summaryrefslogtreecommitdiffstats
path: root/kdecore/kcharsets.cpp
blob: f4ae826f5fa897b3be29f0a0aa572a7c6fb7d06c (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
/* This file is part of the KDE libraries
    Copyright (C) 1999 Lars Knoll (knoll@kde.org)

    This library is free software; you can redistribute it and/or
    modify it under the terms of the GNU Library General Public
    License as published by the Free Software Foundation; either
    version 2 of the License, or (at your option) any later version.

    This library is distributed in the hope that it will be useful,
    but WITHOUT ANY WARRANTY; without even the implied warranty of
    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
    Library General Public License for more details.

    You should have received a copy of the GNU Library General Public License
    along with this library; see the file COPYING.LIB.  If not, write to
    the Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor,
    Boston, MA 02110-1301, USA.
*/
#include "kcharsets.h"

#include "kqiodevicegzip_p.h"
#include "kentities.c"

#include <kapplication.h>
#include <kglobal.h>
#include <klocale.h>
#include <kconfig.h>

#include <tqfontinfo.h>
#include <tqstrlist.h>
#include <tqfontdatabase.h>
#include <kdebug.h>

#include <tqtextcodec.h>
#include <tqmap.h>
#include <tqcstring.h>
#include <tqdir.h>
#include <tqregexp.h>

#include <assert.h>

static const char * const language_names[] = {
	I18N_NOOP( "Other" ),
	I18N_NOOP( "Arabic" ),
	I18N_NOOP( "Baltic" ),
	I18N_NOOP( "Central European" ),
	I18N_NOOP( "Chinese Simplified" ),
	I18N_NOOP( "Chinese Traditional" ),
	I18N_NOOP( "Cyrillic" ),
	I18N_NOOP( "Greek" ),
	I18N_NOOP( "Hebrew" ),
	I18N_NOOP( "Japanese" ),
	I18N_NOOP( "Korean" ),
	I18N_NOOP( "Thai" ),
	I18N_NOOP( "Turkish" ),
	I18N_NOOP( "Western European" ),
	I18N_NOOP( "Tamil" ),
	I18N_NOOP( "Unicode" ),
	I18N_NOOP( "Northern Saami" ),
        I18N_NOOP( "Vietnamese" ),
        I18N_NOOP( "South-Eastern Europe" )
};

// This list gives the charsets that can be used to display a file given in a certain encoding.
// The list should be in order of preference
static const char* const charsets_for_encoding[] = {
    "koi8-r",
    "koi8-u",
    "iso 8859-1",
    "iso 8859-2",
    "iso 8859-3",
    "iso 8859-4",
    "iso 8859-5",
    "iso 8859-6",
    "iso 8859-7",
    "iso 8859-8",
    "iso 8859-8-i",
    "iso 8859-9",
    "iso 8859-11",
    "iso 8859-13",
    "iso 8859-14",
    "iso 8859-15",
    "iso 8859-16",
    "utf8",
    "utf16",
    "iso-10646-ucs-2",
    "cp 1250",
    "cp 1251",
    "cp 1252",
    "cp 1253",
    "cp 1254",
    "cp 1255",
    "cp 1256",
    "cp 1257",
    "cp 1258",
    "ibm850",
    "ibm852",
    "ibm866",
    "tis620",
    "eucjp",
    "sjis",
    "jis7",
    "big5",
    "big5-hkscs",
    "gbk",
    "gb18030",
    "gb2312",
    "euckr",
    "tscii",
//    "pt 154",
    "winsami2",
    "cp 874",
    0 }; // extra 0 for end

