File: htmltext.c

package info (click to toggle)
tk-html3 3.0~fossil20110109-6
  • links: PTS, VCS
  • area: main
  • in suites: stretch
  • size: 6,644 kB
  • ctags: 5,882
  • sloc: ansic: 48,994; tcl: 26,030; sh: 1,190; yacc: 161; makefile: 24
file content (2238 lines) | stat: -rw-r--r-- 75,122 bytes parent folder | download | duplicates (5)
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
/*
 *--------------------------------------------------------------------------
 * Copyright (c) 2006 Dan Kennedy.
 * All rights reserved.
 *
 * This Open Source project was made possible through the financial support
 * of Eolas Technologies Inc.
 * 
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions are met:
 * 
 *     * Redistributions of source code must retain the above copyright
 *       notice, this list of conditions and the following disclaimer.
 *     * Redistributions in binary form must reproduce the above copyright
 *       notice, this list of conditions and the following disclaimer in the
 *       documentation and/or other materials provided with the distribution.
 *     * Neither the name of Eolas Technologies Inc. nor the names of its
 *       contributors may be used to endorse or promote products derived from
 *       this software without specific prior written permission.
 * 
 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
 * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
 * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
 * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
 * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
 * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
 * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
 * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
 * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
 * POSSIBILITY OF SUCH DAMAGE.
 */

#include <ctype.h>
#include <assert.h>
#include <stdlib.h>
#include "html.h"

#define ISNEWLINE(x) ((x) == '\n' || (x) == '\r')
#define ISTAB(x) ((x) == '\t')
#define ISSPACE(x) isspace((unsigned char)(x))

/*
 * This file implements the experimental [tag] widget method. The
 * following summarizes the interface supported:
 *
 *         html tag add TAGNAME FROM-NODE FROM-INDEX TO-NODE TO-INDEX
 *         html tag remove TAGNAME FROM-NODE FROM-INDEX TO-NODE TO-INDEX
 *         html tag delete TAGNAME
 *         html tag configure TAGNAME ?-fg COLOR? ?-bg COLOR?
 *
 * This file exports the following functions:
 *
 *     HtmlTranslateEscapes()
 *         Translates Html escapes (i.e. "&nbsp;").
 *
 *     HtmlTagAddRemoveCmd()
 *         Implementation of [pathName tag add] and [pathName tag remove]
 *
 *     HtmlTagDeleteCmd()
 *         Implementation of [pathName tag delete]
 *
 *     HtmlTagConfigureCmd()
 *         Implementation of [pathName tag configured]
 *
 *     HtmlTagCleanupNode()
 *     HtmlTagCleanupTree()
 *         Respectively called when an HtmlNode or HtmlTree structure is being
 *         deallocated to free outstanding tag related stuff.
 *
 *
 * Also:
 *
 *     HtmlTextTextCmd()
 *     HtmlTextBboxCmd()
 *     HtmlTextOffsetCmd()
 *     HtmlTextIndexCmd()
 */

/****************** Begin Escape Sequence Translator *************/

/*
** The next section of code implements routines used to translate
** the '&' escape sequences of SGML to individual characters.
** Examples:
**
**         &amp;          &
**         &lt;           <
**         &gt;           >
**         &nbsp;         nonbreakable space
*/

/* Each escape sequence is recorded as an instance of the following
** structure
*/
struct sgEsc {
    char *zName;              /* The name of this escape sequence. ex: "amp" */
    char value[8];            /* The value for this sequence. ex: "&" */
    struct sgEsc *pNext;      /* Next sequence with the same hash on zName */
};

