File: gutf8.c

package info (click to toggle)
glib2.0 2.58.3-2+deb10u2
  • links: PTS, VCS
  • area: main
  • in suites: bullseye, buster, buster-backports, buster-proposed-updates, sid
  • size: 48,956 kB
  • sloc: ansic: 452,656; xml: 16,781; python: 6,149; makefile: 3,776; sh: 1,499; perl: 1,140; cpp: 9
file content (1848 lines) | stat: -rw-r--r-- 47,834 bytes parent folder | download
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
/* gutf8.c - Operations on UTF-8 strings.
 *
 * Copyright (C) 1999 Tom Tromey
 * Copyright (C) 2000 Red Hat, Inc.
 *
 * This library is free software; you can redistribute it and/or
 * modify it under the terms of the GNU Lesser General Public
 * License as published by the Free Software Foundation; either
 * version 2.1 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
 * Lesser General Public License for more details.
 *
 * You should have received a copy of the GNU Lesser General Public
 * License along with this library; if not, see <http://www.gnu.org/licenses/>.
 */

#include "config.h"

#include <stdlib.h>
#ifdef HAVE_CODESET
#include <langinfo.h>
#endif
#include <string.h>

#ifdef G_PLATFORM_WIN32
#include <stdio.h>
#define STRICT
#include <windows.h>
#undef STRICT
#endif

#include "gconvert.h"
#include "ghash.h"
#include "gstrfuncs.h"
#include "gtestutils.h"
#include "gtypes.h"
#include "gthread.h"
#include "glibintl.h"
#include "gunicodeprivate.h"

#define UTF8_COMPUTE(Char, Mask, Len)					      \
  if (Char < 128)							      \
    {									      \
      Len = 1;								      \
      Mask = 0x7f;							      \
    }									      \
  else if ((Char & 0xe0) == 0xc0)					      \
    {									      \
      Len = 2;								      \
      Mask = 0x1f;							      \
    }									      \
  else if ((Char & 0xf0) == 0xe0)					      \
    {									      \
      Len = 3;								      \
      Mask = 0x0f;							      \
    }									      \
  else if ((Char & 0xf8) == 0xf0)					      \
    {									      \
      Len = 4;								      \
      Mask = 0x07;							      \
    }									      \
  else if ((Char & 0xfc) == 0xf8)					      \
    {									      \
      Len = 5;								      \
      Mask = 0x03;							      \
    }									      \
  else if ((Char & 0xfe) == 0xfc)					      \
    {									      \
      Len = 6;								      \
      Mask = 0x01;							      \
    }									      \
  else									      \
    Len = -1;

#define UTF8_LENGTH(Char)              \
  ((Char) < 0x80 ? 1 :                 \
   ((Char) < 0x800 ? 2 :               \
    ((Char) < 0x10000 ? 3 :            \
     ((Char) < 0x200000 ? 4 :          \
      ((Char) < 0x4000000 ? 5 : 6)))))
   

#define UTF8_GET(Result, Chars, Count, Mask, Len)			      \
  (Result) = (Chars)[0] & (Mask);					      \
  for ((Count) = 1; (Count) < (Len); ++(Count))				      \
    {									      \
      if (((Chars)[(Count)] & 0xc0) != 0x80)				      \
	{								      \
	  (Result) = -1;						      \
	  break;							      \
	}								      \
      (Result) <<= 6;							      \
      (Result) |= ((Chars)[(Count)] & 0x3f);				      \
    }
    
/*
 * Check whether a Unicode (5.2) char is in a valid range.
 *
 * The first check comes from the Unicode guarantee to never encode
 * a point above 0x0010ffff, since UTF-16 couldn't represent it.
 * 
 * The second check covers surrogate pairs (category Cs).
 *
 * @param Char the character
 */
#define UNICODE_VALID(Char)                   \
    ((Char) < 0x110000 &&                     \
     (((Char) & 0xFFFFF800) != 0xD800))

    
static const gchar utf8_skip_data[256] = {
  1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
  1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
  1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
  1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
  1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
  1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
  2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,
  3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,4,4,4,4,4,4,4,4,5,5,5,5,6,6,1,1
};

const gchar * const g_utf8_skip = utf8_skip_data;

/**
 * g_utf8_find_prev_char:
 * @str: pointer to the beginning of a UTF-8 encoded string
 * @p: pointer to some position within @str
 * 
 * Given a position @p with a UTF-8 encoded string @str, find the start
 * of the previous UTF-8 character starting before @p. Returns %NULL if no
 * UTF-8 characters are present in @str before @p.
 *
 * @p does not have to be at the beginning of a UTF-8 character. No check
 * is made to see if the character found is actually valid other than
 * it starts with an appropriate byte.
 *
 * Returns: a pointer to the found character or %NULL.
 */
gchar *
g_utf8_find_prev_char (const char *str,
		       const char *p)
{
  for (--p; p >= str; --p)
    {
      if ((*p & 0xc0) != 0x80)
	return (gchar *)p;
    }
  return NULL;
}

/**
 * g_utf8_find_next_char:
 * @p: a pointer to a position within a UTF-8 encoded string
 * @end: (nullable): a pointer to the byte following the end of the string,
 *     or %NULL to indicate that the string is nul-terminated
 *
 * Finds the start of the next UTF-8 character in the string after @p.
 *
 * @p does not have to be at the beginning of a UTF-8 character. No check
 * is made to see if the character found is actually valid other than
 * it starts with an appropriate byte.
 * 
 * If @end is %NULL, the return value will never be %NULL: if the end of the
 * string is reached, a pointer to the terminating nul byte is returned. If
 * @end is non-%NULL, the return value will be %NULL if the end of the string
 * is reached.
 *
 * Returns: (nullable): a pointer to the found character or %NULL if @end is
 *    set and is reached
 */
gchar *
g_utf8_find_next_char (const gchar *p,
		       const gchar *end)
{
  if (end)
    {
      for (++p; p < end && (*p & 0xc0) == 0x80; ++p)
        ;
      return (p >= end) ? NULL : (gchar *)p;
    }
  else
    {
      for (++p; (*p & 0xc0) == 0x80; ++p)
        ;
      return (gchar *)p;
    }
}

/**
 * g_utf8_prev_char:
 * @p: a pointer to a position within a UTF-8 encoded string
 *
 * Finds the previous UTF-8 character in the string before @p.
 *
 * @p does not have to be at the beginning of a UTF-8 character. No check
 * is made to see if the character found is actually valid other than
 * it starts with an appropriate byte. If @p might be the first
 * character of the string, you must use g_utf8_find_prev_char() instead.
 * 
 * Returns: a pointer to the found character
 */
gchar *
g_utf8_prev_char (const gchar *p)
{
  while (TRUE)
    {
      p--;
      if ((*p & 0xc0) != 0x80)
	return (gchar *)p;
    }
}
 