// 0 other
// 1 Arabic
// 2 Baltic
// 3 Central European
// 4 Chinese Simplified
// 5 Chinese Traditional
// 6 Cyrillic
// 7 Greek
// 8 Hebrew
// 9 Japanese
// 10 Korean
// 11 Thai
// 12 Turkish
// 13 Western European
// 14 Tamil
// 15 Unicode
// 16 Northern Sami
// 17 Vietnamese
// 18 South-Eastern Europe
// ### FIXME KDE4: the name of the encodings should mostly be uppercase
static struct LanguageForEncoding
    {
    const char* index;
    int data;
    } const language_for_encoding[] = {
    { "iso 8859-1", 13 },
    { "iso 8859-15", 13 },
    { "iso 8859-14", 13 },
    { "cp 1252", 13 },
    { "ibm850", 13 },
    { "iso 8859-2", 3 },
    { "iso 8859-3", 3 },
    { "iso 8859-4", 2 },
    { "iso 8859-13", 2 },
    { "iso 8859-16", 18 },
    { "cp 1250", 3 },
    { "cp 1254", 12 },
    { "cp 1257", 2 },
    { "ibm852", 3 },
    { "koi8-r", 6 },
    { "iso 8859-5", 6 },
    { "cp 1251", 6 },
    { "koi8-u", 6 },
//    { "pt 154", 6 },
    { "ibm866", 6 },
    { "big5", 5 },
    { "big5-hkscs", 5 },
    { "gb18030", 4 },
    { "gbk", 4 },
    { "gb2312", 4 },
    { "euckr", 10 },
    { "sjis", 9 },
    { "jis7", 9 },
    { "eucjp", 9 },
    { "iso 8859-7", 7 },
    { "cp 1253", 7 },
    { "iso 8859-6", 1 },
    { "cp 1256", 1 },
    { "iso 8859-8", 8 },
    { "iso 8859-8-i", 8 },
    { "cp 1255", 8 },
    { "iso 8859-9", 12 },
    { "tis620", 11 },
    { "iso 8859-11", 11 },
    { "cp 874", 11 },
    { "cp 1258", 17 },
    { "tscii", 14 },
    { "utf8", 15 },
    { "utf16", 15 },
    { "utf7", 15 }, // ### FIXME: UTF-7 is not in Qt
    { "ucs2", 15 },
    { "iso-10646-ucs-2", 15 },
    { "winsami2", 16},
    { 0, 0 } };

// defines some different names for codecs that are built into Qt.
static struct Builtin
    {
    const char* index;
    const char* data;
    } const builtin[] = {
    { "iso-ir-111", "koi8-r" },
    { "koi8-ru", "koi8-u" }, // ### Qt 3.3 maps it to koi8-r
    { "koi unified", "koi8-r" }, // ### FIXME: Qt 3.3 seems to map this to EUC-KR, so this mapping is too late :-(
    // Using ISO-8859-1 for ASCII is an approximation at write
    { "us-ascii", "iso 8859-1" },
    { "usascii", "iso 8859-1" },
    { "ascii", "iso 8859-1" },
    { "x-utf-8", "utf-8" },
    { "x-utf-7", "utf-7" }, // ### FIXME: UTF-7 is not in Qt 
    { "unicode-1-1-utf-7", "utf-7" }, // ### FIXME: UTF-7 is not in Qt
    { "utf-16", "iso-10646-ucs-2" },
    { "utf16", "iso-10646-ucs-2" },
    { "ucs2", "iso-10646-ucs-2" },
    { "iso10646-1", "iso-10646-ucs-2" },
    { "gb18030.2000-1", "gb18030" },
    { "gb18030.2000-0", "gb18030" },
    { "gbk-0", "gbk" },
    { "gb2312.1980-0", "gbk" },
    { "gb_2312-80", "gbk" },/* this one is not official, but MS is using it :/ */
    { "x-euc-kr", "euckr" },
    { "jisx0201.1976-0", "eucjp" },
    { "jisx0208.1983-0", "eucjp" },
    { "jisx0208.1990-0", "eucjp" },
    { "jisx0208.1997-0", "eucjp" },
    { "jisx0212.1990-0", "eucjp" },
    { "jisx0213.2000-1", "eucjp" },
    { "jisx0213.2000-2", "eucjp" },
    { "windows850", "ibm850" },
    { "windows866", "ibm866" },
    { "windows1251", "cp 1251" },
    { "windows1252", "cp 1252" },
    { "windows1253", "cp 1253" },
    { "windows1254", "cp 1254" },
    { "windows1255", "cp 1255" },
    { "windows1256", "cp 1256" },
    { "windows1257", "cp 1257" },
    { "windows1258", "cp 1258" },
    { "windows-850", "ibm850" },
    { "windows-866", "ibm866" },
    { "x-windows-850", "ibm850" },
    { "x-windows-866", "ibm866" },
    { "x-windows-1250", "cp 1250" },
    { "x-windows-1251", "cp 1251" },
    { "x-windows-1252", "cp 1252" },
    { "x-windows-1253", "cp 1253" },
    { "x-windows-1254", "cp 1254" },
    { "x-windows-1255", "cp 1255" },
    { "x-windows-1256", "cp 1256" },
    { "x-windows-1257", "cp 1257" },
    { "x-windows-1258", "cp 1258" },
    { "cp819", "iso 8859-1" },
    { "cp850", "ibm850" },
    { "cp866", "ibm866" },
    { "cp-819", "iso 8859-1" },
    { "cp-850", "ibm850" },
    { "cp-866", "ibm866" },
    { "cp-1250", "cp 1250" },
    { "cp-1251", "cp 1251" },
    { "cp-1252", "cp 1252" },
    { "cp-1253", "cp 1253" },
    { "cp-1254", "cp 1254" },
    { "cp-1255", "cp 1255" },
    { "cp-1256", "cp 1256" },
    { "cp-1257", "cp 1257" },
    { "cp-1258", "cp 1258" },
    { "cp-10000", "apple roman" },
    { "x-cp-850", "ibm850" },
    { "x-cp-866", "ibm866" },
    { "x-cp-1250", "cp 1250" },
    { "x-cp-1251", "cp 1251" },
    { "x-cp-1252", "cp 1252" },
    { "x-cp-1253", "cp 1253" },
    { "x-cp-1254", "cp 1254" },
    { "x-cp-1255", "cp 1255" },
    { "x-cp-1256", "cp 1256" },
    { "x-cp-1257", "cp 1257" },
    { "x-cp-1258", "cp 1258" },
    { "x-cp-10000", "apple roman" },
    { "ibm819", "iso 8859-1" },
    { "thai-tis620", "iso 8859-11" },
    { "windows-874", "cp 874" },
    { "windows874", "cp 874" },
    { "x-windows-874", "cp 874" },
    { "x-cp-874", "cp 874" },
    { "ibm 874", "cp 874" },
    { "ibm874", "cp 874" }, // Qt4 name
    { "x-ibm874", "cp 874" },
    { "ksc5601.1987-0", "euckr" },
    { "x-winsami2", "winsami2" },
    { "x-mac-roman", "apple roman" },
    { "macintosh", "apple roman" },
    { "mac", "apple roman" },
    { "csiso2022jp", "jis7" }, // See bug #77243
    { "big5-eten", "big5-hkscs" },
    { "cp950", "big5-hkscs" },
    { 0, 0 }};

