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
|
/* -*- 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 <o3tl/string_view.hxx>
#include <osl/diagnose.h>
#include <rtl/character.hxx>
#include <rtl/ustrbuf.hxx>
#include <tools/color.hxx>
#include <tools/solar.h>
#include <svtools/htmltokn.h>
#include <comphelper/string.hxx>
#include "parcss1.hxx"
// Loop-Check: Used to avoid infinite loops, is checked after every
// loop, if there is progress of the input position
#define LOOP_CHECK
#ifdef LOOP_CHECK
#define LOOP_CHECK_DECL \
sal_Int32 nOldInPos = SAL_MAX_INT32;
#define LOOP_CHECK_RESTART \
nOldInPos = SAL_MAX_INT32;
#define LOOP_CHECK_CHECK( where ) \
OSL_ENSURE( nOldInPos!=m_nInPos || m_cNextCh==sal_Unicode(EOF), where ); \
if( nOldInPos==m_nInPos && m_cNextCh!=sal_Unicode(EOF) ) \
break; \
else \
nOldInPos = m_nInPos;
#else
#define LOOP_CHECK_DECL
#define LOOP_CHECK_RESTART
#define LOOP_CHECK_CHECK( where )
#endif
const sal_Int32 MAX_LEN = 1024;
void CSS1Parser::InitRead( const OUString& rIn )
{
m_nlLineNr = 0;
m_nlLinePos = 0;
m_bWhiteSpace = true; // if nothing was read it's like there was WS
m_bEOF = false;
m_eState = CSS1_PAR_WORKING;
m_nValue = 0.;
m_aIn = rIn;
m_nInPos = 0;
m_cNextCh = GetNextChar();
m_nToken = GetNextToken();
}
sal_Unicode CSS1Parser::GetNextChar()
{
if( m_nInPos >= m_aIn.getLength() )
{
m_bEOF = true;
return sal_Unicode(EOF);
}
sal_Unicode c = m_aIn[m_nInPos];
m_nInPos++;
if( c == '\n' )
{
++m_nlLineNr;
m_nlLinePos = 1;
}
else
++m_nlLinePos;
return c;
}
// This function implements the scanner described in
// http://www.w3.org/pub/WWW/TR/WD-css1.html
// resp. http://www.w3.org/pub/WWW/TR/WD-css1-960220.html
// for CSS1. It's a direct implementation of the
// described Lex grammar.
CSS1Token CSS1Parser::GetNextToken()
{
CSS1Token nRet = CSS1_NULL;
m_aToken.clear();
do {
// remember if white space was read
bool bPrevWhiteSpace = m_bWhiteSpace;
m_bWhiteSpace = false;
bool bNextCh = true;
switch( m_cNextCh )
{
case '/': // COMMENT | '/'
{
m_cNextCh = GetNextChar();
if( '*' == m_cNextCh )
{
// COMMENT
m_cNextCh = GetNextChar();
bool bAsterisk = false;
while( !(bAsterisk && '/'==m_cNextCh) && !IsEOF() )
{
bAsterisk = ('*'==m_cNextCh);
m_cNextCh = GetNextChar();
}
}
else
{
// '/'
bNextCh = false;
nRet = CSS1_SLASH;
}
}
break;
case '@': // '@import' | '@XXX'
{
m_cNextCh = GetNextChar();
if (rtl::isAsciiAlpha(m_cNextCh))
{
// scan the next identifier
OUStringBuffer sTmpBuffer(32);
do {
sTmpBuffer.append( m_cNextCh );
m_cNextCh = GetNextChar();
} while( (rtl::isAsciiAlphanumeric(m_cNextCh) ||
'-' == m_cNextCh) && !IsEOF() );
m_aToken += sTmpBuffer;
// check if we know it
switch( m_aToken[0] )
{
case 'i':
case 'I':
if( m_aToken.equalsIgnoreAsciiCase( "import" ) )
nRet = CSS1_IMPORT_SYM;
break;
case 'p':
case 'P':
if( m_aToken.equalsIgnoreAsciiCase( "page" ) )
nRet = CSS1_PAGE_SYM;
break;
}
// error handling: ignore '@indent' and the rest until
// semicolon at end of the next block
if( CSS1_NULL==nRet )
{
m_aToken.clear();
int nBlockLvl = 0;
sal_Unicode cQuoteCh = 0;
bool bDone = false, bEscape = false;
while( !bDone && !IsEOF() )
{
bool bOldEscape = bEscape;
bEscape = false;
switch( m_cNextCh )
{
case '{':
if( !cQuoteCh && !bOldEscape )
nBlockLvl++;
break;
case ';':
if( !cQuoteCh && !bOldEscape )
bDone = nBlockLvl==0;
break;
case '}':
if( !cQuoteCh && !bOldEscape )
bDone = --nBlockLvl==0;
break;
case '\"':
case '\'':
if( !bOldEscape )
{
if( cQuoteCh )
{
if( cQuoteCh == m_cNextCh )
cQuoteCh = 0;
}
else
{
