that transforms wiki markup into
* HTML. Only called for $mOutputType == self::OT_HTML.
*
* @private
*/
function internalParse( $text, $isMain = true, $frame=false ) {
wfProfileIn( __METHOD__ );
$origText = $text;
# Hook to suspend the parser in this state
if ( !wfRunHooks( 'ParserBeforeInternalParse', array( &$this, &$text, &$this->mStripState ) ) ) {
wfProfileOut( __METHOD__ );
return $text ;
}
// if $frame is provided, then use $frame for replacing any variables
if ($frame) {
// use frame depth to infer how include/noinclude tags should be handled
// depth=0 means this is the top-level document; otherwise it's an included document
if( !$frame->depth )
$flag = 0;
else
$flag = Parser::PTD_FOR_INCLUSION;
$dom = $this->preprocessToDom( $text, $flag );
$text = $frame->expand( $dom );
}
// if $frame is not provided, then use old-style replaceVariables
else {
$text = $this->replaceVariables( $text );
}
$text = Sanitizer::removeHTMLtags( $text, array( &$this, 'attributeStripCallback' ), false, array_keys( $this->mTransparentTagHooks ) );
wfRunHooks( 'InternalParseBeforeLinks', array( &$this, &$text, &$this->mStripState ) );
// Tables need to come after variable replacement for things to work
// properly; putting them before other transformations should keep
// exciting things like link expansions from showing up in surprising
// places.
$text = $this->doTableStuff( $text );
$text = preg_replace( '/(^|\n)-----*/', '\\1<hr />', $text );
$text = $this->doDoubleUnderscore( $text );
$text = $this->doHeadings( $text );
if( $this->mOptions->getUseDynamicDates() ) {
$df = DateFormatter::getInstance();
$text = $df->reformat( $this->mOptions->getDateFormat(), $text );
}
$text = $this->doAllQuotes( $text );
$text = $this->replaceInternalLinks( $text );
$text = $this->replaceExternalLinks( $text );
# replaceInternalLinks may sometimes leave behind
# absolute URLs, which have to be masked to hide them from replaceExternalLinks
$text = str_replace($this->mUniqPrefix.'NOPARSE', '', $text);
$text = $this->doMagicLinks( $text );
$text = $this->formatHeadings( $text, $origText, $isMain );
wfProfileOut( __METHOD__ );
return $text;
}
/**
* Replace special strings like "ISBN xxx" and "RFC xxx" with
* magic external links.
*
* DML
* @private
*/
function doMagicLinks( $text ) {
wfProfileIn( __METHOD__ );
$prots = $this->mUrlProtocols;
$urlChar = self::EXT_LINK_URL_CLASS;
$text = preg_replace_callback(
'!(?: # Start cases
(<a.*?</a>) | # m[1]: Skip link text
(<.*?>) | # m[2]: Skip stuff inside HTML elements' . "
(\\b(?:$prots)$urlChar+) | # m[3]: Free external links" . '
(?:RFC|PMID)\s+([0-9]+) | # m[4]: RFC or PMID, capture number
ISBN\s+(\b # m[5]: ISBN, capture number
(?: 97[89] [\ \-]? )? # optional 13-digit ISBN prefix
(?: [0-9] [\ \-]? ){9} # 9 digits with opt. delimiters
[0-9Xx] # check digit
\b)
)!x', array( &$this, 'magicLinkCallback' ), $text );
wfProfileOut( __METHOD__ );
return $text;
}
function magicLinkCallback( $m ) {
if ( isset( $m[1] ) && $m[1] !== '' ) {
# Skip anchor
return $m[0];
} elseif ( isset( $m[2] ) && $m[2] !== '' ) {
# Skip HTML element
return $m[0];
} elseif ( isset( $m[3] ) && $m[3] !== '' ) {
# Free external link
return $this->makeFreeExternalLink( $m[0] );
} elseif ( isset( $m[4] ) && $m[4] !== '' ) {
# RFC or PMID
$CssClass = '';
if ( substr( $m[0], 0, 3 ) === 'RFC' ) {
$keyword = 'RFC';
$urlmsg = 'rfcurl';
$CssClass = 'mw-magiclink-rfc';
$id = $m[4];
} elseif ( substr( $m[0], 0, 4 ) === 'PMID' ) {
$keyword = 'PMID';
$urlmsg = 'pubmedurl';
$CssClass = 'mw-magiclink-pmid';
$id = $m[4];
} else {
throw new MWException( __METHOD__.': unrecognised match type "' .
substr($m[0], 0, 20 ) . '"' );
}
$url = wfMsg( $urlmsg, $id);
$sk = $this->mOptions->getSkin();
$la = $sk->getExternalLinkAttributes( "external $CssClass" );
return "<a href=\"{$url}\"{$la}>{$keyword} {$id}</a>";
} elseif ( isset( $m[5] ) && $m[5] !== '' ) {
# ISBN
$isbn = $m[5];
$num = strtr( $isbn, array(
'-' => '',
' ' => '',
'x' => 'X',
));
$titleObj = SpecialPage::getTitleFor( 'Booksources', $num );
return'<a href="' .
$titleObj->escapeLocalUrl() .
"\" class=\"internal mw-magiclink-isbn\">ISBN $isbn</a>";
} else {
return $m[0];
}
}
/**
* Make a free external link, given a user-supplied URL
* @return HTML
* @private
*/
function makeFreeExternalLink( $url ) {
global $wgContLang;
wfProfileIn( __METHOD__ );
$sk = $this->mOptions->getSkin();
$trail = '';
# The characters '<' and '>' (which were escaped by
# removeHTMLtags()) should not be included in
# URLs, per RFC 2396.
$m2 = array();
if (preg_match('/&(lt|gt);/', $url, $m2, PREG_OFFSET_CAPTURE)) {
$trail = substr($url, $m2[0][1]) . $trail;
$url = substr($url, 0, $m2[0][1]);
}
# Move trailing punctuation to $trail
$sep = ',;\.:!?';
# If there is no left bracket, then consider right brackets fair game too
if ( strpos( $url, '(' ) === false ) {
$sep .= ')';
}
$numSepChars = strspn( strrev( $url ), $sep );
if ( $numSepChars ) {
$trail = substr( $url, -$numSepChars ) . $trail;
$url = substr( $url, 0, -$numSepChars );
}
$url = Sanitizer::cleanUrl( $url );
# Is this an external image?
$text = $this->maybeMakeExternalImage( $url );
if ( $text === false ) {
# Not an image, make a link
$text = $sk->makeExternalLink( $url, $wgContLang->markNoConversion($url), true, 'free',
$this->getExternalLinkAttribs( $url ) );
# Register it in the output object...
# Replace unnecessary URL escape codes with their equivalent characters
$pasteurized = self::replaceUnusualEscapes( $url );
$this->mOutput->addExternalLink( $pasteurized );
}
wfProfileOut( __METHOD__ );
return $text . $trail;
}
/**
* Parse headers and return html
*
* @private
*/
function doHeadings( $text ) {
wfProfileIn( __METHOD__ );
for ( $i = 6; $i >= 1; --$i ) {
$h = str_repeat( '=', $i );
$text = preg_replace( "/^$h(.+)$h\\s*$/m",
"<h$i>\\1</h$i>", $text );
}
wfProfileOut( __METHOD__ );
return $text;
}
/**
* Replace single quotes with HTML markup
* @private
* @return string the altered text
*/
function doAllQuotes( $text ) {
wfProfileIn( __METHOD__ );
$outtext = '';
$lines = StringUtils::explode( "\n", $text );
foreach ( $lines as $line ) {
$outtext .= $this->doQuotes( $line ) . "\n";
}
$outtext = substr($outtext, 0,-1);
wfProfileOut( __METHOD__ );
return $outtext;
}
/**
* Helper function for doAllQuotes()
*/
public function doQuotes( $text ) {
$arr = preg_split( "/(''+)/", $text, -1, PREG_SPLIT_DELIM_CAPTURE );
if ( count( $arr ) == 1 )
return $text;
else
{
# First, do some preliminary work. This may shift some apostrophes from
# being mark-up to being text. It also counts the number of occurrences
# of bold and italics mark-ups.
$i = 0;
$numbold = 0;
$numitalics = 0;
foreach ( $arr as $r )
{
if ( ( $i % 2 ) == 1 )
{
# If there are ever four apostrophes, assume the first is supposed to
# be text, and the remaining three constitute mark-up for bold text.
if ( strlen( $arr[$i] ) == 4 )
{
$arr[$i-1] .= "'";
$arr[$i] = "'''";
}
# If there are more than 5 apostrophes in a row, assume they're all
# text except for the last 5.
else if ( strlen( $arr[$i] ) > 5 )
{
$arr[$i-1] .= str_repeat( "'", strlen( $arr[$i] ) - 5 );
$arr[$i] = "'''''";
}
# Count the number of occurrences of bold and italics mark-ups.
# We are not counting sequences of five apostrophes.
if ( strlen( $arr[$i] ) == 2 ) { $numitalics++; }
else if ( strlen( $arr[$i] ) == 3 ) { $numbold++; }
else if ( strlen( $arr[$i] ) == 5 ) { $numitalics++; $numbold++; }
}
$i++;
}
# If there is an odd number of both bold and italics, it is likely
# that one of the bold ones was meant to be an apostrophe followed
# by italics. Which one we cannot know for certain, but it is more
# likely to be one that has a single-letter word before it.
if ( ( $numbold % 2 == 1 ) && ( $numitalics % 2 == 1 ) )
{
$i = 0;
$firstsingleletterword = -1;
$firstmultiletterword = -1;
$firstspace = -1;
foreach ( $arr as $r )
{
if ( ( $i % 2 == 1 ) and ( strlen( $r ) == 3 ) )
{
$x1 = substr ($arr[$i-1], -1);
$x2 = substr ($arr[$i-1], -2, 1);
if ($x1 === ' ') {
if ($firstspace == -1) $firstspace = $i;
} else if ($x2 === ' ') {
if ($firstsingleletterword == -1) $firstsingleletterword = $i;
} else {
if ($firstmultiletterword == -1) $firstmultiletterword = $i;
}
}
$i++;
}
# If there is a single-letter word, use it!
if ($firstsingleletterword > -1)
{
$arr [ $firstsingleletterword ] = "''";
$arr [ $firstsingleletterword-1 ] .= "'";
}
# If not, but there's a multi-letter word, use that one.
else if ($firstmultiletterword > -1)
{
$arr [ $firstmultiletterword ] = "''";
$arr [ $firstmultiletterword-1 ] .= "'";
}
# ... otherwise use the first one that has neither.
# (notice that it is possible for all three to be -1 if, for example,
# there is only one pentuple-apostrophe in the line)
else if ($firstspace > -1)
{
$arr [ $firstspace ] = "''";
$arr [ $firstspace-1 ] .= "'";
}
}
# Now let's actually convert our apostrophic mush to HTML!
$output = '';
$buffer = '';
$state = '';
$i = 0;
foreach ($arr as $r)
{
if (($i % 2) == 0)
{
if ($state === 'both')
$buffer .= $r;
else
$output .= $r;
}
else
{
if (strlen ($r) == 2)
{
if ($state === 'i')
{ $output .= '</i>'; $state = ''; }
else if ($state === 'bi')
{ $output .= '</i>'; $state = 'b'; }
else if ($state === 'ib')
{ $output .= '</b></i><b>'; $state = 'b'; }
else if ($state === 'both')
{ $output .= '<b><i>'.$buffer.'</i>'; $state = 'b'; }
else # $state can be 'b' or ''
{ $output .= '<i>'; $state .= 'i'; }
}
else if (strlen ($r) == 3)
{
if ($state === 'b')
{ $output .= '</b>'; $state = ''; }
else if ($state === 'bi')
{ $output .= '</i></b><i>'; $state = 'i'; }
else if ($state === 'ib')
{ $output .= '</b>'; $state = 'i'; }
else if ($state === 'both')
{ $output .= '<i><b>'.$buffer.'</b>'; $state = 'i'; }
else # $state can be 'i' or ''
{ $output .= '<b>'; $state .= 'b'; }
}
else if (strlen ($r) == 5)
{
if ($state === 'b')
{ $output .= '</b><i>'; $state = 'i'; }
else if ($state === 'i')
{ $output .= '</i><b>'; $state = 'b'; }
else if ($state === 'bi')
{ $output .= '</i></b>'; $state = ''; }
else if ($state === 'ib')
{ $output .= '</b></i>'; $state = ''; }
else if ($state === 'both')
{ $output .= '<i><b>'.$buffer.'</b></i>'; $state = ''; }
else # ($state == '')
{ $buffer = ''; $state = 'both'; }
}
}
$i++;
}
# Now close all remaining tags. Notice that the order is important.
if ($state === 'b' || $state === 'ib')
$output .= '</b>';
if ($state === 'i' || $state === 'bi' || $state === 'ib')
$output .= '</i>';
if ($state === 'bi')
$output .= '</b>';
# There might be lonely ''''', so make sure we have a buffer
if ($state === 'both' && $buffer)
$output .= '<b><i>'.$buffer.'</i></b>';
return $output;
}
}
/**
* Replace external links (REL)
*
* Note: this is all very hackish and the order of execution matters a lot.
* Make sure to run maintenance/parserTests.php if you change this code.
*
* @private
*/
function replaceExternalLinks( $text ) {
global $wgContLang;
wfProfileIn( __METHOD__ );
$sk = $this->mOptions->getSkin();
$bits = preg_split( $this->mExtLinkBracketedRegex, $text, -1, PREG_SPLIT_DELIM_CAPTURE );
$s = array_shift( $bits );
$i = 0;
while ( $i<count( $bits ) ) {
$url = $bits[$i++];
$protocol = $bits[$i++];
$text = $bits[$i++];
$trail = $bits[$i++];
# The characters '<' and '>' (which were escaped by
# removeHTMLtags()) should not be included in
# URLs, per RFC 2396.
$m2 = array();
if (preg_match('/&(lt|gt);/', $url, $m2, PREG_OFFSET_CAPTURE)) {
$text = substr($url, $m2[0][1]) . ' ' . $text;
$url = substr($url, 0, $m2[0][1]);
}
# If the link text is an image URL, replace it with an <img> tag
# This happened by accident in the original parser, but some people used it extensively
$img = $this->maybeMakeExternalImage( $text );
if ( $img !== false ) {
$text = $img;
}
$dtrail = '';
# Set linktype for CSS - if URL==text, link is essentially free
$linktype = ($text === $url) ? 'free' : 'text';
# No link text, e.g. [http://domain.tld/some.link]
if ( $text == '' ) {
# Autonumber if allowed. See bug #5918
if ( strpos( wfUrlProtocols(), substr($protocol, 0, strpos($protocol, ':')) ) !== false ) {
$langObj = $this->getFunctionLang();
$text = '[' . $langObj->formatNum( ++$this->mAutonumber ) . ']';
$linktype = 'autonumber';
} else {
# Otherwise just use the URL
$text = htmlspecialchars( $url );
$linktype = 'free';
}
} else {
# Have link text, e.g. [http://domain.tld/some.link text]s
# Check for trail
list( $dtrail, $trail ) = Linker::splitTrail( $trail );
}
$text = $wgContLang->markNoConversion($text);
$url = Sanitizer::cleanUrl( $url );
# Use the encoded URL
# This means that users can paste URLs directly into the text
# Funny characters like ö aren't valid in URLs anyway
# This was changed in August 2004
$s .= $sk->makeExternalLink( $url, $text, false, $linktype,
$this->getExternalLinkAttribs( $url ) ) . $dtrail . $trail;
# Register link in the output object.
# Replace unnecessary URL escape codes with the referenced character
# This prevents spammers from hiding links from the filters
$pasteurized = self::replaceUnusualEscapes( $url );
$this->mOutput->addExternalLink( $pasteurized );
}
wfProfileOut( __METHOD__ );
return $s;
}
/**
* Get an associative array of additional HTML attributes appropriate for a
* particular external link. This currently may include rel => nofollow
* (depending on configuration, namespace, and the URL's domain) and/or a
* target attribute (depending on configuration).
*
* @param string $url Optional URL, to extract the domain from for rel =>
* nofollow if appropriate
* @return array Associative array of HTML attributes
*/
function getExternalLinkAttribs( $url = false ) {
$attribs = array();
global $wgNoFollowLinks, $wgNoFollowNsExceptions;
$ns = $this->mTitle->getNamespace();
if( $wgNoFollowLinks && !in_array($ns, $wgNoFollowNsExceptions) ) {
$attribs['rel'] = 'nofollow';
global $wgNoFollowDomainExceptions;
if ( $wgNoFollowDomainExceptions ) {
$bits = wfParseUrl( $url );
if ( is_array( $bits ) && isset( $bits['host'] ) ) {
foreach ( $wgNoFollowDomainExceptions as $domain ) {
if( substr( $bits['host'], -strlen( $domain ) )
== $domain ) {
unset( $attribs['rel'] );
break;
}
}
}
}
}
if ( $this->mOptions->getExternalLinkTarget() ) {
$attribs['target'] = $this->mOptions->getExternalLinkTarget();
}
return $attribs;
}
/**
* Replace unusual URL escape codes with their equivalent characters
* @param string
* @return string
* @static
* @todo This can merge genuinely required bits in the path or query string,
* breaking legit URLs. A proper fix would treat the various parts of
* the URL differently; as a workaround, just use the output for
* statistical records, not for actual linking/output.
*/
static function replaceUnusualEscapes( $url ) {
return preg_replace_callback( '/%[0-9A-Fa-f]{2}/',
array( __CLASS__, 'replaceUnusualEscapesCallback' ), $url );
}
/**
* Callback function used in replaceUnusualEscapes().
