summaryrefslogtreecommitdiffstats
path: root/src/corelib/tools/qchar.cpp
blob: b806d22a3c68fe6c97978ef5e5640aab1d3d48aa (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
/****************************************************************************
**
** Copyright (C) 2011 Nokia Corporation and/or its subsidiary(-ies).
** All rights reserved.
** Contact: Nokia Corporation (qt-info@nokia.com)
**
** This file is part of the QtCore module of the Qt Toolkit.
**
** $QT_BEGIN_LICENSE:LGPL$
** GNU Lesser General Public License Usage
** This file may be used under the terms of the GNU Lesser General Public
** License version 2.1 as published by the Free Software Foundation and
** appearing in the file LICENSE.LGPL included in the packaging of this
** file. Please review the following information to ensure the GNU Lesser
** General Public License version 2.1 requirements will be met:
** http://www.gnu.org/licenses/old-licenses/lgpl-2.1.html.
**
** In addition, as a special exception, Nokia gives you certain additional
** rights. These rights are described in the Nokia Qt LGPL Exception
** version 1.1, included in the file LGPL_EXCEPTION.txt in this package.
**
** GNU General Public License Usage
** Alternatively, this file may be used under the terms of the GNU General
** Public License version 3.0 as published by the Free Software Foundation
** and appearing in the file LICENSE.GPL included in the packaging of this
** file. Please review the following information to ensure the GNU General
** Public License version 3.0 requirements will be met:
** http://www.gnu.org/copyleft/gpl.html.
**
** Other Usage
** Alternatively, this file may be used in accordance with the terms and
** conditions contained in a signed written agreement between you and Nokia.
**
**
**
**
**
** $QT_END_LICENSE$
**
****************************************************************************/

// Don't define it while compiling this module, or USERS of Qt will
// not be able to link.
#ifdef QT_NO_CAST_FROM_ASCII
#  undef QT_NO_CAST_FROM_ASCII
#endif
#ifdef QT_NO_CAST_TO_ASCII
#  undef QT_NO_CAST_TO_ASCII
#endif
#include "qchar.h"
#include "qdatastream.h"
#include "qtextcodec.h"

#include "qunicodetables_p.h"

#include "qunicodetables.cpp"

QT_BEGIN_NAMESPACE

#ifndef QT_NO_CODEC_FOR_C_STRINGS
#  ifdef QT_NO_TEXTCODEC
#    define QT_NO_CODEC_FOR_C_STRINGS
#  endif
#endif

#define FLAG(x) (1 << (x))

/*!
    \class QLatin1Char
    \brief The QLatin1Char class provides an 8-bit ASCII/Latin-1 character.

    \ingroup string-processing

    This class is only useful to avoid the codec for C strings business
    in the QChar(ch) constructor. You can avoid it by writing
    QChar(ch, 0).

    \sa QChar, QLatin1String, QString
*/

/*!
    \fn const char QLatin1Char::toLatin1() const

    Converts a Latin-1 character to an 8-bit ASCII representation of
    the character.
*/

/*!
    \fn const ushort QLatin1Char::unicode() const

    Converts a Latin-1 character to an 16-bit-encoded Unicode representation
    of the character.
*/

/*!
    \fn QLatin1Char::QLatin1Char(char c)

    Constructs a Latin-1 character for \a c. This constructor should be
    used when the encoding of the input character is known to be Latin-1.
*/

/*!
    \class QChar
    \brief The QChar class provides a 16-bit Unicode character.

    \ingroup string-processing
    \reentrant

    In Qt, Unicode characters are 16-bit entities without any markup
    or structure. This class represents such an entity. It is
    lightweight, so it can be used everywhere. Most compilers treat
    it like a \c{unsigned short}.

    QChar provides a full complement of testing/classification
    functions, converting to and from other formats, converting from
    composed to decomposed Unicode, and trying to compare and
    case-convert if you ask it to.

    The classification functions include functions like those in the
    standard C++ header \<cctype\> (formerly \<ctype.h\>), but
    operating on the full range of Unicode characters. They all
    return true if the character is a certain type of character;
    otherwise they return false. These classification functions are
    isNull() (returns true if the character is '\\0'), isPrint()
    (true if the character is any sort of printable character,
    including whitespace), isPunct() (any sort of punctation),
    isMark() (Unicode Mark), isLetter() (a letter), isNumber() (any
    sort of numeric character, not just 0-9), isLetterOrNumber(), and
    isDigit() (decimal digits). All of these are wrappers around
    category() which return the Unicode-defined category of each
    character.

    QChar also provides direction(), which indicates the "natural"
    writing direction of this character. The joining() function
    indicates how the character joins with its neighbors (needed
    mostly for Arabic) and finally hasMirrored(), which indicates
    whether the character needs to be mirrored when it is printed in
    its "unnatural" writing direction.

    Composed Unicode characters (like \aring) can be converted to
    decomposed Unicode ("a" followed by "ring above") by using
    decomposition().

    In Unicode, comparison is not necessarily possible and case
    conversion is very difficult at best. Unicode, covering the
    "entire" world, also includes most of the world's case and
    sorting problems. operator==() and friends will do comparison
    based purely on the numeric Unicode value (code point) of the
    characters, and toUpper() and toLower() will do case changes when
    the character has a well-defined uppercase/lowercase equivalent.
    For locale-dependent comparisons, use
    QString::localeAwareCompare().

    The conversion functions include unicode() (to a scalar),
    toLatin1() (to scalar, but converts all non-Latin-1 characters to
    0), row() (gives the Unicode row), cell() (gives the Unicode
    cell), digitValue() (gives the integer value of any of the
    numerous digit characters), and a host of constructors.