cQuoteCh = m_cNextCh;
}
}
break;
case '\\':
if( !bOldEscape )
bEscape = true;
break;
}
m_cNextCh = GetNextChar();
}
}
bNextCh = false;
}
}
break;
case '!': // '!' 'legal' | '!' 'important' | syntax error
{
// ignore white space
m_cNextCh = GetNextChar();
while( ( ' ' == m_cNextCh ||
(m_cNextCh >= 0x09 && m_cNextCh <= 0x0d) ) && !IsEOF() )
{
m_bWhiteSpace = true;
m_cNextCh = GetNextChar();
}
if( 'i'==m_cNextCh || 'I'==m_cNextCh)
{
// scan next identifier
OUStringBuffer sTmpBuffer(32);
do {
sTmpBuffer.append( m_cNextCh );
m_cNextCh = GetNextChar();
} while( (rtl::isAsciiAlphanumeric(m_cNextCh) ||
'-' == m_cNextCh) && !IsEOF() );
m_aToken += sTmpBuffer;
if( ( 'i'==m_aToken[0] || 'I'==m_aToken[0] ) &&
m_aToken.equalsIgnoreAsciiCase( "important" ) )
{
// '!' 'important'
nRet = CSS1_IMPORTANT_SYM;
}
else
{
// error handling: ignore '!', not IDENT
nRet = CSS1_IDENT;
}
m_bWhiteSpace = false;
bNextCh = false;
}
else
{
// error handling: ignore '!'
bNextCh = false;
}
}
break;
case '\"':
case '\'': // STRING
{
// \... isn't possible yet!!!
sal_Unicode cQuoteChar = m_cNextCh;
m_cNextCh = GetNextChar();
OUStringBuffer sTmpBuffer( MAX_LEN );
do {
sTmpBuffer.append( m_cNextCh );
m_cNextCh = GetNextChar();
} while( cQuoteChar != m_cNextCh && !IsEOF() );
m_aToken += sTmpBuffer;
nRet = CSS1_STRING;
}
break;
case '0':
case '1':
case '2':
case '3':
case '4':
case '5':
case '6':
case '7':
case '8':
case '9': // NUMBER | PERCENTAGE | LENGTH
{
// save current position
std::size_t nInPosSave = m_nInPos;
sal_Unicode cNextChSave = m_cNextCh;
sal_uInt32 nlLineNrSave = m_nlLineNr;
sal_uInt32 nlLinePosSave = m_nlLinePos;
bool bEOFSave = m_bEOF;
// first try to parse a hex digit
OUStringBuffer sTmpBuffer( 16 );
do {
sTmpBuffer.append( m_cNextCh );
m_cNextCh = GetNextChar();
} while( sTmpBuffer.getLength() < 7 &&
( ('0'<=m_cNextCh && '9'>=m_cNextCh) ||
('A'<=m_cNextCh && 'F'>=m_cNextCh) ||
('a'<=m_cNextCh && 'f'>=m_cNextCh) ) &&
!IsEOF() );
if( sTmpBuffer.getLength()==6 )
{
// we found a color in hex
m_aToken += sTmpBuffer;
nRet = CSS1_HEXCOLOR;
bNextCh = false;
break;
}
// otherwise we try a number
m_nInPos = nInPosSave;
m_cNextCh = cNextChSave;
m_nlLineNr = nlLineNrSave;
m_nlLinePos = nlLinePosSave;
m_bEOF = bEOFSave;
// first parse the number
sTmpBuffer.setLength( 0 );
do {
sTmpBuffer.append( m_cNextCh );
m_cNextCh = GetNextChar();
} while( (('0'<=m_cNextCh && '9'>=m_cNextCh) || '.'==m_cNextCh) &&
!IsEOF() );
m_aToken += sTmpBuffer;
m_nValue = m_aToken.toDouble();
// ignore white space
while( ( ' ' == m_cNextCh ||
(m_cNextCh >= 0x09 && m_cNextCh <= 0x0d) ) && !IsEOF() )
{
m_bWhiteSpace = true;
m_cNextCh = GetNextChar();
}
// check now, of there is a unit
switch( m_cNextCh )
{
case '%': // PERCENTAGE
m_bWhiteSpace = false;
nRet = CSS1_PERCENTAGE;
break;
case 'c':
case 'C': // LENGTH cm | LENGTH IDENT
case 'e':
case 'E': // LENGTH (em | ex) | LENGTH IDENT
case 'i':
case 'I': // LENGTH inch | LENGTH IDENT
case 'p':
case 'P': // LENGTH (pt | px | pc) | LENGTH IDENT
case 'm':
case 'M': // LENGTH mm | LENGTH IDENT
{
// save current position
sal_Int32 nInPosOld = m_nInPos;
sal_Unicode cNextChOld = m_cNextCh;
sal_uInt32 nlLineNrOld = m_nlLineNr;
sal_uInt32 nlLinePosOld = m_nlLinePos;
bool bEOFOld = m_bEOF;
// parse the next identifier
OUString aIdent;
OUStringBuffer sTmpBuffer2(64);
do {
sTmpBuffer2.append( m_cNextCh );
m_cNextCh = GetNextChar();
} while( (rtl::isAsciiAlphanumeric(m_cNextCh) ||
'-' == m_cNextCh) && !IsEOF() );
aIdent += sTmpBuffer2;
// Is it a unit?