* Replaces unusual URL escape codes with their equivalent character
* @static
* @private
*/
private static function replaceUnusualEscapesCallback( $matches ) {
$char = urldecode( $matches[0] );
$ord = ord( $char );
// Is it an unsafe or HTTP reserved character according to RFC 1738?
if ( $ord > 32 && $ord < 127 && strpos( '<>"#{}|\^~[]`;/?', $char ) === false ) {
// No, shouldn't be escaped
return $char;
} else {
// Yes, leave it escaped
return $matches[0];
}
}
/**
* make an image if it's allowed, either through the global
* option, through the exception, or through the on-wiki whitelist
* @private
*/
function maybeMakeExternalImage( $url ) {
$sk = $this->mOptions->getSkin();
$imagesfrom = $this->mOptions->getAllowExternalImagesFrom();
$imagesexception = !empty($imagesfrom);
$text = false;
# $imagesfrom could be either a single string or an array of strings, parse out the latter
if( $imagesexception && is_array( $imagesfrom ) ) {
$imagematch = false;
foreach( $imagesfrom as $match ) {
if( strpos( $url, $match ) === 0 ) {
$imagematch = true;
break;
}
}
} elseif( $imagesexception ) {
$imagematch = (strpos( $url, $imagesfrom ) === 0);
} else {
$imagematch = false;
}
if ( $this->mOptions->getAllowExternalImages()
|| ( $imagesexception && $imagematch ) ) {
if ( preg_match( self::EXT_IMAGE_REGEX, $url ) ) {
# Image found
$text = $sk->makeExternalImage( $url );
}
}
if( !$text && $this->mOptions->getEnableImageWhitelist()
&& preg_match( self::EXT_IMAGE_REGEX, $url ) ) {
$whitelist = explode( "\n", wfMsgForContent( 'external_image_whitelist' ) );
foreach( $whitelist as $entry ) {
# Sanitize the regex fragment, make it case-insensitive, ignore blank entries/comments
if( strpos( $entry, '#' ) === 0 || $entry === '' )
continue;
if( preg_match( '/' . str_replace( '/', '\\/', $entry ) . '/i', $url ) ) {
# Image matches a whitelist entry
$text = $sk->makeExternalImage( $url );
break;
}
}
}
return $text;
}
/**
* Process [[ ]] wikilinks
* @return processed text
*
* @private
*/
function replaceInternalLinks( $s ) {
$this->mLinkHolders->merge( $this->replaceInternalLinks2( $s ) );
return $s;
}
/**
* Process [[ ]] wikilinks (RIL)
* @return LinkHolderArray
*
* @private
*/
function replaceInternalLinks2( &$s ) {
global $wgContLang;
wfProfileIn( __METHOD__ );
wfProfileIn( __METHOD__.'-setup' );
static $tc = FALSE, $e1, $e1_img;
# the % is needed to support urlencoded titles as well
if ( !$tc ) {
$tc = Title::legalChars() . '#%';
# Match a link having the form [[namespace:link|alternate]]trail
$e1 = "/^([{$tc}]+)(?:\\|(.+?))?]](.*)\$/sD";
# Match cases where there is no "]]", which might still be images
$e1_img = "/^([{$tc}]+)\\|(.*)\$/sD";
}
$sk = $this->mOptions->getSkin();
$holders = new LinkHolderArray( $this );
#split the entire text string on occurences of [[
$a = StringUtils::explode( '[[', ' ' . $s );
#get the first element (all text up to first [[), and remove the space we added
$s = $a->current();
$a->next();
$line = $a->current(); # Workaround for broken ArrayIterator::next() that returns "void"
$s = substr( $s, 1 );
$useLinkPrefixExtension = $wgContLang->linkPrefixExtension();
$e2 = null;
if ( $useLinkPrefixExtension ) {
# Match the end of a line for a word that's not followed by whitespace,
# e.g. in the case of 'The Arab al[[Razi]]', 'al' will be matched
$e2 = wfMsgForContent( 'linkprefix' );
}
if( is_null( $this->mTitle ) ) {
wfProfileOut( __METHOD__.'-setup' );
wfProfileOut( __METHOD__ );
throw new MWException( __METHOD__.": \$this->mTitle is null\n" );
}
$nottalk = !$this->mTitle->isTalkPage();
if ( $useLinkPrefixExtension ) {
$m = array();
if ( preg_match( $e2, $s, $m ) ) {
$first_prefix = $m[2];
} else {
$first_prefix = false;
}
} else {
$prefix = '';
}
if($wgContLang->hasVariants()) {
$selflink = $wgContLang->convertLinkToAllVariants($this->mTitle->getPrefixedText());
} else {
$selflink = array($this->mTitle->getPrefixedText());
}
$useSubpages = $this->areSubpagesAllowed();
wfProfileOut( __METHOD__.'-setup' );
# Loop for each link
for ( ; $line !== false && $line !== null ; $a->next(), $line = $a->current() ) {
# Check for excessive memory usage
if ( $holders->isBig() ) {
# Too big
# Do the existence check, replace the link holders and clear the array
$holders->replace( $s );
$holders->clear();
}
if ( $useLinkPrefixExtension ) {
wfProfileIn( __METHOD__.'-prefixhandling' );
if ( preg_match( $e2, $s, $m ) ) {
$prefix = $m[2];
$s = $m[1];
} else {
$prefix='';
}
# first link
if($first_prefix) {
$prefix = $first_prefix;
$first_prefix = false;
}
wfProfileOut( __METHOD__.'-prefixhandling' );
}
$might_be_img = false;
wfProfileIn( __METHOD__."-e1" );
if ( preg_match( $e1, $line, $m ) ) { # page with normal text or alt
$text = $m[2];
# If we get a ] at the beginning of $m[3] that means we have a link that's something like:
# [[Image:Foo.jpg|[http://example.com desc]]] <- having three ] in a row fucks up,
# the real problem is with the $e1 regex
# See bug 1300.
#
# Still some problems for cases where the ] is meant to be outside punctuation,
# and no image is in sight. See bug 2095.
#
if( $text !== '' &&
substr( $m[3], 0, 1 ) === ']' &&
strpos($text, '[') !== false
)
{
$text .= ']'; # so that replaceExternalLinks($text) works later
$m[3] = substr( $m[3], 1 );
}
# fix up urlencoded title texts
if( strpos( $m[1], '%' ) !== false ) {
# Should anchors '#' also be rejected?
$m[1] = str_replace( array('<', '>'), array('<', '>'), urldecode($m[1]) );
}
$trail = $m[3];
} elseif( preg_match($e1_img, $line, $m) ) { # Invalid, but might be an image with a link in its caption
$might_be_img = true;
$text = $m[2];
if ( strpos( $m[1], '%' ) !== false ) {
$m[1] = urldecode($m[1]);
}
$trail = "";
} else { # Invalid form; output directly
$s .= $prefix . '[[' . $line ;
wfProfileOut( __METHOD__."-e1" );
continue;
}
wfProfileOut( __METHOD__."-e1" );
wfProfileIn( __METHOD__."-misc" );
# Don't allow internal links to pages containing
# PROTO: where PROTO is a valid URL protocol; these
# should be external links.
if ( preg_match( '/^\b(?:' . wfUrlProtocols() . ')/', $m[1] ) ) {
$s .= $prefix . '[[' . $line ;
wfProfileOut( __METHOD__."-misc" );
continue;
}
# Make subpage if necessary
if ( $useSubpages ) {
$link = $this->maybeDoSubpageLink( $m[1], $text );
} else {
$link = $m[1];
}
$noforce = (substr( $m[1], 0, 1 ) !== ':');
if (!$noforce) {
# Strip off leading ':'
$link = substr( $link, 1 );
}
wfProfileOut( __METHOD__."-misc" );
wfProfileIn( __METHOD__."-title" );
$nt = Title::newFromText( $this->mStripState->unstripNoWiki( $link ) );
if ( $nt === null ) {
$s .= $prefix . '[[' . $line;
wfProfileOut( __METHOD__."-title" );
continue;
}
$ns = $nt->getNamespace();
$iw = $nt->getInterWiki();
wfProfileOut( __METHOD__."-title" );
if ( $might_be_img ) { # if this is actually an invalid link
wfProfileIn( __METHOD__."-might_be_img" );
if ( $ns == NS_FILE && $noforce ) { #but might be an image
$found = false;
while ( true ) {
#look at the next 'line' to see if we can close it there
$a->next();
$next_line = $a->current();
if ( $next_line === false || $next_line === null ) {
break;
}
$m = explode( ']]', $next_line, 3 );
if ( count( $m ) == 3 ) {
# the first ]] closes the inner link, the second the image
$found = true;
$text .= "[[{$m[0]}]]{$m[1]}";
$trail = $m[2];
break;
} elseif ( count( $m ) == 2 ) {
#if there's exactly one ]] that's fine, we'll keep looking
$text .= "[[{$m[0]}]]{$m[1]}";
} else {
#if $next_line is invalid too, we need look no further
$text .= '[[' . $next_line;
break;
}
}
if ( !$found ) {
# we couldn't find the end of this imageLink, so output it raw
#but don't ignore what might be perfectly normal links in the text we've examined
$holders->merge( $this->replaceInternalLinks2( $text ) );
$s .= "{$prefix}[[$link|$text";
# note: no $trail, because without an end, there *is* no trail
wfProfileOut( __METHOD__."-might_be_img" );
continue;
}
} else { #it's not an image, so output it raw
$s .= "{$prefix}[[$link|$text";
# note: no $trail, because without an end, there *is* no trail
wfProfileOut( __METHOD__."-might_be_img" );
continue;
}
wfProfileOut( __METHOD__."-might_be_img" );
}
$wasblank = ( $text == '' );
if ( $wasblank ) $text = $link;
# Link not escaped by : , create the various objects
if ( $noforce ) {
# Interwikis
wfProfileIn( __METHOD__."-interwiki" );
if ( $iw && $this->mOptions->getInterwikiMagic() && $nottalk && $wgContLang->getLanguageName( $iw ) ) {
$this->mOutput->addLanguageLink( $nt->getFullText() );
$s = rtrim($s . $prefix);
$s .= trim($trail, "\n") == '' ? '': $prefix . $trail;
wfProfileOut( __METHOD__."-interwiki" );
continue;
}
wfProfileOut( __METHOD__."-interwiki" );
if ( $ns == NS_FILE ) {
wfProfileIn( __METHOD__."-image" );
if ( !wfIsBadImage( $nt->getDBkey(), $this->mTitle ) ) {
if ( $wasblank ) {
# if no parameters were passed, $text
# becomes something like "File:Foo.png",
# which we don't want to pass on to the
# image generator
$text = '';
} else {
# recursively parse links inside the image caption
# actually, this will parse them in any other parameters, too,
# but it might be hard to fix that, and it doesn't matter ATM
$text = $this->replaceExternalLinks($text);
$holders->merge( $this->replaceInternalLinks2( $text ) );
}
# cloak any absolute URLs inside the image markup, so replaceExternalLinks() won't touch them
$s .= $prefix . $this->armorLinks( $this->makeImage( $nt, $text, $holders ) ) . $trail;
} else {
$s .= $prefix . $trail;
}
$this->mOutput->addImage( $nt->getDBkey() );
wfProfileOut( __METHOD__."-image" );
continue;
}
if ( $ns == NS_CATEGORY ) {
wfProfileIn( __METHOD__."-category" );
$s = rtrim($s . "\n"); # bug 87
if ( $wasblank ) {
$sortkey = $this->getDefaultSort();
} else {
$sortkey = $text;
}
$sortkey = Sanitizer::decodeCharReferences( $sortkey );
$sortkey = str_replace( "\n", '', $sortkey );
$sortkey = $wgContLang->convertCategoryKey( $sortkey );
$this->mOutput->addCategory( $nt->getDBkey(), $sortkey );
/**
* Strip the whitespace Category links produce, see bug 87
* @todo We might want to use trim($tmp, "\n") here.
*/
$s .= trim($prefix . $trail, "\n") == '' ? '': $prefix . $trail;
wfProfileOut( __METHOD__."-category" );
continue;
}
}
# Self-link checking
if( $nt->getFragment() === '' && $ns != NS_SPECIAL ) {
if( in_array( $nt->getPrefixedText(), $selflink, true ) ) {
$s .= $prefix . $sk->makeSelfLinkObj( $nt, $text, '', $trail );
continue;
}
}
# NS_MEDIA is a pseudo-namespace for linking directly to a file
# FIXME: Should do batch file existence checks, see comment below
if( $ns == NS_MEDIA ) {
wfProfileIn( __METHOD__."-media" );
# Give extensions a chance to select the file revision for us
$skip = $time = false;
wfRunHooks( 'BeforeParserMakeImageLinkObj', array( &$this, &$nt, &$skip, &$time ) );
if ( $skip ) {
$link = $sk->link( $nt );
} else {
$link = $sk->makeMediaLinkObj( $nt, $text, $time );
}
# Cloak with NOPARSE to avoid replacement in replaceExternalLinks
$s .= $prefix . $this->armorLinks( $link ) . $trail;
$this->mOutput->addImage( $nt->getDBkey() );
wfProfileOut( __METHOD__."-media" );
continue;
}
wfProfileIn( __METHOD__."-always_known" );
# Some titles, such as valid special pages or files in foreign repos, should
# be shown as bluelinks even though they're not included in the page table
#
# FIXME: isAlwaysKnown() can be expensive for file links; we should really do
# batch file existence checks for NS_FILE and NS_MEDIA
if( $iw == '' && $nt->isAlwaysKnown() ) {
$this->mOutput->addLink( $nt );
$s .= $this->makeKnownLinkHolder( $nt, $text, '', $trail, $prefix );
} else {
# Links will be added to the output link list after checking
$s .= $holders->makeHolder( $nt, $text, '', $trail, $prefix );
}
wfProfileOut( __METHOD__."-always_known" );
}
wfProfileOut( __METHOD__ );
return $holders;
}
/**
* Make a link placeholder. The text returned can be later resolved to a real link with
* replaceLinkHolders(). This is done for two reasons: firstly to avoid further
* parsing of interwiki links, and secondly to allow all existence checks and
* article length checks (for stub links) to be bundled into a single query.
*
* @deprecated
*/
function makeLinkHolder( &$nt, $text = '', $query = '', $trail = '', $prefix = '' ) {
return $this->mLinkHolders->makeHolder( $nt, $text, $query, $trail, $prefix );
}
/**
* Render a forced-blue link inline; protect against double expansion of
* URLs if we're in a mode that prepends full URL prefixes to internal links.
* Since this little disaster has to split off the trail text to avoid
* breaking URLs in the following text without breaking trails on the
* wiki links, it's been made into a horrible function.
*
* @param Title $nt
* @param string $text
* @param string $query
* @param string $trail
* @param string $prefix
* @return string HTML-wikitext mix oh yuck
*/
function makeKnownLinkHolder( $nt, $text = '', $query = '', $trail = '', $prefix = '' ) {
list( $inside, $trail ) = Linker::splitTrail( $trail );
$sk = $this->mOptions->getSkin();
// FIXME: use link() instead of deprecated makeKnownLinkObj()
$link = $sk->makeKnownLinkObj( $nt, $text, $query, $inside, $prefix );
return $this->armorLinks( $link ) . $trail;
}
/**
* Insert a NOPARSE hacky thing into any inline links in a chunk that's
* going to go through further parsing steps before inline URL expansion.
*
* Not needed quite as much as it used to be since free links are a bit
* more sensible these days. But bracketed links are still an issue.
*
* @param string more-or-less HTML
* @return string less-or-more HTML with NOPARSE bits
*/
function armorLinks( $text ) {
return preg_replace( '/\b(' . wfUrlProtocols() . ')/',
"{$this->mUniqPrefix}NOPARSE$1", $text );
}
/**
* Return true if subpage links should be expanded on this page.
* @return bool
*/
function areSubpagesAllowed() {
# Some namespaces don't allow subpages
return MWNamespace::hasSubpages( $this->mTitle->getNamespace() );
}
/**
* Handle link to subpage if necessary
* @param string $target the source of the link
* @param string &$text the link text, modified as necessary
* @return string the full name of the link
* @private
*/
function maybeDoSubpageLink($target, &$text) {
return Linker::normalizeSubpageLink( $this->mTitle, $target, $text );
}
/**#@+
* Used by doBlockLevels()
* @private
*/
/* private */ function closeParagraph() {
$result = '';
if ( $this->mLastSection != '' ) {
$result = '</' . $this->mLastSection . ">\n";
}
$this->mInPre = false;
$this->mLastSection = '';
return $result;
}
# getCommon() returns the length of the longest common substring
# of both arguments, starting at the beginning of both.
#
/* private */ function getCommon( $st1, $st2 ) {
$fl = strlen( $st1 );
$shorter = strlen( $st2 );
if ( $fl < $shorter ) { $shorter = $fl; }
for ( $i = 0; $i < $shorter; ++$i ) {
if ( $st1{$i} != $st2{$i} ) { break; }
}
return $i;
}
# These next three functions open, continue, and close the list
# element appropriate to the prefix character passed into them.
#
/* private */ function openList( $char ) {
$result = $this->closeParagraph();
if ( '*' === $char ) { $result .= '<ul><li>'; }
elseif ( '#' === $char ) { $result .= '<ol><li>'; }
elseif ( ':' === $char ) { $result .= '<dl><dd>'; }
elseif ( ';' === $char ) {
$result .= '<dl><dt>';
$this->mDTopen = true;
}
else { $result = '<!-- ERR 1 -->'; }
return $result;
}
/* private */ function nextItem( $char ) {
if ( '*' === $char || '#' === $char ) { return '</li><li>'; }
elseif ( ':' === $char || ';' === $char ) {
$close = '</dd>';
if ( $this->mDTopen ) { $close = '</dt>'; }
if ( ';' === $char ) {
$this->mDTopen = true;
return $close . '<dt>';
} else {
$this->mDTopen = false;
return $close . '<dd>';
}
}
return '<!-- ERR 2 -->';
}
/* private */ function closeList( $char ) {
if ( '*' === $char ) { $text = '</li></ul>'; }
elseif ( '#' === $char ) { $text = '</li></ol>'; }
elseif ( ':' === $char ) {
if ( $this->mDTopen ) {
$this->mDTopen = false;
$text = '</dt></dl>';
} else {
$text = '</dd></dl>';
}
}
else { return '<!-- ERR 3 -->'; }
return $text."\n";
}
/**#@-*/
/**
* Make lists from lines starting with ':', '*', '#', etc. (DBL)
*
* @param $linestart bool whether or not this is at the start of a line.
