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
|
#!/usr/bin/perl -T
#
# W3C Markup Validation Service
# A CGI script to retrieve and validate a markup file
#
# Copyright 1995-2004 Gerald Oskoboiny <gerald@w3.org>
# for additional contributors, see http://dev.w3.org/cvsweb/validator/
#
# This source code is available under the license at:
# http://www.w3.org/Consortium/Legal/copyright-software
#
# $Id: check,v 1.332 2004-07-21 17:06:27 link Exp $
#
# Disable buffering on STDOUT!
$| = 1;
#
# We need Perl 5.6.0+.
use 5.006;
###############################################################################
#### Load modules. ############################################################
###############################################################################
#
# Pragmas.
use strict;
use warnings;
#
# Modules. See also the BEGIN block further down below.
#
# Version numbers given where we absolutely need a minimum version of a given
# module (gives nicer error messages). By default, add an empty import list
# when loading modules to prevent non-OO or poorly written modules from
# polluting our namespace.
#
use CGI 2.81 qw(
-newstyle_urls
-private_tempfiles
redirect
); # 2.81 for XHTML, and import redirect() function.
use CGI::Carp qw(carp croak fatalsToBrowser);
use Config::General 2.19 qw(); # Need 2.19 for -AutoLaunder
use File::Spec qw();
use HTML::Parser 3.25 qw(); # Need 3.25 for $p->ignore_elements.
use HTML::Template 2.6 qw();
use HTTP::Request qw();
use HTTP::Headers::Auth qw(); # Needs to be imported after other HTTP::*.
use IO::File qw();
use IPC::Open3 qw(open3);
use LWP::UserAgent 1.90 qw(); # Need 1.90 for protocols_(allowed|forbidden)
use Net::hostent qw(gethostbyname);
use Net::IP qw();
use Set::IntSpan qw();
use Socket qw(inet_ntoa);
use Text::Iconv qw();
use Text::Wrap qw(wrap);
use URI qw();
use URI::Escape qw(uri_escape);
###############################################################################
#### Constant definitions. ####################################################
###############################################################################
#
# Define global constants
use constant TRUE => 1;
use constant FALSE => 0;
#
# Tentative Validation Severities.
use constant T_DEBUG => 1; # 0000 0001
use constant T_INFO => 2; # 0000 0010
use constant T_WARN => 4; # 0000 0100
use constant T_ERROR => 8; # 0000 1000
use constant T_FATAL => 16; # 0001 0000
use constant T_FALL => 32; # 0010 0000, Fallback in effect.
#
# Output flags for error processing
use constant O_SOURCE => 1; # 0000 0001
use constant O_CHARSET => 2; # 0000 0010
use constant O_DOCTYPE => 4; # 0000 0100
use constant O_NONE => 8; # 0000 1000
#
# Define global variables.
use vars qw($DEBUG $CFG $RSRC $VERSION $HAVE_IPC_RUN);
our $HAVE_SOAP_LITE;
#
# Things inside BEGIN don't happen on every request in persistent
# environments, such as mod_perl. So let's do globals, eg. read config here.
BEGIN {
#
# Read Config Files.
eval {
my %config_opts =
(-ConfigFile => $ENV{W3C_VALIDATOR_CFG} || '/etc/w3c/validator.conf',
-MergeDuplicateOptions => 'yes',
-SplitPolicy => 'equalsign',
-UseApacheInclude => TRUE,
-IncludeRelative => TRUE,
-InterPolateVars => TRUE,
-AutoLaunder => TRUE,
-DefaultConfig => { Allowed_Protocols => 'http,https',
SGML_Parser => '/usr/bin/onsgmls',
Template_Path => '/usr/local/validator/share/templates/en_US',
},
);
my %cfg = Config::General->new(%config_opts)->getall();
$CFG = \%cfg;
};
if ($@) {
die <<".EOF.";
Couldn't read configuration. Set the W3C_VALIDATOR_CFG environment variable
or copy conf/* to /etc/w3c/, and make sure that the configuration file, as
well as all included files are readable by the web server user.
The error reported was: '$@'
.EOF.
}
# Split allowed protocols into a list.
# We could use the array / identical values feature of Config::General,
# but that has unwanted effects when the only array type option we need is
# Allowed_Protocols.
if (my $allowed = delete($CFG->{Allowed_Protocols})) {
$CFG->{Allowed_Protocols} = [ split(/\s*,\s*/, $allowed) ];
}
#
# Make sure onsgmls exists and is executable.
unless (-x $CFG->{SGML_Parser}) {
die qq(Configured SGML Parser "$CFG->{SGML_Parser}" not executable!\n);
}
{ # Make types config indexed by FPI.
my $_types = {};
map {$_types->{$CFG->{Types}->{$_}->{PubID}} = $CFG->{Types}->{$_}}
keys %{$CFG->{Types}};
$CFG->{Types} = $_types;
}
#
# Use IPC::Run on mod_perl if it's available, IPC::Open3 otherwise.
$HAVE_IPC_RUN = 0;
if ($ENV{MOD_PERL}) {
eval {
local $SIG{__DIE__};
require IPC::Run;
IPC::Run->import('run', 'timeout');
};
$HAVE_IPC_RUN = !$@;
}
unless ($HAVE_IPC_RUN) {
require IPC::Open3;
IPC::Open3->import('open3');
}
#FIXME: This is just a framework and highly experimental!
#
# Load SOAP::Lite if available and allowed by config.
$HAVE_SOAP_LITE = FALSE;
if (exists $ENV{'HTTP_SOAPACTION'} and $CFG->{'Enable SOAP'} == TRUE) {
eval {
local $SIG{__DIE__};
require SOAP::Transport::HTTP;
};
$HAVE_SOAP_LITE = !$@;
}
#FIXME;
#
# Read Resource files... (friendly error messages)
my %config_opts = (-ConfigFile => $CFG->{'Verbose Msg'});
my %rsrc = Config::General->new(%config_opts)->getall();
$RSRC = \%rsrc;
#
# Set debug flag.
$DEBUG = TRUE if $ENV{W3C_VALIDATOR_DEBUG} || $CFG->{DEBUG};
#
# Strings
$VERSION = q$Revision: 1.332 $;
$VERSION =~ s/Revision: ([\d\.]+) /$1/;
#
# Use passive FTP by default.
$ENV{FTP_PASSIVE} = 1 unless exists($ENV{FTP_PASSIVE});
} # end of BEGIN block.
#
# Get rid of (possibly insecure) $PATH.
delete $ENV{PATH};
#use Data::Dumper qw(Dumper);
#print Dumper($CFG);
#exit;
###############################################################################
#### Process CGI variables and initialize. ####################################
###############################################################################
#
# Create a new CGI object.
my $q;
unless ($HAVE_SOAP_LITE) {
$q = new CGI;
}
#
# The data structure that will hold all session data.
my $File;
##############################################
# Populate $File->{Env} -- Session Metadata. #
##############################################
#
# The URL to this CGI Script.
unless ($HAVE_SOAP_LITE) {
$File->{Env}->{'Self URI'} = $q->url(-query => 0);
}
#################################
# Initialize the datastructure. #
#################################
#
# Charset data (casing policy: lowercase early).
$File->{Charset}->{Use} = ''; # The charset used for validation.
$File->{Charset}->{Auto} = ''; # Autodetection using XML rules (Appendix F)
$File->{Charset}->{HTTP} = ''; # From HTTP's "charset" parameter.
$File->{Charset}->{META} = ''; # From HTML's <meta http-equiv>.
$File->{Charset}->{XML} = ''; # From the XML Declaration.
$File->{Charset}->{Override} = ''; # From CGI/user override.
#
# Misc simple types.
$File->{Type} = '';
#
# Array (ref) used to store character offsets for the XML report.
$File->{Offsets}->[0] = [0, 0]; # The first item isn't used...
#
# Listrefs.
$File->{Lines} = []; # Line numbers for encoding errors.
$File->{Warnings} = []; # Warnings...
$File->{'Other Namespaces'} = []; # Other (non-root) Namespaces.
###############################################################################
#### Generate Template for Result. ############################################
###############################################################################
my $T = HTML::Template->new(
filename => File::Spec->catfile($CFG->{Template_Path}, 'result.tmpl'),
die_on_bad_params => FALSE,
);
my $E = HTML::Template->new(
filename => File::Spec->catfile($CFG->{Template_Path}, 'fatal-error.tmpl'),
die_on_bad_params => FALSE,
);
$T->param(cfg_home_page => $CFG->{Home_Page});
#########################################
# Populate $File->{Opt} -- CGI Options. #
#########################################
#
# Preprocess the CGI parameters.
if ($HAVE_SOAP_LITE) {
SOAP::Transport::HTTP::CGI->dispatch_to('MySOAP')->handle;
exit; # SOAP calls do all the processing in the sub...
} else {
$q = &prepCGI($File, $q);
#
# Set session switches.
$File->{Opt}->{'Outline'} = $q->param('outline') ? TRUE : FALSE;
$File->{Opt}->{'Show Source'} = $q->param('ss') ? TRUE : FALSE;
$File->{Opt}->{'Show Parsetree'} = $q->param('sp') ? TRUE : FALSE;
$File->{Opt}->{'No Attributes'} = $q->param('noatt') ? TRUE : FALSE;
$File->{Opt}->{'Show ESIS'} = $q->param('esis') ? TRUE : FALSE;
$File->{Opt}->{'Show Errors'} = $q->param('errors') ? TRUE : FALSE;
$File->{Opt}->{'Verbose'} = $q->param('verbose') ? TRUE : FALSE;
$File->{Opt}->{'Debug'} = $q->param('debug') ? TRUE : FALSE;
$File->{Opt}->{'No200'} = $q->param('No200') ? TRUE : FALSE;
# $File->{Opt}->{'Fussy'} = $q->param('fussy') ? TRUE : FALSE;
$File->{Opt}->{'Charset'} = $q->param('charset') ? lc $q->param('charset'): '';
$File->{Opt}->{'DOCTYPE'} = $q->param('doctype') ? $q->param('doctype') : '';
$File->{Opt}->{'URI'} = $q->param('uri') ? $q->param('uri') : '';
$File->{Opt}->{'Output'} = $q->param('output') ? $q->param('output') : 'html';
$File->{Opt}->{'Max Errors'} = $q->param('me') ? $q->param('me') : '';
#
# "Fallback" info for Character Encoding (fbc), Content-Type (fbt),
# and DOCTYPE (fbd). If TRUE, the Override values are treated as
# Fallbacks instead of Overrides.
$File->{Opt}->{FB}->{Charset} = $q->param('fbc') ? TRUE : FALSE;
$File->{Opt}->{FB}->{Type} = $q->param('fbt') ? TRUE : FALSE;
$File->{Opt}->{FB}->{DOCTYPE} = $q->param('fbd') ? TRUE : FALSE;
#
# If ";debug" was given, let it overrule the value from the config file,
# regardless of whether it's "0" or "1" (on or off).
$DEBUG = $q->param('debug') if defined $q->param('debug');
$File->{Opt}->{Verbose} = TRUE if $DEBUG;
&abort_if_error_flagged($File, O_NONE); # Too early to &print_table.
#
# Get the file and metadata.
if ($q->param('uploaded_file')) {
$File = &handle_file($q, $File);
} elsif ($q->param('fragment')) {
$File = &handle_frag($q, $File);
} elsif ($q->param('uri')) {
$File = &handle_uri($q, $File);
}
}
#
# Abort if an error was flagged during initialization.
&abort_if_error_flagged($File, 0);
#
# Get rid of the CGI object.
undef $q;
#
# We don't need STDIN any more, so get rid of it to avoid getting clobbered
# by Apache::Registry's idiotic interference under mod_perl.
untie *STDIN;
###############################################################################
#### Output validation results. ###############################################
###############################################################################
#
# Find the XML Encoding.
$File = &find_xml_encoding($File);
#
# Decide on a charset to use (first part)
#
if ($File->{Charset}->{HTTP}) { # HTTP, if given, is authoritative.