/**
 * g_utf8_strlen:
 * @p: pointer to the start of a UTF-8 encoded string
 * @max: the maximum number of bytes to examine. If @max
 *       is less than 0, then the string is assumed to be
 *       nul-terminated. If @max is 0, @p will not be examined and
 *       may be %NULL. If @max is greater than 0, up to @max
 *       bytes are examined
 *
 * Computes the length of the string in characters, not including
 * the terminating nul character. If the @max'th byte falls in the
 * middle of a character, the last (partial) character is not counted.
 *
 * Returns: the length of the string in characters
 */
glong
g_utf8_strlen (const gchar *p,
               gssize       max)
{
  glong len = 0;
  const gchar *start = p;
  g_return_val_if_fail (p != NULL || max == 0, 0);

  if (max < 0)
    {
      while (*p)
        {
          p = g_utf8_next_char (p);
          ++len;
        }
    }
  else
    {
      if (max == 0 || !*p)
        return 0;

      p = g_utf8_next_char (p);

      while (p - start < max && *p)
        {
          ++len;
          p = g_utf8_next_char (p);
        }

      /* only do the last len increment if we got a complete
       * char (don't count partial chars)
       */
      if (p - start <= max)
        ++len;
    }

  return len;
}

/**
 * g_utf8_substring:
 * @str: a UTF-8 encoded string
 * @start_pos: a character offset within @str
 * @end_pos: another character offset within @str
 *
 * Copies a substring out of a UTF-8 encoded string.
 * The substring will contain @end_pos - @start_pos characters.
 *
 * Returns: a newly allocated copy of the requested
 *     substring. Free with g_free() when no longer needed.
 *
 * Since: 2.30
 */
gchar *
g_utf8_substring (const gchar *str,
                  glong        start_pos,
                  glong        end_pos)
{
  gchar *start, *end, *out;

  start = g_utf8_offset_to_pointer (str, start_pos);
  end = g_utf8_offset_to_pointer (start, end_pos - start_pos);

  out = g_malloc (end - start + 1);
  memcpy (out, start, end - start);
  out[end - start] = 0;

  return out;
}

/**
 * g_utf8_get_char:
 * @p: a pointer to Unicode character encoded as UTF-8
 * 
 * Converts a sequence of bytes encoded as UTF-8 to a Unicode character.
 *
 * If @p does not point to a valid UTF-8 encoded character, results
 * are undefined. If you are not sure that the bytes are complete
 * valid Unicode characters, you should use g_utf8_get_char_validated()
 * instead.
 * 
 * Returns: the resulting character
 */
gunichar
g_utf8_get_char (const gchar *p)
{
  int i, mask = 0, len;
  gunichar result;
  unsigned char c = (unsigned char) *p;

  UTF8_COMPUTE (c, mask, len);
  if (len == -1)
    return (gunichar)-1;
  UTF8_GET (result, p, i, mask, len);

  return result;
}

/**
 * g_utf8_offset_to_pointer:
 * @str: a UTF-8 encoded string
 * @offset: a character offset within @str
 *
 * Converts from an integer character offset to a pointer to a position
 * within the string.
 *
 * Since 2.10, this function allows to pass a negative @offset to
 * step backwards. It is usually worth stepping backwards from the end
 * instead of forwards if @offset is in the last fourth of the string,
 * since moving forward is about 3 times faster than moving backward.
 *
 * Note that this function doesn't abort when reaching the end of @str.
 * Therefore you should be sure that @offset is within string boundaries
 * before calling that function. Call g_utf8_strlen() when unsure.
 * This limitation exists as this function is called frequently during
 * text rendering and therefore has to be as fast as possible.
 *
 * Returns: the resulting pointer
 */
gchar *
g_utf8_offset_to_pointer  (const gchar *str,
			   glong        offset)
{
  const gchar *s = str;

  if (offset > 0) 
    while (offset--)
      s = g_utf8_next_char (s);
  else
    {
      const char *s1;

      /* This nice technique for fast backwards stepping 
       * through a UTF-8 string was dubbed "stutter stepping" 
       * by its inventor, Larry Ewing.
       */
      while (offset)
	{
	  s1 = s;
	  s += offset;
	  while ((*s & 0xc0) == 0x80)
	    s--;

	  offset += g_utf8_pointer_to_offset (s, s1);
	}
    }

  return (gchar *)s;
}

/**
 * g_utf8_pointer_to_offset:
 * @str: a UTF-8 encoded string
 * @pos: a pointer to a position within @str
 * 
 * Converts from a pointer to position within a string to a integer
 * character offset.
 *
 * Since 2.10, this function allows @pos to be before @str, and returns
 * a negative offset in this case.
 * 
 * Returns: the resulting character offset
 */
glong    
g_utf8_pointer_to_offset (const gchar *str,
			  const gchar *pos)
{
  const gchar *s = str;
  glong offset = 0;    

  if (pos < str) 
    offset = - g_utf8_pointer_to_offset (pos, str);
  else
    while (s < pos)
      {
	s = g_utf8_next_char (s);
	offset++;
      }
  
  return offset;
}


/**
 * g_utf8_strncpy:
 * @dest: buffer to fill with characters from @src
 * @src: UTF-8 encoded string
 * @n: character count
 * 
 * Like the standard C strncpy() function, but copies a given number
 * of characters instead of a given number of bytes. The @src string
 * must be valid UTF-8 encoded text. (Use g_utf8_validate() on all
 * text before trying to use UTF-8 utility functions with it.)
 * 
 * Note you must ensure @dest is at least 4 * @n to fit the
 * largest possible UTF-8 characters
 *
 * Returns: @dest
 */
gchar *
g_utf8_strncpy (gchar       *dest,
		const gchar *src,
		gsize        n)
{
  const gchar *s = src;
  while (n && *s)
    {
      s = g_utf8_next_char(s);
      n--;
    }
  strncpy(dest, src, s - src);
  dest[s - src] = 0;
  return dest;
}