/* The following is a table of all escape sequences.  Add new sequences
** by adding entries to this table.
*/
static struct sgEsc esc_sequences[] = {
    {"nbsp", "\xC2\xA0", 0},            /* Unicode code-point 160 */
    {"iexcl", "\xC2\xA1", 0},           /* Unicode code-point 161 */
    {"cent", "\xC2\xA2", 0},            /* Unicode code-point 162 */
    {"pound", "\xC2\xA3", 0},           /* Unicode code-point 163 */
    {"curren", "\xC2\xA4", 0},          /* Unicode code-point 164 */
    {"yen", "\xC2\xA5", 0},             /* Unicode code-point 165 */
    {"brvbar", "\xC2\xA6", 0},          /* Unicode code-point 166 */
    {"sect", "\xC2\xA7", 0},            /* Unicode code-point 167 */
    {"uml", "\xC2\xA8", 0},             /* Unicode code-point 168 */
    {"copy", "\xC2\xA9", 0},            /* Unicode code-point 169 */
    {"ordf", "\xC2\xAA", 0},            /* Unicode code-point 170 */
    {"laquo", "\xC2\xAB", 0},           /* Unicode code-point 171 */
    {"not", "\xC2\xAC", 0},             /* Unicode code-point 172 */
    {"shy", "\xC2\xAD", 0},             /* Unicode code-point 173 */
    {"reg", "\xC2\xAE", 0},             /* Unicode code-point 174 */
    {"macr", "\xC2\xAF", 0},            /* Unicode code-point 175 */
    {"deg", "\xC2\xB0", 0},             /* Unicode code-point 176 */
    {"plusmn", "\xC2\xB1", 0},          /* Unicode code-point 177 */
    {"sup2", "\xC2\xB2", 0},            /* Unicode code-point 178 */
    {"sup3", "\xC2\xB3", 0},            /* Unicode code-point 179 */
    {"acute", "\xC2\xB4", 0},           /* Unicode code-point 180 */
    {"micro", "\xC2\xB5", 0},           /* Unicode code-point 181 */
    {"para", "\xC2\xB6", 0},            /* Unicode code-point 182 */
    {"middot", "\xC2\xB7", 0},          /* Unicode code-point 183 */
    {"cedil", "\xC2\xB8", 0},           /* Unicode code-point 184 */
    {"sup1", "\xC2\xB9", 0},            /* Unicode code-point 185 */
    {"ordm", "\xC2\xBA", 0},            /* Unicode code-point 186 */
    {"raquo", "\xC2\xBB", 0},           /* Unicode code-point 187 */
    {"frac14", "\xC2\xBC", 0},          /* Unicode code-point 188 */
    {"frac12", "\xC2\xBD", 0},          /* Unicode code-point 189 */
    {"frac34", "\xC2\xBE", 0},          /* Unicode code-point 190 */
    {"iquest", "\xC2\xBF", 0},          /* Unicode code-point 191 */
    {"Agrave", "\xC3\x80", 0},          /* Unicode code-point 192 */
    {"Aacute", "\xC3\x81", 0},          /* Unicode code-point 193 */
    {"Acirc", "\xC3\x82", 0},           /* Unicode code-point 194 */
    {"Atilde", "\xC3\x83", 0},          /* Unicode code-point 195 */
    {"Auml", "\xC3\x84", 0},            /* Unicode code-point 196 */
    {"Aring", "\xC3\x85", 0},           /* Unicode code-point 197 */
    {"AElig", "\xC3\x86", 0},           /* Unicode code-point 198 */
    {"Ccedil", "\xC3\x87", 0},          /* Unicode code-point 199 */
    {"Egrave", "\xC3\x88", 0},          /* Unicode code-point 200 */
    {"Eacute", "\xC3\x89", 0},          /* Unicode code-point 201 */
    {"Ecirc", "\xC3\x8A", 0},           /* Unicode code-point 202 */
    {"Euml", "\xC3\x8B", 0},            /* Unicode code-point 203 */
    {"Igrave", "\xC3\x8C", 0},          /* Unicode code-point 204 */
    {"Iacute", "\xC3\x8D", 0},          /* Unicode code-point 205 */
    {"Icirc", "\xC3\x8E", 0},           /* Unicode code-point 206 */
    {"Iuml", "\xC3\x8F", 0},            /* Unicode code-point 207 */
    {"ETH", "\xC3\x90", 0},             /* Unicode code-point 208 */
    {"Ntilde", "\xC3\x91", 0},          /* Unicode code-point 209 */
    {"Ograve", "\xC3\x92", 0},          /* Unicode code-point 210 */
    {"Oacute", "\xC3\x93", 0},          /* Unicode code-point 211 */
    {"Ocirc", "\xC3\x94", 0},           /* Unicode code-point 212 */
    {"Otilde", "\xC3\x95", 0},          /* Unicode code-point 213 */
    {"Ouml", "\xC3\x96", 0},            /* Unicode code-point 214 */
    {"times", "\xC3\x97", 0},           /* Unicode code-point 215 */
    {"Oslash", "\xC3\x98", 0},          /* Unicode code-point 216 */
    {"Ugrave", "\xC3\x99", 0},          /* Unicode code-point 217 */
    {"Uacute", "\xC3\x9A", 0},          /* Unicode code-point 218 */
    {"Ucirc", "\xC3\x9B", 0},           /* Unicode code-point 219 */
    {"Uuml", "\xC3\x9C", 0},            /* Unicode code-point 220 */
    {"Yacute", "\xC3\x9D", 0},          /* Unicode code-point 221 */
    {"THORN", "\xC3\x9E", 0},           /* Unicode code-point 222 */
    {"szlig", "\xC3\x9F", 0},           /* Unicode code-point 223 */
    {"agrave", "\xC3\xA0", 0},          /* Unicode code-point 224 */
    {"aacute", "\xC3\xA1", 0},          /* Unicode code-point 225 */
    {"acirc", "\xC3\xA2", 0},           /* Unicode code-point 226 */
    {"atilde", "\xC3\xA3", 0},          /* Unicode code-point 227 */
    {"auml", "\xC3\xA4", 0},            /* Unicode code-point 228 */
    {"aring", "\xC3\xA5", 0},           /* Unicode code-point 229 */
    {"aelig", "\xC3\xA6", 0},           /* Unicode code-point 230 */
    {"ccedil", "\xC3\xA7", 0},          /* Unicode code-point 231 */
    {"egrave", "\xC3\xA8", 0},          /* Unicode code-point 232 */
    {"eacute", "\xC3\xA9", 0},          /* Unicode code-point 233 */
    {"ecirc", "\xC3\xAA", 0},           /* Unicode code-point 234 */
    {"euml", "\xC3\xAB", 0},            /* Unicode code-point 235 */
    {"igrave", "\xC3\xAC", 0},          /* Unicode code-point 236 */
    {"iacute", "\xC3\xAD", 0},          /* Unicode code-point 237 */
    {"icirc", "\xC3\xAE", 0},           /* Unicode code-point 238 */
    {"iuml", "\xC3\xAF", 0},            /* Unicode code-point 239 */
    {"eth", "\xC3\xB0", 0},             /* Unicode code-point 240 */
    {"ntilde", "\xC3\xB1", 0},          /* Unicode code-point 241 */
    {"ograve", "\xC3\xB2", 0},          /* Unicode code-point 242 */
    {"oacute", "\xC3\xB3", 0},          /* Unicode code-point 243 */
    {"ocirc", "\xC3\xB4", 0},           /* Unicode code-point 244 */
    {"otilde", "\xC3\xB5", 0},          /* Unicode code-point 245 */
    {"ouml", "\xC3\xB6", 0},            /* Unicode code-point 246 */
    {"divide", "\xC3\xB7", 0},          /* Unicode code-point 247 */
    {"oslash", "\xC3\xB8", 0},          /* Unicode code-point 248 */
    {"ugrave", "\xC3\xB9", 0},          /* Unicode code-point 249 */
    {"uacute", "\xC3\xBA", 0},          /* Unicode code-point 250 */
    {"ucirc", "\xC3\xBB", 0},           /* Unicode code-point 251 */
    {"uuml", "\xC3\xBC", 0},            /* Unicode code-point 252 */
    {"yacute", "\xC3\xBD", 0},          /* Unicode code-point 253 */
    {"thorn", "\xC3\xBE", 0},           /* Unicode code-point 254 */
    {"yuml", "\xC3\xBF", 0},            /* Unicode code-point 255 */
    {"quot", "\x22", 0},                /* Unicode code-point 34 */
    {"amp", "\x26", 0},                 /* Unicode code-point 38 */
    {"lt", "\x3C", 0},                  /* Unicode code-point 60 */
    {"gt", "\x3E", 0},                  /* Unicode code-point 62 */
    {"OElig", "\xC5\x92", 0},           /* Unicode code-point 338 */
    {"oelig", "\xC5\x93", 0},           /* Unicode code-point 339 */
    {"Scaron", "\xC5\xA0", 0},          /* Unicode code-point 352 */
    {"scaron", "\xC5\xA1", 0},          /* Unicode code-point 353 */
    {"Yuml", "\xC5\xB8", 0},            /* Unicode code-point 376 */
    {"circ", "\xCB\x86", 0},            /* Unicode code-point 710 */
    {"tilde", "\xCB\x9C", 0},           /* Unicode code-point 732 */
    {"ensp", "\xE2\x80\x82", 0},        /* Unicode code-point 8194 */
    {"emsp", "\xE2\x80\x83", 0},        /* Unicode code-point 8195 */
    {"thinsp", "\xE2\x80\x89", 0},      /* Unicode code-point 8201 */
    {"zwnj", "\xE2\x80\x8C", 0},        /* Unicode code-point 8204 */
    {"zwj", "\xE2\x80\x8D", 0},         /* Unicode code-point 8205 */
    {"lrm", "\xE2\x80\x8E", 0},         /* Unicode code-point 8206 */
    {"rlm", "\xE2\x80\x8F", 0},         /* Unicode code-point 8207 */
    {"ndash", "\xE2\x80\x93", 0},       /* Unicode code-point 8211 */
    {"mdash", "\xE2\x80\x94", 0},       /* Unicode code-point 8212 */
    {"lsquo", "\xE2\x80\x98", 0},       /* Unicode code-point 8216 */
    {"rsquo", "\xE2\x80\x99", 0},       /* Unicode code-point 8217 */
    {"sbquo", "\xE2\x80\x9A", 0},       /* Unicode code-point 8218 */
    {"ldquo", "\xE2\x80\x9C", 0},       /* Unicode code-point 8220 */
    {"rdquo", "\xE2\x80\x9D", 0},       /* Unicode code-point 8221 */
    {"bdquo", "\xE2\x80\x9E", 0},       /* Unicode code-point 8222 */
    {"dagger", "\xE2\x80\xA0", 0},      /* Unicode code-point 8224 */
    {"Dagger", "\xE2\x80\xA1", 0},      /* Unicode code-point 8225 */
    {"permil", "\xE2\x80\xB0", 0},      /* Unicode code-point 8240 */
    {"lsaquo", "\xE2\x80\xB9", 0},      /* Unicode code-point 8249 */
    {"rsaquo", "\xE2\x80\xBA", 0},      /* Unicode code-point 8250 */
    {"euro", "\xE2\x82\xAC", 0},        /* Unicode code-point 8364 */
    {"fnof", "\xC6\x92", 0},            /* Unicode code-point 402 */
    {"Alpha", "\xCE\x91", 0},           /* Unicode code-point 913 */
    {"Beta", "\xCE\x92", 0},            /* Unicode code-point 914 */
    {"Gamma", "\xCE\x93", 0},           /* Unicode code-point 915 */
    {"Delta", "\xCE\x94", 0},           /* Unicode code-point 916 */
    {"Epsilon", "\xCE\x95", 0},         /* Unicode code-point 917 */
    {"Zeta", "\xCE\x96", 0},            /* Unicode code-point 918 */
    {"Eta", "\xCE\x97", 0},             /* Unicode code-point 919 */
    {"Theta", "\xCE\x98", 0},           /* Unicode code-point 920 */
    {"Iota", "\xCE\x99", 0},            /* Unicode code-point 921 */
    {"Kappa", "\xCE\x9A", 0},           /* Unicode code-point 922 */
    {"Lambda", "\xCE\x9B", 0},          /* Unicode code-point 923 */
    {"Mu", "\xCE\x9C", 0},              /* Unicode code-point 924 */
    {"Nu", "\xCE\x9D", 0},              /* Unicode code-point 925 */
    {"Xi", "\xCE\x9E", 0},              /* Unicode code-point 926 */
    {"Omicron", "\xCE\x9F", 0},         /* Unicode code-point 927 */
    {"Pi", "\xCE\xA0", 0},              /* Unicode code-point 928 */
    {"Rho", "\xCE\xA1", 0},             /* Unicode code-point 929 */
    {"Sigma", "\xCE\xA3", 0},           /* Unicode code-point 931 */
    {"Tau", "\xCE\xA4", 0},             /* Unicode code-point 932 */
    {"Upsilon", "\xCE\xA5", 0},         /* Unicode code-point 933 */
    {"Phi", "\xCE\xA6", 0},             /* Unicode code-point 934 */
    {"Chi", "\xCE\xA7", 0},             /* Unicode code-point 935 */
    {"Psi", "\xCE\xA8", 0},             /* Unicode code-point 936 */
    {"Omega", "\xCE\xA9", 0},           /* Unicode code-point 937 */
    {"alpha", "\xCE\xB1", 0},           /* Unicode code-point 945 */
    {"beta", "\xCE\xB2", 0},            /* Unicode code-point 946 */
    {"gamma", "\xCE\xB3", 0},           /* Unicode code-point 947 */
    {"delta", "\xCE\xB4", 0},           /* Unicode code-point 948 */
    {"epsilon", "\xCE\xB5", 0},         /* Unicode code-point 949 */
    {"zeta", "\xCE\xB6", 0},            /* Unicode code-point 950 */
    {"eta", "\xCE\xB7", 0},             /* Unicode code-point 951 */
    {"theta", "\xCE\xB8", 0},           /* Unicode code-point 952 */
    {"iota", "\xCE\xB9", 0},            /* Unicode code-point 953 */
    {"kappa", "\xCE\xBA", 0},           /* Unicode code-point 954 */
    {"lambda", "\xCE\xBB", 0},          /* Unicode code-point 955 */
    {"mu", "\xCE\xBC", 0},              /* Unicode code-point 956 */
    {"nu", "\xCE\xBD", 0},              /* Unicode code-point 957 */
    {"xi", "\xCE\xBE", 0},              /* Unicode code-point 958 */
    {"omicron", "\xCE\xBF", 0},         /* Unicode code-point 959 */
    {"pi", "\xCF\x80", 0},              /* Unicode code-point 960 */
    {"rho", "\xCF\x81", 0},             /* Unicode code-point 961 */
    {"sigmaf", "\xCF\x82", 0},          /* Unicode code-point 962 */
    {"sigma", "\xCF\x83", 0},           /* Unicode code-point 963 */
    {"tau", "\xCF\x84", 0},             /* Unicode code-point 964 */
    {"upsilon", "\xCF\x85", 0},         /* Unicode code-point 965 */
    {"phi", "\xCF\x86", 0},             /* Unicode code-point 966 */
    {"chi", "\xCF\x87", 0},             /* Unicode code-point 967 */
    {"psi", "\xCF\x88", 0},             /* Unicode code-point 968 */
    {"omega", "\xCF\x89", 0},           /* Unicode code-point 969 */
    {"thetasym", "\xCF\x91", 0},        /* Unicode code-point 977 */
    {"upsih", "\xCF\x92", 0},           /* Unicode code-point 978 */
    {"piv", "\xCF\x96", 0},             /* Unicode code-point 982 */
    {"bull", "\xE2\x80\xA2", 0},        /* Unicode code-point 8226 */
    {"hellip", "\xE2\x80\xA6", 0},      /* Unicode code-point 8230 */
    {"prime", "\xE2\x80\xB2", 0},       /* Unicode code-point 8242 */
    {"Prime", "\xE2\x80\xB3", 0},       /* Unicode code-point 8243 */
    {"oline", "\xE2\x80\xBE", 0},       /* Unicode code-point 8254 */
    {"frasl", "\xE2\x81\x84", 0},       /* Unicode code-point 8260 */
    {"weierp", "\xE2\x84\x98", 0},      /* Unicode code-point 8472 */
    {"image", "\xE2\x84\x91", 0},       /* Unicode code-point 8465 */
    {"real", "\xE2\x84\x9C", 0},        /* Unicode code-point 8476 */
    {"trade", "\xE2\x84\xA2", 0},       /* Unicode code-point 8482 */
    {"alefsym", "\xE2\x84\xB5", 0},     /* Unicode code-point 8501 */
    {"larr", "\xE2\x86\x90", 0},        /* Unicode code-point 8592 */
    {"uarr", "\xE2\x86\x91", 0},        /* Unicode code-point 8593 */
    {"rarr", "\xE2\x86\x92", 0},        /* Unicode code-point 8594 */
    {"darr", "\xE2\x86\x93", 0},        /* Unicode code-point 8595 */
    {"harr", "\xE2\x86\x94", 0},        /* Unicode code-point 8596 */
    {"crarr", "\xE2\x86\xB5", 0},       /* Unicode code-point 8629 */
    {"lArr", "\xE2\x87\x90", 0},        /* Unicode code-point 8656 */
    {"uArr", "\xE2\x87\x91", 0},        /* Unicode code-point 8657 */
    {"rArr", "\xE2\x87\x92", 0},        /* Unicode code-point 8658 */
    {"dArr", "\xE2\x87\x93", 0},        /* Unicode code-point 8659 */
    {"hArr", "\xE2\x87\x94", 0},        /* Unicode code-point 8660 */
    {"forall", "\xE2\x88\x80", 0},      /* Unicode code-point 8704 */
    {"part", "\xE2\x88\x82", 0},        /* Unicode code-point 8706 */
    {"exist", "\xE2\x88\x83", 0},       /* Unicode code-point 8707 */
    {"empty", "\xE2\x88\x85", 0},       /* Unicode code-point 8709 */
    {"nabla", "\xE2\x88\x87", 0},       /* Unicode code-point 8711 */
    {"isin", "\xE2\x88\x88", 0},        /* Unicode code-point 8712 */
    {"notin", "\xE2\x88\x89", 0},       /* Unicode code-point 8713 */
    {"ni", "\xE2\x88\x8B", 0},          /* Unicode code-point 8715 */
    {"prod", "\xE2\x88\x8F", 0},        /* Unicode code-point 8719 */
    {"sum", "\xE2\x88\x91", 0},         /* Unicode code-point 8721 */
    {"minus", "\xE2\x88\x92", 0},       /* Unicode code-point 8722 */
    {"lowast", "\xE2\x88\x97", 0},      /* Unicode code-point 8727 */
    {"radic", "\xE2\x88\x9A", 0},       /* Unicode code-point 8730 */
    {"prop", "\xE2\x88\x9D", 0},        /* Unicode code-point 8733 */
    {"infin", "\xE2\x88\x9E", 0},       /* Unicode code-point 8734 */
    {"ang", "\xE2\x88\xA0", 0},         /* Unicode code-point 8736 */
    {"and", "\xE2\x88\xA7", 0},         /* Unicode code-point 8743 */
    {"or", "\xE2\x88\xA8", 0},          /* Unicode code-point 8744 */
    {"cap", "\xE2\x88\xA9", 0},         /* Unicode code-point 8745 */
    {"cup", "\xE2\x88\xAA", 0},         /* Unicode code-point 8746 */
    {"int", "\xE2\x88\xAB", 0},         /* Unicode code-point 8747 */
    {"there4", "\xE2\x88\xB4", 0},      /* Unicode code-point 8756 */
    {"sim", "\xE2\x88\xBC", 0},         /* Unicode code-point 8764 */
    {"cong", "\xE2\x89\x85", 0},        /* Unicode code-point 8773 */
    {"asymp", "\xE2\x89\x88", 0},       /* Unicode code-point 8776 */
    {"ne", "\xE2\x89\xA0", 0},          /* Unicode code-point 8800 */
    {"equiv", "\xE2\x89\xA1", 0},       /* Unicode code-point 8801 */
    {"le", "\xE2\x89\xA4", 0},          /* Unicode code-point 8804 */
    {"ge", "\xE2\x89\xA5", 0},          /* Unicode code-point 8805 */
    {"sub", "\xE2\x8A\x82", 0},         /* Unicode code-point 8834 */
    {"sup", "\xE2\x8A\x83", 0},         /* Unicode code-point 8835 */
    {"nsub", "\xE2\x8A\x84", 0},        /* Unicode code-point 8836 */
    {"sube", "\xE2\x8A\x86", 0},        /* Unicode code-point 8838 */
    {"supe", "\xE2\x8A\x87", 0},        /* Unicode code-point 8839 */
    {"oplus", "\xE2\x8A\x95", 0},       /* Unicode code-point 8853 */
    {"otimes", "\xE2\x8A\x97", 0},      /* Unicode code-point 8855 */
    {"perp", "\xE2\x8A\xA5", 0},        /* Unicode code-point 8869 */
    {"sdot", "\xE2\x8B\x85", 0},        /* Unicode code-point 8901 */
    {"lceil", "\xE2\x8C\x88", 0},       /* Unicode code-point 8968 */
    {"rceil", "\xE2\x8C\x89", 0},       /* Unicode code-point 8969 */
    {"lfloor", "\xE2\x8C\x8A", 0},      /* Unicode code-point 8970 */
    {"rfloor", "\xE2\x8C\x8B", 0},      /* Unicode code-point 8971 */
    {"lang", "\xE2\x8C\xA9", 0},        /* Unicode code-point 9001 */
    {"rang", "\xE2\x8C\xAA", 0},        /* Unicode code-point 9002 */
    {"loz", "\xE2\x97\x8A", 0},         /* Unicode code-point 9674 */
    {"spades", "\xE2\x99\xA0", 0},      /* Unicode code-point 9824 */
    {"clubs", "\xE2\x99\xA3", 0},       /* Unicode code-point 9827 */
    {"hearts", "\xE2\x99\xA5", 0},      /* Unicode code-point 9829 */
    {"diams", "\xE2\x99\xA6", 0},       /* Unicode code-point 9830 */
  