$File->{Charset}->{Use} = $File->{Charset}->{HTTP};
} elsif ($File->{ContentType} =~ m(^text/([-.a-zA-Z0-9]\+)?xml$)) {
# Act as if $http_charset was 'us-ascii'. (MIME rules)
$File->{Charset}->{Use} = 'us-ascii';
my @_source;
if ($File->{'Is Upload'}) {
@_source = ('sent by your web browser', ($File->{Server}||'unknown'), 'browser send');
} else {
@_source = ('returned by your web server', ($File->{Server}||'unknown'), 'server return');
}
&add_warning($File, 'note', 'Note:', <<".EOF.");
The HTTP Content-Type header $_source[0] ($_source[1]) did not contain
a "charset" parameter, but the Content-Type was one of the XML text/*
sub-types (<code>$File->{ContentType}</code>). The relevant
specification
(<a href="http://www.ietf.org/rfc/rfc3023.txt">RFC 3023</a>)
specifies a strong default of "us-ascii" for
such documents so we will use this value regardless of any encoding you
may have indicated elsewhere. If you would like to use a different
encoding, you should arrange to have your $_source[2] this new encoding
information.
.EOF.
} elsif ($File->{Charset}->{XML}) {
$File->{Charset}->{Use} = $File->{Charset}->{XML};
} elsif ($File->{Charset}->{Auto} =~ /^utf-16[bl]e$/ && $File->{BOM} == 2) {
$File->{Charset}->{Use} = 'utf-16';
} elsif ($File->{ContentType} =~ m(^application/([-.a-zA-Z0-9]+\+)?xml$)) {
$File->{Charset}->{Use} = "utf-8";
} elsif (&is_xml($File) and not $File->{ContentType} =~ m(^text/)) {
$File->{Charset}->{Use} = 'utf-8'; # UTF-8 (image/svg+xml etc.)
}
$File->{Content} = &normalize_newlines($File->{Bytes},
exact_charset($File, $File->{Charset}->{Use}));
#
# Try to extract META charset
# (works only if ascii-based and reasonably clean before <meta>)
$File = &preparse($File);
unless ($File->{Charset}->{Use}) {
$File->{Charset}->{Use} = $File->{Charset}->{META};
}
#
# Handle any Fallback or Override for the charset.
if (&conflict($File->{Opt}->{Charset}, '(detect automatically)')) {
# charset=foo was given to the CGI and it wasn't "autodetect".
#
# Extract the user-requested charset from CGI param.
my ($override, undef) = split(/\s/, $File->{Opt}->{Charset}, 2);
$File->{Charset}->{Override} = lc($override);
if ($File->{Opt}->{FB}->{Charset}) {
unless ($File->{Charset}->{Use}) {
&add_warning($File, 'fallback', 'No Character Encoding Found!', <<".EOF."); # Warn about fallback...
Falling back to "$File->{Charset}->{Override}"
(<a href="docs/users.html#fbc">explain...</a>).
.EOF.
$File->{Tentative} |= T_ERROR; # Tag it as Invalid.
$File->{Charset}->{Use} = $File->{Charset}->{Override};
}
} else {
# Warn about Override unless it's the same as the real charset...
unless ($File->{Charset}->{Override} eq $File->{Charset}->{Use}) {
my $cs_use = &ent($File->{Charset}->{Use});
my $cs_opt = &ent($File->{Charset}->{Override});
&add_warning($File, 'override', 'Character Encoding Override in effect!', <<".EOF.");
The detected character encoding "<code>$cs_use</code>"
has been suppressed and "<code>$cs_opt</code>" used instead.
.EOF.
$File->{Tentative} |= T_ERROR;
$File->{Charset}->{Use} = $File->{Charset}->{Override};
}
}
}
unless ($File->{Charset}->{Use}) { # No charset given...
my $message = <<".EOF.";
<p>
I was not able to extract a character encoding labeling from any of
the valid sources for such information. Without encoding information
it is impossible to reliably validate the document. I'm falling back
to the "UTF-8" encoding and will attempt to perform the validation,
but this is likely to fail for all non-trivial documents.
</p>
.EOF.
if ($File->{Opt}->{Verbose}) {
$message .= <<".EOF.";
<p>The sources I tried to find encoding information include:</p>
<ul>
<li>The HTTP Content-Type field.</li>
<li>The XML Declaration.</li>
<li>The HTML "META" element.</li>
</ul>
<p>
And I even tried to autodetect it using the algorithm defined in
<a href="http://www.w3.org/TR/REC-xml#sec-guessing">Appendix F of
the XML 1.0 Recommendation</a>.
</p>
<p>
Since none of these sources yielded any usable information, I will not be
able to reliably validate this document. Sorry. Please make sure you
specify the character encoding in use.
</p>
<p class="note">
Specifying a character encoding is normally done in the web server
configuration file or administration program. The <a
href="http://www.w3.org/"><abbr
title="World Wide Web Consortium">W3C</abbr></a> <a
href="http://www.w3.org/International/"><abbr
title="Internationalization">I18N</abbr> Activity</a> has collected
<a href="http://www.w3.org/International/O-HTTP-charset"
title="A Few Tips On How To Specify The Character Encoding">a few
tips on how to do this</a> in popular web server implementations.
</p>
.EOF.
$message .= &iana_charset_blurb();
$message .= <<".EOF.";
<p>
To quickly check whether the document would validate after addressing
the missing character encoding information, you can use the "Encoding"
form control (accesskey "2") earlier in the page to force an encoding
override to take effect. "iso-8859-1" (Western Europe and North America)
and "utf-8" (Universal, but not commonly used in legacy documents) are
common encodings if you are not sure what encoding to choose.
</p>
.EOF.
}
else {
$message .= <<".EOF.";
<p>So what should I do? <a href="docs/help.html#faq-charset">Tell me more...</a></p>
.EOF.
}
my $title = 'No Character Encoding Found! Falling back to UTF-8.';
&add_warning($File, 'fatal', $title, $message);
$File->{Tentative} |= T_ERROR; # Can never be valid.
$File->{Charset}->{Use} = 'utf-8';
}
sub iana_charset_blurb () {
return <<".EOF.";
<p>
<a href="http://www.iana.org/"><abbr
title="Internet Assigned Numbers Authority">IANA</abbr></a>
maintains the list of <a
href="http://www.iana.org/assignments/character-sets">official
names for character sets</a> and the <abbr
title="Web Design Group">WDG</abbr> has some <a
href="http://www.htmlhelp.com/tools/validator/charset.html">information
to help you correctly specify the character encoding</a>.
</p>
.EOF.
}
#
# Abort if an error was flagged while finding the encoding.
&abort_if_error_flagged($File, O_CHARSET|O_DOCTYPE);
#
# Check the detected Encoding and transcode.
if (&conflict($File->{Charset}->{Use}, 'utf-8')) {
$File = &transcode($File);
&abort_if_error_flagged($File, O_CHARSET);
}
$File = &check_utf8($File); # always check
$File = &byte_error($File);
#
# Abort if an error was flagged during transcoding
&abort_if_error_flagged($File, O_SOURCE|O_CHARSET);
#
# Overall parsing algorithm for documents returned as text/html:
#
# For documents that come to us as text/html,
#
# 1. check if there's a doctype
# 2. if there is a doctype, parse/validate against that DTD
# 3. if no doctype, check for an xmlns= attribute on the first element
# 4. if there is an xmlns= attribute, check for XML well-formedness
# 5. if there is no xmlns= attribute, and no DOCTYPE, punt.
#
#
# Override DOCTYPE if user asked for it.
if ($File->{Opt}->{DOCTYPE}
and not $File->{Opt}->{DOCTYPE} =~ /(Inline|detect)/i) {
$File = &override_doctype($File);
my $dtd = ent($File->{Opt}->{DOCTYPE});
&add_warning($File, 'DOCTYPE Override in effect!', <<".EOF.");
Any DOCTYPE Declaration in the document has been suppressed and the DOCTYPE
for «<code>$dtd</code>» inserted instead. The document will not be
Valid until you alter the source file to reflect this new DOCTYPE.
.EOF.
$File->{Tentative} |= T_ERROR; # Tag it as Invalid.
}
#
# Try to extract a DOCTYPE or xmlns.
$File = &preparse($File);
#
# Set document type to XHTML if the DOCTYPE was for XHTML.
# Set document type to MathML if the DOCTYPE was for MathML.
# This happens when the file is served as text/html
$File->{Type} = 'xhtml+xml' if $File->{DOCTYPE} =~ /xhtml/i;
$File->{Type} = 'mathml+xml' if $File->{DOCTYPE} =~ /mathml/i;
#
# Sanity check Charset information and add any warnings necessary.
$File = &charset_conflicts($File);
#
# Abandon all hope ye who enter here...
$File = &parse($File);
sub parse (\$) {
my $File = shift;
#
# By default, use SGML catalog file and SGML Declaration.
my $catalog = File::Spec->catfile($CFG->{'SGML Library'}, 'sgml.soc');
my @spopt = qw(
-R
-wvalid
-wnon-sgml-char-ref
-wno-duplicate
);
#
# Switch to XML semantics if file is XML.
if (&is_xml($File)) {
$catalog = File::Spec->catfile($CFG->{'SGML Library'}, 'xml.soc');
push(@spopt, '-wxml');
&add_warning($File, 'note', 'Note:', <<".EOF.");
The Validator XML support has
<a href="http://openjade.sourceforge.net/doc/xml.htm"
title="Limitations in Validator XML support">some limitations</a>.
.EOF.
} else { # Only add these in SGML mode.
# if ($File->{Opt}->{'Fussy'}) {
# push @spopt, '-wmin-tag';
# push @spopt, '-wfully-tagged';
# push @spopt, '-wrefc';
# push @spopt, '-wmissing-att-name';
# push @spopt, '-wdata-delim';
# &add_warning($File, 'note', 'Note:', <<".EOF.");
# The Validator is running in "Fussy" mode. In this mode it will generate
# warnings about some things that are not strictly forbidden in the HTML
# Recommendation, but that are known to be problematic in popular browsers.
# In general it is recommended that you fix any such errors regardless, but
# if in doubt you can rerun the Validator in its lax mode to find out if it
# will pass your document then.
#.EOF.
# }
}
#
# Defaults for SP; turn off fixed charset mode and set encoding to UTF-8.
$ENV{SP_CHARSET_FIXED} = 'NO';
$ENV{SP_ENCODING} = 'UTF-8';
$ENV{SP_BCTF} = 'UTF-8';
#
# Tell onsgmls about the SGML Library.
$ENV{SGML_SEARCH_PATH} = $CFG->{'SGML Library'};
#
# Set the command to execute.
my @cmd = ($CFG->{'SGML Parser'}, '-n', '-c', $catalog, @spopt);
#
# Set debug info for HTML report.
$T->param(is_debug => $DEBUG);
$T->param(
debug => [
{name => 'Command', value => &ent("@cmd")},
{name => 'SP_CHARSET_FIXED', value => &ent($ENV{SP_CHARSET_FIXED})},
{name => 'SP_ENCODING', value => &ent($ENV{SP_ENCODING})},
{name => 'SP_BCTF', value => &ent($ENV{SP_BCTF})},
],
);
#FIXME: This needs a UI and testing!
