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
|
/* -*- Mode: C++; tab-width: 4; indent-tabs-mode: nil; c-basic-offset: 4 -*- */
/*
* This file is part of the LibreOffice project.
*
* This Source Code Form is subject to the terms of the Mozilla Public
* License, v. 2.0. If a copy of the MPL was not distributed with this
* file, You can obtain one at http://mozilla.org/MPL/2.0/.
*
* This file incorporates work covered by the following license notice:
*
* Licensed to the Apache Software Foundation (ASF) under one or more
* contributor license agreements. See the NOTICE file distributed
* with this work for additional information regarding copyright
* ownership. The ASF licenses this file to you under the Apache
* License, Version 2.0 (the "License"); you may not use this file
* except in compliance with the License. You may obtain a copy of
* the License at http://www.apache.org/licenses/LICENSE-2.0 .
*/
#include <comphelper/string.hxx>
#include <tools/stream.hxx>
#include <tools/debug.hxx>
#include <tools/color.hxx>
#include <rtl/ustrbuf.hxx>
#include <rtl/strbuf.hxx>
#include <rtl/character.hxx>
#include <tools/tenccvt.hxx>
#include <tools/datetime.hxx>
#include <svl/inettype.hxx>
#include <com/sun/star/beans/PropertyAttribute.hpp>
#include <com/sun/star/document/XDocumentProperties.hpp>
#include <svtools/parhtml.hxx>
#include <svtools/htmltokn.h>
#include <svtools/htmlkywd.hxx>
#include <memory>
#include <utility>
using namespace ::com::sun::star;
const sal_Int32 MAX_LEN( 1024L );
const sal_Int32 MAX_ENTITY_LEN( 8L );
// Tables to convert option values into strings
// <INPUT TYPE=xxx>
static HTMLOptionEnum<HTMLInputType> const aInputTypeOptEnums[] =
{
{ OOO_STRING_SVTOOLS_HTML_IT_text, HTMLInputType::Text },
{ OOO_STRING_SVTOOLS_HTML_IT_password, HTMLInputType::Password },
{ OOO_STRING_SVTOOLS_HTML_IT_checkbox, HTMLInputType::Checkbox },
{ OOO_STRING_SVTOOLS_HTML_IT_radio, HTMLInputType::Radio },
{ OOO_STRING_SVTOOLS_HTML_IT_range, HTMLInputType::Range },
{ OOO_STRING_SVTOOLS_HTML_IT_scribble, HTMLInputType::Scribble },
{ OOO_STRING_SVTOOLS_HTML_IT_file, HTMLInputType::File },
{ OOO_STRING_SVTOOLS_HTML_IT_hidden, HTMLInputType::Hidden },
{ OOO_STRING_SVTOOLS_HTML_IT_submit, HTMLInputType::Submit },
{ OOO_STRING_SVTOOLS_HTML_IT_image, HTMLInputType::Image },
{ OOO_STRING_SVTOOLS_HTML_IT_reset, HTMLInputType::Reset },
{ OOO_STRING_SVTOOLS_HTML_IT_button, HTMLInputType::Button },
{ nullptr, (HTMLInputType)0 }
};
// <TABLE FRAME=xxx>
static HTMLOptionEnum<HTMLTableFrame> const aTableFrameOptEnums[] =
{
{ OOO_STRING_SVTOOLS_HTML_TF_void, HTMLTableFrame::Void },
{ OOO_STRING_SVTOOLS_HTML_TF_above, HTMLTableFrame::Above },
{ OOO_STRING_SVTOOLS_HTML_TF_below, HTMLTableFrame::Below },
{ OOO_STRING_SVTOOLS_HTML_TF_hsides, HTMLTableFrame::HSides },
{ OOO_STRING_SVTOOLS_HTML_TF_lhs, HTMLTableFrame::LHS },
{ OOO_STRING_SVTOOLS_HTML_TF_rhs, HTMLTableFrame::RHS },
{ OOO_STRING_SVTOOLS_HTML_TF_vsides, HTMLTableFrame::VSides },
{ OOO_STRING_SVTOOLS_HTML_TF_box, HTMLTableFrame::Box },
{ OOO_STRING_SVTOOLS_HTML_TF_border, HTMLTableFrame::Box },
{ nullptr, (HTMLTableFrame)0 }
};
// <TABLE RULES=xxx>
static HTMLOptionEnum<HTMLTableRules> const aTableRulesOptEnums[] =
{
{ OOO_STRING_SVTOOLS_HTML_TR_none, HTMLTableRules::NONE },
{ OOO_STRING_SVTOOLS_HTML_TR_groups, HTMLTableRules::Groups },
{ OOO_STRING_SVTOOLS_HTML_TR_rows, HTMLTableRules::Rows },
{ OOO_STRING_SVTOOLS_HTML_TR_cols, HTMLTableRules::Cols },
{ OOO_STRING_SVTOOLS_HTML_TR_all, HTMLTableRules::All },
{ nullptr, (HTMLTableRules)0 }
};
HTMLOption::HTMLOption( sal_uInt16 nTok, const OUString& rToken,
const OUString& rValue )
: aValue(rValue)
, aToken(rToken)
, nToken( nTok )
{
DBG_ASSERT( nToken>=HTML_OPTION_START && nToken<HTML_OPTION_END,
"HTMLOption: unknown token" );
}
sal_uInt32 HTMLOption::GetNumber() const
{
DBG_ASSERT( (nToken>=HTML_OPTION_NUMBER_START &&
nToken<HTML_OPTION_NUMBER_END) ||
(nToken>=HTML_OPTION_CONTEXT_START &&
nToken<HTML_OPTION_CONTEXT_END) ||
nToken==HTML_O_VALUE,
"GetNumber: Option not numerical" );
OUString aTmp(comphelper::string::stripStart(aValue, ' '));
sal_Int32 nTmp = aTmp.toInt32();
return nTmp >= 0 ? (sal_uInt32)nTmp : 0;
}
sal_Int32 HTMLOption::GetSNumber() const
{
DBG_ASSERT( (nToken>=HTML_OPTION_NUMBER_START && nToken<HTML_OPTION_NUMBER_END) ||
(nToken>=HTML_OPTION_CONTEXT_START && nToken<HTML_OPTION_CONTEXT_END),
"GetSNumber: Option not numerical" );
OUString aTmp(comphelper::string::stripStart(aValue, ' '));
return aTmp.toInt32();
}
void HTMLOption::GetNumbers( std::vector<sal_uInt32> &rNumbers ) const
{
rNumbers.clear();
// This is a very simplified scanner: it only searches all
// numerals in the string.
bool bInNum = false;
sal_uLong nNum = 0;
for( sal_Int32 i=0; i<aValue.getLength(); i++ )
{
sal_Unicode c = aValue[ i ];
if( c>='0' && c<='9' )
{
nNum *= 10;
nNum += (c - '0');
bInNum = true;
}
else if( bInNum )
{
rNumbers.push_back( nNum );
bInNum = false;
nNum = 0;
}
}
if( bInNum )
{
rNumbers.push_back( nNum );
}
}
void HTMLOption::GetColor( Color& rColor ) const
{
DBG_ASSERT( (nToken>=HTML_OPTION_COLOR_START && nToken<HTML_OPTION_COLOR_END) || nToken==HTML_O_SIZE,
"GetColor: Option is not a color." );
OUString aTmp(aValue.toAsciiLowerCase());
sal_uInt32 nColor = SAL_MAX_UINT32;
if (!aTmp.isEmpty() && aTmp[0] != '#')
nColor = GetHTMLColor(aTmp);
if( SAL_MAX_UINT32 == nColor )
{
nColor = 0;
sal_Int32 nPos = 0;
for (sal_uInt32 i=0; i<6; ++i)
{
// Whatever Netscape does to get color values,
// at maximum three characters < '0' are ignored.