* @private
* @return string the lists rendered as HTML
*/
function doBlockLevels( $text, $linestart ) {
wfProfileIn( __METHOD__ );
# Parsing through the text line by line. The main thing
# happening here is handling of block-level elements p, pre,
# and making lists from lines starting with * # : etc.
#
$textLines = StringUtils::explode( "\n", $text );
$lastPrefix = $output = '';
$this->mDTopen = $inBlockElem = false;
$prefixLength = 0;
$paragraphStack = false;
foreach ( $textLines as $oLine ) {
# Fix up $linestart
if ( !$linestart ) {
$output .= $oLine;
$linestart = true;
continue;
}
// * = ul
// # = ol
// ; = dt
// : = dd
$lastPrefixLength = strlen( $lastPrefix );
$preCloseMatch = preg_match('/<\\/pre/i', $oLine );
$preOpenMatch = preg_match('/<pre/i', $oLine );
// If not in a <pre> element, scan for and figure out what prefixes are there.
if ( !$this->mInPre ) {
# Multiple prefixes may abut each other for nested lists.
$prefixLength = strspn( $oLine, '*#:;' );
$prefix = substr( $oLine, 0, $prefixLength );
# eh?
// ; and : are both from definition-lists, so they're equivalent
// for the purposes of determining whether or not we need to open/close
// elements.
$prefix2 = str_replace( ';', ':', $prefix );
$t = substr( $oLine, $prefixLength );
$this->mInPre = (bool)$preOpenMatch;
} else {
# Don't interpret any other prefixes in preformatted text
$prefixLength = 0;
$prefix = $prefix2 = '';
$t = $oLine;
}
# List generation
if( $prefixLength && $lastPrefix === $prefix2 ) {
# Same as the last item, so no need to deal with nesting or opening stuff
$output .= $this->nextItem( substr( $prefix, -1 ) );
$paragraphStack = false;
if ( substr( $prefix, -1 ) === ';') {
# The one nasty exception: definition lists work like this:
# ; title : definition text
# So we check for : in the remainder text to split up the
# title and definition, without b0rking links.
$term = $t2 = '';
if ($this->findColonNoLinks($t, $term, $t2) !== false) {
$t = $t2;
$output .= $term . $this->nextItem( ':' );
}
}
} elseif( $prefixLength || $lastPrefixLength ) {
// We need to open or close prefixes, or both.
# Either open or close a level...
$commonPrefixLength = $this->getCommon( $prefix, $lastPrefix );
$paragraphStack = false;
// Close all the prefixes which aren't shared.
while( $commonPrefixLength < $lastPrefixLength ) {
$output .= $this->closeList( $lastPrefix[$lastPrefixLength-1] );
--$lastPrefixLength;
}
// Continue the current prefix if appropriate.
if ( $prefixLength <= $commonPrefixLength && $commonPrefixLength > 0 ) {
$output .= $this->nextItem( $prefix[$commonPrefixLength-1] );
}
// Open prefixes where appropriate.
while ( $prefixLength > $commonPrefixLength ) {
$char = substr( $prefix, $commonPrefixLength, 1 );
$output .= $this->openList( $char );
if ( ';' === $char ) {
# FIXME: This is dupe of code above
if ($this->findColonNoLinks($t, $term, $t2) !== false) {
$t = $t2;
$output .= $term . $this->nextItem( ':' );
}
}
++$commonPrefixLength;
}
$lastPrefix = $prefix2;
}
// If we have no prefixes, go to paragraph mode.
if( 0 == $prefixLength ) {
wfProfileIn( __METHOD__."-paragraph" );
# No prefix (not in list)--go to paragraph mode
// XXX: use a stack for nestable elements like span, table and div
$openmatch = preg_match('/(?:<table|<blockquote|<h1|<h2|<h3|<h4|<h5|<h6|<pre|<tr|<p|<ul|<ol|<li|<\\/tr|<\\/td|<\\/th)/iS', $t );
$closematch = preg_match(
'/(?:<\\/table|<\\/blockquote|<\\/h1|<\\/h2|<\\/h3|<\\/h4|<\\/h5|<\\/h6|'.
'<td|<th|<\\/?div|<hr|<\\/pre|<\\/p|'.$this->mUniqPrefix.'-pre|<\\/li|<\\/ul|<\\/ol|<\\/?center)/iS', $t );
if ( $openmatch or $closematch ) {
$paragraphStack = false;
# TODO bug 5718: paragraph closed
$output .= $this->closeParagraph();
if ( $preOpenMatch and !$preCloseMatch ) {
$this->mInPre = true;
}
if ( $closematch ) {
$inBlockElem = false;
} else {
$inBlockElem = true;
}
} else if ( !$inBlockElem && !$this->mInPre ) {
if ( ' ' == substr( $t, 0, 1 ) and ( $this->mLastSection === 'pre' or trim($t) != '' ) ) {
// pre
if ($this->mLastSection !== 'pre') {
$paragraphStack = false;
$output .= $this->closeParagraph().'<pre>';
$this->mLastSection = 'pre';
}
$t = substr( $t, 1 );
} else {
// paragraph
if ( trim($t) == '' ) {
if ( $paragraphStack ) {
$output .= $paragraphStack.'<br />';
$paragraphStack = false;
$this->mLastSection = 'p';
} else {
if ($this->mLastSection !== 'p' ) {
$output .= $this->closeParagraph();
$this->mLastSection = '';
$paragraphStack = '<p>';
} else {
$paragraphStack = '</p><p>';
}
}
} else {
if ( $paragraphStack ) {
$output .= $paragraphStack;
$paragraphStack = false;
$this->mLastSection = 'p';
} else if ($this->mLastSection !== 'p') {
$output .= $this->closeParagraph().'<p>';
$this->mLastSection = 'p';
}
}
}
}
wfProfileOut( __METHOD__."-paragraph" );
}
// somewhere above we forget to get out of pre block (bug 785)
if($preCloseMatch && $this->mInPre) {
$this->mInPre = false;
}
if ($paragraphStack === false) {
$output .= $t."\n";
}
}
while ( $prefixLength ) {
$output .= $this->closeList( $prefix2[$prefixLength-1] );
--$prefixLength;
}
if ( $this->mLastSection != '' ) {
$output .= '</' . $this->mLastSection . '>';
$this->mLastSection = '';
}
wfProfileOut( __METHOD__ );
return $output;
}
/**
* Split up a string on ':', ignoring any occurences inside tags
* to prevent illegal overlapping.
* @param string $str the string to split
* @param string &$before set to everything before the ':'
* @param string &$after set to everything after the ':'
* return string the position of the ':', or false if none found
*/
function findColonNoLinks($str, &$before, &$after) {
wfProfileIn( __METHOD__ );
$pos = strpos( $str, ':' );
if( $pos === false ) {
// Nothing to find!
wfProfileOut( __METHOD__ );
return false;
}
$lt = strpos( $str, '<' );
if( $lt === false || $lt > $pos ) {
// Easy; no tag nesting to worry about
$before = substr( $str, 0, $pos );
$after = substr( $str, $pos+1 );
wfProfileOut( __METHOD__ );
return $pos;
}
// Ugly state machine to walk through avoiding tags.
$state = self::COLON_STATE_TEXT;
$stack = 0;
$len = strlen( $str );
for( $i = 0; $i < $len; $i++ ) {
$c = $str{$i};
switch( $state ) {
// (Using the number is a performance hack for common cases)
case 0: // self::COLON_STATE_TEXT:
switch( $c ) {
case "<":
// Could be either a <start> tag or an </end> tag
$state = self::COLON_STATE_TAGSTART;
break;
case ":":
if( $stack == 0 ) {
// We found it!
$before = substr( $str, 0, $i );
$after = substr( $str, $i + 1 );
wfProfileOut( __METHOD__ );
return $i;
}
// Embedded in a tag; don't break it.
break;
default:
// Skip ahead looking for something interesting
$colon = strpos( $str, ':', $i );
if( $colon === false ) {
// Nothing else interesting
wfProfileOut( __METHOD__ );
return false;
}
$lt = strpos( $str, '<', $i );
if( $stack === 0 ) {
if( $lt === false || $colon < $lt ) {
// We found it!
$before = substr( $str, 0, $colon );
$after = substr( $str, $colon + 1 );
wfProfileOut( __METHOD__ );
return $i;
}
}
if( $lt === false ) {
// Nothing else interesting to find; abort!
// We're nested, but there's no close tags left. Abort!
break 2;
}
// Skip ahead to next tag start
$i = $lt;
$state = self::COLON_STATE_TAGSTART;
}
break;
case 1: // self::COLON_STATE_TAG:
// In a <tag>
switch( $c ) {
case ">":
$stack++;
$state = self::COLON_STATE_TEXT;
break;
case "/":
// Slash may be followed by >?
$state = self::COLON_STATE_TAGSLASH;
break;
default:
// ignore
}
break;
case 2: // self::COLON_STATE_TAGSTART:
switch( $c ) {
case "/":
$state = self::COLON_STATE_CLOSETAG;
break;
case "!":
$state = self::COLON_STATE_COMMENT;
break;
case ">":
// Illegal early close? This shouldn't happen D:
$state = self::COLON_STATE_TEXT;
break;
default:
$state = self::COLON_STATE_TAG;
}
break;
case 3: // self::COLON_STATE_CLOSETAG:
// In a </tag>
if( $c === ">" ) {
$stack--;
if( $stack < 0 ) {
wfDebug( __METHOD__.": Invalid input; too many close tags\n" );
wfProfileOut( __METHOD__ );
return false;
}
$state = self::COLON_STATE_TEXT;
}
break;
case self::COLON_STATE_TAGSLASH:
if( $c === ">" ) {
// Yes, a self-closed tag <blah/>
$state = self::COLON_STATE_TEXT;
} else {
// Probably we're jumping the gun, and this is an attribute
$state = self::COLON_STATE_TAG;
}
break;
case 5: // self::COLON_STATE_COMMENT:
if( $c === "-" ) {
$state = self::COLON_STATE_COMMENTDASH;
}
break;
case self::COLON_STATE_COMMENTDASH:
if( $c === "-" ) {
$state = self::COLON_STATE_COMMENTDASHDASH;
} else {
$state = self::COLON_STATE_COMMENT;
}
break;
case self::COLON_STATE_COMMENTDASHDASH:
if( $c === ">" ) {
$state = self::COLON_STATE_TEXT;
} else {
$state = self::COLON_STATE_COMMENT;
}
break;
default:
throw new MWException( "State machine error in " . __METHOD__ );
}
}
if( $stack > 0 ) {
wfDebug( __METHOD__.": Invalid input; not enough close tags (stack $stack, state $state)\n" );
return false;
}
wfProfileOut( __METHOD__ );
return false;
}
/**
* Return value of a magic variable (like PAGENAME)
*
* @private
*/
function getVariableValue( $index, $frame=false ) {
global $wgContLang, $wgSitename, $wgServer, $wgServerName;
global $wgScriptPath, $wgStylePath;
/**
* Some of these require message or data lookups and can be
* expensive to check many times.
*/
if ( wfRunHooks( 'ParserGetVariableValueVarCache', array( &$this, &$this->mVarCache ) ) ) {
if ( isset( $this->mVarCache[$index] ) ) {
return $this->mVarCache[$index];
}
}
$ts = wfTimestamp( TS_UNIX, $this->mOptions->getTimestamp() );
wfRunHooks( 'ParserGetVariableValueTs', array( &$this, &$ts ) );
# Use the time zone
global $wgLocaltimezone;
if ( isset( $wgLocaltimezone ) ) {
$oldtz = date_default_timezone_get();
date_default_timezone_set( $wgLocaltimezone );
}
$localTimestamp = date( 'YmdHis', $ts );
$localMonth = date( 'm', $ts );
$localMonth1 = date( 'n', $ts );
$localMonthName = date( 'n', $ts );
$localDay = date( 'j', $ts );
$localDay2 = date( 'd', $ts );
$localDayOfWeek = date( 'w', $ts );
$localWeek = date( 'W', $ts );
$localYear = date( 'Y', $ts );
$localHour = date( 'H', $ts );
if ( isset( $wgLocaltimezone ) ) {
date_default_timezone_set( $oldtz );
}
switch ( $index ) {
case 'currentmonth':
$value = $wgContLang->formatNum( gmdate( 'm', $ts ) );
break;
case 'currentmonth1':
$value = $wgContLang->formatNum( gmdate( 'n', $ts ) );
break;
case 'currentmonthname':
$value = $wgContLang->getMonthName( gmdate( 'n', $ts ) );
break;
case 'currentmonthnamegen':
$value = $wgContLang->getMonthNameGen( gmdate( 'n', $ts ) );
break;
case 'currentmonthabbrev':
$value = $wgContLang->getMonthAbbreviation( gmdate( 'n', $ts ) );
break;
case 'currentday':
$value = $wgContLang->formatNum( gmdate( 'j', $ts ) );
break;
case 'currentday2':
$value = $wgContLang->formatNum( gmdate( 'd', $ts ) );
break;
case 'localmonth':
$value = $wgContLang->formatNum( $localMonth );
break;
case 'localmonth1':
$value = $wgContLang->formatNum( $localMonth1 );
break;
case 'localmonthname':
$value = $wgContLang->getMonthName( $localMonthName );
break;
case 'localmonthnamegen':
$value = $wgContLang->getMonthNameGen( $localMonthName );
break;
case 'localmonthabbrev':
$value = $wgContLang->getMonthAbbreviation( $localMonthName );
break;
case 'localday':
$value = $wgContLang->formatNum( $localDay );
break;
case 'localday2':
$value = $wgContLang->formatNum( $localDay2 );
break;
case 'pagename':
$value = wfEscapeWikiText( $this->mTitle->getText() );
break;
case 'pagenamee':
$value = $this->mTitle->getPartialURL();
break;
case 'fullpagename':
$value = wfEscapeWikiText( $this->mTitle->getPrefixedText() );
break;
case 'fullpagenamee':
$value = $this->mTitle->getPrefixedURL();
break;
case 'subpagename':
$value = wfEscapeWikiText( $this->mTitle->getSubpageText() );
break;
case 'subpagenamee':
$value = $this->mTitle->getSubpageUrlForm();
break;
case 'basepagename':
$value = wfEscapeWikiText( $this->mTitle->getBaseText() );
break;
case 'basepagenamee':
$value = wfUrlEncode( str_replace( ' ', '_', $this->mTitle->getBaseText() ) );
break;
case 'talkpagename':
if( $this->mTitle->canTalk() ) {
$talkPage = $this->mTitle->getTalkPage();
$value = wfEscapeWikiText( $talkPage->getPrefixedText() );
} else {
$value = '';
}
break;
case 'talkpagenamee':
if( $this->mTitle->canTalk() ) {
$talkPage = $this->mTitle->getTalkPage();
$value = $talkPage->getPrefixedUrl();
} else {
$value = '';
}
break;
case 'subjectpagename':
$subjPage = $this->mTitle->getSubjectPage();
$value = wfEscapeWikiText( $subjPage->getPrefixedText() );
break;
case 'subjectpagenamee':
$subjPage = $this->mTitle->getSubjectPage();
$value = $subjPage->getPrefixedUrl();
break;
case 'revisionid':
// Let the edit saving system know we should parse the page
// *after* a revision ID has been assigned.
$this->mOutput->setFlag( 'vary-revision' );
wfDebug( __METHOD__ . ": {{REVISIONID}} used, setting vary-revision...\n" );
$value = $this->mRevisionId;
break;
case 'revisionday':
// Let the edit saving system know we should parse the page
// *after* a revision ID has been assigned. This is for null edits.
$this->mOutput->setFlag( 'vary-revision' );
wfDebug( __METHOD__ . ": {{REVISIONDAY}} used, setting vary-revision...\n" );
$value = intval( substr( $this->getRevisionTimestamp(), 6, 2 ) );
break;
case 'revisionday2':
// Let the edit saving system know we should parse the page
// *after* a revision ID has been assigned. This is for null edits.
$this->mOutput->setFlag( 'vary-revision' );
wfDebug( __METHOD__ . ": {{REVISIONDAY2}} used, setting vary-revision...\n" );
$value = substr( $this->getRevisionTimestamp(), 6, 2 );
break;
case 'revisionmonth':
// Let the edit saving system know we should parse the page
// *after* a revision ID has been assigned. This is for null edits.
$this->mOutput->setFlag( 'vary-revision' );
wfDebug( __METHOD__ . ": {{REVISIONMONTH}} used, setting vary-revision...\n" );
$value = intval( substr( $this->getRevisionTimestamp(), 4, 2 ) );
break;
case 'revisionyear':
// Let the edit saving system know we should parse the page
// *after* a revision ID has been assigned. This is for null edits.
$this->mOutput->setFlag( 'vary-revision' );
wfDebug( __METHOD__ . ": {{REVISIONYEAR}} used, setting vary-revision...\n" );
$value = substr( $this->getRevisionTimestamp(), 0, 4 );
break;
case 'revisiontimestamp':
// Let the edit saving system know we should parse the page
// *after* a revision ID has been assigned. This is for null edits.
$this->mOutput->setFlag( 'vary-revision' );
wfDebug( __METHOD__ . ": {{REVISIONTIMESTAMP}} used, setting vary-revision...\n" );
$value = $this->getRevisionTimestamp();
break;
case 'revisionuser':
// Let the edit saving system know we should parse the page
// *after* a revision ID has been assigned. This is for null edits.
