summaryrefslogtreecommitdiffstats
path: root/src/corelib/codecs/qtextcodec.cpp
blob: 8fef333a77389129843eab1ecb3de8cc248d4676 (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
/****************************************************************************
**
** Copyright (C) 2015 The Qt Company Ltd.
** Contact: http://www.qt.io/licensing/
**
** This file is part of the QtCore module of the Qt Toolkit.
**
** $QT_BEGIN_LICENSE:LGPL21$
** Commercial License Usage
** Licensees holding valid commercial Qt licenses may use this file in
** accordance with the commercial license agreement provided with the
** Software or, alternatively, in accordance with the terms contained in
** a written agreement between you and The Qt Company. For licensing terms
** and conditions see http://www.qt.io/terms-conditions. For further
** information use the contact form at http://www.qt.io/contact-us.
**
** GNU Lesser General Public License Usage
** Alternatively, this file may be used under the terms of the GNU Lesser
** General Public License version 2.1 or version 3 as published by the Free
** Software Foundation and appearing in the file LICENSE.LGPLv21 and
** LICENSE.LGPLv3 included in the packaging of this file. Please review the
** following information to ensure the GNU Lesser General Public License
** requirements will be met: https://www.gnu.org/licenses/lgpl.html and
** http://www.gnu.org/licenses/old-licenses/lgpl-2.1.html.
**
** As a special exception, The Qt Company gives you certain additional
** rights. These rights are described in The Qt Company LGPL Exception
** version 1.1, included in the file LGPL_EXCEPTION.txt in this package.
**
** $QT_END_LICENSE$
**
****************************************************************************/

#include "qplatformdefs.h"
#include "qtextcodec.h"
#include "qtextcodec_p.h"

#ifndef QT_NO_TEXTCODEC

#include "qlist.h"
#include "qfile.h"
#include "qstringlist.h"
#include "qvarlengtharray.h"
#if !defined(QT_BOOTSTRAPPED)
#include <private/qcoreapplication_p.h>
#endif
#include "private/qcoreglobaldata_p.h"

#include "qutfcodec_p.h"
#include "qlatincodec_p.h"

#if !defined(QT_BOOTSTRAPPED)
#  include "qtsciicodec_p.h"
#  include "qisciicodec_p.h"
#if defined(QT_USE_ICU)
#include "qicucodec_p.h"
#else
#if !defined(QT_NO_ICONV)
#  include "qiconvcodec_p.h"
#endif
#ifdef Q_OS_WIN
#  include "qwindowscodec_p.h"
#endif
#  include "qsimplecodec_p.h"
#if !defined(QT_NO_BIG_CODECS)
#  ifndef Q_OS_INTEGRITY
#    include "qgb18030codec_p.h"
#    include "qeucjpcodec_p.h"
#    include "qjiscodec_p.h"
#    include "qsjiscodec_p.h"
#    include "qeuckrcodec_p.h"
#    include "qbig5codec_p.h"
#  endif // !Q_OS_INTEGRITY
#endif // !QT_NO_BIG_CODECS

#endif // QT_USE_ICU
#endif // QT_BOOTSTRAPPED

#include "qmutex.h"

#include <stdlib.h>
#include <ctype.h>
#include <locale.h>
#if defined (_XOPEN_UNIX) && !defined(Q_OS_QNX) && !defined(Q_OS_OSF) && !defined(Q_OS_ANDROID)
# include <langinfo.h>
#endif

QT_BEGIN_NAMESPACE

typedef QList<QTextCodec*>::ConstIterator TextCodecListConstIt;
typedef QList<QByteArray>::ConstIterator ByteArrayListConstIt;

Q_GLOBAL_STATIC_WITH_ARGS(QMutex, textCodecsMutex, (QMutex::Recursive));
QMutex *qTextCodecsMutex() { return textCodecsMutex(); }

#if !defined(QT_USE_ICU)
static char qtolower(char c)
{ if (c >= 'A' && c <= 'Z') return c + 0x20; return c; }
static bool qisalnum(char c)
{ return (c >= '0' && c <= '9') || ((c | 0x20) >= 'a' && (c | 0x20) <= 'z'); }

bool qTextCodecNameMatch(const char *n, const char *h)
{
    if (qstricmp(n, h) == 0)
        return true;

    // if the letters and numbers are the same, we have a match
    while (*n != '\0') {
        if (qisalnum(*n)) {
            for (;;) {
                if (*h == '\0')
                    return false;
                if (qisalnum(*h))
                    break;
                ++h;
            }
            if (qtolower(*n) != qtolower(*h))
                return false;
            ++h;
        }
        ++n;
    }
    while (*h && !qisalnum(*h))
           ++h;
    return (*h == '\0');
}