sal_Unicode c = nPos<aTmp.getLength() ? aTmp[ nPos++ ] : '0';
if( c < '0' )
{
c = nPos<aTmp.getLength() ? aTmp[nPos++] : '0';
if( c < '0' )
c = nPos<aTmp.getLength() ? aTmp[nPos++] : '0';
}
nColor *= 16;
if( c >= '0' && c <= '9' )
nColor += (c - '0');
else if( c >= 'a' && c <= 'f' )
nColor += (c + 0xa - 'a');
}
}
rColor.SetRed( (sal_uInt8)((nColor & 0x00ff0000) >> 16) );
rColor.SetGreen( (sal_uInt8)((nColor & 0x0000ff00) >> 8));
rColor.SetBlue( (sal_uInt8)(nColor & 0x000000ff) );
}
HTMLInputType HTMLOption::GetInputType() const
{
DBG_ASSERT( nToken==HTML_O_TYPE, "GetInputType: Option not TYPE" );
return (HTMLInputType)GetEnum( aInputTypeOptEnums, HTMLInputType::Text );
}
HTMLTableFrame HTMLOption::GetTableFrame() const
{
DBG_ASSERT( nToken==HTML_O_FRAME, "GetTableFrame: Option not FRAME" );
return (HTMLTableFrame)GetEnum( aTableFrameOptEnums );
}
HTMLTableRules HTMLOption::GetTableRules() const
{
DBG_ASSERT( nToken==HTML_O_RULES, "GetTableRules: Option not RULES" );
return (HTMLTableRules)GetEnum( aTableRulesOptEnums );
}
HTMLParser::HTMLParser( SvStream& rIn, bool bReadNewDoc ) :
SvParser( rIn ),
bNewDoc(bReadNewDoc),
bIsInHeader(true),
bIsInBody(false),
bReadListing(false),
bReadXMP(false),
bReadPRE(false),
bReadTextArea(false),
bReadScript(false),
bReadStyle(false),
bEndTokenFound(false),
bPre_IgnoreNewPara(false),
bReadNextChar(false),
bReadComment(false),
nPre_LinePos(0),
mnPendingOffToken(0)
{
//#i76649, default to UTF-8 for HTML unless we know differently
SetSrcEncoding(RTL_TEXTENCODING_UTF8);
}
HTMLParser::~HTMLParser()
{
}
SvParserState HTMLParser::CallParser()
{
eState = SvParserState::Working;
nNextCh = GetNextChar();
SaveState( 0 );
nPre_LinePos = 0;
bPre_IgnoreNewPara = false;
AddFirstRef();
Continue( 0 );
if( SvParserState::Pending != eState )
ReleaseRef(); // Parser not needed anymore
return eState;
}
void HTMLParser::Continue( int nToken )
{
if( !nToken )
nToken = GetNextToken();
while( IsParserWorking() )
{
SaveState( nToken );
nToken = FilterToken( nToken );
if( nToken )
NextToken( nToken );
if( IsParserWorking() )
SaveState( 0 ); // continue with new token
nToken = GetNextToken();
}
}
int HTMLParser::FilterToken( int nToken )
{
switch( nToken )
{
case sal_Unicode(EOF):
nToken = 0;
break; // don't pass
case HTML_HEAD_OFF:
bIsInBody = true;
bIsInHeader = false;
break;
case HTML_HEAD_ON:
bIsInHeader = true;
break;
case HTML_BODY_ON:
bIsInHeader = false;
bIsInBody = true;
break;
case HTML_FRAMESET_ON:
bIsInHeader = false;
bIsInBody = false;
break;
case HTML_BODY_OFF:
bIsInBody = bReadPRE = bReadListing = bReadXMP = false;
break;
case HTML_HTML_OFF:
nToken = 0;
bReadPRE = bReadListing = bReadXMP = false;
break; // HTML_ON hasn't been passed either !
case HTML_PREFORMTXT_ON:
StartPRE();
break;
case HTML_PREFORMTXT_OFF:
FinishPRE();
break;
case HTML_LISTING_ON:
StartListing();
break;
case HTML_LISTING_OFF:
FinishListing();
break;
case HTML_XMP_ON:
StartXMP();
break;
case HTML_XMP_OFF:
FinishXMP();
break;
default:
if( bReadPRE )
nToken = FilterPRE( nToken );
else if( bReadListing )
nToken = FilterListing( nToken );
else if( bReadXMP )
nToken = FilterXMP( nToken );
break;
}
return nToken;
}
#define HTML_ISDIGIT( c ) rtl::isAsciiDigit(c)
#define HTML_ISALPHA( c ) rtl::isAsciiAlpha(c)
#define HTML_ISALNUM( c ) rtl::isAsciiAlphanumeric(c)
#define HTML_ISSPACE( c ) ( ' ' == c || (c >= 0x09 && c <= 0x0d) )
#define HTML_ISPRINTABLE( c ) ( c >= 32 && c != 127)
#define HTML_ISHEXDIGIT( c ) rtl::isAsciiHexDigit(c)
int HTMLParser::ScanText( const sal_Unicode cBreak )
{
OUStringBuffer sTmpBuffer( MAX_LEN );
bool bContinue = true;
bool bEqSignFound = false;
sal_uInt32 cQuote = 0U;
while( bContinue && IsParserWorking() )
{
bool bNextCh = true;
switch( nNextCh )
{
case '&':
bEqSignFound = false;
if( bReadXMP )
sTmpBuffer.append( '&' );
else
{
sal_uLong nStreamPos = rInput.Tell();
sal_uLong nLinePos = GetLinePos();
sal_uInt32 cChar = 0U;
if( '#' == (nNextCh = GetNextChar()) )
{
nNextCh = GetNextChar();
const bool bIsHex( 'x' == nNextCh );
const bool bIsDecOrHex( bIsHex || HTML_ISDIGIT(nNextCh) );
if ( bIsDecOrHex )
{
if ( bIsHex )
{
nNextCh = GetNextChar();
while ( HTML_ISHEXDIGIT(nNextCh) )
{
cChar = cChar * 16U +
( nNextCh <= '9'
? sal_uInt32( nNextCh - '0' )
: ( nNextCh <= 'F'
? sal_uInt32( nNextCh - 'A' + 10 )
: sal_uInt32( nNextCh - 'a' + 10 ) ) );
nNextCh = GetNextChar();
}
}
else
{
do
{
cChar = cChar * 10U + sal_uInt32( nNextCh - '0');
nNextCh = GetNextChar();
}
while( HTML_ISDIGIT(nNextCh) );
}
if( RTL_TEXTENCODING_DONTKNOW != eSrcEnc &&
RTL_TEXTENCODING_UCS2 != eSrcEnc &&
RTL_TEXTENCODING_UTF8 != eSrcEnc &&
cChar < 256 )
{
const sal_uInt32 convertFlags =
RTL_TEXTTOUNICODE_FLAGS_UNDEFINED_DEFAULT |
RTL_TEXTTOUNICODE_FLAGS_MBUNDEFINED_DEFAULT |
RTL_TEXTTOUNICODE_FLAGS_INVALID_DEFAULT;
sal_Char cEncodedChar = static_cast<sal_Char>(cChar);
cChar = OUString(&cEncodedChar, 1, eSrcEnc, convertFlags).toChar();
if( 0U == cChar )
{
// If the character could not be
// converted, because a conversion is not
// available, do no conversion at all.