    /* Non-standard. But very common. */
    {"quote", "\"", 0},
    {"apos", "'", 0},
};

/* The size of the handler hash table.  For best results this should
** be a prime number which is about the same size as the number of
** escape sequences known to the system. */
#define ESC_HASH_SIZE (sizeof(esc_sequences)/sizeof(esc_sequences[0])+7)

/* The hash table 
**
** If the name of an escape sequences hashes to the value H, then
** apEscHash[H] will point to a linked list of Esc structures, one of
** which will be the Esc structure for that escape sequence.
*/
static struct sgEsc *apEscHash[ESC_HASH_SIZE];

/* Hash a escape sequence name.  The value returned is an integer
** between 0 and ESC_HASH_SIZE-1, inclusive.
*/
static int
EscHash(zName)
    const char *zName;
{
    int h = 0;                         /* The hash value to be returned */
    char c;                            /* The next character in the name
                                        * being hashed */

    while ((c = *zName) != 0) {
        h = h << 5 ^ h ^ c;
        zName++;
    }
    if (h < 0) {
        h = -h;
    }
    else {
    }
    return h % ESC_HASH_SIZE;
}

#ifdef TEST

/* 
** Compute the longest and average collision chain length for the
** escape sequence hash table
*/
static void
EscHashStats(void)
{
    int i;
    int sum = 0;
    int max = 0;
    int cnt;
    int notempty = 0;
    struct sgEsc *p;

    for (i = 0; i < sizeof(esc_sequences) / sizeof(esc_sequences[0]); i++) {
        cnt = 0;
        p = apEscHash[i];
        if (p)
            notempty++;
        while (p) {
            cnt++;
            p = p->pNext;
        }
        sum += cnt;
        if (cnt > max)
            max = cnt;
    }
    printf("Longest chain=%d  avg=%g  slots=%d  empty=%d (%g%%)\n",
           max, (double) sum / (double) notempty, i, i - notempty,
           100.0 * (i - notempty) / (double) i);
}
#endif

/* Initialize the escape sequence hash table
*/
static void
EscInit()
{
    int i;                             /* For looping thru the list of escape 
                                        * sequences */
    int h;                             /* The hash on a sequence */

    for (i = 0; i < sizeof(esc_sequences) / sizeof(esc_sequences[i]); i++) {

/* #ifdef TCL_UTF_MAX */
#if 0
        {
            int c = esc_sequences[i].value[0];
            Tcl_UniCharToUtf(c, esc_sequences[i].value);
        }
#endif
        h = EscHash(esc_sequences[i].zName);
        esc_sequences[i].pNext = apEscHash[h];
        apEscHash[h] = &esc_sequences[i];
    }
#ifdef TEST
    EscHashStats();
#endif
}

/*
** This table translates the non-standard microsoft characters between
** 0x80 and 0x9f into plain ASCII so that the characters will be visible
** on Unix systems.  Care is taken to translate the characters
** into values less than 0x80, to avoid UTF-8 problems.
*/
#ifndef __WIN32__
static char acMsChar[] = {
    /*
     * 0x80 
     */ 'C',
    /*
     * 0x81 
     */ ' ',
    /*
     * 0x82 
     */ ',',
    /*
     * 0x83 
     */ 'f',
    /*
     * 0x84 
     */ '"',
    /*
     * 0x85 
     */ '.',
    /*
     * 0x86 
     */ '*',
    /*
     * 0x87 
     */ '*',
    /*
     * 0x88 
     */ '^',
    /*
     * 0x89 
     */ '%',
    /*
     * 0x8a 
     */ 'S',
    /*
     * 0x8b 
     */ '<',
    /*
     * 0x8c 
     */ 'O',
    /*
     * 0x8d 
     */ ' ',
    /*
     * 0x8e 
     */ 'Z',
    /*
     * 0x8f 
     */ ' ',
    /*
     * 0x90 
     */ ' ',
    /*
     * 0x91 
     */ '\'',
    /*
     * 0x92 
     */ '\'',
    /*
     * 0x93 
     */ '"',
    /*
     * 0x94 
     */ '"',
    /*
     * 0x95 
     */ '*',
    /*
     * 0x96 
     */ '-',
    /*
     * 0x97 
     */ '-',
    /*
     * 0x98 
     */ '~',
    /*
     * 0x99 
     */ '@',
    /*
     * 0x9a 
     */ 's',
    /*
     * 0x9b 
     */ '>',
    /*
     * 0x9c 
     */ 'o',
    /*
     * 0x9d 
     */ ' ',
    /*
     * 0x9e 
     */ 'z',
    /*
     * 0x9f 
     */ 'Y',
};
#endif

static int 
translateNumericEscape(z, pI)
    char *z;
    int *pI;          /* IN/OUT: Index into string z */
{
    char *zLocal = &z[*pI];
    int base = 10;
    int iRet = 10;

    if (*zLocal == 'x' || *zLocal == 'X') {
        /* Hexadecimal number */
        base = 16;
        zLocal++;
    }

    iRet = strtol(zLocal, &zLocal, base);

    /* Gobble up a trailing semi-colon */
    if (*zLocal == ';') {
        zLocal++;
    }

    *pI = (zLocal - z);
    return iRet;
}

/* Translate escape sequences in the string "z".  "z" is overwritten
** with the translated sequence.
**
** Unrecognized escape sequences are unaltered.
**
** Example:
**
**      input =    "AT&amp;T &gt MCI"
**      output =   "AT&T > MCI"
*/
void
HtmlTranslateEscapes(z)
    char *z;
{
    int from;                          /* Read characters from this position
                                        * in z[] */
    int to;                            /* Write characters into this position 
                                        * in z[] */
    int h;                             /* A hash on the escape sequence */
    struct sgEsc *p;                   /* For looping down the escape
                                        * sequence collision chain */
    static int isInit = 0;             /* True after initialization */

    from = to = 0;
    if (!isInit) {
        EscInit();
        isInit = 1;
    }
    while (z[from]) {
        if (z[from] == '&') {
            if (z[from + 1] == '#') {
                int i = from + 2;
                int v = translateNumericEscape(z, &i);