/* unicode_strchr */

/**
 * g_unichar_to_utf8:
 * @c: a Unicode character code
 * @outbuf: (out caller-allocates) (optional): output buffer, must have at
 *       least 6 bytes of space. If %NULL, the length will be computed and
 *       returned and nothing will be written to @outbuf.
 * 
 * Converts a single character to UTF-8.
 * 
 * Returns: number of bytes written
 */
int
g_unichar_to_utf8 (gunichar c,
		   gchar   *outbuf)
{
  /* If this gets modified, also update the copy in g_string_insert_unichar() */
  guint len = 0;    
  int first;
  int i;

  if (c < 0x80)
    {
      first = 0;
      len = 1;
    }
  else if (c < 0x800)
    {
      first = 0xc0;
      len = 2;
    }
  else if (c < 0x10000)
    {
      first = 0xe0;
      len = 3;
    }
   else if (c < 0x200000)
    {
      first = 0xf0;
      len = 4;
    }
  else if (c < 0x4000000)
    {
      first = 0xf8;
      len = 5;
    }
  else
    {
      first = 0xfc;
      len = 6;
    }

  if (outbuf)
    {
      for (i = len - 1; i > 0; --i)
	{
	  outbuf[i] = (c & 0x3f) | 0x80;
	  c >>= 6;
	}
      outbuf[0] = c | first;
    }

  return len;
}

/**
 * g_utf8_strchr:
 * @p: a nul-terminated UTF-8 encoded string
 * @len: the maximum length of @p
 * @c: a Unicode character
 * 
 * Finds the leftmost occurrence of the given Unicode character
 * in a UTF-8 encoded string, while limiting the search to @len bytes.
 * If @len is -1, allow unbounded search.
 * 
 * Returns: %NULL if the string does not contain the character, 
 *     otherwise, a pointer to the start of the leftmost occurrence
 *     of the character in the string.
 */
gchar *
g_utf8_strchr (const char *p,
	       gssize      len,
	       gunichar    c)
{
  gchar ch[10];

  gint charlen = g_unichar_to_utf8 (c, ch);
  ch[charlen] = '\0';
  
  return g_strstr_len (p, len, ch);
}


/**
 * g_utf8_strrchr:
 * @p: a nul-terminated UTF-8 encoded string
 * @len: the maximum length of @p
 * @c: a Unicode character
 * 
 * Find the rightmost occurrence of the given Unicode character
 * in a UTF-8 encoded string, while limiting the search to @len bytes.
 * If @len is -1, allow unbounded search.
 * 
 * Returns: %NULL if the string does not contain the character, 
 *     otherwise, a pointer to the start of the rightmost occurrence
 *     of the character in the string.
 */
gchar *
g_utf8_strrchr (const char *p,
		gssize      len,
		gunichar    c)
{
  gchar ch[10];

  gint charlen = g_unichar_to_utf8 (c, ch);
  ch[charlen] = '\0';
  
  return g_strrstr_len (p, len, ch);
}


/* Like g_utf8_get_char, but take a maximum length
 * and return (gunichar)-2 on incomplete trailing character;
 * also check for malformed or overlong sequences
 * and return (gunichar)-1 in this case.
 */
static inline gunichar
g_utf8_get_char_extended (const  gchar *p,
			  gssize max_len)
{
  guint i, len;
  gunichar min_code;
  gunichar wc = (guchar) *p;
  const gunichar partial_sequence = (gunichar) -2;
  const gunichar malformed_sequence = (gunichar) -1;

  if (wc < 0x80)
    {
      return wc;
    }
  else if (G_UNLIKELY (wc < 0xc0))
    {
      return malformed_sequence;
    }
  else if (wc < 0xe0)
    {
      len = 2;
      wc &= 0x1f;
      min_code = 1 << 7;
    }
  else if (wc < 0xf0)
    {
      len = 3;
      wc &= 0x0f;
      min_code = 1 << 11;
    }
  else if (wc < 0xf8)
    {
      len = 4;
      wc &= 0x07;
      min_code = 1 << 16;
    }
  else if (wc < 0xfc)
    {
      len = 5;
      wc &= 0x03;
      min_code = 1 << 21;
    }
  else if (wc < 0xfe)
    {
      len = 6;
      wc &= 0x01;
      min_code = 1 << 26;
    }
  else
    {
      return malformed_sequence;
    }

  if (G_UNLIKELY (max_len >= 0 && len > max_len))
    {
      for (i = 1; i < max_len; i++)
	{
	  if ((((guchar *)p)[i] & 0xc0) != 0x80)
	    return malformed_sequence;
	}
      return partial_sequence;
    }

  for (i = 1; i < len; ++i)
    {
      gunichar ch = ((guchar *)p)[i];

      if (G_UNLIKELY ((ch & 0xc0) != 0x80))
	{
	  if (ch)
	    return malformed_sequence;
	  else
	    return partial_sequence;
	}

      wc <<= 6;
      wc |= (ch & 0x3f);
    }

  if (G_UNLIKELY (wc < min_code))
    return malformed_sequence;

  return wc;
}

/**
 * g_utf8_get_char_validated:
 * @p: a pointer to Unicode character encoded as UTF-8
 * @max_len: the maximum number of bytes to read, or -1 if @p is nul-terminated
 *
 * Convert a sequence of bytes encoded as UTF-8 to a Unicode character.
 * This function checks for incomplete characters, for invalid characters
 * such as characters that are out of the range of Unicode, and for
 * overlong encodings of valid characters.
 *
 * Note that g_utf8_get_char_validated() returns (gunichar)-2 if
 * @max_len is positive and any of the bytes in the first UTF-8 character
 * sequence are nul.
 * 
 * Returns: the resulting character. If @p points to a partial
 *     sequence at the end of a string that could begin a valid 
 *     character (or if @max_len is zero), returns (gunichar)-2; 
 *     otherwise, if @p does not point to a valid UTF-8 encoded 
 *     Unicode character, returns (gunichar)-1.
 */
gunichar
g_utf8_get_char_validated (const gchar *p,
			   gssize       max_len)
{
  gunichar result;

  if (max_len == 0)
    return (gunichar)-2;

  result = g_utf8_get_char_extended (p, max_len);

  if (result & 0x80000000)
    return result;
  else if (!UNICODE_VALID (result))
    return (gunichar)-1;
  else
    return result;
}

#define CONT_BYTE_FAST(p) ((guchar)*p++ & 0x3f)

