summaryrefslogtreecommitdiff
path: root/libc/misc/wchar/wchar.c
blob: 25f8efa7b62c9acaf54d0667cae755f7cc161c07 (plain)
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

/*  Copyright (C) 2002, 2003, 2004     Manuel Novoa III
 *
 *  This library is free software; you can redistribute it and/or
 *  modify it under the terms of the GNU Library General Public
 *  License as published by the Free Software Foundation; either
 *  version 2 of the License, or (at your option) any later version.
 *
 *  This library is distributed in the hope that it will be useful,
 *  but WITHOUT ANY WARRANTY; without even the implied warranty of
 *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
 *  Library General Public License for more details.
 *
 *  You should have received a copy of the GNU Library General Public
 *  License along with this library; if not, write to the Free
 *  Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
 */

/*  ATTENTION!   ATTENTION!   ATTENTION!   ATTENTION!   ATTENTION!
 *
 *  Besides uClibc, I'm using this code in my libc for elks, which is
 *  a 16-bit environment with a fairly limited compiler.  It would make
 *  things much easier for me if this file isn't modified unnecessarily.
 *  In particular, please put any new or replacement functions somewhere
 *  else, and modify the makefile to use your version instead.
 *  Thanks.  Manuel
 *
 *  ATTENTION!   ATTENTION!   ATTENTION!   ATTENTION!   ATTENTION! */


/* May 23, 2002     Initial Notes:
 *
 * I'm still tweaking this stuff, but it passes the tests I've thrown
 * at it, and Erik needs it for the gcc port.  The glibc extension
 * __wcsnrtombs() hasn't been tested, as I didn't find a test for it
 * in the glibc source.  I also need to fix the behavior of
 * _wchar_utf8sntowcs() if the max number of wchars to convert is 0.
 *
 * UTF-8 -> wchar -> UTF-8 conversion tests on Markus Kuhn's UTF-8-demo.txt
 * file on my platform (x86) show about 5-10% faster conversion speed than
 * glibc with mbsrtowcs()/wcsrtombs() and almost twice as fast as glibc with
 * individual mbrtowc()/wcrtomb() calls.
 *
 * If 'DECODER' is defined, then _wchar_utf8sntowcs() will be compiled
 * as a fail-safe UTF-8 decoder appropriate for a terminal, etc.  which
 * needs to deal gracefully with whatever is sent to it.  In that mode,
 * it passes Markus Kuhn's UTF-8-test.txt stress test.  I plan to add
 * an arg to force that behavior, so the interface will be changing.
 *
 * I need to fix the error checking for 16-bit wide chars.  This isn't
 * an issue for uClibc, but may be for ELKS.  I'm currently not sure
 * if I'll use 16-bit, 32-bit, or configureable wchars in ELKS.
 *
 * July 1, 2002
 *
 * Fixed _wchar_utf8sntowcs() for the max number of wchars == 0 case.
 * Fixed nul-char bug in btowc(), and another in __mbsnrtowcs() for 8-bit
 *    locales.
 * Enabled building of a C/POSIX-locale-only version, so full locale support
 *    no longer needs to be enabled.
 *
 * Nov 4, 2002
 *
 * Fixed a bug in _wchar_wcsntoutf8s().  Don't store wcs position if dst is NULL.
 * Also, introduce an awful hack into _wchar_wcsntoutf8s() and wcsrtombs() in
 *   order to support %ls in printf.  See comments below for details.
 * Change behaviour of wc<->mb functions when in the C locale.  Now they do
 *   a 1-1 map for the range 0x80-UCHAR_MAX.  This is for backwards compatibility
 *   and consistency with the stds requirements that a printf format string by
 *   a valid multibyte string beginning and ending in it's initial shift state.
 *
 * Nov 5, 2002
 *
 * Forgot to change btowc and wctob when I changed the wc<->mb functions yesterday.
 *
 * Nov 7, 2002
 *
 * Add wcwidth and wcswidth, based on Markus Kuhn's wcwidth of 2002-05-08.
 *   Added some size/speed optimizations and integrated it into my locale
 *   framework.  Minimally tested at the moment, but the stub C-locale
 *   version (which most people would probably be using) should be fine.
 *
 * Nov 21, 2002
 *
 * Revert the wc<->mb changes from earlier this month involving the C-locale.
 * Add a couple of ugly hacks to support *wprintf.
 * Add a mini iconv() and iconv implementation (requires locale support).
 *
 * Aug 1, 2003
 * Bug fix for mbrtowc.
 *
 * Aug 18, 2003
 * Bug fix: _wchar_utf8sntowcs and _wchar_wcsntoutf8s now set errno if EILSEQ.
 *
 * Feb 11, 2004
 * Bug fix: Fix size check for remaining output space in iconv().
 *
 * Manuel
 */

#define memmove __memmove

#define _GNU_SOURCE
#define _ISOC99_SOURCE
#include <errno.h>
#include <stddef.h>
#include <limits.h>
#include <stdint.h>
#include <inttypes.h>
#include <stdlib.h>
#include <stdio.h>
#include <assert.h>
#include <locale.h>
#include <wchar.h>
#include <bits/uClibc_uwchar.h>

/**********************************************************************/
#ifdef __UCLIBC_HAS_LOCALE__
#ifdef __UCLIBC_MJN3_ONLY__
#ifdef L_iswspace
/* generates one warning */
#warning TODO: Fix Cc2wc* and Cwc2c* defines!
#endif
#endif /* __UCLIBC_MJN3_ONLY__ */

#define ENCODING		((__UCLIBC_CURLOCALE_DATA).encoding)

#define Cc2wc_IDX_SHIFT		__LOCALE_DATA_Cc2wc_IDX_SHIFT
#define Cc2wc_ROW_LEN		__LOCALE_DATA_Cc2wc_ROW_LEN
#define Cwc2c_DOMAIN_MAX	__LOCALE_DATA_Cwc2c_DOMAIN_MAX
#define Cwc2c_TI_SHIFT		__LOCALE_DATA_Cwc2c_TI_SHIFT
#define Cwc2c_TT_SHIFT		__LOCALE_DATA_Cwc2c_TT_SHIFT
#define Cwc2c_TI_LEN		__LOCALE_DATA_Cwc2c_TI_LEN

#ifndef __CTYPE_HAS_UTF_8_LOCALES
#warning __CTYPE_HAS_UTF_8_LOCALES not set!
#endif

#else  /* __UCLIBC_HAS_LOCALE__ */

#ifdef __UCLIBC_MJN3_ONLY__
#ifdef L_btowc
/* emit only once */
#warning fix preprocessor logic testing locale settings
#endif
#endif

#define ENCODING (__ctype_encoding_7_bit)
#ifdef __CTYPE_HAS_8_BIT_LOCALES
#error __CTYPE_HAS_8_BIT_LOCALES is defined!
#endif
#ifdef __CTYPE_HAS_UTF_8_LOCALES
#error __CTYPE_HAS_UTF_8_LOCALES is defined!
#endif
#undef L__wchar_utf8sntowcs
#undef L__wchar_wcsntoutf8s

#endif /* __UCLIBC_HAS_LOCALE__ */
/**********************************************************************/

#if WCHAR_MAX > 0xffffUL
#define UTF_8_MAX_LEN 6
#else
#define UTF_8_MAX_LEN 3
#endif

#define KUHN 1

extern size_t __mbrtowc (wchar_t *__restrict __pwc,
		       __const char *__restrict __s, size_t __n,
		       mbstate_t *__p) attribute_hidden;

extern size_t __wcrtomb (char *__restrict __s, wchar_t __wc,
		       mbstate_t *__restrict __ps) attribute_hidden;

/* Implementation-specific work functions. */

extern size_t _wchar_utf8sntowcs(wchar_t *__restrict pwc, size_t wn,
								 const char **__restrict src, size_t n,
								 mbstate_t *ps, int allow_continuation);

extern size_t _wchar_wcsntoutf8s(char *__restrict s, size_t n,
								 const wchar_t **__restrict src, size_t wn);