                /*
                 * On Unix systems, translate the non-standard microsoft **
                 * characters in the range of 0x80 to 0x9f into something **
                 * we can see. 
                 */
#ifndef __WIN32__
                if (v >= 0x80 && v < 0xa0) {
                    v = acMsChar[v & 0x1f];
                }
#endif
                /*
                 * Put the character in the output stream in place of ** the
                 * "&#000;".  How we do this depends on whether or ** not we
                 * are using UTF-8. 
                 */
#ifdef TCL_UTF_MAX
                {
                    int j, n;
                    char value[8];
                    n = Tcl_UniCharToUtf(v, value);
                    for (j = 0; j < n; j++) {
                        z[to++] = value[j];
                    }
                }
#else
                z[to++] = v;
#endif
                from = i;
            }
            else {
                int i = from + 1;
                int c;
                while (z[i] && isalnum(z[i])) {
                    i++;
                }
                c = z[i];
                z[i] = 0;
                h = EscHash(&z[from + 1]);
                p = apEscHash[h];
                while (p && strcmp(p->zName, &z[from + 1]) != 0) {
                    p = p->pNext;
                }
                z[i] = c;
                if (p) {
                    int j;
                    for (j = 0; p->value[j]; j++) {
                        z[to++] = p->value[j];
                    }
                    from = i;
                    if (c == ';') {
                        from++;
                    }
                }
                else {
                    z[to++] = z[from++];
                }
            }

            /*
             * On UNIX systems, look for the non-standard microsoft
             * characters ** between 0x80 and 0x9f and translate them into
             * printable ASCII ** codes.  Separate algorithms are required to 
             * do this for plain ** ascii and for utf-8. 
             */
#ifndef __WIN32__
#ifdef TCL_UTF_MAX
        }
        else if ((z[from] & 0x80) != 0) {
            Tcl_UniChar c;
            int n;
            n = Tcl_UtfToUniChar(&z[from], &c);
            if (c >= 0x80 && c < 0xa0) {
                z[to++] = acMsChar[c & 0x1f];
                from += n;
            }
            else {
                while (n--)
                    z[to++] = z[from++];
            }
#else /* if !defined(TCL_UTF_MAX) */
        }
        else if (((unsigned char) z[from]) >= 0x80
                 && ((unsigned char) z[from]) < 0xa0) {
            z[to++] = acMsChar[z[from++] & 0x1f];
#endif /* TCL_UTF_MAX */
#endif /* __WIN32__ */
        }
        else {
            z[to++] = z[from++];
        }
    }
    z[to] = 0;
}

static HtmlWidgetTag *
getWidgetTag(pTree, zTag, pIsNew)
    HtmlTree *pTree;
    const char *zTag;
    int *pIsNew;
{
    Tcl_HashEntry *pEntry;
    int isNew;
    HtmlWidgetTag *pTag;

    pEntry = Tcl_CreateHashEntry(&pTree->aTag, zTag, &isNew);
    if (isNew) {
        Tk_OptionTable otab = pTree->tagOptionTable;
        static Tk_OptionSpec ospec[] = {
            {TK_OPTION_COLOR, "-foreground", "", "", "white", -1, \
             Tk_Offset(HtmlWidgetTag, foreground), 0, 0, 0},
            {TK_OPTION_COLOR, "-background", "", "", "black", -1, \
             Tk_Offset(HtmlWidgetTag, background), 0, 0, 0},

            {TK_OPTION_SYNONYM, "-bg", 0, 0, 0, 0, -1, 0, "-background", 0},
            {TK_OPTION_SYNONYM, "-fg", 0, 0, 0, 0, -1, 0, "-foreground", 0},

            {TK_OPTION_END, 0, 0, 0, 0, 0, 0, 0, 0}
        };
        pTag = (HtmlWidgetTag *)HtmlClearAlloc("", sizeof(HtmlWidgetTag));
        Tcl_SetHashValue(pEntry, pTag);
        if (0 == otab) {
            pTree->tagOptionTable = Tk_CreateOptionTable(pTree->interp, ospec);
            otab = pTree->tagOptionTable;
            assert(otab);
        }
        Tk_InitOptions(pTree->interp, (char *)pTag, otab, pTree->tkwin);
        assert(pTag->foreground && pTag->background);
    } else {
        pTag = (HtmlWidgetTag *)Tcl_GetHashValue(pEntry);
    }

    if (pIsNew) {
        *pIsNew = isNew;
    }
    return pTag;
}

static HtmlNode * 
orderIndexPair(ppA, piA, ppB, piB)
    HtmlNode **ppA;
    int *piA;
    HtmlNode **ppB;
    int *piB;
{
    HtmlNode *pA;
    HtmlNode *pB;
    HtmlNode *pParent;
    int nDepthA = 0;
    int nDepthB = 0;
    int ii;

    int swap = 0;

    for(pA = HtmlNodeParent(*ppA); pA; pA = HtmlNodeParent(pA)) nDepthA++;
    for(pB = HtmlNodeParent(*ppB); pB; pB = HtmlNodeParent(pB)) nDepthB++;

    pA = *ppA;
    pB = *ppB;
    for(ii = 0; ii < (nDepthA - nDepthB); ii++) pA = HtmlNodeParent(pA);
    for(ii = 0; ii < (nDepthB - nDepthA); ii++) pB = HtmlNodeParent(pB);

    if (pA == pB) {
        if (nDepthA == nDepthB) {
            /* In this case *ppA and *ppB are the same node */
            swap = (*piA > *piB);
        } else {
            /* One of (*ppA, *ppB) is a descendant of the other */
            swap = (nDepthA > nDepthB);
        }
        pParent = pA;
    } else {
        while (HtmlNodeParent(pA) != HtmlNodeParent(pB)) {
            pA = HtmlNodeParent(pA);
            pB = HtmlNodeParent(pB);
            assert(pA && pB && pA != pB);
        }
        pParent = HtmlNodeParent(pA);
        for (ii = 0; ; ii++) {
            HtmlNode *pChild = HtmlNodeChild(pParent, ii);
            assert(ii < HtmlNodeNumChildren(pParent) && pChild);
            if (pChild == pA) break;
            if (pChild == pB) {
                swap = 1;
                break;
            }
        }
    }

    if (swap) {
        HtmlNode *p;
        int i;
        p = *ppB;
        *ppB = *ppA;
        *ppA = p;
        i = *piB;
        *piB = *piA;
        *piA = i;
    }

    return pParent;
}

/*
 *---------------------------------------------------------------------------
 *
 * removeTagFromNode --
 * 
 * Results:
 *     Returns non-zero if one or more characters of this node were tagged.
 *
 * Side effects:
 *     None.
 *
 *---------------------------------------------------------------------------
 */
static int
removeTagFromNode(pTextNode, pTag)
    HtmlTextNode *pTextNode;
    HtmlWidgetTag *pTag;
{
    int eRet = 0;
    HtmlTaggedRegion *pTagged = pTextNode->pTagged;
    if (pTagged) { 
        HtmlTaggedRegion **pPtr = &pTextNode->pTagged;
        
        while (pTagged) {
            if (pTagged->pTag == pTag) {
                *pPtr = pTagged->pNext;
                HtmlFree(pTagged);
                eRet = 1;
            } else {
                pPtr = &pTagged->pNext;
            }
            pTagged = *pPtr;
        }
    }

#ifndef NDEBUG
    for (pTagged = pTextNode->pTagged; pTagged ; pTagged = pTagged->pNext) {
        assert(pTagged->pTag != pTag);
    }
#endif

    return eRet;
}

static HtmlTaggedRegion *
findTagInNode(pTextNode, pTag, ppPtr)
    HtmlTextNode *pTextNode;
    HtmlWidgetTag *pTag;
    HtmlTaggedRegion ***ppPtr;
{
    HtmlTaggedRegion *pTagged;
    HtmlTaggedRegion **pPtr = &pTextNode->pTagged;
    for (pTagged = pTextNode->pTagged; pTagged; pTagged = pTagged->pNext) {
        if (pTagged->pTag == pTag) {
            *ppPtr = pPtr;
            return pTagged;
        }
        pPtr = &pTagged->pNext;
    }
    *ppPtr = pPtr;
    return 0;
}

typedef struct TagOpData TagOpData;
struct TagOpData {
    HtmlNode *pFrom;
    int iFrom;
    HtmlNode *pTo;
    int iTo;
    int eSeenFrom;          /* True after pFrom has been traversed */
    HtmlWidgetTag *pTag;

    int isAdd;              /* True for [add] false for [remove] */

    HtmlNode *pFirst;
    HtmlNode *pLast;
    int iFirst;
    int iLast;
};

#define OVERLAP_NONE     1
#define OVERLAP_SUPER    2
#define OVERLAP_SUB      3
#define OVERLAP_FROM     4
#define OVERLAP_TO       5
#define OVERLAP_EXACT    6
static int
getOverlap(pTagged, iFrom, iTo)
    HtmlTaggedRegion *pTagged;
    int iFrom;
    int iTo;
{
    assert(iFrom <= iTo);
    assert(pTagged->iFrom <= pTagged->iTo);

    if (iFrom == pTagged->iFrom && iTo == pTagged->iTo) {
        return OVERLAP_EXACT;
    }
    if (iFrom <= pTagged->iFrom && iTo >= pTagged->iTo) {
        return OVERLAP_SUPER;
    }
    if (iFrom >= pTagged->iFrom && iTo <= pTagged->iTo) {
        return OVERLAP_SUB;
    }
    if (iFrom > pTagged->iTo || iTo < pTagged->iFrom) {
        return OVERLAP_NONE;
    }
    if (iFrom > pTagged->iFrom) {
        assert(iFrom <= pTagged->iTo);
        assert(iTo > pTagged->iTo);
        return OVERLAP_TO;
    }
    assert(iTo >= pTagged->iFrom);
    assert(iTo < pTagged->iTo);
    assert(iFrom < pTagged->iFrom);
    return OVERLAP_FROM;
}


static int
tagAddRemoveCallback(pTree, pNode, clientData)
    HtmlTree *pTree;
    HtmlNode *pNode;
    ClientData clientData;
{
    TagOpData *pData = (TagOpData *)clientData;
    HtmlTextNode *pTextNode = HtmlNodeAsText(pNode);

    if (pNode == pData->pFrom) {
        assert(0 == pData->eSeenFrom);
        pData->eSeenFrom = 1;
    }

    if (pTextNode && pData->eSeenFrom) {
        HtmlTaggedRegion *pTagged;
        HtmlTaggedRegion **pPtr;
        int iFrom = 0;
        int iTo = 1000000;
        if (pNode == pData->pFrom) iFrom = pData->iFrom;
        if (pNode == pData->pTo) iTo = pData->iTo;

        assert(iFrom <= iTo);

