summaryrefslogtreecommitdiffstats
path: root/khtml/misc/decoder.cpp
blob: f227f4014c877e4d32034646ca33673f46c7093e (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
/*
    This file is part of the KDE libraries

    Copyright (C) 1999 Lars Knoll (knoll@kde.org)
    Copyright (C) 2003 Dirk Mueller (mueller@kde.org)
    Copyright (C) 2003 Apple Computer, Inc.

    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.
*/
//----------------------------------------------------------------------------
//
// KDE HTML Widget -- decoder for input stream

#undef DECODE_DEBUG
//#define DECODE_DEBUG

#include <assert.h>

#include "decoder.h"
#include "guess_ja.h"

using namespace khtml;

#include "htmlhashes.h"

#include <tqregexp.h>
#include <tqtextcodec.h>

#include <kglobal.h>
#include <kcharsets.h>

#include <ctype.h>
#include <kdebug.h>
#include <klocale.h>



Decoder::Decoder()
{
    // latin1
    m_codec = TQTextCodec::codecForMib(4);
    m_decoder = m_codec->makeDecoder();
    enc = 0;
    m_type = DefaultEncoding;
    body = false;
    beginning = true;
    visualRTL = false;
    m_autoDetectLanguage = SemiautomaticDetection;
    kc = NULL;
}

Decoder::~Decoder()
{
    delete m_decoder;
    if (kc)
        delete kc;
}

void Decoder::setEncoding(const char *_encoding, EncodingType type)
{
#ifdef DECODE_DEBUG
    kdDebug(6005) << "setEncoding " << _encoding << " " << type << endl;
#endif
    enc = _encoding;
#ifdef DECODE_DEBUG
    kdDebug(6005) << "old encoding is:" << m_codec->name() << endl;
#endif
    enc = enc.lower();
#ifdef DECODE_DEBUG
    kdDebug(6005) << "requesting:" << enc << endl;
#endif
    if(enc.isNull() || enc.isEmpty())
        return;

#ifdef APPLE_CHANGES
    TQTextCodec *codec = (type == EncodingFromMetaTag || type == EncodingFromXMLHeader)
        ? TQTextCodec::codecForNameEightBitOnly(enc)
        : TQTextCodec::codecForName(enc);
    if (codec) {
        enc = codec->name();
        visualRTL = codec->usesVisualOrdering();
    }
#else
    if(enc == "visual") // hebrew visually ordered
        enc = "iso8859-8";
    bool b;
    TQTextCodec *codec = KGlobal::charsets()->codecForName(enc, b);
    if (!b)
        codec = 0;

    if (type == EncodingFromMetaTag || type  == EncodingFromXMLHeader) {
        //Sometimes the codec specified is absurd, i.e. UTF-16 despite
        //us decoding a meta tag as ASCII. In that case, ignore it.
        if (codec &&
            (codec->mibEnum() == 1000)) //UTF16 or similar.
                codec = 0;
    }

    if (codec && codec->mibEnum() == 11)  {
        //We do NOT want to use Qt's TQHebrewCodec, since it tries to reorder itself.
        codec = TQTextCodec::codecForName("iso8859-8-i");
	
        // visually ordered unless one of the following
        if( !(enc == "iso-8859-8-i" || enc == "iso_8859-8-i"
                || enc == "csiso88598i" || enc == "logical") )
        visualRTL = true;
    }
#endif

    if( codec ) { // in case the codec didn't exist, we keep the old one (fixes some sites specifying invalid codecs)
        m_codec = codec;
        m_type = type;
        delete m_decoder;
        m_decoder = m_codec->makeDecoder();
    }

#ifdef DECODE_DEBUG
    kdDebug(6005) << "Decoder::encoding used is" << m_codec->name() << endl;
#endif
}

const char *Decoder::encoding() const
{
    return enc;
}

// Other browsers allow comments in the head section, so we need to also.
// It's important not to look for tags inside the comments.
static void skipComment(const char *&ptr, const char *pEnd)
{
    const char *p = ptr;
    // Allow <!-->; other browsers do.
    if (*p == '>') {
        p++;
    } else {
        while (p != pEnd) {
            if (*p == '-') {
                // This is the real end of comment, "-->".
                if (p[1] == '-' && p[2] == '>') {
                    p += 3;
                    break;
                }
                // This is the incorrect end of comment that other browsers allow, "--!>".
                if (p[1] == '-' && p[2] == '!' && p[3] == '>') {
                    p += 4;
                    break;
                }
            }
            p++;
        }
    }
    ptr = p;
}