    QChar provides constructors and cast operators that make it easy
    to convert to and from traditional 8-bit \c{char}s. If you
    defined \c QT_NO_CAST_FROM_ASCII and \c QT_NO_CAST_TO_ASCII, as
    explained in the QString documentation, you will need to
    explicitly call fromAscii() or fromLatin1(), or use QLatin1Char,
    to construct a QChar from an 8-bit \c char, and you will need to
    call toAscii() or toLatin1() to get the 8-bit value back.

    \sa QString, Unicode, QLatin1Char
*/

/*!
    \enum QChar::UnicodeVersion

    Specifies which version of the \l{http://www.unicode.org/}{Unicode standard}
    introduced a certain character.

    \value Unicode_1_1  Version 1.1
    \value Unicode_2_0  Version 2.0
    \value Unicode_2_1_2  Version 2.1.2
    \value Unicode_3_0  Version 3.0
    \value Unicode_3_1  Version 3.1
    \value Unicode_3_2  Version 3.2
    \value Unicode_4_0  Version 4.0
    \value Unicode_4_1  Version 4.1
    \value Unicode_5_0  Version 5.0
    \value Unicode_Unassigned  The value is not assigned to any character
        in version 5.0 of Unicode.

    \sa unicodeVersion()
*/

/*!
    \enum QChar::Category

    This enum maps the Unicode character categories.

    The following characters are normative in Unicode:

    \value Mark_NonSpacing  Unicode class name Mn

    \value Mark_SpacingCombining  Unicode class name Mc

    \value Mark_Enclosing  Unicode class name Me

    \value Number_DecimalDigit  Unicode class name Nd

    \value Number_Letter  Unicode class name Nl

    \value Number_Other  Unicode class name No

    \value Separator_Space  Unicode class name Zs

    \value Separator_Line  Unicode class name Zl

    \value Separator_Paragraph  Unicode class name Zp

    \value Other_Control  Unicode class name Cc

    \value Other_Format  Unicode class name Cf

    \value Other_Surrogate  Unicode class name Cs

    \value Other_PrivateUse  Unicode class name Co

    \value Other_NotAssigned  Unicode class name Cn


    The following categories are informative in Unicode:

    \value Letter_Uppercase  Unicode class name Lu

    \value Letter_Lowercase  Unicode class name Ll

    \value Letter_Titlecase  Unicode class name Lt

    \value Letter_Modifier  Unicode class name Lm

    \value Letter_Other Unicode class name Lo

    \value Punctuation_Connector  Unicode class name Pc

    \value Punctuation_Dash  Unicode class name Pd

    \value Punctuation_Open  Unicode class name Ps

    \value Punctuation_Close  Unicode class name Pe

    \value Punctuation_InitialQuote  Unicode class name Pi

    \value Punctuation_FinalQuote  Unicode class name Pf

    \value Punctuation_Other  Unicode class name Po

    \value Symbol_Math  Unicode class name Sm

    \value Symbol_Currency  Unicode class name Sc

    \value Symbol_Modifier  Unicode class name Sk

    \value Symbol_Other  Unicode class name So

    \value NoCategory  Qt cannot find an appropriate category for the character.

    \omitvalue Punctuation_Dask

    \sa category()
*/

/*!
    \enum QChar::Direction

    This enum type defines the Unicode direction attributes. See the
    \l{http://www.unicode.org/}{Unicode Standard} for a description
    of the values.

    In order to conform to C/C++ naming conventions "Dir" is prepended
    to the codes used in the Unicode Standard.

    \value DirAL
    \value DirAN
    \value DirB
    \value DirBN
    \value DirCS
    \value DirEN
    \value DirES
    \value DirET
    \value DirL
    \value DirLRE
    \value DirLRO
    \value DirNSM
    \value DirON
    \value DirPDF
    \value DirR
    \value DirRLE
    \value DirRLO
    \value DirS
    \value DirWS

    \sa direction()
*/

/*!
    \enum QChar::Decomposition

    This enum type defines the Unicode decomposition attributes. See
    the \l{http://www.unicode.org/}{Unicode Standard} for a
    description of the values.

    \value NoDecomposition
    \value Canonical
    \value Circle
    \value Compat
    \value Final
    \value Font
    \value Fraction
    \value Initial
    \value Isolated
    \value Medial
    \value Narrow
    \value NoBreak
    \value Small
    \value Square
    \value Sub
    \value Super
    \value Vertical
    \value Wide

    \omitvalue Single

    \sa decomposition()
*/

/*!
    \enum QChar::Joining

    This enum type defines the Unicode joining attributes. See the
    \l{http://www.unicode.org/}{Unicode Standard} for a description
    of the values.

    \value Center
    \value Dual
    \value OtherJoining
    \value Right

    \sa joining()
*/

/*!
    \enum QChar::CombiningClass

    \internal

    This enum type defines names for some of the Unicode combining
    classes. See the \l{http://www.unicode.org/}{Unicode Standard}
    for a description of the values.

    \value Combining_Above
    \value Combining_AboveAttached
    \value Combining_AboveLeft
    \value Combining_AboveLeftAttached
    \value Combining_AboveRight
    \value Combining_AboveRightAttached
    \value Combining_Below
    \value Combining_BelowAttached
    \value Combining_BelowLeft
    \value Combining_BelowLeftAttached
    \value Combining_BelowRight
    \value Combining_BelowRightAttached
    \value Combining_DoubleAbove
    \value Combining_DoubleBelow
    \value Combining_IotaSubscript
    \value Combining_Left
    \value Combining_LeftAttached
    \value Combining_Right
    \value Combining_RightAttached
*/

/*!
    \enum QChar::SpecialCharacter

    \value Null A QChar with this value isNull().
    \value Nbsp Non-breaking space.
    \value ReplacementCharacter The character shown when a font has no glyph
           for a certain codepoint. A special question mark character is often
           used. Codecs use this codepoint when input data cannot be
           represented in Unicode.
    \value ObjectReplacementCharacter Used to represent an object such as an
           image when such objects cannot be presented.
    \value ByteOrderMark
    \value ByteOrderSwapped
    \value ParagraphSeparator
    \value LineSeparator

    \omitvalue null
    \omitvalue replacement
    \omitvalue byteOrderMark
    \omitvalue byteOrderSwapped
    \omitvalue nbsp
*/

/*!
    \fn void QChar::setCell(uchar cell)
    \internal
*/

/*!
    \fn void QChar::setRow(uchar row)
    \internal
*/

/*!
    \fn QChar::QChar()

    Constructs a null QChar ('\\0').