#if !defined(Q_OS_WIN32) && !defined(Q_OS_WINCE) && !defined(QT_LOCALE_IS_UTF8)
static QTextCodec *checkForCodec(const QByteArray &name) {
    QTextCodec *c = QTextCodec::codecForName(name);
    if (!c) {
        const int index = name.indexOf('@');
        if (index != -1) {
            c = QTextCodec::codecForName(name.left(index));
        }
    }
    return c;
}
#endif

static void setup();

// \threadsafe
// this returns the codec the method sets up as locale codec to
// avoid a race condition in codecForLocale() when
// setCodecForLocale(0) is called at the same time.
static QTextCodec *setupLocaleMapper()
{
    QCoreGlobalData *globalData = QCoreGlobalData::instance();

    QTextCodec *locale = 0;

    {
        QMutexLocker locker(textCodecsMutex());
        if (globalData->allCodecs.isEmpty())
            setup();
    }

#if !defined(QT_BOOTSTRAPPED)
    QCoreApplicationPrivate::initLocale();
#endif

#if defined(QT_LOCALE_IS_UTF8)
    locale = QTextCodec::codecForName("UTF-8");
#elif defined(Q_OS_WIN) || defined(Q_OS_WINCE)
    locale = QTextCodec::codecForName("System");
#else

    // First try getting the codecs name from nl_langinfo and see
    // if we have a builtin codec for it.
    // Only fall back to using iconv if we can't find a builtin codec
    // This is because the builtin utf8 codec is around 5 times faster
    // then the using QIconvCodec

#if defined (_XOPEN_UNIX) && !defined(Q_OS_OSF)
    char *charset = nl_langinfo(CODESET);
    if (charset)
        locale = QTextCodec::codecForName(charset);
#endif
#if !defined(QT_NO_ICONV) && !defined(QT_BOOTSTRAPPED)
    if (!locale) {
        // no builtin codec for the locale found, let's try using iconv
        (void) new QIconvCodec();
        locale = QTextCodec::codecForName("System");
    }
#endif

    if (!locale) {
        // Very poorly defined and followed standards causes lots of
        // code to try to get all the cases... This logic is
        // duplicated in QIconvCodec, so if you change it here, change
        // it there too.

        // Try to determine locale codeset from locale name assigned to
        // LC_CTYPE category.

        // First part is getting that locale name.  First try setlocale() which
        // definitely knows it, but since we cannot fully trust it, get ready
        // to fall back to environment variables.
        const QByteArray ctype = setlocale(LC_CTYPE, 0);

        // Get the first nonempty value from $LC_ALL, $LC_CTYPE, and $LANG
        // environment variables.
        QByteArray lang = qgetenv("LC_ALL");
        if (lang.isEmpty() || lang == "C") {
            lang = qgetenv("LC_CTYPE");
        }
        if (lang.isEmpty() || lang == "C") {
            lang = qgetenv("LANG");
        }

        // Now try these in order:
        // 1. CODESET from ctype if it contains a .CODESET part (e.g. en_US.ISO8859-15)
        // 2. CODESET from lang if it contains a .CODESET part
        // 3. ctype (maybe the locale is named "ISO-8859-1" or something)
        // 4. locale (ditto)
        // 5. check for "@euro"
        // 6. guess locale from ctype unless ctype is "C"
        // 7. guess locale from lang

        // 1. CODESET from ctype if it contains a .CODESET part (e.g. en_US.ISO8859-15)
        int indexOfDot = ctype.indexOf('.');
        if (indexOfDot != -1)
            locale = checkForCodec( ctype.mid(indexOfDot + 1) );

        // 2. CODESET from lang if it contains a .CODESET part
        if (!locale) {
            indexOfDot = lang.indexOf('.');
            if (indexOfDot != -1)
                locale = checkForCodec( lang.mid(indexOfDot + 1) );
        }

        // 3. ctype (maybe the locale is named "ISO-8859-1" or something)
        if (!locale && !ctype.isEmpty() && ctype != "C")
            locale = checkForCodec(ctype);

        // 4. locale (ditto)
        if (!locale && !lang.isEmpty())
            locale = checkForCodec(lang);

        // 5. "@euro"
        if ((!locale && ctype.contains("@euro")) || lang.contains("@euro"))
            locale = checkForCodec("ISO 8859-15");
    }

#endif
    // If everything failed, we default to 8859-1
    if (!locale)
        locale = QTextCodec::codecForName("ISO 8859-1");
    globalData->codecForLocale.storeRelease(locale);
    return locale;
}