/**
 * g_utf8_to_ucs4_fast:
 * @str: a UTF-8 encoded string
 * @len: the maximum length of @str to use, in bytes. If @len < 0,
 *     then the string is nul-terminated.
 * @items_written: (out caller-allocates) (optional): location to store the
 *     number of characters in the result, or %NULL.
 *
 * Convert a string from UTF-8 to a 32-bit fixed width
 * representation as UCS-4, assuming valid UTF-8 input.
 * This function is roughly twice as fast as g_utf8_to_ucs4()
 * but does no error checking on the input. A trailing 0 character
 * will be added to the string after the converted text.
 * 
 * Returns: a pointer to a newly allocated UCS-4 string.
 *     This value must be freed with g_free().
 */
gunichar *
g_utf8_to_ucs4_fast (const gchar *str,
		     glong        len,              
		     glong       *items_written)    
{
  gunichar *result;
  gint n_chars, i;
  const gchar *p;

  g_return_val_if_fail (str != NULL, NULL);

  p = str;
  n_chars = 0;
  if (len < 0)
    {
      while (*p)
	{
	  p = g_utf8_next_char (p);
	  ++n_chars;
	}
    }
  else
    {
      while (p < str + len && *p)
	{
	  p = g_utf8_next_char (p);
	  ++n_chars;
	}
    }
  
  result = g_new (gunichar, n_chars + 1);
  
  p = str;
  for (i=0; i < n_chars; i++)
    {
      guchar first = (guchar)*p++;
      gunichar wc;

      if (first < 0xc0)
	{
          /* We really hope first < 0x80, but we don't want to test an
           * extra branch for invalid input, which this function
           * does not care about. Handling unexpected continuation bytes
           * here will do the least damage. */
	  wc = first;
	}
      else
	{
          gunichar c1 = CONT_BYTE_FAST(p);
          if (first < 0xe0)
            {
              wc = ((first & 0x1f) << 6) | c1;
            }
          else
            {
              gunichar c2 = CONT_BYTE_FAST(p);
              if (first < 0xf0)
                {
                  wc = ((first & 0x0f) << 12) | (c1 << 6) | c2;
                }
              else
                {
                  gunichar c3 = CONT_BYTE_FAST(p);
                  wc = ((first & 0x07) << 18) | (c1 << 12) | (c2 << 6) | c3;
                  if (G_UNLIKELY (first >= 0xf8))
                    {
                      /* This can't be valid UTF-8, but g_utf8_next_char()
                       * and company allow out-of-range sequences */
                      gunichar mask = 1 << 20;
                      while ((wc & mask) != 0)
                        {
                          wc <<= 6;
                          wc |= CONT_BYTE_FAST(p);
                          mask <<= 5;
                        }
                      wc &= mask - 1;
                    }
                }
            }
	}
      result[i] = wc;
    }
  result[i] = 0;

  if (items_written)
    *items_written = i;

  return result;
}

static gpointer
try_malloc_n (gsize n_blocks, gsize n_block_bytes, GError **error)
{
    gpointer ptr = g_try_malloc_n (n_blocks, n_block_bytes);
    if (ptr == NULL)
      g_set_error_literal (error, G_CONVERT_ERROR, G_CONVERT_ERROR_NO_MEMORY,
                           _("Failed to allocate memory"));
    return ptr;
}

/**
 * g_utf8_to_ucs4:
 * @str: a UTF-8 encoded string
 * @len: the maximum length of @str to use, in bytes. If @len < 0,
 *     then the string is nul-terminated.
 * @items_read: (out caller-allocates) (optional): location to store number of
  *    bytes read, or %NULL.
 *     If %NULL, then %G_CONVERT_ERROR_PARTIAL_INPUT will be
 *     returned in case @str contains a trailing partial
 *     character. If an error occurs then the index of the
 *     invalid input is stored here.
 * @items_written: (out caller-allocates) (optional): location to store number
 *     of characters written or %NULL. The value here stored does not include
 *     the trailing 0 character.
 * @error: location to store the error occurring, or %NULL to ignore
 *     errors. Any of the errors in #GConvertError other than
 *     %G_CONVERT_ERROR_NO_CONVERSION may occur.
 *
 * Convert a string from UTF-8 to a 32-bit fixed width
 * representation as UCS-4. A trailing 0 character will be added to the
 * string after the converted text.
 * 
 * Returns: a pointer to a newly allocated UCS-4 string.
 *     This value must be freed with g_free(). If an error occurs,
 *     %NULL will be returned and @error set.
 */
gunichar *
g_utf8_to_ucs4 (const gchar *str,
		glong        len,             
		glong       *items_read,      
		glong       *items_written,   
		GError     **error)
{
  gunichar *result = NULL;
  gint n_chars, i;
  const gchar *in;
  
  in = str;
  n_chars = 0;
  while ((len < 0 || str + len - in > 0) && *in)
    {
      gunichar wc = g_utf8_get_char_extended (in, len < 0 ? 6 : str + len - in);
      if (wc & 0x80000000)
	{
	  if (wc == (gunichar)-2)
	    {
	      if (items_read)
		break;
	      else
		g_set_error_literal (error, G_CONVERT_ERROR, G_CONVERT_ERROR_PARTIAL_INPUT,
                                     _("Partial character sequence at end of input"));
	    }
	  else
	    g_set_error_literal (error, G_CONVERT_ERROR, G_CONVERT_ERROR_ILLEGAL_SEQUENCE,
                                 _("Invalid byte sequence in conversion input"));

	  goto err_out;
	}

      n_chars++;

      in = g_utf8_next_char (in);
    }

  result = try_malloc_n (n_chars + 1, sizeof (gunichar), error);
  if (result == NULL)
      goto err_out;

  in = str;
  for (i=0; i < n_chars; i++)
    {
      result[i] = g_utf8_get_char (in);
      in = g_utf8_next_char (in);
    }
  result[i] = 0;

  if (items_written)
    *items_written = n_chars;

 err_out:
  if (items_read)
    *items_read = in - str;

  return result;
}

/**
 * g_ucs4_to_utf8:
 * @str: a UCS-4 encoded string
 * @len: the maximum length (number of characters) of @str to use. 
 *     If @len < 0, then the string is nul-terminated.
 * @items_read: (out caller-allocates) (optional): location to store number of
 *     characters read, or %NULL.
 * @items_written: (out caller-allocates) (optional): location to store number
 *     of bytes written or %NULL. The value here stored does not include the
 *     trailing 0 byte.
 * @error: location to store the error occurring, or %NULL to ignore
 *         errors. Any of the errors in #GConvertError other than
 *         %G_CONVERT_ERROR_NO_CONVERSION may occur.
 *
 * Convert a string from a 32-bit fixed width representation as UCS-4.
 * to UTF-8. The result will be terminated with a 0 byte.
 * 
 * Returns: a pointer to a newly allocated UTF-8 string.
 *     This value must be freed with g_free(). If an error occurs,
 *     %NULL will be returned and @error set. In that case, @items_read
 *     will be set to the position of the first invalid input character.
 */
gchar *
g_ucs4_to_utf8 (const gunichar *str,
		glong           len,              
		glong          *items_read,       
		glong          *items_written,    
		GError        **error)
{
  gint result_length;
  gchar *result = NULL;
  gchar *p;
  gint i;

  result_length = 0;
  for (i = 0; len < 0 || i < len ; i++)
    {
      if (!str[i])
	break;

      if (str[i] >= 0x80000000)
	{
	  g_set_error_literal (error, G_CONVERT_ERROR, G_CONVERT_ERROR_ILLEGAL_SEQUENCE,
                               _("Character out of range for UTF-8"));
	  goto err_out;
	}
      
      result_length += UTF8_LENGTH (str[i]);
    }

  result = try_malloc_n (result_length + 1, 1, error);
  if (result == NULL)
      goto err_out;

  p = result;

  i = 0;
  while (p < result + result_length)
    p += g_unichar_to_utf8 (str[i++], p);
  