    \sa isNull()
*/

/*!
    \fn QChar::QChar(QLatin1Char ch)

    Constructs a QChar corresponding to ASCII/Latin-1 character \a ch.
*/

/*!
    \fn QChar::QChar(SpecialCharacter ch)

    Constructs a QChar for the predefined character value \a ch.
*/

/*!
    Constructs a QChar corresponding to ASCII/Latin-1 character \a
    ch.
*/
QChar::QChar(char ch)
{
#ifndef QT_NO_CODEC_FOR_C_STRINGS
    if (QTextCodec::codecForCStrings())
        // #####
        ucs =  QTextCodec::codecForCStrings()->toUnicode(&ch, 1).at(0).unicode();
    else
#endif
        ucs = uchar(ch);
}

/*!
    Constructs a QChar corresponding to ASCII/Latin-1 character \a ch.
*/
QChar::QChar(uchar ch)
{
#ifndef QT_NO_CODEC_FOR_C_STRINGS
    if (QTextCodec::codecForCStrings()) {
        // #####
        char c = char(ch);
        ucs =  QTextCodec::codecForCStrings()->toUnicode(&c, 1).at(0).unicode();
    } else
#endif
        ucs = ch;
}

/*!
    \fn QChar::QChar(uchar cell, uchar row)

    Constructs a QChar for Unicode cell \a cell in row \a row.

    \sa cell(), row()
*/

/*!
    \fn QChar::QChar(ushort code)

    Constructs a QChar for the character with Unicode code point \a
    code.
*/


/*!
    \fn QChar::QChar(short code)

    Constructs a QChar for the character with Unicode code point \a
    code.
*/


/*!
    \fn QChar::QChar(uint code)

    Constructs a QChar for the character with Unicode code point \a
    code.
*/


/*!
    \fn QChar::QChar(int code)

    Constructs a QChar for the character with Unicode code point \a
    code.
*/


/*!
    \fn bool QChar::isNull() const

    Returns true if the character is the Unicode character 0x0000
    ('\\0'); otherwise returns false.
*/

/*!
    \fn uchar QChar::cell() const

    Returns the cell (least significant byte) of the Unicode
    character.

    \sa row()
*/

/*!
    \fn uchar QChar::row() const

    Returns the row (most significant byte) of the Unicode character.

    \sa cell()
*/

/*!
    Returns true if the character is a printable character; otherwise
    returns false. This is any character not of category Cc or Cn.

    Note that this gives no indication of whether the character is
    available in a particular font.
*/
bool QChar::isPrint() const
{
    const int test = FLAG(Other_Control) |
                     FLAG(Other_NotAssigned);
    return !(FLAG(qGetProp(ucs)->category) & test);
}

/*!
    Returns true if the character is a separator character
    (Separator_* categories); otherwise returns false.
*/
bool QChar::isSpace() const
{
    if(ucs >= 9 && ucs <=13)
        return true;
    const int test = FLAG(Separator_Space) |
                     FLAG(Separator_Line) |
                     FLAG(Separator_Paragraph);
    return FLAG(qGetProp(ucs)->category) & test;
}

/*!
    Returns true if the character is a mark (Mark_* categories);
    otherwise returns false.

    See QChar::Category for more information regarding marks.
*/
bool QChar::isMark() const
{
    const int test = FLAG(Mark_NonSpacing) |
                     FLAG(Mark_SpacingCombining) |
                     FLAG(Mark_Enclosing);
    return FLAG(qGetProp(ucs)->category) & test;
}

/*!
    Returns true if the character is a punctuation mark (Punctuation_*
    categories); otherwise returns false.
*/
bool QChar::isPunct() const
{
    const int test = FLAG(Punctuation_Connector) |
                     FLAG(Punctuation_Dash) |
                     FLAG(Punctuation_Open) |
                     FLAG(Punctuation_Close) |
                     FLAG(Punctuation_InitialQuote) |
                     FLAG(Punctuation_FinalQuote) |
                     FLAG(Punctuation_Other);
    return FLAG(qGetProp(ucs)->category) & test;
}

/*!
    Returns true if the character is a letter (Letter_* categories);
    otherwise returns false.
*/
bool QChar::isLetter() const
{
    const int test = FLAG(Letter_Uppercase) |
                     FLAG(Letter_Lowercase) |
                     FLAG(Letter_Titlecase) |
                     FLAG(Letter_Modifier) |
                     FLAG(Letter_Other);
    return FLAG(qGetProp(ucs)->category) & test;
}

/*!
    Returns true if the character is a number (Number_* categories,
    not just 0-9); otherwise returns false.

