about summary refs log tree commit diff stats
path: root/src/LYCharUtils.c
blob: 5baa5a7fdf4b2d01bb6c9858b14030dbe9a59834 (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
3021
3022
3023
3024
3025
3026
3027
3028
3029
3030
3031
3032
3033
3034
3035
3036
3037
3038
3039
3040
3041
3042
3043
3044
3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087
3088
3089
3090
3091
3092
3093
3094
3095
3096
3097
3098
3099
3100
3101
3102
3103
3104
3105
3106
3107
3108
3109
3110
3111
3112
3113
3114
3115
3116
3117
3118
3119
3120
3121
3122
3123
3124
3125
3126
3127
3128
3129
3130
3131
3132
3133
3134
3135
3136
3137
3138
3139
3140
3141
3142
3143
3144
3145
3146
3147
3148
3149
3150
3151
3152
3153
3154
3155
3156
3157
3158
3159
3160
3161
3162
3163
3164
3165
3166
3167
3168
3169
3170
3171
3172
3173
3174
3175
3176
3177
3178
3179
3180
3181
3182
3183
3184
3185
3186
3187
3188
3189
3190
3191
3192
3193
3194
3195
3196
3197
3198
3199
3200
3201
3202
3203
3204
3205
3206
3207
3208
3209
3210
3211
3212
3213
3214
3215
3216
3217
3218
3219
3220
3221
3222
3223
3224
3225
3226
3227
3228
3229
3230
3231
3232
3233
3234
3235
3236
3237
3238
3239
3240
3241
3242
3243
3244
3245
3246
3247
3248
3249
3250
3251
3252
3253
3254
3255
3256
3257
3258
3259
3260
3261
3262
3263
3264
3265
3266
3267
3268
3269
3270
3271
3272
3273
3274
3275
3276
3277
3278
3279
3280
3281
3282
3283
3284
3285
3286
3287
3288
3289
3290
3291
3292
3293
3294
3295
3296
3297
3298
3299
3300
3301
3302
3303
3304
3305
3306
3307
3308
3309
3310
3311
3312
3313
3314
3315
3316
3317
3318
3319
3320
3321
3322
3323
3324
3325
3326
3327
3328
3329
3330
3331
3332
3333
3334
3335
3336
3337
3338
3339
3340
3341
3342
3343
3344
3345
3346
3347
3348
3349
3350
3351
3352
3353
3354
3355
3356
3357
3358
3359
3360
3361
3362
3363
3364
3365
3366
3367
3368
3369
3370
3371
3372
3373
3374
3375
3376
3377
3378
3379
3380
3381
3382
3383
3384
3385
3386
3387
3388
3389
3390
3391
3392
3393
3394
3395
3396
3397
3398
3399
3400
3401
3402
3403
3404
3405
3406
3407
3408
3409
3410
3411
3412
3413
3414
3415
3416
3417
3418
3419
3420
3421
3422
3423
3424
3425
3426
3427
3428
3429
3430
3431
3432
3433
3434
3435
3436
3437
3438
3439
3440
3441
3442
3443
3444
3445
3446
3447
3448
3449
3450
3451
3452
/*
 * $LynxId: LYCharUtils.c,v 1.114 2011/10/07 00:57:58 Kihara.Hideto Exp $
 *
 *  Functions associated with LYCharSets.c and the Lynx version of HTML.c - FM
 *  ==========================================================================
 */
#include <HTUtils.h>
#include <SGML.h>

#define Lynx_HTML_Handler
#include <HTChunk.h>
#include <HText.h>
#include <HTStyle.h>
#include <HTMIME.h>
#include <HTML.h>

#include <HTCJK.h>
#include <HTAtom.h>
#include <HTMLGen.h>
#include <HTParse.h>
#include <UCMap.h>
#include <UCDefs.h>
#include <UCAux.h>

#include <LYGlobalDefs.h>
#include <LYCharUtils.h>
#include <LYCharSets.h>

#include <HTAlert.h>
#include <HTForms.h>
#include <HTNestedList.h>
#include <GridText.h>
#include <LYStrings.h>
#include <LYUtils.h>
#include <LYMap.h>
#include <LYBookmark.h>
#include <LYCurses.h>
#include <LYCookie.h>

#include <LYexit.h>
#include <LYLeaks.h>

/*
 * Used for nested lists.  - FM
 */
int OL_CONTINUE = -29999;	/* flag for whether CONTINUE is set */
int OL_VOID = -29998;		/* flag for whether a count is set */

/*
 *  This function converts any ampersands in allocated
 *  strings to "&amp;".  If isTITLE is TRUE, it also
 *  converts any angle-brackets to "&lt;" or "&gt;". - FM
 */
void LYEntify(char **str,
	      int isTITLE)
{
    char *p = *str;
    char *q = NULL, *cp = NULL;
    int amps = 0, lts = 0, gts = 0;

#ifdef CJK_EX
    enum _state {
	S_text,
	S_esc,
	S_dollar,
	S_paren,
	S_nonascii_text,
	S_dollar_paren
    } state = S_text;
    int in_sjis = 0;
#endif

    if (isEmpty(p))
	return;

    /*
     * Count the ampersands.  - FM
     */
    while ((*p != '\0') && (q = strchr(p, '&')) != NULL) {
	amps++;
	p = (q + 1);
    }

    /*
     * Count the left-angle-brackets, if needed.  - FM
     */
    if (isTITLE == TRUE) {
	p = *str;
	while ((*p != '\0') && (q = strchr(p, '<')) != NULL) {
	    lts++;
	    p = (q + 1);
	}
    }

    /*
     * Count the right-angle-brackets, if needed.  - FM
     */
    if (isTITLE == TRUE) {
	p = *str;
	while ((*p != '\0') && (q = strchr(p, '>')) != NULL) {
	    gts++;
	    p = (q + 1);
	}
    }

    /*
     * Check whether we need to convert anything.  - FM
     */
    if (amps == 0 && lts == 0 && gts == 0)
	return;

    /*
     * Allocate space and convert.  - FM
     */
    q = typecallocn(char,
		    (strlen(*str)
		     + (unsigned)(4 * amps)
		     + (unsigned)(3 * lts)
		     + (unsigned)(3 * gts) + 1));
    if ((cp = q) == NULL)
	outofmem(__FILE__, "LYEntify");

    assert(cp != NULL);
    assert(q != NULL);

    for (p = *str; *p; p++) {
#ifdef CJK_EX
	if (IS_CJK_TTY) {
	    switch (state) {
	    case S_text:
		if (*p == '\033') {
		    state = S_esc;
		    *q++ = *p;
		    continue;
		}
		break;

	    case S_esc:
		if (*p == '$') {
		    state = S_dollar;
		    *q++ = *p;
		    continue;
		} else if (*p == '(') {
		    state = S_paren;
		    *q++ = *p;
		    continue;
		} else {
		    state = S_text;
		    *q++ = *p;
		    continue;
		}

	    case S_dollar:
		if (*p == '@' || *p == 'B' || *p == 'A') {
		    state = S_nonascii_text;
		    *q++ = *p;
		    continue;
		} else if (*p == '(') {
		    state = S_dollar_paren;
		    *q++ = *p;
		    continue;
		} else {
		    state = S_text;
		    *q++ = *p;
		    continue;
		}

	    case S_dollar_paren:
		if (*p == 'C') {
		    state = S_nonascii_text;
		    *q++ = *p;
		    continue;
		} else {
		    state = S_text;
		    *q++ = *p;
		    continue;
		}

	    case S_paren:
		if (*p == 'B' || *p == 'J' || *p == 'T') {
		    state = S_text;
		    *q++ = *p;
		    continue;
		} else if (*p == 'I') {
		    state = S_nonascii_text;
		    *q++ = *p;
		    continue;
		}
		/* FALLTHRU */

	    case S_nonascii_text:
		if (*p == '\033')
		    state = S_esc;
		*q++ = *p;
		continue;

	    default:
		break;
	    }
	    if (*(p + 1) != '\0' &&
		(IS_EUC(UCH(*p), UCH(*(p + 1))) ||
		 IS_SJIS(UCH(*p), UCH(*(p + 1)), in_sjis) ||
		 IS_BIG5(UCH(*p), UCH(*(p + 1))))) {
		*q++ = *p++;
		*q++ = *p;
		continue;
	    }
	}
#endif
	if (*p == '&') {
	    *q++ = '&';
	    *q++ = 'a';
	    *q++ = 'm';
	    *q++ = 'p';
	    *q++ = ';';
	} else if (isTITLE && *p == '<') {
	    *q++ = '&';
	    *q++ = 'l';
	    *q++ = 't';
	    *q++ = ';';
	} else if (isTITLE && *p == '>') {
	    *q++ = '&';
	    *q++ = 'g';
	    *q++ = 't';
	    *q++ = ';';
	} else {
	    *q++ = *p;
	}
    }
    *q = '\0';
    FREE(*str);
    *str = cp;
}

/*
 * Callers to LYEntifyTitle/LYEntifyValue do not look at the 'target' param.
 * Optimize things a little by avoiding the memory allocation if not needed,
 * as is usually the case.
 */
static BOOL MustEntify(const char *source)
{
    BOOL result;

#ifdef CJK_EX
    if (IS_CJK_TTY && strchr(source, '\033') != 0) {
	result = TRUE;
    } else
#endif
    {
	size_t length = strlen(source);
	size_t reject = strcspn(source, "<&>");

	result = (BOOL) (length != reject);
    }

    return result;
}

/*
 * Wrappers for LYEntify() which do not assume that the source was allocated,
 * e.g., output from gettext().
 */
const char *LYEntifyTitle(char **target, const char *source)
{
    const char *result = 0;

    if (MustEntify(source)) {
	StrAllocCopy(*target, source);
	LYEntify(target, TRUE);
	result = *target;
    } else {
	result = source;
    }
    return result;
}

const char *LYEntifyValue(char **target, const char *source)
{
    const char *result = 0;

    if (MustEntify(source)) {
	StrAllocCopy(*target, source);
	LYEntify(target, FALSE);
	result = *target;
    } else {
	result = source;
    }
    return result;
}

/*
 *  This function trims characters <= that of a space (32),
 *  including HT_NON_BREAK_SPACE (1) and HT_EN_SPACE (2),
 *  but not ESC, from the heads of strings. - FM
 */
void LYTrimHead(char *str)
{
    const char *s = str;

    if (isEmpty(s))
	return;

    while (*s && WHITE(*s) && UCH(*s) != UCH(CH_ESC))	/* S/390 -- gil -- 1669 */
	s++;
    if (s > str) {
	char *ns = str;

	while (*s) {
	    *ns++ = *s++;
	}
	*ns = '\0';
    }
}

/*
 *  This function trims characters <= that of a space (32),
 *  including HT_NON_BREAK_SPACE (1), HT_EN_SPACE (2), and
 *  ESC from the tails of strings. - FM
 */
void LYTrimTail(char *str)
{
    int i;

    if (isEmpty(str))
	return;

    i = (int) strlen(str) - 1;
    while (i >= 0) {
	if (WHITE(str[i]))
	    str[i] = '\0';
	else
	    break;
	i--;
    }
}

/*
 * This function should receive a pointer to the start
 * of a comment.  It returns a pointer to the end ('>')
 * character of comment, or it's best guess if the comment
 * is invalid. - FM
 */
char *LYFindEndOfComment(char *str)
{
    char *cp, *cp1;
    enum comment_state {
	start1,
	start2,
	end1,
	end2
    } state;

    if (str == NULL)
	/*
	 * We got NULL, so return NULL.  - FM
	 */
	return NULL;

    if (StrNCmp(str, "<!--", 4))
	/*
	 * We don't have the start of a comment, so return the beginning of the
	 * string.  - FM
	 */
	return str;

    cp = (str + 4);
    if (*cp == '>')
	/*
	 * It's an invalid comment, so
	 * return this end character. - FM
	 */
	return cp;

    if ((cp1 = strchr(cp, '>')) == NULL)
	/*
	 * We don't have an end character, so return the beginning of the
	 * string.  - FM
	 */
	return str;

    if (*cp == '-')
	/*
	 * Ugh, it's a "decorative" series of dashes, so return the next end
	 * character.  - FM
	 */
	return cp1;

    /*
     * OK, we're ready to start parsing.  - FM
     */
    state = start2;
    while (*cp != '\0') {
	switch (state) {
	case start1:
	    if (*cp == '-')
		state = start2;
	    else
		/*
		 * Invalid comment, so return the first '>' from the start of
		 * the string.  - FM
		 */
		return cp1;
	    break;

	case start2:
	    if (*cp == '-')
		state = end1;
	    break;

	case end1:
	    if (*cp == '-')
		state = end2;
	    else
		/*
		 * Invalid comment, so return the first '>' from the start of
		 * the string.  - FM
		 */
		return cp1;
	    break;

	case end2:
	    if (*cp == '>')
		/*
		 * Valid comment, so return the end character.  - FM
		 */
		return cp;
	    if (*cp == '-') {
		state = start1;
	    } else if (!(WHITE(*cp) && UCH(*cp) != UCH(CH_ESC))) {	/* S/390 -- gil -- 1686 */
		/*
		 * Invalid comment, so return the first '>' from the start of
		 * the string.  - FM
		 */
		return cp1;
	    }
	    break;

	default:
	    break;
	}
	cp++;
    }

    /*
     * Invalid comment, so return the first '>' from the start of the string. 
     * - FM
     */
    return cp1;
}