cChar = cEncodedChar;
}
}
}
else
nNextCh = 0U;
if ( ! rtl::isUnicodeCodePoint( cChar ) )
cChar = '?';
}
else if( HTML_ISALPHA( nNextCh ) )
{
OUStringBuffer sEntityBuffer( MAX_ENTITY_LEN );
sal_Int32 nPos = 0L;
do
{
sEntityBuffer.appendUtf32( nNextCh );
nPos++;
nNextCh = GetNextChar();
}
while( nPos < MAX_ENTITY_LEN && HTML_ISALNUM( nNextCh ) &&
!rInput.IsEof() );
if( IsParserWorking() && !rInput.IsEof() )
{
OUString sEntity(sEntityBuffer.getStr(), nPos);
cChar = GetHTMLCharName( sEntity );
// not found ( == 0 ): plain text
// or a character which is inserted as attribute
if( 0U == cChar && ';' != nNextCh )
{
DBG_ASSERT( rInput.Tell() - nStreamPos ==
(sal_uLong)(nPos+1L)*GetCharSize(),
"UTF-8 is failing here" );
for( sal_Int32 i = nPos-1; i>1; i-- )
{
nNextCh = sEntityBuffer[i];
sEntityBuffer.setLength( i );
sEntity = OUString(sEntityBuffer.getStr(), i);
cChar = GetHTMLCharName( sEntity );
if( cChar )
{
rInput.SeekRel( -(long)
((nPos-i)*GetCharSize()) );
nlLinePos -= sal_uInt32(nPos-i);
nPos = i;
ClearTxtConvContext();
break;
}
}
}
if( !cChar ) // unknown character?
{
// back in stream, insert '&'
// and restart with next character
sTmpBuffer.append( '&' );
DBG_ASSERT( rInput.Tell()-nStreamPos ==
(sal_uLong)(nPos+1)*GetCharSize(),
"Wrong stream position" );
DBG_ASSERT( nlLinePos-nLinePos ==
(sal_uLong)(nPos+1),
"Wrong line position" );
rInput.Seek( nStreamPos );
nlLinePos = nLinePos;
ClearTxtConvContext();
break;
}
assert(cChar != 0);
// 1 == Non Breaking Space
// 2 == SoftHyphen
if (cChar == 1 || cChar == 2)
{
if( '>' == cBreak )
{
// When reading the content of a tag we have
// to change it to ' ' or '-'
if( 1U == cChar )
cChar = ' ';
else //2U
cChar = '-';
}
else
{
// If not scanning a tag return token
aToken += sTmpBuffer.makeStringAndClear();
if( !aToken.isEmpty() )
{
// restart with character
nNextCh = '&';
DBG_ASSERT( rInput.Tell()-nStreamPos ==
(sal_uLong)(nPos+1)*GetCharSize(),
"Wrong stream position" );
DBG_ASSERT( nlLinePos-nLinePos ==
(sal_uLong)(nPos+1),
"Wrong line position" );
rInput.Seek( nStreamPos );
nlLinePos = nLinePos;
ClearTxtConvContext();
return HTML_TEXTTOKEN;
}
// Hack: _GetNextChar shall not read the
// next character
if( ';' != nNextCh )
aToken += " ";
if( 1U == cChar )
return HTML_NONBREAKSPACE;
else //2U
return HTML_SOFTHYPH;
}
}
}
else
nNextCh = 0U;
}
// &{...};-JavaScript-Macros are not supported any longer.
else if( IsParserWorking() )
{
sTmpBuffer.append( '&' );
bNextCh = false;
break;
}
bNextCh = (';' == nNextCh);
if( cBreak=='>' && (cChar=='\\' || cChar=='\'' ||
cChar=='\"' || cChar==' ') )
{
// ' and " have to be escaped within tags to separate
// them from ' and " enclosing options.
// \ has to be escaped as well.
// Space is protected because it's not a delimiter between
// options.
sTmpBuffer.append( '\\' );
if( MAX_LEN == sTmpBuffer.getLength() )
aToken += sTmpBuffer.makeStringAndClear();
}
if( IsParserWorking() )
{
if( cChar )
sTmpBuffer.appendUtf32( cChar );
}
else if( SvParserState::Pending==eState && '>'!=cBreak )
{
// Restart with '&', the remainder is returned as
// text token.
if( !aToken.isEmpty() || !sTmpBuffer.isEmpty() )
{
// _GetNextChar() returns the previous text and
// during the next execution a new character is read.
// Thus we have to position in front of the '&'.
nNextCh = 0U;
rInput.Seek( nStreamPos-(sal_uInt32)GetCharSize() );
nlLinePos = nLinePos-1;
ClearTxtConvContext();
bReadNextChar = true;
}
bNextCh = false;
}
}
break;
case '=':
if( '>'==cBreak && !cQuote )
bEqSignFound = true;
sTmpBuffer.appendUtf32( nNextCh );
break;
case '\\':
if( '>'==cBreak )
{
// Innerhalb von Tags kennzeichnen
sTmpBuffer.append( '\\' );
if( MAX_LEN == sTmpBuffer.getLength() )
aToken += sTmpBuffer.makeStringAndClear();
}
sTmpBuffer.append( '\\' );
break;
case '\"':
case '\'':
if( '>'==cBreak )
{
if( bEqSignFound )
cQuote = nNextCh;
else if( cQuote && (cQuote==nNextCh ) )
cQuote = 0U;
}
sTmpBuffer.appendUtf32( nNextCh );
bEqSignFound = false;
break;
case sal_Unicode(EOF):
if( rInput.IsEof() )
{
bContinue = false;
}
else
{
sTmpBuffer.appendUtf32( nNextCh );
}
break;
case '<':
bEqSignFound = false;
if( '>'==cBreak )
sTmpBuffer.appendUtf32( nNextCh );
else
bContinue = false; // break, String zusammen
break;
case '\f':
if( '>' == cBreak )
{
// If scanning options treat it like a space, ...
sTmpBuffer.append( ' ' );
}
else
{
// otherwise it's a separate token.
bContinue = false;
}
break;
case '\r':
case '\n':
if( '>'==cBreak )
{
// cr/lf in tag is handled in GetNextToken_()
sTmpBuffer.appendUtf32( nNextCh );
break;
}
else if( bReadListing || bReadXMP || bReadPRE || bReadTextArea )
{
bContinue = false;
break;
}
// Reduce sequence of CR/LF/BLANK/TAB to a single blank
SAL_FALLTHROUGH;
case '\t':
if( '\t'==nNextCh && bReadPRE && '>'!=cBreak )
{
// Pass Tabs up in <PRE>
bContinue = false;
break;
}
SAL_FALLTHROUGH;
case '\x0b':
if( '\x0b'==nNextCh && (bReadPRE || bReadXMP ||bReadListing) &&
'>'!=cBreak )
{
break;
}
nNextCh = ' ';
SAL_FALLTHROUGH;
case ' ':
sTmpBuffer.appendUtf32( nNextCh );
if( '>'!=cBreak && (!bReadListing && !bReadXMP &&
!bReadPRE && !bReadTextArea) )
{
// Reduce sequences of Blanks/Tabs/CR/LF to a single blank
do {
if( sal_Unicode(EOF) == (nNextCh = GetNextChar()) &&
rInput.IsEof() )
{
if( !aToken.isEmpty() || sTmpBuffer.getLength() > 1L )
{
// Have seen s.th. aside from blanks?
aToken += sTmpBuffer.makeStringAndClear();
return HTML_TEXTTOKEN;
}
else
// Only read blanks: no text must be returned
// and GetNextToken_ has to read until EOF
return 0;
}
} while ( ' ' == nNextCh || '\t' == nNextCh ||
'\r' == nNextCh || '\n' == nNextCh ||
'\x0b' == nNextCh );
bNextCh = false;
}
break;
default:
bEqSignFound = false;
if (nNextCh == cBreak && !cQuote)
bContinue = false;
else
{
do {
// All remaining characters make their way into the text.