    \sa isDigit()
*/
bool QChar::isNumber() const
{
    const int test = FLAG(Number_DecimalDigit) |
                     FLAG(Number_Letter) |
                     FLAG(Number_Other);
    return FLAG(qGetProp(ucs)->category) & test;
}

/*!
    Returns true if the character is a letter or number (Letter_* or
    Number_* categories); otherwise returns false.
*/
bool QChar::isLetterOrNumber() const
{
    const int test = FLAG(Letter_Uppercase) |
                     FLAG(Letter_Lowercase) |
                     FLAG(Letter_Titlecase) |
                     FLAG(Letter_Modifier) |
                     FLAG(Letter_Other) |
                     FLAG(Number_DecimalDigit) |
                     FLAG(Number_Letter) |
                     FLAG(Number_Other);
    return FLAG(qGetProp(ucs)->category) & test;
}


/*!
    Returns true if the character is a decimal digit
    (Number_DecimalDigit); otherwise returns false.
*/
bool QChar::isDigit() const
{
    return (qGetProp(ucs)->category == Number_DecimalDigit);
}


/*!
    Returns true if the character is a symbol (Symbol_* categories);
    otherwise returns false.
*/
bool QChar::isSymbol() const
{
    const int test = FLAG(Symbol_Math) |
                     FLAG(Symbol_Currency) |
                     FLAG(Symbol_Modifier) |
                     FLAG(Symbol_Other);
    return FLAG(qGetProp(ucs)->category) & test;
}

/*!
    \fn bool QChar::isHighSurrogate() const

    Returns true if the QChar is the high part of a utf16 surrogate
    (ie. if its code point is between 0xd800 and 0xdbff, inclusive).
*/

/*!
    \fn bool QChar::isLowSurrogate() const

    Returns true if the QChar is the low part of a utf16 surrogate
    (ie. if its code point is between 0xdc00 and 0xdfff, inclusive).
*/

/*!
    \fn static bool QChar::isHighSurrogate(uint ucs4)
    \since 4.7

    Returns true if the UCS-4-encoded character specified by \a ucs4
    is the high part of a utf16 surrogate
    (ie. if its code point is between 0xd800 and 0xdbff, inclusive).
*/

/*!
    \fn static bool QChar::isLowSurrogate(uint ucs4)
    \since 4.7

    Returns true if the UCS-4-encoded character specified by \a ucs4
    is the high part of a utf16 surrogate
    (ie. if its code point is between 0xdc00 and 0xdfff, inclusive).
*/

/*!
    \fn static bool QChar::requiresSurrogates(uint ucs4)
    \since 4.7

    Returns true if the UCS-4-encoded character specified by \a ucs4
    can be splited to the high and low parts of a utf16 surrogate
    (ie. if its code point is greater than or equals to 0x10000).
*/

/*!
    \fn static uint QChar::surrogateToUcs4(ushort high, ushort low)

    Converts a UTF16 surrogate pair with the given \a high and \a low values
    to its UCS-4 code point.
*/

/*!
    \fn static uint QChar::surrogateToUcs4(QChar high, QChar low)

    Converts a utf16 surrogate pair (\a high, \a low) to its ucs4 code point.
*/

/*!
    \fn static ushort QChar::highSurrogate(uint ucs4)

    Returns the high surrogate value of a ucs4 code point.
    The returned result is undefined if \a ucs4 is smaller than 0x10000.
*/

/*!
    \fn static ushort QChar::lowSurrogate(uint ucs4)

    Returns the low surrogate value of a ucs4 code point.
    The returned result is undefined if \a ucs4 is smaller than 0x10000.
*/

/*!
    Returns the numeric value of the digit, or -1 if the character is
    not a digit.
*/
int QChar::digitValue() const
{
    return qGetProp(ucs)->digitValue;
}

/*!
    \overload
    Returns the numeric value of the digit, specified by the UCS-2-encoded
    character, \a ucs2, or -1 if the character is not a digit.
*/
int QChar::digitValue(ushort ucs2)
{
    return qGetProp(ucs2)->digitValue;
}

/*!
    \overload
    Returns the numeric value of the digit specified by the UCS-4-encoded
    character, \a ucs4, or -1 if the character is not a digit.
*/
int QChar::digitValue(uint ucs4)
{
    if (ucs4 > UNICODE_LAST_CODEPOINT)
        return 0;
    return qGetProp(ucs4)->digitValue;
}

/*!
    Returns the character's category.
*/
QChar::Category QChar::category() const
{
    return (QChar::Category) qGetProp(ucs)->category;
}

/*!
    \overload
    \since 4.3
    Returns the category of the UCS-4-encoded character specified by \a ucs4.
*/
QChar::Category QChar::category(uint ucs4)
{
    if (ucs4 > UNICODE_LAST_CODEPOINT)
        return QChar::NoCategory;
    return (QChar::Category) qGetProp(ucs4)->category;
}

/*!
    \overload
    Returns the category of the UCS-2-encoded character specified by \a ucs2.
*/
QChar::Category QChar::category(ushort ucs2)
{
    return (QChar::Category) qGetProp(ucs2)->category;
}


/*!
    Returns the character's direction.
*/
QChar::Direction QChar::direction() const
{
    return (QChar::Direction) qGetProp(ucs)->direction;
}

/*!
    \overload
    Returns the direction of the UCS-4-encoded character specified by \a ucs4.
*/
QChar::Direction QChar::direction(uint ucs4)
{
    if (ucs4 > UNICODE_LAST_CODEPOINT)
        return QChar::DirL;
    return (QChar::Direction) qGetProp(ucs4)->direction;
}

/*!
    \overload
    Returns the direction of the UCS-2-encoded character specified by \a ucs2.
*/
QChar::Direction QChar::direction(ushort ucs2)
{
    return (QChar::Direction) qGetProp(ucs2)->direction;
}

/*!
    Returns information about the joining properties of the character
    (needed for certain languages such as Arabic).
*/
QChar::Joining QChar::joining() const
{
    return (QChar::Joining) qGetProp(ucs)->joining;
}

/*!
    \overload
    Returns information about the joining properties of the UCS-4-encoded
    character specified by \a ucs4 (needed for certain languages such as
    Arabic).
*/
QChar::Joining QChar::joining(uint ucs4)
{
    if (ucs4 > UNICODE_LAST_CODEPOINT)
        return QChar::OtherJoining;
    return (QChar::Joining) qGetProp(ucs4)->joining;
}

/*!
    \overload
    Returns information about the joining properties of the UCS-2-encoded
    character specified by \a ucs2 (needed for certain languages such as
    Arabic).
*/
QChar::Joining QChar::joining(ushort ucs2)
{
    return (QChar::Joining) qGetProp(ucs2)->joining;
}


/*!
    Returns true if the character should be reversed if the text
    direction is reversed; otherwise returns false.