const char *pCmp1 = nullptr, *pCmp2 = nullptr, *pCmp3 = nullptr;
double nScale1 = 1., nScale2 = 1.;
CSS1Token nToken1 = CSS1_LENGTH,
nToken2 = CSS1_LENGTH,
nToken3 = CSS1_LENGTH;
switch( aIdent[0] )
{
case 'c':
case 'C':
pCmp1 = "cm";
nScale1 = (72.*20.)/2.54; // twip
break;
case 'e':
case 'E':
pCmp1 = "em";
nToken1 = CSS1_EMS;
pCmp2 = "ex";
nToken2 = CSS1_EMX;
break;
case 'i':
case 'I':
pCmp1 = "in";
nScale1 = 72.*20.; // twip
break;
case 'm':
case 'M':
pCmp1 = "mm";
nScale1 = (72.*20.)/25.4; // twip
break;
case 'p':
case 'P':
pCmp1 = "pt";
nScale1 = 20.; // twip
pCmp2 = "pc";
nScale2 = 12.*20.; // twip
pCmp3 = "px";
nToken3 = CSS1_PIXLENGTH;
break;
}
double nScale = 0.0;
OSL_ENSURE( pCmp1, "Where does the first digit come from?" );
if( aIdent.equalsIgnoreAsciiCaseAscii( pCmp1 ) )
{
nScale = nScale1;
nRet = nToken1;
}
else if( pCmp2 &&
aIdent.equalsIgnoreAsciiCaseAscii( pCmp2 ) )
{
nScale = nScale2;
nRet = nToken2;
}
else if( pCmp3 &&
aIdent.equalsIgnoreAsciiCaseAscii( pCmp3 ) )
{
nScale = 1.; // nScale3
nRet = nToken3;
}
else
{
nRet = CSS1_NUMBER;
}
if( CSS1_LENGTH==nRet && nScale!=1.0 )
m_nValue *= nScale;
if( nRet == CSS1_NUMBER )
{
m_nInPos = nInPosOld;
m_cNextCh = cNextChOld;
m_nlLineNr = nlLineNrOld;
m_nlLinePos = nlLinePosOld;
m_bEOF = bEOFOld;
}
else
{
m_bWhiteSpace = false;
}
bNextCh = false;
}
break;
default: // NUMBER IDENT
bNextCh = false;
nRet = CSS1_NUMBER;
break;
}
}
break;
case ':': // ':'
// catch link/visited/active !!!