// textCodecsMutex need to be locked to enter this function
static void setup()
{
    static bool initialized = false;
    if (initialized)
        return;
    initialized = true;

#if !defined(QT_NO_CODECS) && !defined(QT_BOOTSTRAPPED)
    (void)new QTsciiCodec;
    for (int i = 0; i < 9; ++i)
        (void)new QIsciiCodec(i);
    for (int i = 0; i < QSimpleTextCodec::numSimpleCodecs; ++i)
        (void)new QSimpleTextCodec(i);

#  if !defined(QT_NO_BIG_CODECS) && !defined(Q_OS_INTEGRITY)
    (void)new QGb18030Codec;
    (void)new QGbkCodec;
    (void)new QGb2312Codec;
    (void)new QEucJpCodec;
    (void)new QJisCodec;
    (void)new QSjisCodec;
    (void)new QEucKrCodec;
    (void)new QCP949Codec;
    (void)new QBig5Codec;
    (void)new QBig5hkscsCodec;
#  endif // !QT_NO_BIG_CODECS && !Q_OS_INTEGRITY
#if !defined(QT_NO_ICONV)
    (void) new QIconvCodec;
#endif
#if defined(Q_OS_WIN32) || defined(Q_OS_WINCE)
    (void) new QWindowsLocalCodec;
#endif // Q_OS_WIN32
#endif // !QT_NO_CODECS && !QT_BOOTSTRAPPED

    (void)new QUtf16Codec;
    (void)new QUtf16BECodec;
    (void)new QUtf16LECodec;
    (void)new QUtf32Codec;
    (void)new QUtf32BECodec;
    (void)new QUtf32LECodec;
    (void)new QLatin15Codec;
    (void)new QLatin1Codec;
    (void)new QUtf8Codec;
}
#else
static void setup() {}
#endif // QT_USE_ICU

/*!
    \enum QTextCodec::ConversionFlag

    \value DefaultConversion  No flag is set.
    \value ConvertInvalidToNull  If this flag is set, each invalid input
                                 character is output as a null character.
    \value IgnoreHeader  Ignore any Unicode byte-order mark and don't generate any.

    \omitvalue FreeFunction
*/

/*!
    \fn QTextCodec::ConverterState::ConverterState(ConversionFlags flags)

    Constructs a ConverterState object initialized with the given \a flags.
*/

/*!
    Destroys the ConverterState object.
*/
QTextCodec::ConverterState::~ConverterState()
{
    if (flags & FreeFunction)
        (QTextCodecUnalignedPointer::decode(state_data))(this);
    else if (d)
        free(d);
}

/*!
    \class QTextCodec
    \inmodule QtCore
    \brief The QTextCodec class provides conversions between text encodings.
    \reentrant
    \ingroup i18n

    Qt uses Unicode to store, draw and manipulate strings. In many
    situations you may wish to deal with data that uses a different
    encoding. For example, most Japanese documents are still stored
    in Shift-JIS or ISO 2022-JP, while Russian users often have their
    documents in KOI8-R or Windows-1251.

    Qt provides a set of QTextCodec classes to help with converting
    non-Unicode formats to and from Unicode. You can also create your
    own codec classes.

    The supported encodings are:

    \list
    \li \l{Big5 Text Codec}{Big5}
    \li \l{Big5-HKSCS Text Codec}{Big5-HKSCS}
    \li CP949
    \li \l{EUC-JP Text Codec}{EUC-JP}
    \li \l{EUC-KR Text Codec}{EUC-KR}
    \li \l{GBK Text Codec}{GB18030}
    \li HP-ROMAN8
    \li IBM 850
    \li IBM 866
    \li IBM 874
    \li \l{ISO 2022-JP (JIS) Text Codec}{ISO 2022-JP}
    \li ISO 8859-1 to 10
    \li ISO 8859-13 to 16
    \li Iscii-Bng, Dev, Gjr, Knd, Mlm, Ori, Pnj, Tlg, and Tml
    \li KOI8-R
    \li KOI8-U
    \li Macintosh
    \li \l{Shift-JIS Text Codec}{Shift-JIS}
    \li TIS-620
    \li \l{TSCII Text Codec}{TSCII}
    \li UTF-8
    \li UTF-16
    \li UTF-16BE
    \li UTF-16LE
    \li UTF-32
    \li UTF-32BE
    \li UTF-32LE
    \li Windows-1250 to 1258
    \endlist

    If Qt is compiled with ICU support enabled, most codecs supported by
    ICU will also be available to the application.