    Same as (ch.mirroredChar() != ch).

    \sa mirroredChar()
*/
bool QChar::hasMirrored() const
{
    return qGetProp(ucs)->mirrorDiff != 0;
}

/*!
    \fn bool QChar::isLower() const

    Returns true if the character is a lowercase letter, i.e.
    category() is Letter_Lowercase.

    \sa isUpper(), toLower(), toUpper()
*/

/*!
    \fn bool QChar::isUpper() const

    Returns true if the character is an uppercase letter, i.e.
    category() is Letter_Uppercase.

    \sa isLower(), toUpper(), toLower()
*/

/*!
    \fn bool QChar::isTitleCase() const
    \since 4.3

    Returns true if the character is a titlecase letter, i.e.
    category() is Letter_Titlecase.

    \sa isLower(), toUpper(), toLower(), toTitleCase()
*/

/*!
    Returns the mirrored character if this character is a mirrored
    character; otherwise returns the character itself.

    \sa hasMirrored()
*/
QChar QChar::mirroredChar() const
{
    return ucs + qGetProp(ucs)->mirrorDiff;
}

/*!
    \overload
    Returns the mirrored character if the UCS-4-encoded character specified
    by \a ucs4 is a mirrored character; otherwise returns the character itself.

    \sa hasMirrored()
*/
uint QChar::mirroredChar(uint ucs4)
{
    if (ucs4 > UNICODE_LAST_CODEPOINT)
        return ucs4;
    return ucs4 + qGetProp(ucs4)->mirrorDiff;
}

/*!
    \overload
    Returns the mirrored character if the UCS-2-encoded character specified
    by \a ucs2 is a mirrored character; otherwise returns the character itself.

    \sa hasMirrored()
*/
ushort QChar::mirroredChar(ushort ucs2)
{
    return ucs2 + qGetProp(ucs2)->mirrorDiff;
}


enum {
    Hangul_SBase = 0xac00,
    Hangul_LBase = 0x1100,
    Hangul_VBase = 0x1161,
    Hangul_TBase = 0x11a7,
    Hangul_SCount = 11172,
    Hangul_LCount = 19,
    Hangul_VCount = 21,
    Hangul_TCount = 28,
    Hangul_NCount = 21*28
};

// buffer has to have a length of 3. It's needed for Hangul decomposition
static const unsigned short * QT_FASTCALL decompositionHelper
    (uint ucs4, int *length, int *tag, unsigned short *buffer)
{
    *length = 0;
    if (ucs4 > UNICODE_LAST_CODEPOINT)
        return 0;
    if (ucs4 >= Hangul_SBase && ucs4 < Hangul_SBase + Hangul_SCount) {
        int SIndex = ucs4 - Hangul_SBase;
        buffer[0] = Hangul_LBase + SIndex / Hangul_NCount; // L
        buffer[1] = Hangul_VBase + (SIndex % Hangul_NCount) / Hangul_TCount; // V
        buffer[2] = Hangul_TBase + SIndex % Hangul_TCount; // T
        *length = buffer[2] == Hangul_TBase ? 2 : 3;
        *tag = QChar::Canonical;
        return buffer;
    }

    const unsigned short index = GET_DECOMPOSITION_INDEX(ucs4);
    if (index == 0xffff)
        return 0;
    const unsigned short *decomposition = uc_decomposition_map+index;
    *tag = (*decomposition) & 0xff;
    *length = (*decomposition) >> 8;
    return decomposition+1;
}

/*!
    Decomposes a character into its parts. Returns an empty string if
    no decomposition exists.
*/
QString QChar::decomposition() const
{
    return decomposition(ucs);
}

/*!
    \overload
    Decomposes the UCS-4-encoded character specified by \a ucs4 into its
    constituent parts. Returns an empty string if no decomposition exists.
*/
QString QChar::decomposition(uint ucs4)
{
    unsigned short buffer[3];
    int length;
    int tag;
    const unsigned short *d = decompositionHelper(ucs4, &length, &tag, buffer);
    return QString::fromUtf16(d, length);
}

/*!
    Returns the tag defining the composition of the character. Returns
    QChar::Single if no decomposition exists.
*/
QChar::Decomposition QChar::decompositionTag() const
{
    return decompositionTag(ucs);
}

/*!
    \overload
    Returns the tag defining the composition of the UCS-4-encoded character
    specified by \a ucs4. Returns QChar::Single if no decomposition exists.
*/
QChar::Decomposition QChar::decompositionTag(uint ucs4)
{
    if (ucs4 > UNICODE_LAST_CODEPOINT)
        return QChar::NoDecomposition;
    const unsigned short index = GET_DECOMPOSITION_INDEX(ucs4);
    if (index == 0xffff)
        return QChar::NoDecomposition;
    return (QChar::Decomposition)(uc_decomposition_map[index] & 0xff);
}

/*!
    Returns the combining class for the character as defined in the
    Unicode standard. This is mainly useful as a positioning hint for
    marks attached to a base character.