  *p = '\0';

  if (items_written)
    *items_written = p - result;

 err_out:
  if (items_read)
    *items_read = i;

  return result;
}

#define SURROGATE_VALUE(h,l) (((h) - 0xd800) * 0x400 + (l) - 0xdc00 + 0x10000)

/**
 * g_utf16_to_utf8:
 * @str: a UTF-16 encoded string
 * @len: the maximum length (number of #gunichar2) of @str to use. 
 *     If @len < 0, then the string is nul-terminated.
 * @items_read: (out caller-allocates) (optional): location to store number of
 *     words read, or %NULL. If %NULL, then %G_CONVERT_ERROR_PARTIAL_INPUT will
 *     be returned in case @str contains a trailing partial character. If
 *     an error occurs then the index of the invalid input is stored here.
 * @items_written: (out caller-allocates) (optional): location to store number
 *     of bytes written, or %NULL. The value stored here does not include the
 *     trailing 0 byte.
 * @error: location to store the error occurring, or %NULL to ignore
 *     errors. Any of the errors in #GConvertError other than
 *     %G_CONVERT_ERROR_NO_CONVERSION may occur.
 *
 * Convert a string from UTF-16 to UTF-8. The result will be
 * terminated with a 0 byte.
 *
 * Note that the input is expected to be already in native endianness,
 * an initial byte-order-mark character is not handled specially.
 * g_convert() can be used to convert a byte buffer of UTF-16 data of
 * ambiguous endianess.
 *
 * Further note that this function does not validate the result
 * string; it may e.g. include embedded NUL characters. The only
 * validation done by this function is to ensure that the input can
 * be correctly interpreted as UTF-16, i.e. it doesn't contain
 * things unpaired surrogates.
 *
 * Returns: a pointer to a newly allocated UTF-8 string.
 *     This value must be freed with g_free(). If an error occurs,
 *     %NULL will be returned and @error set.
 **/
gchar *
g_utf16_to_utf8 (const gunichar2  *str,
		 glong             len,
		 glong            *items_read,
		 glong            *items_written,
		 GError          **error)
{
  /* This function and g_utf16_to_ucs4 are almost exactly identical -
   * The lines that differ are marked.
   */
  const gunichar2 *in;
  gchar *out;
  gchar *result = NULL;
  gint n_bytes;
  gunichar high_surrogate;

  g_return_val_if_fail (str != NULL, NULL);

  n_bytes = 0;
  in = str;
  high_surrogate = 0;
  while ((len < 0 || in - str < len) && *in)
    {
      gunichar2 c = *in;
      gunichar wc;

      if (c >= 0xdc00 && c < 0xe000) /* low surrogate */
	{
	  if (high_surrogate)
	    {
	      wc = SURROGATE_VALUE (high_surrogate, c);
	      high_surrogate = 0;
	    }
	  else
	    {
	      g_set_error_literal (error, G_CONVERT_ERROR, G_CONVERT_ERROR_ILLEGAL_SEQUENCE,
                                   _("Invalid sequence in conversion input"));
	      goto err_out;
	    }
	}
      else
	{
	  if (high_surrogate)
	    {
	      g_set_error_literal (error, G_CONVERT_ERROR, G_CONVERT_ERROR_ILLEGAL_SEQUENCE,
                                   _("Invalid sequence in conversion input"));
	      goto err_out;
	    }

	  if (c >= 0xd800 && c < 0xdc00) /* high surrogate */
	    {
	      high_surrogate = c;
	      goto next1;
	    }
	  else
	    wc = c;
	}

      /********** DIFFERENT for UTF8/UCS4 **********/
      n_bytes += UTF8_LENGTH (wc);

    next1:
      in++;
    }

  if (high_surrogate && !items_read)
    {
      g_set_error_literal (error, G_CONVERT_ERROR, G_CONVERT_ERROR_PARTIAL_INPUT,
                           _("Partial character sequence at end of input"));
      goto err_out;
    }
  
  /* At this point, everything is valid, and we just need to convert
   */
  /********** DIFFERENT for UTF8/UCS4 **********/
  result = try_malloc_n (n_bytes + 1, 1, error);
  if (result == NULL)
      goto err_out;

  high_surrogate = 0;
  out = result;
  in = str;
  while (out < result + n_bytes)
    {
      gunichar2 c = *in;
      gunichar wc;

      if (c >= 0xdc00 && c < 0xe000) /* low surrogate */
	{
	  wc = SURROGATE_VALUE (high_surrogate, c);
	  high_surrogate = 0;
	}
      else if (c >= 0xd800 && c < 0xdc00) /* high surrogate */
	{
	  high_surrogate = c;
	  goto next2;
	}
      else
	wc = c;

      /********** DIFFERENT for UTF8/UCS4 **********/
      out += g_unichar_to_utf8 (wc, out);

    next2:
      in++;
    }
  
  /********** DIFFERENT for UTF8/UCS4 **********/
  *out = '\0';

  if (items_written)
    /********** DIFFERENT for UTF8/UCS4 **********/
    *items_written = out - result;

 err_out:
  if (items_read)
    *items_read = in - str;

  return result;
}

/**
 * g_utf16_to_ucs4:
 * @str: a UTF-16 encoded string
 * @len: the maximum length (number of #gunichar2) of @str to use. 
 *     If @len < 0, then the string is nul-terminated.
 * @items_read: (out caller-allocates) (optional): location to store number of
 *     words read, or %NULL. If %NULL, then %G_CONVERT_ERROR_PARTIAL_INPUT will
 *     be returned in case @str contains a trailing partial character. If
 *     an error occurs then the index of the invalid input is stored here.
 * @items_written: (out caller-allocates) (optional): location to store number
 *     of characters written, or %NULL. The value stored here does not include
 *     the trailing 0 character.
 * @error: location to store the error occurring, or %NULL to ignore
 *     errors. Any of the errors in #GConvertError other than
 *     %G_CONVERT_ERROR_NO_CONVERSION may occur.
 *
 * Convert a string from UTF-16 to UCS-4. The result will be
 * nul-terminated.
 * 
 * Returns: a pointer to a newly allocated UCS-4 string.
 *     This value must be freed with g_free(). If an error occurs,
 *     %NULL will be returned and @error set.
 */
gunichar *
g_utf16_to_ucs4 (const gunichar2  *str,
		 glong             len,              
		 glong            *items_read,       
		 glong            *items_written,    
		 GError          **error)
{
  const gunichar2 *in;
  gchar *out;
  gchar *result = NULL;
  gint n_bytes;
  gunichar high_surrogate;