    \l {QTextCodec}s can be used as follows to convert some locally encoded
    string to Unicode. Suppose you have some string encoded in Russian
    KOI8-R encoding, and want to convert it to Unicode. The simple way
    to do it is like this:

    \snippet code/src_corelib_codecs_qtextcodec.cpp 0

    After this, \c string holds the text converted to Unicode.
    Converting a string from Unicode to the local encoding is just as
    easy:

    \snippet code/src_corelib_codecs_qtextcodec.cpp 1

    To read or write files in various encodings, use QTextStream and
    its \l{QTextStream::setCodec()}{setCodec()} function. See the
    \l{tools/codecs}{Codecs} example for an application of QTextCodec
    to file I/O.

    Some care must be taken when trying to convert the data in chunks,
    for example, when receiving it over a network. In such cases it is
    possible that a multi-byte character will be split over two
    chunks. At best this might result in the loss of a character and
    at worst cause the entire conversion to fail.

    The approach to use in these situations is to create a QTextDecoder
    object for the codec and use this QTextDecoder for the whole
    decoding process, as shown below:

    \snippet code/src_corelib_codecs_qtextcodec.cpp 2

    The QTextDecoder object maintains state between chunks and therefore
    works correctly even if a multi-byte character is split between
    chunks.

    \section1 Creating Your Own Codec Class

    Support for new text encodings can be added to Qt by creating
    QTextCodec subclasses.

    The pure virtual functions describe the encoder to the system and
    the coder is used as required in the different text file formats
    supported by QTextStream, and under X11, for the locale-specific
    character input and output.

    To add support for another encoding to Qt, make a subclass of
    QTextCodec and implement the functions listed in the table below.

    \table
    \header \li Function \li Description

    \row \li name()
         \li Returns the official name for the encoding. If the
            encoding is listed in the
            \l{IANA character-sets encoding file}, the name
            should be the preferred MIME name for the encoding.

    \row \li aliases()
         \li Returns a list of alternative names for the encoding.
            QTextCodec provides a default implementation that returns
            an empty list. For example, "ISO-8859-1" has "latin1",
            "CP819", "IBM819", and "iso-ir-100" as aliases.

    \row \li \l{QTextCodec::mibEnum()}{mibEnum()}
         \li Return the MIB enum for the encoding if it is listed in
            the \l{IANA character-sets encoding file}.

    \row \li convertToUnicode()
         \li Converts an 8-bit character string to Unicode.

    \row \li convertFromUnicode()
         \li Converts a Unicode string to an 8-bit character string.
    \endtable

    \sa QTextStream, QTextDecoder, QTextEncoder, {Text Codecs Example}
*/

/*!
    Constructs a QTextCodec, and gives it the highest precedence. The
    QTextCodec should always be constructed on the heap (i.e. with \c
    new). Qt takes ownership and will delete it when the application
    terminates.
*/
QTextCodec::QTextCodec()
{
    QMutexLocker locker(textCodecsMutex());

    QCoreGlobalData *globalInstance = QCoreGlobalData::instance();
    if (globalInstance->allCodecs.isEmpty())
        setup();

    globalInstance->allCodecs.prepend(this);
}


/*!
    \nonreentrant

    Destroys the QTextCodec. Note that you should not delete codecs
    yourself: once created they become Qt's responsibility.
*/
QTextCodec::~QTextCodec()
{
}

/*!
    \fn QTextCodec *QTextCodec::codecForName(const char *name)

    Searches all installed QTextCodec objects and returns the one
    which best matches \a name; the match is case-insensitive. Returns
    0 if no codec matching the name \a name could be found.
*/

/*!
    \threadsafe
    Searches all installed QTextCodec objects and returns the one
    which best matches \a name; the match is case-insensitive. Returns
    0 if no codec matching the name \a name could be found.
*/
QTextCodec *QTextCodec::codecForName(const QByteArray &name)
{
    if (name.isEmpty())
        return 0;

    QMutexLocker locker(textCodecsMutex());

    QCoreGlobalData *globalData = QCoreGlobalData::instance();
    if (!globalData)
        return 0;
    setup();