nRet = CSS1_COLON;
break;
case '.': // DOT_W_WS | DOT_WO_WS
nRet = bPrevWhiteSpace ? CSS1_DOT_W_WS : CSS1_DOT_WO_WS;
break;
case '+': // '+'
nRet = CSS1_PLUS;
break;
case '-': // '-'
nRet = CSS1_MINUS;
break;
case '{': // '{'
nRet = CSS1_OBRACE;
break;
case '}': // '}'
nRet = CSS1_CBRACE;
break;
case ';': // ';'
nRet = CSS1_SEMICOLON;
break;
case ',': // ','
nRet = CSS1_COMMA;
break;
case '#': // '#'
m_cNextCh = GetNextChar();
if( ('0'<=m_cNextCh && '9'>=m_cNextCh) ||
('a'<=m_cNextCh && 'f'>=m_cNextCh) ||
('A'<=m_cNextCh && 'F'>=m_cNextCh) )
{
// save current position
sal_Int32 nInPosSave = m_nInPos;
sal_Unicode cNextChSave = m_cNextCh;
sal_uInt32 nlLineNrSave = m_nlLineNr;
sal_uInt32 nlLinePosSave = m_nlLinePos;
bool bEOFSave = m_bEOF;
// first try to parse a hex digit
OUStringBuffer sTmpBuffer(8);
do {
sTmpBuffer.append( m_cNextCh );
m_cNextCh = GetNextChar();
} while( sTmpBuffer.getLength() < 9 &&
( ('0'<=m_cNextCh && '9'>=m_cNextCh) ||
('A'<=m_cNextCh && 'F'>=m_cNextCh) ||
('a'<=m_cNextCh && 'f'>=m_cNextCh) ) &&
!IsEOF() );
if( sTmpBuffer.getLength()==6 || sTmpBuffer.getLength()==3 )
{
// we found a color in hex (RGB)
m_aToken += sTmpBuffer;
nRet = CSS1_HEXCOLOR;
bNextCh = false;
break;
}
if( sTmpBuffer.getLength()==8 )
{
// we found a color in hex (RGBA)
// we convert it to RGB assuming white background
sal_uInt32 nColor = sTmpBuffer.makeStringAndClear().toUInt32(16);
sal_uInt32 nRed = (nColor & 0xff000000) >> 24;
sal_uInt32 nGreen = (nColor & 0xff0000) >> 16;
sal_uInt32 nBlue = (nColor & 0xff00) >> 8;
double nAlpha = (nColor & 0xff) / 255.0;
nRed = (1 - nAlpha) * 255 + nAlpha * nRed;
nGreen = (1 - nAlpha) * 255 + nAlpha * nGreen;
nBlue = (1 - nAlpha) * 255 + nAlpha * nBlue;
nColor = (nRed << 16) + (nGreen << 8) + nBlue;
m_aToken += OUString::number(nColor, 16);
nRet = CSS1_HEXCOLOR;
bNextCh = false;
break;
}
// otherwise we try a number
m_nInPos = nInPosSave;
m_cNextCh = cNextChSave;
m_nlLineNr = nlLineNrSave;
m_nlLinePos = nlLinePosSave;
m_bEOF = bEOFSave;
}
nRet = CSS1_HASH;
bNextCh = false;
break;
case ' ':
case '\t':
case '\r':
case '\n': // White-Space
m_bWhiteSpace = true;
break;
case sal_Unicode(EOF):
if( IsEOF() )
{
m_eState = CSS1_PAR_ACCEPTED;
bNextCh = false;
break;
}
[[fallthrough]];
default: // IDENT | syntax error
if (rtl::isAsciiAlpha(m_cNextCh))
{
// IDENT
bool bHexColor = true;
// parse the next identifier
OUStringBuffer sTmpBuffer(64);
do {
sTmpBuffer.append( m_cNextCh );
if( bHexColor )
{
bHexColor = sTmpBuffer.getLength()<7 &&
( ('0'<=m_cNextCh && '9'>=m_cNextCh) ||
('A'<=m_cNextCh && 'F'>=m_cNextCh) ||
('a'<=m_cNextCh && 'f'>=m_cNextCh) );
}
m_cNextCh = GetNextChar();
} while( (rtl::isAsciiAlphanumeric(m_cNextCh) ||
'-' == m_cNextCh) && !IsEOF() );
m_aToken += sTmpBuffer;
if( bHexColor && sTmpBuffer.getLength()==6 )
{
bNextCh = false;
nRet = CSS1_HEXCOLOR;
break;
}
if( '('==m_cNextCh &&
( (('u'==m_aToken[0] || 'U'==m_aToken[0]) &&
m_aToken.equalsIgnoreAsciiCase( "url" )) ||
(('r'==m_aToken[0] || 'R'==m_aToken[0]) &&
(m_aToken.equalsIgnoreAsciiCase( "rgb" ) || m_aToken.equalsIgnoreAsciiCase( "rgba" ) )
) ) )
{
int nNestCnt = 0;
OUStringBuffer sTmpBuffer2(64);
do {
sTmpBuffer2.append( m_cNextCh );
switch( m_cNextCh )
{
case '(': nNestCnt++; break;
case ')': nNestCnt--; break;
}
m_cNextCh = GetNextChar();
} while( (nNestCnt>1 || ')'!=m_cNextCh) && !IsEOF() );
sTmpBuffer2.append( m_cNextCh );
m_aToken += sTmpBuffer2;
bNextCh = true;
nRet = 'u'==m_aToken[0] || 'U'==m_aToken[0]
? CSS1_URL
: CSS1_RGB;
}
else
{
bNextCh = false;
nRet = CSS1_IDENT;
}
}
// error handling: ignore digit
break;
}
if( bNextCh )
m_cNextCh = GetNextChar();
} while( CSS1_NULL==nRet && IsParserWorking() );
return nRet;
}
// These functions implement the parser described in
// http://www.w3.org/pub/WWW/TR/WD-css1.html
// resp. http://www.w3.org/pub/WWW/TR/WD-css1-960220.html
// for CSS1. It's a direct implementation of the
// described Lex grammar.