/*
 *  If an HREF, itself or if resolved against a base,
 *  represents a file URL, and the host is defaulted,
 *  force in "//localhost".  We need this until
 *  all the other Lynx code which performs security
 *  checks based on the "localhost" string is changed
 *  to assume "//localhost" when a host field is not
 *  present in file URLs - FM
 */
void LYFillLocalFileURL(char **href,
			const char *base)
{
    char *temp = NULL;

    if (isEmpty(*href))
	return;

    if (!strcmp(*href, "//") || !StrNCmp(*href, "///", 3)) {
	if (base != NULL && isFILE_URL(base)) {
	    StrAllocCopy(temp, STR_FILE_URL);
	    StrAllocCat(temp, *href);
	    StrAllocCopy(*href, temp);
	}
    }
    if (isFILE_URL(*href)) {
	if (*(*href + 5) == '\0') {
	    StrAllocCat(*href, "//localhost");
	} else if (!strcmp(*href, "file://")) {
	    StrAllocCat(*href, "localhost");
	} else if (!StrNCmp(*href, "file:///", 8)) {
	    StrAllocCopy(temp, (*href + 7));
	    LYLocalFileToURL(href, temp);
	} else if (!StrNCmp(*href, "file:/", 6) && !LYIsHtmlSep(*(*href + 6))) {
	    StrAllocCopy(temp, (*href + 5));
	    LYLocalFileToURL(href, temp);
	}
    }
#if defined(USE_DOS_DRIVES)
    if (LYIsDosDrive(*href)) {
	/*
	 * If it's a local DOS path beginning with drive letter,
	 * add file://localhost/ prefix and go ahead.
	 */
	StrAllocCopy(temp, *href);
	LYLocalFileToURL(href, temp);
    }

    /* use below: strlen("file://localhost/") = 17 */
    if (!StrNCmp(*href, "file://localhost/", 17)
	&& (strlen(*href) == 19)
	&& LYIsDosDrive(*href + 17)) {
	/*
	 * Terminate DOS drive letter with a slash to surf root successfully.
	 * Here seems a proper place to do so.
	 */
	LYAddPathSep(href);
    }
#endif /* USE_DOS_DRIVES */

    /*
     * No path in a file://localhost URL means a
     * directory listing for the current default. - FM
     */
    if (!strcmp(*href, "file://localhost")) {
	const char *temp2;

#ifdef VMS
	temp2 = HTVMS_wwwName(LYGetEnv("PATH"));
#else
	char curdir[LY_MAXPATH];

	temp2 = wwwName(Current_Dir(curdir));
#endif /* VMS */
	if (!LYIsHtmlSep(*temp2))
	    LYAddHtmlSep(href);
	/*
	 * Check for pathological cases - current dir has chars which MUST BE
	 * URL-escaped - kw
	 */
	if (strchr(temp2, '%') != NULL || strchr(temp2, '#') != NULL) {
	    FREE(temp);
	    temp = HTEscape(temp2, URL_PATH);
	    StrAllocCat(*href, temp);
	} else {
	    StrAllocCat(*href, temp2);
	}
    }
#ifdef VMS
    /*
     * On VMS, a file://localhost/ URL means
     * a listing for the login directory. - FM
     */
    if (!strcmp(*href, "file://localhost/"))
	StrAllocCat(*href, (HTVMS_wwwName(Home_Dir()) + 1));
#endif /* VMS */

    FREE(temp);
    return;
}

void LYAddMETAcharsetToStream(HTStream *target, int disp_chndl)
{
    char *buf = 0;

    if (disp_chndl == -1)
	/*
	 * -1 means use current_char_set.
	 */
	disp_chndl = current_char_set;

    if (target != 0 && disp_chndl >= 0) {
	HTSprintf0(&buf, "<META %s content=\"text/html;charset=%s\">\n",
		   "http-equiv=\"content-type\"",
		   LYCharSet_UC[disp_chndl].MIMEname);
	(*target->isa->put_string) (target, buf);
	FREE(buf);
    }
}

/*
 *  This function writes a line with a META tag to an open file,
 *  which will specify a charset parameter to use when the file is
 *  read back in.  It is meant for temporary HTML files used by the
 *  various special pages which may show titles of documents.  When those
 *  files are created, the title strings normally have been translated and
 *  expanded to the display character set, so we have to make sure they
 *  don't get translated again.
 *  If the user has changed the display character set during the lifetime
 *  of the Lynx session (or, more exactly, during the time the title
 *  strings to be written were generated), they may now have different
 *  character encodings and there is currently no way to get it all right.
 *  To change this, we would have to add a variable for each string which
 *  keeps track of its character encoding.
 *  But at least we can try to ensure that reading the file after future
 *  display character set changes will give reasonable output.
 *
 *  The META tag is not written if the display character set (passed as
 *  disp_chndl) already corresponds to the charset assumption that
 *  would be made when the file is read. - KW
 *
 *  Currently this function is used for temporary files like "Lynx Info Page"
 *  and for one permanent - bookmarks (so it may be a problem if you change
 *  the display charset later: new bookmark entries may be mistranslated).
 *								 - LP
 */
void LYAddMETAcharsetToFD(FILE *fd, int disp_chndl)
{
    if (disp_chndl == -1)
	/*
	 * -1 means use current_char_set.
	 */
	disp_chndl = current_char_set;

    if (fd == NULL || disp_chndl < 0)
	/*
	 * Should not happen.
	 */
	return;

    if (UCLYhndl_HTFile_for_unspec == disp_chndl)
	/*
	 * Not need to do, so we don't.
	 */
	return;

    if (LYCharSet_UC[disp_chndl].enc == UCT_ENC_7BIT)
	/*
	 * There shouldn't be any 8-bit characters in this case.
	 */
	return;

    /*
     * In other cases we don't know because UCLYhndl_for_unspec may change
     * during the lifetime of the file (by toggling raw mode or changing the
     * display character set), so proceed.
     */
    fprintf(fd, "<META %s content=\"text/html;charset=%s\">\n",
	    "http-equiv=\"content-type\"",
	    LYCharSet_UC[disp_chndl].MIMEname);
}

/*
 * This function returns OL TYPE="A" strings in
 * the range of " A." (1) to "ZZZ." (18278). - FM
 */
char *LYUppercaseA_OL_String(int seqnum)
{
    static char OLstring[8];

    if (seqnum <= 1) {
	strcpy(OLstring, " A.");
	return OLstring;
    }
    if (seqnum < 27) {
	sprintf(OLstring, " %c.", (seqnum + 64));
	return OLstring;
    }
    if (seqnum < 703) {
	sprintf(OLstring, "%c%c.", ((seqnum - 1) / 26 + 64),
		(seqnum - ((seqnum - 1) / 26) * 26 + 64));
	return OLstring;
    }
    if (seqnum < 18279) {
	sprintf(OLstring, "%c%c%c.", ((seqnum - 27) / 676 + 64),
		(((seqnum - ((seqnum - 27) / 676) * 676) - 1) / 26 + 64),
		(seqnum - ((seqnum - 1) / 26) * 26 + 64));
	return OLstring;
    }
    strcpy(OLstring, "ZZZ.");
    return OLstring;
}

/*
 * This function returns OL TYPE="a" strings in
 * the range of " a." (1) to "zzz." (18278). - FM
 */
char *LYLowercaseA_OL_String(int seqnum)
{
    static char OLstring[8];

    if (seqnum <= 1) {
	strcpy(OLstring, " a.");
	return OLstring;
    }
    if (seqnum < 27) {
	sprintf(OLstring, " %c.", (seqnum + 96));
	return OLstring;
    }
    if (seqnum < 703) {
	sprintf(OLstring, "%c%c.", ((seqnum - 1) / 26 + 96),
		(seqnum - ((seqnum - 1) / 26) * 26 + 96));
	return OLstring;
    }
    if (seqnum < 18279) {
	sprintf(OLstring, "%c%c%c.", ((seqnum - 27) / 676 + 96),
		(((seqnum - ((seqnum - 27) / 676) * 676) - 1) / 26 + 96),
		(seqnum - ((seqnum - 1) / 26) * 26 + 96));
	return OLstring;
    }
    strcpy(OLstring, "zzz.");
    return OLstring;
}

/*
 * This function returns OL TYPE="I" strings in the
 * range of " I." (1) to "MMM." (3000).- FM
 * Maximum length: 16 -TD
 */
char *LYUppercaseI_OL_String(int seqnum)
{
    static char OLstring[20];
    int Arabic = seqnum;

    if (Arabic >= 3000) {
	strcpy(OLstring, "MMM.");
	return OLstring;
    }

    switch (Arabic) {
    case 1:
	strcpy(OLstring, " I.");
	return OLstring;
    case 5:
	strcpy(OLstring, " V.");
	return OLstring;
    case 10:
	strcpy(OLstring, " X.");
	return OLstring;
    case 50:
	strcpy(OLstring, " L.");
	return OLstring;
    case 100:
	strcpy(OLstring, " C.");
	return OLstring;
    case 500:
	strcpy(OLstring, " D.");
	return OLstring;
    case 1000:
	strcpy(OLstring, " M.");
	return OLstring;
    default:
	OLstring[0] = '\0';
	break;
    }

    while (Arabic >= 1000) {
	strcat(OLstring, "M");
	Arabic -= 1000;
    }

    if (Arabic >= 900) {
	strcat(OLstring, "CM");
	Arabic -= 900;
    }

    if (Arabic >= 500) {
	strcat(OLstring, "D");
	Arabic -= 500;
	while (Arabic >= 500) {
	    strcat(OLstring, "C");
	    Arabic -= 10;
	}
    }

    if (Arabic >= 400) {
	strcat(OLstring, "CD");
	Arabic -= 400;
    }

    while (Arabic >= 100) {
	strcat(OLstring, "C");
	Arabic -= 100;
    }

    if (Arabic >= 90) {
	strcat(OLstring, "XC");
	Arabic -= 90;
    }

    if (Arabic >= 50) {
	strcat(OLstring, "L");
	Arabic -= 50;
	while (Arabic >= 50) {
	    strcat(OLstring, "X");
	    Arabic -= 10;
	}
    }

    if (Arabic >= 40) {
	strcat(OLstring, "XL");
	Arabic -= 40;
    }

    while (Arabic > 10) {
	strcat(OLstring, "X");
	Arabic -= 10;
    }

    switch (Arabic) {
    case 1:
	strcat(OLstring, "I.");
	break;
    case 2:
	strcat(OLstring, "II.");
	break;
    case 3:
	strcat(OLstring, "III.");
	break;
    case 4:
	strcat(OLstring, "IV.");
	break;
    case 5:
	strcat(OLstring, "V.");
	break;
    case 6:
	strcat(OLstring, "VI.");
	break;
    case 7:
	strcat(OLstring, "VII.");
	break;
    case 8:
	strcat(OLstring, "VIII.");
	break;
    case 9:
	strcat(OLstring, "IX.");
	break;
    case 10:
	strcat(OLstring, "X.");
	break;
    default:
	strcat(OLstring, ".");
	break;
    }

    return OLstring;
}

/*
 * This function returns OL TYPE="i" strings in
 * range of " i." (1) to "mmm." (3000).- FM
 * Maximum length: 16 -TD
 */
char *LYLowercaseI_OL_String(int seqnum)
{
    static char OLstring[20];
    int Arabic = seqnum;

    if (Arabic >= 3000) {
	strcpy(OLstring, "mmm.");
	return OLstring;
    }

    switch (Arabic) {
    case 1:
	strcpy(OLstring, " i.");
	return OLstring;
    case 5:
	strcpy(OLstring, " v.");
	return OLstring;
    case 10:
	strcpy(OLstring, " x.");
	return OLstring;
    case 50:
	strcpy(OLstring, " l.");
	return OLstring;
    case 100:
	strcpy(OLstring, " c.");
	return OLstring;
    case 500:
	strcpy(OLstring, " d.");
	return OLstring;
    case 1000:
	strcpy(OLstring, " m.");
	return OLstring;
    default:
	OLstring[0] = '\0';
	break;
    }

    while (Arabic >= 1000) {
	strcat(OLstring, "m");
	Arabic -= 1000;
    }

    if (Arabic >= 900) {
	strcat(OLstring, "cm");
	Arabic -= 900;
    }

    if (Arabic >= 500) {
	strcat(OLstring, "d");
	Arabic -= 500;
	while (Arabic >= 500) {
	    strcat(OLstring, "c");
	    Arabic -= 10;
	}
    }

    if (Arabic >= 400) {
	strcat(OLstring, "cd");
	Arabic -= 400;
    }

    while (Arabic >= 100) {
	strcat(OLstring, "c");
	Arabic -= 100;
    }

    if (Arabic >= 90) {
	strcat(OLstring, "xc");
	Arabic -= 90;
    }

    if (Arabic >= 50) {
	strcat(OLstring, "l");
	Arabic -= 50;
	while (Arabic >= 50) {
	    strcat(OLstring, "x");
	    Arabic -= 10;
	}
    }

    if (Arabic >= 40) {
	strcat(OLstring, "xl");
	Arabic -= 40;
    }

    while (Arabic > 10) {
	strcat(OLstring, "x");
	Arabic -= 10;
    }

    switch (Arabic) {
    case 1:
	strcat(OLstring, "i.");
	break;
    case 2:
	strcat(OLstring, "ii.");
	break;
    case 3:
	strcat(OLstring, "iii.");
	break;
    case 4:
	strcat(OLstring, "iv.");
	break;
    case 5:
	strcat(OLstring, "v.");
	break;
    case 6:
	strcat(OLstring, "vi.");
	break;
    case 7:
	strcat(OLstring, "vii.");
	break;
    case 8:
	strcat(OLstring, "viii.");
	break;
    case 9:
	strcat(OLstring, "ix.");
	break;
    case 10:
	strcat(OLstring, "x.");
	break;
    default:
	strcat(OLstring, ".");
	break;
    }

    return OLstring;
}

/*
 *  This function initializes the Ordered List counter. - FM
 */
void LYZero_OL_Counter(HTStructured * me)
{
    int i;

    if (!me)
	return;

    for (i = 0; i < 12; i++) {
	me->OL_Counter[i] = OL_VOID;
	me->OL_Type[i] = '1';
    }

    me->Last_OL_Count = 0;
    me->Last_OL_Type = '1';

    return;
}

/*
 *  This function is used by the HTML Structured object. - KW
 */
void LYGetChartransInfo(HTStructured * me)
{
    me->UCLYhndl = HTAnchor_getUCLYhndl(me->node_anchor,
					UCT_STAGE_STRUCTURED);
    if (me->UCLYhndl < 0) {
	int chndl = HTAnchor_getUCLYhndl(me->node_anchor, UCT_STAGE_HTEXT);

	if (chndl < 0) {
	    chndl = current_char_set;
	    HTAnchor_setUCInfoStage(me->node_anchor, chndl,
				    UCT_STAGE_HTEXT,
				    UCT_SETBY_STRUCTURED);
	}
	HTAnchor_setUCInfoStage(me->node_anchor, chndl,
				UCT_STAGE_STRUCTURED,
				UCT_SETBY_STRUCTURED);
	me->UCLYhndl = HTAnchor_getUCLYhndl(me->node_anchor,
					    UCT_STAGE_STRUCTURED);
    }
    me->UCI = HTAnchor_getUCInfoStage(me->node_anchor,
				      UCT_STAGE_STRUCTURED);
}