#ifndef QT_USE_ICU
    QTextCodecCache *cache = &globalData->codecCache;
    QTextCodec *codec;
    if (cache) {
        codec = cache->value(name);
        if (codec)
            return codec;
    }

    for (TextCodecListConstIt it = globalData->allCodecs.constBegin(), cend = globalData->allCodecs.constEnd(); it != cend; ++it) {
        QTextCodec *cursor = *it;
        if (qTextCodecNameMatch(cursor->name(), name)) {
            if (cache)
                cache->insert(name, cursor);
            return cursor;
        }
        QList<QByteArray> aliases = cursor->aliases();
        for (ByteArrayListConstIt ait = aliases.constBegin(), acend = aliases.constEnd(); ait != acend; ++ait) {
            if (qTextCodecNameMatch(*ait, name)) {
                if (cache)
                    cache->insert(name, cursor);
                return cursor;
            }
        }
    }

    return 0;
#else
    return QIcuCodec::codecForNameUnlocked(name);
#endif
}


/*!
    \threadsafe
    Returns the QTextCodec which matches the
    \l{QTextCodec::mibEnum()}{MIBenum} \a mib.
*/
QTextCodec* QTextCodec::codecForMib(int mib)
{
    QMutexLocker locker(textCodecsMutex());

    QCoreGlobalData *globalData = QCoreGlobalData::instance();
    if (!globalData)
        return 0;
    if (globalData->allCodecs.isEmpty())
        setup();

    QByteArray key = "MIB: " + QByteArray::number(mib);

    QTextCodecCache *cache = &globalData->codecCache;
    QTextCodec *codec;
    if (cache) {
        codec = cache->value(key);
        if (codec)
            return codec;
    }

    for (TextCodecListConstIt it = globalData->allCodecs.constBegin(), cend = globalData->allCodecs.constEnd(); it != cend; ++it) {
        QTextCodec *cursor = *it;
        if (cursor->mibEnum() == mib) {
            if (cache)
                cache->insert(key, cursor);
            return cursor;
        }
    }

#ifdef QT_USE_ICU
    return QIcuCodec::codecForMibUnlocked(mib);
#else
    return 0;
#endif
}

/*!
    \threadsafe
    Returns the list of all available codecs, by name. Call
    QTextCodec::codecForName() to obtain the QTextCodec for the name.

    The list may contain many mentions of the same codec
    if the codec has aliases.

    \sa availableMibs(), name(), aliases()
*/
QList<QByteArray> QTextCodec::availableCodecs()
{
    QMutexLocker locker(textCodecsMutex());

    QCoreGlobalData *globalData = QCoreGlobalData::instance();
    if (globalData->allCodecs.isEmpty())
        setup();

    QList<QByteArray> codecs;

    for (TextCodecListConstIt it = globalData->allCodecs.constBegin(), cend = globalData->allCodecs.constEnd(); it != cend; ++it) {
        codecs += (*it)->name();
        codecs += (*it)->aliases();
    }

#ifdef QT_USE_ICU
    codecs += QIcuCodec::availableCodecs();
#endif

    return codecs;
}

/*!
    \threadsafe
    Returns the list of MIBs for all available codecs. Call
    QTextCodec::codecForMib() to obtain the QTextCodec for the MIB.

    \sa availableCodecs(), mibEnum()
*/
QList<int> QTextCodec::availableMibs()
{
#ifdef QT_USE_ICU
    return QIcuCodec::availableMibs();
#else
    QMutexLocker locker(textCodecsMutex());

    QCoreGlobalData *globalData = QCoreGlobalData::instance();
    if (globalData->allCodecs.isEmpty())
        setup();

    QList<int> codecs;

    for (TextCodecListConstIt it = globalData->allCodecs.constBegin(), cend = globalData->allCodecs.constEnd(); it != cend; ++it)
        codecs += (*it)->mibEnum();

    return codecs;
#endif
}

/*!
    \nonreentrant

    Set the codec to \a c; this will be returned by
    codecForLocale(). If \a c is a null pointer, the codec is reset to
    the default.

    This might be needed for some applications that want to use their
    own mechanism for setting the locale.

    \sa codecForLocale()
*/
void QTextCodec::setCodecForLocale(QTextCodec *c)
{
    QCoreGlobalData::instance()->codecForLocale.storeRelease(c);
}

/*!
    \threadsafe
    Returns a pointer to the codec most suitable for this locale.

    On Windows, the codec will be based on a system locale. On Unix
    systems, the codec will might fall back to using the \e iconv
    library if no builtin codec for the locale can be found.

    Note that in these cases the codec's name will be "System".
*/

QTextCodec* QTextCodec::codecForLocale()
{
    QCoreGlobalData *globalData = QCoreGlobalData::instance();
    if (!globalData)
        return 0;

    QTextCodec *codec = globalData->codecForLocale.loadAcquire();
    if (!codec) {
#ifdef QT_USE_ICU
        textCodecsMutex()->lock();
        codec = QIcuCodec::defaultCodecUnlocked();
        textCodecsMutex()->unlock();
#else
        // setupLocaleMapper locks as necessary
        codec = setupLocaleMapper();
#endif
    }

    return codec;
}


/*!
    \fn QByteArray QTextCodec::name() const

    QTextCodec subclasses must reimplement this function. It returns
    the name of the encoding supported by the subclass.