#
# Set onsgmls' -E switch to the number of errors requested.
if ($File->{Opt}->{'Max Errors'} =~ m(^all$)i) {
push @cmd, '-E0';
} elsif ($File->{Opt}->{'Max Errors'} =~ m(^(\d+)$)) {
my $numErr = $1;
if ($numErr >= 200) {
$numErr = 200;
} elsif ($numErr <= 0) {
$numErr = 0; #FIXME: Should add feature to supress error output in this case.;
}
push @cmd, '-E' . $numErr;
} else {
push @cmd, '-E' . ($CFG->{'Max Errors'} || 0); # "-E0" means "all".
}
#FIXME;
#
# Temporary filehandles.
my $spin = IO::File->new_tmpfile;
my $spout = IO::File->new_tmpfile;
my $sperr = IO::File->new_tmpfile;
#
# Dump file to a temp file for parsing.
for (@{$File->{Content}}) {
print $spin $_, "\n";
}
#
# seek() to beginning of the file.
seek $spin, 0, 0;
#
# Run it through SP, redirecting output to temporary files.
if ($HAVE_IPC_RUN) {
local $^W = 0;
run(\@cmd, $spin, $spout, $sperr, timeout(60));
undef $spin;
} else {
my $pid = do {
no warnings 'once';
local(*SPIN, *SPOUT, *SPERR) = ($spin, $spout, $sperr);
open3("<&SPIN", ">&SPOUT", ">&SPERR", @cmd);
};
undef $spin;
waitpid $pid, 0;
}
#
# Rewind temporary filehandles.
seek $_, 0, 0 for $spout, $sperr;
$File = &parse_errors($File, $sperr); # Parse error output.
undef $sperr; # Get rid of no longer needed filehandle.
$File->{ESIS} = [];
my $elements_found = 0;
while (<$spout>) {
push @{$File->{'DEBUG'}->{ESIS}}, $_;
$elements_found++ if /^\(/;
if (/^Axmlns() \w+ (.*)/ or /^Axmlns:([^ ]+) \w+ (.*)/) {
if (not $File->{Namespace} and $elements_found == 0 and $1 eq "") {
$File->{Namespace} = $2;
}
$File->{Namespaces}->{$2}++;
}
next if / IMPLIED$/;
next if /^ASDAFORM CDATA /;
next if /^ASDAPREF CDATA /;
chomp; # Removes trailing newlines
push @{$File->{ESIS}}, $_;
}
undef $spout;
if (@{$File->{ESIS}} && $File->{ESIS}->[-1] =~ /^C$/) {
pop(@{$File->{ESIS}});
$File->{'Is Valid'} = TRUE;
} else {
$File->{'Is Valid'} = FALSE;
}
#
# Set Version to be the FPI initially.
$File->{Version} = $File->{DOCTYPE};
#
# Extract any version attribute from the ESIS.
for (@{$File->{ESIS}}) {
no warnings 'uninitialized';
next unless /^AVERSION CDATA (.*)/;
if ($1 eq '-//W3C//DTD HTML Fallback//EN') {
$File->{Tentative} |= (T_ERROR | T_FALL);
&add_warning($File, 'fallback', 'DOCTYPE Fallback in effect!', <<".EOF.");
The DOCTYPE Declaration in your document was not recognized. This
probably means that the Formal Public Identifier contains a spelling
error, or that the Declaration is not using correct syntax. Validation
has been performed using a default "fallback" Document Type Definition
that closely resembles HTML 4.01 Transitional, but the document will not
be Valid until you have corrected the problem with the DOCTYPE
Declaration.
.EOF.
}
$File->{Version} = $1;
last;
}
return $File;
}
#
# Force "XML" if type is an XML type and an FPI was not found.
# Otherwise set the type to be the FPI.
if (&is_xml($File) and not $File->{DOCTYPE}) {
$File->{Version} = 'XML';
} else {
$File->{Version} = $File->{DOCTYPE} unless $File->{Version};
}
#
# Get the pretty text version of the FPI if a mapping exists.
if (my $prettyver = $CFG->{Types}->{$File->{Version}}->{Display}) {
$File->{Version} = $prettyver;
} else {
$File->{Version} = &ent($File->{Version});
}
#
# Warn about unknown Namespaces.
if (&is_xml($File) and $File->{Namespace}) {
my $rns = &ent($File->{Namespace});
if (&is_xhtml($File) and $File->{Namespace} ne 'http://www.w3.org/1999/xhtml') {
&add_warning($File, 'warning', 'Warning:',
"Unknown namespace («<code>$rns</code>») for text/html document!",
);
} elsif (&is_svg($File) and $File->{Namespace} ne 'http://www.w3.org/2000/svg') {
&add_warning($File, 'warning', 'Warning:',
"Unknown namespace («<code>$rns</code>») for SVG document!",
);
}
}
if (defined $File->{Tentative}) {
my $class = '';
$class .= ($File->{Tentative} & T_INFO ? ' info' :'');
$class .= ($File->{Tentative} & T_WARN ? ' warning' :'');
$class .= ($File->{Tentative} & T_ERROR ? ' error' :'');
$class .= ($File->{Tentative} & T_FATAL ? ' fatal' :'');
unless ($File->{Tentative} == T_DEBUG) {
$File->{Notice} = <<".EOF.";
<p id="Notice" class="$class">
Please note that you have chosen one or more options that alter the
content of the document before validation, or have not provided enough
information to accurately validate the document. Even if no errors are
reported below, the document will not be valid until you manually make
the changes we have performed automatically. Specifically, if you used
some of the options that override a property of the document (e.g. the
DOCTYPE or Character Encoding), you must make the same change to the
source document or the server setup before it can be valid. You will
also need to insert an appropriate DOCTYPE Declaration or Character
Encoding (the "charset" parameter for the Content-Type HTTP header) if
any of those are missing.
</p>
.EOF.
}
}
if ($File->{Opt}->{Output} eq 'xml') {
&report_xml($File);
} elsif ($File->{Opt}->{Output} eq 'earl') {
&report_earl($File);
} elsif ($File->{Opt}->{Output} eq 'n3') {
&report_n3($File);
} else {
&prep_template($File, $T);
if ($File->{'Is Valid'}) {
$T->param(VALID => TRUE);
&report_valid($File, $T);
} else {
$T->param(VALID => FALSE);
$T->param(file_errors => &report_errors($File));
}
$T->param(file_warnings => $File->{Warnings});
$T->param(file_outline => &outline($File));
$T->param(file_source => &source($File));
$T->param(file_parsetree => &parsetree($File));
# &show_esis($File) if $File->{Opt}->{'Show ESIS'};
# &show_errors($File) if $File->{Opt}->{'Show Errors'};
print $T->output;
}
#
# Get rid of $File object and exit.
undef $File;
exit;
#############################################################################
# Subroutine definitions
#############################################################################
#
# Generate HTML report.
sub prep_template ($$) {
my $File = shift;
my $T = shift;
#
# XML mode...
$T->param(is_xml => &is_xml($File));
#
# Upload?
$T->param(is_upload => $File->{'Is Upload'});
#
# The URI...
$T->param(file_uri => &ent($File->{URI}));
#
# Metadata...
$T->param(file_modified => $File->{Modified});
$T->param(file_server => $File->{Server});
$T->param(file_size => $File->{Size});
$T->param(file_contenttype => $File->{ContentType});
$T->param(file_charset => $File->{Charset}->{Use});
#
# Output options...
$T->param(opt_show_source => $File->{Opt}->{'Show Source'});
$T->param(opt_show_outline => $File->{Opt}->{'Outline'});
$T->param(opt_show_parsetree => $File->{Opt}->{'Show Parsetree'});
$T->param(opt_show_noatt => $File->{Opt}->{'No Attributes'});
$T->param(opt_verbose => $File->{Opt}->{'Verbose'});
$T->param(opt_no200 => $File->{Opt}->{'No200'});
#
# Tip of the Day...
my $tip = &get_tip;
$T->param(tip_uri => $tip->[0]);
$T->param(tip_slug => $tip->[1]);
#
# Namespaces...
$T->param(file_namespace => &ent($File->{Namespace}));
# $T->param(file_namespaces => $File->{Namespaces})
# if $File->{Namespaces};
}
#
# Output "This page is Valid" report.
sub report_valid {
my $File = shift;
my $T = shift;
$T->param(file_uri => &ent($File->{URI}));
my $gifborder = ' border="0"';
my $xhtmlendtag = '';
my($image_uri, $alttext, $gifhw);
unless ($File->{Version} eq 'unknown' or defined $File->{Tentative}) {
$T->param(file_version => $File->{Version});
# @@@
# print &daily_tip($File, $CFG->{Tips_DB});
# &print_warnings($File);
if (defined $image_uri) {
$T->param(have_badge => TRUE);
$T->param(badge_uri => $image_uri);
$T->param(badge_alt => $alttext);
$T->param(badge_gifhw => $gifhw);
$T->param(badge_xhtml => $xhtmlendtag);
}
} elsif (defined $File->{Tentative}) {
$T->param(is_tentative => TRUE);
}
my $thispage = $File->{Env}->{'Self URI'};
my $escaped_uri = uri_escape($File->{URI});
$thispage .= qq(?uri=$escaped_uri);
$thispage .= ';ss=1' if $File->{Opt}->{'Show Source'};
$thispage .= ';sp=1' if $File->{Opt}->{'Show Parsetree'};
$thispage .= ';noatt=1' if $File->{Opt}->{'No Attributes'};
$thispage .= ';outline=1' if $File->{Opt}->{'Outline'};
$T->param(file_thispage => $thispage);
}
#
# Add a waring message to the output.
sub add_warning ($$$$) {
my $File = shift;
my $Class = shift;
my $Title = shift;
my $Message = shift;
push @{$File->{Warnings}}, {
Class => $Class,
Title => $Title,
Message => $Message,
};
}
#
# Print HTML explaining why/how to use a DOCTYPE Declaration.
sub doctype_spiel {
return <<".EOF.";
<p>
You should place a DOCTYPE declaration as the very first thing in your
HTML document. For example, for a typical <a
href="http://www.w3.org/TR/xhtml1/">XHTML 1.0</a> document:
</p>
<pre>
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
"http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
<html xmlns="http://www.w3.org/1999/xhtml" lang="en" xml:lang="en">
<head>
<title>Title</title>
</head>
<body>
<!-- ... body of document ... -->
</body>
</html>
</pre>
<p>
For XML documents, you may also wish to include an "XML Declaration"
even before the DOCTYPE Declaration, but this is not well supported
in older browsers. More information about this can be found in the
<a href="http://www.w3.org/TR/xhtml1/">XHTML 1.0</a> Recommendation.
</p>
.EOF.
}
#
# Proxy authentication requests.
# Note: expects the third argument to be a hash ref (see HTTP::Headers::Auth).
sub authenticate {
my $File = shift;
my $resource = shift;
my $authHeader = shift || {};
my $realm = $resource;
$realm =~ s([^\w\d.-]*){}g;
$resource = &ent($resource);
for my $scheme (keys(%$authHeader)) {
my $origrealm = $authHeader->{$scheme}->{realm};
if (!defined($origrealm) || lc($scheme) !~ /^(?:basic|digest)$/) {
delete($authHeader->{$scheme});
next;
}
$authHeader->{$scheme}->{realm} = "$realm-$origrealm";
}
my $headers = HTTP::Headers->new(Connection => 'close');
$headers->content_type('text/html; charset=utf-8');
$headers->www_authenticate(%$authHeader);
$headers = $headers->as_string();
print <<"EOF";
Status: 401 Authorization Required
$headers
<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN"
"http://www.w3.org/TR/1999/REC-html401-19991224/loose.dtd">
<html lang="en">
<head><title>401 Authorization Required</title></head>
<body>
<h1>Authorization Required</h1>
<p>Sorry, I am not authorized to access the specified URL.</p>
<p>
The URL you specified, <<a href="$resource">$resource</a>>,
returned a 401 "authorization required" response when I tried
to download it.