	/* as in HTParse.c, saves some calls - kw */
static const char *hex = "0123456789ABCDEF";

/*
 *	  Any raw 8-bit or multibyte characters already have been
 *	  handled in relation to the display character set
 *	  in SGML_character(), including named and numeric entities.
 *
 *  This function used for translations HTML special fields inside tags
 *  (ALT=, VALUE=, etc.) from charset `cs_from' to charset `cs_to'.
 *  It also unescapes non-ASCII characters from URL (#fragments !)
 *  if st_URL is active.
 *
 *  If `do_ent' is YES, it converts named entities
 *  and numeric character references (NCRs) to their `cs_to' replacements.
 *
 *  Named entities converted to unicodes.  NCRs (unicodes) converted
 *  by UCdomap.c chartrans functions.
 *  ???NCRs with values in the ISO-8859-1 range 160-255 may be converted
 *  to their HTML entity names (via old-style entities) and then translated
 *  according to the LYCharSets.c array for `cs_out'???.
 *
 *  Some characters (see descriptions in `put_special_unicodes' from SGML.c)
 *  translated in relation with the state of boolean variables
 *  `use_lynx_specials', `plain_space' and `hidden'.  It is not clear yet:
 *
 *  If plain_space is TRUE, nbsp (160) will be treated as an ASCII
 *  space (32).  If hidden is TRUE, entities will be translated
 *  (if `do_ent' is YES) but escape sequences will be passed unaltered.
 *  If `hidden' is FALSE, some characters are converted to Lynx special
 *  codes (see `put_special_unicodes') or ASCII space if `plain_space'
 *  applies).  @@ is `use_lynx_specials' needed, does it have any effect? @@
 *  If `use_lynx_specials' is YES, translate byte values 160 and 173
 *  meaning U+00A0 and U+00AD given as or converted from raw char input
 *  are converted to HT_NON_BREAK_SPACE and LY_SOFT_HYPHEN, respectively
 *  (unless input and output charset are both iso-8859-1, for compatibility
 *  with previous usage in HTML.c) even if `hidden' or `plain_space' is set.
 *
 *  If `Back' is YES, the reverse is done instead i.e., Lynx special codes
 *  in the input are translated back to character values.
 *
 *  If `Back' is YES, an attempt is made to use UCReverseTransChar() for
 *  back translation which may be more efficient. (?)
 *
 *  If `stype' is st_URL, non-ASCII characters are URL-encoded instead.
 *  The sequence of bytes being URL-encoded is the raw input character if
 *  we couldn't translate it from `cs_in' (CJK etc.); otherwise it is the
 *  UTF-8 representation if either `cs_to' requires this or if the
 *  character's Unicode value is > 255, otherwise it should be the iso-8859-1
 *  representation.
 *  No general URL-encoding occurs for displayable ASCII characters and
 *  spaces and some C0 controls valid in HTML (LF, TAB), it is expected
 *  that other functions will take care of that as appropriate.
 *
 *  Escape characters (0x1B, '\033') are
 *  - URL-encoded	if `stype'  is st_URL,	 otherwise
 *  - dropped		if `stype'  is st_other, otherwise (i.e., st_HTML)
 *  - passed		if `hidden' is TRUE or HTCJK is set, otherwise
 *  - dropped.
 *
 *  (If `stype' is st_URL or st_other most of the parameters really predefined:
 *  cs_from=cs_to, use_lynx_specials=plain_space=NO, and hidden=YES)
 *
 *
 *  Returns pointer to the char** passed in
 *		 if string translated or translation unnecessary,
 *	    NULL otherwise
 *		 (in which case something probably went wrong.)
 *
 *
 *  In general, this somehow ugly function (KW)
 *  cover three functions from v.2.7.2 (FM):
 *		    extern void LYExpandString (
 *		       HTStructured *	       me,
 *		       char **		       str);
 *		    extern void LYUnEscapeEntities (
 *		       HTStructured *	       me,
 *		       char **		       str);
 *		    extern void LYUnEscapeToLatinOne (
 *		       HTStructured *	       me,
 *		       char **		       str,
 *		       BOOLEAN		       isURL);
 */

char **LYUCFullyTranslateString(char **str,
				int cs_from,
				int cs_to,
				int do_ent,
				int use_lynx_specials,
				int plain_space,
				int hidden,
				int Back,
				CharUtil_st stype)
{
    char *p;
    char *q, *qs;
    HTChunk *chunk = NULL;
    char *cp = 0;
    char cpe = 0;
    char *esc = NULL;
    char replace_buf[64];
    int uck;
    int lowest_8;
    UCode_t code = 0;
    unsigned long lcode;
    BOOL output_utf8 = 0, repl_translated_C0 = 0;
    size_t len;
    const char *name = NULL;
    BOOLEAN no_bytetrans;
    UCTransParams T;
    BOOL from_is_utf8 = FALSE;
    char *puni;
    enum _state {
	S_text,
	S_esc,
	S_dollar,
	S_paren,
	S_nonascii_text,
	S_dollar_paren,
	S_trans_byte,
	S_check_ent,
	S_ncr,
	S_check_uni,
	S_named,
	S_check_name,
	S_recover,
	S_got_oututf8,
	S_got_outstring,
	S_put_urlstring,
	S_got_outchar,
	S_put_urlchar,
	S_next_char,
	S_done
    } state = S_text;
    enum _parsing_what {
	P_text,
	P_utf8,
	P_hex,
	P_decimal,
	P_named
    } what = P_text;

#ifdef KANJI_CODE_OVERRIDE
    static unsigned char sjis_1st = '\0';

    unsigned char sjis_str[3];
#endif

    /*
     * Make sure we have a non-empty string.  - FM
     */
    if (isEmpty(*str))
	return str;

    /*
     * FIXME: something's wrong with the limit checks here (clearing the
     * buffer helps).
     */
    memset(replace_buf, 0, sizeof(replace_buf));

    /*
     * Don't do byte translation if original AND target character sets are both
     * iso-8859-1 (and we are not called to back-translate), or if we are in
     * CJK mode.
     */
    if (IS_CJK_TTY
#ifdef EXP_JAPANESEUTF8_SUPPORT
	&& (strcmp(LYCharSet_UC[cs_from].MIMEname, "utf-8") != 0)
	&& (strcmp(LYCharSet_UC[cs_to].MIMEname, "utf-8") != 0)
#endif
	) {
	no_bytetrans = TRUE;
    } else if (cs_to <= 0 && cs_from == cs_to && (!Back || cs_to < 0)) {
	no_bytetrans = TRUE;
    } else {
	/* No need to translate or examine the string any further */
	no_bytetrans = (BOOL) (!use_lynx_specials && !Back &&
			       UCNeedNotTranslate(cs_from, cs_to));
    }
    /*
     * Save malloc/calloc overhead in simple case - kw
     */
    if (do_ent && hidden && (stype != st_URL) && (strchr(*str, '&') == NULL))
	do_ent = FALSE;

    /* Can't do, caller should figure out what to do... */
    if (!UCCanTranslateFromTo(cs_from, cs_to)) {
	if (cs_to < 0)
	    return NULL;
	if (!do_ent && no_bytetrans)
	    return NULL;
	no_bytetrans = TRUE;
    } else if (cs_to < 0) {
	do_ent = FALSE;
    }

    if (!do_ent && no_bytetrans)
	return str;
    p = *str;

    if (!no_bytetrans) {
	UCTransParams_clear(&T);
	UCSetTransParams(&T, cs_from, &LYCharSet_UC[cs_from],
			 cs_to, &LYCharSet_UC[cs_to]);
	from_is_utf8 = (BOOL) (LYCharSet_UC[cs_from].enc == UCT_ENC_UTF8);
	output_utf8 = T.output_utf8;
	repl_translated_C0 = T.repl_translated_C0;
	puni = p;
    } else if (do_ent) {
	output_utf8 = (BOOL) (LYCharSet_UC[cs_to].enc == UCT_ENC_UTF8 ||
			      HText_hasUTF8OutputSet(HTMainText));
	repl_translated_C0 = (BOOL) (LYCharSet_UC[cs_to].enc == UCT_ENC_8BIT_C0);
    }

    lowest_8 = LYlowest_eightbit[cs_to];

    /*
     * Create a buffer string seven times the length of the original, so we
     * have plenty of room for expansions.  - FM
     */
    len = strlen(p) + 16;
    q = p;

    qs = q;

/*  Create the HTChunk only if we need it */
#define CHUNK (chunk ? chunk : (chunk = HTChunkCreate2(128, len+1)))

#define REPLACE_STRING(s) \
		if (q != qs) HTChunkPutb(CHUNK, qs, (int) (q - qs)); \
		HTChunkPuts(CHUNK, s); \
		qs = q = *str

#define REPLACE_CHAR(c) if (q > p) { \
		HTChunkPutb(CHUNK, qs, (int) (q - qs)); \
		qs = q = *str; \
		*q++ = c; \
	    } else \
		*q++ = c

    /*
     * Loop through string, making conversions as needed.
     *
     * The while() checks for a non-'\0' char only for the normal text states
     * since other states may temporarily modify p or *p (which should be
     * restored before S_done!) - kw
     */
    while (*p || (state != S_text && state != S_nonascii_text)) {
	switch (state) {
	case S_text:
	    code = UCH(*p);
#ifdef KANJI_CODE_OVERRIDE
	    if (HTCJK == JAPANESE && last_kcode == SJIS) {
		if (sjis_1st == '\0' && (IS_SJIS_HI1(code) || IS_SJIS_HI2(code))) {
		    sjis_1st = UCH(code);
		} else if (sjis_1st && IS_SJIS_LO(code)) {
		    sjis_1st = '\0';
		} else {
		    if (conv_jisx0201kana && 0xA1 <= code && code <= 0xDF) {
			sjis_str[2] = '\0';
			JISx0201TO0208_SJIS(UCH(code),
					    sjis_str, sjis_str + 1);
			REPLACE_STRING(sjis_str);
			p++;
			continue;
		    }
		}
	    }
#endif
	    if (*p == '\033') {
		if ((IS_CJK_TTY && !hidden) || stype != st_HTML) {
		    state = S_esc;
		    if (stype == st_URL) {
			REPLACE_STRING("%1B");
			p++;
			continue;
		    } else if (stype != st_HTML) {
			p++;
			continue;
		    } else {
			*q++ = *p++;
			continue;
		    }
		} else if (!hidden) {
		    /*
		     * CJK handling not on, and not a hidden INPUT, so block
		     * escape.  - FM
		     */
		    state = S_next_char;
		} else {
		    state = S_trans_byte;
		}
	    } else {
		state = (do_ent ? S_check_ent : S_trans_byte);
	    }
	    break;

	case S_esc:
	    if (*p == '$') {
		state = S_dollar;
		*q++ = *p++;
		continue;
	    } else if (*p == '(') {
		state = S_paren;
		*q++ = *p++;
		continue;
	    } else {
		state = S_text;
	    }
	    break;

	case S_dollar:
	    if (*p == '@' || *p == 'B' || *p == 'A') {
		state = S_nonascii_text;
		*q++ = *p++;
		continue;
	    } else if (*p == '(') {
		state = S_dollar_paren;
		*q++ = *p++;
		continue;
	    } else {
		state = S_text;
	    }
	    break;

	case S_dollar_paren:
	    if (*p == 'C') {
		state = S_nonascii_text;
		*q++ = *p++;
		continue;
	    } else {
		state = S_text;
	    }
	    break;

	case S_paren:
	    if (*p == 'B' || *p == 'J' || *p == 'T') {
		state = S_text;
		*q++ = *p++;
		continue;
	    } else if (*p == 'I') {
		state = S_nonascii_text;
		*q++ = *p++;
		continue;
	    } else {
		state = S_text;
	    }
	    break;

	case S_nonascii_text:
	    if (*p == '\033') {
		if ((IS_CJK_TTY && !hidden) || stype != st_HTML) {
		    state = S_esc;
		    if (stype == st_URL) {
			REPLACE_STRING("%1B");
			p++;
			continue;
		    } else if (stype != st_HTML) {
			p++;
			continue;
		    }
		}
	    }
	    *q++ = *p++;
	    continue;

	case S_trans_byte:
	    /* character translation goes here */
	    /*
	     * Don't do anything if we have no string, or if original AND
	     * target character sets are both iso-8859-1, or if we are in CJK
	     * mode.
	     */
	    if (*p == '\0' || no_bytetrans) {
		state = S_got_outchar;
		break;
	    }

	    if (Back) {
		int rev_c;