$this->mOutput->setFlag( 'vary-revision' );
wfDebug( __METHOD__ . ": {{REVISIONUSER}} used, setting vary-revision...\n" );
$value = $this->getRevisionUser();
break;
case 'namespace':
$value = str_replace('_',' ',$wgContLang->getNsText( $this->mTitle->getNamespace() ) );
break;
case 'namespacee':
$value = wfUrlencode( $wgContLang->getNsText( $this->mTitle->getNamespace() ) );
break;
case 'talkspace':
$value = $this->mTitle->canTalk() ? str_replace('_',' ',$this->mTitle->getTalkNsText()) : '';
break;
case 'talkspacee':
$value = $this->mTitle->canTalk() ? wfUrlencode( $this->mTitle->getTalkNsText() ) : '';
break;
case 'subjectspace':
$value = $this->mTitle->getSubjectNsText();
break;
case 'subjectspacee':
$value = ( wfUrlencode( $this->mTitle->getSubjectNsText() ) );
break;
case 'currentdayname':
$value = $wgContLang->getWeekdayName( gmdate( 'w', $ts ) + 1 );
break;
case 'currentyear':
$value = $wgContLang->formatNum( gmdate( 'Y', $ts ), true );
break;
case 'currenttime':
$value = $wgContLang->time( wfTimestamp( TS_MW, $ts ), false, false );
break;
case 'currenthour':
$value = $wgContLang->formatNum( gmdate( 'H', $ts ), true );
break;
case 'currentweek':
// @bug 4594 PHP5 has it zero padded, PHP4 does not, cast to
// int to remove the padding
$value = $wgContLang->formatNum( (int)gmdate( 'W', $ts ) );
break;
case 'currentdow':
$value = $wgContLang->formatNum( gmdate( 'w', $ts ) );
break;
case 'localdayname':
$value = $wgContLang->getWeekdayName( $localDayOfWeek + 1 );
break;
case 'localyear':
$value = $wgContLang->formatNum( $localYear, true );
break;
case 'localtime':
$value = $wgContLang->time( $localTimestamp, false, false );
break;
case 'localhour':
$value = $wgContLang->formatNum( $localHour, true );
break;
case 'localweek':
// @bug 4594 PHP5 has it zero padded, PHP4 does not, cast to
// int to remove the padding
$value = $wgContLang->formatNum( (int)$localWeek );
break;
case 'localdow':
$value = $wgContLang->formatNum( $localDayOfWeek );
break;
case 'numberofarticles':
$value = $wgContLang->formatNum( SiteStats::articles() );
break;
case 'numberoffiles':
$value = $wgContLang->formatNum( SiteStats::images() );
break;
case 'numberofusers':
$value = $wgContLang->formatNum( SiteStats::users() );
break;
case 'numberofactiveusers':
$value = $wgContLang->formatNum( SiteStats::activeUsers() );
break;
case 'numberofpages':
$value = $wgContLang->formatNum( SiteStats::pages() );
break;
case 'numberofadmins':
$value = $wgContLang->formatNum( SiteStats::numberingroup('sysop') );
break;
case 'numberofedits':
$value = $wgContLang->formatNum( SiteStats::edits() );
break;
case 'numberofviews':
$value = $wgContLang->formatNum( SiteStats::views() );
break;
case 'currenttimestamp':
$value = wfTimestamp( TS_MW, $ts );
break;
case 'localtimestamp':
$value = $localTimestamp;
break;
case 'currentversion':
$value = SpecialVersion::getVersion();
break;
case 'sitename':
return $wgSitename;
case 'server':
return $wgServer;
case 'servername':
return $wgServerName;
case 'scriptpath':
return $wgScriptPath;
case 'stylepath':
return $wgStylePath;
case 'directionmark':
return $wgContLang->getDirMark();
case 'contentlanguage':
global $wgContLanguageCode;
return $wgContLanguageCode;
default:
$ret = null;
if ( wfRunHooks( 'ParserGetVariableValueSwitch', array( &$this, &$this->mVarCache, &$index, &$ret, &$frame ) ) )
return $ret;
else
return null;
}
if ( $index )
$this->mVarCache[$index] = $value;
return $value;
}
/**
* initialise the magic variables (like CURRENTMONTHNAME) and substitution modifiers
*
* @private
*/
function initialiseVariables() {
wfProfileIn( __METHOD__ );
$variableIDs = MagicWord::getVariableIDs();
$substIDs = MagicWord::getSubstIDs();
$this->mVariables = new MagicWordArray( $variableIDs );
$this->mSubstWords = new MagicWordArray( $substIDs );
wfProfileOut( __METHOD__ );
}
/**
* Preprocess some wikitext and return the document tree.
* This is the ghost of replace_variables().
*
* @param string $text The text to parse
* @param integer flags Bitwise combination of:
* self::PTD_FOR_INCLUSION Handle <noinclude>/<includeonly> as if the text is being
* included. Default is to assume a direct page view.
*
* The generated DOM tree must depend only on the input text and the flags.
* The DOM tree must be the same in OT_HTML and OT_WIKI mode, to avoid a regression of bug 4899.
*
* Any flag added to the $flags parameter here, or any other parameter liable to cause a
* change in the DOM tree for a given text, must be passed through the section identifier
* in the section edit link and thus back to extractSections().
*
* The output of this function is currently only cached in process memory, but a persistent
* cache may be implemented at a later date which takes further advantage of these strict
* dependency requirements.
*
* @private
*/
function preprocessToDom ( $text, $flags = 0 ) {
$dom = $this->getPreprocessor()->preprocessToObj( $text, $flags );
return $dom;
}
/*
* Return a three-element array: leading whitespace, string contents, trailing whitespace
*/
public static function splitWhitespace( $s ) {
$ltrimmed = ltrim( $s );
$w1 = substr( $s, 0, strlen( $s ) - strlen( $ltrimmed ) );
$trimmed = rtrim( $ltrimmed );
$diff = strlen( $ltrimmed ) - strlen( $trimmed );
if ( $diff > 0 ) {
$w2 = substr( $ltrimmed, -$diff );
} else {
$w2 = '';
}
return array( $w1, $trimmed, $w2 );
}
/**
* Replace magic variables, templates, and template arguments
* with the appropriate text. Templates are substituted recursively,
* taking care to avoid infinite loops.
*
* Note that the substitution depends on value of $mOutputType:
* self::OT_WIKI: only {{subst:}} templates
* self::OT_PREPROCESS: templates but not extension tags
* self::OT_HTML: all templates and extension tags
*
* @param string $tex The text to transform
* @param PPFrame $frame Object describing the arguments passed to the template.
* Arguments may also be provided as an associative array, as was the usual case before MW1.12.
* Providing arguments this way may be useful for extensions wishing to perform variable replacement explicitly.
* @param bool $argsOnly Only do argument (triple-brace) expansion, not double-brace expansion
* @private
*/
function replaceVariables( $text, $frame = false, $argsOnly = false ) {
# Is there any text? Also, Prevent too big inclusions!
if ( strlen( $text ) < 1 || strlen( $text ) > $this->mOptions->getMaxIncludeSize() ) {
return $text;
}
wfProfileIn( __METHOD__ );
if ( $frame === false ) {
$frame = $this->getPreprocessor()->newFrame();
} elseif ( !( $frame instanceof PPFrame ) ) {
wfDebug( __METHOD__." called using plain parameters instead of a PPFrame instance. Creating custom frame.\n" );
$frame = $this->getPreprocessor()->newCustomFrame($frame);
}
$dom = $this->preprocessToDom( $text );
$flags = $argsOnly ? PPFrame::NO_TEMPLATES : 0;
$text = $frame->expand( $dom, $flags );
wfProfileOut( __METHOD__ );
return $text;
}
/// Clean up argument array - refactored in 1.9 so parserfunctions can use it, too.
static function createAssocArgs( $args ) {
$assocArgs = array();
$index = 1;
foreach( $args as $arg ) {
$eqpos = strpos( $arg, '=' );
if ( $eqpos === false ) {
$assocArgs[$index++] = $arg;
} else {
$name = trim( substr( $arg, 0, $eqpos ) );
$value = trim( substr( $arg, $eqpos+1 ) );
if ( $value === false ) {
$value = '';
}
if ( $name !== false ) {
$assocArgs[$name] = $value;
}
}
}
return $assocArgs;
}
/**
* Warn the user when a parser limitation is reached
* Will warn at most once the user per limitation type
*
* @param string $limitationType, should be one of:
* 'expensive-parserfunction' (corresponding messages: 'expensive-parserfunction-warning', 'expensive-parserfunction-category')
* 'post-expand-template-argument' (corresponding messages: 'post-expand-template-argument-warning', 'post-expand-template-argument-category')
* 'post-expand-template-inclusion' (corresponding messages: 'post-expand-template-inclusion-warning', 'post-expand-template-inclusion-category')
* @params int $current, $max When an explicit limit has been
* exceeded, provide the values (optional)
*/
function limitationWarn( $limitationType, $current=null, $max=null) {
//does no harm if $current and $max are present but are unnecessary for the message
$warning = wfMsgExt( "$limitationType-warning", array( 'parsemag', 'escape' ), $current, $max );
$this->mOutput->addWarning( $warning );
$this->addTrackingCategory( "$limitationType-category" );
}
/**
* Return the text of a template, after recursively
* replacing any variables or templates within the template.
*
* @param array $piece The parts of the template
* $piece['title']: the title, i.e. the part before the |
* $piece['parts']: the parameter array
* $piece['lineStart']: whether the brace was at the start of a line
* @param PPFrame The current frame, contains template arguments
* @return string the text of the template
* @private
*/
function braceSubstitution( $piece, $frame ) {
global $wgContLang, $wgNonincludableNamespaces;
wfProfileIn( __METHOD__ );
wfProfileIn( __METHOD__.'-setup' );
# Flags
$found = false; # $text has been filled
$nowiki = false; # wiki markup in $text should be escaped
$isHTML = false; # $text is HTML, armour it against wikitext transformation
$forceRawInterwiki = false; # Force interwiki transclusion to be done in raw mode not rendered
$isChildObj = false; # $text is a DOM node needing expansion in a child frame
$isLocalObj = false; # $text is a DOM node needing expansion in the current frame
# Title object, where $text came from
$title = null;
# $part1 is the bit before the first |, and must contain only title characters.
# Various prefixes will be stripped from it later.
$titleWithSpaces = $frame->expand( $piece['title'] );
$part1 = trim( $titleWithSpaces );
$titleText = false;
# Original title text preserved for various purposes
$originalTitle = $part1;
# $args is a list of argument nodes, starting from index 0, not including $part1
$args = (null == $piece['parts']) ? array() : $piece['parts'];
wfProfileOut( __METHOD__.'-setup' );
# SUBST
wfProfileIn( __METHOD__.'-modifiers' );
if ( !$found ) {
$substMatch = $this->mSubstWords->matchStartAndRemove( $part1 );
# Possibilities for substMatch: "subst", "safesubst" or FALSE
# Decide whether to expand template or keep wikitext as-is.
if ( $this->ot['wiki'] ) {
if ( $substMatch === false ) {
$literal = true; # literal when in PST with no prefix
} else {
$literal = false; # expand when in PST with subst: or safesubst:
}
} else {
if ( $substMatch == 'subst' ) {
$literal = true; # literal when not in PST with plain subst:
} else {
$literal = false; # expand when not in PST with safesubst: or no prefix
}
}
if ( $literal ) {
$text = $frame->virtualBracketedImplode( '{{', '|', '}}', $titleWithSpaces, $args );
$isLocalObj = true;
$found = true;
}
}
# Variables
if ( !$found && $args->getLength() == 0 ) {
$id = $this->mVariables->matchStartToEnd( $part1 );
if ( $id !== false ) {
$text = $this->getVariableValue( $id, $frame );
if (MagicWord::getCacheTTL($id)>-1)
$this->mOutput->mContainsOldMagic = true;
$found = true;
}
}
# MSG, MSGNW and RAW
if ( !$found ) {
# Check for MSGNW:
$mwMsgnw = MagicWord::get( 'msgnw' );
if ( $mwMsgnw->matchStartAndRemove( $part1 ) ) {
$nowiki = true;
} else {
# Remove obsolete MSG:
$mwMsg = MagicWord::get( 'msg' );
$mwMsg->matchStartAndRemove( $part1 );
}
# Check for RAW:
$mwRaw = MagicWord::get( 'raw' );
if ( $mwRaw->matchStartAndRemove( $part1 ) ) {
$forceRawInterwiki = true;
}
}
wfProfileOut( __METHOD__.'-modifiers' );
# Parser functions
if ( !$found ) {
wfProfileIn( __METHOD__ . '-pfunc' );
$colonPos = strpos( $part1, ':' );
if ( $colonPos !== false ) {
# Case sensitive functions
$function = substr( $part1, 0, $colonPos );
if ( isset( $this->mFunctionSynonyms[1][$function] ) ) {
$function = $this->mFunctionSynonyms[1][$function];
} else {
# Case insensitive functions
$function = $wgContLang->lc( $function );
if ( isset( $this->mFunctionSynonyms[0][$function] ) ) {
$function = $this->mFunctionSynonyms[0][$function];
} else {
$function = false;
}
}
if ( $function ) {
list( $callback, $flags ) = $this->mFunctionHooks[$function];
$initialArgs = array( &$this );
$funcArgs = array( trim( substr( $part1, $colonPos + 1 ) ) );
if ( $flags & SFH_OBJECT_ARGS ) {
# Add a frame parameter, and pass the arguments as an array
$allArgs = $initialArgs;
$allArgs[] = $frame;
for ( $i = 0; $i < $args->getLength(); $i++ ) {
$funcArgs[] = $args->item( $i );
}
$allArgs[] = $funcArgs;
} else {
# Convert arguments to plain text
for ( $i = 0; $i < $args->getLength(); $i++ ) {
$funcArgs[] = trim( $frame->expand( $args->item( $i ) ) );
}
$allArgs = array_merge( $initialArgs, $funcArgs );
}
# Workaround for PHP bug 35229 and similar
if ( !is_callable( $callback ) ) {
wfProfileOut( __METHOD__ . '-pfunc' );
wfProfileOut( __METHOD__ );
throw new MWException( "Tag hook for $function is not callable\n" );
}
$result = call_user_func_array( $callback, $allArgs );
$found = true;
$noparse = true;
$preprocessFlags = 0;
if ( is_array( $result ) ) {
if ( isset( $result[0] ) ) {
$text = $result[0];
unset( $result[0] );
}
// Extract flags into the local scope
// This allows callers to set flags such as nowiki, found, etc.
extract( $result );
} else {
$text = $result;
}
if ( !$noparse ) {
$text = $this->preprocessToDom( $text, $preprocessFlags );
$isChildObj = true;
}
}
}
wfProfileOut( __METHOD__ . '-pfunc' );
}
# Finish mangling title and then check for loops.
# Set $title to a Title object and $titleText to the PDBK
if ( !$found ) {
$ns = NS_TEMPLATE;
# Split the title into page and subpage
$subpage = '';
$part1 = $this->maybeDoSubpageLink( $part1, $subpage );
if ($subpage !== '') {
$ns = $this->mTitle->getNamespace();
}
$title = Title::newFromText( $part1, $ns );
if ( $title ) {
$titleText = $title->getPrefixedText();
# Check for language variants if the template is not found
if($wgContLang->hasVariants() && $title->getArticleID() == 0){
$wgContLang->findVariantLink( $part1, $title, true );
}
# Do recursion depth check
$limit = $this->mOptions->getMaxTemplateDepth();
if ( $frame->depth >= $limit ) {
$found = true;
$text = '<span class="error">' . wfMsgForContent( 'parser-template-recursion-depth-warning', $limit ) . '</span>';
}
}
}
# Load from database
if ( !$found && $title ) {
wfProfileIn( __METHOD__ . '-loadtpl' );
if ( !$title->isExternal() ) {
if ( $title->getNamespace() == NS_SPECIAL && $this->mOptions->getAllowSpecialInclusion() && $this->ot['html'] ) {
$text = SpecialPage::capturePath( $title );
if ( is_string( $text ) ) {
$found = true;
$isHTML = true;
$this->disableCache();
}
} else if ( $wgNonincludableNamespaces && in_array( $title->getNamespace(), $wgNonincludableNamespaces ) ) {
$found = false; //access denied
wfDebug( __METHOD__.": template inclusion denied for " . $title->getPrefixedDBkey() );
} else {
list( $text, $title ) = $this->getTemplateDom( $title );
if ( $text !== false ) {
$found = true;
$isChildObj = true;
}
}
# If the title is valid but undisplayable, make a link to it
if ( !$found && ( $this->ot['html'] || $this->ot['pre'] ) ) {
$text = "[[:$titleText]]";
$found = true;
}
} elseif ( $title->isTrans() ) {
// Interwiki transclusion
if ( $this->ot['html'] && !$forceRawInterwiki ) {
$text = $this->interwikiTransclude( $title, 'render' );
$isHTML = true;
} else {
$text = $this->interwikiTransclude( $title, 'raw' );
// Preprocess it like a template
$text = $this->preprocessToDom( $text, self::PTD_FOR_INCLUSION );
$isChildObj = true;
}
$found = true;
}
# Do infinite loop check
# This has to be done after redirect resolution to avoid infinite loops via redirects
if ( !$frame->loopCheck( $title ) ) {
$found = true;
$text = '<span class="error">' . wfMsgForContent( 'parser-template-loop-warning', $titleText ) . '</span>';
wfDebug( __METHOD__.": template loop broken at '$titleText'\n" );
}
wfProfileOut( __METHOD__ . '-loadtpl' );
}
# If we haven't found text to substitute by now, we're done
# Recover the source wikitext and return it
if ( !$found ) {
$text = $frame->virtualBracketedImplode( '{{', '|', '}}', $titleWithSpaces, $args );
wfProfileOut( __METHOD__ );
return array( 'object' => $text );
}
# Expand DOM-style return values in a child frame
if ( $isChildObj ) {
# Clean up argument array
$newFrame = $frame->newChild( $args, $title );
if ( $nowiki ) {
$text = $newFrame->expand( $text, PPFrame::RECOVER_ORIG );
} elseif ( $titleText !== false && $newFrame->isEmpty() ) {
# Expansion is eligible for the empty-frame cache
if ( isset( $this->mTplExpandCache[$titleText] ) ) {
$text = $this->mTplExpandCache[$titleText];
} else {
$text = $newFrame->expand( $text );
$this->mTplExpandCache[$titleText] = $text;
}
} else {
# Uncached expansion
$text = $newFrame->expand( $text );
}
}
if ( $isLocalObj && $nowiki ) {
$text = $frame->expand( $text, PPFrame::RECOVER_ORIG );
$isLocalObj = false;
}
# Replace raw HTML by a placeholder
# Add a blank line preceding, to prevent it from mucking up
# immediately preceding headings
if ( $isHTML ) {
$text = "\n\n" . $this->insertStripItem( $text );
}
# Escape nowiki-style return values
elseif ( $nowiki && ( $this->ot['html'] || $this->ot['pre'] ) ) {
$text = wfEscapeWikiText( $text );
}
# Bug 529: if the template begins with a table or block-level
# element, it should be treated as beginning a new line.
# This behaviour is somewhat controversial.
elseif ( is_string( $text ) && !$piece['lineStart'] && preg_match('/^(?:{\\||:|;|#|\*)/', $text)) /*}*/{
$text = "\n" . $text;
}
if ( is_string( $text ) && !$this->incrementIncludeSize( 'post-expand', strlen( $text ) ) ) {
# Error, oversize inclusion
$text = "[[$originalTitle]]" .