</p>
<p>
You should have been prompted by your browser for a
username/password pair; if you had supplied this information, I
would have forwarded it to your server for authorization to
access the resource. You can use your browser's "reload" function
to try again, if you wish.
</p>
<p>
Of course, you may not want to trust me with this information,
which is fine. I can tell you that I don't log it or do
anything else nasty with it, and you can <a href="source/">download the
source code for this service</a> to see what it does, but you have no
guarantee that this is actually the code I'm using; you basically have to
decide whether to trust me or not :-)
</p>
<p>
You should also be aware that the way we proxy this authentication
information defeats the normal working of HTTP Authentication.
If you authenticate to server A, your browser may keep sending
the authentication information to us every time you validate
a page, regardless of what server it's on, and we'll happily pass
that on to the server thereby making it possible for a malicious
server operator to capture your credentials.
</p>
<p>
Due to the way HTTP Authentication works there is no way we can
avoid this. We are using some "tricks" to fool your client into
not sending this information in the first place, but there is no
guarantee this will work. If security is a concern to you, you
may wish to avoid validating protected resources or take extra
precautions to prevent your browser from sending authentication
information when validating other servers.
</p>
<p>
Also note that you shouldn't use HTTP Basic Authentication for
anything which really needs to be private, since the password
goes across the network unencrypted.
</p>
EOF
}
#
# Complain about unknown HTTP responses.
sub http_error {
my $uri = &ent(shift);
my $code = &ent(shift);
my $message = &ent(shift);
return <<"EOF";
<p>
I got the following unexpected response when trying to
retrieve <<a href="$uri">$uri</a>>:
</p>
<blockquote>
<p><code>$code $message</code></p>
</blockquote>
<p>
Please make sure you have entered the URL correctly.
</p>
EOF
}
#
# Fetch an URL and return the content and selected meta-info.
sub handle_uri {
my $q = shift; # The CGI object.
my $File = shift; # The master datastructure.
my $uri = new URI (ref $q ? $q->param('uri') : $q);
my $ua = new LWP::UserAgent;
$ua->agent("W3C_Validator/$VERSION " . $ua->agent);
$ua->parse_head(0); # Parse the http-equiv stuff ourselves. @@ Why?
$ua->protocols_allowed($CFG->{'Allowed Protocols'} || ['http', 'https']);
unless ($ua->is_protocol_supported($uri)) {
$File->{'Error Flagged'} = TRUE;
$File->{'Error Message'} = &uri_rejected($uri->scheme());
return $File;
}
my $addr = my $iptype = undef;
if (my $host = gethostbyname($uri->host())) {
$addr = inet_ntoa($host->addr()) if $host->addr();
if ($addr && (my $ip = Net::IP->new($addr))) {
$iptype = $ip->iptype();
}
}
$iptype = 'PUBLIC'
if ($iptype && $iptype eq 'PRIVATE' && $CFG->{'Allow Private IPs'});
if ($iptype && $iptype ne 'PUBLIC') {
$File->{'Error Flagged'} = TRUE;
$File->{'Error Message'} = &ip_rejected($uri->host(), $addr);
return $File;
}
undef $iptype;
undef $addr;
my $req = new HTTP::Request(GET => $uri);
# If we got a Authorization header, the client is back at it after being
# prompted for a password so we insert the header as is in the request.
if($ENV{HTTP_AUTHORIZATION}){
$req->headers->header(Authorization => $ENV{HTTP_AUTHORIZATION});
}
my $res = $ua->request($req);
unless ($res->code == 200 || $File->{Opt}->{'No200'}) {
if ($res->code == 401) {
my %auth = $res->www_authenticate(); # HTTP::Headers::Auth
&authenticate($File, $res->request->url, \%auth);
} else {
$File->{'Error Flagged'} = TRUE;
$File->{'Error Message'} = &http_error($uri->as_string, $res->code, $res->message);
}
return $File;
}
my($type, $ct, $charset)
= &parse_content_type(
$File,
$res->header('Content-Type'),
scalar($res->request->url),
);
my $lastmod = undef;
if ( $res->last_modified ) {
$lastmod = scalar(gmtime($res->last_modified));
}
$File->{Bytes} = $res->content;
$File->{Type} = $type;
$File->{ContentType} = $ct;
$File->{Charset}->{HTTP} = lc $charset;
$File->{Modified} = $lastmod;
$File->{Server} = &ent(scalar $res->server);
$File->{Size} = scalar $res->content_length;
$File->{URI} = scalar $res->request->url;
$File->{'Is Upload'} = FALSE;
return $File;
}
#
# Handle uploaded file and return the content and selected meta-info.
sub handle_file {
my $q = shift; # The CGI object.
my $File = shift; # The master datastructure.
my $f = $q->param('uploaded_file');
my $h = $q->uploadInfo($f);
my $file;
local $/ = undef; # set line delimiter so that <> reads rest of file
$file = <$f>;
my($type, $ct, $charset) = &parse_content_type($File, $h->{'Content-Type'});
$File->{Bytes} = $file;
$File->{Type} = $type;
$File->{ContentType} = $ct;
$File->{Charset}->{HTTP} = lc $charset;
$File->{Modified} = $h->{'Last-Modified'};
$File->{Server} = &ent($h->{'User-Agent'}); # Fake a "server". :-)
$File->{Size} = $h->{'Content-Length'};
$File->{URI} = "$f"; # Need to stringify because we want ref
# to return false later in add_table. This
# is also a file handle... see man CGI.
$File->{'Is Upload'} = TRUE;
return $File;
}
#
# Handle uploaded file and return the content and selected meta-info.
sub handle_frag {
my $q = shift; # The CGI object.
my $File = shift; # The master datastructure.
$File->{Bytes} = $q->param('fragment');
$File->{Type} = 'html';
$File->{Modified} = '';
$File->{Server} = '';
$File->{Size} = '';
$File->{URI} = 'upload://Form Submission';
$File->{'Is Upload'} = TRUE;
return $File;
}
#
# Parse a Content-Type and parameters. Return document type and charset.
sub parse_content_type {
my $File = shift;
my $Content_Type = shift;
my $url = shift;
my $charset = '';
my $type = '';
my($ct, @param) = split /\s*;\s*/, lc $Content_Type;
$type = $CFG->{File_Type}->{$ct} || $ct;
foreach my $param (@param) {
my($p, $v) = split /\s*=\s*/, $param;
next unless $p =~ m(charset)i;
if ($v =~ m/([\'\"]?)(\S+)\1/i) {
$charset = lc $2;
last;
}
}
if ($type =~ m(/)) {
if ($type =~ m(text/css) and defined $url) {
print redirect
'http://jigsaw.w3.org/css-validator/validator?uri='
. uri_escape $url;
exit;
} else {
$File->{'Error Flagged'} = TRUE;
$File->{'Error Message'} = sprintf(<<" EOF", &ent($type));
<div class="error">
<p>
Sorry, I am unable to validate this document because its content type
is <code>%s</code>, which is not currently supported by this service.
</p>
<p>
The Content-Type field is sent by your web server (or web browser if
you use the file upload interface) and depends on its configuration.
Commonly, web servers will have a mapping of filename extensions
(such as ".html") to <abbr
title="Multipurpose Internet Mail Extensions">MIME</abbr>
<code>Content-Type</code> values (such as <code>text/html</code>).
</p>
<p>
That you recieved this message can mean that your server is
not configured correctly, that your file does not have the correct
filename extension, or that you are attempting to validate a file
type that we do not support yet. In the latter case you should let
us know that you need us to support that content type (please include
all relevant details, including the URL to the standards document
defining the content type) using the instructions on the
<a href="feedback.html">Feedback Page</a>.
</p>
</div>
EOF
}
}
return $type, $ct, $charset;
}
#
# Normalize newline forms (CRLF/CR/LF) to native newline.
sub normalize_newlines {
my $file = shift;
local $_ = shift; #charset
my $pattern = '';
# don't use backreference parentheses!
$pattern = '\x00\x0D(?:\x00\x0A)?|\x00\x0A' if /^utf-16be$/;
$pattern = '\x0D\x00(?:\x0A\x00)?|\x0A\x00' if /^utf-16le$/;
# $pattern = '\x00\x00\x00\x0D(?:\x00\x00\x00\x0A)?|\x00\x00\x00\x0A' if /^UCS-4be$/;
# $pattern = '\x0D\x00\x00\x00(?:\x0A\x00\x00\x00)?|\x0A\x00\x00\x00' if /^UCS-4le$/;
# insert other special cases here, such as EBCDIC
$pattern = '\x0D(?:\x0A)?|\x0A' if !$pattern; # all other cases
return [split /$pattern/, $file];
}
#
# find exact charset from general one (utf-16)
#
# needed for per-line conversion and line splitting
# (BE is default, but this will apply only to HTML)
sub exact_charset {
my $File = shift;
my $general_charset = shift;
my $exact_charset = $general_charset;
if ($general_charset eq 'utf-16') {
if ($File->{Charset}->{Auto} =~ m/^utf-16[bl]e$/) {
$exact_charset = $File->{Charset}->{Auto};
} else { $exact_charset = 'utf-16be'; }
}
# add same code for ucs-4 here
return $exact_charset;
}
#
# Return $_[0] encoded for HTML entities (cribbed from merlyn).
#
# Note that this is used both for HTML and XML escaping.
#
sub ent {
local $_ = shift;
return '' unless defined; # Eliminate warnings
s(["<&>"]){'&#' . ord($&) . ';'}ge; # should switch to hex sooner or later
return $_;
}
#
# Truncate source lines for report.
#
# This *really* wants Perl 5.8.0 and it's improved UNICODE support.
# Byte semantics are in effect on all length(), substr(), etc. calls,
# so offsets will be wrong if there are multi-byte sequences prior to
# the column where the error is detected.
#
sub truncate_line {
my $line = shift;
my $col = shift;
my $start = $col;
my $end = $col;
for (1..40) {
$start-- if ($start - 1 >= 0); # in/de-crement until...
$end++ if ($end + 1 <= length $line); # ...we hit end of line.
}
unless ($end - $start == 80) {
if ($start == 0) { # Hit start of line, maybe grab more at end.
my $diff = 40 - $col;
for (1..$diff) {
$end++ if ($end + 1 <= length $line);
}
} elsif ($end == length $line) { # Hit end of line, maybe grab more at beginning.
my $diff = 80 - $col;
for (1..$diff) {
$start-- if ($start - 1 >= 0);
}
}
}
#
# Add elipsis at end if necessary.
unless ($end == length $line) {substr $line, -3, 3, '...'};
$col = $col - $start; # New offset is diff from $col to $start.
$line = substr $line, $start, $end - $start; # Truncate.
#
# Add elipsis at start if necessary.
unless ($start == 0) {substr $line, 0, 3, '...'};
return $line, $col;
}
#
# Suppress any existing DOCTYPE by commenting it out.
sub override_doctype {
no strict 'vars';
my $File = shift;
my $pubid = $CFG->{Types}->{$File->{Opt}->{DOCTYPE}}->{PubID};
my $sysid = $CFG->{Types}->{$File->{Opt}->{DOCTYPE}}->{SysID};
my $name = $CFG->{Types}->{$File->{Opt}->{DOCTYPE}}->{Name};
local $dtd = qq(<!DOCTYPE $name PUBLIC "$pubid"\n "$sysid">);
local $org_dtd = '';
local $HTML = '';
local $seen = FALSE;
my $declaration = sub {
$seen = TRUE;
# No Override if Fallback was requested.
if ($File->{Opt}->{FB}->{DOCTYPE}) {
$HTML .= $_[0]; # Stash it as is...
} else { # Comment it out and insert the new one...