// Returns the position of the encoding string.
static int findXMLEncoding(const TQCString &str, int &encodingLength)
{
    int len = str.length();

    int pos = str.find("encoding");
    if (pos == -1)
        return -1;
    pos += 8;

    // Skip spaces and stray control characters.
    while (pos < len && str[pos] <= ' ')
        ++pos;

    //Bail out if nothing after
    if (pos >= len)
        return -1;

    // Skip equals sign.
    if (str[pos] != '=')
        return -1;
    ++pos;

    // Skip spaces and stray control characters.
    while (pos < len && str[pos] <= ' ')
        ++pos;

    //Bail out if nothing after
    if (pos >= len)
        return -1;

    // Skip quotation mark.
    char quoteMark = str[pos];
    if (quoteMark != '"' && quoteMark != '\'')
        return -1;
    ++pos;

    // Find the trailing quotation mark.
    int end = pos;
    while (end < len && str[end] != quoteMark)
        ++end;

    if (end >= len)
        return -1;

    encodingLength = end - pos;
    return pos;
}

TQString Decoder::decode(const char *data, int len)
{
    // Check for UTF-16 or UTF-8 BOM mark at the beginning, which is a sure sign of a Unicode encoding.
    int bufferLength = buffer.length();
    const int maximumBOMLength = 10;
    if (beginning && bufferLength + len >= maximumBOMLength) {
        // If the user has chosen utf16 we still need to auto-detect the endianness
        if ((m_type != UserChosenEncoding) || (m_codec->mibEnum() == 1000)) {
            // Extract the first three bytes.
            // Handle the case where some of bytes are already in the buffer.
            const uchar *udata = (const uchar *)data;
            uchar c1 = bufferLength >= 1 ? (uchar)buffer[0] : *udata++;
            uchar c2 = bufferLength >= 2 ? (uchar)buffer[1] : *udata++;
            uchar c3 = bufferLength >= 3 ? (uchar)buffer[2] : *udata++;

            // Check for the BOM
            const char *autoDetectedEncoding;
            if ((c1 == 0xFE && c2 == 0xFF) || (c1 == 0xFF && c2 == 0xFE)) {
                autoDetectedEncoding = "ISO-10646-UCS-2";
            } else if (c1 == 0xEF && c2 == 0xBB && c3 == 0xBF) {
                autoDetectedEncoding = "UTF-8";
            } else if (c1 == 0x00 || c2 == 0x00) {
                uchar c4 = bufferLength >= 4 ? (uchar)buffer[3] : *udata++;
                uchar c5 = bufferLength >= 5 ? (uchar)buffer[4] : *udata++;
                uchar c6 = bufferLength >= 6 ? (uchar)buffer[5] : *udata++;
                uchar c7 = bufferLength >= 7 ? (uchar)buffer[6] : *udata++;
                uchar c8 = bufferLength >= 8 ? (uchar)buffer[7] : *udata++;
                uchar c9 = bufferLength >= 9 ? (uchar)buffer[8] : *udata++;
                uchar c10 = bufferLength >= 10 ? (uchar)buffer[9] : *udata++;
                int nul_count_even = (c2 != 0) + (c4 != 0) + (c6 != 0) + (c8 != 0) + (c10 != 0);
                int nul_count_odd = (c1 != 0) + (c3 != 0) + (c5 != 0) + (c7 != 0) + (c9 != 0);
                if ((nul_count_even == 0 && nul_count_odd == 5) ||
                    (nul_count_even == 5 && nul_count_odd == 0))
                    autoDetectedEncoding = "ISO-10646-UCS-2";
                else
                    autoDetectedEncoding = 0;
            } else {
                autoDetectedEncoding = 0;
            }