sTmpBuffer.appendUtf32( nNextCh );
if( MAX_LEN == sTmpBuffer.getLength() )
{
aToken += sTmpBuffer.makeStringAndClear();
}
if( ( sal_Unicode(EOF) == (nNextCh = GetNextChar()) &&
rInput.IsEof() ) ||
!IsParserWorking() )
{
if( !sTmpBuffer.isEmpty() )
aToken += sTmpBuffer.makeStringAndClear();
return HTML_TEXTTOKEN;
}
} while( HTML_ISALPHA( nNextCh ) || HTML_ISDIGIT( nNextCh ) );
bNextCh = false;
}
}
if( MAX_LEN == sTmpBuffer.getLength() )
aToken += sTmpBuffer.makeStringAndClear();
if( bContinue && bNextCh )
nNextCh = GetNextChar();
}
if( !sTmpBuffer.isEmpty() )
aToken += sTmpBuffer.makeStringAndClear();
return HTML_TEXTTOKEN;
}
int HTMLParser::GetNextRawToken()
{
OUStringBuffer sTmpBuffer( MAX_LEN );
if( bEndTokenFound )
{
// During the last execution we already found the end token,
// thus we don't have to search it again.
bReadScript = false;
bReadStyle = false;
aEndToken.clear();
bEndTokenFound = false;
return 0;
}
// Default return value: HTML_RAWDATA
bool bContinue = true;
int nToken = HTML_RAWDATA;
SaveState( 0 );
while( bContinue && IsParserWorking() )
{
bool bNextCh = true;
switch( nNextCh )
{
case '<':
{
// Maybe we've reached the end.
// Save what we have read previously...
aToken += sTmpBuffer.makeStringAndClear();
// and remember position in stream.
sal_uLong nStreamPos = rInput.Tell();
sal_uLong nLineNr = GetLineNr();
sal_uLong nLinePos = GetLinePos();
// Start of an end token?
bool bOffState = false;
if( '/' == (nNextCh = GetNextChar()) )
{
bOffState = true;
nNextCh = GetNextChar();
}
else if( '!' == nNextCh )
{
sTmpBuffer.appendUtf32( nNextCh );
nNextCh = GetNextChar();
}
// Read following letters
while( (HTML_ISALPHA(nNextCh) || '-'==nNextCh) &&
IsParserWorking() && sTmpBuffer.getLength() < MAX_LEN )
{
sTmpBuffer.appendUtf32( nNextCh );
nNextCh = GetNextChar();
}
OUString aTok( sTmpBuffer.toString() );
aTok = aTok.toAsciiLowerCase();
bool bDone = false;
if( bReadScript || !aEndToken.isEmpty() )
{
if( !bReadComment )
{
if( aTok.startsWith( OOO_STRING_SVTOOLS_HTML_comment ) )
{
bReadComment = true;
}
else
{
// A script has to end with "</SCRIPT>". But
// ">" is optional for security reasons
bDone = bOffState &&
( bReadScript
? aTok == OOO_STRING_SVTOOLS_HTML_script
: aTok.equals(aEndToken) );
}
}
if( bReadComment && '>'==nNextCh && aTok.endsWith( "--" ) )
{
// End of comment of style <!----->
bReadComment = false;
}
}
else
{
// Style sheets can be closed by </STYLE>, </HEAD> or <BODY>
if( bOffState )
bDone = aTok == OOO_STRING_SVTOOLS_HTML_style ||
aTok == OOO_STRING_SVTOOLS_HTML_head;
else
bDone = aTok == OOO_STRING_SVTOOLS_HTML_body;
}
if( bDone )
{
// Done! Return the previously read string (if requested)
// and continue.
bContinue = false;
// nToken==0 means, GetNextToken_ continues to read
if( aToken.isEmpty() && (bReadStyle || bReadScript) )
{
// Immediately close environment (or context?)
// and parse the end token
bReadScript = false;
bReadStyle = false;
aEndToken.clear();
nToken = 0;
}
else
{
// Keep bReadScript/bReadStyle alive
// and parse end token during next execution
bEndTokenFound = true;
}
// Move backwards in stream to '<'
rInput.Seek( nStreamPos );
SetLineNr( nLineNr );
SetLinePos( nLinePos );
ClearTxtConvContext();
nNextCh = '<';
// Don't append string to token.
sTmpBuffer.setLength( 0L );
}
else
{
// remember "</" , everything else we find in the buffer
aToken += "<";
if( bOffState )
aToken += "/";
bNextCh = false;
}
}
break;
case '-':
sTmpBuffer.appendUtf32( nNextCh );
if( bReadComment )
{
bool bTwoMinus = false;
nNextCh = GetNextChar();
while( '-' == nNextCh && IsParserWorking() )
{
bTwoMinus = true;
if( MAX_LEN == sTmpBuffer.getLength() )
aToken += sTmpBuffer.makeStringAndClear();
sTmpBuffer.appendUtf32( nNextCh );
nNextCh = GetNextChar();
}
if( '>' == nNextCh && IsParserWorking() && bTwoMinus )
bReadComment = false;
bNextCh = false;
}
break;
case '\r':
// \r\n? closes the current text token (even if it's empty)
nNextCh = GetNextChar();
if( nNextCh=='\n' )
nNextCh = GetNextChar();
bContinue = false;
break;
case '\n':
// \n closes the current text token (even if it's empty)
nNextCh = GetNextChar();
bContinue = false;
break;
case sal_Unicode(EOF):
// eof closes the current text token and behaves like having read
// an end token
if( rInput.IsEof() )
{
bContinue = false;
if( !aToken.isEmpty() || !sTmpBuffer.isEmpty() )
{
bEndTokenFound = true;
}
else
{
bReadScript = false;
bReadStyle = false;
aEndToken.clear();
nToken = 0;
}
break;
}
SAL_FALLTHROUGH;
default:
// all remaining characters are appended to the buffer
sTmpBuffer.appendUtf32( nNextCh );
break;
}
if( (!bContinue && !sTmpBuffer.isEmpty()) ||
MAX_LEN == sTmpBuffer.getLength() )
aToken += sTmpBuffer.makeStringAndClear();
if( bContinue && bNextCh )
nNextCh = GetNextChar();
}
if( IsParserWorking() )
SaveState( 0 );
else
nToken = 0;
return nToken;
}
// Scan next token
int HTMLParser::GetNextToken_()
{
int nRet = 0;
sSaveToken.clear();
if (mnPendingOffToken)
{
// HTML_<TOKEN>_OFF generated for HTML_<TOKEN>_ON
nRet = mnPendingOffToken;
mnPendingOffToken = 0;
aToken.clear();
return nRet;
}
// Delete options
if (!maOptions.empty())
maOptions.clear();
if( !IsParserWorking() ) // Don't continue if already an error occurred
return 0;
bool bReadNextCharSave = bReadNextChar;
if( bReadNextChar )
{
DBG_ASSERT( !bEndTokenFound,
"Read a character despite </SCRIPT> was read?" );
nNextCh = GetNextChar();
if( !IsParserWorking() ) // Don't continue if already an error occurred
return 0;
bReadNextChar = false;
}
if( bReadScript || bReadStyle || !aEndToken.isEmpty() )
{
nRet = GetNextRawToken();
if( nRet || !IsParserWorking() )
return nRet;
}
do {
bool bNextCh = true;
switch( nNextCh )
{
case '<':
{
sal_uLong nStreamPos = rInput.Tell();
sal_uLong nLineNr = GetLineNr();
sal_uLong nLinePos = GetLinePos();
bool bOffState = false;
if( '/' == (nNextCh = GetNextChar()) )
{
bOffState = true;
nNextCh = GetNextChar();
}
if( HTML_ISALPHA( nNextCh ) || '!'==nNextCh )
{
OUStringBuffer sTmpBuffer;
do {
sTmpBuffer.appendUtf32( nNextCh );
if( MAX_LEN == sTmpBuffer.getLength() )
aToken += sTmpBuffer.makeStringAndClear();
nNextCh = GetNextChar();
} while( '>' != nNextCh && '/' != nNextCh && !HTML_ISSPACE( nNextCh ) &&
IsParserWorking() && !rInput.IsEof() );
if( !sTmpBuffer.isEmpty() )
aToken += sTmpBuffer.makeStringAndClear();
// Skip blanks
while( HTML_ISSPACE( nNextCh ) && IsParserWorking() )
nNextCh = GetNextChar();
if( !IsParserWorking() )
{
if( SvParserState::Pending == eState )
bReadNextChar = bReadNextCharSave;
break;
}
// Search token in table:
sSaveToken = aToken;
aToken = aToken.toAsciiLowerCase();
if( 0 == (nRet = GetHTMLToken( aToken )) )
// Unknown control
nRet = HTML_UNKNOWNCONTROL_ON;
// If it's a token which can be switched off...