$HTML .= "$dtd\n" . '<!-- ' . $_[0] . ' -->';
$org_dtd = &ent($_[0]);
}
};
HTML::Parser->new(default_h => [sub {$HTML .= shift}, 'text'],
declaration_h => [$declaration, 'text']
)->parse(join "\n", @{$File->{Content}})->eof();
$File->{Content} = [split /\n/, $HTML];
if ($seen) {
unless ($File->{Opt}->{FB}->{DOCTYPE}) {
my $dtd = ent($File->{Opt}->{DOCTYPE});
&add_warning($File, 'override', 'DOCTYPE Override in effect!', <<".EOF.");
The detected DOCTYPE Declaration "$org_dtd" has been suppressed and
the DOCTYPE for "<code>$dtd</code>" inserted instead, but even if no
errors are shown below the document will not be Valid until you update
it to reflect this new DOCTYPE.
.EOF.
$File->{Tentative} |= T_ERROR; # Tag it as Invalid.
}
} else {
unshift @{$File->{Content}}, $dtd;
if ($File->{Opt}->{FB}->{DOCTYPE}) {
&add_warning($File, 'fallback', 'No DOCTYPE Found!', <<".EOF.");
Falling back to HTML 4.01 Transitional. (<a href="docs/users.html#fbd">explain...</a>)
.EOF.
$File->{Tentative} |= T_ERROR; # Tag it as Invalid.
} else {
my $dtd = ent($File->{Opt}->{DOCTYPE});
&add_warning($File, 'override', 'DOCTYPE Override in effect!', <<".EOF.");
The DOCTYPE Declaration for "$dtd" has been inserted at the start of
the document, but even if no errors are shown below the document will
not be Valid until you add the new DOCTYPE Declaration.
.EOF.
$File->{Tentative} |= T_ERROR; # Tag it as Invalid.
}
}
return $File;
}
#
# Parse errors reported by SP.
sub parse_errors ($$) {
my $File = shift;
my $fh = shift;
$File->{Errors} = []; # Initialize to an (empty) anonymous array ref.
for (<$fh>) {
push @{$File->{'DEBUG'}->{Errors}}, $_;
chomp;
my($err, @errors);
next if /^<OSFD>0:[0-9]+:[0-9]+:[^A-Z]/;
next if /numbers exceeding 65535 not supported/;
next if /URL Redirected to/;
my(@_err) = split /:/;
next unless $_err[1] eq '<OSFD>0'; #@@@ This is a polite fiction!
if ($_err[1] =~ m(^<URL>)) {
@errors = ($_err[0], join(':', $_err[1], $_err[2]), @_err[3..$#_err]);
} else {
@errors = @_err;
}
$err->{src} = $errors[1];
$err->{line} = $errors[2];
$err->{char} = $errors[3];
# Workaround for onsgmls 1.5 sometimes reporting errors beyond EOL.
if ((my $l = length($File->{Content}->[$err->{line}-1])) < $err->{char}) {
$err->{char} = $l;
}
$err->{num} = $errors[4] || '';
$err->{type} = $errors[5] || '';
if ($err->{type} eq 'E' or $err->{type} eq 'X' or $err->{type} eq 'Q') {
$err->{msg} = join ':', @errors[6 .. $#errors];
} elsif ($err->{type} eq 'W') {
&add_warning($File, 'fake', 'Warning:',
"Line $err->{line}, column $err->{char}: " . &ent($errors[6]));
$err->{msg} = join ':', @errors[6 .. $#errors];
} else {
$err->{type} = 'I';
$err->{num} = '';
$err->{msg} = join ':', @errors[4 .. $#errors];
}
# No or unknown FPI and a relative SI.
if ($err->{msg} =~ m(cannot (open|find))) {
$File->{'Error Flagged'} = TRUE;
$File->{'Error Message'} = <<".EOF.";
<div class="fatal">
<h2>Fatal Error: $err->{msg}</h2>
<p>
I could not parse this document, because it makes reference to a
system-specific file instead of using a well-known public identifier
to specify the type of markup being used.
</p>
.EOF.
$File->{'Error Message'} .= &doctype_spiel();
$File->{'Error Message'} .= " </div>\n";
}
# No DOCTYPE.
if ($err->{msg} =~ m(prolog can\'t be omitted)) {
my $class = 'fatal';
my $title = 'No DOCTYPE Found! Falling Back to HTML 4.01 Transitional';
my $message = <<".EOF.";
<p>
A DOCTYPE Declaration is mandatory for most current markup languages
and without one it is impossible to reliably validate this document.
I am falling back to "HTML 4.01 Transitional" and will attempt to
validate the document anyway, but this is very likely to produce
spurious error messages for most non-trivial documents.
</p>
.EOF.
if ($File->{Opt}->{Verbose}) {
$message .= &doctype_spiel();
$message .= <<".EOF.";
<p>
The W3C QA Activity maintains a <a
href="http://www.w3.org/QA/2002/04/valid-dtd-list.html">List of
Valid Doctypes</a> that you can choose from, and the <acronym
title="Web Design Group">WDG</acronym> maintains a document on
"<a href="http://htmlhelp.com/tools/validator/doctype.html">Choosing
a DOCTYPE</a>".
</p>
.EOF.
} else {
$message .= <<".EOF.";
<p>
So what should I do?
<a href="docs/help.html#faq-doctype">Tell me more...</a>
</p>
.EOF.
}
&add_warning($File, $class, $title, $message);
next; # Don't report this as a normal error.
}
&abort_if_error_flagged($File, O_DOCTYPE);
$err->{msg} =~ s/^\s*//;
push @{$File->{Errors}}, $err;
}
undef $fh;
return $File;
}
#
# Generate a HTML report of detected errors.
sub report_errors ($) {
my $File = shift;
my $Errors = [];
if (scalar @{$File->{Errors}}) {
foreach my $err (@{$File->{Errors}}) {
my($line, $col) = &truncate_line($File->{Content}->[$err->{line}-1], $err->{char});
#DEBUG: Gather vars for print below.
my $orglength = length($File->{Content}->[$err->{line}-1]);
my $adjlength = length $line;
my $orgcol = $err->{char};
my $adjcol = $col;
#DEBUG;
$line = &mark_error($line, $col);
#DEBUG: Print misc. vars relevant to source display.
if ($DEBUG) {
$line .= "<br /> <strong>org length: $orglength - adj length: $adjlength - org col: $orgcol - adj col: $adjcol</strong>";
}
#DEBUG;
# if (defined $CFG->{Error_to_URI}->{$err->{idx}}) {
# $err->{uri} = $CFG->{Msg_FAQ_URI} . '#'
# . $CFG->{Error_to_URI}->{$err->{idx}};
# }
$err->{src} = $line;
$err->{col} = ' ' x $col;
push @{$Errors}, $err;
}
}
return $Errors;
}
#
# Chop the source line into 3 pieces; the character at which the error
# was detected, and everything to the left and right of that position.
# That way we can add markup to the relevant char without breaking &ent().
sub mark_error (\$\$) {
my $line = shift;
my $col = shift;
#
# Left side...
my $left;
{
my $offset = 0; # Left side allways starts at 0.
my $length;
if ($col - 1 < 0) { # If error is at start of line...
$length = 0; # ...floor to 0 (no negative offset).
} elsif ($col == length $line) { # If error is at EOL...
$length = $col - 1; # ...leave last char to indicate position.
} else { # Otherwise grab everything up to pos of error.
$length = $col;
}
$left = substr $line, $offset, $length;
$left = &ent($left);
}
#
# The character where the error was detected.
my $char;
{
my $offset;
my $length = 1; # Length is always 1; the char where error was found.
if ($col == length $line) { # If err is at EOL...
$offset = $col - 1; # ...then grab last char on line instead.
} else {
$offset = $col; # Otherwise just grab the char.
}
$char = substr $line, $offset, $length;
$char = &ent($char);
}
#
# The right side up to the end of the line...
my $right;
{
my $offset;
my $length;
# Offset...
if ($col == length $line) { # If at EOL...
$offset = 0; # Don't bother as there is nothing left to grab.
} else {
$offset = $col + 1; # Otherwise get everything from char-after-error.
}
# Length...
if ($col == length $line) { # If at end of line...
$length = 0; # ...then don't grab anything.
} else {
$length = length($line) - ($col - 1); # Otherwise get the rest of the line.
}
$right = substr $line, $offset, $length;
$right = &ent($right);
}
$char = qq(<strong title="Position where error was detected.">$char</strong>);
$line = $left . $char . $right;
return $line;
}
#
# Produce an outline of the document based on Hn elements from the ESIS.
sub outline {
my $File = shift;
my $outline = '';
my $prevlevel = 0;
my $level = 0;
for (1 .. $#{$File->{ESIS}}) {
my $line = $File->{ESIS}->[$_];
next unless ($line && $line =~ /^\(H([1-6])$/i);
$prevlevel = $level;
$level = $1;
my $TAB = $level + 2;
if ($prevlevel == 0) {
$outline .= " <ul>\n";
} else {
if ($level < $prevlevel) {
$outline .= "</li>\n";
for (my $i = $prevlevel; $i > $level; $i--) {
$outline .= " " x ($i + 2) . "</ul>\n";
$outline .= " " x (($i + 2) - 1) . "</li>\n";
}
} elsif ($level == $prevlevel) {
$outline .= "</li>\n";
} elsif ($level > $prevlevel) {
if ($level - $prevlevel > 1) {
foreach my $i (($prevlevel + 1) .. ($level - 1)) {
$outline .= "\n", " " x ($i + 2) . "<ul>\n" . " " x ($i + 2);
$outline .= qq(<li class="warning">A level $i heading is missing!);
}
$outline .= "\n" . " " x $TAB . "<ul>\n";
} else {
$outline .= "\n" . " " x $TAB;
$outline .= "<ul>\n";
}
}
}
$line = '';
my $heading = '';
until (substr($line, 0, 3) =~ /^\)H$level/i) {
$line = $File->{ESIS}->[$_++];
if ($line =~ /^-/) {
my $headcont = $line;
substr($headcont, 0, 1) = " ";
$heading .= $headcont;
} elsif ($line =~ /^AALT CDATA( .+)/i) {
my $headcont = $1;
$heading .= $headcont;
}
}
$heading =~ s/\\011/ /g;
$heading =~ s/\\012/ /g;
$heading =~ s/\\n/ /g;
$heading =~ s/\s+/ /g;
$heading =~ s/^[- ]//;
$heading = &ent($heading);
$outline .= " <li>$heading</li>\n";
}
$outline .= " </ul>\n" x $level;
return $outline;
}
#
# Create a HTML representation of the document.
sub source {
my $File = shift;
my $line = 1;
my @source = ();
my $comment = '';
if ($File->{'Error Flagged'}) {
$comment = "<p>I have marked lines that I haven't been able to decode.</p>\n";