/* glibc extensions. */

extern size_t __mbsnrtowcs(wchar_t *__restrict dst,
				   const char **__restrict src,
				   size_t NMC, size_t len, mbstate_t *__restrict ps) attribute_hidden;

extern size_t __wcsnrtombs(char *__restrict dst,
				   const wchar_t **__restrict src,
				   size_t NWC, size_t len, mbstate_t *__restrict ps) attribute_hidden;

/**********************************************************************/
#ifdef L_btowc

wint_t attribute_hidden __btowc(int c)
{
#ifdef __CTYPE_HAS_8_BIT_LOCALES

	wchar_t wc;
	unsigned char buf[1];
	mbstate_t mbstate;

	if (c != EOF) {
		*buf = (unsigned char) c;
		mbstate.__mask = 0;		/* Initialize the mbstate. */
		if (__mbrtowc(&wc, buf, 1, &mbstate) <= 1) {
			return wc;
		}
	}
	return WEOF;

#else  /*  __CTYPE_HAS_8_BIT_LOCALES */

#ifdef __UCLIBC_HAS_LOCALE__
	assert((ENCODING == __ctype_encoding_7_bit)
		   || (ENCODING == __ctype_encoding_utf8));
#endif /* __UCLIBC_HAS_LOCALE__ */

	/* If we don't have 8-bit locale support, then this is trivial since
	 * anything outside of 0-0x7f is illegal in C/POSIX and UTF-8 locales. */
	return (((unsigned int)c) < 0x80) ? c : WEOF;

#endif /*  __CTYPE_HAS_8_BIT_LOCALES */
}
strong_alias(__btowc,btowc)

#endif
/**********************************************************************/
#ifdef L_wctob

/* Note: We completely ignore ps in all currently supported conversions. */

int wctob(wint_t c)
{
#ifdef __CTYPE_HAS_8_BIT_LOCALES

	unsigned char buf[MB_LEN_MAX];

	return (__wcrtomb(buf, c, NULL) == 1) ? *buf : EOF;

#else  /*  __CTYPE_HAS_8_BIT_LOCALES */

#ifdef __UCLIBC_HAS_LOCALE__
	assert((ENCODING == __ctype_encoding_7_bit)
		   || (ENCODING == __ctype_encoding_utf8));
#endif /* __UCLIBC_HAS_LOCALE__ */

	/* If we don't have 8-bit locale support, then this is trivial since
	 * anything outside of 0-0x7f is illegal in C/POSIX and UTF-8 locales. */
	
	/* TODO: need unsigned version of wint_t... */
/*  	return (((unsigned int)c) < 0x80) ? c : WEOF; */
	return ((c >= 0) && (c < 0x80)) ? c : EOF;

#endif /*  __CTYPE_HAS_8_BIT_LOCALES */
}

#endif
/**********************************************************************/
#ifdef L_mbsinit

int mbsinit(const mbstate_t *ps)
{
	return !ps || !ps->__mask;
}

#endif
/**********************************************************************/
#ifdef L_mbrlen

size_t __mbrlen(const char *__restrict s, size_t n, mbstate_t *__restrict ps)
{
	static mbstate_t mbstate;	/* Rely on bss 0-init. */

	return __mbrtowc(NULL, s, n, (ps != NULL) ? ps : &mbstate);
}

size_t mbrlen(const char *__restrict s, size_t n, mbstate_t *__restrict ps)
	 __attribute__ ((__weak__, __alias__("__mbrlen")));

#endif
/**********************************************************************/
#ifdef L_mbrtowc

size_t attribute_hidden __mbrtowc(wchar_t *__restrict pwc, const char *__restrict s,
			   size_t n, mbstate_t *__restrict ps)
{
	static mbstate_t mbstate;	/* Rely on bss 0-init. */
	wchar_t wcbuf[1];
	const char *p;
	size_t r;
	char empty_string[1];		/* Avoid static to be fPIC friendly. */

	if (!ps) {
		ps = &mbstate;
	}

	if (!s) {
		pwc = (wchar_t *) s;	/* NULL */
		empty_string[0] = 0;	/* Init the empty string when necessary. */
		s = empty_string;
		n = 1;
	} else if (!n) {
		/* TODO: change error code? */
		return (ps->__mask && (ps->__wc == 0xffffU))
			? ((size_t) -1) : ((size_t) -2);
	}

	p = s;

#ifdef __CTYPE_HAS_UTF_8_LOCALES
	/* Need to do this here since mbsrtowcs doesn't allow incompletes. */
	if (ENCODING == __ctype_encoding_utf8) {
		if (!pwc) {
			pwc = wcbuf;
		}
		r = _wchar_utf8sntowcs(pwc, 1, &p, n, ps, 1);
		return (r == 1) ? (p-s) : r; /* Need to return 0 if nul char. */
	}
#endif

#ifdef __UCLIBC_MJN3_ONLY__
#warning TODO: This adds a trailing nul!
#endif /* __UCLIBC_MJN3_ONLY__ */

	r = __mbsnrtowcs(wcbuf, &p, SIZE_MAX, 1, ps);

	if (((ssize_t) r) >= 0) {
		if (pwc) {
			*pwc = *wcbuf;
		}
	}
	return (size_t) r;
}
strong_alias(__mbrtowc,mbrtowc)

#endif
/**********************************************************************/
#ifdef L_wcrtomb

/* Note: We completely ignore ps in all currently supported conversions. */
/* TODO: Check for valid state anyway? */

size_t attribute_hidden __wcrtomb(register char *__restrict s, wchar_t wc,
			   mbstate_t *__restrict ps)
{
#ifdef __UCLIBC_MJN3_ONLY__
#warning TODO: Should wcsnrtombs nul-terminate unconditionally?  Check glibc.
#endif /* __UCLIBC_MJN3_ONLY__ */
	wchar_t wcbuf[1];
	const wchar_t *pwc;
	size_t r;
	char buf[MB_LEN_MAX];

	if (!s) {
		s = buf;
		wc = 0;
	}

	pwc = wcbuf;
	wcbuf[0] = wc;

	r = __wcsnrtombs(s, &pwc, 1, MB_LEN_MAX, ps);
	return (r != 0) ? r : 1;
}
strong_alias(__wcrtomb,wcrtomb)

#endif
/**********************************************************************/
#ifdef L_mbsrtowcs

size_t mbsrtowcs(wchar_t *__restrict dst, const char **__restrict src,
				 size_t len, mbstate_t *__restrict ps)
{
	static mbstate_t mbstate;	/* Rely on bss 0-init. */

	return __mbsnrtowcs(dst, src, SIZE_MAX, len,
						((ps != NULL) ? ps : &mbstate));
}

#endif
/**********************************************************************/
#ifdef L_wcsrtombs

/* Note: We completely ignore ps in all currently supported conversions.