// stylesheet
// : import* rule*
// import
// : IMPORT_SYM url
// url
// : STRING
void CSS1Parser::ParseStyleSheet()
{
LOOP_CHECK_DECL
// import*
bool bDone = false;
while( !bDone && IsParserWorking() )
{
LOOP_CHECK_CHECK( "Infinite loop in ParseStyleSheet()/import *" )
switch( m_nToken )
{
case CSS1_IMPORT_SYM:
// IMPORT_SYM url
// URL are skipped without checks
m_nToken = GetNextToken();
break;
case CSS1_IDENT: // Look-Aheads
case CSS1_DOT_W_WS:
case CSS1_HASH:
case CSS1_PAGE_SYM:
// rule
bDone = true;
break;
default:
// error handling: ignore
break;
}
if( !bDone )
m_nToken = GetNextToken();
}
LOOP_CHECK_RESTART
// rule *
while( IsParserWorking() )
{
LOOP_CHECK_CHECK( "Infinite loop in ParseStyleSheet()/rule *" )
switch( m_nToken )
{
case CSS1_IDENT: // Look-Aheads
case CSS1_DOT_W_WS:
case CSS1_HASH:
case CSS1_PAGE_SYM:
// rule
ParseRule();
break;
default:
// error handling: ignore
m_nToken = GetNextToken();
break;
}
}
}
// rule
// : selector [ ',' selector ]*
// '{' declaration [ ';' declaration ]* '}'
void CSS1Parser::ParseRule()
{
// selector
std::unique_ptr<CSS1Selector> pSelector = ParseSelector();
if( !pSelector )
return;
// process selector
SelectorParsed( std::move(pSelector), true );
LOOP_CHECK_DECL
// [ ',' selector ]*
while( CSS1_COMMA==m_nToken && IsParserWorking() )
{
LOOP_CHECK_CHECK( "Infinite loop in ParseRule()/selector *" )
// ignore ','
m_nToken = GetNextToken();
// selector
pSelector = ParseSelector();
if( !pSelector )
return;
// process selector
SelectorParsed( std::move(pSelector), false );
}
// '{'
if( CSS1_OBRACE != m_nToken )
return;
m_nToken = GetNextToken();
// declaration
OUString aProperty;
std::unique_ptr<CSS1Expression> pExpr = ParseDeclaration( aProperty );
if( !pExpr )
return;
// process expression
DeclarationParsed( aProperty, std::move(pExpr) );
LOOP_CHECK_RESTART
// [ ';' declaration ]*
while( CSS1_SEMICOLON==m_nToken && IsParserWorking() )
{
LOOP_CHECK_CHECK( "Infinite loop in ParseRule()/declaration *" )
// ';'
m_nToken = GetNextToken();
// declaration
if( CSS1_IDENT == m_nToken )
{
std::unique_ptr<CSS1Expression> pExp = ParseDeclaration( aProperty );
if( pExp )
{
// process expression
DeclarationParsed( aProperty, std::move(pExp));
}
}
}
// '}'
if( CSS1_CBRACE == m_nToken )
m_nToken = GetNextToken();
}
// selector
// : simple_selector+ [ ':' pseudo_element ]?
// simple_selector
// : element_name [ DOT_WO_WS class ]?
// | DOT_W_WS class
// | id_selector
// element_name
// : IDENT
// class
// : IDENT
// id_selector
// : '#' IDENT
// pseudo_element
// : IDENT
std::unique_ptr<CSS1Selector> CSS1Parser::ParseSelector()
{
std::unique_ptr<CSS1Selector> pRoot;
CSS1Selector *pLast = nullptr;
bool bDone = false;
CSS1Selector *pNew = nullptr;
LOOP_CHECK_DECL
// simple_selector+
while( !bDone && IsParserWorking() )
{
LOOP_CHECK_CHECK( "Infinite loop in ParseSelector()" )
bool bNextToken = true;
switch( m_nToken )
{
case CSS1_IDENT:
{
// element_name [ DOT_WO_WS class ]?