}
# Remove any BOM since we're not at BOT anymore...
$File->{Content}->[0] =
substr $File->{Content}->[0], ($File->{BOM} ? 3 : 0); # remove BOM
my $maxhlen = length scalar @{$File->{Content}};
for (@{$File->{Content}}) {
my $hline = (' ' x ($maxhlen - length("$line"))) . $line;
push @source, {file_source_i => $line, file_source_line => ent $hline};
$line++;
}
return \@source;
}
#
# Create a HTML Parse Tree of the document for validation report.
sub parsetree {
return;
my $File = shift;
my $tree = '';
$T->param(file_parsetree_noatt => TRUE) if $File->{Opt}->{'No Attributes'};
my $indent = 0;
my $prevdata = '';
foreach my $line (@{$File->{ESIS}}) {
next if ($File->{Opt}->{'No Attributes'} && $line =~ /^A/);
$line =~ s/\\n/ /g;
$line =~ s/\\011/ /g;
$line =~ s/\\012/ /g;
$line =~ s/\s+/ /g;
next if $line =~ /^-\s*$/;
if ($line =~ /^-/) {
substr($line, 0, 1) = ' ';
$prevdata .= $line;
next;
} elsif ($prevdata) {
$prevdata = &ent($prevdata);
$prevdata =~ s/\s+/ /go;
$tree .= wrap(' ' x $indent, ' ' x $indent, $prevdata) . "\n";
undef $prevdata;
}
$line = &ent($line);
if ($line =~ /^\)/) {
$indent -= 2;
}
my $printme;
chomp($printme = $line);
if (my ($close, $elem) = $printme =~ /^([()])(.+)/) {
# reformat and add links on HTML elements
$close = ($close eq ')') ? '/' : ''; # ")" -> close-tag
if (my $u = $CFG->{'Element Map'}->{lc($elem)}) {
$elem = '<a href="' . $CFG->{'Element Ref URI'} . "$u\">$elem</a>";
}
$printme = "<$close$elem>";
} else {
$printme =~ s,^A, A,; # indent attributes a bit
}
$tree .= ' ' x $indent . $printme . "\n";
if ($line =~ /^\(/) {
$indent += 2;
}
}
return $tree;
}
#
# Do an initial parse of the Document Entity to extract charset and FPI.
sub preparse {
my $File = shift;
#
# Reset DOCTYPE, Root, and Charset (for second invocation).
$File->{Charset}->{META} = '';
$File->{DOCTYPE} = '';
$File->{Root} = '';
my $dtd = sub {
return if $File->{Root};
($File->{Root}, $File->{DOCTYPE}) = shift =~ m(<!DOCTYPE\s+(\w+)\s+PUBLIC\s+(?:[\'\"])([^\"\']+)(?:[\"\']).*>)si;
};
my $start = sub {
my $tag = shift;
my $attr = shift;
my %attr = map {lc($_) => $attr->{$_}} keys %{$attr};
if ($File->{Root}) {
if (lc $tag eq 'meta') {
if (lc $attr{'http-equiv'} eq 'content-type') {
if ($attr{content} =~ m(charset\s*=[\s\"\']*([^\s;\"\'>]*))si) {
$File->{Charset}->{META} = lc $1;
}
}
}
return unless $tag eq $File->{Root};
} else {
$File->{Root} = $tag;
}
if ($attr->{xmlns}) {$File->{Namespace} = $attr->{xmlns}};
};
my $p = HTML::Parser->new(api_version => 3);
$p->xml_mode(TRUE);
$p->ignore_elements('BODY');
$p->ignore_elements('body');
$p->handler(declaration => $dtd, 'text');
$p->handler(start => $start, 'tag,attr');
$p->parse(join "\n", @{$File->{Content}});
$File->{DOCTYPE} = '' unless defined $File->{DOCTYPE};
$File->{DOCTYPE} =~ s(^\s+){ }g;
$File->{DOCTYPE} =~ s(\s+$){ }g;
$File->{DOCTYPE} =~ s(\s+) { }g;
return $File;
}
#
# Print out the raw ESIS output for debugging.
sub show_esis ($) {
print <<'EOF';
<div id="raw_esis" class="mtb">
<hr />
<h2><a name="raw_esis">Raw ESIS Output</a></h2>
<pre>
EOF
for (@{shift->{'DEBUG'}->{ESIS}}) {
s/\\012//g;
s/\\n/\n/g;
print ent $_;
}
print " </pre>\n </div>";
}
#
# Print out the raw error output for debugging.
sub show_errors ($) {
print <<'EOF';
<div id="raw_errors" class="mtb">
<hr />
<h2><a name="raw_errors">Raw Error Output</a></h2>
<pre>
EOF
for (@{shift->{'DEBUG'}->{Errors}}) {print ent $_};
print " </pre>\n </div>";
}
#
# Preprocess CGI parameters.
sub prepCGI {
my $File = shift;
my $q = shift;
# Avoid CGI.pm's "exists but undef" behaviour.
if (scalar $q->param) {
foreach my $param ($q->param) {
next if $param eq 'uploaded_file'; # 'uploaded_file' contains data.
next if $q->param($param) eq '0'; # Keep false-but-set params.
#
# Parameters that are given to us without specifying a value get
# set to "1" (the "TRUE" constant). This is so we can test for the
# boolean value of a parameter instead of first checking whether
# the param was given and then testing it's value. Needed because
# CGI.pm sets ";param" and ";param=" to a boolean false value
# (undef() or a null string, respectively).
$q->param($param, TRUE) unless $q->param($param);
}
}
# Futz the URL so "/referer" works.
if ($q->path_info) {
if ($q->path_info eq '/referer' or $q->path_info eq '/referrer') {
if ($q->referer) {
$q->param('uri', $q->referer);
print redirect &self_url_q($q, $File);
exit;
} else {
print redirect $q->url() . '?uri=' . 'referer';
exit;
}
} else {
print redirect &self_url_q($q, $File);
exit;
}
}
# Use "url" unless a "uri" was also given.
if ($q->param('url') and not $q->param('uri')) {
$q->param('uri', $q->param('url'));
}
# Munge the URL to include commonly omitted prefix.
my $u = $q->param('uri');
$q->param('uri', "http://$u") if $u && $u =~ m(^www)i;
# Issue a redirect for uri=referer.
if ($q->param('uri') and $q->param('uri') eq 'referer') {
if ($q->referer) {
$q->param('uri', $q->referer);
print redirect &self_url_q($q, $File);
exit;
} else {
# Redirected from /check/referer to /check?uri=referer because
# the browser didn't send a Referer header, or the request was
# for /check?uri=referer but no Referer header was found.
$File->{'Error Flagged'} = TRUE;
$File->{'Error Message'} = <<".EOF.";
<div class="error">
<a id="skip" name="skip"></a>
<h2><strong>No Referer header found!</strong></h2>
<p>
You have requested we check the referring page, but your browser did
not send the HTTP "Referer" header field. This can be for several
reasons, but most commonly it is because your browser does not
know about this header, has been configured not to send one, or is
behind a proxy or firewall that strips it out of the request before
it reaches us.
</p>
<p>This is <em>not</em> an error in the referring page!</p>
<p>
Please use the form interface on the
<a href="$CFG->{'Home Page'}">Validator Home Page</a> (or the
<a href="detailed.html">Extended Interface</a>) to check the
page by URL.
</p>
</div>
.EOF.
}
}
# Supersede URL with an uploaded file.
if ($q->param('uploaded_file')) {
$q->param('uri', 'upload://' . $q->param('uploaded_file'));
$File->{'Is Upload'} = TRUE; # Tag it for later use.
}
# Supersede URL with an uploaded fragment.
if ($q->param('fragment')) {
$q->param('uri', 'upload://Form Submission');
$File->{'Is Upload'} = TRUE; # Tag it for later use.
}
# Redirect to a GETable URL if method is POST without a file upload.
if ($q->request_method eq 'POST' and not $File->{'Is Upload'}) {
my $thispage = &self_url_q($q, $File);
print redirect $thispage;
exit;
}
#
# Flag an error if we didn't get a file to validate.
unless ($q->param('uri')) {
$File->{'Error Flagged'} = TRUE;
$File->{'Error Message'} = &uri_rejected();
}
return $q;
}
#
# Preprocess SSI files.
sub prepSSI {
my $opt = shift;
my $fh = new IO::File "< $opt->{File}"
or croak "open($opt->{File}) returned: $!\n";
my $ssi = join '', <$fh>;
close $fh or carp "close($opt->{File}) returned: $!\n";
$ssi =~ s/<!--\#echo var="title" -->/$opt->{Title}/g
if defined $opt->{Title};
$ssi =~ s/<!--\#echo var="date" -->/$opt->{Date}/g
if defined $opt->{Date};
$ssi =~ s/<!--\#echo\s+var="revision"\s+-->/$opt->{Revision}/g
if defined $opt->{Revision};
# No need to parametrize this one, it's always "./" in this context.
$ssi =~ s|<!--\#echo\s+var="relroot"\s+-->|./|g;
return $ssi;
}
#
# Output errors for a rejected IP address.
sub ip_rejected {
my ($host, $ip) = @_;
my $msg = $host || 'undefined';
$msg = 'of ' . $msg if ($ip && $host ne $ip);
return sprintf(<<".EOF.", &ent($msg));
<div class="error">
<a id="skip" name="skip"></a>
<p>
Sorry, the IP address %s is not public.
For security reasons, validating resources located at non-public IP
addresses has been disabled in this service.
</p>
</div>
.EOF.
}
#
# Output errors for a rejected URL.
sub uri_rejected {
my $scheme = shift || 'undefined';
return sprintf(<<".EOF.", &ent($scheme));
<div class="error">
<a id="skip" name="skip"></a>
<p>
Sorry, this type of
<a href="http://www.w3.org/Addressing/">URL</a>
<a href="http://www.iana.org/assignments/uri-schemes">scheme</a>
(<q>%s</q>) is not supported by this service. Please check
that you entered the URL correctly.
</p>
<p>URLs should be in the form: <code>http://validator.w3.org/</code></p>
<p>
If you entered a valid URL using a scheme that we should support,
please let us know as outlined on our
<a href="feedback.html">Feedback page</a>. Make sure to include the
specific URL you would like us to support, and if possible provide a
reference to the relevant standards document describing the URL scheme
in question.
</p>
<p class="tip">
Remember that you can always save the page to disk and Validate it
using the File Upload interface.
</p>
<p>
Incomplete support for <abbr title="Secure Sockets Layer">SSL</abbr>
and <abbr title="Transport Layer Security">TLS</abbr> is a known
limitation and is being tracked as
<a href="http://www.w3.org/Bugs/Public/show_bug.cgi?id=77">Issue #77</a>.
</p>
</div>
.EOF.
}
#
# Utility subs to tell if type "is" something.
sub is_xml {shift->{Type} =~ m(^[^+]+\+xml$)};
sub is_svg {shift->{Type} =~ m(svg\+xml$)};
sub is_smil {shift->{Type} =~ m(smil\+xml$)};
sub is_html {shift->{Type} =~ m(html\+sgml$)};
sub is_xhtml {shift->{Type} =~ m(xhtml\+xml$)};
sub is_mathml {shift->{Type} =~ m(mathml\+xml$)};
#
# Check charset conflicts and add any warnings necessary.
sub charset_conflicts {
my $File = shift;
#
# Handle the case where there was no charset to be found.
unless ($File->{Charset}->{Use}) {
&add_warning($File, 'No Character Encoding detected!', <<".EOF.");
To ensure correct validation, processing, and display, it is important
that the character encoding is properly labeled.
<a href="http://www.w3.org/International/O-charset.html">More
information...</a>
.EOF.
$File->{Tentative} |= T_WARN;
}
my $cs_use = $File->{Charset}->{Use} ? &ent($File->{Charset}->{Use}) : '';
my $cs_opt = $File->{Opt}->{Charset} ? &ent($File->{Opt}->{Charset}) : '';
my $cs_http = $File->{Charset}->{HTTP} ? &ent($File->{Charset}->{HTTP}) : '';
my $cs_xml = $File->{Charset}->{XML} ? &ent($File->{Charset}->{XML}) : '';
my $cs_meta = $File->{Charset}->{META} ? &ent($File->{Charset}->{META}) : '';
#
# Add a warning if there was charset info conflict (HTTP header,
# XML declaration, or <meta> element).
if (&conflict($File->{Charset}->{HTTP}, $File->{Charset}->{XML})) {
&add_warning($File, 'note', 'Character Encoding mismatch!', <<".EOF.");
The character encoding specified in the HTTP header (<code>$cs_http</code>)
is different from the value in the XML declaration (<code>$cs_xml</code>).