        pTagged = findTagInNode(pTextNode, pData->pTag, &pPtr);
        assert(*pPtr == pTagged);

        switch (pData->isAdd) {
            case HTML_TAG_ADD:
                while (pTagged && pTagged->pTag == pData->pTag) {
                    int e = getOverlap(pTagged, iFrom, iTo);
                    pPtr = &pTagged->pNext;
                    if (e != OVERLAP_NONE) {
                        if (0 == pData->pFirst) {
                            if (e == OVERLAP_SUPER || e == OVERLAP_FROM) {
                                pData->pFirst = pNode;
                                pData->iFirst = iFrom;
                            } else if (e == OVERLAP_TO) {
                                pData->pFirst = pNode;
                                pData->iFirst = pTagged->iTo;
                            }
                        }
                        if (e == OVERLAP_TO || e == OVERLAP_SUPER) {
                            pData->pLast = pNode;
                            pData->iLast = iTo;
                        } if (e == OVERLAP_FROM) {
                            pData->pLast = pNode;
                            pData->iLast = pTagged->iFrom;
                        }
                        pTagged->iFrom = MIN(pTagged->iFrom, iFrom);
                        pTagged->iTo = MAX(pTagged->iTo, iTo);
                        break;
                    }
                    pTagged = *pPtr;
                }
                if (!pTagged || pTagged->pTag != pData->pTag) {
                    HtmlTaggedRegion *pNew = (HtmlTaggedRegion *)
                        HtmlClearAlloc("", sizeof(HtmlTaggedRegion));
                    pNew->iFrom = iFrom;
                    pNew->iTo = iTo;
                    pNew->pNext = pTagged;
                    pNew->pTag = pData->pTag;

                    if (!pData->pFirst) {
                        pData->pFirst = pNode;
                        pData->iFirst = iFrom;
                    }
                    pData->pLast = pNode;
                    pData->iLast = iTo;

                    *pPtr = pNew;
                }

                break;

            case HTML_TAG_REMOVE:
                while (pTagged && pTagged->pTag == pData->pTag) {
                    int eOverlap = getOverlap(pTagged, iFrom, iTo);

                    switch (eOverlap) {
                        case OVERLAP_EXACT:
                        case OVERLAP_SUPER: {
                            /* Delete the whole list entry */
                            *pPtr = pTagged->pNext;
                            HtmlFree(pTagged);
                            break;
                        };
                            
                        case OVERLAP_TO:
                            pTagged->iTo = iFrom;
                            pPtr = &pTagged->pNext;
                            break;
                        case OVERLAP_FROM:
                            pTagged->iFrom = iTo;
                            pPtr = &pTagged->pNext;
                            break;

                        case OVERLAP_NONE:
                            /* Do nothing */
                            pPtr = &pTagged->pNext;
                            break;

                        case OVERLAP_SUB: {
                            HtmlTaggedRegion *pNew = (HtmlTaggedRegion *)
                                HtmlClearAlloc("", sizeof(HtmlTaggedRegion));
                            pNew->iFrom = iTo;
                            pNew->iTo = pTagged->iTo;
                            pNew->pTag = pData->pTag;
                            pNew->pNext = pTagged->pNext;
                            pTagged->pNext = pNew;
                            pTagged->iTo = iFrom;
                            pPtr = &pNew->pNext;
                            break;
                        }
                    }
                    pTagged = *pPtr;
                }
                break;
        }
    }

    if (pNode == pData->pTo) {
        return HTML_WALK_ABANDON;
    }
    return HTML_WALK_DESCEND;
}

int 
HtmlTagAddRemoveCmd(clientData, interp, objc, objv, isAdd)
    ClientData clientData;             /* The HTML widget */
    Tcl_Interp *interp;                /* The interpreter */
    int objc;                          /* Number of arguments */
    Tcl_Obj *CONST objv[];             /* List of all arguments */
    int isAdd;
{
    HtmlTree *pTree = (HtmlTree *)clientData;
    HtmlNode *pParent;
    HtmlWidgetTag *pTag;

    TagOpData sData;
    memset(&sData, 0, sizeof(TagOpData));

    assert(isAdd == HTML_TAG_REMOVE || isAdd == HTML_TAG_ADD);

    if (objc != 8) {
        Tcl_WrongNumArgs(interp, 3, objv, 
            "TAGNAME FROM-NODE FROM-INDEX TO-NODE TO-INDEX"
        );
        return TCL_ERROR;
    }
    if (
        0 == (sData.pFrom=HtmlNodeGetPointer(pTree, Tcl_GetString(objv[4]))) ||
        TCL_OK != Tcl_GetIntFromObj(interp, objv[5], &sData.iFrom) ||
        0 == (sData.pTo=HtmlNodeGetPointer(pTree, Tcl_GetString(objv[6]))) ||
        TCL_OK != Tcl_GetIntFromObj(interp, objv[7], &sData.iTo)
    ) {
        return TCL_ERROR;
    }

    /* If either node is an orphan node, throw a Tcl exception. */
    if (HtmlNodeIsOrphan(sData.pFrom)) {
        Tcl_AppendResult(interp, Tcl_GetString(objv[4]), " is an orphan", 0);
        return TCL_ERROR;
    }
    if (HtmlNodeIsOrphan(sData.pTo)) {
        Tcl_AppendResult(interp, Tcl_GetString(objv[6]), " is an orphan", 0);
        return TCL_ERROR;
    }

    pTag = getWidgetTag(pTree, Tcl_GetString(objv[3]), 0);
    sData.pTag = pTag;
    sData.isAdd = isAdd;

    pParent = orderIndexPair(&sData.pFrom,&sData.iFrom,&sData.pTo,&sData.iTo);
    HtmlWalkTree(pTree, pParent, tagAddRemoveCallback, &sData);

    if (isAdd == HTML_TAG_REMOVE) {
        HtmlWidgetDamageText(pTree, 
            sData.pFrom, sData.iFrom,
            sData.pTo, sData.iTo
        );
    } else if (sData.pFirst) {
        assert(sData.pLast);
        HtmlWidgetDamageText(pTree, 
            sData.pFirst, sData.iFirst,
            sData.pLast, sData.iLast
        );
    }

    return TCL_OK;
}

int 
HtmlTagConfigureCmd(clientData, interp, objc, objv)
    ClientData clientData;             /* The HTML widget */
    Tcl_Interp *interp;                /* The interpreter */
    int objc;                          /* Number of arguments */
    Tcl_Obj *CONST objv[];             /* List of all arguments */
{
    HtmlTree *pTree = (HtmlTree *)clientData;
    Tk_OptionTable otab;
    HtmlWidgetTag *pTag;
    Tk_Window win = pTree->tkwin;
    int isNew;

    if (objc < 4) {
        Tcl_WrongNumArgs(interp, 3, objv, "TAGNAME ?options?");
        return TCL_ERROR;
    }

    pTag = getWidgetTag(pTree, Tcl_GetString(objv[3]), &isNew);
    otab = pTree->tagOptionTable;
    assert(otab);
    Tk_SetOptions(interp, (char *)pTag, otab, objc - 4, &objv[4], win, 0, 0);

    if (!isNew) {
        /* Redraw the whole viewport. Todo: Update only the tagged regions */
        HtmlCallbackDamage(pTree, 0, 0, 1000000, 1000000);
    }

    return TCL_OK;
}

struct TagDeleteContext {
    HtmlWidgetTag *pTag; 
    int nOcc;
};
typedef struct TagDeleteContext TagDeleteContext;

static int
tagDeleteCallback(pTree, pNode, clientData)
    HtmlTree *pTree;
    HtmlNode *pNode;
    ClientData clientData;
{
    HtmlTextNode *pTextNode = HtmlNodeAsText(pNode);
    if (pTextNode) {
        TagDeleteContext *p = (TagDeleteContext *)clientData;
        p->nOcc += removeTagFromNode(pTextNode, p->pTag);
    }
    return HTML_WALK_DESCEND;
}

int 
HtmlTagDeleteCmd(clientData, interp, objc, objv)
    ClientData clientData;             /* The HTML widget */
    Tcl_Interp *interp;                /* The interpreter */
    int objc;                          /* Number of arguments */
    Tcl_Obj *CONST objv[];             /* List of all arguments */
{
    const char *zTag;
    Tcl_HashEntry *pEntry;
    HtmlTree *pTree = (HtmlTree *)clientData;
    TagDeleteContext context = {0, 0};

    if (objc != 4) {
        Tcl_WrongNumArgs(interp, 3, objv, "TAGNAME");
        return TCL_ERROR;
    }

    zTag = Tcl_GetString(objv[3]);
    pEntry = Tcl_FindHashEntry(&pTree->aTag, zTag);
    if (pEntry) {
        HtmlWidgetTag *pTag = (HtmlWidgetTag *)Tcl_GetHashValue(pEntry);
        context.pTag = pTag;
        HtmlWalkTree(pTree, 0, tagDeleteCallback, (ClientData)&context);
        HtmlFree(pTag);
        Tcl_DeleteHashEntry(pEntry);
    }

    /* Redraw the whole viewport. Todo: Update only the required regions */
    if (context.nOcc) {
        HtmlCallbackDamage(pTree, 0, 0, 1000000, 1000000);
    }

    return TCL_OK;
}

void
HtmlTagCleanupNode(pTextNode)
    HtmlTextNode *pTextNode;
{
    HtmlTaggedRegion *pTagged = pTextNode->pTagged;
    while (pTagged) {
        HtmlTaggedRegion *pNext = pTagged->pNext;
        HtmlFree(pTagged);
        pTagged = pNext;
    }
    pTextNode->pTagged = 0;
}

void
HtmlTagCleanupTree(pTree)
    HtmlTree *pTree;
{
    Tcl_HashEntry *pEntry;
    Tcl_HashSearch search;
    pEntry = Tcl_FirstHashEntry(&pTree->aTag, &search);
    for ( ; pEntry; pEntry = Tcl_NextHashEntry(&search)) {
        HtmlWidgetTag *pTag = (HtmlWidgetTag *)Tcl_GetHashValue(pEntry);
        Tk_FreeConfigOptions((char *)pTag, pTree->tagOptionTable, pTree->tkwin);
        HtmlFree(pTag);
    }
    Tcl_DeleteHashTable(&pTree->aTag);
}


/*
 * The following two structs are used together to create a data-structure 
 * to store the text-representation of the document.
 *
 */
typedef struct HtmlTextMapping HtmlTextMapping;
struct HtmlTextMapping {
    HtmlTextNode *pTextNode;
    int iStrIndex;             /* Character offset in HtmlText.pObj */
    int iNodeIndex;            /* Byte offset in HtmlTextNode.zText */
    HtmlTextMapping *pNext;
};
struct HtmlText {
    Tcl_Obj *pObj;
    HtmlTextMapping *pMapping;
};

typedef struct HtmlTextInit HtmlTextInit;
struct HtmlTextInit {
    HtmlText *pText;
    int eState;
    int iIdx;
};