		if ((*p) == HT_NON_BREAK_SPACE ||
		    (*p) == HT_EN_SPACE) {
		    if (plain_space) {
			code = *p = ' ';
			state = S_got_outchar;
			break;
		    } else {
			code = 160;
			if (LYCharSet_UC[cs_to].enc == UCT_ENC_8859 ||
			    (LYCharSet_UC[cs_to].like8859 & UCT_R_8859SPECL)) {
			    state = S_got_outchar;
			    break;
			} else if (!(LYCharSet_UC[cs_from].enc == UCT_ENC_8859
				     || (LYCharSet_UC[cs_from].like8859 & UCT_R_8859SPECL))) {
			    state = S_check_uni;
			    break;
			} else {
			    *(unsigned char *) p = UCH(160);
			}
		    }
		} else if ((*p) == LY_SOFT_HYPHEN) {
		    code = 173;
		    if (LYCharSet_UC[cs_to].enc == UCT_ENC_8859 ||
			(LYCharSet_UC[cs_to].like8859 & UCT_R_8859SPECL)) {
			state = S_got_outchar;
			break;
		    } else if (!(LYCharSet_UC[cs_from].enc == UCT_ENC_8859
				 || (LYCharSet_UC[cs_from].like8859 & UCT_R_8859SPECL))) {
			state = S_check_uni;
			break;
		    } else {
			*(unsigned char *) p = UCH(173);
		    }
#ifdef EXP_JAPANESEUTF8_SUPPORT
		} else if (output_utf8) {
		    if ((!strcmp(LYCharSet_UC[cs_from].MIMEname, "euc-jp") &&
			 (IS_EUC((unsigned char) (*p),
				 (unsigned char) (*(p + 1))))) ||
			(!strcmp(LYCharSet_UC[cs_from].MIMEname, "shift_jis") &&
			 (IS_SJIS_2BYTE((unsigned char) (*p),
					(unsigned char) (*(p + 1)))))) {
			code = UCTransJPToUni(p, 2, cs_from);
			p++;
			state = S_check_uni;
			break;
		    }
#endif
		} else if (code < 127 || T.transp) {
		    state = S_got_outchar;
		    break;
		}
		rev_c = UCReverseTransChar(*p, cs_to, cs_from);
		if (rev_c > 127) {
		    *p = (char) rev_c;
		    code = rev_c;
		    state = S_got_outchar;
		    break;
		}
	    } else if (code < 127) {
		state = S_got_outchar;
		break;
	    }

	    if (from_is_utf8) {
		if (((*p) & 0xc0) == 0xc0) {
		    puni = p;
		    code = UCGetUniFromUtf8String(&puni);
		    if (code <= 0) {
			code = UCH(*p);
		    } else {
			what = P_utf8;
		    }
		}
	    } else if (use_lynx_specials && !Back &&
		       (code == 160 || code == 173) &&
		       (LYCharSet_UC[cs_from].enc == UCT_ENC_8859 ||
			(LYCharSet_UC[cs_from].like8859 & UCT_R_8859SPECL))) {
		if (code == 160)
		    code = *p = HT_NON_BREAK_SPACE;
		else if (code == 173)
		    code = *p = LY_SOFT_HYPHEN;
		state = S_got_outchar;
		break;
	    } else if (T.trans_to_uni) {
		code = UCTransToUni(*p, cs_from);
		if (code <= 0) {
		    /* What else can we do? */
		    code = UCH(*p);
		}
	    } else if (!T.trans_from_uni) {
		state = S_got_outchar;
		break;
	    }
	    /*
	     * Substitute Lynx special character for 160 (nbsp) if
	     * use_lynx_specials is set.
	     */
	    if (use_lynx_specials && !Back &&
		(code == 160 || code == 173)) {
		code = ((code == 160 ? HT_NON_BREAK_SPACE : LY_SOFT_HYPHEN));
		state = S_got_outchar;
		break;
	    }

	    state = S_check_uni;
	    break;

	case S_check_ent:
	    if (*p == '&') {
		char *pp = p + 1;

		len = strlen(pp);
		/*
		 * Check for a numeric entity.  - FM
		 */
		if (*pp == '#' && len > 2 &&
		    (*(pp + 1) == 'x' || *(pp + 1) == 'X') &&
		    UCH(*(pp + 2)) < 127 &&
		    isxdigit(UCH(*(pp + 2)))) {
		    what = P_hex;
		    state = S_ncr;
		} else if (*pp == '#' && len > 2 &&
			   UCH(*(pp + 1)) < 127 &&
			   isdigit(UCH(*(pp + 1)))) {
		    what = P_decimal;
		    state = S_ncr;
		} else if (UCH(*pp) < 127 &&
			   isalpha(UCH(*pp))) {
		    what = P_named;
		    state = S_named;
		} else {
		    state = S_trans_byte;
		}
	    } else {
		state = S_trans_byte;
	    }
	    break;

	case S_ncr:
	    if (what == P_hex) {
		p += 3;
	    } else {		/* P_decimal */
		p += 2;
	    }
	    cp = p;
	    while (*p && UCH(*p) < 127 &&
		   (what == P_hex ? isxdigit(UCH(*p)) :
		    isdigit(UCH(*p)))) {
		p++;
	    }
	    /*
	     * Save the terminator and isolate the digit(s).  - FM
	     */
	    cpe = *p;
	    if (*p)
		*p++ = '\0';
	    /*
	     * Show the numeric entity if the value:
	     * (1) Is greater than 255 and unhandled Unicode.
	     * (2) Is less than 32, and not valid and we don't have HTCJK set.
	     * (3) Is 127 and we don't have HTPassHighCtrlRaw or HTCJK set.
	     * (4) Is 128 - 159 and we don't have HTPassHighCtrlNum set.
	     */
	    if ((((what == P_hex)
		  ? sscanf(cp, "%lx", &lcode)
		  : sscanf(cp, "%lu", &lcode)) != 1) ||
		lcode > 0x7fffffffL) {
		state = S_recover;
		break;
	    } else {
		code = LYcp1252ToUnicode((UCode_t) lcode);
		state = S_check_uni;
	    }
	    break;

	case S_check_uni:
	    /*
	     * Show the numeric entity if the value:
	     * (2) Is less than 32, and not valid and we don't have HTCJK set.
	     * (3) Is 127 and we don't have HTPassHighCtrlRaw or HTCJK set.
	     * (4) Is 128 - 159 and we don't have HTPassHighCtrlNum set.
	     */
	    if ((code < 32 &&
		 code != 9 && code != 10 && code != 13 &&
		 !IS_CJK_TTY) ||
		(code == 127 &&
		 !(HTPassHighCtrlRaw || IS_CJK_TTY)) ||
		(code > 127 && code < 160 &&
		 !HTPassHighCtrlNum)) {
		state = S_recover;
		break;
	    }
	    /*
	     * Convert the value as an unsigned char, hex escaped if isURL is
	     * set and it's 8-bit, and then recycle the terminator if it is not
	     * a semicolon.  - FM
	     */
	    if (code > 159 && stype == st_URL) {
		state = S_got_oututf8;
		break;
	    }
	    /*
	     * For 160 (nbsp), use that value if it's a hidden INPUT, otherwise
	     * use an ASCII space (32) if plain_space is TRUE, otherwise use
	     * the Lynx special character.  - FM
	     */
	    if (code == 160) {
		if (plain_space) {
		    code = ' ';
		    state = S_got_outchar;
		    break;
		} else if (use_lynx_specials) {
		    code = HT_NON_BREAK_SPACE;
		    state = S_got_outchar;
		    break;
		} else if ((hidden && !Back)
			   || (LYCharSet_UC[cs_to].codepoints & UCT_CP_SUPERSETOF_LAT1)
			   || LYCharSet_UC[cs_to].enc == UCT_ENC_8859
			   || (LYCharSet_UC[cs_to].like8859 &
			       UCT_R_8859SPECL)) {
		    state = S_got_outchar;
		    break;
		} else if (
			      (LYCharSet_UC[cs_to].repertoire & UCT_REP_SUPERSETOF_LAT1)) {
		    ;		/* nothing, may be translated later */
		} else {
		    code = ' ';
		    state = S_got_outchar;
		    break;
		}
	    }
	    /*
	     * For 173 (shy), use that value if it's a hidden INPUT, otherwise
	     * ignore it if plain_space is TRUE, otherwise use the Lynx special
	     * character.  - FM
	     */
	    if (code == 173) {
		if (plain_space) {
		    replace_buf[0] = '\0';
		    state = S_got_outstring;
		    break;
		} else if (Back &&
			   !(LYCharSet_UC[cs_to].enc == UCT_ENC_8859 ||
			     (LYCharSet_UC[cs_to].like8859 &
			      UCT_R_8859SPECL))) {
		    ;		/* nothing, may be translated later */
		} else if (hidden || Back) {
		    state = S_got_outchar;
		    break;
		} else if (use_lynx_specials) {
		    code = LY_SOFT_HYPHEN;
		    state = S_got_outchar;
		    break;
		}
	    }
	    /*
	     * Seek a translation from the chartrans tables.
	     */
	    if ((uck = UCTransUniChar(code,
				      cs_to)) >= 32 &&
		uck < 256 &&
		(uck < 127 || uck >= lowest_8)) {
		code = uck;
		state = S_got_outchar;
		break;
	    } else if ((uck == -4 ||
			(repl_translated_C0 &&
			 uck > 0 && uck < 32)) &&
		/*
		 * Not found; look for replacement string.
		 */
		       UCTransUniCharStr(replace_buf,
					 60, code,
					 cs_to,
					 0) >= 0) {
		state = S_got_outstring;
		break;
	    }
	    if (output_utf8 &&
		code > 127 && code < 0x7fffffffL) {
		state = S_got_oututf8;
		break;
	    }
	    /*
	     * For 8194 (ensp), 8195 (emsp), or 8201 (thinsp), use the
	     * character reference if it's a hidden INPUT, otherwise use an
	     * ASCII space (32) if plain_space is TRUE, otherwise use the Lynx
	     * special character.  - FM
	     */
	    if (code == 8194 || code == 8195 || code == 8201) {
		if (hidden) {
		    state = S_recover;
		} else if (plain_space) {
		    code = ' ';
		    state = S_got_outchar;
		} else {
		    code = HT_EN_SPACE;
		    state = S_got_outchar;
		}
		break;
		/*
		 * Ignore 8204 (zwnj), 8205 (zwj) 8206 (lrm), and 8207 (rlm),
		 * for now, if we got this far without finding a representation
		 * for them.
		 */
	    } else if (code == 8204 || code == 8205 ||
		       code == 8206 || code == 8207) {
		CTRACE((tfp, "LYUCFullyTranslateString: Ignoring '%"
			PRI_UCode_t "'.\n", code));
		replace_buf[0] = '\0';
		state = S_got_outstring;
		break;
		/*
		 * Show the numeric entity if the value:  (1) Is greater than
		 * 255 and unhandled Unicode.
		 */
	    } else if (code > 255) {
		/*
		 * Illegal or not yet handled value.  Return "&#" verbatim and
		 * continue from there.  - FM
		 */
		state = S_recover;
		break;
		/*
		 * If it's ASCII, or is 8-bit but HTPassEightBitNum is set or
		 * the character set is "ISO Latin 1", use it's value.  - FM
		 */
	    } else if (code < 161 ||
		       (code < 256 &&
			(HTPassEightBitNum || cs_to == LATIN1))) {
		/*
		 * No conversion needed.
		 */
		state = S_got_outchar;
		break;

		/* The following disabled section doesn't make sense any more. 
		 * It used to make sense in the past, when S_check_named would
		 * look in "old style" tables in addition to what it does now. 
		 * Disabling of going to S_check_name here prevents endless
		 * looping between S_check_uni and S_check_names states, which
		 * could occur here for Latin 1 codes for some cs_to if they
		 * had no translation in that cs_to.  Normally all cs_to
		 * *should* now have valid translations via UCTransUniChar or
		 * UCTransUniCharStr for all Latin 1 codes, so that we would
		 * not get here anyway, and no loop could occur.  Still, if we
		 * *do* get here, FALL THROUGH to case S_recover now.  - kw
		 */
#if 0
		/*
		 * If we get to here, convert and handle the character as a
		 * named entity.  - FM
		 */
	    } else {
		name = HTMLGetEntityName(code - 160);
		state = S_check_name;
		break;
#endif
	    }

	case S_recover:
	    if (what == P_decimal || what == P_hex) {
		/*
		 * Illegal or not yet handled value.  Return "&#" verbatim and
		 * continue from there.  - FM
		 */
		*q++ = '&';
		*q++ = '#';
		if (what == P_hex)
		    *q++ = 'x';
		if (cpe != '\0')
		    *(p - 1) = cpe;
		p = cp;
		state = S_done;
	    } else if (what == P_named) {
		*cp = cpe;
		*q++ = '&';
		state = S_done;
	    } else if (!T.output_utf8 && stype == st_HTML && !hidden &&
		       !(HTPassEightBitRaw &&
			 UCH(*p) >= lowest_8)) {
		sprintf(replace_buf, "U%.2" PRI_UCode_t "", code);

		state = S_got_outstring;
	    } else {
		puni = p;
		code = UCH(*p);
		state = S_got_outchar;
	    }
	    break;

	case S_named:
	    cp = ++p;
	    while (*cp && UCH(*cp) < 127 &&
		   isalnum(UCH(*cp)))
		cp++;
	    cpe = *cp;
	    *cp = '\0';
	    name = p;
	    state = S_check_name;
	    break;

	case S_check_name:
	    /*
	     * Seek the Unicode value for the named entity.
	     *
	     * !!!!  We manually recover the case of '=' terminator which is
	     * commonly found on query to CGI-scripts enclosed as href= URLs
	     * like "somepath/?x=1&yz=2" Without this dirty fix, submission of
	     * such URLs was broken if &yz string happened to be a recognized
	     * entity name.  - LP
	     */
	    if (((code = HTMLGetEntityUCValue(name)) > 0) &&
		!((cpe == '=') && (stype == st_URL))) {
		state = S_check_uni;
		break;
	    }
	    /*
	     * Didn't find the entity.  Return verbatim.
	     */
	    state = S_recover;
	    break;