I will use the value from the HTTP header (<code>$cs_use</code>).
.EOF.
} elsif (&conflict($File->{Charset}->{HTTP}, $File->{Charset}->{META})) {
&add_warning($File, 'note', 'Character Encoding mismatch!', <<".EOF.");
The character encoding specified in the HTTP header (<code>$cs_http</code>)
is different from the value in the <code><meta></code> element
(<code>$cs_meta</code>). I will use the value from the HTTP header
(<code>$cs_use</code>) for this validation.
.EOF.
}
elsif (&conflict($File->{Charset}->{XML}, $File->{Charset}->{META})) {
&add_warning($File, 'note', 'Character Encoding mismatch!', <<".EOF.");
The character encoding specified in the XML declaration (<code>$cs_xml</code>)
is different from the value in the <code><meta></code> element
(<code>$cs_meta</code>). I will use the value from the XML declaration
(<code>$cs_xml</code>) for this validation.
.EOF.
$File->{Tentative} |= T_WARN;
}
return $File;
}
#
# Transcode to UTF-8
sub transcode {
my $File = shift;
my ($command, $result_charset) = ('', '');
if ($CFG->{Charsets}->{$File->{Charset}->{Use}}) {
($command, $result_charset) =
split(" ", $CFG->{Charsets}->{$File->{Charset}->{Use}}, 2);
}
$result_charset = exact_charset($File, $result_charset);
if ($command eq 'I') {
# test if given charset is available
eval {my $c = Text::Iconv->new($result_charset, 'utf-8')};
$command = '' if $@;
} elsif ($command eq 'X') {
$@ = "$File->{Charset}->{Use} undefined; replace by $result_charset";
}
if ($command ne 'I') {
my $cs = &ent($File->{Charset}->{Use});
$File->{'Error Flagged'} = TRUE;
$File->{'Error Message'} = sprintf(<<".EOF.", $cs, &ent($@));
<p>Sorry!
A fatal error occurred when attempting to transcode the character
encoding of the document. Either we do not support this character
encoding yet, or you have specified a non-existent character encoding
(often a misspelling).
</p>
<p>The detected character encoding was "%s".</p>
<p>The error was "%s".</p>
<p>
If you believe the character encoding to be valid you can submit a
request for that character encoding (see the
<a href="feedback.html">feedback page</a> for details) and we will
look into supporting it in the future.
</p>
.EOF.
$File->{'Error Message'} .= &iana_charset_blurb();
return $File;
}
my $c = Text::Iconv->new($result_charset, 'utf-8');
my $line = 0;
for (@{$File->{Content}}) {
my $in = $_;
$line++;
$_ = $c->convert($_); # $_ is local!!
if ($in ne "" and (!defined($_) || $_ eq "")) {
push @{$File->{Lines}}, $line;
# try to decoded as much as possible of the line
my $short = 0; # longest okay
my $long = (length $in) - 1; # longest unknown
while ($long > $short) { # binary search
my $try = int (($long+$short+1) / 2);
my $converted = $c->convert(substr($in, 0, $try));
if (!defined($converted) || $converted eq "") {
$long = $try-1;
} else {
$short = $try;
}
}
my $remain = (length $in) - $short;
$_ = $c->convert(substr($in,0,$short))
. "#### $remain byte(s) unconvertable ####";
}
}
return $File;
}
#
# Check correctness of UTF-8 both for UTF-8 input and for conversion results
sub check_utf8 {
my $File = shift;
for (my $i = 0; $i < $#{$File->{Content}}; $i++) {
# substitution needed for very long lines (>32K), to avoid backtrack
# stack overflow. Handily, this also happens to count characters.
local $_ = $File->{Content}->[$i];
my $count =
s/ [\x00-\x7F] # ASCII
| [\xC2-\xDF] [\x80-\xBF] # non-overlong 2-byte sequences
| \xE0[\xA0-\xBF] [\x80-\xBF] # excluding overlongs
| [\xE1-\xEC\xEE\xEF][\x80-\xBF]{2} # straight 3-byte sequences
| \xED[\x80-\x9F] [\x80-\xBF] # excluding surrogates
| \xF0[\x90-\xBF] [\x80-\xBF]{2} # planes 1-3
| [\xF1-\xF3] [\x80-\xBF]{3} # planes 4-15
| \xF4[\x80-\x8F][\x80-\xBF]{2} # plane 16
//xg;
if (length) {
push @{$File->{Lines}}, ($i+1);
$File->{Content}->[$i] = "#### encoding problem on this line, not shown ####";
$count = 50; # length of above text
}
$count += 0; # Force numeric.
$File->{Offsets}->[$i + 1] = [$count, $File->{Offsets}->[$i]->[1] + $count];
}
# Add a warning if doc is UTF-8 and contains a BOM.
if ($File->{Content}->[0] =~ m(^\xEF\xBB\xBF)) {
&add_warning($File, 'note', 'Note:', <<".EOF.");
The Unicode Byte-Order Mark (BOM) in UTF-8 encoded files is known to cause
problems for some text editors and older browsers. You may want to consider
avoiding its use until it is better supported.
.EOF.
}
return $File;
}
#
# byte error analysis
sub byte_error {
my $File = shift;
my @lines = @{$File->{Lines}};
if (scalar @lines) {
$File->{'Error Flagged'} = TRUE;
my $s = $#lines ? 's' : '';
my $lines = join ', ', split ',', Set::IntSpan->new(\@lines)->run_list;
my $cs = &ent($File->{Charset}->{Use});
$File->{'Error Message'} = <<".EOF.";
<p class="error">
Sorry, I am unable to validate this document because on line$s
<strong>$lines</strong>
it contained one or more bytes that I cannot interpret as
<code>$cs</code> (in other words, the bytes
found are not valid values in the specified Character Encoding).
Please check both the content of the file and the character
encoding indication.
</p>
.EOF.
}
return $File;
}
#
# Return an XML report for the page.
sub report_xml {
my $File = shift;
my $valid = ($File->{'Is Valid'} ? 'Valid' : 'Invalid');
my $errs = ($File->{'Is Valid'} ? '0' : scalar @{$File->{Errors}});
print <<".EOF.";
Content-Type: application/xml; charset=UTF-8
X-W3C-Validator-Status: $valid
X-W3C-Validator-Errors: $errs
<?xml version="1.0" encoding="UTF-8"?>
<?xml-stylesheet type="text/xsl" href="xml-results.xsl"?>
<!DOCTYPE result [
<!ELEMENT result (meta, warnings?, messages?)>
<!ATTLIST result
version CDATA #FIXED '0.9'
>
<!ELEMENT meta (uri, modified, server, size, encoding, doctype)>
<!ELEMENT uri (#PCDATA)>
<!ELEMENT modified (#PCDATA)>
<!ELEMENT server (#PCDATA)>
<!ELEMENT size (#PCDATA)>
<!ELEMENT encoding (#PCDATA)>
<!ELEMENT doctype (#PCDATA)>
<!ELEMENT warnings (warning)+>
<!ELEMENT warning (#PCDATA)>
<!ELEMENT messages (msg)*>
<!ELEMENT msg (#PCDATA)>
<!ATTLIST msg
line CDATA #IMPLIED
col CDATA #IMPLIED
offset CDATA #IMPLIED
>
]>
.EOF.
print qq(
<result>
<meta>
<uri>), &ent($File->{URI}), qq(</uri>
<modified>), &ent($File->{Modified}), qq(</modified>
<server>), $File->{Server}, qq(</server>
<size>), &ent($File->{Size}), qq(</size>
<encoding>), &ent($File->{Charset}->{Use}), qq(</encoding>
<doctype>), &ent($File->{DOCTYPE}), qq(</doctype>
</meta>
);
&add_warning($File, 'note', 'Note:', <<".EOF.");
This interface is highly experimental and the output *will* change
-- probably even several times -- before finished. Do *not* rely on it!
See http://validator.w3.org/docs/users.html#api-warning
.EOF.
if (defined $File->{Warnings} and scalar @{$File->{Warnings}}) {
print qq( <warnings>\n);
printf qq( <warning>%s</warning>\n),
&ent($_->{Message}) for @{$File->{Warnings}};
print qq( </warnings>\n);
}
if (defined $File->{Errors} and scalar @{$File->{Errors}}) {
print qq( <messages>\n);
foreach my $err (@{$File->{Errors}}) {
chomp $err->{msg};
# Find index into the %frag hash for the "explanation..." links.
$err->{idx} = $err->{msg};
$err->{idx} =~ s/"[^\"]*"/FOO/g;
$err->{idx} =~ s/[^A-Za-z ]//g;
$err->{idx} =~ s/\s+/ /g; # Collapse spaces
$err->{idx} =~ s/(^\s|\s$)//g; # Remove leading and trailing spaces.
$err->{idx} =~ s/(FOO )+/FOO /g; # Collapse FOOs.
$err->{idx} =~ s/FOO FOO/FOO/g; # Collapse FOOs.
my $offset = $File->{Offsets}->[$err->{line} - 1]->[1] + $err->{char};
printf <<".EOF.", &ent($err->{msg});
<msg line="$err->{line}" col="$err->{char}" offset="$offset">%s</msg>
.EOF.
}
print qq( </messages>\n);
}
print qq(</result>\n);
}
#
# Return an EARL report for the page.
sub report_earl {
my $File = shift;
my $valid = ($File->{'Is Valid'} ? 'Valid' : 'Invalid');
my $errs = ($File->{'Is Valid'} ? '0' : scalar @{$File->{Errors}});
print <<".EOF.";
Content-Type: application/rdf+xml; charset=UTF-8
X-W3C-Validator-Status: $valid
X-W3C-Validator-Errors: $errs
<?xml version="1.0" encoding="UTF-8"?>
<rdf:RDF
xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
xmlns="http://www.w3.org/2001/03/earl/1.0-test#"
xmlns:val="http://validator.w3.org/this_will_change/do_not_rely_on_it!">
<Assertor rdf:about="http://validator.w3.org/">
<name>W3 Validator</name>
<contactInfo rdf:resource="http://validator.w3.org/about.html"/>
<testMode rdf:resource="http://www.w3.org/2001/03/earl/1.00#Auto" />
.EOF.
unless ($File->{'Is Valid'}) {
printf <<".EOF.", &ent($File->{URI});
<asserts>
<Assertion rdf:ID="result">
<subject rdf:resource="%s" />
<result rdf:resource="http://www.w3.org/2001/03/earl/1.00#fails" />
<testCase rdf:resource="http://www.w3.org/MarkUp/" />
<note>Invalid!</note>
</Assertion>
</asserts>
.EOF.
my $errnum = 0 ;
foreach my $err (@{$File->{Errors}}) {
++$errnum ;
chomp $err->{msg};
# Find index into the %frag hash for the "explanation..." links.
$err->{idx} = $err->{msg};
$err->{idx} =~ s/"[^\"]*"/FOO/g;
$err->{idx} =~ s/[^A-Za-z ]//g;
$err->{idx} =~ s/\s+/ /g; # Collapse spaces
$err->{idx} =~ s/(^\s|\s\Z)//g; # Remove leading and trailing spaces.
$err->{idx} =~ s/(FOO )+/FOO /g; # Collapse FOOs.