 * TODO: Check for valid state anyway? */

size_t wcsrtombs(char *__restrict dst, const wchar_t **__restrict src,
				 size_t len, mbstate_t *__restrict ps)
{
	return __wcsnrtombs(dst, src, SIZE_MAX, len, ps);
}

#endif
/**********************************************************************/
#ifdef L__wchar_utf8sntowcs

/* Define DECODER to generate a UTF-8 decoder which passes Markus Kuhn's
 * UTF-8-test.txt strss test.
 */
/*  #define DECODER */

#ifdef DECODER
#ifndef KUHN
#define KUHN
#endif
#endif

size_t _wchar_utf8sntowcs(wchar_t *__restrict pwc, size_t wn,
						  const char **__restrict src, size_t n,
						  mbstate_t *ps, int allow_continuation)
{
	register const char *s;
	__uwchar_t mask;
	__uwchar_t wc;
	wchar_t wcbuf[1];
	size_t count;
	int incr;

	s = *src;

	assert(s != NULL);
	assert(ps != NULL);

	incr = 1;
	/* NOTE: The following is an AWFUL HACK!  In order to support %s in
	 * wprintf, we need to be able to compute the number of wchars needed
	 * for the mbs conversion, not to exceed the precision specified.
	 * But if dst is NULL, the return value is the length assuming a
	 * sufficiently sized buffer.  So, we allow passing of (wchar_t *) ps
	 * as pwc in order to flag that we really want the length, subject
	 * to the restricted buffer size and no partial conversions.
	 * See mbsnrtowcs() as well. */
	if (!pwc || (pwc == ((wchar_t *)ps))) {
		if (!pwc) {
			wn = SIZE_MAX;
		}
		pwc = wcbuf;
		incr = 0;
	}

	/* This is really here only to support the glibc extension function
	 * __mbsnrtowcs which apparently returns 0 if wn == 0 without any
	 * check on the validity of the mbstate. */
	if (!(count = wn)) {
		return 0;
	}

	if ((mask = (__uwchar_t) ps->__mask) != 0) { /* A continuation... */
#ifdef DECODER
		wc = (__uwchar_t) ps->__wc;
		if (n) {
			goto CONTINUE;
		}
		goto DONE;
#else
		if ((wc = (__uwchar_t) ps->__wc) != 0xffffU) {
			/* TODO: change error code here and below? */
			if (n) {
				goto CONTINUE;
			}
			goto DONE;
		}
		__set_errno(EILSEQ);
		return (size_t) -1;		/* We're in an error state. */
#endif
	}

	do {
		if (!n) {
			goto DONE;
		}
		--n;
		if ((wc = ((unsigned char) *s++)) >= 0x80) { /* Not ASCII... */
			mask = 0x40;
#ifdef __UCLIBC_MJN3_ONLY__
#warning TODO: Fix range for 16 bit wchar_t case.
#endif
			if ( ((unsigned char)(s[-1] - 0xc0)) < (0xfe - 0xc0) ) {
				goto START;
			}
		BAD:
#ifdef DECODER
			wc = 0xfffdU;
			goto COMPLETE;
#else
			ps->__mask = mask;
			ps->__wc = 0xffffU;
			__set_errno(EILSEQ);
			return (size_t) -1;	/* Illegal start byte! */
#endif

		CONTINUE:
			while (n) {
				--n;
				if ((*s & 0xc0) != 0x80) {
					goto BAD;
				}
				mask <<= 5;
				wc <<= 6;
				wc += (*s & 0x3f);	/* keep seperate for bcc (smaller code) */
				++s;
			START:
				wc &= ~(mask << 1);

				if ((wc & mask) == 0) {	/* Character completed. */
					if ((mask >>= 5) == 0x40) {
						mask += mask;
					}
					/* Check for invalid sequences (longer than necessary)
					 * and invalid chars.  */
					if ( (wc < mask) /* Sequence not minimal length. */
#ifdef KUHN
#if UTF_8_MAX_LEN == 3
#error broken since mask can overflow!!
						 /* For plane 0, these are the only defined values.*/
						 || (wc > 0xfffdU)
#else
						 /* Note that we don't need to worry about exceeding */
						 /* 31 bits as that is the most that UTF-8 provides. */
						 || ( ((__uwchar_t)(wc - 0xfffeU)) < 2)
#endif
						 || ( ((__uwchar_t)(wc - 0xd800U)) < (0xe000U - 0xd800U) )
#endif /* KUHN */
						 ) {
						goto BAD;
					}
					goto COMPLETE;
				}
			}
			/* Character potentially valid but incomplete. */
			if (!allow_continuation) {
				if (count != wn) {
					return 0;
				}
				/* NOTE: The following can fail if you allow and then disallow
				 * continuation!!! */
#if UTF_8_MAX_LEN == 3
#error broken since mask can overflow!!
#endif
				/* Need to back up... */
				do {
					--s;
				} while ((mask >>= 5) >= 0x40);
				goto DONE;
			}
			ps->__mask = (wchar_t) mask;
			ps->__wc = (wchar_t) wc;
			*src = s;
			return (size_t) -2;
		}
	COMPLETE:
		*pwc = wc;
		pwc += incr;
	}
#ifdef DECODER
	while (--count);
#else
	while (wc && --count);

	if (!wc) {
		s = NULL;
	}
#endif

 DONE:
	/* ps->__wc is irrelavent here. */
	ps->__mask = 0;
	if (pwc != wcbuf) {
		*src = s;
	}

	return wn - count;
}

#endif
/**********************************************************************/
#ifdef L__wchar_wcsntoutf8s

size_t _wchar_wcsntoutf8s(char *__restrict s, size_t n,
						  const wchar_t **__restrict src, size_t wn)
{
	register char *p;
	size_t len, t;
	__uwchar_t wc;
	const __uwchar_t *swc;
	int store;
	char buf[MB_LEN_MAX];
	char m;

	store = 1;
	/* NOTE: The following is an AWFUL HACK!  In order to support %ls in
	 * printf, we need to be able to compute the number of bytes needed
	 * for the mbs conversion, not to exceed the precision specified.
	 * But if dst is NULL, the return value is the length assuming a
	 * sufficiently sized buffer.  So, we allow passing of (char *) src
	 * as dst in order to flag that we really want the length, subject
	 * to the restricted buffer size and no partial conversions.
	 * See wcsnrtombs() as well. */
	if (!s || (s == ((char *) src))) {
		if (!s) {
			n = SIZE_MAX;
		}
	    s = buf;
		store = 0;
	}

	t = n;
	swc = (const __uwchar_t *) *src;

	assert(swc != NULL);

	while (wn && t) {
		wc = *swc;

		*s = wc;
		len = 1;

		if (wc >= 0x80) {
#ifdef KUHN
			if (
#if UTF_8_MAX_LEN == 3
				/* For plane 0, these are the only defined values.*/
				/* Note that we don't need to worry about exceeding */
				/* 31 bits as that is the most that UTF-8 provides. */
				(wc > 0xfffdU)
#else
				/* UTF_8_MAX_LEN == 6 */
				(wc > 0x7fffffffUL)
				|| ( ((__uwchar_t)(wc - 0xfffeU)) < 2)
#endif
				|| ( ((__uwchar_t)(wc - 0xd800U)) < (0xe000U - 0xd800U) )
				) {
				__set_errno(EILSEQ);
				return (size_t) -1;
			}
#else  /* KUHN */
#if UTF_8_MAX_LEN != 3
			if (wc > 0x7fffffffUL) { /* Value too large. */
				__set_errno(EILSEQ);
				return (size_t) -1;
			}
#endif
#endif /* KUHN */

			wc >>= 1;
			p = s;
			do {
				++p;
			} while (wc >>= 5);
			wc = *swc;
			if ((len = p - s) > t) { /* Not enough space. */
				break;
			}

			m = 0x80;
			while( p>s ) {
				m = (m >> 1) | 0x80;
				*--p = (wc & 0x3f) | 0x80;
				wc >>= 6;
			}
			*s |= (m << 1);
		} else if (wc == 0) {	/* End of string. */
			swc = NULL;
			break;
		}

		++swc;
		--wn;
		t -= len;
		if (store) {
			s += len;
		}
	}

	if (store) {
		*src = (const wchar_t *) swc;
	}

	return n - t;
}


#endif
/**********************************************************************/
#ifdef L___mbsnrtowcs