// some different names for the encodings defined in the charmaps files.
// even though the charmap file names are all uppercase, the names are all lowercase here.
static struct Aliases
    {
    const char* index;
    const char* data;
    } const aliases[] = {
    { "cp852", "ibm852" },
    { "cp-852", "ibm852" },
    { "x-cp-852", "ibm852" },
    { "windows852", "ibm852" },
    { "windows-852", "ibm852" },
    { "x-windows-852", "ibm852" },
    { 0, 0 }};

// some last resort hints in case the charmap file couldn't be found. This gives at least a partial conversion
// and helps making things readable.
// the name used as input here is already converted to the more canonical name as defined in the aliases array.
static struct ConversionHints
    {
    const char* index;
    const char* data;
    } const conversion_hints[] = {
    { "cp1250", "iso-8859-2" },
    { "koi8-r", "iso-8859-5" },
    { "koi8-u", "koi8-r" },
    // KDE had always "CP 1251" as best fallback to PT 154. Now that Qt does not offer this encoding anymore, it is our fallback.
    { "pt 154", "cp 1251" },
    { "paratype-154", "cp 1251" },
    { "pt-154", "cp 1251" },
    { 0, 0 }};


// search an array of items index/data, index is const char*, data is T, find first matching index
// and return data, or return 0
template< typename T, typename Data >
static Data kcharsets_array_search( const T* start, const char* entry )
{
    for( const T* pos = start;
         pos->index != 0;
         ++pos )
        if( qstrcmp( pos->index, entry ) == 0 )
            return pos->data;
    return 0;
}


class KCharsetsPrivate
{
public:
    KCharsetsPrivate(KCharsets* _kc)
        : codecForNameDict(43, false) // case insensitive
    {
        db = 0;
        kc = _kc;
    }
    ~KCharsetsPrivate()
    {
        delete db;
    }
    TQFontDatabase *db;
    TQAsciiDict<TQTextCodec> codecForNameDict;
    KCharsets* kc;
};

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

KCharsets::KCharsets()
{
    d = new KCharsetsPrivate(this);
}

KCharsets::~KCharsets()
{
    delete d;
}

TQChar KCharsets::fromEntity(const TQString &str)
{
    TQChar res = TQChar::null;

    int pos = 0;
    if(str[pos] == '&') pos++;