if( bOffState )
{
if( HTML_TOKEN_ONOFF & nRet )
{
// and there is an off token, return off token instead
++nRet;
}
else if( HTML_LINEBREAK!=nRet )
{
// and there is no off token, return unknown token.
// (except for </BR>, that is treated like <BR>)
nRet = HTML_UNKNOWNCONTROL_OFF;
}
}
if( nRet == HTML_COMMENT )
{
// fix: due to being case sensitive use sSaveToken as start of comment
// and append a blank.
aToken = sSaveToken;
if( '>'!=nNextCh )
aToken += " ";
sal_uLong nCStreamPos = 0;
sal_uLong nCLineNr = 0;
sal_uLong nCLinePos = 0;
sal_Int32 nCStrLen = 0;
bool bDone = false;
// Read until closing -->. If not found restart at first >
while( !bDone && !rInput.IsEof() && IsParserWorking() )
{
if( '>'==nNextCh )
{
if( !nCStreamPos )
{
nCStreamPos = rInput.Tell();
nCStrLen = aToken.getLength();
nCLineNr = GetLineNr();
nCLinePos = GetLinePos();
}
bDone = aToken.endsWith( "--" );
if( !bDone )
aToken += OUString(&nNextCh,1);
}
else
aToken += OUString(&nNextCh,1);
if( !bDone )
nNextCh = GetNextChar();
}
if( !bDone && IsParserWorking() && nCStreamPos )
{
rInput.Seek( nCStreamPos );
SetLineNr( nCLineNr );
SetLinePos( nCLinePos );
ClearTxtConvContext();
aToken = aToken.copy(0, nCStrLen);
nNextCh = '>';
}
}
else
{
// TokenString not needed anymore
aToken.clear();
}
// Read until closing '>'
if( '>' != nNextCh && IsParserWorking() )
{
ScanText( '>' );
// fdo#34666 fdo#36080 fdo#36390: closing "/>"?:
// generate pending HTML_<TOKEN>_OFF for HTML_<TOKEN>_ON
// Do not convert this to a single HTML_<TOKEN>_OFF
// which lead to fdo#56772.
if ((HTML_TOKEN_ONOFF & nRet) && aToken.endsWith("/"))
{
mnPendingOffToken = nRet + 1; // HTML_<TOKEN>_ON -> HTML_<TOKEN>_OFF
aToken = aToken.replaceAt( aToken.getLength()-1, 1, ""); // remove trailing '/'
}
if( sal_Unicode(EOF) == nNextCh && rInput.IsEof() )
{
// Move back in front of < and restart there.
// Return < as text.
rInput.Seek( nStreamPos );
SetLineNr( nLineNr );
SetLinePos( nLinePos );
ClearTxtConvContext();
aToken = "<";
nRet = HTML_TEXTTOKEN;
nNextCh = GetNextChar();
bNextCh = false;
break;
}
}
if( SvParserState::Pending == eState )
bReadNextChar = bReadNextCharSave;
}
else
{
if( bOffState )
{
// einfach alles wegschmeissen
ScanText( '>' );
if( sal_Unicode(EOF) == nNextCh && rInput.IsEof() )
{
// Move back in front of < and restart there.
// Return < as text.
rInput.Seek( nStreamPos );
SetLineNr( nLineNr );
SetLinePos( nLinePos );
ClearTxtConvContext();
aToken = "<";
nRet = HTML_TEXTTOKEN;
nNextCh = GetNextChar();
bNextCh = false;
break;
}
if( SvParserState::Pending == eState )
bReadNextChar = bReadNextCharSave;
aToken.clear();
}
else if( '%' == nNextCh )
{
nRet = HTML_UNKNOWNCONTROL_ON;
sal_uLong nCStreamPos = rInput.Tell();
sal_uLong nCLineNr = GetLineNr(), nCLinePos = GetLinePos();
bool bDone = false;
// Read until closing %>. If not found restart at first >.
while( !bDone && !rInput.IsEof() && IsParserWorking() )
{
bDone = '>'==nNextCh && aToken.endsWith("%");
if( !bDone )
{
aToken += OUString(&nNextCh,1);
nNextCh = GetNextChar();
}
}
if( !bDone && IsParserWorking() )
{
rInput.Seek( nCStreamPos );
SetLineNr( nCLineNr );
SetLinePos( nCLinePos );
ClearTxtConvContext();
aToken = "<%";
nRet = HTML_TEXTTOKEN;
break;
}
if( IsParserWorking() )
{
sSaveToken = aToken;
aToken.clear();
}
}
else
{
aToken = "<";
nRet = HTML_TEXTTOKEN;
bNextCh = false;
break;
}
}
if( IsParserWorking() )
{
bNextCh = '>' == nNextCh;
switch( nRet )
{
case HTML_TEXTAREA_ON:
bReadTextArea = true;
break;
case HTML_TEXTAREA_OFF:
bReadTextArea = false;
break;
case HTML_SCRIPT_ON:
if( !bReadTextArea )
bReadScript = true;
break;
case HTML_SCRIPT_OFF:
if( !bReadTextArea )
{
bReadScript = false;
// JavaScript might modify the stream,
// thus the last character has to be read again.
bReadNextChar = true;
bNextCh = false;
}
break;
case HTML_STYLE_ON:
bReadStyle = true;
break;
case HTML_STYLE_OFF:
bReadStyle = false;
break;
}
}
}
break;
case sal_Unicode(EOF):
if( rInput.IsEof() )
{
eState = SvParserState::Accepted;
nRet = nNextCh;
}
else
{
// Read normal text.