	    /* * * O U T P U T   S T A T E S * * */

	case S_got_oututf8:
	    if (code > 255 ||
		(code >= 128 && LYCharSet_UC[cs_to].enc == UCT_ENC_UTF8)) {
		UCConvertUniToUtf8(code, replace_buf);
		state = S_got_outstring;
	    } else {
		state = S_got_outchar;
	    }
	    break;
	case S_got_outstring:
	    if (what == P_decimal || what == P_hex) {
		if (cpe != ';' && cpe != '\0')
		    *(--p) = cpe;
		p--;
	    } else if (what == P_named) {
		*cp = cpe;
		p = (*cp != ';') ? (cp - 1) : cp;
	    } else if (what == P_utf8) {
		p = puni;
	    }
	    if (replace_buf[0] == '\0') {
		state = S_next_char;
		break;
	    }
	    if (stype == st_URL) {
		code = replace_buf[0];	/* assume string OK if first char is */
		if (code >= 127 ||
		    (code < 32 && (code != 9 && code != 10 && code != 0))) {
		    state = S_put_urlstring;
		    break;
		}
	    }
	    REPLACE_STRING(replace_buf);
	    state = S_next_char;
	    break;
	case S_put_urlstring:
	    esc = HTEscape(replace_buf, URL_XALPHAS);
	    REPLACE_STRING(esc);
	    FREE(esc);
	    state = S_next_char;
	    break;
	case S_got_outchar:
	    if (what == P_decimal || what == P_hex) {
		if (cpe != ';' && cpe != '\0')
		    *(--p) = cpe;
		p--;
	    } else if (what == P_named) {
		*cp = cpe;
		p = (*cp != ';') ? (cp - 1) : cp;
	    } else if (what == P_utf8) {
		p = puni;
	    }
	    if (stype == st_URL &&
	    /*  Not a full HTEscape, only for 8bit and ctrl chars */
		(TOASCII(code) >= 127 ||	/* S/390 -- gil -- 1925 */
		 (code < ' ' && (code != '\t' && code != '\n')))) {
		state = S_put_urlchar;
		break;
	    } else if (!hidden && code == 10 && *p == 10
		       && q != qs && *(q - 1) == 13) {
		/*
		 * If this is not a hidden string, and the current char is the
		 * LF ('\n') of a CRLF pair, drop the CR ('\r').  - KW
		 */
		*(q - 1) = *p++;
		state = S_done;
		break;
	    }
	    *q++ = (char) code;
	    state = S_next_char;
	    break;
	case S_put_urlchar:
	    *q++ = '%';
	    REPLACE_CHAR(hex[(TOASCII(code) >> 4) & 15]);	/* S/390 -- gil -- 1944 */
	    REPLACE_CHAR(hex[(TOASCII(code) & 15)]);
	    /* fall through */
	case S_next_char:
	    p++;		/* fall through */
	case S_done:
	    state = S_text;
	    what = P_text;
	    /* for next round */
	}
    }

    *q = '\0';
    if (chunk) {
	HTChunkPutb(CHUNK, qs, (int) (q - qs + 1));	/* also terminates */
	if (stype == st_URL || stype == st_other) {
	    LYTrimHead(chunk->data);
	    LYTrimTail(chunk->data);
	}
	StrAllocCopy(*str, chunk->data);
	HTChunkFree(chunk);
    } else {
	if (stype == st_URL || stype == st_other) {
	    LYTrimHead(qs);
	    LYTrimTail(qs);
	}
    }
    return str;
}

#undef REPLACE_CHAR
#undef REPLACE_STRING

BOOL LYUCTranslateHTMLString(char **str,
			     int cs_from,
			     int cs_to,
			     int use_lynx_specials,
			     int plain_space,
			     int hidden,
			     CharUtil_st stype)
{
    BOOL ret = YES;

    /* May reallocate *str even if cs_to == 0 */
    if (!LYUCFullyTranslateString(str, cs_from, cs_to, TRUE,
				  use_lynx_specials, plain_space, hidden,
				  NO, stype)) {
	ret = NO;
    }
    return ret;
}

BOOL LYUCTranslateBackFormData(char **str,
			       int cs_from,
			       int cs_to,
			       int plain_space)
{
    char **ret;

    /* May reallocate *str */
    ret = (LYUCFullyTranslateString(str, cs_from, cs_to, FALSE,
				    NO, plain_space, YES,
				    YES, st_HTML));
    return (BOOL) (ret != NULL);
}

/*
 * Parse a parameter from an HTML META tag, i.e., the CONTENT.
 */
char *LYParseTagParam(char *from,
		      const char *name)
{
    size_t len = strlen(name);
    char *result = NULL;
    char *string = from;

    do {
	if ((string = strchr(string, ';')) == NULL)
	    return NULL;
	while (*string != '\0' && (*string == ';' || isspace(UCH(*string)))) {
	    string++;
	}
	if (strlen(string) < len)
	    return NULL;
    } while (strncasecomp(string, name, (int) len) != 0);
    string += len;
    while (*string != '\0' && (isspace(UCH(*string)) || *string == '=')) {
	string++;
    }

    StrAllocCopy(result, string);
    len = 0;
    while (isprint(UCH(string[len])) && !isspace(UCH(string[len]))) {
	len++;
    }
    result[len] = '\0';

    /*
     * Strip single quotes, just in case.
     */
    if (len > 2 && result[0] == '\'' && result[len - 1] == result[0]) {
	result[len - 1] = '\0';
	for (string = result; (string[0] = string[1]) != '\0'; ++string) ;
    }
    return result;
}

/*
 * Given a refresh-URL content string, parses the delay time and the URL
 * string.  Ignore the remainder of the content.
 */
void LYParseRefreshURL(char *content,
		       char **p_seconds,
		       char **p_address)
{
    char *cp;
    char *cp1 = NULL;
    char *Seconds = NULL;

    /*
     * Look for the Seconds field.  - FM
     */
    cp = LYSkipBlanks(content);
    if (*cp && isdigit(UCH(*cp))) {
	cp1 = cp;
	while (*cp1 && isdigit(UCH(*cp1)))
	    cp1++;
	StrnAllocCopy(Seconds, cp, (int) (cp1 - cp));
    }
    *p_seconds = Seconds;
    *p_address = LYParseTagParam(content, "URL");

    CTRACE((tfp,
	    "LYParseRefreshURL\n\tcontent: %s\n\tseconds: %s\n\taddress: %s\n",
	    content, NonNull(*p_seconds), NonNull(*p_address)));
}

/*
 *  This function processes META tags in HTML streams. - FM
 */
void LYHandleMETA(HTStructured * me, const BOOL *present,
		  const char **value,
		  char **include GCC_UNUSED)
{
    char *http_equiv = NULL, *name = NULL, *content = NULL, *charset = NULL;
    char *href = NULL, *id_string = NULL, *temp = NULL;
    char *cp, *cp0, *cp1 = NULL;
    int url_type = 0;

    if (!me || !present)
	return;

    /*
     * Load the attributes for possible use by Lynx.  - FM
     */
    if (present[HTML_META_HTTP_EQUIV] &&
	non_empty(value[HTML_META_HTTP_EQUIV])) {
	StrAllocCopy(http_equiv, value[HTML_META_HTTP_EQUIV]);
	convert_to_spaces(http_equiv, TRUE);
	LYUCTranslateHTMLString(&http_equiv, me->tag_charset, me->tag_charset,
				NO, NO, YES, st_other);
	if (*http_equiv == '\0') {
	    FREE(http_equiv);
	}
    }
    if (present[HTML_META_NAME] &&
	non_empty(value[HTML_META_NAME])) {
	StrAllocCopy(name, value[HTML_META_NAME]);
	convert_to_spaces(name, TRUE);
	LYUCTranslateHTMLString(&name, me->tag_charset, me->tag_charset,
				NO, NO, YES, st_other);
	if (*name == '\0') {
	    FREE(name);
	}
    }
    if (present[HTML_META_CONTENT] &&
	non_empty(value[HTML_META_CONTENT])) {
	/*
	 * Technically, we should be creating a comma-separated list, but META
	 * tags come one at a time, and we'll handle (or ignore) them as each
	 * is received.  Also, at this point, we only trim leading and trailing
	 * blanks from the CONTENT value, without translating any named
	 * entities or numeric character references, because how we should do
	 * that depends on what type of information it contains, and whether or
	 * not any of it might be sent to the screen.  - FM
	 */
	StrAllocCopy(content, value[HTML_META_CONTENT]);
	convert_to_spaces(content, FALSE);
	LYTrimHead(content);
	LYTrimTail(content);
	if (*content == '\0') {
	    FREE(content);
	}
    }
    if (present[HTML_META_CHARSET] &&
	non_empty(value[HTML_META_CHARSET])) {
	StrAllocCopy(charset, value[HTML_META_CHARSET]);
	convert_to_spaces(charset, TRUE);
	LYUCTranslateHTMLString(&charset, me->tag_charset, me->tag_charset,
				NO, NO, YES, st_other);
	if (*charset == '\0') {
	    FREE(charset);
	}
    }
    CTRACE((tfp,
	    "LYHandleMETA: HTTP-EQUIV=\"%s\" NAME=\"%s\" CONTENT=\"%s\" CHARSET=\"%s\"\n",
	    NONNULL(http_equiv),
	    NONNULL(name),
	    NONNULL(content),
	    NONNULL(charset)));

    /*
     * Check for a text/html Content-Type with a charset directive, if we
     * didn't already set the charset via a server's header.  - AAC & FM
     */
    if (isEmpty(me->node_anchor->charset) &&
	(charset ||
	 (!strcasecomp(NonNull(http_equiv), "Content-Type") && content))) {
	LYUCcharset *p_in = NULL;
	LYUCcharset *p_out = NULL;

	if (charset) {
	    LYLowerCase(charset);
	} else {
	    LYUCTranslateHTMLString(&content, me->tag_charset, me->tag_charset,
				    NO, NO, YES, st_other);
	    LYLowerCase(content);
	}

	if ((cp1 = charset) != NULL ||
	    (cp1 = strstr(content, "charset")) != NULL) {
	    BOOL chartrans_ok = NO;
	    char *cp3 = NULL, *cp4;
	    int chndl;

	    if (!charset)
		cp1 += 7;
	    while (*cp1 == ' ' || *cp1 == '=' || *cp1 == '"')
		cp1++;

	    StrAllocCopy(cp3, cp1);	/* copy to mutilate more */
	    for (cp4 = cp3; (*cp4 != '\0' && *cp4 != '"' &&
			     *cp4 != ';' && *cp4 != ':' &&
			     !WHITE(*cp4)); cp4++) {
		;		/* do nothing */
	    }
	    *cp4 = '\0';
	    cp4 = cp3;
	    chndl = UCGetLYhndl_byMIME(cp3);

#ifdef CAN_SWITCH_DISPLAY_CHARSET
	    /* Allow a switch to a more suitable display charset */
	    if (Switch_Display_Charset(chndl, SWITCH_DISPLAY_CHARSET_MAYBE)) {
		/* UCT_STAGE_STRUCTURED and UCT_STAGE_HTEXT
		   should have the same setting for UCInfoStage. */
		HTAnchor_getUCInfoStage(me->node_anchor, UCT_STAGE_STRUCTURED);

		me->outUCLYhndl = current_char_set;
		HTAnchor_setUCInfoStage(me->node_anchor,
					current_char_set,
					UCT_STAGE_HTEXT,
					UCT_SETBY_MIME);	/* highest priorty! */
		HTAnchor_setUCInfoStage(me->node_anchor,
					current_char_set,
					UCT_STAGE_STRUCTURED,
					UCT_SETBY_MIME);	/* highest priorty! */
		me->outUCI = HTAnchor_getUCInfoStage(me->node_anchor,
						     UCT_STAGE_HTEXT);
		/* The SGML stage will be reset in change_chartrans_handling */
	    }
#endif