  g_return_val_if_fail (str != NULL, NULL);

  n_bytes = 0;
  in = str;
  high_surrogate = 0;
  while ((len < 0 || in - str < len) && *in)
    {
      gunichar2 c = *in;

      if (c >= 0xdc00 && c < 0xe000) /* low surrogate */
	{
	  if (high_surrogate)
	    {
	      high_surrogate = 0;
	    }
	  else
	    {
	      g_set_error_literal (error, G_CONVERT_ERROR, G_CONVERT_ERROR_ILLEGAL_SEQUENCE,
                                   _("Invalid sequence in conversion input"));
	      goto err_out;
	    }
	}
      else
	{
	  if (high_surrogate)
	    {
	      g_set_error_literal (error, G_CONVERT_ERROR, G_CONVERT_ERROR_ILLEGAL_SEQUENCE,
                                   _("Invalid sequence in conversion input"));
	      goto err_out;
	    }

	  if (c >= 0xd800 && c < 0xdc00) /* high surrogate */
	    {
	      high_surrogate = c;
	      goto next1;
	    }
	}

      /********** DIFFERENT for UTF8/UCS4 **********/
      n_bytes += sizeof (gunichar);

    next1:
      in++;
    }

  if (high_surrogate && !items_read)
    {
      g_set_error_literal (error, G_CONVERT_ERROR, G_CONVERT_ERROR_PARTIAL_INPUT,
                           _("Partial character sequence at end of input"));
      goto err_out;
    }
  
  /* At this point, everything is valid, and we just need to convert
   */
  /********** DIFFERENT for UTF8/UCS4 **********/
  result = try_malloc_n (n_bytes + 4, 1, error);
  if (result == NULL)
      goto err_out;

  high_surrogate = 0;
  out = result;
  in = str;
  while (out < result + n_bytes)
    {
      gunichar2 c = *in;
      gunichar wc;

      if (c >= 0xdc00 && c < 0xe000) /* low surrogate */
	{
	  wc = SURROGATE_VALUE (high_surrogate, c);
	  high_surrogate = 0;
	}
      else if (c >= 0xd800 && c < 0xdc00) /* high surrogate */
	{
	  high_surrogate = c;
	  goto next2;
	}
      else
	wc = c;

      /********** DIFFERENT for UTF8/UCS4 **********/
      *(gunichar *)out = wc;
      out += sizeof (gunichar);

    next2:
      in++;
    }

  /********** DIFFERENT for UTF8/UCS4 **********/
  *(gunichar *)out = 0;

  if (items_written)
    /********** DIFFERENT for UTF8/UCS4 **********/
    *items_written = (out - result) / sizeof (gunichar);

 err_out:
  if (items_read)
    *items_read = in - str;

  return (gunichar *)result;
}

/**
 * g_utf8_to_utf16:
 * @str: a UTF-8 encoded string
 * @len: the maximum length (number of bytes) of @str to use.
 *     If @len < 0, then the string is nul-terminated.
 * @items_read: (out caller-allocates) (optional): location to store number of
 *     bytes read, or %NULL. If %NULL, then %G_CONVERT_ERROR_PARTIAL_INPUT will
 *     be returned in case @str contains a trailing partial character. If
 *     an error occurs then the index of the invalid input is stored here.
 * @items_written: (out caller-allocates) (optional): location to store number
 *     of #gunichar2 written, or %NULL. The value stored here does not include
 *     the trailing 0.
 * @error: location to store the error occurring, or %NULL to ignore
 *     errors. Any of the errors in #GConvertError other than
 *     %G_CONVERT_ERROR_NO_CONVERSION may occur.
 *
 * Convert a string from UTF-8 to UTF-16. A 0 character will be
 * added to the result after the converted text.
 *
 * Returns: a pointer to a newly allocated UTF-16 string.
 *     This value must be freed with g_free(). If an error occurs,
 *     %NULL will be returned and @error set.
 */
gunichar2 *
g_utf8_to_utf16 (const gchar *str,
		 glong        len,
		 glong       *items_read,
		 glong       *items_written,
		 GError     **error)
{
  gunichar2 *result = NULL;
  gint n16;
  const gchar *in;
  gint i;

  g_return_val_if_fail (str != NULL, NULL);

  in = str;
  n16 = 0;
  while ((len < 0 || str + len - in > 0) && *in)
    {
      gunichar wc = g_utf8_get_char_extended (in, len < 0 ? 6 : str + len - in);
      if (wc & 0x80000000)
	{
	  if (wc == (gunichar)-2)
	    {
	      if (items_read)
		break;
	      else
		g_set_error_literal (error, G_CONVERT_ERROR, G_CONVERT_ERROR_PARTIAL_INPUT,
                                     _("Partial character sequence at end of input"));
	    }
	  else
	    g_set_error_literal (error, G_CONVERT_ERROR, G_CONVERT_ERROR_ILLEGAL_SEQUENCE,
                                 _("Invalid byte sequence in conversion input"));

	  goto err_out;
	}

      if (wc < 0xd800)
	n16 += 1;
      else if (wc < 0xe000)
	{
	  g_set_error_literal (error, G_CONVERT_ERROR, G_CONVERT_ERROR_ILLEGAL_SEQUENCE,
                               _("Invalid sequence in conversion input"));

	  goto err_out;
	}
      else if (wc < 0x10000)
	n16 += 1;
      else if (wc < 0x110000)
	n16 += 2;
      else
	{
	  g_set_error_literal (error, G_CONVERT_ERROR, G_CONVERT_ERROR_ILLEGAL_SEQUENCE,
                               _("Character out of range for UTF-16"));

	  goto err_out;
	}
      
      in = g_utf8_next_char (in);
    }

  result = try_malloc_n (n16 + 1, sizeof (gunichar2), error);
  if (result == NULL)
      goto err_out;

  in = str;
  for (i = 0; i < n16;)
    {
      gunichar wc = g_utf8_get_char (in);

      if (wc < 0x10000)
	{
	  result[i++] = wc;
	}
      else
	{
	  result[i++] = (wc - 0x10000) / 0x400 + 0xd800;
	  result[i++] = (wc - 0x10000) % 0x400 + 0xdc00;
	}
      
      in = g_utf8_next_char (in);
    }

  result[i] = 0;

  if (items_written)
    *items_written = n16;