$this->insertStripItem( '<!-- WARNING: template omitted, post-expand include size too large -->' );
$this->limitationWarn( 'post-expand-template-inclusion' );
}
if ( $isLocalObj ) {
$ret = array( 'object' => $text );
} else {
$ret = array( 'text' => $text );
}
wfProfileOut( __METHOD__ );
return $ret;
}
/**
* Get the semi-parsed DOM representation of a template with a given title,
* and its redirect destination title. Cached.
*/
function getTemplateDom( $title ) {
$cacheTitle = $title;
$titleText = $title->getPrefixedDBkey();
if ( isset( $this->mTplRedirCache[$titleText] ) ) {
list( $ns, $dbk ) = $this->mTplRedirCache[$titleText];
$title = Title::makeTitle( $ns, $dbk );
$titleText = $title->getPrefixedDBkey();
}
if ( isset( $this->mTplDomCache[$titleText] ) ) {
return array( $this->mTplDomCache[$titleText], $title );
}
// Cache miss, go to the database
list( $text, $title ) = $this->fetchTemplateAndTitle( $title );
if ( $text === false ) {
$this->mTplDomCache[$titleText] = false;
return array( false, $title );
}
$dom = $this->preprocessToDom( $text, self::PTD_FOR_INCLUSION );
$this->mTplDomCache[ $titleText ] = $dom;
if (! $title->equals($cacheTitle)) {
$this->mTplRedirCache[$cacheTitle->getPrefixedDBkey()] =
array( $title->getNamespace(),$cdb = $title->getDBkey() );
}
return array( $dom, $title );
}
/**
* Fetch the unparsed text of a template and register a reference to it.
*/
function fetchTemplateAndTitle( $title ) {
$templateCb = $this->mOptions->getTemplateCallback();
$stuff = call_user_func( $templateCb, $title, $this );
$text = $stuff['text'];
$finalTitle = isset( $stuff['finalTitle'] ) ? $stuff['finalTitle'] : $title;
if ( isset( $stuff['deps'] ) ) {
foreach ( $stuff['deps'] as $dep ) {
$this->mOutput->addTemplate( $dep['title'], $dep['page_id'], $dep['rev_id'] );
}
}
return array($text,$finalTitle);
}
function fetchTemplate( $title ) {
$rv = $this->fetchTemplateAndTitle($title);
return $rv[0];
}
/**
* Static function to get a template
* Can be overridden via ParserOptions::setTemplateCallback().
*/
static function statelessFetchTemplate( $title, $parser=false ) {
$text = $skip = false;
$finalTitle = $title;
$deps = array();
// Loop to fetch the article, with up to 1 redirect
for ( $i = 0; $i < 2 && is_object( $title ); $i++ ) {
# Give extensions a chance to select the revision instead
$id = false; // Assume current
wfRunHooks( 'BeforeParserFetchTemplateAndtitle', array( $parser, &$title, &$skip, &$id ) );
if( $skip ) {
$text = false;
$deps[] = array(
'title' => $title,
'page_id' => $title->getArticleID(),
'rev_id' => null );
break;
}
$rev = $id ? Revision::newFromId( $id ) : Revision::newFromTitle( $title );
$rev_id = $rev ? $rev->getId() : 0;
// If there is no current revision, there is no page
if( $id === false && !$rev ) {
$linkCache = LinkCache::singleton();
$linkCache->addBadLinkObj( $title );
}
$deps[] = array(
'title' => $title,
'page_id' => $title->getArticleID(),
'rev_id' => $rev_id );
if( $rev ) {
$text = $rev->getText();
} elseif( $title->getNamespace() == NS_MEDIAWIKI ) {
global $wgContLang;
$message = $wgContLang->lcfirst( $title->getText() );
$text = wfMsgForContentNoTrans( $message );
if( wfEmptyMsg( $message, $text ) ) {
$text = false;
break;
}
} else {
break;
}
if ( $text === false ) {
break;
}
// Redirect?
$finalTitle = $title;
$title = Title::newFromRedirect( $text );
}
return array(
'text' => $text,
'finalTitle' => $finalTitle,
'deps' => $deps );
}
/**
* Transclude an interwiki link.
*/
function interwikiTransclude( $title, $action ) {
global $wgEnableScaryTranscluding;
if (!$wgEnableScaryTranscluding)
return wfMsg('scarytranscludedisabled');
$url = $title->getFullUrl( "action=$action" );
if (strlen($url) > 255)
return wfMsg('scarytranscludetoolong');
return $this->fetchScaryTemplateMaybeFromCache($url);
}
function fetchScaryTemplateMaybeFromCache($url) {
global $wgTranscludeCacheExpiry;
$dbr = wfGetDB(DB_SLAVE);
$tsCond = $dbr->timestamp( time() - $wgTranscludeCacheExpiry );
$obj = $dbr->selectRow('transcache', array('tc_time', 'tc_contents'),
array('tc_url' => $url, "tc_time >= " . $dbr->addQuotes( $tsCond ) ) );
if ($obj) {
return $obj->tc_contents;
}
$text = Http::get($url);
if (!$text)
return wfMsg('scarytranscludefailed', $url);
$dbw = wfGetDB(DB_MASTER);
$dbw->replace('transcache', array('tc_url'), array(
'tc_url' => $url,
'tc_time' => $dbw->timestamp( time() ),
'tc_contents' => $text));
return $text;
}
/**
* Triple brace replacement -- used for template arguments
* @private
*/
function argSubstitution( $piece, $frame ) {
wfProfileIn( __METHOD__ );
$error = false;
$parts = $piece['parts'];
$nameWithSpaces = $frame->expand( $piece['title'] );
$argName = trim( $nameWithSpaces );
$object = false;
$text = $frame->getArgument( $argName );
if ( $text === false && $parts->getLength() > 0
&& (
$this->ot['html']
|| $this->ot['pre']
|| ( $this->ot['wiki'] && $frame->isTemplate() )
)
) {
# No match in frame, use the supplied default
$object = $parts->item( 0 )->getChildren();
}
if ( !$this->incrementIncludeSize( 'arg', strlen( $text ) ) ) {
$error = '<!-- WARNING: argument omitted, expansion size too large -->';
$this->limitationWarn( 'post-expand-template-argument' );
}
if ( $text === false && $object === false ) {
# No match anywhere
$object = $frame->virtualBracketedImplode( '{{{', '|', '}}}', $nameWithSpaces, $parts );
}
if ( $error !== false ) {
$text .= $error;
}
if ( $object !== false ) {
$ret = array( 'object' => $object );
} else {
$ret = array( 'text' => $text );
}
wfProfileOut( __METHOD__ );
return $ret;
}
/**
* Return the text to be used for a given extension tag.
* This is the ghost of strip().
*
* @param array $params Associative array of parameters:
* name PPNode for the tag name
* attr PPNode for unparsed text where tag attributes are thought to be
* attributes Optional associative array of parsed attributes
* inner Contents of extension element
* noClose Original text did not have a close tag
* @param PPFrame $frame
*/
function extensionSubstitution( $params, $frame ) {
global $wgRawHtml, $wgContLang;
$name = $frame->expand( $params['name'] );
$attrText = !isset( $params['attr'] ) ? null : $frame->expand( $params['attr'] );
$content = !isset( $params['inner'] ) ? null : $frame->expand( $params['inner'] );
$marker = "{$this->mUniqPrefix}-$name-" . sprintf('%08X', $this->mMarkerIndex++) . self::MARKER_SUFFIX;
$isFunctionTag = isset( $this->mFunctionTagHooks[strtolower($name)] ) &&
( $this->ot['html'] || $this->ot['pre'] );
if ( $isFunctionTag ) {
$markerType = 'none';
} else {
$markerType = 'general';
}
if ( $this->ot['html'] || $isFunctionTag ) {
$name = strtolower( $name );
$attributes = Sanitizer::decodeTagAttributes( $attrText );
if ( isset( $params['attributes'] ) ) {
$attributes = $attributes + $params['attributes'];
}
if( isset( $this->mTagHooks[$name] ) ) {
# Workaround for PHP bug 35229 and similar
if ( !is_callable( $this->mTagHooks[$name] ) ) {
throw new MWException( "Tag hook for $name is not callable\n" );
}
$output = call_user_func_array( $this->mTagHooks[$name],
array( $content, $attributes, $this, $frame ) );
} elseif( isset( $this->mFunctionTagHooks[$name] ) ) {
list( $callback, $flags ) = $this->mFunctionTagHooks[$name];
if( !is_callable( $callback ) )
throw new MWException( "Tag hook for $name is not callable\n" );
$output = call_user_func_array( $callback,
array( &$this, $frame, $content, $attributes ) );
} else {
$output = '<span class="error">Invalid tag extension name: ' .
htmlspecialchars( $name ) . '</span>';
}
if ( is_array( $output ) ) {
// Extract flags to local scope (to override $markerType)
$flags = $output;
$output = $flags[0];
unset( $flags[0] );
extract( $flags );
}
} else {
if ( is_null( $attrText ) ) {
$attrText = '';
}
if ( isset( $params['attributes'] ) ) {
foreach ( $params['attributes'] as $attrName => $attrValue ) {
$attrText .= ' ' . htmlspecialchars( $attrName ) . '="' .
htmlspecialchars( $attrValue ) . '"';
}
}
if ( $content === null ) {
$output = "<$name$attrText/>";
} else {
$close = is_null( $params['close'] ) ? '' : $frame->expand( $params['close'] );
$output = "<$name$attrText>$content$close";
}
}
if( $markerType === 'none' ) {
return $output;
} elseif ( $markerType === 'nowiki' ) {
$this->mStripState->nowiki->setPair( $marker, $output );
} elseif ( $markerType === 'general' ) {
$this->mStripState->general->setPair( $marker, $output );
} else {
throw new MWException( __METHOD__.': invalid marker type' );
}
return $marker;
}
/**
* Increment an include size counter
*
* @param string $type The type of expansion
* @param integer $size The size of the text
* @return boolean False if this inclusion would take it over the maximum, true otherwise
*/
function incrementIncludeSize( $type, $size ) {
if ( $this->mIncludeSizes[$type] + $size > $this->mOptions->getMaxIncludeSize( $type ) ) {
return false;
} else {
$this->mIncludeSizes[$type] += $size;
return true;
}
}
/**
* Increment the expensive function count
*
* @return boolean False if the limit has been exceeded
*/
function incrementExpensiveFunctionCount() {
global $wgExpensiveParserFunctionLimit;
$this->mExpensiveFunctionCount++;
if($this->mExpensiveFunctionCount <= $wgExpensiveParserFunctionLimit) {
return true;
}
return false;
}
/**
* Strip double-underscore items like __NOGALLERY__ and __NOTOC__
* Fills $this->mDoubleUnderscores, returns the modified text
*/
function doDoubleUnderscore( $text ) {
wfProfileIn( __METHOD__ );
// The position of __TOC__ needs to be recorded
$mw = MagicWord::get( 'toc' );
if( $mw->match( $text ) ) {
$this->mShowToc = true;
$this->mForceTocPosition = true;
// Set a placeholder. At the end we'll fill it in with the TOC.
$text = $mw->replace( '<!--MWTOC-->', $text, 1 );
// Only keep the first one.
$text = $mw->replace( '', $text );
}
// Now match and remove the rest of them
$mwa = MagicWord::getDoubleUnderscoreArray();
$this->mDoubleUnderscores = $mwa->matchAndRemove( $text );
if ( isset( $this->mDoubleUnderscores['nogallery'] ) ) {
$this->mOutput->mNoGallery = true;
}
if ( isset( $this->mDoubleUnderscores['notoc'] ) && !$this->mForceTocPosition ) {
$this->mShowToc = false;
}
if ( isset( $this->mDoubleUnderscores['hiddencat'] ) && $this->mTitle->getNamespace() == NS_CATEGORY ) {
$this->mOutput->setProperty( 'hiddencat', 'y' );
$this->addTrackingCategory( 'hidden-category-category' );
}
# (bug 8068) Allow control over whether robots index a page.
#
# FIXME (bug 14899): __INDEX__ always overrides __NOINDEX__ here! This
# is not desirable, the last one on the page should win.
if( isset( $this->mDoubleUnderscores['noindex'] ) && $this->mTitle->canUseNoindex() ) {
$this->mOutput->setIndexPolicy( 'noindex' );
$this->addTrackingCategory( 'noindex-category' );
}
if( isset( $this->mDoubleUnderscores['index'] ) && $this->mTitle->canUseNoindex() ){
$this->mOutput->setIndexPolicy( 'index' );
$this->addTrackingCategory( 'index-category' );
}
wfProfileOut( __METHOD__ );
return $text;
}
/**
* Add a tracking category, getting the title from a system message,
* or print a debug message if the title is invalid.
* @param $msg String message key
* @return Bool whether the addition was successful
*/
protected function addTrackingCategory( $msg ){
$cat = wfMsgForContent( $msg );
# Allow tracking categories to be disabled by setting them to "-"
if( $cat === '-' ) return false;
$containerCategory = Title::makeTitleSafe( NS_CATEGORY, $cat );
if ( $containerCategory ) {
$this->mOutput->addCategory( $containerCategory->getDBkey(), $this->getDefaultSort() );
return true;
} else {
wfDebug( __METHOD__.": [[MediaWiki:$msg]] is not a valid title!\n" );
return false;
}
}
/**
* This function accomplishes several tasks:
* 1) Auto-number headings if that option is enabled
* 2) Add an [edit] link to sections for users who have enabled the option and can edit the page
* 3) Add a Table of contents on the top for users who have enabled the option
* 4) Auto-anchor headings
*
* It loops through all headlines, collects the necessary data, then splits up the
* string and re-inserts the newly formatted headlines.