	    if (UCCanTranslateFromTo(chndl, current_char_set)) {
		chartrans_ok = YES;
		StrAllocCopy(me->node_anchor->charset, cp4);
		HTAnchor_setUCInfoStage(me->node_anchor, chndl,
					UCT_STAGE_PARSER,
					UCT_SETBY_STRUCTURED);
	    } else if (chndl < 0) {
		/*
		 * Got something but we don't recognize it.
		 */
		chndl = UCLYhndl_for_unrec;
		if (chndl < 0)	/* UCLYhndl_for_unrec not defined :-( */
		    chndl = UCLYhndl_for_unspec;	/* always >= 0 */
		if (UCCanTranslateFromTo(chndl, current_char_set)) {
		    chartrans_ok = YES;
		    HTAnchor_setUCInfoStage(me->node_anchor, chndl,
					    UCT_STAGE_PARSER,
					    UCT_SETBY_STRUCTURED);
		}
	    }
	    if (chartrans_ok) {
		p_in = HTAnchor_getUCInfoStage(me->node_anchor,
					       UCT_STAGE_PARSER);
		p_out = HTAnchor_setUCInfoStage(me->node_anchor,
						current_char_set,
						UCT_STAGE_HTEXT,
						UCT_SETBY_DEFAULT);
		if (!p_out) {
		    /*
		     * Try again.
		     */
		    p_out = HTAnchor_getUCInfoStage(me->node_anchor,
						    UCT_STAGE_HTEXT);
		}
		if (!strcmp(p_in->MIMEname, "x-transparent")) {
		    HTPassEightBitRaw = TRUE;
		    HTAnchor_setUCInfoStage(me->node_anchor,
					    HTAnchor_getUCLYhndl(me->node_anchor,
								 UCT_STAGE_HTEXT),
					    UCT_STAGE_PARSER,
					    UCT_SETBY_DEFAULT);
		}
		if (!strcmp(p_out->MIMEname, "x-transparent")) {
		    HTPassEightBitRaw = TRUE;
		    HTAnchor_setUCInfoStage(me->node_anchor,
					    HTAnchor_getUCLYhndl(me->node_anchor,
								 UCT_STAGE_PARSER),
					    UCT_STAGE_HTEXT,
					    UCT_SETBY_DEFAULT);
		}
		if ((p_in->enc != UCT_ENC_CJK)
#ifdef EXP_JAPANESEUTF8_SUPPORT
		    && (p_in->enc != UCT_ENC_UTF8)
#endif
		    ) {
		    HTCJK = NOCJK;
		    if (!(p_in->codepoints &
			  UCT_CP_SUBSETOF_LAT1) &&
			chndl == current_char_set) {
			HTPassEightBitRaw = TRUE;
		    }
		} else if (p_out->enc == UCT_ENC_CJK) {
		    Set_HTCJK(p_in->MIMEname, p_out->MIMEname);
		}
		LYGetChartransInfo(me);
		/*
		 * Update the chartrans info homologously to a Content-Type
		 * MIME header with a charset parameter.  - FM
		 */
		if (me->UCLYhndl != chndl) {
		    HTAnchor_setUCInfoStage(me->node_anchor, chndl,
					    UCT_STAGE_MIME,
					    UCT_SETBY_STRUCTURED);
		    HTAnchor_setUCInfoStage(me->node_anchor, chndl,
					    UCT_STAGE_PARSER,
					    UCT_SETBY_STRUCTURED);
		    me->inUCLYhndl = HTAnchor_getUCLYhndl(me->node_anchor,
							  UCT_STAGE_PARSER);
		    me->inUCI = HTAnchor_getUCInfoStage(me->node_anchor,
							UCT_STAGE_PARSER);
		}
		UCSetTransParams(&me->T,
				 me->inUCLYhndl, me->inUCI,
				 me->outUCLYhndl, me->outUCI);
	    } else {
		/*
		 * Cannot translate.  If according to some heuristic the given
		 * charset and the current display character both are likely to
		 * be like ISO-8859 in structure, pretend we have some kind of
		 * match.
		 */
		BOOL given_is_8859 = (BOOL) (!StrNCmp(cp4, "iso-8859-", 9) &&
					     isdigit(UCH(cp4[9])));
		BOOL given_is_8859like = (BOOL) (given_is_8859
						 || !StrNCmp(cp4, "windows-", 8)
						 || !StrNCmp(cp4, "cp12", 4)
						 || !StrNCmp(cp4, "cp-12", 5));
		BOOL given_and_display_8859like = (BOOL) (given_is_8859like &&
							  (strstr(LYchar_set_names[current_char_set],
								  "ISO-8859") ||
							   strstr(LYchar_set_names[current_char_set],
								  "windows-")));

		if (given_is_8859) {
		    cp1 = &cp4[10];
		    while (*cp1 &&
			   isdigit(UCH((*cp1))))
			cp1++;
		    *cp1 = '\0';
		}
		if (given_and_display_8859like) {
		    StrAllocCopy(me->node_anchor->charset, cp4);
		    HTPassEightBitRaw = TRUE;
		}
		HTAlert(*cp4 ? cp4 : me->node_anchor->charset);

	    }
	    FREE(cp3);

	    if (me->node_anchor->charset) {
		CTRACE((tfp,
			"LYHandleMETA: New charset: %s\n",
			me->node_anchor->charset));
	    }
	}
	/*
	 * Set the kcode element based on the charset.  - FM
	 */
	HText_setKcode(me->text, me->node_anchor->charset, p_in);
    }

    /*
     * Make sure we have META name/value pairs to handle.  - FM
     */
    if (!(http_equiv || name) || !content)
	goto free_META_copies;

    /*
     * Check for a no-cache Pragma
     * or Cache-Control directive. - FM
     */
    if (!strcasecomp(NonNull(http_equiv), "Pragma") ||
	!strcasecomp(NonNull(http_equiv), "Cache-Control")) {
	LYUCTranslateHTMLString(&content, me->tag_charset, me->tag_charset,
				NO, NO, YES, st_other);
	if (!strcasecomp(content, "no-cache")) {
	    me->node_anchor->no_cache = TRUE;
	    HText_setNoCache(me->text);
	}

	/*
	 * If we didn't get a Cache-Control MIME header, and the META has one,
	 * convert to lowercase, store it in the anchor element, and if we
	 * haven't yet set no_cache, check whether we should.  - FM
	 */
	if ((!me->node_anchor->cache_control) &&
	    !strcasecomp(NonNull(http_equiv), "Cache-Control")) {
	    LYLowerCase(content);
	    StrAllocCopy(me->node_anchor->cache_control, content);
	    if (me->node_anchor->no_cache == FALSE) {
		cp0 = content;
		while ((cp = strstr(cp0, "no-cache")) != NULL) {
		    cp += 8;
		    while (*cp != '\0' && WHITE(*cp))
			cp++;
		    if (*cp == '\0' || *cp == ';') {
			me->node_anchor->no_cache = TRUE;
			HText_setNoCache(me->text);
			break;
		    }
		    cp0 = cp;
		}
		if (me->node_anchor->no_cache == TRUE)
		    goto free_META_copies;
		cp0 = content;
		while ((cp = strstr(cp0, "max-age")) != NULL) {
		    cp += 7;
		    while (*cp != '\0' && WHITE(*cp))
			cp++;
		    if (*cp == '=') {
			cp++;
			while (*cp != '\0' && WHITE(*cp))
			    cp++;
			if (isdigit(UCH(*cp))) {
			    cp0 = cp;
			    while (isdigit(UCH(*cp)))
				cp++;
			    if (*cp0 == '0' && cp == (cp0 + 1)) {
				me->node_anchor->no_cache = TRUE;
				HText_setNoCache(me->text);
				break;
			    }
			}
		    }
		    cp0 = cp;
		}
	    }
	}

	/*
	 * Check for an Expires directive. - FM
	 */
    } else if (!strcasecomp(NonNull(http_equiv), "Expires")) {
	/*
	 * If we didn't get an Expires MIME header, store it in the anchor
	 * element, and if we haven't yet set no_cache, check whether we
	 * should.  Note that we don't accept a Date header via META tags,
	 * because it's likely to be untrustworthy, but do check for a Date
	 * header from a server when making the comparison.  - FM
	 */
	LYUCTranslateHTMLString(&content, me->tag_charset, me->tag_charset,
				NO, NO, YES, st_other);
	StrAllocCopy(me->node_anchor->expires, content);
	if (me->node_anchor->no_cache == FALSE) {
	    if (!strcmp(content, "0")) {
		/*
		 * The value is zero, which we treat as an absolute no-cache
		 * directive.  - FM
		 */
		me->node_anchor->no_cache = TRUE;
		HText_setNoCache(me->text);
	    } else if (me->node_anchor->date != NULL) {
		/*
		 * We have a Date header, so check if the value is less than or
		 * equal to that.  - FM
		 */
		if (LYmktime(content, TRUE) <=
		    LYmktime(me->node_anchor->date, TRUE)) {
		    me->node_anchor->no_cache = TRUE;
		    HText_setNoCache(me->text);
		}
	    } else if (LYmktime(content, FALSE) == 0) {
		/*
		 * We don't have a Date header, and the value is in past for
		 * us.  - FM
		 */
		me->node_anchor->no_cache = TRUE;
		HText_setNoCache(me->text);
	    }
	}

	/*
	 * Check for a Refresh directive.  - FM
	 */
    } else if (!strcasecomp(NonNull(http_equiv), "Refresh")) {
	char *Seconds = NULL;

	LYUCTranslateHTMLString(&content, me->tag_charset, me->tag_charset,
				NO, NO, YES, st_other);
	LYParseRefreshURL(content, &Seconds, &href);

	if (Seconds) {
	    if (href) {
		/*
		 * We found a URL field, so check it out.  - FM
		 */
		if (!LYLegitimizeHREF(me, &href, TRUE, FALSE)) {
		    /*
		     * The specs require a complete URL, but this is a
		     * Netscapism, so don't expect the author to know that.  -
		     * FM
		     */
		    HTUserMsg(REFRESH_URL_NOT_ABSOLUTE);
		    /*
		     * Use the document's address as the base.  - FM
		     */
		    if (*href != '\0') {
			temp = HTParse(href,
				       me->node_anchor->address, PARSE_ALL);
			StrAllocCopy(href, temp);
			FREE(temp);
		    } else {
			StrAllocCopy(href, me->node_anchor->address);
			HText_setNoCache(me->text);
		    }

		} else {
		    /*
		     * Check whether to fill in localhost.  - FM
		     */
		    LYFillLocalFileURL(&href,
				       (me->inBASE ?
					me->base_href : me->node_anchor->address));
		}

		/*
		 * Set the no_cache flag if the Refresh URL is the same as the
		 * document's address.  - FM
		 */
		if (!strcmp(href, me->node_anchor->address)) {
		    HText_setNoCache(me->text);
		}
	    } else {
		/*
		 * We didn't find a URL field, so use the document's own
		 * address and set the no_cache flag.  - FM
		 */
		StrAllocCopy(href, me->node_anchor->address);
		HText_setNoCache(me->text);
	    }
	    /*
	     * Check for an anchor in http or https URLs.  - FM
	     */
	    cp = NULL;
#ifndef DONT_TRACK_INTERNAL_LINKS
	    /* id_string seems to be used wrong below if given.
	       not that it matters much.  avoid setting it here. - kw */
	    if ((StrNCmp(href, "http", 4) == 0) &&
		(cp = strchr(href, '#')) != NULL) {
		StrAllocCopy(id_string, cp);
		*cp = '\0';
	    }
#endif
	    if (me->inA) {
		/*
		 * Ugh!  The META tag, which is a HEAD element, is in an
		 * Anchor, which is BODY element.  All we can do is close the
		 * Anchor and cross our fingers.  - FM
		 */
		if (me->inBoldA == TRUE && me->inBoldH == FALSE)
		    HText_appendCharacter(me->text, LY_BOLD_END_CHAR);
		me->inBoldA = FALSE;
		HText_endAnchor(me->text, me->CurrentANum);
		me->inA = FALSE;
		me->CurrentANum = 0;
	    }
	    me->CurrentA = HTAnchor_findChildAndLink
		(
		    me->node_anchor,	/* Parent */
		    id_string,	/* Tag */
		    href,	/* Addresss */
		    (HTLinkType *) 0);	/* Type */
	    if (id_string)
		*cp = '#';
	    FREE(id_string);
	    LYEnsureSingleSpace(me);
	    if (me->inUnderline == FALSE)
		HText_appendCharacter(me->text, LY_UNDERLINE_START_CHAR);
	    HTML_put_string(me, "REFRESH(");
	    HTML_put_string(me, Seconds);
	    HTML_put_string(me, " sec):");
	    FREE(Seconds);
	    if (me->inUnderline == FALSE)
		HText_appendCharacter(me->text, LY_UNDERLINE_END_CHAR);
	    HTML_put_character(me, ' ');
	    me->in_word = NO;
	    HText_beginAnchor(me->text, me->inUnderline, me->CurrentA);
	    if (me->inBoldH == FALSE)
		HText_appendCharacter(me->text, LY_BOLD_START_CHAR);
	    HTML_put_string(me, href);
	    FREE(href);
	    if (me->inBoldH == FALSE)
		HText_appendCharacter(me->text, LY_BOLD_END_CHAR);
	    HText_endAnchor(me->text, 0);
	    LYEnsureSingleSpace(me);
	}

	/*
	 * Check for a suggested filename via a Content-Disposition with a
	 * filename=name.suffix in it, if we don't already have it via a server
	 * header.  - FM
	 */
    } else if (isEmpty(me->node_anchor->SugFname) &&
	       !strcasecomp((http_equiv ?
			     http_equiv : ""), "Content-Disposition")) {
	cp = content;
	while (*cp != '\0' && strncasecomp(cp, "filename", 8))
	    cp++;
	if (*cp != '\0') {
	    cp = LYSkipBlanks(cp + 8);
	    if (*cp == '=')
		cp++;
	    cp = LYSkipBlanks(cp);
	    if (*cp != '\0') {
		StrAllocCopy(me->node_anchor->SugFname, cp);
		if (*me->node_anchor->SugFname == '"') {
		    if ((cp = strchr((me->node_anchor->SugFname + 1),
				     '"')) != NULL) {
			*(cp + 1) = '\0';
			HTMIME_TrimDoubleQuotes(me->node_anchor->SugFname);
			if (isEmpty(me->node_anchor->SugFname)) {
			    FREE(me->node_anchor->SugFname);
			}
		    } else {
			FREE(me->node_anchor->SugFname);
		    }
		}
#if defined(UNIX) && !defined(DOSPATH)
		/*
		 * If blanks are not legal for local filenames, replace them
		 * with underscores.
		 */
		if ((cp = me->node_anchor->SugFname) != NULL) {
		    while (*cp != '\0') {
			if (isspace(UCH(*cp)))
			    *cp = '_';
			++cp;
		    }
		}
#endif
	    }
	}
	/*
	 * Check for a Set-Cookie directive.  - AK
	 */
    } else if (!strcasecomp(NonNull(http_equiv), "Set-Cookie")) {
	/*
	 * This will need to be updated when Set-Cookie/Set-Cookie2 handling is
	 * finalized.  For now, we'll still assume "historical" cookies in META
	 * directives.  - FM
	 */
	url_type = is_url(me->inBASE ?
			  me->base_href : me->node_anchor->address);
	if (url_type == HTTP_URL_TYPE || url_type == HTTPS_URL_TYPE) {
	    LYSetCookie(content,
			NULL,
			(me->inBASE ?
			 me->base_href : me->node_anchor->address));
	}
    }

    /*
     * Free the copies.  - FM
     */
  free_META_copies:
    FREE(http_equiv);
    FREE(name);
    FREE(content);
    FREE(charset);
}