// element_name
OUString aElement = m_aToken;
CSS1SelectorType eType = CSS1_SELTYPE_ELEMENT;
m_nToken = GetNextToken();
if( CSS1_DOT_WO_WS == m_nToken )
{
// DOT_WO_WS
m_nToken = GetNextToken();
// class
if( CSS1_IDENT == m_nToken )
{
aElement += "." + m_aToken;
eType = CSS1_SELTYPE_ELEM_CLASS;
}
else
{
// missing class
return pRoot;
}
}
else
{
// that was a look-ahead
bNextToken = false;
}
pNew = new CSS1Selector( eType, aElement );
}
break;
case CSS1_DOT_W_WS:
// DOT_W_WS class
// DOT_W_WS
m_nToken = GetNextToken();
if( CSS1_IDENT==m_nToken )
{
// class
pNew = new CSS1Selector( CSS1_SELTYPE_CLASS, m_aToken );
}
else
{
// missing class
return pRoot;
}
break;
case CSS1_HASH:
// '#' id_selector
// '#'
m_nToken = GetNextToken();
if( CSS1_IDENT==m_nToken )
{
// id_selector
pNew = new CSS1Selector( CSS1_SELTYPE_ID, m_aToken );
}
else
{
// missing id_selector
return pRoot;
}
break;
case CSS1_PAGE_SYM:
{
// @page
pNew = new CSS1Selector( CSS1_SELTYPE_PAGE, m_aToken );
}
break;
default:
// stop because we don't know what's next
bDone = true;
break;
}
// if created a new selector then save it
if( pNew )
{
OSL_ENSURE( (pRoot!=nullptr) == (pLast!=nullptr),
"Root-Selector, but no Last" );
if( pLast )
pLast->SetNext( pNew );
else
pRoot.reset(pNew);
pLast = pNew;
pNew = nullptr;
}
if( bNextToken && !bDone )
m_nToken = GetNextToken();
}
if( !pRoot )
{
// missing simple_selector
return pRoot;
}
// [ ':' pseudo_element ]?
if( CSS1_COLON==m_nToken && IsParserWorking() )
{
// ':' pseudo element
m_nToken = GetNextToken();
if( CSS1_IDENT==m_nToken )
{
if (pLast)
pLast->SetNext( new CSS1Selector(CSS1_SELTYPE_PSEUDO,m_aToken) );
m_nToken = GetNextToken();
}
else
{
// missing pseudo_element
return pRoot;
}
}
return pRoot;
}
// declaration
// : property ':' expr prio?
// | /* empty */
// expression
// : term [ operator term ]*
// term
// : unary_operator?
// [ NUMBER | STRING | PERCENTAGE | LENGTH | EMS | EXS | IDENT |
// HEXCOLOR | URL | RGB ]
// operator
// : '/' | ',' | /* empty */
// unary_operator
// : '-' | '+'
// property
// : ident
// the sign is only used for numeric values (except PERCENTAGE)
// and it's applied on nValue!
std::unique_ptr<CSS1Expression> CSS1Parser::ParseDeclaration( OUString& rProperty )
{
std::unique_ptr<CSS1Expression> pRoot;
CSS1Expression *pLast = nullptr;
// property
if( CSS1_IDENT != m_nToken )
{
// missing property
return pRoot;
}
rProperty = m_aToken;
m_nToken = GetNextToken();
// ':'
if( CSS1_COLON != m_nToken )
{
// missing ':'
return pRoot;
}
m_nToken = GetNextToken();
// term [operator term]*
// here we're pretty lax regarding the syntax, but this shouldn't
// be a problem
bool bDone = false;
sal_Unicode cSign = 0, cOp = 0;
CSS1Expression *pNew = nullptr;
LOOP_CHECK_DECL
while( !bDone && IsParserWorking() )
{
LOOP_CHECK_CHECK( "Infinite loop in ParseDeclaration()" )
switch( m_nToken )
{
case CSS1_MINUS:
cSign = '-';
break;
case CSS1_PLUS:
cSign = '+';
break;
case CSS1_NUMBER:
case CSS1_LENGTH:
case CSS1_PIXLENGTH:
case CSS1_EMS:
case CSS1_EMX:
if( '-'==cSign )
m_nValue = -m_nValue;
[[fallthrough]];
case CSS1_STRING:
case CSS1_PERCENTAGE:
case CSS1_IDENT:
case CSS1_URL:
case CSS1_RGB:
case CSS1_HEXCOLOR:
pNew = new CSS1Expression( m_nToken, m_aToken, m_nValue, cOp );
m_nValue = 0; // otherwise this also is applied to next ident
cSign = 0;
cOp = 0;
break;
case CSS1_SLASH:
cOp = '/';
cSign = 0;
break;
case CSS1_COMMA:
cOp = ',';
cSign = 0;
break;
default:
bDone = true;
break;
}
// if created a new expression save it
if( pNew )
{
OSL_ENSURE( (pRoot!=nullptr) == (pLast!=nullptr),
"Root-Selector, but no Last" );
if( pLast )
pLast->SetNext( pNew );
else
pRoot.reset(pNew);
pLast = pNew;
pNew = nullptr;
}
if( !bDone )
m_nToken = GetNextToken();
}
if( !pRoot )
{
// missing term
return pRoot;
}
// prio?