    If the codec is registered as a character set in the
    \l{IANA character-sets encoding file} this method should
    return the preferred mime name for the codec if defined,
    otherwise its name.
*/

/*!
    \fn int QTextCodec::mibEnum() const

    Subclasses of QTextCodec must reimplement this function. It
    returns the \l{QTextCodec::mibEnum()}{MIBenum} (see \l{IANA character-sets encoding file}
    for more information). It is important that each QTextCodec
    subclass returns the correct unique value for this function.
*/

/*!
  Subclasses can return a number of aliases for the codec in question.

  Standard aliases for codecs can be found in the
  \l{IANA character-sets encoding file}.
*/
QList<QByteArray> QTextCodec::aliases() const
{
    return QList<QByteArray>();
}

/*!
    \fn QString QTextCodec::convertToUnicode(const char *chars, int len,
                                             ConverterState *state) const

    QTextCodec subclasses must reimplement this function.

    Converts the first \a len characters of \a chars from the
    encoding of the subclass to Unicode, and returns the result in a
    QString.

    \a state can be 0, in which case the conversion is stateless and
    default conversion rules should be used. If state is not 0, the
    codec should save the state after the conversion in \a state, and
    adjust the \c remainingChars and \c invalidChars members of the struct.
*/

/*!
    \fn QByteArray QTextCodec::convertFromUnicode(const QChar *input, int number,
                                                  ConverterState *state) const

    QTextCodec subclasses must reimplement this function.

    Converts the first \a number of characters from the \a input array
    from Unicode to the encoding of the subclass, and returns the result
    in a QByteArray.

    \a state can be 0 in which case the conversion is stateless and
    default conversion rules should be used. If state is not 0, the
    codec should save the state after the conversion in \a state, and
    adjust the \c remainingChars and \c invalidChars members of the struct.
*/

/*!
    Creates a QTextDecoder with a specified \a flags to decode chunks
    of \c{char *} data to create chunks of Unicode data.

    The caller is responsible for deleting the returned object.

    \since 4.7
*/
QTextDecoder* QTextCodec::makeDecoder(QTextCodec::ConversionFlags flags) const
{
    return new QTextDecoder(this, flags);
}

/*!
    Creates a QTextEncoder with a specified \a flags to encode chunks
    of Unicode data as \c{char *} data.

    The caller is responsible for deleting the returned object.

    \since 4.7
*/
QTextEncoder* QTextCodec::makeEncoder(QTextCodec::ConversionFlags flags) const
{
    return new QTextEncoder(this, flags);
}

/*!
    \fn QByteArray QTextCodec::fromUnicode(const QChar *input, int number,
                                           ConverterState *state) const

    Converts the first \a number of characters from the \a input array
    from Unicode to the encoding of this codec, and returns the result
    in a QByteArray.

    The \a state of the convertor used is updated.
*/

/*!
    Converts \a str from Unicode to the encoding of this codec, and
    returns the result in a QByteArray.
*/
QByteArray QTextCodec::fromUnicode(const QString& str) const
{
    return convertFromUnicode(str.constData(), str.length(), 0);
}

/*!
    \fn QString QTextCodec::toUnicode(const char *input, int size,
                                      ConverterState *state) const

    Converts the first \a size characters from the \a input from the
    encoding of this codec to Unicode, and returns the result in a
    QString.

    The \a state of the convertor used is updated.
*/

/*!
    Converts \a a from the encoding of this codec to Unicode, and
    returns the result in a QString.
*/
QString QTextCodec::toUnicode(const QByteArray& a) const
{
    return convertToUnicode(a.constData(), a.length(), 0);
}

/*!
    Returns \c true if the Unicode character \a ch can be fully encoded
    with this codec; otherwise returns \c false.
*/
bool QTextCodec::canEncode(QChar ch) const
{
    ConverterState state;
    state.flags = ConvertInvalidToNull;
    convertFromUnicode(&ch, 1, &state);
    return (state.invalidChars == 0);
}

/*!
    \overload

    \a s contains the string being tested for encode-ability.
*/
bool QTextCodec::canEncode(const QString& s) const
{
    ConverterState state;
    state.flags = ConvertInvalidToNull;
    convertFromUnicode(s.constData(), s.length(), &state);
    return (state.invalidChars == 0);
}

/*!
    \overload

    \a chars contains the source characters.
*/
QString QTextCodec::toUnicode(const char *chars) const
{
    int len = qstrlen(chars);
    return convertToUnicode(chars, len, 0);
}


/*!
    \class QTextEncoder
    \inmodule QtCore
    \brief The QTextEncoder class provides a state-based encoder.
    \reentrant
    \ingroup i18n

    A text encoder converts text from Unicode into an encoded text format
    using a specific codec.