/*
 *  This function handles P elements in HTML streams.
 *  If start is TRUE it handles a start tag, and if
 *  FALSE, an end tag.	We presently handle start
 *  and end tags identically, but this can lead to
 *  a different number of blank lines between the
 *  current paragraph and subsequent text when a P
 *  end tag is present or not in the markup. - FM
 */
void LYHandlePlike(HTStructured * me, const BOOL *present,
		   const char **value,
		   char **include GCC_UNUSED,
		   int align_idx,
		   int start)
{
    if (TRUE) {
	/*
	 * FIG content should be a true block, which like P inherits the
	 * current style.  APPLET is like character elements or an ALT
	 * attribute, unless it content contains a block element.  If we
	 * encounter a P in either's content, we set flags to treat the content
	 * as a block.  - FM
	 */
	if (start) {
	    if (me->inFIG)
		me->inFIGwithP = TRUE;

	    if (me->inAPPLET)
		me->inAPPLETwithP = TRUE;
	}

	UPDATE_STYLE;
	if (me->List_Nesting_Level >= 0) {
	    /*
	     * We're in a list.  Treat P as an instruction to create one blank
	     * line, if not already present, then fall through to handle
	     * attributes, with the "second line" margins.  - FM
	     */
	    if (me->inP) {
		if (me->inFIG || me->inAPPLET ||
		    me->inCAPTION || me->inCREDIT ||
		    me->sp->style->spaceAfter > 0 ||
		    (start && me->sp->style->spaceBefore > 0)) {
		    LYEnsureDoubleSpace(me);
		} else {
		    LYEnsureSingleSpace(me);
		}
	    }
	} else if (me->sp[0].tag_number == HTML_ADDRESS) {
	    /*
	     * We're in an ADDRESS.  Treat P as an instruction to start a
	     * newline, if needed, then fall through to handle attributes.  -
	     * FM
	     */
	    if (!HText_LastLineEmpty(me->text, FALSE)) {
		HText_setLastChar(me->text, ' ');	/* absorb white space */
		HText_appendCharacter(me->text, '\r');
	    }
	} else {
	    if (start) {
		if (!(me->inLABEL && !me->inP)) {
		    HText_appendParagraph(me->text);
		}
	    } else if (me->sp->style->spaceAfter > 0) {
		LYEnsureDoubleSpace(me);
	    } else {
		LYEnsureSingleSpace(me);
	    }
	    me->inLABEL = FALSE;
	}
	me->in_word = NO;

	if (LYoverride_default_alignment(me)) {
	    me->sp->style->alignment = LYstyles(me->sp[0].tag_number)->alignment;
	} else if ((me->List_Nesting_Level >= 0 &&
		    (me->sp->style->id == ST_DivCenter ||
		     me->sp->style->id == ST_DivLeft ||
		     me->sp->style->id == ST_DivRight)) ||
		   ((me->Division_Level < 0) &&
		    (me->sp->style->id == ST_Normal ||
		     me->sp->style->id == ST_Preformatted))) {
	    me->sp->style->alignment = HT_LEFT;
	} else {
	    me->sp->style->alignment = (short) me->current_default_alignment;
	}

	if (start) {
	    if (present && present[align_idx] && value[align_idx]) {
		if (!strcasecomp(value[align_idx], "center") &&
		    !(me->List_Nesting_Level >= 0 && !me->inP))
		    me->sp->style->alignment = HT_CENTER;
		else if (!strcasecomp(value[align_idx], "right") &&
			 !(me->List_Nesting_Level >= 0 && !me->inP))
		    me->sp->style->alignment = HT_RIGHT;
		else if (!strcasecomp(value[align_idx], "left") ||
			 !strcasecomp(value[align_idx], "justify"))
		    me->sp->style->alignment = HT_LEFT;
	    }

	}

	/*
	 * Mark that we are starting a new paragraph and don't have any of it's
	 * text yet.  - FM
	 */
	me->inP = FALSE;
    }

    return;
}

/*
 *  This function handles SELECT elements in HTML streams.
 *  If start is TRUE it handles a start tag, and if FALSE,
 *  an end tag. - FM
 */
void LYHandleSELECT(HTStructured * me, const BOOL *present,
		    const char **value,
		    char **include GCC_UNUSED,
		    int start)
{
    int i;

    if (start == TRUE) {
	char *name = NULL;
	BOOLEAN multiple = NO;
	char *size = NULL;

	/*
	 * Initialize the disable attribute.
	 */
	me->select_disabled = FALSE;

	/*
	 * Check for unclosed TEXTAREA.
	 */
	if (me->inTEXTAREA) {
	    if (LYBadHTML(me)) {
		LYShowBadHTML("Bad HTML: Missing TEXTAREA end tag\n");
	    }
	}

	/*
	 * Set to know we are in a select tag.
	 */
	me->inSELECT = TRUE;

	if (!(present && present[HTML_SELECT_NAME] &&
	      non_empty(value[HTML_SELECT_NAME]))) {
	    StrAllocCopy(name, "");
	} else if (strchr(value[HTML_SELECT_NAME], '&') == NULL) {
	    StrAllocCopy(name, value[HTML_SELECT_NAME]);
	} else {
	    StrAllocCopy(name, value[HTML_SELECT_NAME]);
	    UNESCAPE_FIELDNAME_TO_STD(&name);
	}
	if (present && present[HTML_SELECT_MULTIPLE])
	    multiple = YES;
	if (present && present[HTML_SELECT_DISABLED])
	    me->select_disabled = TRUE;
	if (present && present[HTML_SELECT_SIZE] &&
	    non_empty(value[HTML_SELECT_SIZE])) {
	    /*
	     * Let the size be determined by the number of OPTIONs.  - FM
	     */
	    CTRACE((tfp, "LYHandleSELECT: Ignoring SIZE=\"%s\" for SELECT.\n",
		    value[HTML_SELECT_SIZE]));
	}

	if (me->inBoldH == TRUE &&
	    (multiple == NO || LYSelectPopups == FALSE)) {
	    HText_appendCharacter(me->text, LY_BOLD_END_CHAR);
	    me->inBoldH = FALSE;
	    me->needBoldH = TRUE;
	}
	if (me->inUnderline == TRUE &&
	    (multiple == NO || LYSelectPopups == FALSE)) {
	    HText_appendCharacter(me->text, LY_UNDERLINE_END_CHAR);
	    me->inUnderline = FALSE;
	}

	if ((multiple == NO && LYSelectPopups == TRUE) &&
	    (me->sp[0].tag_number == HTML_PRE || me->inPRE == TRUE ||
	     !me->sp->style->freeFormat) &&
	    HText_LastLineSize(me->text, FALSE) > (LYcolLimit - 7)) {
	    /*
	     * Force a newline when we're using a popup in a PRE block and are
	     * within 7 columns from the right margin.  This will allow for the
	     * '[' popup designator and help avoid a wrap in the underscore
	     * placeholder for the retracted popup entry in the HText
	     * structure.  - FM
	     */
	    HTML_put_character(me, '\n');
	    me->in_word = NO;
	}

	LYCheckForID(me, present, value, (int) HTML_SELECT_ID);

	HText_beginSelect(name, ATTR_CS_IN, multiple, size);
	FREE(name);
	FREE(size);

	me->first_option = TRUE;
    } else {
	/*
	 * Handle end tag.
	 */
	char *ptr;

	/*
	 * Make sure we had a select start tag.
	 */
	if (!me->inSELECT) {
	    if (LYBadHTML(me)) {
		LYShowBadHTML("Bad HTML: Unmatched SELECT end tag\n");
	    }
	    return;
	}

	/*
	 * Set to know that we are no longer in a select tag.
	 */
	me->inSELECT = FALSE;

	/*
	 * Clear the disable attribute.
	 */
	me->select_disabled = FALSE;

	/*
	 * Finish the data off.
	 */
	HTChunkTerminate(&me->option);
	/*
	 * Finish the previous option.
	 */
	ptr = HText_setLastOptionValue(me->text,
				       me->option.data,
				       me->LastOptionValue,
				       LAST_ORDER,
				       me->LastOptionChecked,
				       me->UCLYhndl,
				       ATTR_CS_IN);
	FREE(me->LastOptionValue);

	me->LastOptionChecked = FALSE;

	if (HTCurSelectGroupType == F_CHECKBOX_TYPE ||
	    LYSelectPopups == FALSE) {
	    /*
	     * Start a newline after the last checkbox/button option.
	     */
	    LYEnsureSingleSpace(me);
	} else {
	    /*
	     * Output popup box with the default option to screen, but use
	     * non-breaking spaces for output.
	     */
	    if (ptr &&
		me->sp[0].tag_number == HTML_PRE && strlen(ptr) > 6) {
		/*
		 * The code inadequately handles OPTION fields in PRE tags. 
		 * We'll put up a minimum of 6 characters, and if any more
		 * would exceed the wrap column, we'll ignore them.
		 */
		for (i = 0; i < 6; i++) {
		    if (*ptr == ' ')
			HText_appendCharacter(me->text, HT_NON_BREAK_SPACE);
		    else
			HText_appendCharacter(me->text, *ptr);
		    ptr++;
		}
	    }
	    for (; non_empty(ptr); ptr++) {
		if (*ptr == ' ')
		    HText_appendCharacter(me->text, HT_NON_BREAK_SPACE);
		else
		    HText_appendCharacter(me->text, *ptr);
	    }
	    /*
	     * Add end option character.
	     */
	    if (!me->first_option) {
		HText_appendCharacter(me->text, ']');
		HText_setLastChar(me->text, ']');
		me->in_word = YES;
	    }
	}
	HTChunkClear(&me->option);

	if (me->Underline_Level > 0 && me->inUnderline == FALSE) {
	    HText_appendCharacter(me->text, LY_UNDERLINE_START_CHAR);
	    me->inUnderline = TRUE;
	}
	if (me->needBoldH == TRUE && me->inBoldH == FALSE) {
	    HText_appendCharacter(me->text, LY_BOLD_START_CHAR);
	    me->inBoldH = TRUE;
	    me->needBoldH = FALSE;
	}
    }
}

/*
 *  This function strips white characters and
 *  generally fixes up attribute values that
 *  were received from the SGML parser and
 *  are to be treated as partial or absolute
 *  URLs. - FM
 */
int LYLegitimizeHREF(HTStructured * me, char **href,
		     int force_slash,
		     int strip_dots)
{
    int url_type = 0;
    char *p = NULL;
    char *pound = NULL;
    const char *Base = NULL;

    if (!me || !href || isEmpty(*href))
	return (url_type);

    if (!LYTrimStartfile(*href)) {
	/*
	 * Collapse spaces in the actual URL, but just protect against tabs or
	 * newlines in the fragment, if present.  This seeks to cope with
	 * atrocities inflicted on the Web by authoring tools such as
	 * Frontpage.  - FM
	 */

	/*  Before working on spaces check if we have any, usually none. */
	p = LYSkipNonBlanks(*href);

	if (*p) {		/* p == first space character */
	    /* no reallocs below, all converted in place */

	    pound = findPoundSelector(*href);

	    if (pound != NULL && pound < p) {
		convert_to_spaces(p, FALSE);	/* done */

	    } else {
		if (pound != NULL)
		    *pound = '\0';	/* mark */

		/*
		 * No blanks really belong in the HREF,
		 * but if it refers to an actual file,
		 * it may actually have blanks in the name.
		 * Try to accommodate. See also HTParse().
		 */
		if (LYRemoveNewlines(p) || strchr(p, '\t') != 0) {
		    LYRemoveBlanks(p);	/* a compromise... */
		}

		if (pound != NULL) {
		    p = strchr(p, '\0');
		    *pound = '#';	/* restore */
		    convert_to_spaces(pound, FALSE);
		    if (p < pound)
			strcpy(p, pound);
		}
	    }
	}
    }
    if (**href == '\0')
	return (url_type);

    TRANSLATE_AND_UNESCAPE_TO_STD(href);

    Base = me->inBASE ?
	me->base_href : me->node_anchor->address;

    url_type = is_url(*href);
    if (!url_type && force_slash && **href == '.' &&
	(!strcmp(*href, ".") || !strcmp(*href, "..")) &&
	!isFILE_URL(Base)) {
	/*
	 * The Fielding RFC/ID for resolving partial HREFs says that a slash
	 * should be on the end of the preceding symbolic element for "." and
	 * "..", but all tested browsers only do that for an explicit "./" or
	 * "../", so we'll respect the RFC/ID only if force_slash was TRUE and
	 * it's not a file URL.  - FM
	 */
	StrAllocCat(*href, "/");
    }
    if ((!url_type && LYStripDotDotURLs && strip_dots && **href == '.') &&
	!strncasecomp(Base, "http", 4)) {
	/*
	 * We will be resolving a partial reference versus an http or https
	 * URL, and it has lead dots, which may be retained when resolving via
	 * HTParse(), but the request would fail if the first element of the
	 * resultant path is two dots, because no http or https server accepts
	 * such paths, and the current URL draft, likely to become an RFC, says
	 * that it's optional for the UA to strip them as a form of error
	 * recovery.  So we will, recursively, for http/https URLs, like the
	 * "major market browsers" which made this problem so common on the
	 * Web, but we'll also issue a message about it, such that the bad
	 * partial reference might get corrected by the document provider.  -
	 * FM
	 */
	char *temp = NULL, *path = NULL, *cp;
	const char *str = "";

	temp = HTParse(*href, Base, PARSE_ALL);
	path = HTParse(temp, "", PARSE_PATH + PARSE_PUNCTUATION);
	if (!StrNCmp(path, "/..", 3)) {
	    cp = (path + 3);
	    if (LYIsHtmlSep(*cp) || *cp == '\0') {
		if (Base[4] == 's') {
		    str = "s";
		}
		CTRACE((tfp,
			"LYLegitimizeHREF: Bad value '%s' for http%s URL.\n",
			*href, str));
		CTRACE((tfp, "                  Stripping lead dots.\n"));
		if (!me->inBadHREF) {
		    HTUserMsg(BAD_PARTIAL_REFERENCE);
		    me->inBadHREF = TRUE;
		}
	    }
	    if (*cp == '\0') {
		StrAllocCopy(*href, "/");
	    } else if (LYIsHtmlSep(*cp)) {
		while (!StrNCmp(cp, "/..", 3)) {
		    if (*(cp + 3) == '/') {
			cp += 3;
			continue;
		    } else if (*(cp + 3) == '\0') {
			*(cp + 1) = '\0';
			*(cp + 2) = '\0';
		    }
		    break;
		}
		StrAllocCopy(*href, cp);
	    }
	}
	FREE(temp);
	FREE(path);
    }
    return (url_type);
}