/* WARNING: We treat len as SIZE_MAX when dst is NULL! */

size_t attribute_hidden __mbsnrtowcs(wchar_t *__restrict dst, const char **__restrict src,
					size_t NMC, size_t len, mbstate_t *__restrict ps)
{
	static mbstate_t mbstate;	/* Rely on bss 0-init. */
	wchar_t wcbuf[1];
	const char *s;
	size_t count;
	int incr;

	if (!ps) {
		ps = &mbstate;
	}

#ifdef __CTYPE_HAS_UTF_8_LOCALES
	if (ENCODING == __ctype_encoding_utf8) {
		size_t r;
		return ((r = _wchar_utf8sntowcs(dst, len, src, NMC, ps, 1))
				!= (size_t) -2) ? r : 0;
	}
#endif
	incr = 1;
	/* NOTE: The following is an AWFUL HACK!  In order to support %s in
	 * wprintf, we need to be able to compute the number of wchars needed
	 * for the mbs conversion, not to exceed the precision specified.
	 * But if dst is NULL, the return value is the length assuming a
	 * sufficiently sized buffer.  So, we allow passing of ((wchar_t *)ps)
	 * as dst in order to flag that we really want the length, subject
	 * to the restricted buffer size and no partial conversions.
	 * See _wchar_utf8sntowcs() as well. */
	if (!dst || (dst == ((wchar_t *)ps))) {
		if (!dst) {
			len = SIZE_MAX;
		}
		dst = wcbuf;
		incr = 0;
	}

	/* Since all the following encodings are single-byte encodings... */
	if (len > NMC) {
		len = NMC;
	}

	count = len;
	s = *src;

#ifdef __CTYPE_HAS_8_BIT_LOCALES
	if (ENCODING == __ctype_encoding_8_bit) {
		wchar_t wc;
		while (count) {
			if ((wc = ((unsigned char)(*s))) >= 0x80) {	/* Non-ASCII... */
				wc -= 0x80;
				wc = __UCLIBC_CURLOCALE_DATA.tbl8c2wc[
						  (__UCLIBC_CURLOCALE_DATA.idx8c2wc[wc >> Cc2wc_IDX_SHIFT]
						   << Cc2wc_IDX_SHIFT) + (wc & (Cc2wc_ROW_LEN - 1))];
				if (!wc) {
					goto BAD;
				}
			}
			if (!(*dst = wc)) {
				s = NULL;
				break;
			}
			dst += incr;
			++s;
			--count;
		}
		if (dst != wcbuf) {
			*src = s;
		}
		return len - count;
	}
#endif

#ifdef __UCLIBC_HAS_LOCALE__
	assert(ENCODING == __ctype_encoding_7_bit);
#endif

	while (count) {
		if ((*dst = (unsigned char) *s) == 0) {
			s = NULL;
			break;
		}
		if (*dst >= 0x80) {
#ifdef __CTYPE_HAS_8_BIT_LOCALES
		BAD:
#endif
			__set_errno(EILSEQ);
			return (size_t) -1;
		}
		++s;
		dst += incr;
		--count;
	}
	if (dst != wcbuf) {
		*src = s;
	}
	return len - count;
}

size_t mbsnrtowcs(wchar_t *__restrict dst, const char **__restrict src,
				  size_t NMC, size_t len, mbstate_t *__restrict ps)
	 __attribute__ ((__weak__, __alias__("__mbsnrtowcs")));

#endif
/**********************************************************************/
#ifdef L___wcsnrtombs

/* WARNING: We treat len as SIZE_MAX when dst is NULL! */

/* Note: We completely ignore ps in all currently supported conversions.
 * TODO: Check for valid state anyway? */

size_t attribute_hidden __wcsnrtombs(char *__restrict dst, const wchar_t **__restrict src,
					size_t NWC, size_t len, mbstate_t *__restrict ps)
{
	const __uwchar_t *s;
	size_t count;
	int incr;
	char buf[MB_LEN_MAX];

#ifdef __CTYPE_HAS_UTF_8_LOCALES
	if (ENCODING == __ctype_encoding_utf8) {
		return _wchar_wcsntoutf8s(dst, len, src, NWC);
	}
#endif /* __CTYPE_HAS_UTF_8_LOCALES */

	incr = 1;
	/* NOTE: The following is an AWFUL HACK!  In order to support %ls in
	 * printf, we need to be able to compute the number of bytes needed
	 * for the mbs conversion, not to exceed the precision specified.
	 * But if dst is NULL, the return value is the length assuming a
	 * sufficiently sized buffer.  So, we allow passing of (char *) src
	 * as dst in order to flag that we really want the length, subject
	 * to the restricted buffer size and no partial conversions.
	 * See _wchar_wcsntoutf8s() as well. */
	if (!dst || (dst == ((char *) src))) {
		if (!dst) {
			len = SIZE_MAX;
		}
		dst = buf;
		incr = 0;
	}

	/* Since all the following encodings are single-byte encodings... */
	if (len > NWC) {
		len = NWC;
	}

	count = len;
	s = (const __uwchar_t *) *src;

#ifdef __CTYPE_HAS_8_BIT_LOCALES
	if (ENCODING == __ctype_encoding_8_bit) {
		__uwchar_t wc;
		__uwchar_t u;
		while (count) {
			if ((wc = *s) <= 0x7f) {
				if (!(*dst = (unsigned char) wc)) {
					s = NULL;
					break;
				}
			} else {
				u = 0;
				if (wc <= Cwc2c_DOMAIN_MAX) {
					u = __UCLIBC_CURLOCALE_DATA.idx8wc2c[wc >> (Cwc2c_TI_SHIFT
														+ Cwc2c_TT_SHIFT)];
					u = __UCLIBC_CURLOCALE_DATA.tbl8wc2c[(u << Cwc2c_TI_SHIFT)
									+ ((wc >> Cwc2c_TT_SHIFT)
									   & ((1 << Cwc2c_TI_SHIFT)-1))];
					u = __UCLIBC_CURLOCALE_DATA.tbl8wc2c[Cwc2c_TI_LEN
									+ (u << Cwc2c_TT_SHIFT)
									+ (wc & ((1 << Cwc2c_TT_SHIFT)-1))];
				}

#define __WCHAR_REPLACEMENT_CHAR '?'
#ifdef __WCHAR_REPLACEMENT_CHAR
				*dst = (unsigned char) ( u ? u : __WCHAR_REPLACEMENT_CHAR );
#else  /* __WCHAR_REPLACEMENT_CHAR */
				if (!u) {
					goto BAD;
				}
				*dst = (unsigned char) u;
#endif /* __WCHAR_REPLACEMENT_CHAR */
			}
			++s;
			dst += incr;
			--count;
		}
		if (dst != buf) {
			*src = (const wchar_t *) s;
		}
		return len - count;
	}
#endif /* __CTYPE_HAS_8_BIT_LOCALES */

#ifdef __UCLIBC_HAS_LOCALE__
	assert(ENCODING == __ctype_encoding_7_bit);
#endif

	while (count) {
		if (*s >= 0x80) {
#if defined(__CTYPE_HAS_8_BIT_LOCALES) && !defined(__WCHAR_REPLACEMENT_CHAR)
		BAD:
#endif
			__set_errno(EILSEQ);
			return (size_t) -1;
		}
		if ((*dst = (unsigned char) *s) == 0) {
			s = NULL;
			break;
		}
		++s;
		dst += incr;
		--count;
	}
	if (dst != buf) {
		*src = (const wchar_t *) s;
	}
	return len - count;
}

size_t wcsnrtombs(char *__restrict dst, const wchar_t **__restrict src,
				  size_t NWC, size_t len, mbstate_t *__restrict ps)
	 __attribute__ ((__weak__, __alias__("__wcsnrtombs")));

#endif
/**********************************************************************/
#ifdef L_wcswidth

#ifdef __UCLIBC_MJN3_ONLY__
#warning REMINDER: If we start doing translit, wcwidth and wcswidth will need updating.
#warning TODO: Update wcwidth to match latest by Kuhn.
#endif