    The encoder converts Unicode into another format, remembering any
    state that is required between calls.

    \sa QTextCodec::makeEncoder(), QTextDecoder
*/

/*!
    \fn QTextEncoder::QTextEncoder(const QTextCodec *codec)

    Constructs a text encoder for the given \a codec.
*/

/*!
    Constructs a text encoder for the given \a codec and conversion \a flags.

    \since 4.7
*/
QTextEncoder::QTextEncoder(const QTextCodec *codec, QTextCodec::ConversionFlags flags)
    : c(codec), state()
{
    state.flags = flags;
}

/*!
    Destroys the encoder.
*/
QTextEncoder::~QTextEncoder()
{
}

/*!
    \internal
    \since 4.5
    Determines whether the eecoder encountered a failure while decoding the input. If
    an error was encountered, the produced result is undefined, and gets converted as according
    to the conversion flags.
 */
bool QTextEncoder::hasFailure() const
{
    return state.invalidChars != 0;
}

/*!
    Converts the Unicode string \a str into an encoded QByteArray.
*/
QByteArray QTextEncoder::fromUnicode(const QString& str)
{
    QByteArray result = c->fromUnicode(str.constData(), str.length(), &state);
    return result;
}

/*!
    \overload

    Converts \a len characters (not bytes) from \a uc, and returns the
    result in a QByteArray.
*/
QByteArray QTextEncoder::fromUnicode(const QChar *uc, int len)
{
    QByteArray result = c->fromUnicode(uc, len, &state);
    return result;
}

/*!
    \class QTextDecoder
    \inmodule QtCore
    \brief The QTextDecoder class provides a state-based decoder.
    \reentrant
    \ingroup i18n

    A text decoder converts text from an encoded text format into Unicode
    using a specific codec.

    The decoder converts text in this format into Unicode, remembering any
    state that is required between calls.

    \sa QTextCodec::makeDecoder(), QTextEncoder
*/

/*!
    \fn QTextDecoder::QTextDecoder(const QTextCodec *codec)

    Constructs a text decoder for the given \a codec.
*/

/*!
    Constructs a text decoder for the given \a codec and conversion \a flags.

    \since 4.7
*/

QTextDecoder::QTextDecoder(const QTextCodec *codec, QTextCodec::ConversionFlags flags)
    : c(codec), state()
{
    state.flags = flags;
}

/*!
    Destroys the decoder.
*/
QTextDecoder::~QTextDecoder()
{
}

/*!
    \fn QString QTextDecoder::toUnicode(const char *chars, int len)

    Converts the first \a len bytes in \a chars to Unicode, returning
    the result.

    If not all characters are used (e.g. if only part of a multi-byte
    encoding is at the end of the characters), the decoder remembers
    enough state to continue with the next call to this function.
*/
QString QTextDecoder::toUnicode(const char *chars, int len)
{
    return c->toUnicode(chars, len, &state);
}

// in qstring.cpp:
void qt_from_latin1(ushort *dst, const char *str, size_t size);

/*! \overload

    The converted string is returned in \a target.
 */
void QTextDecoder::toUnicode(QString *target, const char *chars, int len)
{
    Q_ASSERT(target);
    switch (c->mibEnum()) {
    case 106: // utf8
        static_cast<const QUtf8Codec*>(c)->convertToUnicode(target, chars, len, &state);
        break;
    case 4: // latin1
        target->resize(len);
        qt_from_latin1((ushort*)target->data(), chars, len);
        break;
    default:
        *target = c->toUnicode(chars, len, &state);
    }
}


/*!
    \overload

    Converts the bytes in the byte array specified by \a ba to Unicode
    and returns the result.
*/
QString QTextDecoder::toUnicode(const QByteArray &ba)
{
    return c->toUnicode(ba.constData(), ba.length(), &state);
}

/*!
    \since 4.4

    Tries to detect the encoding of the provided snippet of HTML in
    the given byte array, \a ba, by checking the BOM (Byte Order Mark)
    and the content-type meta header and returns a QTextCodec instance
    that is capable of decoding the html to unicode.  If the codec
    cannot be detected from the content provided, \a defaultCodec is
    returned.