*
* @param string $text
* @param string $origText Original, untouched wikitext
* @param boolean $isMain
* @private
*/
function formatHeadings( $text, $origText, $isMain=true ) {
global $wgMaxTocLevel, $wgContLang, $wgHtml5, $wgExperimentalHtmlIds;
$doNumberHeadings = $this->mOptions->getNumberHeadings();
$showEditLink = $this->mOptions->getEditSection();
// Do not call quickUserCan unless necessary
if( $showEditLink && !$this->mTitle->quickUserCan( 'edit' ) ) {
$showEditLink = 0;
}
# Inhibit editsection links if requested in the page
if ( isset( $this->mDoubleUnderscores['noeditsection'] ) || $this->mOptions->getIsPrintable() ) {
$showEditLink = 0;
}
# Get all headlines for numbering them and adding funky stuff like [edit]
# links - this is for later, but we need the number of headlines right now
$matches = array();
$numMatches = preg_match_all( '/<H(?P<level>[1-6])(?P<attrib>.*?'.'>)(?P<header>.*?)<\/H[1-6] *>/i', $text, $matches );
# if there are fewer than 4 headlines in the article, do not show TOC
# unless it's been explicitly enabled.
$enoughToc = $this->mShowToc &&
(($numMatches >= 4) || $this->mForceTocPosition);
# Allow user to stipulate that a page should have a "new section"
# link added via __NEWSECTIONLINK__
if ( isset( $this->mDoubleUnderscores['newsectionlink'] ) ) {
$this->mOutput->setNewSection( true );
}
# Allow user to remove the "new section"
# link via __NONEWSECTIONLINK__
if ( isset( $this->mDoubleUnderscores['nonewsectionlink'] ) ) {
$this->mOutput->hideNewSection( true );
}
# if the string __FORCETOC__ (not case-sensitive) occurs in the HTML,
# override above conditions and always show TOC above first header
if ( isset( $this->mDoubleUnderscores['forcetoc'] ) ) {
$this->mShowToc = true;
$enoughToc = true;
}
# We need this to perform operations on the HTML
$sk = $this->mOptions->getSkin();
# headline counter
$headlineCount = 0;
$numVisible = 0;
# Ugh .. the TOC should have neat indentation levels which can be
# passed to the skin functions. These are determined here
$toc = '';
$full = '';
$head = array();
$sublevelCount = array();
$levelCount = array();
$toclevel = 0;
$level = 0;
$prevlevel = 0;
$toclevel = 0;
$prevtoclevel = 0;
$markerRegex = "{$this->mUniqPrefix}-h-(\d+)-" . self::MARKER_SUFFIX;
$baseTitleText = $this->mTitle->getPrefixedDBkey();
$oldType = $this->mOutputType;
$this->setOutputType( self::OT_WIKI );
$frame = $this->getPreprocessor()->newFrame();
$root = $this->preprocessToDom( $origText );
$node = $root->getFirstChild();
$byteOffset = 0;
$tocraw = array();
foreach( $matches[3] as $headline ) {
$isTemplate = false;
$titleText = false;
$sectionIndex = false;
$numbering = '';
$markerMatches = array();
if (preg_match("/^$markerRegex/", $headline, $markerMatches)) {
$serial = $markerMatches[1];
list( $titleText, $sectionIndex ) = $this->mHeadings[$serial];
$isTemplate = ($titleText != $baseTitleText);
$headline = preg_replace("/^$markerRegex/", "", $headline);
}
if( $toclevel ) {
$prevlevel = $level;
$prevtoclevel = $toclevel;
}
$level = $matches[1][$headlineCount];
if ( $level > $prevlevel ) {
# Increase TOC level
$toclevel++;
$sublevelCount[$toclevel] = 0;
if( $toclevel<$wgMaxTocLevel ) {
$prevtoclevel = $toclevel;
$toc .= $sk->tocIndent();
$numVisible++;
}
}
elseif ( $level < $prevlevel && $toclevel > 1 ) {
# Decrease TOC level, find level to jump to
for ($i = $toclevel; $i > 0; $i--) {
if ( $levelCount[$i] == $level ) {
# Found last matching level
$toclevel = $i;
break;
}
elseif ( $levelCount[$i] < $level ) {
# Found first matching level below current level
$toclevel = $i + 1;
break;
}
}
if( $i == 0 ) $toclevel = 1;
if( $toclevel<$wgMaxTocLevel ) {
if($prevtoclevel < $wgMaxTocLevel) {
# Unindent only if the previous toc level was shown :p
$toc .= $sk->tocUnindent( $prevtoclevel - $toclevel );
$prevtoclevel = $toclevel;
} else {
$toc .= $sk->tocLineEnd();
}
}
}
else {
# No change in level, end TOC line
if( $toclevel<$wgMaxTocLevel ) {
$toc .= $sk->tocLineEnd();
}
}
$levelCount[$toclevel] = $level;
# count number of headlines for each level
@$sublevelCount[$toclevel]++;
$dot = 0;
for( $i = 1; $i <= $toclevel; $i++ ) {
if( !empty( $sublevelCount[$i] ) ) {
if( $dot ) {
$numbering .= '.';
}
$numbering .= $wgContLang->formatNum( $sublevelCount[$i] );
$dot = 1;
}
}
# The safe header is a version of the header text safe to use for links
# Avoid insertion of weird stuff like <math> by expanding the relevant sections
$safeHeadline = $this->mStripState->unstripBoth( $headline );
# Remove link placeholders by the link text.
# <!--LINK number-->
# turns into
# link text with suffix
$safeHeadline = $this->replaceLinkHoldersText( $safeHeadline );
# Strip out HTML (other than plain <sup> and <sub>: bug 8393)
$tocline = preg_replace(
array( '#<(?!/?(sup|sub)).*?'.'>#', '#<(/?(sup|sub)).*?'.'>#' ),
array( '', '<$1>'),
$safeHeadline
);
$tocline = trim( $tocline );
# For the anchor, strip out HTML-y stuff period
$safeHeadline = preg_replace( '/<.*?'.'>/', '', $safeHeadline );
$safeHeadline = preg_replace( '/[ _]+/', ' ', $safeHeadline );
$safeHeadline = trim( $safeHeadline );
# Save headline for section edit hint before it's escaped
$headlineHint = $safeHeadline;
if ( $wgHtml5 && $wgExperimentalHtmlIds ) {
# For reverse compatibility, provide an id that's
# HTML4-compatible, like we used to.
#
# It may be worth noting, academically, that it's possible for
# the legacy anchor to conflict with a non-legacy headline
# anchor on the page. In this case likely the "correct" thing
# would be to either drop the legacy anchors or make sure
# they're numbered first. However, this would require people
# to type in section names like "abc_.D7.93.D7.90.D7.A4"
# manually, so let's not bother worrying about it.
$legacyHeadline = Sanitizer::escapeId( $safeHeadline,
array( 'noninitial', 'legacy' ) );
$safeHeadline = Sanitizer::escapeId( $safeHeadline );
if ( $legacyHeadline == $safeHeadline ) {
# No reason to have both (in fact, we can't)
$legacyHeadline = false;
}
} else {
$legacyHeadline = false;
$safeHeadline = Sanitizer::escapeId( $safeHeadline,
'noninitial' );
}
# HTML names must be case-insensitively unique (bug 10721). FIXME:
# Does this apply to Unicode characters? Because we aren't
# handling those here.
$arrayKey = strtolower( $safeHeadline );
if ( $legacyHeadline === false ) {
$legacyArrayKey = false;
} else {
$legacyArrayKey = strtolower( $legacyHeadline );
}
# count how many in assoc. array so we can track dupes in anchors
if ( isset( $refers[$arrayKey] ) ) {
$refers[$arrayKey]++;
} else {
$refers[$arrayKey] = 1;
}
if ( isset( $refers[$legacyArrayKey] ) ) {
$refers[$legacyArrayKey]++;
} else {
$refers[$legacyArrayKey] = 1;
}
# Don't number the heading if it is the only one (looks silly)
if( $doNumberHeadings && count( $matches[3] ) > 1) {
# the two are different if the line contains a link
$headline = $numbering . ' ' . $headline;
}
# Create the anchor for linking from the TOC to the section
$anchor = $safeHeadline;
$legacyAnchor = $legacyHeadline;
if ( $refers[$arrayKey] > 1 ) {
$anchor .= '_' . $refers[$arrayKey];
}
if ( $legacyHeadline !== false && $refers[$legacyArrayKey] > 1 ) {
$legacyAnchor .= '_' . $refers[$legacyArrayKey];
}
if( $enoughToc && ( !isset($wgMaxTocLevel) || $toclevel<$wgMaxTocLevel ) ) {
$toc .= $sk->tocLine($anchor, $tocline,
$numbering, $toclevel, ($isTemplate ? false : $sectionIndex));
}
# Add the section to the section tree
# Find the DOM node for this header
while ( $node && !$isTemplate ) {
if ( $node->getName() === 'h' ) {
$bits = $node->splitHeading();
if ( $bits['i'] == $sectionIndex )
break;
}
$byteOffset += mb_strlen( $this->mStripState->unstripBoth(
$frame->expand( $node, PPFrame::RECOVER_ORIG ) ) );
$node = $node->getNextSibling();
}
$tocraw[] = array(
'toclevel' => $toclevel,
'level' => $level,
'line' => $tocline,
'number' => $numbering,
'index' => ($isTemplate ? 'T-' : '' ) . $sectionIndex,
'fromtitle' => $titleText,
'byteoffset' => ( $isTemplate ? null : $byteOffset ),
'anchor' => $anchor,
);
# give headline the correct <h#> tag
if( $showEditLink && $sectionIndex !== false ) {
if( $isTemplate ) {
# Put a T flag in the section identifier, to indicate to extractSections()
# that sections inside <includeonly> should be counted.
$editlink = $sk->doEditSectionLink(Title::newFromText( $titleText ), "T-$sectionIndex");
} else {
$editlink = $sk->doEditSectionLink($this->mTitle, $sectionIndex, $headlineHint);
}
} else {
$editlink = '';
}
$head[$headlineCount] = $sk->makeHeadline( $level,
$matches['attrib'][$headlineCount], $anchor, $headline,
$editlink, $legacyAnchor );
$headlineCount++;
}
$this->setOutputType( $oldType );
# Never ever show TOC if no headers
if( $numVisible < 1 ) {
$enoughToc = false;
}
if( $enoughToc ) {
if( $prevtoclevel > 0 && $prevtoclevel < $wgMaxTocLevel ) {
$toc .= $sk->tocUnindent( $prevtoclevel - 1 );
}
$toc = $sk->tocList( $toc );
$this->mOutput->setTOCHTML( $toc );
}
if ( $isMain ) {
$this->mOutput->setSections( $tocraw );
}
# split up and insert constructed headlines
$blocks = preg_split( '/<H[1-6].*?' . '>.*?<\/H[1-6]>/i', $text );
$i = 0;
foreach( $blocks as $block ) {
if( $showEditLink && $headlineCount > 0 && $i == 0 && $block !== "\n" ) {
# This is the [edit] link that appears for the top block of text when
# section editing is enabled
# Disabled because it broke block formatting
# For example, a bullet point in the top line
# $full .= $sk->editSectionLink(0);
}
$full .= $block;
if( $enoughToc && !$i && $isMain && !$this->mForceTocPosition ) {
# Top anchor now in skin
$full = $full.$toc;
}
if( !empty( $head[$i] ) ) {
$full .= $head[$i];
}
$i++;
}
if( $this->mForceTocPosition ) {
return str_replace( '<!--MWTOC-->', $toc, $full );
} else {
return $full;
}
}
/**
* Merge $tree2 into $tree1 by replacing the section with index
* $section in $tree1 and its descendants with the sections in $tree2.
* Note that in the returned section tree, only the 'index' and
* 'byteoffset' fields are guaranteed to be correct.
* @param $tree1 array Section tree from ParserOutput::getSectons()
* @param $tree2 array Section tree
* @param $section int Section index
* @param $title Title Title both section trees come from
* @param $len2 int Length of the original wikitext for $tree2
* @return array Merged section tree
*/
public static function mergeSectionTrees( $tree1, $tree2, $section, $title, $len2 ) {
global $wgContLang;
$newTree = array();
$targetLevel = false;
$merged = false;
$lastLevel = 1;
$nextIndex = 1;
$numbering = array( 0 );
$titletext = $title->getPrefixedDBkey();
foreach ( $tree1 as $s ) {
if ( $targetLevel !== false ) {
if ( $s['level'] <= $targetLevel )
// We've skipped enough
$targetLevel = false;
else
continue;
}
if ( $s['index'] != $section ||
$s['fromtitle'] != $titletext ) {
self::incrementNumbering( $numbering,
$s['toclevel'], $lastLevel );
// Rewrite index, byteoffset and number
if ( $s['fromtitle'] == $titletext ) {
$s['index'] = $nextIndex++;
if ( $merged )
$s['byteoffset'] += $len2;
}
$s['number'] = implode( '.', array_map(
array( $wgContLang, 'formatnum' ),
$numbering ) );
$lastLevel = $s['toclevel'];
$newTree[] = $s;
} else {
// We're at $section
// Insert sections from $tree2 here
foreach ( $tree2 as $s2 ) {
// Rewrite the fields in $s2
// before inserting it
$s2['toclevel'] += $s['toclevel'] - 1;
$s2['level'] += $s['level'] - 1;
$s2['index'] = $nextIndex++;
$s2['byteoffset'] += $s['byteoffset'];
self::incrementNumbering( $numbering,
$s2['toclevel'], $lastLevel );
$s2['number'] = implode( '.', array_map(
array( $wgContLang, 'formatnum' ),
$numbering ) );
$lastLevel = $s2['toclevel'];
$newTree[] = $s2;
}
// Skip all descendants of $section in $tree1
$targetLevel = $s['level'];
$merged = true;
}
}
return $newTree;
}
/**
* Increment a section number. Helper function for mergeSectionTrees()
* @param $number array Array representing a section number
* @param $level int Current TOC level (depth)
* @param $lastLevel int Level of previous TOC entry
*/
private static function incrementNumbering( &$number, $level, $lastLevel ) {
if ( $level > $lastLevel )
$number[$level - 1] = 1;
else if ( $level < $lastLevel ) {
foreach ( $number as $key => $unused )
if ( $key >= $level )
unset( $number[$key] );
$number[$level - 1]++;
} else
$number[$level - 1]++;
}
/**
* Transform wiki markup when saving a page by doing \r\n -> \n
* conversion, substitting signatures, {{subst:}} templates, etc.
*
* @param string $text the text to transform
* @param Title &$title the Title object for the current article
* @param User $user the User object describing the current user
* @param ParserOptions $options parsing options
* @param bool $clearState whether to clear the parser state first
* @return string the altered wiki markup
* @public
*/
function preSaveTransform( $text, Title $title, $user, $options, $clearState = true ) {
$this->mOptions = $options;
$this->setTitle( $title );
$this->setOutputType( self::OT_WIKI );
if ( $clearState ) {
$this->clearState();
}
$pairs = array(
"\r\n" => "\n",
);
$text = str_replace( array_keys( $pairs ), array_values( $pairs ), $text );
$text = $this->pstPass2( $text, $user );
$text = $this->mStripState->unstripBoth( $text );
return $text;
}
/**
* Pre-save transform helper function
* @private
*/
function pstPass2( $text, $user ) {
global $wgContLang, $wgLocaltimezone;
/* Note: This is the timestamp saved as hardcoded wikitext to
* the database, we use $wgContLang here in order to give
* everyone the same signature and use the default one rather
* than the one selected in each user's preferences.
*
* (see also bug 12815)
*/
$ts = $this->mOptions->getTimestamp();
if ( isset( $wgLocaltimezone ) ) {
$tz = $wgLocaltimezone;
} else {
$tz = date_default_timezone_get();
}
$unixts = wfTimestamp( TS_UNIX, $ts );
$oldtz = date_default_timezone_get();
date_default_timezone_set( $tz );
$ts = date( 'YmdHis', $unixts );
$tzMsg = date( 'T', $unixts ); # might vary on DST changeover!
/* Allow translation of timezones trough wiki. date() can return
* whatever crap the system uses, localised or not, so we cannot
* ship premade translations.
*/
$key = 'timezone-' . strtolower( trim( $tzMsg ) );
$value = wfMsgForContent( $key );
if ( !wfEmptyMsg( $key, $value ) ) $tzMsg = $value;
date_default_timezone_set( $oldtz );
$d = $wgContLang->timeanddate( $ts, false, false ) . " ($tzMsg)";
# Variable replacement
# Because mOutputType is OT_WIKI, this will only process {{subst:xxx}} type tags
$text = $this->replaceVariables( $text );
# Signatures
$sigText = $this->getUserSig( $user );
$text = strtr( $text, array(
'~~~~~' => $d,
'~~~~' => "$sigText $d",
'~~~' => $sigText
) );
# Context links: [[|name]] and [[name (context)|]]
#
global $wgLegalTitleChars;
$tc = "[$wgLegalTitleChars]";
$nc = '[ _0-9A-Za-z\x80-\xff-]'; # Namespaces can use non-ascii!
$p1 = "/\[\[(:?$nc+:|:|)($tc+?)( \\($tc+\\))\\|]]/"; # [[ns:page (context)|]]
$p4 = "/\[\[(:?$nc+:|:|)($tc+?)(($tc+))\\|]]/"; # [[ns:page(context)|]]
$p3 = "/\[\[(:?$nc+:|:|)($tc+?)( \\($tc+\\)|)(, $tc+|)\\|]]/"; # [[ns:page (context), context|]]
$p2 = "/\[\[\\|($tc+)]]/"; # [[|page]]
# try $p1 first, to turn "[[A, B (C)|]]" into "[[A, B (C)|A, B]]"
$text = preg_replace( $p1, '[[\\1\\2\\3|\\2]]', $text );
$text = preg_replace( $p4, '[[\\1\\2\\3|\\2]]', $text );
$text = preg_replace( $p3, '[[\\1\\2\\3\\4|\\2]]', $text );
$t = $this->mTitle->getText();
$m = array();
if ( preg_match( "/^($nc+:|)$tc+?( \\($tc+\\))$/", $t, $m ) ) {
$text = preg_replace( $p2, "[[$m[1]\\1$m[2]|\\1]]", $text );
} elseif ( preg_match( "/^($nc+:|)$tc+?(, $tc+|)$/", $t, $m ) && "$m[1]$m[2]" != '' ) {
$text = preg_replace( $p2, "[[$m[1]\\1$m[2]|\\1]]", $text );
} else {
# if there's no context, don't bother duplicating the title
$text = preg_replace( $p2, '[[\\1]]', $text );
}
# Trim trailing whitespace
$text = rtrim( $text );
return $text;
}
/**
* Fetch the user's signature text, if any, and normalize to
* validated, ready-to-insert wikitext.
* If you have pre-fetched the nickname or the fancySig option, you can
* specify them here to save a database query.
*
* @param User $user
* @return string
*/
function getUserSig( &$user, $nickname = false, $fancySig = null ) {
global $wgMaxSigChars;
$username = $user->getName();
// If not given, retrieve from the user object.
if ( $nickname === false )
$nickname = $user->getOption( 'nickname' );
if ( is_null( $fancySig ) )
$fancySig = $user->getBoolOption( 'fancysig' );
$nickname = $nickname == null ? $username : $nickname;
if( mb_strlen( $nickname ) > $wgMaxSigChars ) {
$nickname = $username;
wfDebug( __METHOD__ . ": $username has overlong signature.\n" );
} elseif( $fancySig !== false ) {
# Sig. might contain markup; validate this
if( $this->validateSig( $nickname ) !== false ) {
# Validated; clean up (if needed) and return it
return $this->cleanSig( $nickname, true );
} else {
# Failed to validate; fall back to the default
$nickname = $username;
wfDebug( __METHOD__.": $username has bad XML tags in signature.\n" );
}
}
// Make sure nickname doesnt get a sig in a sig
$nickname = $this->cleanSigInSig( $nickname );
# If we're still here, make it a link to the user page
$userText = wfEscapeWikiText( $username );
$nickText = wfEscapeWikiText( $nickname );
if ( $user->isAnon() ) {
return wfMsgExt( 'signature-anon', array( 'content', 'parsemag' ), $userText, $nickText );
} else {
return wfMsgExt( 'signature', array( 'content', 'parsemag' ), $userText, $nickText );
}
}
/**
* Check that the user's signature contains no bad XML
*
* @param string $text
* @return mixed An expanded string, or false if invalid.