if( CSS1_IMPORTANT_SYM==m_nToken )
{
// IMPORTANT_SYM
m_nToken = GetNextToken();
}
return pRoot;
}
CSS1Parser::CSS1Parser()
: m_bWhiteSpace(false)
, m_bEOF(false)
, m_cNextCh(0)
, m_nInPos(0)
, m_nlLineNr(0)
, m_nlLinePos(0)
, m_nValue(0)
, m_eState(CSS1_PAR_ACCEPTED)
, m_nToken(CSS1_NULL)
{
}
CSS1Parser::~CSS1Parser()
{
}
void CSS1Parser::ParseStyleSheet( const OUString& rIn )
{
OUString aTmp( rIn );
sal_Unicode c;
while( !aTmp.isEmpty() &&
( ' '==(c=aTmp[0]) || '\t'==c || '\r'==c || '\n'==c ) )
aTmp = aTmp.copy( 1 );
while( !aTmp.isEmpty() && ( ' '==(c=aTmp[aTmp.getLength()-1])
|| '\t'==c || '\r'==c || '\n'==c ) )
aTmp = aTmp.copy( 0, aTmp.getLength()-1 );
// remove SGML comments
if( aTmp.getLength() >= 4 &&
aTmp.startsWith( "<!--" ) )
aTmp = aTmp.copy( 4 );
if( aTmp.getLength() >=3 &&
aTmp.endsWith("-->") )
aTmp = aTmp.copy( 0, aTmp.getLength() - 3 );
if( aTmp.isEmpty() )
return;
InitRead( aTmp );
ParseStyleSheet();
}
void CSS1Parser::ParseStyleOption( const OUString& rIn )
{
if( rIn.isEmpty() )
return;
InitRead( rIn );
// fdo#41796: skip over spurious semicolons
while (CSS1_SEMICOLON == m_nToken)
{
m_nToken = GetNextToken();
}
OUString aProperty;
std::unique_ptr<CSS1Expression> pExpr = ParseDeclaration( aProperty );
if( !pExpr )
return;
// process expression
DeclarationParsed( aProperty, std::move(pExpr) );
LOOP_CHECK_DECL
// [ ';' declaration ]*
while( CSS1_SEMICOLON==m_nToken && IsParserWorking() )
{
LOOP_CHECK_CHECK( "Infinite loop in ParseStyleOption()" )
m_nToken = GetNextToken();
if( CSS1_IDENT==m_nToken )
{
std::unique_ptr<CSS1Expression> pExp = ParseDeclaration( aProperty );
if( pExp )
{
// process expression
DeclarationParsed( aProperty, std::move(pExp) );
}
}
}
}
void CSS1Parser::SelectorParsed( std::unique_ptr<CSS1Selector> /* pSelector */, bool /*bFirst*/ )
{
}
void CSS1Parser::DeclarationParsed( const OUString& /*rProperty*/,
std::unique_ptr<CSS1Expression> /* pExpr */ )
{
}
CSS1Selector::~CSS1Selector()
{
delete m_pNext;
}
CSS1Expression::~CSS1Expression()
{
delete pNext;
}
void CSS1Expression::GetURL( OUString& rURL ) const
{
OSL_ENSURE( CSS1_URL==eType, "CSS1-Expression is not URL" );
OSL_ENSURE( aValue.startsWithIgnoreAsciiCase( "url" ) &&
aValue.getLength() > 5 &&
'(' == aValue[3] &&
')' == aValue[aValue.getLength()-1],
"no valid URL(...)" );
if( aValue.getLength() <= 5 )
return;
rURL = aValue.copy( 4, aValue.getLength() - 5 );
// tdf#94088 original stripped only spaces, but there may also be
// double quotes in CSS style URLs, so be prepared to spaces followed
// by a single quote followed by spaces
const sal_Unicode aSpace(' ');
const sal_Unicode aSingleQuote('\'');
rURL = comphelper::string::strip(rURL, aSpace);
rURL = comphelper::string::strip(rURL, aSingleQuote);
rURL = comphelper::string::strip(rURL, aSpace);
}
bool CSS1Expression::GetColor( Color &rColor ) const
{
OSL_ENSURE( CSS1_IDENT==eType || CSS1_RGB==eType ||