    The Qt text rendering engine uses this information to correctly
    position non-spacing marks around a base character.
*/
unsigned char QChar::combiningClass() const
{
    return (unsigned char) qGetProp(ucs)->combiningClass;
}

/*!
    \overload
    Returns the combining class for the UCS-4-encoded character specified by
    \a ucs4, as defined in the Unicode standard.
*/
unsigned char QChar::combiningClass(uint ucs4)
{
    if (ucs4 > UNICODE_LAST_CODEPOINT)
        return 0;
    return (unsigned char) qGetProp(ucs4)->combiningClass;
}

/*!
    \overload
    Returns the combining class for the UCS-2-encoded character specified by
    \a ucs2, as defined in the Unicode standard.
*/
unsigned char QChar::combiningClass(ushort ucs2)
{
    return (unsigned char) qGetProp(ucs2)->combiningClass;
}

/*!
    Returns the Unicode version that introduced this character.
*/
QChar::UnicodeVersion QChar::unicodeVersion() const
{
    return (QChar::UnicodeVersion) qGetProp(ucs)->unicodeVersion;
}

/*!
    \overload
    Returns the Unicode version that introduced the character specified in
    its UCS-4-encoded form as \a ucs4.
*/
QChar::UnicodeVersion QChar::unicodeVersion(uint ucs4)
{
    if (ucs4 > UNICODE_LAST_CODEPOINT)
        return QChar::Unicode_Unassigned;
    return (QChar::UnicodeVersion) qGetProp(ucs4)->unicodeVersion;
}

/*!
    \overload
    Returns the Unicode version that introduced the character specified in
    its UCS-2-encoded form as \a ucs2.
*/
QChar::UnicodeVersion QChar::unicodeVersion(ushort ucs2)
{
    return (QChar::UnicodeVersion) qGetProp(ucs2)->unicodeVersion;
}


/*!
    Returns the lowercase equivalent if the character is uppercase or titlecase;
    otherwise returns the character itself.
*/
QChar QChar::toLower() const
{
    const QUnicodeTables::Properties *p = qGetProp(ucs);
    if (!p->lowerCaseSpecial)
        return ucs + p->lowerCaseDiff;
    return ucs;
}

/*!
    \overload
    Returns the lowercase equivalent of the UCS-4-encoded character specified
    by \a ucs4 if the character is uppercase or titlecase; otherwise returns
    the character itself.
*/
uint QChar::toLower(uint ucs4)
{
    if (ucs4 > UNICODE_LAST_CODEPOINT)
        return ucs4;
    const QUnicodeTables::Properties *p = qGetProp(ucs4);
    if (!p->lowerCaseSpecial)
        return ucs4 + p->lowerCaseDiff;
    return ucs4;
}

/*!
    \overload
    Returns the lowercase equivalent of the UCS-2-encoded character specified
    by \a ucs2 if the character is uppercase or titlecase; otherwise returns
    the character itself.
*/
ushort QChar::toLower(ushort ucs2)
{
    const QUnicodeTables::Properties *p = qGetProp(ucs2);
    if (!p->lowerCaseSpecial)
        return ucs2 + p->lowerCaseDiff;
    return ucs2;
}

/*!
    Returns the uppercase equivalent if the character is lowercase or titlecase;
    otherwise returns the character itself.
*/
QChar QChar::toUpper() const
{
    const QUnicodeTables::Properties *p = qGetProp(ucs);
    if (!p->upperCaseSpecial)
        return ucs + p->upperCaseDiff;
    return ucs;
}

/*!
    \overload
    Returns the uppercase equivalent of the UCS-4-encoded character specified
    by \a ucs4 if the character is lowercase or titlecase; otherwise returns
    the character itself.
*/
uint QChar::toUpper(uint ucs4)
{
    if (ucs4 > UNICODE_LAST_CODEPOINT)
        return ucs4;
    const QUnicodeTables::Properties *p = qGetProp(ucs4);
    if (!p->upperCaseSpecial)
        return ucs4 + p->upperCaseDiff;
    return ucs4;
}

/*!
    \overload
    Returns the uppercase equivalent of the UCS-2-encoded character specified
    by \a ucs2 if the character is lowercase or titlecase; otherwise returns
    the character itself.
*/
ushort QChar::toUpper(ushort ucs2)
{
    const QUnicodeTables::Properties *p = qGetProp(ucs2);
    if (!p->upperCaseSpecial)
        return ucs2 + p->upperCaseDiff;
    return ucs2;
}

/*!
    Returns the title case equivalent if the character is lowercase or uppercase;
    otherwise returns the character itself.
*/
QChar QChar::toTitleCase() const
{
    const QUnicodeTables::Properties *p = qGetProp(ucs);
    if (!p->titleCaseSpecial)
        return ucs + p->titleCaseDiff;
    return ucs;
}

/*!
    \overload
    Returns the title case equivalent of the UCS-4-encoded character specified
    by \a ucs4 if the character is lowercase or uppercase; otherwise returns
    the character itself.
*/
uint QChar::toTitleCase(uint ucs4)
{
    if (ucs4 > UNICODE_LAST_CODEPOINT)
        return ucs4;
    const QUnicodeTables::Properties *p = qGetProp(ucs4);
    if (!p->titleCaseSpecial)
        return ucs4 + p->titleCaseDiff;
    return ucs4;
}

/*!
    \overload
    Returns the title case equivalent of the UCS-2-encoded character specified
    by \a ucs2 if the character is lowercase or uppercase; otherwise returns
    the character itself.
*/
ushort QChar::toTitleCase(ushort ucs2)
{
    const QUnicodeTables::Properties *p = qGetProp(ucs2);
    if (!p->titleCaseSpecial)
        return ucs2 + p->titleCaseDiff;
    return ucs2;
}


static inline uint foldCase(const ushort *ch, const ushort *start)
{
    uint c = *ch;
    if (QChar(c).isLowSurrogate() && ch > start && QChar(*(ch - 1)).isHighSurrogate())
        c = QChar::surrogateToUcs4(*(ch - 1), c);
    return *ch + qGetProp(c)->caseFoldDiff;
}

static inline uint foldCase(uint ch, uint &last)
{
    uint c = ch;
    if (QChar(c).isLowSurrogate() && QChar(last).isHighSurrogate())
        c = QChar::surrogateToUcs4(last, c);
    last = ch;
    return ch + qGetProp(c)->caseFoldDiff;
}

static inline ushort foldCase(ushort ch)
{
    return ch + qGetProp(ch)->caseFoldDiff;
}