#if defined(__UCLIBC_HAS_LOCALE__) && \
( defined(__CTYPE_HAS_8_BIT_LOCALES) || defined(__CTYPE_HAS_UTF_8_LOCALES) )

static const unsigned char new_idx[] = {
	0,    5,    5,    6,   10,   15,   28,   39, 
	48,   48,   71,   94,  113,  128,  139,  154, 
	175,  186,  188,  188,  188,  188,  188,  188, 
	203,  208,  208,  208,  208,  208,  208,  208, 
	208,  219,  219,  219,  222,  222,  222,  222, 
	222,  222,  222,  222,  222,  222,  222,  224, 
	224,  231,  231,  231,  231,  231,  231,  231, 
	231,  231,  231,  231,  231,  231,  231,  231, 
	231,  231,  231,  231,  231,  231,  231,  231, 
	231,  231,  231,  231,  231,  231,  231,  231, 
	231,  231,  231,  231,  231,  231,  231,  231, 
	231,  231,  231,  231,  231,  231,  231,  231, 
	231,  231,  231,  231,  231,  231,  231,  231, 
	231,  231,  231,  231,  231,  231,  231,  231, 
	231,  231,  231,  231,  231,  231,  231,  231, 
	231,  231,  231,  231,  231,  231,  231,  231, 
	231,  231,  231,  231,  231,  231,  231,  231, 
	231,  231,  231,  231,  231,  231,  231,  231, 
	231,  231,  231,  231,  231,  231,  231,  231, 
	231,  231,  231,  231,  231,  231,  231,  231, 
	231,  231,  231,  231,  231,  233,  233,  233, 
	233,  233,  233,  233,  234,  234,  234,  234, 
	234,  234,  234,  234,  234,  234,  234,  234, 
	234,  234,  234,  234,  234,  234,  234,  234, 
	234,  234,  234,  234,  234,  234,  234,  234, 
	234,  234,  234,  234,  234,  234,  234,  234, 
	234,  234,  234,  234,  234,  234,  234,  234, 
	236,  236,  236,  236,  236,  236,  236,  236, 
	236,  236,  236,  236,  236,  236,  236,  236, 
	236,  236,  236,  236,  236,  236,  236,  236, 
	236,  236,  236,  236,  236,  236,  236,  236, 
	236,  237,  237,  238,  241,  241,  242,  249, 
	255, 
};

static const unsigned char new_tbl[] = {
	0x00, 0x01, 0x20, 0x7f, 0xa0, 0x00, 0x00, 0x50, 
	0x60, 0x70, 0x00, 0x83, 0x87, 0x88, 0x8a, 0x00, 
	0x91, 0xa2, 0xa3, 0xba, 0xbb, 0xbe, 0xbf, 0xc0, 
	0xc1, 0xc3, 0xc4, 0xc5, 0x00, 0x4b, 0x56, 0x70, 
	0x71, 0xd6, 0xe5, 0xe7, 0xe9, 0xea, 0xee, 0x00, 
	0x0f, 0x10, 0x11, 0x12, 0x30, 0x4b, 0xa6, 0xb1, 
	0x00, 0x01, 0x03, 0x3c, 0x3d, 0x41, 0x49, 0x4d, 
	0x4e, 0x51, 0x55, 0x62, 0x64, 0x81, 0x82, 0xbc, 
	0xbd, 0xc1, 0xc5, 0xcd, 0xce, 0xe2, 0xe4, 0x00, 
	0x02, 0x03, 0x3c, 0x3d, 0x41, 0x43, 0x47, 0x49, 
	0x4b, 0x4e, 0x70, 0x72, 0x81, 0x83, 0xbc, 0xbd, 
	0xc1, 0xc6, 0xc7, 0xc9, 0xcd, 0xce, 0x00, 0x01, 
	0x02, 0x3c, 0x3d, 0x3f, 0x40, 0x41, 0x44, 0x4d, 
	0x4e, 0x56, 0x57, 0x82, 0x83, 0xc0, 0xc1, 0xcd, 
	0xce, 0x00, 0x3e, 0x41, 0x46, 0x49, 0x4a, 0x4e, 
	0x55, 0x57, 0xbf, 0xc0, 0xc6, 0xc7, 0xcc, 0xce, 
	0x00, 0x41, 0x44, 0x4d, 0x4e, 0xca, 0xcb, 0xd2, 
	0xd5, 0xd6, 0xd7, 0x00, 0x31, 0x32, 0x34, 0x3b, 
	0x47, 0x4f, 0xb1, 0xb2, 0xb4, 0xba, 0xbb, 0xbd, 
	0xc8, 0xce, 0x00, 0x18, 0x1a, 0x35, 0x36, 0x37, 
	0x38, 0x39, 0x3a, 0x71, 0x7f, 0x80, 0x85, 0x86, 
	0x88, 0x90, 0x98, 0x99, 0xbd, 0xc6, 0xc7, 0x00, 
	0x2d, 0x31, 0x32, 0x33, 0x36, 0x38, 0x39, 0x3a, 
	0x58, 0x5a, 0x00, 0x60, 0x00, 0x12, 0x15, 0x32, 
	0x35, 0x52, 0x54, 0x72, 0x74, 0xb7, 0xbe, 0xc6, 
	0xc7, 0xc9, 0xd4, 0x00, 0x0b, 0x0f, 0xa9, 0xaa, 
	0x00, 0x0b, 0x10, 0x2a, 0x2f, 0x60, 0x64, 0x6a, 
	0x70, 0xd0, 0xeb, 0x00, 0x29, 0x2b, 0x00, 0x80, 
	0x00, 0x2a, 0x30, 0x3f, 0x40, 0x99, 0x9b, 0x00, 
	0xd0, 0x00, 0x00, 0xa4, 0x00, 0x00, 0x00, 0x1e, 
	0x1f, 0x00, 0x00, 0x10, 0x20, 0x24, 0x30, 0x70, 
	0xff, 0x00, 0x61, 0xe0, 0xe7, 0xf9, 0xfc, 
};

static const signed char new_wtbl[] = {
	0,   -1,    1,   -1,    1,    1,    0,    1, 
	0,    1,    1,    0,    1,    0,    1,    1, 
	0,    1,    0,    1,    0,    1,    0,    1, 
	0,    1,    0,    1,    1,    0,    1,    0, 
	1,    0,    1,    0,    1,    0,    1,    1, 
	0,    1,    0,    1,    0,    1,    0,    1, 
	1,    0,    1,    0,    1,    0,    1,    0, 
	1,    0,    1,    0,    1,    0,    1,    0, 
	1,    0,    1,    0,    1,    0,    1,    1, 
	0,    1,    0,    1,    0,    1,    0,    1, 
	0,    1,    0,    1,    0,    1,    0,    1, 
	0,    1,    0,    1,    0,    1,    1,    0, 
	1,    0,    1,    0,    1,    0,    1,    0, 
	1,    0,    1,    0,    1,    0,    1,    0, 
	1,    1,    0,    1,    0,    1,    0,    1, 
	0,    1,    0,    1,    0,    1,    0,    1, 
	1,    0,    1,    0,    1,    0,    1,    0, 
	1,    0,    1,    1,    0,    1,    0,    1, 
	0,    1,    0,    1,    0,    1,    0,    1, 
	0,    1,    1,    0,    1,    0,    1,    0, 
	1,    0,    1,    0,    1,    0,    1,    0, 
	1,    0,    1,    0,    1,    0,    1,    1, 
	0,    1,    0,    1,    0,    1,    0,    1, 
	0,    1,    2,    0,    1,    0,    1,    0, 
	1,    0,    1,    0,    1,    0,    1,    0, 
	1,    0,    1,    1,    0,    1,    0,    1, 
	1,    0,    1,    0,    1,    0,    1,    0, 
	1,    0,    1,    1,    2,    1,    1,    2, 
	2,    0,    2,    1,    2,    0,    2,    2, 
	1,    1,    2,    1,    1,    2,    1,    0, 
	1,    1,    0,    1,    0,    1,    2,    1, 
	0,    2,    1,    2,    1,    0,    1, 
};