#define SEEN_TEXT  0
#define SEEN_SPACE 1
#define SEEN_BLOCK 2

static void
addTextMapping(pText, pTextNode, iNodeIndex, iStrIndex)
    HtmlText *pText;
    HtmlTextNode *pTextNode;
    int iNodeIndex;
    int iStrIndex;
{
    HtmlTextMapping *p;
    p = (HtmlTextMapping *)HtmlAlloc("HtmlTextMapping",sizeof(HtmlTextMapping));
    p->iStrIndex = iStrIndex;
    p->iNodeIndex = iNodeIndex;
    p->pTextNode = pTextNode;
    p->pNext = pText->pMapping;
    pText->pMapping = p;
}

static void
initHtmlText_TextNode(pTree, pTextNode, pInit)
    HtmlTree *pTree;
    HtmlTextNode *pTextNode;
    HtmlTextInit *pInit;
{
    HtmlNode *pNode = &pTextNode->node;
    int isPre = (HtmlNodeComputedValues(pNode)->eWhitespace == CSS_CONST_PRE);

    HtmlTextIter sIter;

    if (pInit->eState == SEEN_BLOCK) {
        Tcl_AppendToObj(pInit->pText->pObj, "\n", 1);
        pInit->iIdx++;
    }
    for (
        HtmlTextIterFirst(pTextNode, &sIter);
        HtmlTextIterIsValid(&sIter);
        HtmlTextIterNext(&sIter)
    ) {
        int eType = HtmlTextIterType(&sIter);
        int nData = HtmlTextIterLength(&sIter);
        char const * zData = HtmlTextIterData(&sIter);

        switch (eType) {
            case HTML_TEXT_TOKEN_NEWLINE:
            case HTML_TEXT_TOKEN_SPACE:
                if (isPre) {
                    int ii;
                    const char *zWhite;
                    zWhite = (eType==HTML_TEXT_TOKEN_SPACE ? " " : "\n");
                    for (ii = 0; ii < nData; ii++) {
                        Tcl_AppendToObj(pInit->pText->pObj, zWhite, 1);
                    }
                    pInit->iIdx += nData;
                    pInit->eState = SEEN_TEXT;
                } else {
                    pInit->eState = MAX(pInit->eState, SEEN_SPACE);
                }
                break;

            case HTML_TEXT_TOKEN_TEXT:
                if (pInit->iIdx > 0 && pInit->eState == SEEN_SPACE) {
                    Tcl_AppendToObj(pInit->pText->pObj, " ", 1);
                    pInit->iIdx++;
                }

                addTextMapping(pTree->pText, 
                    pTextNode, (zData - pTextNode->zText), pInit->iIdx
                );
                Tcl_AppendToObj(pInit->pText->pObj, zData, nData);
                pInit->eState = SEEN_TEXT;
                assert(nData >= 0);
                pInit->iIdx += Tcl_NumUtfChars(zData, nData);
                break;

            default:
                assert(!"Bad return value from HtmlTextIterType()");
        }
    }
}

static void
initHtmlText_Elem(pTree, pElem, pInit)
    HtmlTree *pTree;
    HtmlElementNode *pElem;
    HtmlTextInit *pInit;
{
    HtmlNode *pNode = &pElem->node;
    int eDisplay = HtmlNodeComputedValues(pNode)->eDisplay; 
    int ii;

    /* If the element has "display:none" or a replacement window, do
     * not consider any text children to be part of the text
     * rendering of the document.
     */
    if (
        (eDisplay == CSS_CONST_NONE) ||
        (pElem->pReplacement && pElem->pReplacement->win)
    ) {
        return;
    }

    if (eDisplay != CSS_CONST_INLINE) {
        pInit->eState = SEEN_BLOCK;
    }

    for (ii = 0; ii < HtmlNodeNumChildren(pNode); ii++) {
        HtmlNode *p = HtmlNodeChild(pNode, ii);
        if (HtmlNodeIsText(p)) {
            initHtmlText_TextNode(pTree, HtmlNodeAsText(p), pInit);
        } else {
            initHtmlText_Elem(pTree, HtmlNodeAsElement(p), pInit);
        }
    }

    if (eDisplay != CSS_CONST_INLINE) {
        pInit->eState = SEEN_BLOCK;
    }
}

/*
 *---------------------------------------------------------------------------
 *
 * initHtmlText --
 * 
 *     This function is called to initialise the HtmlText data structure 
 *     at HtmlTree.pText. If the data structure is already initialised
 *     this function is a no-op.
 *
 * Results:
 *     None.
 *
 * Side effects:
 *     None.
 *
 *---------------------------------------------------------------------------
 */
static void
initHtmlText(pTree)
    HtmlTree *pTree;
{
    if (!pTree->pText) {
        HtmlTextInit sInit;
        HtmlCallbackForce(pTree);
        pTree->pText = (HtmlText *)HtmlClearAlloc(0, sizeof(HtmlText));
        memset(&sInit, 0, sizeof(HtmlTextInit));
        sInit.pText = pTree->pText;
        sInit.pText->pObj = Tcl_NewObj();
        Tcl_IncrRefCount(sInit.pText->pObj);
        initHtmlText_Elem(pTree, HtmlNodeAsElement(pTree->pRoot), &sInit);
        Tcl_AppendToObj(sInit.pText->pObj, "\n", 1);
    }
}

void 
HtmlTextInvalidate(pTree)
    HtmlTree *pTree;
{
    if (pTree->pText) {
        HtmlText *pText = pTree->pText;
        HtmlTextMapping *pMapping = pText->pMapping;

        Tcl_DecrRefCount(pTree->pText->pObj);
        while (pMapping) {
            HtmlTextMapping *pNext = pMapping->pNext;
            HtmlFree(pMapping);
            pMapping = pNext;
        }
        HtmlFree(pTree->pText);
        pTree->pText = 0;
    }
}

int
HtmlTextTextCmd(clientData, interp, objc, objv)
    ClientData clientData;             /* The HTML widget */
    Tcl_Interp *interp;                /* The interpreter */
    int objc;                          /* Number of arguments */
    Tcl_Obj *CONST objv[];             /* List of all arguments */
{
    HtmlTree *pTree = (HtmlTree *)clientData;
    if (objc != 3) {
        Tcl_WrongNumArgs(interp, 3, objv, "");
        return TCL_ERROR;
    }
    initHtmlText(pTree);
    Tcl_SetObjResult(interp, pTree->pText->pObj);
    return TCL_OK;
}

/*
 *---------------------------------------------------------------------------
 *
 * HtmlTextIndexCmd --
 * 
 *         $html text index OFFSET ?OFFSET? ?OFFSET?
 *
 *     The argument $OFFSET is an offset into the string returned
 *     by [$html text text]. This Tcl command returns a list of two
 *     elements - the node and node index corresponding to the 
 *     equivalent point in the document tree.
 *
 * Results:
 *     None.
 *
 * Side effects:
 *     None.
 *
 *---------------------------------------------------------------------------
 */
int
HtmlTextIndexCmd(clientData, interp, objc, objv)
    ClientData clientData;             /* The HTML widget */
    Tcl_Interp *interp;                /* The interpreter */
    int objc;                          /* Number of arguments */
    Tcl_Obj *CONST objv[];             /* List of all arguments */
{
    HtmlTree *pTree = (HtmlTree *)clientData;
    int ii;
    Tcl_Obj *p = Tcl_NewObj();

    HtmlTextMapping *pMap = 0;
    int iPrev = 0;
 
    if (objc < 4) {
        Tcl_WrongNumArgs(interp, 3, objv, "OFFSET ?OFFSET? ...");
        return TCL_ERROR;
    }

    initHtmlText(pTree);
    for (ii = objc-1; ii >= 3; ii--) {
        int iIndex;
        if (Tcl_GetIntFromObj(interp, objv[ii], &iIndex)) {
            return TCL_ERROR;
        }
        if (pMap == 0 || iIndex > iPrev) {
            pMap = pTree->pText->pMapping;
        }
        for ( ; pMap; pMap = pMap->pNext) {
            assert(!pMap->pNext || pMap->iStrIndex >= pMap->pNext->iStrIndex);
            if (pMap->iStrIndex <= iIndex || !pMap->pNext) {
                int iNodeIdx = pMap->iNodeIndex; 
                Tcl_Obj *apObj[2];

                int nExtra = iIndex - pMap->iStrIndex;
                char *zExtra = &(pMap->pTextNode->zText[iNodeIdx]);
                iNodeIdx += (Tcl_UtfAtIndex(zExtra, nExtra) - zExtra);

                apObj[0] = HtmlNodeCommand(pTree, &pMap->pTextNode->node);
                apObj[1] = Tcl_NewIntObj(iNodeIdx);
                Tcl_ListObjReplace(0, p, 0, 0, 2, apObj);
                break;
            }
        }
        iPrev = iIndex;
    }

    Tcl_SetObjResult(interp, p);
    return TCL_OK;
}

/*
 *---------------------------------------------------------------------------
 *
 * HtmlTextOffsetCmd --
 * 
 *         $html text index NODE INDEX
 *
 *     Given the supplied node/index pair, return the corresponding offset
 *     in the text representation of the document.
 * 
 *     The INDEX parameter is in bytes. The returned value is in characters.
 *
 * Results:
 *     None.
 *
 * Side effects:
 *     None.
 *
 *---------------------------------------------------------------------------
 */
int
HtmlTextOffsetCmd(clientData, interp, objc, objv)
    ClientData clientData;             /* The HTML widget */
    Tcl_Interp *interp;                /* The interpreter */
    int objc;                          /* Number of arguments */
    Tcl_Obj *CONST objv[];             /* List of all arguments */
{
    HtmlTree *pTree = (HtmlTree *)clientData;
    HtmlTextMapping *pMap;

    /* C interpretations of arguments passed to the Tcl command */
    HtmlNode *pNode;
    HtmlTextNode *pTextNode;
    int iIndex;