/*!
    Returns the case folded equivalent of the character. For most Unicode characters this
    is the same as toLowerCase().
*/
QChar QChar::toCaseFolded() const
{
    return ucs + qGetProp(ucs)->caseFoldDiff;
}

/*!
    \overload
    Returns the case folded equivalent of the UCS-4-encoded character specified
    by \a ucs4. For most Unicode characters this is the same as toLowerCase().
*/
uint QChar::toCaseFolded(uint ucs4)
{
    if (ucs4 > UNICODE_LAST_CODEPOINT)
        return ucs4;
    return ucs4 + qGetProp(ucs4)->caseFoldDiff;
}

/*!
    \overload
    Returns the case folded equivalent of the UCS-2-encoded character specified
    by \a ucs2. For most Unicode characters this is the same as toLowerCase().
*/
ushort QChar::toCaseFolded(ushort ucs2)
{
    return ucs2 + qGetProp(ucs2)->caseFoldDiff;
}


/*!
    \fn char QChar::latin1() const

    Use toLatin1() instead.
*/

/*!
    \fn char QChar::ascii() const

    Use toAscii() instead.
*/

/*!
    \fn char QChar::toLatin1() const

    Returns the Latin-1 character equivalent to the QChar, or 0. This
    is mainly useful for non-internationalized software.

    \sa toAscii(), unicode(), QTextCodec::codecForCStrings()
*/

/*!
    \fn char QChar::toAscii() const
    Returns the character value of the QChar obtained using the current
    codec used to read C strings, or 0 if the character is not representable
    using this codec. The default codec handles Latin-1 encoded text,
    but this can be changed to assist developers writing source code using
    other encodings.

    The main purpose of this function is to preserve ASCII characters used
    in C strings. This is mainly useful for developers of non-internationalized
    software.

    \sa toLatin1(), unicode(), QTextCodec::codecForCStrings()
*/
#ifdef Q_COMPILER_MANGLES_RETURN_TYPE
const char QChar::toAscii() const
#else
char QChar::toAscii() const
#endif
{
#ifndef QT_NO_CODEC_FOR_C_STRINGS
    if (QTextCodec::codecForCStrings())
        // #####
        return QTextCodec::codecForCStrings()->fromUnicode(QString(*this)).at(0);
#endif
    return ucs > 0xff ? 0 : char(ucs);
}

/*!
    \fn QChar QChar::fromLatin1(char c)

    Converts the Latin-1 character \a c to its equivalent QChar. This
    is mainly useful for non-internationalized software.

    \sa fromAscii(), unicode(), QTextCodec::codecForCStrings()
*/

/*!
    Converts the ASCII character \a c to its equivalent QChar. This
    is mainly useful for non-internationalized software.

    An alternative is to use QLatin1Char.

    \sa fromLatin1(), unicode(), QTextCodec::codecForCStrings()
*/
QChar QChar::fromAscii(char c)
{
#ifndef QT_NO_CODEC_FOR_C_STRINGS
    if (QTextCodec::codecForCStrings())
        // #####
        return QTextCodec::codecForCStrings()->toUnicode(&c, 1).at(0).unicode();
#endif
    return QChar(ushort((uchar)c));
}

#ifndef QT_NO_DATASTREAM
/*!
    \relates QChar

    Writes the char \a chr to the stream \a out.

    \sa {Serializing Qt Data Types}
*/
QDataStream &operator<<(QDataStream &out, const QChar &chr)
{
    out << quint16(chr.unicode());
    return out;
}

/*!
    \relates QChar

    Reads a char from the stream \a in into char \a chr.

    \sa {Serializing Qt Data Types}
*/
QDataStream &operator>>(QDataStream &in, QChar &chr)
{
    quint16 u;
    in >> u;
    chr.unicode() = ushort(u);
    return in;
}
#endif // QT_NO_DATASTREAM

/*!
    \fn ushort & QChar::unicode()

    Returns a reference to the numeric Unicode value of the QChar.
*/

/*!
    \fn ushort QChar::unicode() const

    \overload
*/

/*****************************************************************************
  Documentation of QChar related functions
 *****************************************************************************/

/*!
    \fn bool operator==(QChar c1, QChar c2)

    \relates QChar

    Returns true if \a c1 and \a c2 are the same Unicode character;
    otherwise returns false.
*/

/*!
    \fn int operator!=(QChar c1, QChar c2)

    \relates QChar

    Returns true if \a c1 and \a c2 are not the same Unicode
    character; otherwise returns false.
*/

/*!
    \fn int operator<=(QChar c1, QChar c2)

    \relates QChar

    Returns true if the numeric Unicode value of \a c1 is less than
    or equal to that of \a c2; otherwise returns false.
*/

/*!
    \fn int operator>=(QChar c1, QChar c2)

    \relates QChar

    Returns true if the numeric Unicode value of \a c1 is greater than
    or equal to that of \a c2; otherwise returns false.
*/

/*!
    \fn int operator<(QChar c1, QChar c2)

    \relates QChar

    Returns true if the numeric Unicode value of \a c1 is less than
    that of \a c2; otherwise returns false.
*/

/*!
    \fn int operator>(QChar c1, QChar c2)

    \relates QChar

    Returns true if the numeric Unicode value of \a c1 is greater than
    that of \a c2; otherwise returns false.
*/

/*!
    \fn bool QChar::mirrored() const

    Use hasMirrored() instead.
*/

/*!
    \fn QChar QChar::lower() const

    Use toLower() instead.
*/

/*!
    \fn QChar QChar::upper() const

    Use toUpper() instead.
*/

/*!
    \fn bool QChar::networkOrdered()