*/
function validateSig( $text ) {
return( Xml::isWellFormedXmlFragment( $text ) ? $text : false );
}
/**
* Clean up signature text
*
* 1) Strip ~~~, ~~~~ and ~~~~~ out of signatures @see cleanSigInSig
* 2) Substitute all transclusions
*
* @param string $text
* @param $parsing Whether we're cleaning (preferences save) or parsing
* @return string Signature text
*/
function cleanSig( $text, $parsing = false ) {
if ( !$parsing ) {
global $wgTitle;
$this->clearState();
$this->setTitle( $wgTitle );
$this->mOptions = new ParserOptions;
$this->setOutputType = self::OT_PREPROCESS;
}
# Option to disable this feature
if ( !$this->mOptions->getCleanSignatures() ) {
return $text;
}
# FIXME: regex doesn't respect extension tags or nowiki
# => Move this logic to braceSubstitution()
$substWord = MagicWord::get( 'subst' );
$substRegex = '/\{\{(?!(?:' . $substWord->getBaseRegex() . '))/x' . $substWord->getRegexCase();
$substText = '{{' . $substWord->getSynonym( 0 );
$text = preg_replace( $substRegex, $substText, $text );
$text = $this->cleanSigInSig( $text );
$dom = $this->preprocessToDom( $text );
$frame = $this->getPreprocessor()->newFrame();
$text = $frame->expand( $dom );
if ( !$parsing ) {
$text = $this->mStripState->unstripBoth( $text );
}
return $text;
}
/**
* Strip ~~~, ~~~~ and ~~~~~ out of signatures
* @param string $text
* @return string Signature text with /~{3,5}/ removed
*/
function cleanSigInSig( $text ) {
$text = preg_replace( '/~{3,5}/', '', $text );
return $text;
}
/**
* Set up some variables which are usually set up in parse()
* so that an external function can call some class members with confidence
* @public
*/
function startExternalParse( &$title, $options, $outputType, $clearState = true ) {
$this->setTitle( $title );
$this->mOptions = $options;
$this->setOutputType( $outputType );
if ( $clearState ) {
$this->clearState();
}
}
/**
* Wrapper for preprocess()
*
* @param string $text the text to preprocess
* @param ParserOptions $options options
* @return string
* @public
*/
function transformMsg( $text, $options ) {
global $wgTitle;
static $executing = false;
# Guard against infinite recursion
if ( $executing ) {
return $text;
}
$executing = true;
wfProfileIn(__METHOD__);
$text = $this->preprocess( $text, $wgTitle, $options );
$executing = false;
wfProfileOut(__METHOD__);
return $text;
}
/**
* Create an HTML-style tag, e.g. <yourtag>special text</yourtag>
* The callback should have the following form:
* function myParserHook( $text, $params, &$parser ) { ... }
*
* Transform and return $text. Use $parser for any required context, e.g. use
* $parser->getTitle() and $parser->getOptions() not $wgTitle or $wgOut->mParserOptions
*
* @public
*
* @param mixed $tag The tag to use, e.g. 'hook' for <hook>
* @param mixed $callback The callback function (and object) to use for the tag
*
* @return The old value of the mTagHooks array associated with the hook
*/
function setHook( $tag, $callback ) {
$tag = strtolower( $tag );
$oldVal = isset( $this->mTagHooks[$tag] ) ? $this->mTagHooks[$tag] : null;
$this->mTagHooks[$tag] = $callback;
if( !in_array( $tag, $this->mStripList ) ) {
$this->mStripList[] = $tag;
}
return $oldVal;
}
function setTransparentTagHook( $tag, $callback ) {
$tag = strtolower( $tag );
$oldVal = isset( $this->mTransparentTagHooks[$tag] ) ? $this->mTransparentTagHooks[$tag] : null;
$this->mTransparentTagHooks[$tag] = $callback;
return $oldVal;
}
/**
* Remove all tag hooks
*/
function clearTagHooks() {
$this->mTagHooks = array();
$this->mStripList = $this->mDefaultStripList;
}
/**
* Create a function, e.g. {{sum:1|2|3}}
* The callback function should have the form:
* function myParserFunction( &$parser, $arg1, $arg2, $arg3 ) { ... }
*
* Or with SFH_OBJECT_ARGS:
* function myParserFunction( $parser, $frame, $args ) { ... }
*
* The callback may either return the text result of the function, or an array with the text
* in element 0, and a number of flags in the other elements. The names of the flags are
* specified in the keys. Valid flags are:
* found The text returned is valid, stop processing the template. This
* is on by default.
* nowiki Wiki markup in the return value should be escaped
* isHTML The returned text is HTML, armour it against wikitext transformation
*
* @public
*
* @param string $id The magic word ID
* @param mixed $callback The callback function (and object) to use
* @param integer $flags a combination of the following flags:
* SFH_NO_HASH No leading hash, i.e. {{plural:...}} instead of {{#if:...}}
*
* SFH_OBJECT_ARGS Pass the template arguments as PPNode objects instead of text. This
* allows for conditional expansion of the parse tree, allowing you to eliminate dead
* branches and thus speed up parsing. It is also possible to analyse the parse tree of
* the arguments, and to control the way they are expanded.
*
* The $frame parameter is a PPFrame. This can be used to produce expanded text from the
* arguments, for instance:
* $text = isset( $args[0] ) ? $frame->expand( $args[0] ) : '';
*
* For technical reasons, $args[0] is pre-expanded and will be a string. This may change in
* future versions. Please call $frame->expand() on it anyway so that your code keeps
* working if/when this is changed.
*
* If you want whitespace to be trimmed from $args, you need to do it yourself, post-
* expansion.
*
* Please read the documentation in includes/parser/Preprocessor.php for more information
* about the methods available in PPFrame and PPNode.
*
* @return The old callback function for this name, if any
*/
function setFunctionHook( $id, $callback, $flags = 0 ) {
global $wgContLang;
$oldVal = isset( $this->mFunctionHooks[$id] ) ? $this->mFunctionHooks[$id][0] : null;
$this->mFunctionHooks[$id] = array( $callback, $flags );
# Add to function cache
$mw = MagicWord::get( $id );
if( !$mw )
throw new MWException( __METHOD__.'() expecting a magic word identifier.' );
$synonyms = $mw->getSynonyms();
$sensitive = intval( $mw->isCaseSensitive() );
foreach ( $synonyms as $syn ) {
# Case
if ( !$sensitive ) {
$syn = $wgContLang->lc( $syn );
}
# Add leading hash
if ( !( $flags & SFH_NO_HASH ) ) {
$syn = '#' . $syn;
}
# Remove trailing colon
if ( substr( $syn, -1, 1 ) === ':' ) {
$syn = substr( $syn, 0, -1 );
}
$this->mFunctionSynonyms[$sensitive][$syn] = $id;
}
return $oldVal;
}
/**
* Get all registered function hook identifiers
*
* @return array
*/
function getFunctionHooks() {
return array_keys( $this->mFunctionHooks );
}
/**
* Create a tag function, e.g. <test>some stuff</test>.
* Unlike tag hooks, tag functions are parsed at preprocessor level.
* Unlike parser functions, their content is not preprocessed.
*/
function setFunctionTagHook( $tag, $callback, $flags ) {
$tag = strtolower( $tag );
$old = isset( $this->mFunctionTagHooks[$tag] ) ?
$this->mFunctionTagHooks[$tag] : null;
$this->mFunctionTagHooks[$tag] = array( $callback, $flags );
if( !in_array( $tag, $this->mStripList ) ) {
$this->mStripList[] = $tag;
}
return $old;
}
/**
* FIXME: update documentation. makeLinkObj() is deprecated.
* Replace <!--LINK--> link placeholders with actual links, in the buffer
* Placeholders created in Skin::makeLinkObj()
* Returns an array of link CSS classes, indexed by PDBK.
*/
function replaceLinkHolders( &$text, $options = 0 ) {
return $this->mLinkHolders->replace( $text );
}
/**
* Replace <!--LINK--> link placeholders with plain text of links
* (not HTML-formatted).
* @param string $text
* @return string
*/
function replaceLinkHoldersText( $text ) {
return $this->mLinkHolders->replaceText( $text );
}
/**
* Renders an image gallery from a text with one line per image.
* text labels may be given by using |-style alternative text. E.g.
* Image:one.jpg|The number "1"
* Image:tree.jpg|A tree
* given as text will return the HTML of a gallery with two images,
* labeled 'The number "1"' and
* 'A tree'.
*/
function renderImageGallery( $text, $params ) {
$ig = new ImageGallery();
$ig->setContextTitle( $this->mTitle );
$ig->setShowBytes( false );
$ig->setShowFilename( false );
$ig->setParser( $this );
$ig->setHideBadImages();
$ig->setAttributes( Sanitizer::validateTagAttributes( $params, 'table' ) );
$ig->useSkin( $this->mOptions->getSkin() );
$ig->mRevisionId = $this->mRevisionId;
if( isset( $params['caption'] ) ) {
$caption = $params['caption'];
$caption = htmlspecialchars( $caption );
$caption = $this->replaceInternalLinks( $caption );
$ig->setCaptionHtml( $caption );
}
if( isset( $params['perrow'] ) ) {
$ig->setPerRow( $params['perrow'] );
}
if( isset( $params['widths'] ) ) {
$ig->setWidths( $params['widths'] );
}
if( isset( $params['heights'] ) ) {
$ig->setHeights( $params['heights'] );
}
wfRunHooks( 'BeforeParserrenderImageGallery', array( &$this, &$ig ) );
$lines = StringUtils::explode( "\n", $text );
foreach ( $lines as $line ) {
# match lines like these:
# Image:someimage.jpg|This is some image
$matches = array();
preg_match( "/^([^|]+)(\\|(.*))?$/", $line, $matches );
# Skip empty lines
if ( count( $matches ) == 0 ) {
continue;
}
if ( strpos( $matches[0], '%' ) !== false )
$matches[1] = urldecode( $matches[1] );
$tp = Title::newFromText( $matches[1]/*, NS_FILE*/ );
$nt =& $tp;
if( is_null( $nt ) ) {
# Bogus title. Ignore these so we don't bomb out later.
continue;
}
if ( isset( $matches[3] ) ) {
$label = $matches[3];
} else {
$label = '';
}
$html = $this->recursiveTagParse( trim( $label ) );
$ig->add( $nt, $html );
# Only add real images (bug #5586)
if ( $nt->getNamespace() == NS_FILE ) {
$this->mOutput->addImage( $nt->getDBkey() );
}
}
return $ig->toHTML();
}
function getImageParams( $handler ) {
if ( $handler ) {
$handlerClass = get_class( $handler );
} else {
$handlerClass = '';
}
if ( !isset( $this->mImageParams[$handlerClass] ) ) {
// Initialise static lists
static $internalParamNames = array(
'horizAlign' => array( 'left', 'right', 'center', 'none' ),
'vertAlign' => array( 'baseline', 'sub', 'super', 'top', 'text-top', 'middle',
'bottom', 'text-bottom' ),
'frame' => array( 'thumbnail', 'manualthumb', 'framed', 'frameless',
'upright', 'border', 'link', 'alt' ),
);
static $internalParamMap;
if ( !$internalParamMap ) {
$internalParamMap = array();
foreach ( $internalParamNames as $type => $names ) {
foreach ( $names as $name ) {
$magicName = str_replace( '-', '_', "img_$name" );
$internalParamMap[$magicName] = array( $type, $name );
}
}
}
// Add handler params
$paramMap = $internalParamMap;
if ( $handler ) {
$handlerParamMap = $handler->getParamMap();
foreach ( $handlerParamMap as $magic => $paramName ) {
$paramMap[$magic] = array( 'handler', $paramName );
}
}
$this->mImageParams[$handlerClass] = $paramMap;
$this->mImageParamsMagicArray[$handlerClass] = new MagicWordArray( array_keys( $paramMap ) );
}
return array( $this->mImageParams[$handlerClass], $this->mImageParamsMagicArray[$handlerClass] );
}
/**
* Parse image options text and use it to make an image
* @param Title $title
* @param string $options
* @param LinkHolderArray $holders
*/
function makeImage( $title, $options, $holders = false ) {
# Check if the options text is of the form "options|alt text"
# Options are:
# * thumbnail make a thumbnail with enlarge-icon and caption, alignment depends on lang
# * left no resizing, just left align. label is used for alt= only
# * right same, but right aligned
# * none same, but not aligned
# * ___px scale to ___ pixels width, no aligning. e.g. use in taxobox
# * center center the image
# * frame Keep original image size, no magnify-button.
# * framed Same as "frame"
# * frameless like 'thumb' but without a frame. Keeps user preferences for width
# * upright reduce width for upright images, rounded to full __0 px
# * border draw a 1px border around the image
# * alt Text for HTML alt attribute (defaults to empty)
# * link Set the target of the image link. Can be external, interwiki, or local
# vertical-align values (no % or length right now):
# * baseline
# * sub
# * super
# * top
# * text-top
# * middle
# * bottom
# * text-bottom
$parts = StringUtils::explode( "|", $options );
$sk = $this->mOptions->getSkin();
# Give extensions a chance to select the file revision for us
$skip = $time = $descQuery = false;
wfRunHooks( 'BeforeParserMakeImageLinkObj', array( &$this, &$title, &$skip, &$time, &$descQuery ) );
if ( $skip ) {
return $sk->link( $title );
}
# Get the file
$imagename = $title->getDBkey();
$file = wfFindFile( $title, array( 'time' => $time ) );
# Get parameter map
$handler = $file ? $file->getHandler() : false;
list( $paramMap, $mwArray ) = $this->getImageParams( $handler );
# Process the input parameters
$caption = '';
$params = array( 'frame' => array(), 'handler' => array(),
'horizAlign' => array(), 'vertAlign' => array() );
foreach( $parts as $part ) {
$part = trim( $part );
list( $magicName, $value ) = $mwArray->matchVariableStartToEnd( $part );
$validated = false;
if( isset( $paramMap[$magicName] ) ) {
list( $type, $paramName ) = $paramMap[$magicName];
// Special case; width and height come in one variable together
if( $type === 'handler' && $paramName === 'width' ) {
$m = array();
# (bug 13500) In both cases (width/height and width only),
# permit trailing "px" for backward compatibility.
if ( preg_match( '/^([0-9]*)x([0-9]*)\s*(?:px)?\s*$/', $value, $m ) ) {
$width = intval( $m[1] );
$height = intval( $m[2] );
if ( $handler->validateParam( 'width', $width ) ) {
$params[$type]['width'] = $width;
$validated = true;
}
if ( $handler->validateParam( 'height', $height ) ) {
$params[$type]['height'] = $height;
$validated = true;
}
} elseif ( preg_match( '/^[0-9]*\s*(?:px)?\s*$/', $value ) ) {
$width = intval( $value );
if ( $handler->validateParam( 'width', $width ) ) {
$params[$type]['width'] = $width;
$validated = true;
}
} // else no validation -- bug 13436
} else {
if ( $type === 'handler' ) {
# Validate handler parameter
$validated = $handler->validateParam( $paramName, $value );
} else {
# Validate internal parameters
switch( $paramName ) {
case 'manualthumb':
case 'alt':
// @todo Fixme: possibly check validity here for
// manualthumb? downstream behavior seems odd with
// missing manual thumbs.
$validated = true;
$value = $this->stripAltText( $value, $holders );
break;
case 'link':
$chars = self::EXT_LINK_URL_CLASS;
$prots = $this->mUrlProtocols;
if ( $value === '' ) {
$paramName = 'no-link';
$value = true;
$validated = true;
} elseif ( preg_match( "/^$prots/", $value ) ) {
if ( preg_match( "/^($prots)$chars+$/", $value, $m ) ) {
$paramName = 'link-url';
$this->mOutput->addExternalLink( $value );
$validated = true;
}
} else {
$linkTitle = Title::newFromText( $value );
if ( $linkTitle ) {
$paramName = 'link-title';
$value = $linkTitle;
$this->mOutput->addLink( $linkTitle );
$validated = true;
}
}
break;
default:
// Most other things appear to be empty or numeric...