/*
 *  This function checks for a Content-Base header,
 *  and if not present, a Content-Location header
 *  which is an absolute URL, and sets the BASE
 *  accordingly.  If set, it will be replaced by
 *  any BASE tag in the HTML stream, itself. - FM
 */
void LYCheckForContentBase(HTStructured * me)
{
    char *cp = NULL;
    BOOL present[HTML_BASE_ATTRIBUTES];
    const char *value[HTML_BASE_ATTRIBUTES];
    int i;

    if (!(me && me->node_anchor))
	return;

    if (me->node_anchor->content_base != NULL) {
	/*
	 * We have a Content-Base value.  Use it if it's non-zero length.  - FM
	 */
	if (*me->node_anchor->content_base == '\0')
	    return;
	StrAllocCopy(cp, me->node_anchor->content_base);
	LYRemoveBlanks(cp);
    } else if (me->node_anchor->content_location != NULL) {
	/*
	 * We didn't have a Content-Base value, but do have a Content-Location
	 * value.  Use it if it's an absolute URL.  - FM
	 */
	if (*me->node_anchor->content_location == '\0')
	    return;
	StrAllocCopy(cp, me->node_anchor->content_location);
	LYRemoveBlanks(cp);
	if (!is_url(cp)) {
	    FREE(cp);
	    return;
	}
    } else {
	/*
	 * We had neither a Content-Base nor Content-Location value.  - FM
	 */
	return;
    }

    /*
     * If we collapsed to a zero-length value, ignore it.  - FM
     */
    if (*cp == '\0') {
	FREE(cp);
	return;
    }

    /*
     * Pass the value to HTML_start_element as the HREF of a BASE tag.  - FM
     */
    for (i = 0; i < HTML_BASE_ATTRIBUTES; i++)
	present[i] = NO;
    present[HTML_BASE_HREF] = YES;
    value[HTML_BASE_HREF] = (const char *) cp;
    (*me->isa->start_element) (me, HTML_BASE, present, value,
			       0, 0);
    FREE(cp);
}

/*
 *  This function creates NAMEd Anchors if a non-zero-length NAME
 *  or ID attribute was present in the tag. - FM
 */
void LYCheckForID(HTStructured * me, const BOOL *present,
		  const char **value,
		  int attribute)
{
    HTChildAnchor *ID_A = NULL;
    char *temp = NULL;

    if (!(me && me->text))
	return;

    if (present && present[attribute]
	&& non_empty(value[attribute])) {
	/*
	 * Translate any named or numeric character references.  - FM
	 */
	StrAllocCopy(temp, value[attribute]);
	LYUCTranslateHTMLString(&temp, me->tag_charset, me->tag_charset,
				NO, NO, YES, st_URL);

	/*
	 * Create the link if we still have a non-zero-length string.  - FM
	 */
	if ((temp[0] != '\0') &&
	    (ID_A = HTAnchor_findChildAndLink
	     (
		 me->node_anchor,	/* Parent */
		 temp,		/* Tag */
		 NULL,		/* Addresss */
		 (HTLinkType *) 0))) {	/* Type */
	    HText_beginAnchor(me->text, me->inUnderline, ID_A);
	    HText_endAnchor(me->text, 0);
	}
	FREE(temp);
    }
}

/*
 *  This function creates a NAMEd Anchor for the ID string
 *  passed to it directly as an argument.  It assumes the
 *  does not need checking for character references. - FM
 */
void LYHandleID(HTStructured * me, const char *id)
{
    HTChildAnchor *ID_A = NULL;

    if (!(me && me->text) ||
	isEmpty(id))
	return;

    /*
     * Create the link if we still have a non-zero-length string.  - FM
     */
    if ((ID_A = HTAnchor_findChildAndLink
	 (
	     me->node_anchor,	/* Parent */
	     id,		/* Tag */
	     NULL,		/* Addresss */
	     (HTLinkType *) 0)) != NULL) {	/* Type */
	HText_beginAnchor(me->text, me->inUnderline, ID_A);
	HText_endAnchor(me->text, 0);
    }
}

/*
 *  This function checks whether we want to override
 *  the current default alignment for paragraphs and
 *  instead use that specified in the element's style
 *  sheet. - FM
 */
BOOLEAN LYoverride_default_alignment(HTStructured * me)
{
    if (!me)
	return NO;

    switch (me->sp[0].tag_number) {
    case HTML_BLOCKQUOTE:
    case HTML_BQ:
    case HTML_NOTE:
    case HTML_FN:
    case HTML_ADDRESS:
	me->sp->style->alignment = HT_LEFT;
	return YES;

    default:
	break;
    }
    return NO;
}

/*
 *  This function inserts newlines if needed to create double spacing,
 *  and sets the left margin for subsequent text to the second line
 *  indentation of the current style. - FM
 */
void LYEnsureDoubleSpace(HTStructured * me)
{
    if (!me || !me->text)
	return;

    if (!HText_LastLineEmpty(me->text, FALSE)) {
	HText_setLastChar(me->text, ' ');	/* absorb white space */
	HText_appendCharacter(me->text, '\r');
	HText_appendCharacter(me->text, '\r');
    } else if (!HText_PreviousLineEmpty(me->text, FALSE)) {
	HText_setLastChar(me->text, ' ');	/* absorb white space */
	HText_appendCharacter(me->text, '\r');
    } else if (me->List_Nesting_Level >= 0) {
	HText_NegateLineOne(me->text);
    }
    me->in_word = NO;
    return;
}

/*
 *  This function inserts a newline if needed to create single spacing,
 *  and sets the left margin for subsequent text to the second line
 *  indentation of the current style. - FM
 */
void LYEnsureSingleSpace(HTStructured * me)
{
    if (!me || !me->text)
	return;

    if (!HText_LastLineEmpty(me->text, FALSE)) {
	HText_setLastChar(me->text, ' ');	/* absorb white space */
	HText_appendCharacter(me->text, '\r');
    } else if (me->List_Nesting_Level >= 0) {
	HText_NegateLineOne(me->text);
    }
    me->in_word = NO;
    return;
}

/*
 *  This function resets paragraph alignments for block
 *  elements which do not have a defined style sheet. - FM
 */
void LYResetParagraphAlignment(HTStructured * me)
{
    if (!me)
	return;

    if (me->List_Nesting_Level >= 0 ||
	((me->Division_Level < 0) &&
	 (me->sp->style->id == ST_Normal ||
	  me->sp->style->id == ST_Preformatted))) {
	me->sp->style->alignment = HT_LEFT;
    } else {
	me->sp->style->alignment = (short) me->current_default_alignment;
    }
    return;
}

/*
 *  This example function checks whether the given anchor has
 *  an address with a file scheme, and if so, loads it into the
 *  the SGML parser's context->url element, which was passed as
 *  the second argument.  The handle_comment() calling function in
 *  SGML.c then calls LYDoCSI() in LYUtils.c to insert HTML markup
 *  into the corresponding stream, homologously to an SSI by an
 *  HTTP server. - FM
 *
 *  For functions similar to this but which depend on details of
 *  the HTML handler's internal data, the calling interface should
 *  be changed, and functions in SGML.c would have to make sure not
 *  to call such functions inappropriately (e.g., calling a function
 *  specific to the Lynx_HTML_Handler when SGML.c output goes to
 *  some other HTStructured object like in HTMLGen.c), or the new
 *  functions could be added to the SGML.h interface.
 */
BOOLEAN LYCheckForCSI(HTParentAnchor *anchor,
		      char **url)
{
    if (!(anchor && anchor->address))
	return FALSE;

    if (!isFILE_URL(anchor->address))
	return FALSE;

    if (!LYisLocalHost(anchor->address))
	return FALSE;

    StrAllocCopy(*url, anchor->address);
    return TRUE;
}

/*
 *  This function is called from the SGML parser to look at comments
 *  and see whether we should collect some info from them.  Currently
 *  it only looks for comments with Message-Id and Subject info, in the
 *  exact form generated by MHonArc for archived mailing list.  If found,
 *  the info is stored in the document's HTParentAnchor.  It can later be
 *  used for generating a mail response.
 *
 *  We are extra picky here because there isn't any official definition
 *  for these kinds of comments - we might (and still can) misinterpret
 *  arbitrary comments as something they aren't.
 *
 *  If something doesn't look right, for example invalid characters, the
 *  strings are not stored.  Mail responses will use something else as
 *  the subject, probably the document URL, and will not have an
 *  In-Reply-To header.
 *
 *  All this is a hack - to do this the right way, mailing list archivers
 *  would have to agree on some better mechanism to make this kind of info
 *  from original mail headers available, for example using LINK.  - kw
 */
BOOLEAN LYCommentHacks(HTParentAnchor *anchor,
		       const char *comment)
{
    const char *cp;
    size_t len;

    if (comment == NULL)
	return FALSE;

    if (!(anchor && anchor->address))
	return FALSE;

    if (StrNCmp(comment, "!--X-Message-Id: ", 17) == 0) {
	char *messageid = NULL;
	char *p;

	for (cp = comment + 17; *cp; cp++) {
	    if (UCH(*cp) >= 127 || !isgraph(UCH(*cp))) {
		break;
	    }
	}
	if (strcmp(cp, " --")) {
	    return FALSE;
	}
	cp = comment + 17;
	StrAllocCopy(messageid, cp);
	/* This should be ok - message-id should only contain 7-bit ASCII */
	if (!LYUCTranslateHTMLString(&messageid, 0, 0, NO, NO, YES, st_URL))
	    return FALSE;
	for (p = messageid; *p; p++) {
	    if (UCH(*p) >= 127 || !isgraph(UCH(*p))) {
		break;
	    }
	}
	if (strcmp(p, " --")) {
	    FREE(messageid);
	    return FALSE;
	}
	if ((p = strchr(messageid, '@')) == NULL || p[1] == '\0') {
	    FREE(messageid);
	    return FALSE;
	}
	p = messageid;
	if ((len = strlen(p)) >= 8 && !strcmp(&p[len - 3], " --")) {
	    p[len - 3] = '\0';
	} else {
	    FREE(messageid);
	    return FALSE;
	}
	if (HTAnchor_setMessageID(anchor, messageid)) {
	    FREE(messageid);
	    return TRUE;
	} else {
	    FREE(messageid);
	    return FALSE;
	}
    }
    if (StrNCmp(comment, "!--X-Subject: ", 14) == 0) {
	char *subject = NULL;
	char *p;

	for (cp = comment + 14; *cp; cp++) {
	    if (UCH(*cp) >= 127 || !isprint(UCH(*cp))) {
		return FALSE;
	    }
	}
	cp = comment + 14;
	StrAllocCopy(subject, cp);
	/* @@@
	 * This may not be the right thing for the subject - but mail
	 * subjects shouldn't contain 8-bit characters in raw form anyway.
	 * We have to unescape character entities, since that's what MHonArc
	 * seems to generate.  But if after that there are 8-bit characters
	 * the string is rejected.  We would probably not know correctly
	 * what charset to assume anyway - the mail sender's can differ from
	 * the archive's.  And the code for sending mail cannot deal well
	 * with 8-bit characters - we should not put them in the Subject
	 * header in raw form, but don't have MIME encoding implemented.
	 * Someone may want to do more about this...  - kw
	 */
	if (!LYUCTranslateHTMLString(&subject, 0, 0, NO, YES, NO, st_HTML))
	    return FALSE;
	for (p = subject; *p; p++) {
	    if (UCH(*p) >= 127 || !isprint(UCH(*p))) {
		FREE(subject);
		return FALSE;
	    }
	}
	p = subject;
	if ((len = strlen(p)) >= 4 && !strcmp(&p[len - 3], " --")) {
	    p[len - 3] = '\0';
	} else {
	    FREE(subject);
	    return FALSE;
	}
	if (HTAnchor_setSubject(anchor, subject)) {
	    FREE(subject);
	    return TRUE;
	} else {
	    FREE(subject);
	    return FALSE;
	}
    }

    return FALSE;
}

    /*
     * Create the Title with any left-angle-brackets converted to &lt; entities
     * and any ampersands converted to &amp; entities.  - FM
     *
     * Convert 8-bit letters to &#xUUUU to avoid dependencies from display
     * character set which may need changing.  Do NOT convert any 8-bit chars
     * if we have CJK display.  - LP
     */
void LYformTitle(char **dst,
		 const char *src)
{
    if (HTCJK == JAPANESE) {
	char *tmp_buffer = NULL;

	if ((tmp_buffer = (char *) malloc(strlen(src) + 1)) == 0)
	    outofmem(__FILE__, "LYformTitle");

	assert(tmp_buffer != NULL);

	switch (kanji_code) {	/* 1997/11/22 (Sat) 09:28:00 */
	case EUC:
	    TO_EUC((const unsigned char *) src, (unsigned char *) tmp_buffer);
	    break;
	case SJIS:
	    TO_SJIS((const unsigned char *) src, (unsigned char *) tmp_buffer);
	    break;
	default:
	    CTRACE((tfp, "\nLYformTitle: kanji_code is an unexpected value."));
	    strcpy(tmp_buffer, src);
	    break;
	}
	StrAllocCopy(*dst, tmp_buffer);
	FREE(tmp_buffer);
    } else {
	StrAllocCopy(*dst, src);
    }
}