int wcswidth(const wchar_t *pwcs, size_t n)
{
    int h, l, m, count;
    wchar_t wc;
    unsigned char b;

	if (ENCODING == __ctype_encoding_7_bit) {
		size_t i;
		
		for (i = 0 ; (i < n) && pwcs[i] ; i++) {
			if (pwcs[i] != ((unsigned char)(pwcs[i]))) {
				return -1;
			}
		}
	}
#ifdef __CTYPE_HAS_8_BIT_LOCALES
	else if (ENCODING == __ctype_encoding_8_bit) {
		mbstate_t mbstate;

		mbstate.__mask = 0;			/* Initialize the mbstate. */
		if (__wcsnrtombs(NULL, &pwcs, n, SIZE_MAX, &mbstate) == ((size_t) - 1)) {
			return -1;
		}
	}
#endif /* __CTYPE_HAS_8_BIT_LOCALES */
#if defined(__CTYPE_HAS_UTF_8_LOCALES) && defined(KUHN)
	/* For stricter handling of allowed unicode values... see comments above. */
	else if (ENCODING == __ctype_encoding_utf8) {
		size_t i;
		
		for (i = 0 ; (i < n) && pwcs[i] ; i++) {
			if ( (((__uwchar_t)((pwcs[i]) - 0xfffeU)) < 2)
				 || (((__uwchar_t)((pwcs[i]) - 0xd800U)) < (0xe000U - 0xd800U))
				) {
				return -1;
			}
		}
	}
#endif /* __CTYPE_HAS_UTF_8_LOCALES */

    for (count = 0 ; n && (wc = *pwcs++) ; n--) {
		if (wc <= 0xff) {
			/* If we're here, wc != 0. */
			if ((wc < 32) || ((wc >= 0x7f) && (wc < 0xa0))) {
				return -1;
			}
			++count;
			continue;
		}
		if (((unsigned int) wc) <= 0xffff) {
			b = wc & 0xff;
			h = (wc >> 8);
			l = new_idx[h];
			h = new_idx[h+1];
			while ((m = (l+h) >> 1) != l) {
				if (b >= new_tbl[m]) {
					l = m;
				} else {		/* wc < tbl[m] */
					h = m;
				}
			}
			count += new_wtbl[l]; /* none should be -1. */
			continue;
		}

		/* Redo this to minimize average number of compares?*/
		if (wc >= 0x1d167) {
			if (wc <= 0x1d1ad) {
				if ((wc <= 0x1d169
					 || (wc >= 0x1d173
						 && (wc <= 0x1d182
							 || (wc >= 0x1d185
								 && (wc <= 0x1d18b
									 || (wc >= 0x1d1aa))))))
					) {
					continue;
				}
			} else if (((wc >= 0xe0020) && (wc <= 0xe007f)) || (wc == 0xe0001)) {
				continue;
			} else if ((wc >= 0x20000) && (wc <= 0x2ffff)) {
				++count;		/* need 2.. add one here */
			}
#if (WCHAR_MAX > 0x7fffffffL)
			else if (wc > 0x7fffffffL) {
				return -1;
			}
#endif /* (WCHAR_MAX > 0x7fffffffL) */
		}

		++count;
    }

    return count;
}

#else  /*  __UCLIBC_HAS_LOCALE__ */

int wcswidth(const wchar_t *pwcs, size_t n)
{
	int count;
	wchar_t wc;

    for (count = 0 ; n && (wc = *pwcs++) ; n--) {
		if (wc <= 0xff) {
			/* If we're here, wc != 0. */
			if ((wc < 32) || ((wc >= 0x7f) && (wc < 0xa0))) {
				return -1;
			}
			++count;
			continue;
		} else {
			return -1;
		}
	}

	return count;
}

#endif /*  __UCLIBC_HAS_LOCALE__ */

#endif
/**********************************************************************/
#ifdef L_wcwidth

int wcwidth(wchar_t wc)
{
    return wcswidth(&wc, 1);
}

#endif
/**********************************************************************/


typedef struct {
	mbstate_t tostate;
	mbstate_t fromstate;
	int tocodeset;
	int fromcodeset;
	int frombom;
	int tobom;
	int fromcodeset0;
	int frombom0;
	int tobom0;
	int skip_invalid_input;		/* To support iconv -c option. */
} _UC_iconv_t;



#ifdef L_iconv

#include <iconv.h>
#include <string.h>
#include <endian.h>
#include <byteswap.h>

#if (__BYTE_ORDER != __BIG_ENDIAN) && (__BYTE_ORDER != __LITTLE_ENDIAN)
#error unsupported endianness for iconv
#endif

#ifndef __CTYPE_HAS_8_BIT_LOCALES
#error currently iconv requires 8 bit locales
#endif
#ifndef __CTYPE_HAS_UTF_8_LOCALES
#error currently iconv requires UTF-8 locales
#endif


enum {
	IC_WCHAR_T = 0xe0,
	IC_MULTIBYTE = 0xe0,
#if __BYTE_ORDER == __BIG_ENDIAN
	IC_UCS_4 =	0xec,
	IC_UTF_32 = 0xe4,
	IC_UCS_2 =	0xe2,
	IC_UTF_16 = 0xea,
#else
	IC_UCS_4 =	0xed,
	IC_UTF_32 = 0xe5,
	IC_UCS_2 =	0xe3,
	IC_UTF_16 = 0xeb,
#endif
	IC_UTF_8 = 2,
	IC_ASCII = 1
};

/* For the multibyte
 * bit 0 means swap endian
 * bit 1 means 2 byte
 * bit 2 means 4 byte
 *
 */

const unsigned char __iconv_codesets[] =
	"\x0a\xe0""WCHAR_T\x00"		/* superset of UCS-4 but platform-endian */
#if __BYTE_ORDER == __BIG_ENDIAN
	"\x08\xec""UCS-4\x00"		/* always BE */
	"\x0a\xec""UCS-4BE\x00"
	"\x0a\xed""UCS-4LE\x00"
	"\x09\fe4""UTF-32\x00"		/* platform endian with BOM */
	"\x0b\xe4""UTF-32BE\x00"
	"\x0b\xe5""UTF-32LE\x00"
	"\x08\xe2""UCS-2\x00"		/* always BE */
	"\x0a\xe2""UCS-2BE\x00"
	"\x0a\xe3""UCS-2LE\x00"
	"\x09\xea""UTF-16\x00"		/* platform endian with BOM */
	"\x0b\xea""UTF-16BE\x00"
	"\x0b\xeb""UTF-16LE\x00"
#elif __BYTE_ORDER == __LITTLE_ENDIAN
	"\x08\xed""UCS-4\x00"		/* always BE */
	"\x0a\xed""UCS-4BE\x00"
	"\x0a\xec""UCS-4LE\x00"
	"\x09\xf4""UTF-32\x00"		/* platform endian with BOM */
	"\x0b\xe5""UTF-32BE\x00"
	"\x0b\xe4""UTF-32LE\x00"
	"\x08\xe3""UCS-2\x00"		/* always BE */
	"\x0a\xe3""UCS-2BE\x00"
	"\x0a\xe2""UCS-2LE\x00"
	"\x09\xfa""UTF-16\x00"		/* platform endian with BOM */
	"\x0b\xeb""UTF-16BE\x00"
	"\x0b\xea""UTF-16LE\x00"
#endif
	"\x08\x02""UTF-8\x00"
	"\x0b\x01""US-ASCII\x00"
	"\x07\x01""ASCII";			/* Must be last! (special case to save a nul) */

static int find_codeset(const char *name)
{
	const unsigned char *s;
	int codeset;

	for (s = __iconv_codesets ; *s ; s += *s) {
		if (!strcasecmp(s+2, name)) {
			return s[1];
		}
	}