goto scan_text;
}
break;
case '\f':
// form feeds are passed upwards separately
nRet = HTML_LINEFEEDCHAR; // !!! should be FORMFEEDCHAR
break;
case '\n':
case '\r':
if( bReadListing || bReadXMP || bReadPRE || bReadTextArea )
{
sal_Unicode c = GetNextChar();
if( ( '\n' != nNextCh || '\r' != c ) &&
( '\r' != nNextCh || '\n' != c ) )
{
bNextCh = false;
nNextCh = c;
}
nRet = HTML_NEWPARA;
break;
}
SAL_FALLTHROUGH;
case '\t':
if( bReadPRE )
{
nRet = HTML_TABCHAR;
break;
}
SAL_FALLTHROUGH;
case ' ':
SAL_FALLTHROUGH;
default:
scan_text:
// "normal" text to come
nRet = ScanText();
bNextCh = 0 == aToken.getLength();
// the text should be processed
if( !bNextCh && eState == SvParserState::Pending )
{
eState = SvParserState::Working;
bReadNextChar = true;
}
break;
}
if( bNextCh && SvParserState::Working == eState )
{
nNextCh = GetNextChar();
if( SvParserState::Pending == eState && nRet && HTML_TEXTTOKEN != nRet )
{
bReadNextChar = true;
eState = SvParserState::Working;
}
}
} while( !nRet && SvParserState::Working == eState );
if( SvParserState::Pending == eState )
nRet = -1; // s.th. invalid
return nRet;
}
void HTMLParser::UnescapeToken()
{
sal_Int32 nPos=0;
bool bEscape = false;
while( nPos < aToken.getLength() )
{
bool bOldEscape = bEscape;
bEscape = false;
if( '\\'==aToken[nPos] && !bOldEscape )
{
aToken = aToken.replaceAt( nPos, 1, "" );
bEscape = true;
}
else
{
nPos++;
}
}
}
const HTMLOptions& HTMLParser::GetOptions( sal_uInt16 *pNoConvertToken )
{
// If the options for the current token have already been returned,
// return them once again.
if (!maOptions.empty())
return maOptions;
sal_Int32 nPos = 0;
while( nPos < aToken.getLength() )
{
// A letter? Option beginning here.
if( HTML_ISALPHA( aToken[nPos] ) )
{
int nToken;
OUString aValue;
sal_Int32 nStt = nPos;
sal_Unicode cChar = 0;
// Actually only certain characters allowed.
// Netscape only looks for "=" and white space (c.f.
// Mozilla: PA_FetchRequestedNameValues in libparse/pa_mdl.c)
while( nPos < aToken.getLength() && '=' != (cChar=aToken[nPos]) &&
HTML_ISPRINTABLE(cChar) && !HTML_ISSPACE(cChar) )
nPos++;
OUString sName( aToken.copy( nStt, nPos-nStt ) );
// PlugIns require original token name. Convert to lower case only for searching.
nToken = GetHTMLOption( sName.toAsciiLowerCase() ); // Name is ready
SAL_WARN_IF( nToken==HTML_O_UNKNOWN, "svtools",
"GetOption: unknown HTML option '" << sName << "'" );
bool bStripCRLF = (nToken < HTML_OPTION_SCRIPT_START ||
nToken >= HTML_OPTION_SCRIPT_END) &&
(!pNoConvertToken || nToken != *pNoConvertToken);
while( nPos < aToken.getLength() &&
( !HTML_ISPRINTABLE( (cChar=aToken[nPos]) ) ||
HTML_ISSPACE(cChar) ) )
nPos++;
// Option with value?
if( nPos!=aToken.getLength() && '='==cChar )
{
nPos++;
while( nPos < aToken.getLength() &&
( !HTML_ISPRINTABLE( (cChar=aToken[nPos]) ) ||
' '==cChar || '\t'==cChar || '\r'==cChar || '\n'==cChar ) )
nPos++;
if( nPos != aToken.getLength() )
{
sal_Int32 nLen = 0;
nStt = nPos;
if( ('"'==cChar) || ('\'')==cChar )
{
sal_Unicode cEnd = cChar;
nPos++; nStt++;
bool bDone = false;
bool bEscape = false;
while( nPos < aToken.getLength() && !bDone )
{
bool bOldEscape = bEscape;
bEscape = false;
cChar = aToken[nPos];
switch( cChar )
{
case '\r':
case '\n':
if( bStripCRLF )
aToken = aToken.replaceAt( nPos, 1, "" );
else
{
nPos++;
nLen++;
}
break;
case '\\':
if( bOldEscape )
{
nPos++;
nLen++;
}
else
{
aToken = aToken.replaceAt( nPos, 1, "" );
bEscape = true;
}
break;
case '"':
case '\'':
bDone = !bOldEscape && cChar==cEnd;
if( !bDone )
{
nPos++;
nLen++;
}
break;
default:
nPos++;
nLen++;
break;
}
}
if( nPos!=aToken.getLength() )
nPos++;
}
else
{
// More liberal than the standard: allow all printable characters
bool bEscape = false;
bool bDone = false;
while( nPos < aToken.getLength() && !bDone )
{
bool bOldEscape = bEscape;
bEscape = false;
sal_Unicode c = aToken[nPos];
switch( c )
{
case ' ':
bDone = !bOldEscape;
if( !bDone )
{
nPos++;
nLen++;
}
break;
case '\t':
case '\r':
case '\n':
bDone = true;
break;
case '\\':
if( bOldEscape )
{
nPos++;
nLen++;
}
else
{
aToken = aToken.replaceAt( nPos, 1, "" );
bEscape = true;
}
break;
default:
if( HTML_ISPRINTABLE( c ) )
{
nPos++;
nLen++;
}
else
bDone = true;
break;
}
}
}
if( nLen )
aValue = aToken.copy( nStt, nLen );
}
}
// Token is known and can be saved
maOptions.push_back(
HTMLOption(sal::static_int_cast<sal_uInt16>(nToken), sName, aValue));
}
else
// Ignore white space and unexpected characters
nPos++;
}
return maOptions;
}
int HTMLParser::FilterPRE( int nToken )
{
switch( nToken )
{
// in Netscape they only have impact in not empty paragraphs
case HTML_PARABREAK_ON:
nToken = HTML_LINEBREAK;
SAL_FALLTHROUGH;
case HTML_LINEBREAK:
case HTML_NEWPARA:
nPre_LinePos = 0;
if( bPre_IgnoreNewPara )
nToken = 0;
break;
case HTML_TABCHAR:
{
sal_Int32 nSpaces = (8 - (nPre_LinePos % 8));
DBG_ASSERT( aToken.isEmpty(), "Why is the token not empty?" );
if (aToken.getLength() < nSpaces)
{
using comphelper::string::padToLength;
OUStringBuffer aBuf(aToken);
aToken = padToLength(aBuf, nSpaces, ' ').makeStringAndClear();
}
nPre_LinePos += nSpaces;
nToken = HTML_TEXTTOKEN;
}
break;
// Keep those
case HTML_TEXTTOKEN:
nPre_LinePos += aToken.getLength();
break;
case HTML_SELECT_ON:
case HTML_SELECT_OFF:
case HTML_BODY_ON:
case HTML_FORM_ON:
case HTML_FORM_OFF:
case HTML_INPUT:
case HTML_OPTION:
case HTML_TEXTAREA_ON:
case HTML_TEXTAREA_OFF:
case HTML_IMAGE:
case HTML_APPLET_ON:
case HTML_APPLET_OFF:
case HTML_PARAM:
case HTML_EMBED:
case HTML_HEAD1_ON:
case HTML_HEAD1_OFF:
case HTML_HEAD2_ON:
case HTML_HEAD2_OFF:
case HTML_HEAD3_ON:
case HTML_HEAD3_OFF:
case HTML_HEAD4_ON:
case HTML_HEAD4_OFF:
case HTML_HEAD5_ON:
case HTML_HEAD5_OFF:
case HTML_HEAD6_ON:
case HTML_HEAD6_OFF:
case HTML_BLOCKQUOTE_ON:
case HTML_BLOCKQUOTE_OFF:
case HTML_ADDRESS_ON:
case HTML_ADDRESS_OFF:
case HTML_HORZRULE:
case HTML_CENTER_ON:
case HTML_CENTER_OFF:
case HTML_DIVISION_ON:
case HTML_DIVISION_OFF:
case HTML_SCRIPT_ON:
case HTML_SCRIPT_OFF:
case HTML_RAWDATA:
case HTML_TABLE_ON:
case HTML_TABLE_OFF:
case HTML_CAPTION_ON:
case HTML_CAPTION_OFF:
case HTML_COLGROUP_ON:
case HTML_COLGROUP_OFF:
case HTML_COL_ON:
case HTML_COL_OFF:
case HTML_THEAD_ON:
case HTML_THEAD_OFF:
case HTML_TFOOT_ON:
case HTML_TFOOT_OFF:
case HTML_TBODY_ON:
case HTML_TBODY_OFF:
case HTML_TABLEROW_ON:
case HTML_TABLEROW_OFF:
case HTML_TABLEDATA_ON:
case HTML_TABLEDATA_OFF:
case HTML_TABLEHEADER_ON:
case HTML_TABLEHEADER_OFF:
case HTML_ANCHOR_ON:
case HTML_ANCHOR_OFF:
case HTML_BOLD_ON:
case HTML_BOLD_OFF:
case HTML_ITALIC_ON:
case HTML_ITALIC_OFF:
case HTML_STRIKE_ON:
case HTML_STRIKE_OFF:
case HTML_STRIKETHROUGH_ON:
case HTML_STRIKETHROUGH_OFF:
case HTML_UNDERLINE_ON:
case HTML_UNDERLINE_OFF:
case HTML_BASEFONT_ON:
case HTML_BASEFONT_OFF:
case HTML_FONT_ON:
case HTML_FONT_OFF:
case HTML_BLINK_ON:
case HTML_BLINK_OFF:
case HTML_SPAN_ON:
case HTML_SPAN_OFF:
case HTML_SUBSCRIPT_ON:
case HTML_SUBSCRIPT_OFF:
case HTML_SUPERSCRIPT_ON:
case HTML_SUPERSCRIPT_OFF:
case HTML_BIGPRINT_ON:
case HTML_BIGPRINT_OFF:
case HTML_SMALLPRINT_OFF:
case HTML_SMALLPRINT_ON:
case HTML_EMPHASIS_ON:
case HTML_EMPHASIS_OFF:
case HTML_CITIATION_ON:
case HTML_CITIATION_OFF:
case HTML_STRONG_ON:
case HTML_STRONG_OFF:
case HTML_CODE_ON:
case HTML_CODE_OFF:
case HTML_SAMPLE_ON:
case HTML_SAMPLE_OFF:
case HTML_KEYBOARD_ON:
case HTML_KEYBOARD_OFF:
case HTML_VARIABLE_ON:
case HTML_VARIABLE_OFF:
case HTML_DEFINSTANCE_ON:
case HTML_DEFINSTANCE_OFF:
case HTML_SHORTQUOTE_ON:
case HTML_SHORTQUOTE_OFF:
case HTML_LANGUAGE_ON:
case HTML_LANGUAGE_OFF:
case HTML_AUTHOR_ON:
case HTML_AUTHOR_OFF:
case HTML_PERSON_ON:
case HTML_PERSON_OFF:
case HTML_ACRONYM_ON:
case HTML_ACRONYM_OFF:
case HTML_ABBREVIATION_ON:
case HTML_ABBREVIATION_OFF:
case HTML_INSERTEDTEXT_ON:
case HTML_INSERTEDTEXT_OFF:
case HTML_DELETEDTEXT_ON:
case HTML_DELETEDTEXT_OFF:
case HTML_TELETYPE_ON:
case HTML_TELETYPE_OFF:
break;
// The remainder is treated as an unknown token.
default:
if( nToken )
{
nToken =
( ((HTML_TOKEN_ONOFF & nToken) && (1 & nToken))
? HTML_UNKNOWNCONTROL_OFF
: HTML_UNKNOWNCONTROL_ON );
}
break;
}
bPre_IgnoreNewPara = false;
return nToken;
}
int HTMLParser::FilterXMP( int nToken )
{
switch( nToken )
{
case HTML_NEWPARA:
if( bPre_IgnoreNewPara )
nToken = 0;
SAL_FALLTHROUGH;
case HTML_TEXTTOKEN:
case HTML_NONBREAKSPACE:
case HTML_SOFTHYPH:
break; // kept
default:
if( nToken )
{
if( (HTML_TOKEN_ONOFF & nToken) && (1 & nToken) )
{
sSaveToken = "</" + sSaveToken;
}
else
sSaveToken = "<" + sSaveToken;
if( !aToken.isEmpty() )
{
UnescapeToken();
sSaveToken += " ";
aToken = sSaveToken + aToken;
}
else
aToken = sSaveToken;
aToken += ">";
nToken = HTML_TEXTTOKEN;
}
break;
}
bPre_IgnoreNewPara = false;
return nToken;
}
int HTMLParser::FilterListing( int nToken )
{
switch( nToken )
{
case HTML_NEWPARA:
if( bPre_IgnoreNewPara )
nToken = 0;
SAL_FALLTHROUGH;
case HTML_TEXTTOKEN:
case HTML_NONBREAKSPACE:
case HTML_SOFTHYPH:
break; // kept
default:
if( nToken )
{
nToken =
( ((HTML_TOKEN_ONOFF & nToken) && (1 & nToken))
? HTML_UNKNOWNCONTROL_OFF
: HTML_UNKNOWNCONTROL_ON );
}
break;
}
bPre_IgnoreNewPara = false;
return nToken;
}
bool HTMLParser::InternalImgToPrivateURL( OUString& rURL )
{
bool bFound = false;
if( rURL.startsWith( OOO_STRING_SVTOOLS_HTML_internal_icon ) )
{
OUString aName( rURL.copy(14) );
switch( aName[0] )
{
case 'b':
bFound = aName == OOO_STRING_SVTOOLS_HTML_INT_ICON_baddata;
break;
case 'd':
bFound = aName == OOO_STRING_SVTOOLS_HTML_INT_ICON_delayed;
break;
case 'e':
bFound = aName == OOO_STRING_SVTOOLS_HTML_INT_ICON_embed;
break;
case 'i':
bFound = aName == OOO_STRING_SVTOOLS_HTML_INT_ICON_insecure;
break;
case 'n':
bFound = aName == OOO_STRING_SVTOOLS_HTML_INT_ICON_notfound;
break;
}
}
if( bFound )
{
OUString sTmp ( rURL );
rURL = OOO_STRING_SVTOOLS_HTML_private_image;
rURL += sTmp;
}
return bFound;
}
enum class HtmlMeta {
NONE = 0,
Author,
Description,
Keywords,
Refresh,
Classification,
Created,
ChangedBy,
Changed,
Generator,
SDFootnote,
SDEndnote,
ContentType
};
// <META NAME=xxx>
static HTMLOptionEnum<HtmlMeta> const aHTMLMetaNameTable[] =
{
{ OOO_STRING_SVTOOLS_HTML_META_author, HtmlMeta::Author },
{ OOO_STRING_SVTOOLS_HTML_META_changed, HtmlMeta::Changed },
{ OOO_STRING_SVTOOLS_HTML_META_changedby, HtmlMeta::ChangedBy },
{ OOO_STRING_SVTOOLS_HTML_META_classification,HtmlMeta::Classification},
{ OOO_STRING_SVTOOLS_HTML_META_content_type, HtmlMeta::ContentType },
{ OOO_STRING_SVTOOLS_HTML_META_created, HtmlMeta::Created },
{ OOO_STRING_SVTOOLS_HTML_META_description, HtmlMeta::Description },
{ OOO_STRING_SVTOOLS_HTML_META_keywords, HtmlMeta::Keywords },
{ OOO_STRING_SVTOOLS_HTML_META_generator, HtmlMeta::Generator },
{ OOO_STRING_SVTOOLS_HTML_META_refresh, HtmlMeta::Refresh },
{ OOO_STRING_SVTOOLS_HTML_META_sdendnote, HtmlMeta::SDEndnote },
{ OOO_STRING_SVTOOLS_HTML_META_sdfootnote, HtmlMeta::SDFootnote },
{ nullptr, (HtmlMeta)0 }
};
void HTMLParser::AddMetaUserDefined( OUString const & )