    // Check for '&#000' or '&#x0000' sequence
    if (str[pos] == '#' && str.length()-pos > 1) {
        bool ok;
        pos++;
        if (str[pos] == 'x' || str[pos] == 'X') {
            pos++;
            // '&#x0000', hexadeciaml character reference
            TQString tmp(str.unicode()+pos, str.length()-pos);
            res = tmp.toInt(&ok, 16);
        } else {
            //  '&#0000', decimal character reference
            TQString tmp(str.unicode()+pos, str.length()-pos);
            res = tmp.toInt(&ok, 10);
        }
        return res;
    }

    const entity *e = kde_findEntity(str.ascii(), str.length());

    if(!e)
    {
        //kdDebug( 0 ) << "unknown entity " << str <<", len = " << str.length() << endl;
        return TQChar::null;
    }
    //kdDebug() << "got entity " << str << " = " << e->code << endl;

    return TQChar(e->code);
}

TQChar KCharsets::fromEntity(const TQString &str, int &len)
{
    // entities are never longer than 8 chars... we start from
    // that length and work backwards...
    len = 8;
    while(len > 0)
    {
        TQString tmp = str.left(len);
        TQChar res = fromEntity(tmp);
        if( res != TQChar::null ) return res;
        len--;
    }
    return TQChar::null;
}


TQString KCharsets::toEntity(const TQChar &ch)
{
    TQString ent;
    ent.sprintf("&#0x%x;", ch.unicode());
    return ent;
}

TQString KCharsets::resolveEntities( const TQString &input )
{
    TQString text = input;
    const TQChar *p = text.unicode();
    const TQChar *end = p + text.length();
    const TQChar *ampersand = 0;
    bool scanForSemicolon = false;

    for ( ; p < end; ++p ) {
        const TQChar ch = *p;

        if ( ch == '&' ) {
            ampersand = p;
            scanForSemicolon = true;
            continue;
        }

        if ( ch != ';' || scanForSemicolon == false )
            continue;

        assert( ampersand );

        scanForSemicolon = false;

        const TQChar *entityBegin = ampersand + 1;

        const uint entityLength = p - entityBegin;
        if ( entityLength == 0 )
            continue;

        const TQChar entityValue = KCharsets::fromEntity( TQConstString( entityBegin, entityLength ).string() );
        if ( entityValue.isNull() )
            continue;

        const uint ampersandPos = ampersand - text.unicode();

        text[ (int)ampersandPos ] = entityValue;
        text.remove( ampersandPos + 1, entityLength + 1 );
        p = text.unicode() + ampersandPos;
        end = text.unicode() + text.length();
        ampersand = 0;
    }

    return text;
}

TQStringList KCharsets::availableEncodingNames()
{
    TQStringList available;
    for ( const char* const* pos = charsets_for_encoding; *pos; ++pos ) {
        //kdDebug(0) << *charsets << " available" << endl;
        available.append( TQString::fromLatin1( *pos ));
    }
    return available;
}

TQString KCharsets::languageForEncoding( const TQString &encoding )
{
    int lang = kcharsets_array_search< LanguageForEncoding, int >
        ( language_for_encoding, encoding.latin1());
    return i18n( language_names[lang] );
}

TQString KCharsets::encodingForName( const TQString &descriptiveName )
{
    const int left = descriptiveName.findRev( '(' );
    
    if (left<0) // No parenthesis, so assume it is a normal encoding name
	return descriptiveName.stripWhiteSpace();
    
    TQString name(descriptiveName.mid(left+1));
    
    const int right = name.findRev( ')' );
    
    if (right<0) 
        return name;

    return name.left(right).stripWhiteSpace();
}

TQStringList KCharsets::descriptiveEncodingNames()
{
    // As we are sorting, we can directly read the array language_for_encoding
    TQStringList encodings;
    for ( const LanguageForEncoding* pos = language_for_encoding; pos->index; ++pos ) {
        const TQString name = TQString::fromLatin1( pos->index );
        const TQString description = i18n( language_names[ pos->data ] );
        encodings.append( i18n("Descriptive Encoding Name", "%1 ( %2 )"). arg ( description ). arg( name ) );
    }
    encodings.sort();
    return encodings;
}

TQTextCodec *KCharsets::codecForName(const TQString &n) const
{
    bool b;
    return codecForName( n, b );
}

TQTextCodec *KCharsets::codecForName(const TQString &n, bool &ok) const
{
    ok = true;