	/* The following is ripped from find_locale in locale.c. */

	/* TODO: maybe CODESET_LIST + *s ??? */
	/* 7bit is 1, UTF-8 is 2, 8-bit is >= 3 */
	codeset = 2;
	s = __LOCALE_DATA_CODESET_LIST;
	do {
		++codeset;		/* Increment codeset first. */
		if (!strcasecmp(__LOCALE_DATA_CODESET_LIST+*s, name)) {
			return codeset;
		}
	} while (*++s);

	return 0;			/* No matching codeset! */
}

iconv_t weak_function iconv_open(const char *tocode, const char *fromcode)
{
	register _UC_iconv_t *px;
	int tocodeset, fromcodeset;

	if (((tocodeset = find_codeset(tocode)) != 0)
		&& ((fromcodeset = find_codeset(fromcode)) != 0)) {
		if ((px = malloc(sizeof(_UC_iconv_t))) != NULL) {
			px->tocodeset = tocodeset;
			px->tobom0 = px->tobom = (tocodeset & 0x10) >> 4;
			px->fromcodeset0 = px->fromcodeset = fromcodeset;
			px->frombom0 = px->frombom = (fromcodeset & 0x10) >> 4;
			px->skip_invalid_input = px->tostate.__mask
				= px->fromstate.__mask = 0;
			return (iconv_t) px;
		}
	} else {
		__set_errno(EINVAL);
	}
	return (iconv_t)(-1);
}

int weak_function iconv_close(iconv_t cd)
{
	free(cd);

	return 0;
}

size_t weak_function iconv(iconv_t cd, char **__restrict inbuf,
						   size_t *__restrict inbytesleft,
						   char **__restrict outbuf,
						   size_t *__restrict outbytesleft)
{
	_UC_iconv_t *px = (_UC_iconv_t *) cd;
	size_t nrcount, r;
	wchar_t wc, wc2;
	int inci, inco;

	assert(px != (_UC_iconv_t *)(-1));
	assert(sizeof(wchar_t) == 4);

	if (!inbuf || !*inbuf) {	/* Need to reinitialze conversion state. */
		/* Note: For shift-state encodings we possibly need to output the
		 * shift sequence to return to initial state! */
		if ((px->fromcodeset & 0xf0) == 0xe0) {
		}
		px->tostate.__mask = px->fromstate.__mask = 0;
		px->fromcodeset = px->fromcodeset0;
		px->tobom = px->tobom0;
		px->frombom = px->frombom0;
		return 0;
	}

	nrcount = 0;
	while (*inbytesleft) {
		if (!*outbytesleft) {
		TOO_BIG:
			__set_errno(E2BIG);
			return (size_t) -1;
		}

		inci = inco = 1;
		if (px->fromcodeset >= IC_MULTIBYTE) {
			inci = (px->fromcodeset == IC_WCHAR_T) ? 4: (px->fromcodeset & 6);
			if (*inbytesleft < inci) goto INVALID;
			wc = (((unsigned int)((unsigned char)((*inbuf)[0]))) << 8)
				+ ((unsigned char)((*inbuf)[1]));
			if (inci == 4) {
				wc = (((unsigned int)((unsigned char)((*inbuf)[2]))) << 8)
					+ ((unsigned char)((*inbuf)[3])) + (wc << 16);
				if (!(px->fromcodeset & 1)) wc = bswap_32(wc);
			} else {
				if (!(px->fromcodeset & 1)) wc = bswap_16(wc);
				if (((px->fromcodeset & IC_UTF_16) == IC_UTF_16)
					 && (((__uwchar_t)(wc - 0xd800U)) < (0xdc00U - 0xd800U))
					) {			/* surrogate */
					wc =- 0xd800U;
					if (*inbytesleft < 4) goto INVALID;
					wc2 = (((unsigned int)((unsigned char)((*inbuf)[2]))) << 8)
						+ ((unsigned char)((*inbuf)[3]));
					if (!(px->fromcodeset & 1)) wc = bswap_16(wc2);
					if (((__uwchar_t)(wc2 -= 0xdc00U)) < (0xe0000U - 0xdc00U)) {
						goto ILLEGAL;
					}
					inci = 4;	/* Change inci here in case skipping illegals. */
					wc = 0x10000UL + (wc << 10) + wc2;
				}
			}

			if (px->frombom) {
				px->frombom = 0;
				if ((wc == 0xfeffU)
					|| (wc == ((inci == 4)
							   ? (((wchar_t) 0xfffe0000UL))
							   : ((wchar_t)(0xfffeUL))))
					) {
					if (wc != 0xfeffU) {
						px->fromcodeset ^= 1; /* toggle endianness */
						wc = 0xfeffU;
					}
					if (!px->frombom) {
						goto BOM_SKIP_OUTPUT;
					}
					goto GOT_BOM;
				}
			}

			if (px->fromcodeset != IC_WCHAR_T) {
				if (((__uwchar_t) wc) > (((px->fromcodeset & IC_UCS_4) == IC_UCS_4)
										 ? 0x7fffffffUL : 0x10ffffUL)
#ifdef KUHN
					|| (((__uwchar_t)(wc - 0xfffeU)) < 2)
					|| (((__uwchar_t)(wc - 0xd800U)) < (0xe000U - 0xd800U))
#endif
					) {
					goto ILLEGAL;
				}
			}
		} else if (px->fromcodeset == IC_UTF_8) {
			const char *p = *inbuf;
			r = _wchar_utf8sntowcs(&wc, 1, &p, *inbytesleft, &px->fromstate, 0);
			if (((ssize_t) r) <= 0) { /* either EILSEQ or incomplete or nul */
				if (((ssize_t) r) < 0) { /* either EILSEQ or incomplete or nul */
					assert((r == (size_t)(-1)) || (r == (size_t)(-2)));
					if (r == (size_t)(-2)) {
					INVALID:
						__set_errno(EINVAL);
					} else {
						px->fromstate.__mask = 0;
						inci = 1;
					ILLEGAL:
						if (px->skip_invalid_input) {
							px->skip_invalid_input = 2;	/* flag for iconv utility */
							goto BOM_SKIP_OUTPUT;
						}
						__set_errno(EILSEQ);
					}
					return (size_t)(-1);
				}
#ifdef __UCLIBC_MJN3_ONLY__
#warning TODO: optimize this.
#endif
				if (p != NULL) { /* incomplete char case */
					goto INVALID;
				}
				p = *inbuf + 1;	/* nul */
			}
			inci = p - *inbuf;
		} else if ((wc = ((unsigned char)(**inbuf))) >= 0x80) {	/* Non-ASCII... */
			if (px->fromcodeset == IC_ASCII) { /* US-ASCII codeset */
				goto ILLEGAL;
			} else {			/* some other 8-bit ascii-extension codeset */
				const __codeset_8_bit_t *c8b
					= __locale_mmap->codeset_8_bit + px->fromcodeset - 3;
				wc -= 0x80;
				wc = __UCLIBC_CURLOCALE_DATA.tbl8c2wc[
							 (c8b->idx8c2wc[wc >> Cc2wc_IDX_SHIFT]
							  << Cc2wc_IDX_SHIFT) + (wc & (Cc2wc_ROW_LEN - 1))];
				if (!wc) {
					goto ILLEGAL;
				}
			}
		}