$err->{idx} =~ s/FOO FOO/FOO/g; # Collapse FOOs.
my @offsets = (
$File->{Offsets}->[$err->{line} ]->[0],
$File->{Offsets}->[$err->{line} - 1]->[1],
$File->{Offsets}->[$err->{line} - 1]->[1] + $err->{char}
);
printf <<".EOF.", &ent($File->{URI}), &ent($err->{msg});
<asserts>
<Assertion rdf:ID="err$errnum">
<subject rdf:parseType="Resource">
<reprOf rdf:resource="%s"/>
<val:line>$err->{line}</val:line>
<val:column>$err->{char}</val:column>
<val:offset>@offsets</val:offset>
</subject>
<result rdf:resource="http://www.w3.org/2003/03/earl/1.00#fails" />
<testCase rdf:resource="http://www.w3.org/Markup/" />
<note>%s</note>
</Assertion>
</asserts>
.EOF.
}
} else {
printf <<".EOF.", &ent($File->{URI});
<asserts>
<Assertion>
<subject rdf:resource="%s" />
<result rdf:resource="http://www.w3.org/2001/03/earl/1.00#passes" />
<testCase rdf:resource="http://www.w3.org/MarkUp/" />
<note>Valid!</note>
</Assertion>
</asserts>
.EOF.
}
print <<".EOF.";
</Assertor>
</rdf:RDF>
.EOF.
}
#
# Return a Notation3 EARL report for the page.
#
# @@ TODO: escape output
sub report_n3 {
my $File = shift;
my $valid = ($File->{'Is Valid'} ? 'Valid' : 'Invalid');
my $errs = ($File->{'Is Valid'} ? '0' : scalar @{$File->{Errors}});
print <<".EOF.";
Content-Type: text/plain; charset=UTF-8
X-W3C-Validator-Status: $valid
X-W3C-Validator-Errors: $errs
\@prefix earl: <http://www.w3.org/2001/03/earl/1.0-test#> .
\@prefix rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#> .
\@prefix val: <http://validator.w3.org/this_will_change/do_not_rely_on_it!> .
<http://validator.w3.org/> a earl:Assertor;
earl:name "W3 Validator";
earl:asserts
.EOF.
unless ($File->{'Is Valid'}) {
for (my $i = 0; $i <= scalar @{$File->{Errors}}; $i++) {
my $err = $File->{Errors}->[$i];
chomp $err->{msg};
# Find index into the %frag hash for the "explanation..." links.
$err->{idx} = $err->{msg};
$err->{idx} =~ s/"[^\"]*"/FOO/g;
$err->{idx} =~ s/[^A-Za-z ]//g;
$err->{idx} =~ s/\s+/ /g; # Collapse spaces
$err->{idx} =~ s/(^\s|\s\Z)//g; # Remove leading and trailing spaces.
$err->{idx} =~ s/(FOO )+/FOO /g; # Collapse FOOs.
$err->{idx} =~ s/FOO FOO/FOO/g; # Collapse FOOs.
my @offsets = (
$File->{Offsets}->[$err->{line} ]->[0],
$File->{Offsets}->[$err->{line} - 1]->[1],
$File->{Offsets}->[$err->{line} - 1]->[1] + $err->{char}
);
print <<".EOF.";
[
earl:testMode earl:Auto;
rdf:predicate earl:fails;
rdf:subject [
val:column "$err->{char}";
val:line "$err->{line}";
val:offset "@offsets";
earl:testSubject <$File->{URI}>
];
rdf:object [
earl:id <http://www.w3.org/HTML/>;
earl:note """$err->{msg} """
]
.EOF.
if ($i == scalar @{$File->{Errors}}) {
print " ]\n";
} else {
print " ],\n";
}
}
} else {
print <<".EOF.";
[
earl:testMode earl:Auto;
rdf:predicate earl:passes;
rdf:subject [earl:testSubject <$File->{URI}>];
rdf:object [
earl:id <http://www.w3.org/HTML/>;
earl:note "Valid"
]
]
.EOF.
}
print " .\n";
}
#
# Autodetection as in Appendix F of the XML 1.0 Recommendation.
# <http://www.w3.org/TR/2000/REC-xml-20001006#sec-guessing>
#
# return values are: (base_encoding, BOMSize, Size, Pattern)
sub find_base_encoding {
local $_ = shift;
# With a Byte Order Mark:
return ('ucs-4be', 4, 4, '\0\0\0(.)')
if /^\x00\x00\xFE\xFF/; # UCS-4, big-endian machine (1234)
return ('ucs-4le', 4, 4, '(.)\0\0\0')
if /^\xFF\xFE\x00\x00/; # UCS-4, little-endian machine (4321)
return ('utf-16be', 2, 2, '\0(.)')
if /^\xFE\xFF/; # UTF-16, big-endian.
return ('utf-16le', 2, 2, '(.)\0')
if /^\xFF\xFE/; # UTF-16, little-endian.
return ('utf-8', 3, 1, '')
if /^\xEF\xBB\xBF/; # UTF-8.
# Without a Byte Order Mark:
return ('ucs-4be', 0, 4, '\0\0\0(.)')
if /^\x00\x00\x00\x3C/; # UCS-4 or 32bit; big-endian machine (1234 order).
return ('ucs-4le', 0, 4, '(.)\0\0\0')
if /^\x3C\x00\x00\x00/; # UCS-4 or 32bit; little-endian machine (4321 order).
return ('utf-16be', 0, 2, '\0(.)')
if /^\x00\x3C\x00\x3F/; # UCS-2, UTF-16, or 16bit; big-endian.
return ('utf-16le', 0, 2, '(.)\0')
if /^\x3C\x00\x3F\x00/; # UCS-2, UTF-16, or 16bit; little-endian.
return ('utf-8', 0, 1, '')
if /^\x3C\x3F\x78\x6D/; # UTF-8, ISO-646, ASCII, ISO-8859-*, Shift-JIS, EUC, etc.
return ('ebcdic', 0, 1, '')
if /^\x4C\x6F\xA7\x94/; # EBCDIC
return ('', 0, 1, '');
# nothing in particular
}
#
# Find encoding in document according to XML rules
# Only meaningful if file contains a BOM, or for well-formed XML!
sub find_xml_encoding {
my $File = shift;
my ($CodeUnitSize, $Pattern);
($File->{Charset}->{Auto}, $File->{BOM}, $CodeUnitSize, $Pattern)
= &find_base_encoding($File->{Bytes});
my $someBytes = substr $File->{Bytes}, $File->{BOM}, ($CodeUnitSize * 100);
my $someText = ''; # 100 arbitrary, but enough in any case
# translate from guessed encoding to ascii-compatible
if ($File->{Charset}->{Auto} eq 'ebcdic') {
# special treatment for EBCDIC, maybe use tr///
# work on this later
}
elsif (!$Pattern) {
$someText = $someBytes; # efficiency shortcut
}
else { # generic code for UTF-16/UCS-4
$someBytes =~ /^(($Pattern)*)/s;
$someText = $1; # get initial piece without chars >255
$someText =~ s/$Pattern/$1/sg; # select the relevant bytes
}
# try to find encoding pseudo-attribute
my $s = '[\ \t\n\r]';
$someText =~ m(^<\?xml $s+ version $s* = $s* ([\'\"]) [-._:a-zA-Z0-9]+ \1 $s+
encoding $s* = $s* ([\'\"]) ([A-Za-z][-._A-Za-z0-9]*) \2
)xso;
$File->{Charset}->{XML} = lc $3;
return $File;
}
#
# Abort with a message if an error was flagged at point.
sub abort_if_error_flagged {
my $File = shift;
my $Flags = shift;
return unless $File->{'Error Flagged'};
&prep_template($File, $E);
$E->param(error_message => $File->{'Error Message'});
print $E->output;
exit;
}
#
# conflicting encodings
sub conflict {
my $encodingA = shift;
my $encodingB = shift;
return $encodingA && $encodingB && ($encodingA ne $encodingB);
}
#
# Construct a self-referential URL from a CGI.pm $q object.
sub self_url_q {
my ($q, $File) = @_;
my $thispage = $File->{Env}->{'Self URI'};
$thispage .= '?uri=' . uri_escape($q->param('uri'));
$thispage .= ';ss=1' if $q->param('ss');
$thispage .= ';sp=1' if $q->param('sp');
$thispage .= ';noatt=1' if $q->param('noatt');
$thispage .= ';outline=1' if $q->param('outline');
$thispage .= ';No200=1' if $q->param('No200');
$thispage .= ';verbose=1' if $q->param('verbose');
if ($q->param('doctype')
and not $q->param('doctype') =~ /(Inline|detect)/i) {
$thispage .= ';doctype=' . uri_escape($q->param('doctype'));
}
if ($q->param('charset') and not $q->param('charset') =~ /detect/i) {
$thispage .= ';charset=' . uri_escape($q->param('charset'));
}
return $thispage;
}
#
# Return random Tip with it's URL.
sub get_tip {
my @tipAddrs = keys %{$CFG->{Tips_DB}};
my $tipAddr = $tipAddrs[rand scalar @tipAddrs];
my $tipSlug = $CFG->{Tips_DB}->{$tipAddr};
return [$tipAddr, $tipSlug];
}
#
# Construct a self-referential URL from a $File object.
sub self_url_file {
my $File = shift;
my $thispage = $File->{Env}->{'Self URI'};
my $escaped_uri = uri_escape($File->{URI});
$thispage .= qq(?uri=$escaped_uri);
$thispage .= ';ss=1' if $File->{Opt}->{'Show Source'};
$thispage .= ';sp=1' if $File->{Opt}->{'Show Parsetree'};
$thispage .= ';noatt=1' if $File->{Opt}->{'No Attributes'};
$thispage .= ';outline=1' if $File->{Opt}->{'Outline'};
$thispage .= ';verbose=1' if $File->{Opt}->{'Verbose'};
$thispage .= ';No200=1' if $File->{Opt}->{'No200'};
return $thispage;
}
################################################################################
# Abandon all hope ye who enter here... ########################################
################################################################################
#
# This is where the SOAP magic happens.
package MySOAP;
sub check {
my $class = shift || '';
my $uri = shift || '';
my $File = &main::handle_uri($uri, {});
$File = &main::find_xml_encoding($File);
if ($File->{Charset}->{HTTP}) { warn "HTTP";
$File->{Charset}->{Use} = $File->{Charset}->{HTTP};
} elsif ($File->{ContentType} =~ m(^text/([-.a-zA-Z0-9]\+)?xml$)) { warn "CT";
$File->{Charset}->{Use} = 'us-ascii';
} elsif ($File->{Charset}->{XML}) { warn "XML";
$File->{Charset}->{Use} = $File->{Charset}->{XML};
} elsif ($File->{Charset}->{Auto} =~ /^utf-16[bl]e$/ && $File->{BOM} == 2) { warn "autoBOM";
$File->{Charset}->{Use} = 'utf-16';
} elsif ($File->{ContentType} =~ m(^application/([-.a-zA-Z0-9]+\+)?xml$)) { warn "app+xml";
$File->{Charset}->{Use} = "utf-8";
} elsif (&main::is_xml($File) and not $File->{ContentType} =~ m(^text/)) { warn "text";
$File->{Charset}->{Use} = 'utf-8';
}
$File->{Content} = &main::normalize_newlines($File->{Bytes},
&main::exact_charset($File, $File->{Charset}->{Use}));
$File = &main::preparse($File);
unless ($File->{Charset}->{Use}) {
$File->{Charset}->{Use} = $File->{Charset}->{META};
}
$File->{Type} = 'xhtml+xml' if $File->{DOCTYPE} =~ /xhtml/i;
$File->{Type} = 'mathml+xml' if $File->{DOCTYPE} =~ /mathml/i;
$File = &main::parse($File);
if ($File->{'Is Valid'}) {
return $File->{ESIS};
} else {
return $File->{Errors};
# return join '', map {"$_->{line}:$_->{char}:$_->{msg}\n"} @{$File->{Errors}};
}
}
# Local Variables:
# mode: perl
# indent-tabs-mode: nil
# tab-width: 2
# perl-indent-level: 2
# End:
|