$validated = ( $value === false || is_numeric( trim( $value ) ) );
}
}
if ( $validated ) {
$params[$type][$paramName] = $value;
}
}
}
if ( !$validated ) {
$caption = $part;
}
}
# Process alignment parameters
if ( $params['horizAlign'] ) {
$params['frame']['align'] = key( $params['horizAlign'] );
}
if ( $params['vertAlign'] ) {
$params['frame']['valign'] = key( $params['vertAlign'] );
}
$params['frame']['caption'] = $caption;
# Will the image be presented in a frame, with the caption below?
$imageIsFramed = isset( $params['frame']['frame'] ) ||
isset( $params['frame']['framed'] ) ||
isset( $params['frame']['thumbnail'] ) ||
isset( $params['frame']['manualthumb'] );
# In the old days, [[Image:Foo|text...]] would set alt text. Later it
# came to also set the caption, ordinary text after the image -- which
# makes no sense, because that just repeats the text multiple times in
# screen readers. It *also* came to set the title attribute.
#
# Now that we have an alt attribute, we should not set the alt text to
# equal the caption: that's worse than useless, it just repeats the
# text. This is the framed/thumbnail case. If there's no caption, we
# use the unnamed parameter for alt text as well, just for the time be-
# ing, if the unnamed param is set and the alt param is not.
#
# For the future, we need to figure out if we want to tweak this more,
# e.g., introducing a title= parameter for the title; ignoring the un-
# named parameter entirely for images without a caption; adding an ex-
# plicit caption= parameter and preserving the old magic unnamed para-
# meter for BC; ...
if ( $imageIsFramed ) { # Framed image
if ( $caption === '' && !isset( $params['frame']['alt'] ) ) {
# No caption or alt text, add the filename as the alt text so
# that screen readers at least get some description of the image
$params['frame']['alt'] = $title->getText();
}
# Do not set $params['frame']['title'] because tooltips don't make sense
# for framed images
} else { # Inline image
if ( !isset( $params['frame']['alt'] ) ) {
# No alt text, use the "caption" for the alt text
if ( $caption !== '') {
$params['frame']['alt'] = $this->stripAltText( $caption, $holders );
} else {
# No caption, fall back to using the filename for the
# alt text
$params['frame']['alt'] = $title->getText();
}
}
# Use the "caption" for the tooltip text
$params['frame']['title'] = $this->stripAltText( $caption, $holders );
}
wfRunHooks( 'ParserMakeImageParams', array( $title, $file, &$params ) );
# Linker does the rest
$ret = $sk->makeImageLink2( $title, $file, $params['frame'], $params['handler'], $time, $descQuery );
# Give the handler a chance to modify the parser object
if ( $handler ) {
$handler->parserTransformHook( $this, $file );
}
return $ret;
}
protected function stripAltText( $caption, $holders ) {
# Strip bad stuff out of the title (tooltip). We can't just use
# replaceLinkHoldersText() here, because if this function is called
# from replaceInternalLinks2(), mLinkHolders won't be up-to-date.
if ( $holders ) {
$tooltip = $holders->replaceText( $caption );
} else {
$tooltip = $this->replaceLinkHoldersText( $caption );
}
# make sure there are no placeholders in thumbnail attributes
# that are later expanded to html- so expand them now and
# remove the tags
$tooltip = $this->mStripState->unstripBoth( $tooltip );
$tooltip = Sanitizer::stripAllTags( $tooltip );
return $tooltip;
}
/**
* Set a flag in the output object indicating that the content is dynamic and
* shouldn't be cached.
*/
function disableCache() {
wfDebug( "Parser output marked as uncacheable.\n" );
$this->mOutput->mCacheTime = -1;
}
/**#@+
* Callback from the Sanitizer for expanding items found in HTML attribute
* values, so they can be safely tested and escaped.
* @param string $text
* @param PPFrame $frame
* @return string
* @private
*/
function attributeStripCallback( &$text, $frame = false ) {
$text = $this->replaceVariables( $text, $frame );
$text = $this->mStripState->unstripBoth( $text );
return $text;
}
/**#@-*/
/**#@+
* Accessor/mutator
*/
function Title( $x = null ) { return wfSetVar( $this->mTitle, $x ); }
function Options( $x = null ) { return wfSetVar( $this->mOptions, $x ); }
function OutputType( $x = null ) { return wfSetVar( $this->mOutputType, $x ); }
/**#@-*/
/**#@+
* Accessor
*/
function getTags() { return array_merge( array_keys($this->mTransparentTagHooks), array_keys( $this->mTagHooks ) ); }
/**#@-*/
/**
* Break wikitext input into sections, and either pull or replace
* some particular section's text.
*
* External callers should use the getSection and replaceSection methods.
*
* @param string $text Page wikitext
* @param string $section A section identifier string of the form:
* <flag1> - <flag2> - ... - <section number>
*
* Currently the only recognised flag is "T", which means the target section number
* was derived during a template inclusion parse, in other words this is a template
* section edit link. If no flags are given, it was an ordinary section edit link.
* This flag is required to avoid a section numbering mismatch when a section is
* enclosed by <includeonly> (bug 6563).
*
* The section number 0 pulls the text before the first heading; other numbers will
* pull the given section along with its lower-level subsections. If the section is
* not found, $mode=get will return $newtext, and $mode=replace will return $text.
*
* @param string $mode One of "get" or "replace"
* @param string $newText Replacement text for section data.
* @return string for "get", the extracted section text.
* for "replace", the whole page with the section replaced.
*/
private function extractSections( $text, $section, $mode, $newText='' ) {
global $wgTitle;
$this->clearState();
$this->setTitle( $wgTitle ); // not generally used but removes an ugly failure mode
$this->mOptions = new ParserOptions;
$this->setOutputType( self::OT_WIKI );
$outText = '';
$frame = $this->getPreprocessor()->newFrame();
// Process section extraction flags
$flags = 0;
$sectionParts = explode( '-', $section );
$sectionIndex = array_pop( $sectionParts );
foreach ( $sectionParts as $part ) {
if ( $part === 'T' ) {
$flags |= self::PTD_FOR_INCLUSION;
}
}
// Preprocess the text
$root = $this->preprocessToDom( $text, $flags );
// <h> nodes indicate section breaks
// They can only occur at the top level, so we can find them by iterating the root's children
$node = $root->getFirstChild();
// Find the target section
if ( $sectionIndex == 0 ) {
// Section zero doesn't nest, level=big
$targetLevel = 1000;
} else {
while ( $node ) {
if ( $node->getName() === 'h' ) {
$bits = $node->splitHeading();
if ( $bits['i'] == $sectionIndex ) {
$targetLevel = $bits['level'];
break;
}
}
if ( $mode === 'replace' ) {
$outText .= $frame->expand( $node, PPFrame::RECOVER_ORIG );
}
$node = $node->getNextSibling();
}
}
if ( !$node ) {
// Not found
if ( $mode === 'get' ) {
return $newText;
} else {
return $text;
}
}
// Find the end of the section, including nested sections
do {
if ( $node->getName() === 'h' ) {
$bits = $node->splitHeading();
$curLevel = $bits['level'];
if ( $bits['i'] != $sectionIndex && $curLevel <= $targetLevel ) {
break;
}
}
if ( $mode === 'get' ) {
$outText .= $frame->expand( $node, PPFrame::RECOVER_ORIG );
}
$node = $node->getNextSibling();
} while ( $node );
// Write out the remainder (in replace mode only)
if ( $mode === 'replace' ) {
// Output the replacement text
// Add two newlines on -- trailing whitespace in $newText is conventionally
// stripped by the editor, so we need both newlines to restore the paragraph gap
// Only add trailing whitespace if there is newText
if($newText != "") {
$outText .= $newText . "\n\n";
}
while ( $node ) {
$outText .= $frame->expand( $node, PPFrame::RECOVER_ORIG );
$node = $node->getNextSibling();
}
}
if ( is_string( $outText ) ) {
// Re-insert stripped tags
$outText = rtrim( $this->mStripState->unstripBoth( $outText ) );
}
return $outText;
}
/**
* This function returns the text of a section, specified by a number ($section).
* A section is text under a heading like == Heading == or \<h1\>Heading\</h1\>, or
* the first section before any such heading (section 0).
*
* If a section contains subsections, these are also returned.
*
* @param string $text text to look in
* @param string $section section identifier
* @param string $deftext default to return if section is not found
* @return string text of the requested section
*/
public function getSection( $text, $section, $deftext='' ) {
return $this->extractSections( $text, $section, "get", $deftext );
}
public function replaceSection( $oldtext, $section, $text ) {
return $this->extractSections( $oldtext, $section, "replace", $text );
}
/**
* Get the timestamp associated with the current revision, adjusted for
* the default server-local timestamp
*/
function getRevisionTimestamp() {
if ( is_null( $this->mRevisionTimestamp ) ) {
wfProfileIn( __METHOD__ );
global $wgContLang;
$dbr = wfGetDB( DB_SLAVE );
$timestamp = $dbr->selectField( 'revision', 'rev_timestamp',
array( 'rev_id' => $this->mRevisionId ), __METHOD__ );
// Normalize timestamp to internal MW format for timezone processing.
// This has the added side-effect of replacing a null value with
// the current time, which gives us more sensible behavior for
// previews.
$timestamp = wfTimestamp( TS_MW, $timestamp );
// The cryptic '' timezone parameter tells to use the site-default
// timezone offset instead of the user settings.
//
// Since this value will be saved into the parser cache, served
// to other users, and potentially even used inside links and such,
// it needs to be consistent for all visitors.
$this->mRevisionTimestamp = $wgContLang->userAdjust( $timestamp, '' );
wfProfileOut( __METHOD__ );
}
return $this->mRevisionTimestamp;
}
/**
* Get the name of the user that edited the last revision
*/
function getRevisionUser() {
// if this template is subst: the revision id will be blank,
// so just use the current user's name
if( $this->mRevisionId ) {
$revision = Revision::newFromId( $this->mRevisionId );
$revuser = $revision->getUserText();
} else {
global $wgUser;
$revuser = $wgUser->getName();
}
return $revuser;
}
/**
* Mutator for $mDefaultSort
*
* @param $sort New value
*/
public function setDefaultSort( $sort ) {
$this->mDefaultSort = $sort;
}
/**
* Accessor for $mDefaultSort
* Will use the title/prefixed title if none is set
*
* @return string
*/
public function getDefaultSort() {
global $wgCategoryPrefixedDefaultSortkey;
if( $this->mDefaultSort !== false ) {
return $this->mDefaultSort;
} elseif ($this->mTitle->getNamespace() == NS_CATEGORY ||
!$wgCategoryPrefixedDefaultSortkey) {
return $this->mTitle->getText();
} else {
return $this->mTitle->getPrefixedText();
}
}
/**
* Accessor for $mDefaultSort
* Unlike getDefaultSort(), will return false if none is set
*
* @return string or false
*/
public function getCustomDefaultSort() {
return $this->mDefaultSort;
}
/**
* Try to guess the section anchor name based on a wikitext fragment
* presumably extracted from a heading, for example "Header" from
* "== Header ==".
*/
public function guessSectionNameFromWikiText( $text ) {
# Strip out wikitext links(they break the anchor)
$text = $this->stripSectionName( $text );
$headline = Sanitizer::decodeCharReferences( $text );
# strip out HTML
$headline = StringUtils::delimiterReplace( '<', '>', '', $headline );
$headline = trim( $headline );
$sectionanchor = '#' . urlencode( str_replace( ' ', '_', $headline ) );
$replacearray = array(
'%3A' => ':',
'%' => '.'
);
return str_replace(
array_keys( $replacearray ),
array_values( $replacearray ),
$sectionanchor );
}
/**
* Strips a text string of wikitext for use in a section anchor
*
* Accepts a text string and then removes all wikitext from the
* string and leaves only the resultant text (i.e. the result of
* [[User:WikiSysop|Sysop]] would be "Sysop" and the result of
* [[User:WikiSysop]] would be "User:WikiSysop") - this is intended
* to create valid section anchors by mimicing the output of the
* parser when headings are parsed.
*
* @param $text string Text string to be stripped of wikitext
* for use in a Section anchor
* @return Filtered text string
*/
public function stripSectionName( $text ) {
# Strip internal link markup
$text = preg_replace('/\[\[:?([^[|]+)\|([^[]+)\]\]/','$2',$text);
$text = preg_replace('/\[\[:?([^[]+)\|?\]\]/','$1',$text);
# Strip external link markup (FIXME: Not Tolerant to blank link text
# I.E. [http://www.mediawiki.org] will render as [1] or something depending
# on how many empty links there are on the page - need to figure that out.
$text = preg_replace('/\[(?:' . wfUrlProtocols() . ')([^ ]+?) ([^[]+)\]/','$2',$text);
# Parse wikitext quotes (italics & bold)
$text = $this->doQuotes($text);
# Strip HTML tags
$text = StringUtils::delimiterReplace( '<', '>', '', $text );
return $text;
}
function srvus( $text ) {
return $this->testSrvus( $text, $this->mOutputType );
}
/**
* strip/replaceVariables/unstrip for preprocessor regression testing
*/
function testSrvus( $text, $title, $options, $outputType = self::OT_HTML ) {
$this->clearState();
if ( ! ( $title instanceof Title ) ) {
$title = Title::newFromText( $title );
}
$this->mTitle = $title;
$this->mOptions = $options;
$this->setOutputType( $outputType );
$text = $this->replaceVariables( $text );
$text = $this->mStripState->unstripBoth( $text );
$text = Sanitizer::removeHTMLtags( $text );
return $text;
}
function testPst( $text, $title, $options ) {
global $wgUser;
if ( ! ( $title instanceof Title ) ) {
$title = Title::newFromText( $title );
}
return $this->preSaveTransform( $text, $title, $wgUser, $options );
}
function testPreprocess( $text, $title, $options ) {
if ( ! ( $title instanceof Title ) ) {
$title = Title::newFromText( $title );
}
return $this->testSrvus( $text, $title, $options, self::OT_PREPROCESS );
}
function markerSkipCallback( $s, $callback ) {
$i = 0;
$out = '';
while ( $i < strlen( $s ) ) {
$markerStart = strpos( $s, $this->mUniqPrefix, $i );
if ( $markerStart === false ) {
$out .= call_user_func( $callback, substr( $s, $i ) );
break;
} else {
$out .= call_user_func( $callback, substr( $s, $i, $markerStart - $i ) );
$markerEnd = strpos( $s, self::MARKER_SUFFIX, $markerStart );
if ( $markerEnd === false ) {
$out .= substr( $s, $markerStart );
break;
} else {
$markerEnd += strlen( self::MARKER_SUFFIX );
$out .= substr( $s, $markerStart, $markerEnd - $markerStart );
$i = $markerEnd;
}
}
}
return $out;
}
function serialiseHalfParsedText( $text ) {
$data = array();
$data['text'] = $text;
// First, find all strip markers, and store their
// data in an array.
$stripState = new StripState;
$pos = 0;
while( ( $start_pos = strpos( $text, $this->mUniqPrefix, $pos ) ) && ( $end_pos = strpos( $text, self::MARKER_SUFFIX, $pos ) ) ) {
$end_pos += strlen( self::MARKER_SUFFIX );
$marker = substr( $text, $start_pos, $end_pos-$start_pos );
if ( !empty( $this->mStripState->general->data[$marker] ) ) {
$replaceArray = $stripState->general;
$stripText = $this->mStripState->general->data[$marker];
} elseif ( !empty( $this->mStripState->nowiki->data[$marker] ) ) {
$replaceArray = $stripState->nowiki;
$stripText = $this->mStripState->nowiki->data[$marker];
} else {
throw new MWException( "Hanging strip marker: '$marker'." );
}
$replaceArray->setPair( $marker, $stripText );
$pos = $end_pos;
}
$data['stripstate'] = $stripState;
// Now, find all of our links, and store THEIR
// data in an array! :)
$links = array( 'internal' => array(), 'interwiki' => array() );
$pos = 0;
// Internal links
while( ( $start_pos = strpos( $text, '<!--LINK ', $pos ) ) ) {
list( $ns, $trail ) = explode( ':', substr( $text, $start_pos + strlen( '<!--LINK ' ) ), 2 );
$ns = trim($ns);
if (empty( $links['internal'][$ns] )) {
$links['internal'][$ns] = array();
}
$key = trim( substr( $trail, 0, strpos( $trail, '-->' ) ) );
$links['internal'][$ns][] = $this->mLinkHolders->internals[$ns][$key];
$pos = $start_pos + strlen( "<!--LINK $ns:$key-->" );
}
$pos = 0;
// Interwiki links
while( ( $start_pos = strpos( $text, '<!--IWLINK ', $pos ) ) ) {
$data = substr( $text, $start_pos );
$key = trim( substr( $data, 0, strpos( $data, '-->' ) ) );
$links['interwiki'][] = $this->mLinkHolders->interwiki[$key];
$pos = $start_pos + strlen( "<!--IWLINK $key-->" );
}
$data['linkholder'] = $links;
return $data;
}
function unserialiseHalfParsedText( $data, $intPrefix = null /* Unique identifying prefix */ ) {
if (!$intPrefix)
$intPrefix = $this->getRandomString();
// First, extract the strip state.
$stripState = $data['stripstate'];
$this->mStripState->general->merge( $stripState->general );
$this->mStripState->nowiki->merge( $stripState->nowiki );
// Now, extract the text, and renumber links
$text = $data['text'];
$links = $data['linkholder'];
// Internal...
foreach( $links['internal'] as $ns => $nsLinks ) {
foreach( $nsLinks as $key => $entry ) {
$newKey = $intPrefix . '-' . $key;
$this->mLinkHolders->internals[$ns][$newKey] = $entry;
$text = str_replace( "<!--LINK $ns:$key-->", "<!--LINK $ns:$newKey-->", $text );
}
}
// Interwiki...
foreach( $links['interwiki'] as $key => $entry ) {
$newKey = "$intPrefix-$key";
$this->mLinkHolders->interwikis[$newKey] = $entry;
$text = str_replace( "<!--IWLINK $key-->", "<!--IWLINK $newKey-->", $text );
}
// Should be good to go.
return $text;
}
}
/**
* @todo document, briefly.
* @ingroup Parser
*/
class StripState {
var $general, $nowiki;
function __construct() {
$this->general = new ReplacementArray;
$this->nowiki = new ReplacementArray;
}
function unstripGeneral( $text ) {
wfProfileIn( __METHOD__ );
do {
$oldText = $text;
$text = $this->general->replace( $text );
} while ( $text !== $oldText );
wfProfileOut( __METHOD__ );
return $text;
}
function unstripNoWiki( $text ) {
wfProfileIn( __METHOD__ );
do {
$oldText = $text;
$text = $this->nowiki->replace( $text );
} while ( $text !== $oldText );
wfProfileOut( __METHOD__ );
return $text;
}
function unstripBoth( $text ) {
wfProfileIn( __METHOD__ );
do {
$oldText = $text;
$text = $this->general->replace( $text );
$text = $this->nowiki->replace( $text );
} while ( $text !== $oldText );
wfProfileOut( __METHOD__ );
return $text;
}
}
/**
* @todo document, briefly.
* @ingroup Parser
*/
class OnlyIncludeReplacer {
var $output = '';
function replace( $matches ) {
if ( substr( $matches[1], -1 ) === "\n" ) {
$this->output .= substr( $matches[1], 0, -1 );
} else {
$this->output .= $matches[1];
}
}
}
|