		if (px->tobom) {
			inci = 0;
			wc = 0xfeffU;
	GOT_BOM:
			px->tobom = 0;
		}

		if (px->tocodeset >= IC_MULTIBYTE) {
			inco = (px->tocodeset == IC_WCHAR_T) ? 4: (px->tocodeset & 6);
			if (*outbytesleft < inco) goto TOO_BIG;
			if (px->tocodeset != IC_WCHAR_T) {
				if (((__uwchar_t) wc) > (((px->tocodeset & IC_UCS_4) == IC_UCS_4)
										 ? 0x7fffffffUL : 0x10ffffUL)
#ifdef KUHN
					|| (((__uwchar_t)(wc - 0xfffeU)) < 2)
					|| (((__uwchar_t)(wc - 0xd800U)) < (0xe000U - 0xd800U))
#endif
					) {
				REPLACE_32:
					wc = 0xfffd;
					++nrcount;
				}
			}
			if (inco == 4) {
				if (px->tocodeset & 1) wc = bswap_32(wc);
			} else {
				if (((__uwchar_t)wc ) > 0xffffU) {
					if ((px->tocodeset & IC_UTF_16) != IC_UTF_16) {
						goto REPLACE_32;
					}
					if (*outbytesleft < (inco = 4)) goto TOO_BIG;
					wc2 = 0xdc00U + (wc & 0x3ff);
					wc = 0xd800U + ((wc >> 10) & 0x3ff);
					if (px->tocodeset & 1) {
						wc = bswap_16(wc);
						wc2 = bswap_16(wc2);
					}
					wc += (wc2 << 16);
				} else if (px->tocodeset & 1) wc = bswap_16(wc);
			}				
			(*outbuf)[0] = (char)((unsigned char)(wc));
			(*outbuf)[1] = (char)((unsigned char)(wc >> 8));
			if (inco == 4) {
				(*outbuf)[2] = (char)((unsigned char)(wc >> 16));
				(*outbuf)[3] = (char)((unsigned char)(wc >> 24));
			}
		} else if (px->tocodeset == IC_UTF_8) {
			const wchar_t *pw = &wc;
			do {
				r = _wchar_wcsntoutf8s(*outbuf, *outbytesleft, &pw, 1);
				if (r != (size_t)(-1)) {
#ifdef __UCLIBC_MJN3_ONLY__
#warning TODO: What happens for a nul?
#endif
					if (r == 0) {
						if (wc != 0) {
							goto TOO_BIG;
						}
						++r;
					}
					break;
				}
				wc = 0xfffdU;
				++nrcount;
			} while (1);
			inco = r;
		} else if (((__uwchar_t)(wc)) < 0x80) {
		CHAR_GOOD:
				**outbuf = wc;
		} else {
			if ((px->tocodeset != 0x01) && (wc <= Cwc2c_DOMAIN_MAX)) {
				const __codeset_8_bit_t *c8b
					= __locale_mmap->codeset_8_bit + px->tocodeset - 3;
				__uwchar_t u;
				u = c8b->idx8wc2c[wc >> (Cwc2c_TI_SHIFT + Cwc2c_TT_SHIFT)];
				u = __UCLIBC_CURLOCALE_DATA.tbl8wc2c[(u << Cwc2c_TI_SHIFT)
						 + ((wc >> Cwc2c_TT_SHIFT)
							& ((1 << Cwc2c_TI_SHIFT)-1))];
				wc = __UCLIBC_CURLOCALE_DATA.tbl8wc2c[Cwc2c_TI_LEN
						 + (u << Cwc2c_TT_SHIFT)
						 + (wc & ((1 << Cwc2c_TT_SHIFT)-1))];
				if (wc) {
					goto CHAR_GOOD;
				}
			}
			**outbuf = '?';
			++nrcount;
		}

		*outbuf += inco;
		*outbytesleft -= inco;
	BOM_SKIP_OUTPUT:
		*inbuf += inci;
		*inbytesleft -= inci;
	}
	return nrcount;
}

#endif
/**********************************************************************/
#ifdef L_iconv_main

#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <wchar.h>
#include <iconv.h>
#include <stdarg.h>
#include <libgen.h>

extern const unsigned char __iconv_codesets[];

#define IBUF BUFSIZ
#define OBUF BUFSIZ

char *progname;
int hide_errors;

static void error_msg(const char *fmt, ...) 
	 __attribute__ ((noreturn, format (printf, 1, 2)));

static void error_msg(const char *fmt, ...) 
{
	va_list arg;

	if (!hide_errors) {
		fprintf(stderr, "%s: ", progname);
		va_start(arg, fmt);
		vfprintf(stderr, fmt, arg);
		va_end(arg);
	}

	exit(EXIT_FAILURE);
}

int main(int argc, char **argv)
{
	FILE *ifile;
	FILE *ofile = stdout;
	const char *p;
	const char *s;
	static const char opt_chars[] = "tfocsl";
	                              /* 012345 */
	const char *opts[sizeof(opt_chars)]; /* last is infile name */
	iconv_t ic;
	char ibuf[IBUF];
	char obuf[OBUF];
	char *pi;
	char *po;
	size_t ni, no, r, pos;

	hide_errors = 0;

	for (s = opt_chars ; *s ; s++) {
		opts[ s - opt_chars ] = NULL;
	}

	progname = *argv;
	while (--argc) {
		p = *++argv;
		if ((*p != '-') || (*++p == 0)) {
			break;
		}
		do {
			if ((s = strchr(opt_chars,*p)) == NULL) {
			USAGE:
				s = basename(progname);
				fprintf(stderr,
						"%s [-cs] -f fromcode -t tocode [-o outputfile] [inputfile ...]\n"
						"  or\n%s -l\n", s, s);
				return EXIT_FAILURE;
			}
			if ((s - opt_chars) < 3) {
				if ((--argc == 0) || opts[s - opt_chars]) {
					goto USAGE;
				}
				opts[s - opt_chars] = *++argv;
			} else {
				opts[s - opt_chars] = p;
			}
		} while (*++p);
	}

	if (opts[5]) {				/* -l */
		fprintf(stderr, "Recognized codesets:\n");
		for (s = __iconv_codesets ; *s ; s += *s) {
			fprintf(stderr,"  %s\n", s+2);
		}
		s = __LOCALE_DATA_CODESET_LIST;
		do {
			fprintf(stderr,"  %s\n", __LOCALE_DATA_CODESET_LIST+ (unsigned char)(*s));
		} while (*++s);

		return EXIT_SUCCESS;
	}

	if (opts[4]) {
		hide_errors = 1;
	}

	if (!opts[0] || !opts[1]) {
		goto USAGE;
	}
	if ((ic = iconv_open(opts[0],opts[1])) == ((iconv_t)(-1))) {
		error_msg( "unsupported codeset in %s -> %s conversion\n", opts[0], opts[1]);
	}
	if (opts[3]) {				/* -c */
		((_UC_iconv_t *) ic)->skip_invalid_input = 1;
	}

	if ((s = opts[2]) != NULL) {
		if (!(ofile = fopen(s, "w"))) {
			error_msg( "couldn't open %s for writing\n", s);
		}
	}

	pos = ni = 0;
	do {
		if (!argc || ((**argv == '-') && !((*argv)[1]))) {
			ifile = stdin;		/* we don't check for duplicates */
		} else if (!(ifile = fopen(*argv, "r"))) {
			error_msg( "couldn't open %s for reading\n", *argv);
		}

		while ((r = fread(ibuf + ni, 1, IBUF - ni, ifile)) > 0) {
			pos += r;
			ni += r;
			no = OBUF;
			pi = ibuf;
			po = obuf;
			if ((r = iconv(ic, &pi, &ni, &po, &no)) == ((size_t)(-1))) {
				if ((errno != EINVAL) && (errno != E2BIG)) {
					error_msg( "iconv failed at pos %lu : %m\n", (unsigned long) (pos - ni));
				}
			}
			if ((r = OBUF - no) > 0) {
				if (fwrite(obuf, 1, OBUF - no, ofile) < r) {
					error_msg( "write error\n");
				}
			}
			if (ni) {			/* still bytes in buffer! */
				memmove(ibuf, pi, ni);
			}
		}

		if (ferror(ifile)) {
			error_msg( "read error\n");
		}

		++argv;

		if (ifile != stdin) {
			fclose(ifile);
		}

	} while (--argc > 0);

	iconv_close(ic);

	if (ni) {
		error_msg( "incomplete sequence\n");
	}

	return (((_UC_iconv_t *) ic)->skip_invalid_input < 2)
		? EXIT_SUCCESS : EXIT_FAILURE;
}

#endif
/**********************************************************************/