 err_out:
  if (items_read)
    *items_read = in - str;
  
  return result;
}

/**
 * g_ucs4_to_utf16:
 * @str: a UCS-4 encoded string
 * @len: the maximum length (number of characters) of @str to use. 
 *     If @len < 0, then the string is nul-terminated.
 * @items_read: (out caller-allocates) (optional): location to store number of
 *     bytes read, or %NULL. If an error occurs then the index of the invalid
 *     input is stored here.
 * @items_written: (out caller-allocates) (optional): location to store number
 *     of #gunichar2  written, or %NULL. The value stored here does not include
 *     the trailing 0.
 * @error: location to store the error occurring, or %NULL to ignore
 *     errors. Any of the errors in #GConvertError other than
 *     %G_CONVERT_ERROR_NO_CONVERSION may occur.
 *
 * Convert a string from UCS-4 to UTF-16. A 0 character will be
 * added to the result after the converted text.
 * 
 * Returns: a pointer to a newly allocated UTF-16 string.
 *     This value must be freed with g_free(). If an error occurs,
 *     %NULL will be returned and @error set.
 */
gunichar2 *
g_ucs4_to_utf16 (const gunichar  *str,
		 glong            len,              
		 glong           *items_read,       
		 glong           *items_written,    
		 GError         **error)
{
  gunichar2 *result = NULL;
  gint n16;
  gint i, j;

  n16 = 0;
  i = 0;
  while ((len < 0 || i < len) && str[i])
    {
      gunichar wc = str[i];

      if (wc < 0xd800)
	n16 += 1;
      else if (wc < 0xe000)
	{
	  g_set_error_literal (error, G_CONVERT_ERROR, G_CONVERT_ERROR_ILLEGAL_SEQUENCE,
                               _("Invalid sequence in conversion input"));

	  goto err_out;
	}
      else if (wc < 0x10000)
	n16 += 1;
      else if (wc < 0x110000)
	n16 += 2;
      else
	{
	  g_set_error_literal (error, G_CONVERT_ERROR, G_CONVERT_ERROR_ILLEGAL_SEQUENCE,
                               _("Character out of range for UTF-16"));

	  goto err_out;
	}

      i++;
    }

  result = try_malloc_n (n16 + 1, sizeof (gunichar2), error);
  if (result == NULL)
      goto err_out;

  for (i = 0, j = 0; j < n16; i++)
    {
      gunichar wc = str[i];

      if (wc < 0x10000)
	{
	  result[j++] = wc;
	}
      else
	{
	  result[j++] = (wc - 0x10000) / 0x400 + 0xd800;
	  result[j++] = (wc - 0x10000) % 0x400 + 0xdc00;
	}
    }
  result[j] = 0;

  if (items_written)
    *items_written = n16;
  
 err_out:
  if (items_read)
    *items_read = i;
  
  return result;
}

#define VALIDATE_BYTE(mask, expect)                      \
  G_STMT_START {                                         \
    if (G_UNLIKELY((*(guchar *)p & (mask)) != (expect))) \
      goto error;                                        \
  } G_STMT_END

/* see IETF RFC 3629 Section 4 */

static const gchar *
fast_validate (const char *str)

{
  const gchar *p;

  for (p = str; *p; p++)
    {
      if (*(guchar *)p < 128)
	/* done */;
      else 
	{
	  const gchar *last;

	  last = p;
	  if (*(guchar *)p < 0xe0) /* 110xxxxx */
	    {
	      if (G_UNLIKELY (*(guchar *)p < 0xc2))
		goto error;
	    }
	  else
	    {
	      if (*(guchar *)p < 0xf0) /* 1110xxxx */
		{
		  switch (*(guchar *)p++ & 0x0f)
		    {
		    case 0:
		      VALIDATE_BYTE(0xe0, 0xa0); /* 0xa0 ... 0xbf */
		      break;
		    case 0x0d:
		      VALIDATE_BYTE(0xe0, 0x80); /* 0x80 ... 0x9f */
		      break;
		    default:
		      VALIDATE_BYTE(0xc0, 0x80); /* 10xxxxxx */
		    }
		}
	      else if (*(guchar *)p < 0xf5) /* 11110xxx excluding out-of-range */
		{
		  switch (*(guchar *)p++ & 0x07)
		    {
		    case 0:
		      VALIDATE_BYTE(0xc0, 0x80); /* 10xxxxxx */
		      if (G_UNLIKELY((*(guchar *)p & 0x30) == 0))
			goto error;
		      break;
		    case 4:
		      VALIDATE_BYTE(0xf0, 0x80); /* 0x80 ... 0x8f */
		      break;
		    default:
		      VALIDATE_BYTE(0xc0, 0x80); /* 10xxxxxx */
		    }
		  p++;
		  VALIDATE_BYTE(0xc0, 0x80); /* 10xxxxxx */
		}
	      else
		goto error;
	    }

	  p++;
	  VALIDATE_BYTE(0xc0, 0x80); /* 10xxxxxx */

	  continue;

	error:
	  return last;
	}
    }

  return p;
}

static const gchar *
fast_validate_len (const char *str,
		   gssize      max_len)

{
  const gchar *p;

  g_assert (max_len >= 0);

  for (p = str; ((p - str) < max_len) && *p; p++)
    {
      if (*(guchar *)p < 128)
	/* done */;
      else 
	{
	  const gchar *last;

	  last = p;
	  if (*(guchar *)p < 0xe0) /* 110xxxxx */
	    {
	      if (G_UNLIKELY (max_len - (p - str) < 2))
		goto error;
	      
	      if (G_UNLIKELY (*(guchar *)p < 0xc2))
		goto error;
	    }
	  else
	    {
	      if (*(guchar *)p < 0xf0) /* 1110xxxx */
		{
		  if (G_UNLIKELY (max_len - (p - str) < 3))
		    goto error;

		  switch (*(guchar *)p++ & 0x0f)
		    {
		    case 0:
		      VALIDATE_BYTE(0xe0, 0xa0); /* 0xa0 ... 0xbf */
		      break;
		    case 0x0d:
		      VALIDATE_BYTE(0xe0, 0x80); /* 0x80 ... 0x9f */
		      break;
		    default:
		      VALIDATE_BYTE(0xc0, 0x80); /* 10xxxxxx */
		    }
		}
	      else if (*(guchar *)p < 0xf5) /* 11110xxx excluding out-of-range */
		{
		  if (G_UNLIKELY (max_len - (p - str) < 4))
		    goto error;