    /* Return value for the Tcl command. Anything less than 0 results
     * in an empty string being returned.
     */
    int iRet = -1;

    if (objc != 5) {
        Tcl_WrongNumArgs(interp, 3, objv, "NODE INDEX");
        return TCL_ERROR;
    }
    if (
        0 == (pNode = HtmlNodeGetPointer(pTree, Tcl_GetString(objv[3]))) ||
        TCL_OK != Tcl_GetIntFromObj(interp, objv[4], &iIndex)
    ) {
        return TCL_ERROR;
    }
    if (!(pTextNode = HtmlNodeAsText(pNode))) {
        const char *zNode = Tcl_GetString(objv[3]);
        Tcl_AppendResult(interp, zNode, " is not a text node", 0);
        return TCL_ERROR;
    }

    initHtmlText(pTree);
    for (pMap = pTree->pText->pMapping; pMap; pMap = pMap->pNext) {
        if (pMap->pTextNode == pTextNode && pMap->iNodeIndex <= iIndex) {
            char *zExtra = &pTextNode->zText[pMap->iNodeIndex];
            int nExtra = iIndex - pMap->iNodeIndex;
            iRet = pMap->iStrIndex + Tcl_NumUtfChars(zExtra, nExtra);
            break;
        }
    }

    if (iRet >= 0) {
        Tcl_SetObjResult(interp, Tcl_NewIntObj(iRet));
    }
    return TCL_OK;
}

/*
 *---------------------------------------------------------------------------
 *
 * HtmlTextBboxCmd --
 * 
 *         $html text bbox NODE1 INDEX1 NODE2 INDEX2
 *
 * Results:
 *     None.
 *
 * Side effects:
 *     None.
 *
 *---------------------------------------------------------------------------
 */
int
HtmlTextBboxCmd(clientData, interp, objc, objv)
    ClientData clientData;             /* The HTML widget */
    Tcl_Interp *interp;                /* The interpreter */
    int objc;                          /* Number of arguments */
    Tcl_Obj *CONST objv[];             /* List of all arguments */
{
    HtmlTree *pTree = (HtmlTree *)clientData;
    HtmlNode *pFrom;
    HtmlNode *pTo;
    int iFrom;
    int iTo;

    int iTop, iLeft, iBottom, iRight;

    if (objc != 7) {
        Tcl_WrongNumArgs(interp, 3, objv, 
            "FROM-NODE FROM-INDEX TO-NODE TO-INDEX"
        );
        return TCL_ERROR;
    }
    if (
        0 == (pFrom=HtmlNodeGetPointer(pTree, Tcl_GetString(objv[3]))) ||
        TCL_OK != Tcl_GetIntFromObj(interp, objv[4], &iFrom) ||
        0 == (pTo=HtmlNodeGetPointer(pTree, Tcl_GetString(objv[5]))) ||
        TCL_OK != Tcl_GetIntFromObj(interp, objv[6], &iTo)
    ) {
        return TCL_ERROR;
    }
    orderIndexPair(&pFrom, &iFrom, &pTo, &iTo);

    HtmlWidgetBboxText(pTree, pFrom, iFrom, pTo, iTo, 
        &iTop, &iLeft, &iBottom, &iRight
    );
    if (iTop < iBottom && iLeft < iRight) {
        Tcl_Obj *pRes = Tcl_NewObj();
        Tcl_ListObjAppendElement(0, pRes, Tcl_NewIntObj(iLeft));
        Tcl_ListObjAppendElement(0, pRes, Tcl_NewIntObj(iTop));
        Tcl_ListObjAppendElement(0, pRes, Tcl_NewIntObj(iRight));
        Tcl_ListObjAppendElement(0, pRes, Tcl_NewIntObj(iBottom));
        Tcl_SetObjResult(interp, pRes);
    }

    return TCL_OK;
}

/*
 * NOTES ON INTERNALS OF HtmlTextNode:
 * 
 *     The internals of the HtmlTextNode structure should be accessed 
 *     via the following API:
 *
 *         HtmlTextNew()
 *         HtmlTextFree()
 *
 *         HtmlTextIterFirst
 *         HtmlTextIterIsValid
 *         HtmlTextIterNext
 *
 *         HtmlTextIterType
 *         HtmlTextIterLength
 *         HtmlTextIterData
 *
 *         HtmlNodeIsWhitespace
 *
 *         HtmlTextCombine()
 *     
 *     An HtmlTextNode object stores it's text in two parts:
 *
 *         * A character string with SGML escape sequences replaced their
 *           UTF-8 equivalents and each block of whitespace replaced by
 *           a single space character.
 *
 *         * An ordered list of tokens. Each token one of the following:
 *           + An unwrappable block of text (i.e. a word),
 *           + One or more newline characters, or
 *           + One or more space characters.
 *
 *           Each token is represented by an instance of struct 
 *           HtmlTextToken. It has 1 byte type and a 1 byte unsigned 
 *           length indicating the number of bytes, spaces or 
 *           newlines represented by the token.
 *
 *     The following block of text:
 *
 *         "abcde   <NEWLINE>&gt;&lt;<NEWLINE><NEWLINE>hello"
 *
 *     Is represented by the data structures:
 *
 *         HtmlTextNode.aToken = {
 *              {TEXT, 5}, {SPACE, 3}, {NEWLINE, 1}, 
 *              {TEXT, 2}, {NEWLINE 2},
 *              {TEXT, 5},
 *              {END, <unused>},
 *         }
 *         HtmlTextNode.zText  = "abcde <> hello"
 *
 *     Storing the text in this format means that we are well-placed
 *     to rationalise a good percentage calls to Tk_DrawChars() etc. in 
 *     other parts of the widget code.
 *
 *     Blocks of contiguous space or newline characters longer than 255
 *     characters (the maximum value of HtmlTextToken.n) are stored
 *     as two or more contiguous SPACE tokens. i.e. 650 contiguous spaces
 *     require the following three tokens in the aToken array:
 *
 *         {SPACE, 255}, {SPACE, 255}, {SPACE, 140}
 *
 *     Blocks of non-whitespace longer than 255 characters are trickier.
 *     They always require exactly three tokens to be added to the array.
 *     For a 650 byte block of text the following three tokens:
 *
 *         {LONGTEXT, {650 >> 16} & 0xFF}, 
 *         {LONGTEXT, {650 >>  8} & 0xFF}, 
 *         {LONGTEXT, {650 >>  0} & 0xFF}
 *
 *     If a node consists entirely of white-space, then the HtmlTextNode.zText
 *     string is zero bytes in length. In this case HtmlTextNode.zText is
 *     set to NULL, to speed up checking if the node consists entirely
 *     of whitespace.
 *
 *     Todo: It's tempting to use single byte tokens, instead of two. Three
 *     bits for the type and five for the length. On the other hand,
 *     premature optimization.....
 */
struct HtmlTextToken {
    unsigned char n;
    unsigned char eType;
};

/* Return true if the argument is a unicode codpoint that should be handled
 * as a 'cjk' character.
 */
#define ISCJK(ii) ((ii)>=0x3000 && (ii)<=0x9fff)

/*
 *---------------------------------------------------------------------------
 *
 * utf8Read --
 * 
 *     Decode a single UTF8 character from the buffer pointed to by z.
 *
 * Results:
 *     Unicode codepoint of read character, or 0 if the end of the buffer
 *     has been reached.
 *
 * Side effects:
 *     None.
 *
 *---------------------------------------------------------------------------
 */
static Tcl_UniChar utf8Read(
  const unsigned char *z,         /* first byte of utf-8 character */
  const unsigned char *zTerm,     /* pretend this byte is 0x00 */
  const unsigned char **pzNext    /* write first byte past utf-8 char here */
){
    static const unsigned char UtfTrans[] = {
        0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07,
        0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f,
        0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17,
        0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f,
        0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07,
        0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f,
        0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07,
        0x00, 0x01, 0x02, 0x03, 0x00, 0x01, 0x00, 0x00,
    };

    unsigned int c = 0;
    if (zTerm>z) {
        c = (unsigned int)*z;
        if ((c&0xC0)==0xC0) {
            const unsigned char *zCsr = &z[1];
            c = UtfTrans[c-0xC0];
            while (zCsr!=zTerm && ((*zCsr)&0xC0)==0x80){
                c = (c << 6) + ((*zCsr)&0x3F);
                zCsr++;
            }
            *pzNext = zCsr;
        } else {
            *pzNext = &z[1];
        }
    } else {
      *pzNext = zTerm;
    }
  
    return c;
}

/*
 *---------------------------------------------------------------------------
 *
 * tokenLength --
 * 
 *     Argument zToken points at the start of a text token (a non-whitespace
 *     character). This function returns the number of bytes in the token.
 *     zEnd points to 1 byte passed the end of the buffer - reading *zEnd
 *     would be a seg-fault.
 *
 * Results:
 *     Length of token at zToken in bytes.
 *
 * Side effects:
 *     None.
 *
 *---------------------------------------------------------------------------
 */
static int 
tokenLength(zToken, zEnd)
    const unsigned char *zToken;
    const unsigned char *zEnd;
{
    Tcl_UniChar iChar = 0;
    const unsigned char *zCsr = zToken;
    const unsigned char *zNext = zCsr;

    iChar = utf8Read(zCsr, zEnd, &zNext);
    while (iChar && (iChar >= 256 || !ISSPACE(iChar)) && !ISCJK(iChar)){
      zCsr = zNext;
      iChar = utf8Read(zCsr, zEnd, &zNext);
    }

    return ((zCsr==zToken)?zNext:zCsr)-zToken;
}

/*
 *---------------------------------------------------------------------------
 *
 * populateTextNode --
 * 
 *     This function is called to tokenize a block of document text into 
 *     an HtmlTextNode structure. It is a helper function for HtmlTextNew().
 *
 *     This function is designed to be called twice for each block of text
 *     parsed to an HtmlTextNode. The first time, it determines the space
 *     (number of tokens and number of bytes of text) required for the
 *     the new HtmlTextNode. The caller then allocates this space and
 *     calls the function a second time to populate the new structure.
 *
 * Results:
 *     None.
 *
 * Side effects:
 *
 *---------------------------------------------------------------------------
 */
static void
populateTextNode(n, z, pText, pnToken, pnText)
    int n;                     /* Length of input text */
    char const *z;             /* Input text */
    HtmlTextNode *pText;       /* OUT: The structure to populate (or NULL) */
    int *pnToken;              /* OUT: Number of tokens required (or used) */
    int *pnText;               /* OUT: Bytes of text required (or used) */
{
    char const *zCsr = z;
    char const *zStop = &z[n];

    /* A running count of the number of tokens and bytes of text storage
     * required to store the parsed form of the input text.
     */
    int nToken = 0;
    int nText = 0;

    /* This variable is used to expand tabs. */
    int iCol = 0;

    int isPrevTokenText = 0;

    while (zCsr < zStop) {
        unsigned char c = (int)(*zCsr);
        char const *zStart = zCsr;

        if (ISSPACE(c)) {

            int nSpace = 0;                    /* Eventual token length */
            int eType = HTML_TEXT_TOKEN_SPACE; /* Eventual token type */

            if (ISNEWLINE(c)) {
                eType = HTML_TEXT_TOKEN_NEWLINE;
            }

            do {
                /* If a tab character, this is equivalent to adding between
                 * one and eight spaces, depending on the current value of
                 * variable iCol (see comments above variable declaration). 
                 */
                if (ISTAB(*zCsr)) nSpace += (7 - (iCol%8));