{
}
bool HTMLParser::ParseMetaOptionsImpl(
const uno::Reference<document::XDocumentProperties> & i_xDocProps,
SvKeyValueIterator *i_pHTTPHeader,
const HTMLOptions& aOptions,
rtl_TextEncoding& o_rEnc )
{
OUString aName, aContent;
HtmlMeta nAction = HtmlMeta::NONE;
bool bHTTPEquiv = false, bChanged = false;
for ( size_t i = aOptions.size(); i; )
{
const HTMLOption& aOption = aOptions[--i];
switch ( aOption.GetToken() )
{
case HTML_O_NAME:
aName = aOption.GetString();
if ( HtmlMeta::NONE==nAction )
{
aOption.GetEnum( nAction, aHTMLMetaNameTable );
}
break;
case HTML_O_HTTPEQUIV:
aName = aOption.GetString();
aOption.GetEnum( nAction, aHTMLMetaNameTable );
bHTTPEquiv = true;
break;
case HTML_O_CONTENT:
aContent = aOption.GetString();
break;
case HTML_O_CHARSET:
OString sValue(OUStringToOString(aOption.GetString(), RTL_TEXTENCODING_ASCII_US));
o_rEnc = GetExtendedCompatibilityTextEncoding(rtl_getTextEncodingFromMimeCharset(sValue.getStr()));
break;
}
}
if ( bHTTPEquiv || HtmlMeta::Description != nAction )
{
// if it is not a Description, remove CRs and LFs from CONTENT
aContent = aContent.replaceAll("\r", "").replaceAll("\n", "");
}
else
{
// convert line endings for Description
aContent = convertLineEnd(aContent, GetSystemLineEnd());
}
if ( bHTTPEquiv && i_pHTTPHeader )
{
// Netscape seems to just ignore a closing ", so we do too
if ( aContent.endsWith("\"") )
{
aContent = aContent.copy( 0, aContent.getLength() - 1 );
}
SvKeyValue aKeyValue( aName, aContent );
i_pHTTPHeader->Append( aKeyValue );
}
switch ( nAction )
{
case HtmlMeta::Author:
if (i_xDocProps.is()) {
i_xDocProps->setAuthor( aContent );
bChanged = true;
}
break;
case HtmlMeta::Description:
if (i_xDocProps.is()) {
i_xDocProps->setDescription( aContent );
bChanged = true;
}
break;
case HtmlMeta::Keywords:
if (i_xDocProps.is()) {
i_xDocProps->setKeywords(
::comphelper::string::convertCommaSeparated(aContent));
bChanged = true;
}
break;
case HtmlMeta::Classification:
if (i_xDocProps.is()) {
i_xDocProps->setSubject( aContent );
bChanged = true;
}
break;
case HtmlMeta::ChangedBy:
if (i_xDocProps.is()) {
i_xDocProps->setModifiedBy( aContent );
}
break;
case HtmlMeta::Created:
case HtmlMeta::Changed:
if ( i_xDocProps.is() && !aContent.isEmpty() &&
comphelper::string::getTokenCount(aContent, ';') == 2 )
{
Date aDate( (sal_uLong)aContent.getToken(0, ';').toInt32() );
tools::Time aTime( (sal_uLong)aContent.getToken(1, ';').toInt32() );
DateTime aDateTime( aDate, aTime );
::util::DateTime uDT = aDateTime.GetUNODateTime();
if ( HtmlMeta::Created==nAction )
i_xDocProps->setCreationDate( uDT );
else
i_xDocProps->setModificationDate( uDT );
bChanged = true;
}
break;
case HtmlMeta::Refresh:
DBG_ASSERT( !bHTTPEquiv || i_pHTTPHeader,
"Reload-URL aufgrund unterlassener MUSS-Aenderung verlorengegangen" );
break;
case HtmlMeta::ContentType:
if ( !aContent.isEmpty() )
{
o_rEnc = GetEncodingByMIME( aContent );
}
break;
case HtmlMeta::NONE:
if ( !bHTTPEquiv )
{
if (i_xDocProps.is())
{
uno::Reference<beans::XPropertyContainer> xUDProps
= i_xDocProps->getUserDefinedProperties();
try {
xUDProps->addProperty(aName,
beans::PropertyAttribute::REMOVABLE,
uno::makeAny(OUString(aContent)));
AddMetaUserDefined(aName);
bChanged = true;
} catch (uno::Exception &) {
// ignore
}
}
}
break;
default:
break;
}
return bChanged;
}
bool HTMLParser::ParseMetaOptions(
const uno::Reference<document::XDocumentProperties> & i_xDocProps,
SvKeyValueIterator *i_pHeader )
{
sal_uInt16 nContentOption = HTML_O_CONTENT;
rtl_TextEncoding eEnc = RTL_TEXTENCODING_DONTKNOW;
bool bRet = ParseMetaOptionsImpl( i_xDocProps, i_pHeader,
GetOptions(&nContentOption),
eEnc );
// If the encoding is set by a META tag, it may only overwrite the
// current encoding if both, the current and the new encoding, are 1-sal_uInt8
// encodings. Everything else cannot lead to reasonable results.
if (RTL_TEXTENCODING_DONTKNOW != eEnc &&
rtl_isOctetTextEncoding( eEnc ) &&
rtl_isOctetTextEncoding( GetSrcEncoding() ) )
{
eEnc = GetExtendedCompatibilityTextEncoding( eEnc );
SetSrcEncoding( eEnc );
}
return bRet;
}
rtl_TextEncoding HTMLParser::GetEncodingByMIME( const OUString& rMime )
{
OUString sType;
OUString sSubType;
INetContentTypeParameterList aParameters;
if (INetContentTypes::parse(rMime, sType, sSubType, &aParameters))
{
auto const iter = aParameters.find("charset");
if (iter != aParameters.end())
{
const INetContentTypeParameter * pCharset = &iter->second;
OString sValue(OUStringToOString(pCharset->m_sValue, RTL_TEXTENCODING_ASCII_US));
return GetExtendedCompatibilityTextEncoding( rtl_getTextEncodingFromMimeCharset( sValue.getStr() ) );
}
}
return RTL_TEXTENCODING_DONTKNOW;
}
rtl_TextEncoding HTMLParser::GetEncodingByHttpHeader( SvKeyValueIterator *pHTTPHeader )
{
rtl_TextEncoding eRet = RTL_TEXTENCODING_DONTKNOW;
if( pHTTPHeader )
{
SvKeyValue aKV;
for( bool bCont = pHTTPHeader->GetFirst( aKV ); bCont;
bCont = pHTTPHeader->GetNext( aKV ) )
{
if( aKV.GetKey().equalsIgnoreAsciiCase( OOO_STRING_SVTOOLS_HTML_META_content_type ) )
{
if( !aKV.GetValue().isEmpty() )
{
eRet = HTMLParser::GetEncodingByMIME( aKV.GetValue() );
}
}
}
}
return eRet;
}
bool HTMLParser::SetEncodingByHTTPHeader( SvKeyValueIterator *pHTTPHeader )
{
bool bRet = false;
rtl_TextEncoding eEnc = HTMLParser::GetEncodingByHttpHeader( pHTTPHeader );
if(RTL_TEXTENCODING_DONTKNOW != eEnc)
{
SetSrcEncoding( eEnc );
bRet = true;
}
return bRet;
}
/* vim:set shiftwidth=4 softtabstop=4 expandtab: */
|