CSS1_HEXCOLOR==eType || CSS1_STRING==eType,
"CSS1-Expression cannot be colour" );
bool bRet = false;
sal_uInt32 nColor = SAL_MAX_UINT32;
switch( eType )
{
case CSS1_RGB:
{
// fourth value to 255 means no alpha transparency
// so the right by default value
sal_uInt8 aColors[4] = { 0, 0, 0, 255 };
// it can be "rgb" or "rgba"
if (!aValue.startsWithIgnoreAsciiCase( "rgb" ) || aValue.getLength() < 6 ||
(aValue[3] != '(' && aValue[4] != '(' ) || aValue[aValue.getLength()-1] != ')')
{
break;
}
sal_Int32 nPos = aValue.startsWithIgnoreAsciiCase( "rgba" )?5:4; // start after "rgba(" or "rgb("
char cSep = (aValue.indexOf(',') != -1)?',':' ';
// alpha value can be after a "/" or ","
bool bIsSepAlphaDiv = (aValue.indexOf('/') != -1)?true:false;
for ( int nCol = 0; nCol < 4 && nPos > 0; ++nCol )
{
const std::u16string_view aNumber = o3tl::getToken(aValue, 0, cSep, nPos);
sal_Int32 nNumber = o3tl::toInt32(aNumber);
if( nNumber<0 )
{
nNumber = 0;
}
else if( aNumber.find('%') != std::u16string_view::npos )
{
if( nNumber > 100 )
nNumber = 100;
nNumber *= 255;
nNumber /= 100;
}
else if( nNumber > 255 )
nNumber = 255;
else if( aNumber.find('.') != std::u16string_view::npos )
{
// in this case aNumber contains something like "0.3" so not an sal_Int32
nNumber = static_cast<sal_Int32>(255.0*o3tl::toDouble(aNumber));
}
aColors[nCol] = static_cast<sal_uInt8>(nNumber);
// rgb with alpha and '/' has this form: rgb(255 0 0 / 50%)
if (bIsSepAlphaDiv && nCol == 2)
{
// but there can be some spaces or not before and after the "/", so skip them
while (aValue[nPos] == '/' || aValue[nPos] == ' ')
++nPos;
}
}
rColor.SetRed( aColors[0] );
rColor.SetGreen( aColors[1] );
rColor.SetBlue( aColors[2] );
rColor.SetAlpha( aColors[3] );
bRet = true; // something different than a colour isn't possible
}
break;
case CSS1_IDENT:
case CSS1_STRING:
{
OUString aTmp( aValue.toAsciiUpperCase() );
nColor = GetHTMLColor( aTmp );
bRet = nColor != SAL_MAX_UINT32;
}
if( bRet || CSS1_STRING != eType || aValue.isEmpty() ||
aValue[0] != '#' )
break;
[[fallthrough]];
case CSS1_HEXCOLOR:
{
// MS-IE hack: colour can also be a string
sal_Int32 nOffset = CSS1_STRING==eType ? 1 : 0;
bool bDouble = aValue.getLength()-nOffset == 3;
sal_Int32 i = nOffset, nEnd = (bDouble ? 3 : 6) + nOffset;
nColor = 0;
for( ; i<nEnd; i++ )
{
sal_Unicode c = (i<aValue.getLength() ? aValue[i]
: '0' );
if( c >= '0' && c <= '9' )
c -= 48;
else if( c >= 'A' && c <= 'F' )
c -= 55;
else if( c >= 'a' && c <= 'f' )
c -= 87;
else
c = 16;
nColor *= 16;
if( c<16 )
nColor += c;
if( bDouble )
{
nColor *= 16;
if( c<16 )
nColor += c;
}
}
bRet = true;
}
break;
default:
;
}
if( bRet && nColor!=SAL_MAX_UINT32 )
{
rColor.SetRed( static_cast<sal_uInt8>((nColor & 0x00ff0000UL) >> 16) );
rColor.SetGreen( static_cast<sal_uInt8>((nColor & 0x0000ff00UL) >> 8) );
rColor.SetBlue( static_cast<sal_uInt8>(nColor & 0x000000ffUL) );
}
return bRet;
}
/* vim:set shiftwidth=4 softtabstop=4 expandtab: */
|