                /* The sequence CR (carraige return) followed by LF (line 
                 * feed) counts as a single newline. If either is encountered
                 * alone, this is also a single newline. LF followed by CR
                 * is two newlines.
                 */
                if (zCsr[0] == '\r' && &zCsr[1] < zStop && zCsr[1] == '\n') {
                    zCsr++;
                }

                nSpace++;
                zCsr++;
                iCol += nSpace;
            } while (
                zCsr < zStop && nSpace < (255 - 8) && ISSPACE(*zCsr) && (
                    (eType == HTML_TEXT_TOKEN_NEWLINE && ISNEWLINE(*zCsr)) ||
                    (eType == HTML_TEXT_TOKEN_SPACE && !ISNEWLINE(*zCsr))
                )
            );

            if (eType == HTML_TEXT_TOKEN_NEWLINE) {
                iCol = 0;
            }

            assert(nSpace <= 255);
            if (pText) {
                pText->aToken[nToken].n = nSpace;
                pText->aToken[nToken].eType = eType;
            }
            nToken++;

            /* If the previous token was text, add a single space character
             * to the HtmlTextNode.zText buffer. Otherwise, add nothing
             * to the text buffer.
             */
            if (isPrevTokenText) {
                if (pText) {
                    pText->zText[nText] = ' ';
                }
                nText++;
                isPrevTokenText = 0;
            }
        } else {

            /* This block sets nThisText to the number of bytes (not 
             * characters) in the token starting at zStart. zCsr is
             * left pointing to the byte immediately after the token.
             */
            int nThisText = tokenLength(
                (unsigned char *)zCsr, (unsigned char *)zStop
            );
            assert(zCsr == zStart);
            assert(nThisText>0);
            zCsr = &zCsr[nThisText];

            if (nThisText > 255) {
                if (pText) {
                    pText->aToken[nToken].eType = HTML_TEXT_TOKEN_LONGTEXT;
                    pText->aToken[nToken+1].eType = HTML_TEXT_TOKEN_LONGTEXT;
                    pText->aToken[nToken+2].eType = HTML_TEXT_TOKEN_LONGTEXT;
                    pText->aToken[nToken].n = ((nThisText >> 16) & 0x000000FF);
                    pText->aToken[nToken+1].n = ((nThisText >> 8) & 0x000000FF);
                    pText->aToken[nToken+2].n = (nThisText & 0x000000FF);
                    memcpy(&pText->zText[nText], zStart, nThisText);
                }
                nToken += 3;
            } else {
                if (pText) {
                    pText->aToken[nToken].eType = HTML_TEXT_TOKEN_TEXT;
                    pText->aToken[nToken].n = nThisText;
                    memcpy(&pText->zText[nText], zStart, nThisText);
                }
                nToken++;
            }

            nText += nThisText;
            isPrevTokenText = 1;
            iCol += nThisText;
        }
    }

    /* Add the terminator token */
    if (pText) {
        pText->aToken[nToken].eType = HTML_TEXT_TOKEN_END;
    }
    nToken++;

    if (pnToken) *pnToken = nToken;
    if (pnText) *pnText = nText;
}

void
HtmlTextSet(pText, n, z, isTrimEnd, isTrimStart)
    HtmlTextNode *pText;
    int n;
    const char *z;
    int isTrimEnd;
    int isTrimStart;
{
    char *z2;
    HtmlTextToken *pFinal;

    int nText = 0;
    int nToken = 0;
    int nAlloc;                /* Number of bytes allocated */

    if (pText->aToken) {
        HtmlFree(pText->aToken);
    }

    /* Make a temporary copy of the text and translate any embedded html 
     * escape characters (i.e. "&nbsp;"). Todo: Avoid this copy by changing
     * populateTextNode() so that it deals with escapes.
     */
    z2 = (char *)HtmlAlloc("temp", n + 1);
    memcpy(z2, z, n);
    z2[n] = '\0';
    HtmlTranslateEscapes(z2);

    /* Figure out how much space is required for this HtmlTextNode. */
    populateTextNode(strlen(z2), z2, 0, &nToken, &nText);
    assert(nText >= 0 && nToken > 0);

    /* Allocate space for HtmlTextNode.aToken and HtmlTextNode.zText */
    nAlloc = nText + (nToken * sizeof(HtmlTextToken));
    pText->aToken = (HtmlTextToken *)HtmlClearAlloc("TextNode.aToken", nAlloc);
    if (nText > 0) {
        pText->zText = (char *)&pText->aToken[nToken];
    } else {
        /* If the node is all white-space, set HtmlTextNode.zText to NULL */
        pText->zText = 0;
    }

    /* Populate the HtmlTextNode.aToken and zText arrays. */
    populateTextNode(strlen(z2), z2, pText, 0, 0);
    HtmlFree(z2);

    assert(pText->aToken[nToken-1].eType == HTML_TEXT_TOKEN_END);
    pFinal = &pText->aToken[nToken-2];
    if (isTrimEnd && pFinal->eType == HTML_TEXT_TOKEN_NEWLINE) {
        pFinal->n--;
        if( pFinal->n==0 ){
            pFinal->eType = HTML_TEXT_TOKEN_END;
            nToken--;
        }
    }
    if (isTrimStart && pText->aToken[0].eType == HTML_TEXT_TOKEN_NEWLINE) {
        memmove(pText->aToken, &pText->aToken[1], sizeof(HtmlTextToken)*nToken);
    }

#ifndef NDEBUG
    /* This assert() block checks the following:
     *
     *     1) If there is nothing but white-space in this node, then
     *        HtmlTextNode.zText is set to NULL.
     *     2) If there are any text elements in the node HtmlTextNode.zText 
     *        is not set to NULL.
     *
     * In other words, the node is either white-space or not. This test is
     * included because I am paranoid the optimized HtmlNodeIsWhitespace() 
     * test (pText->zText==0) will malfunction one day.
     */
    if (1) {
        int haveText = 0;
        HtmlTextIter sIter;
        HtmlTextIterFirst(pText, &sIter);
        for ( ; HtmlTextIterIsValid(&sIter); HtmlTextIterNext(&sIter)) {
            if (HtmlTextIterType(&sIter) == HTML_TEXT_TOKEN_TEXT) {
                haveText = 1;
            }
        }
        assert(
            (!haveText && pText->zText == 0) ||        /* white-space */
            (haveText && pText->zText)                 /* not white-space */
        );
    }
#endif
}

HtmlTextNode *
HtmlTextNew(n, z, isTrimEnd, isTrimStart)
    int n;
    const char *z;
    int isTrimEnd;
    int isTrimStart;
{
    HtmlTextNode *pText;

    /* Allocate space for the HtmlTextNode. */ 
    pText = HtmlNew(HtmlTextNode);

    HtmlTextSet(pText, n, z, isTrimEnd, isTrimStart);
    return pText;
}

/*
 *---------------------------------------------------------------------------
 *
 * HtmlTextCombine --
 * 
 * Results:
 *
 * Side effects:
 *
 *---------------------------------------------------------------------------
 */
#if 0
static HtmlTextNode *
HtmlTextCombine(p1, p2)
    HtmlTextNode *p1;
    HtmlTextNode *p2;
{
    /* HtmlTextNode *pNew; */
    return 0;
}
#endif

/*
 *---------------------------------------------------------------------------
 *
 * HtmlTextFree --
 * 
 *     Free a text-node structure allocated by HtmlTextNew().
 *
 * Results:
 *     None.
 *
 * Side effects:
 *     Text-node p is deleted.
 *
 *---------------------------------------------------------------------------
 */
void 
HtmlTextFree(p)
    HtmlTextNode *p;
{
    HtmlFree(p);
}

void
HtmlTextIterFirst(pTextNode, pTextIter)
    HtmlTextNode *pTextNode;
    HtmlTextIter *pTextIter;
{
    pTextIter->pTextNode = pTextNode;
    pTextIter->iText = 0;
    pTextIter->iToken = 0;
}

int
HtmlTextIterIsValid(pTextIter)
    HtmlTextIter *pTextIter;
{
    HtmlTextToken *p = &pTextIter->pTextNode->aToken[pTextIter->iToken];
    return (p->eType != HTML_TEXT_TOKEN_END) ? 1 : 0;
}

void
HtmlTextIterNext(pTextIter)
    HtmlTextIter *pTextIter;
{
    HtmlTextToken *p = &pTextIter->pTextNode->aToken[pTextIter->iToken];
    int eType = p[0].eType;
    int eNext = p[1].eType;

    assert(eType != HTML_TEXT_TOKEN_END);

    if (eType == HTML_TEXT_TOKEN_TEXT) {
        pTextIter->iText += p->n;
    }
    else if (eType == HTML_TEXT_TOKEN_LONGTEXT) {
        int n = (p[0].n << 16) + (p[1].n << 8) + p[2].n;
        pTextIter->iText += n;
        pTextIter->iToken += 2;
    }

    if ((eType == HTML_TEXT_TOKEN_TEXT || eType == HTML_TEXT_TOKEN_LONGTEXT) &&
        (eNext != HTML_TEXT_TOKEN_TEXT && eNext != HTML_TEXT_TOKEN_LONGTEXT)
    ) {
        pTextIter->iText++;
    }

    pTextIter->iToken++;
}

int
HtmlTextIterIsLast(pTextIter)
    HtmlTextIter *pTextIter;
{
    HtmlTextIter sIter;
    memcpy(&sIter, pTextIter, sizeof(HtmlTextIter));
    HtmlTextIterNext(&sIter);
    return !HtmlTextIterIsValid(&sIter);
}

int 
HtmlTextIterType(pTextIter)
    HtmlTextIter *pTextIter;
{
    HtmlTextToken *p = &pTextIter->pTextNode->aToken[pTextIter->iToken];
    if (p->eType == HTML_TEXT_TOKEN_LONGTEXT) return HTML_TEXT_TOKEN_TEXT;
    return (int)(p->eType);
}

int 
HtmlTextIterLength(pTextIter)
    HtmlTextIter *pTextIter;
{
    HtmlTextToken *p = &pTextIter->pTextNode->aToken[pTextIter->iToken];
    if (p->eType == HTML_TEXT_TOKEN_LONGTEXT) {
        int n = (p[0].n << 16) + (p[1].n << 8) + p[2].n;
        return n;
    }
    return (int)(p->n);
}

const char *
HtmlTextIterData(pTextIter)
    HtmlTextIter *pTextIter;
{
    return (const char *)(&pTextIter->pTextNode->zText[pTextIter->iText]);
}