    TQTextCodec* codec = 0;
    // dict lookup is case insensitive anyway
    if((codec = d->codecForNameDict[n.isEmpty() ? "->locale<-" : n.latin1()]))
        return codec; // cache hit, return

    if (n.isEmpty()) {
        codec = KGlobal::locale()->codecForEncoding();
        d->codecForNameDict.replace("->locale<-", codec);
        return codec;
    }

    TQCString name = n.lower().latin1();
    TQCString key = name;
    if (name.right(8) == "_charset")
       name.truncate(name.length()-8);

    if (name.isEmpty()) {
      ok = false;
      return TQTextCodec::codecForName("iso8859-1");
    }

    codec = TQTextCodec::codecForName(name);

    if(codec) {
        d->codecForNameDict.replace(key, codec);
        return codec;
    }

    // these codecs are built into Qt, but the name given for the codec is different,
    // so TQTextCodec did not recognize it.
    TQCString cname = kcharsets_array_search< Builtin, const char* >( builtin, name.data());

    if(!cname.isEmpty())
        codec = TQTextCodec::codecForName(cname);

    if(codec)
    {
        d->codecForNameDict.replace(key, codec);
        return codec;
    }

    TQString dir;
    {
    KConfigGroupSaver cfgsav( KGlobal::config(), "i18n" );
    dir = KGlobal::config()->readPathEntry("i18ndir", TQString::fromLatin1("/usr/share/i18n/charmaps"));
    }

    // these are codecs not included in Qt. They can be build up if the corresponding charmap
    // is available in the charmap directory.
    cname = kcharsets_array_search< Aliases, const char* >( aliases, name.data());

    if(cname.isEmpty())
        cname = name;
    cname = cname.upper();

    const TQString basicName = TQString::fromLatin1(cname);
    kdDebug() << k_funcinfo << endl << " Trying to find " << cname << " in " << dir << endl;
    
    TQString charMapFileName;
    bool gzipped = false; 
    TQDir qdir(dir);
    if (!qdir.exists()) {
        // The directory for the charmaps does not even exist... (That is common!)
    }
    else if (qdir.exists(basicName, false)) {
        charMapFileName = basicName;
    }
    else if (qdir.exists(basicName+".gz", false)) {
        charMapFileName = basicName + ".gz";
        gzipped = true;
    }
    else {
        // Check if we are asking a code page
        // If yes, then check "CP99999" and "IBM99999"
        // First we need to find the number of the codepage
        TQRegExp regexp("^(X-)?(CP|IBM)(-| )?(0-9)+");
        if ( regexp.search(basicName) != -1) {
            const TQString num = regexp.cap(4);
            if (num.isEmpty()) {
                // No number, not a code page (or something went wrong)
            }
            else if (qdir.exists("IBM"+num)) {
                charMapFileName = "IBM"+num;
            }
            else if (qdir.exists("IBM"+num+".gz")) {
                charMapFileName = "IBM"+num+".gz";
                gzipped = true;
            }
            else if (qdir.exists("CP"+num)) {
                charMapFileName = "CP"+num;
            }
            else if (qdir.exists("CP"+num+".gz")) {
                charMapFileName = "CP"+num+".gz";
                gzipped = true;
            }
        }
    }
    
    if (gzipped && !charMapFileName.isEmpty()) {
        KQIODeviceGZip gzip(dir + "/" + charMapFileName);
        if (gzip.open(IO_ReadOnly)) {
            kdDebug() << "Loading gzipped charset..." << endl;
            codec = TQTextCodec::loadCharmap(&gzip);
            gzip.close();
        }
        else
            kdWarning() << "Could not open gzipped charset!" << endl;
    }
    else if (!charMapFileName.isEmpty()) {
        codec = TQTextCodec::loadCharmapFile(dir + "/" + charMapFileName);
    }

    if(codec) {
        d->codecForNameDict.replace(key, codec);
        return codec;
    }

    // this also failed, the last resort is now to take some compatibility charmap

    cname = kcharsets_array_search< ConversionHints, const char* >( conversion_hints, (const char*)name.data() );

    if(!cname.isEmpty())
        codec = TQTextCodec::codecForName(cname);

    if(codec) {
        d->codecForNameDict.replace(key, codec);
        return codec;
    }

    // could not assign a codec, let's return Latin1
    ok = false;
    return TQTextCodec::codecForName("iso8859-1");
}