    See if QSysInfo::ByteOrder == QSysInfo::BigEndian instead.
*/


// ---------------------------------------------------------------------------


static void decomposeHelper(QString *str, bool canonical, QChar::UnicodeVersion version, int from)
{
    unsigned short buffer[3];

    QString &s = *str;

    const unsigned short *utf16 = reinterpret_cast<unsigned short *>(s.data());
    const unsigned short *uc = utf16 + s.length();
    while (uc != utf16 + from) {
        uint ucs4 = *(--uc);
        if (QChar(ucs4).isLowSurrogate() && uc != utf16) {
            ushort high = *(uc - 1);
            if (QChar(high).isHighSurrogate()) {
                --uc;
                ucs4 = QChar::surrogateToUcs4(high, ucs4);
            }
        }
        if (QChar::unicodeVersion(ucs4) > version)
            continue;
        int length;
        int tag;
        const unsigned short *d = decompositionHelper(ucs4, &length, &tag, buffer);
        if (!d || (canonical && tag != QChar::Canonical))
            continue;

        int pos = uc - utf16;
        s.replace(pos, QChar::requiresSurrogates(ucs4) ? 2 : 1, reinterpret_cast<const QChar *>(d), length);
        // since the insert invalidates the pointers and we do decomposition recursive
        utf16 = reinterpret_cast<unsigned short *>(s.data());
        uc = utf16 + pos + length;
    }
}


static ushort ligatureHelper(ushort u1, ushort u2)
{
    // hangul L-V pair
    int LIndex = u1 - Hangul_LBase;
    if (0 <= LIndex && LIndex < Hangul_LCount) {
        int VIndex = u2 - Hangul_VBase;
        if (0 <= VIndex && VIndex < Hangul_VCount)
            return Hangul_SBase + (LIndex * Hangul_VCount + VIndex) * Hangul_TCount;
    }

    // hangul LV-T pair
    int SIndex = u1 - Hangul_SBase;
    if (0 <= SIndex && SIndex < Hangul_SCount && (SIndex % Hangul_TCount) == 0) {
        int TIndex = u2 - Hangul_TBase;
        if (0 <= TIndex && TIndex <= Hangul_TCount)
            return u1 + TIndex;
    }

    const unsigned short index = GET_LIGATURE_INDEX(u2);
    if (index == 0xffff)
        return 0;
    const unsigned short *ligatures = uc_ligature_map+index;
    ushort length = *ligatures;
    ++ligatures;
    // ### use bsearch
    for (uint i = 0; i < length; ++i)
        if (ligatures[2*i] == u1)
            return ligatures[2*i+1];
    return 0;
}

static void composeHelper(QString *str, int from)
{
    QString &s = *str;

    if (s.length() - from < 2)
        return;

    // the loop can partly ignore high Unicode as all ligatures are in the BMP
    int starter = 0;
    int lastCombining = 0;
    int pos = from;
    while (pos < s.length()) {
        uint uc = s.at(pos).unicode();
        if (QChar(uc).isHighSurrogate() && pos < s.length()-1) {
            ushort low = s.at(pos+1).unicode();
            if (QChar(low).isLowSurrogate()) {
                uc = QChar::surrogateToUcs4(uc, low);
                ++pos;
            }
        }
        int combining = QChar::combiningClass(uc);
        if (starter == pos - 1 || combining > lastCombining) {
            // allowed to form ligature with S
            QChar ligature = ligatureHelper(s.at(starter).unicode(), uc);
            if (ligature.unicode()) {
                s[starter] = ligature;
                s.remove(pos, 1);
                continue;
            }
        }
        if (!combining)
            starter = pos;
        lastCombining = combining;
        ++pos;
    }
}


static void canonicalOrderHelper(QString *str, QChar::UnicodeVersion version, int from)
{
    QString &s = *str;
    const int l = s.length()-1;
    int pos = from;
    while (pos < l) {
        int p2 = pos+1;
        uint u1 = s.at(pos).unicode();
        if (QChar(u1).isHighSurrogate()) {
            ushort low = s.at(p2).unicode();
            if (QChar(low).isLowSurrogate()) {
                u1 = QChar::surrogateToUcs4(u1, low);
                if (p2 >= l)
                    break;
                ++p2;
            }
        }
        uint u2 = s.at(p2).unicode();
        if (QChar(u2).isHighSurrogate() && p2 < l) {
            ushort low = s.at(p2+1).unicode();
            if (QChar(low).isLowSurrogate()) {
                u2 = QChar::surrogateToUcs4(u2, low);
                ++p2;
            }
        }

        ushort c2 = 0;
        {
            const QUnicodeTables::Properties *p = qGetProp(u2);
            if ((QChar::UnicodeVersion)p->unicodeVersion <= version)
                c2 = p->combiningClass;
        }
        if (c2 == 0) {
            pos = p2+1;
            continue;
        }

        ushort c1 = 0;
        {
            const QUnicodeTables::Properties *p = qGetProp(u1);
            if ((QChar::UnicodeVersion)p->unicodeVersion <= version)
                c1 = p->combiningClass;
        }

        if (c1 > c2) {
            QChar *uc = s.data();
            int p = pos;
            // exchange characters
            if (!QChar::requiresSurrogates(u2)) {
                uc[p++] = u2;
            } else {
                uc[p++] = QChar::highSurrogate(u2);
                uc[p++] = QChar::lowSurrogate(u2);
            }
            if (!QChar::requiresSurrogates(u1)) {
                uc[p++] = u1;
            } else {
                uc[p++] = QChar::highSurrogate(u1);
                uc[p++] = QChar::lowSurrogate(u1);
            }
            if (pos > 0)
                --pos;
            if (pos > 0 && s.at(pos).isLowSurrogate())
                --pos;
        } else {
            ++pos;
            if (QChar::requiresSurrogates(u1))
                ++pos;
        }
    }
}

QT_END_NAMESPACE