		  switch (*(guchar *)p++ & 0x07)
		    {
		    case 0:
		      VALIDATE_BYTE(0xc0, 0x80); /* 10xxxxxx */
		      if (G_UNLIKELY((*(guchar *)p & 0x30) == 0))
			goto error;
		      break;
		    case 4:
		      VALIDATE_BYTE(0xf0, 0x80); /* 0x80 ... 0x8f */
		      break;
		    default:
		      VALIDATE_BYTE(0xc0, 0x80); /* 10xxxxxx */
		    }
		  p++;
		  VALIDATE_BYTE(0xc0, 0x80); /* 10xxxxxx */
		}
	      else
		goto error;
	    }

	  p++;
	  VALIDATE_BYTE(0xc0, 0x80); /* 10xxxxxx */

	  continue;

	error:
	  return last;
	}
    }

  return p;
}

/**
 * g_utf8_validate:
 * @str: (array length=max_len) (element-type guint8): a pointer to character data
 * @max_len: max bytes to validate, or -1 to go until NUL
 * @end: (out) (optional) (transfer none): return location for end of valid data
 * 
 * Validates UTF-8 encoded text. @str is the text to validate;
 * if @str is nul-terminated, then @max_len can be -1, otherwise
 * @max_len should be the number of bytes to validate.
 * If @end is non-%NULL, then the end of the valid range
 * will be stored there (i.e. the start of the first invalid 
 * character if some bytes were invalid, or the end of the text 
 * being validated otherwise).
 *
 * Note that g_utf8_validate() returns %FALSE if @max_len is 
 * positive and any of the @max_len bytes are nul.
 *
 * Returns %TRUE if all of @str was valid. Many GLib and GTK+
 * routines require valid UTF-8 as input; so data read from a file
 * or the network should be checked with g_utf8_validate() before
 * doing anything else with it.
 * 
 * Returns: %TRUE if the text was valid UTF-8
 */
gboolean
g_utf8_validate (const char   *str,
		 gssize        max_len,    
		 const gchar **end)

{
  const gchar *p;

  if (max_len >= 0)
    return _g_utf8_validate_len (str, max_len, end);

  p = fast_validate (str);

  if (end)
    *end = p;

  if (*p != '\0')
    return FALSE;
  else
    return TRUE;
}

/*
 * _g_utf8_validate_len:
 * @str: (array length=max_len) (element-type guint8): a pointer to character data
 * @max_len: max bytes to validate
 * @end: (out) (optional) (transfer none): return location for end of valid data
 *
 * Validates UTF-8 encoded text.
 *
 * As with g_utf8_validate(), but @max_len must be set, and hence this function
 * will always return %FALSE if any of the bytes of @str are nul.
 *
 * Returns: %TRUE if the text was valid UTF-8
 * Since: 2.60 (backported to 2.58)
 */
gboolean
_g_utf8_validate_len (const char   *str,
                      gsize         max_len,
                      const gchar **end)

{
  const gchar *p;

  p = fast_validate_len (str, max_len);

  if (end)
    *end = p;

  if (p != str + max_len)
    return FALSE;
  else
    return TRUE;
}

/**
 * g_unichar_validate:
 * @ch: a Unicode character
 * 
 * Checks whether @ch is a valid Unicode character. Some possible
 * integer values of @ch will not be valid. 0 is considered a valid
 * character, though it's normally a string terminator.
 * 
 * Returns: %TRUE if @ch is a valid Unicode character
 **/
gboolean
g_unichar_validate (gunichar ch)
{
  return UNICODE_VALID (ch);
}

/**
 * g_utf8_strreverse:
 * @str: a UTF-8 encoded string
 * @len: the maximum length of @str to use, in bytes. If @len < 0,
 *     then the string is nul-terminated.
 *
 * Reverses a UTF-8 string. @str must be valid UTF-8 encoded text. 
 * (Use g_utf8_validate() on all text before trying to use UTF-8 
 * utility functions with it.)
 *
 * This function is intended for programmatic uses of reversed strings.
 * It pays no attention to decomposed characters, combining marks, byte 
 * order marks, directional indicators (LRM, LRO, etc) and similar 
 * characters which might need special handling when reversing a string 
 * for display purposes.
 *
 * Note that unlike g_strreverse(), this function returns
 * newly-allocated memory, which should be freed with g_free() when
 * no longer needed. 
 *
 * Returns: a newly-allocated string which is the reverse of @str
 *
 * Since: 2.2
 */
gchar *
g_utf8_strreverse (const gchar *str,
		   gssize       len)
{
  gchar *r, *result;
  const gchar *p;

  if (len < 0)
    len = strlen (str);

  result = g_new (gchar, len + 1);
  r = result + len;
  p = str;
  while (r > result)
    {
      gchar *m, skip = g_utf8_skip[*(guchar*) p];
      r -= skip;
      for (m = r; skip; skip--)
        *m++ = *p++;
    }
  result[len] = 0;

  return result;
}

/**
 * g_utf8_make_valid:
 * @str: string to coerce into UTF-8
 * @len: the maximum length of @str to use, in bytes. If @len < 0,
 *     then the string is nul-terminated.
 *
 * If the provided string is valid UTF-8, return a copy of it. If not,
 * return a copy in which bytes that could not be interpreted as valid Unicode
 * are replaced with the Unicode replacement character (U+FFFD).
 *
 * For example, this is an appropriate function to use if you have received
 * a string that was incorrectly declared to be UTF-8, and you need a valid
 * UTF-8 version of it that can be logged or displayed to the user, with the
 * assumption that it is close enough to ASCII or UTF-8 to be mostly
 * readable as-is.
 *
 * Returns: (transfer full): a valid UTF-8 string whose content resembles @str
 *
 * Since: 2.52
 */
gchar *
g_utf8_make_valid (const gchar *str,
                   gssize       len)
{
  GString *string;
  const gchar *remainder, *invalid;
  gsize remaining_bytes, valid_bytes;

  g_return_val_if_fail (str != NULL, NULL);

  if (len < 0)
    len = strlen (str);

  string = NULL;
  remainder = str;
  remaining_bytes = len;

  while (remaining_bytes != 0) 
    {
      if (g_utf8_validate (remainder, remaining_bytes, &invalid)) 
	break;
      valid_bytes = invalid - remainder;
    
      if (string == NULL) 
	string = g_string_sized_new (remaining_bytes);

      g_string_append_len (string, remainder, valid_bytes);
      /* append U+FFFD REPLACEMENT CHARACTER */
      g_string_append (string, "\357\277\275");
      
      remaining_bytes -= valid_bytes + 1;
      remainder = invalid + 1;
    }
  
  if (string == NULL)
    return g_strndup (str, len);
  
  g_string_append_len (string, remainder, remaining_bytes);
  g_string_append_c (string, '\0');

  g_assert (g_utf8_validate (string->str, -1, NULL));

  return g_string_free (string, FALSE);
}