    \sa codecForUtfText()
*/
QTextCodec *QTextCodec::codecForHtml(const QByteArray &ba, QTextCodec *defaultCodec)
{
    // determine charset
    QTextCodec *c = QTextCodec::codecForUtfText(ba, 0);
    if (!c) {
        QByteArray header = ba.left(1024).toLower();
        int pos = header.indexOf("meta ");
        if (pos != -1) {
            pos = header.indexOf("charset=", pos);
            if (pos != -1) {
                pos += qstrlen("charset=");

                int pos2 = pos;
                // The attribute can be closed with either """, "'", ">" or "/",
                // none of which are valid charset characters.
                while (++pos2 < header.size()) {
                    char ch = header.at(pos2);
                    if (ch == '\"' || ch == '\'' || ch == '>') {
                        QByteArray name = header.mid(pos, pos2 - pos);
                        if (name == "unicode") // QTBUG-41998, ICU will return UTF-16.
                            name = QByteArrayLiteral("UTF-8");
                        c = QTextCodec::codecForName(name);
                        return c ? c : defaultCodec;
                    }
                }
            }
        }
    }
    if (!c)
        c = defaultCodec;

    return c;
}

/*!
    \overload

    Tries to detect the encoding of the provided snippet of HTML in
    the given byte array, \a ba, by checking the BOM (Byte Order Mark)
    and the content-type meta header and returns a QTextCodec instance
    that is capable of decoding the html to unicode. If the codec cannot
    be detected, this overload returns a Latin-1 QTextCodec.
*/
QTextCodec *QTextCodec::codecForHtml(const QByteArray &ba)
{
    return codecForHtml(ba, QTextCodec::codecForName("ISO-8859-1"));
}

/*!
    \since 4.6

    Tries to detect the encoding of the provided snippet \a ba by
    using the BOM (Byte Order Mark) and returns a QTextCodec instance
    that is capable of decoding the text to unicode. If the codec
    cannot be detected from the content provided, \a defaultCodec is
    returned.

    \sa codecForHtml()
*/
QTextCodec *QTextCodec::codecForUtfText(const QByteArray &ba, QTextCodec *defaultCodec)
{
    const int arraySize = ba.size();

    if (arraySize > 3) {
        if ((uchar)ba[0] == 0x00
            && (uchar)ba[1] == 0x00
            && (uchar)ba[2] == 0xFE
            && (uchar)ba[3] == 0xFF)
            return QTextCodec::codecForMib(1018); // utf-32 be
        else if ((uchar)ba[0] == 0xFF
                 && (uchar)ba[1] == 0xFE
                 && (uchar)ba[2] == 0x00
                 && (uchar)ba[3] == 0x00)
            return QTextCodec::codecForMib(1019); // utf-32 le
    }

    if (arraySize < 2)
        return defaultCodec;
    if ((uchar)ba[0] == 0xfe && (uchar)ba[1] == 0xff)
        return QTextCodec::codecForMib(1013); // utf16 be
    else if ((uchar)ba[0] == 0xff && (uchar)ba[1] == 0xfe)
        return QTextCodec::codecForMib(1014); // utf16 le

    if (arraySize < 3)
        return defaultCodec;
    if ((uchar)ba[0] == 0xef
        && (uchar)ba[1] == 0xbb
        && (uchar)ba[2] == 0xbf)
        return QTextCodec::codecForMib(106); // utf-8

    return defaultCodec;
}

/*!
    \overload

    Tries to detect the encoding of the provided snippet \a ba by
    using the BOM (Byte Order Mark) and returns a QTextCodec instance
    that is capable of decoding the text to unicode. If the codec
    cannot be detected, this overload returns a Latin-1 QTextCodec.

    \sa codecForHtml()
*/
QTextCodec *QTextCodec::codecForUtfText(const QByteArray &ba)
{
    return codecForUtfText(ba, QTextCodec::codecForMib(/*Latin 1*/ 4));
}

/*!
    \fn QTextCodec * QTextCodec::codecForTr ()
    \obsolete

    Returns the codec used by QObject::tr() on its argument. If this
    function returns 0 (the default), tr() assumes Latin-1.

    \sa  setCodecForTr()
*/

/*!
    \fn QTextCodec::setCodecForTr ( QTextCodec * c )
    \obsolete

    Sets the codec used by QObject::tr() on its argument to c. If c
    is 0 (the default), tr() assumes Latin-1.
*/

/*!
    \internal
    \since 4.3
    Determines whether the decoder encountered a failure while decoding the
    input. If an error was encountered, the produced result is undefined, and
    gets converted as according to the conversion flags.
 */
bool QTextDecoder::hasFailure() const
{
    return state.invalidChars != 0;
}

QT_END_NAMESPACE

#endif // QT_NO_TEXTCODEC