            // If we found a BOM, use the encoding it implies.
            if (autoDetectedEncoding != 0) {
                m_type = AutoDetectedEncoding;
                m_codec = TQTextCodec::codecForName(autoDetectedEncoding);
                assert(m_codec);
                enc = m_codec->name();
                delete m_decoder;
                m_decoder = m_codec->makeDecoder();
                if (m_codec->mibEnum() == 1000 && c2 == 0x00)
                {
                  // utf16LE, we need to put the decoder in LE mode
                  char reverseUtf16[3] = {0xFF, 0xFE, 0x00};
                  m_decoder->toUnicode(reverseUtf16, 2);
                }
            }
        }
        beginning = false;
    }

    // this is not completely efficient, since the function might go
    // through the html head several times...

    bool lookForMetaTag = m_type == DefaultEncoding && !body;

    if (lookForMetaTag) {
#ifdef DECODE_DEBUG
        kdDebug(6005) << "looking for charset definition" << endl;
#endif
        { // extra level of braces to keep indenting matching original for better diff'ing
#ifdef APPLE_CHANGES
            buffer.append(data, len);
#else
            if(m_codec->mibEnum() != 1000) {  // utf16
                // replace '\0' by spaces, for buggy pages
                char *d = const_cast<char *>(data);
                int i = len - 1;
                while(i >= 0) {
                    if(d[i] == 0) d[i] = ' ';
                    i--;
                }
            }
            buffer += TQCString(data, len+1);
#endif
            // we still don't have an encoding, and are in the head
            // the following tags are allowed in <head>:
            // SCRIPT|STYLE|META|LINK|OBJECT|TITLE|BASE
            int invalid = 0; // invalid head tag count
#ifdef APPLE_CHANGES
            const char *ptr = buffer.latin1();
            const char *pEnd = ptr + buffer.length();
#else
            const char *ptr = buffer.data();
            const char *pEnd = ptr + buffer.length();
#endif
            while(ptr != pEnd)
            {
                if(*ptr == '<') {
                    bool end = false;
                    ptr++;

                    // Handle comments.
                    if (ptr[0] == '!' && ptr[1] == '-' && ptr[2] == '-') {
                        ptr += 3;
                        skipComment(ptr, pEnd);
                        continue;
                    }

                    // Handle XML header, which can have encoding in it.
                    if (ptr[0] == '?' && ptr[1] == 'x' && ptr[2] == 'm' && ptr[3] == 'l') {
                        const char *end = ptr;
                        while (*end != '>' && *end != '\0') end++;
                        if (*end == '\0')
                            break;
                        TQCString str(ptr, end - ptr + 1); //+1 as it must include the \0 terminator
                        int len;
                        int pos = findXMLEncoding(str, len);
                        if (pos != -1) {
                            setEncoding(str.mid(pos, len), EncodingFromXMLHeader);
                            if (m_type == EncodingFromXMLHeader)
                                goto found;
                        }
                    }

                    if(*ptr == '/') ptr++, end=true;
                    char tmp[20];
                    int len = 0;
                    while (
                        ((*ptr >= 'a') && (*ptr <= 'z') ||
                         (*ptr >= 'A') && (*ptr <= 'Z') ||
                         (*ptr >= '0') && (*ptr <= '9'))
                        && len < 19 )
                    {
                        tmp[len] = tolower( *ptr );
                        ptr++;
                        len++;
                    }
		    tmp[len] = 0;
                    int id = khtml::getTagID(tmp, len);
                    if(end) id += ID_CLOSE_TAG;

                    switch( id ) {
                    case ID_META:
                    {
                        // found a meta tag...
                        //ptr += 5;
                        const char * end = ptr;
                        while(*end != '>' && *end != '\0') end++;
                        if ( *end == '\0' ) break;
                        TQCString str( ptr, (end-ptr)+1);
                        str = str.lower();
                        int pos = 0;
                        //if( (pos = str.find("http-equiv", pos)) == -1) break;
                        //if( (pos = str.find("content-type", pos)) == -1) break;
			while( pos < ( int ) str.length() ) {
			    if( (pos = str.find("charset", pos)) == -1) break;
			    pos += 7;
                            // skip whitespace..
			    while(  pos < (int)str.length() && str[pos] <= ' ' ) pos++;
                            if ( pos == ( int )str.length()) break;
                            if ( str[pos++] != '=' ) continue;
                            while ( pos < ( int )str.length() &&
                                    ( str[pos] <= ' ' ) || str[pos] == '=' || str[pos] == '"' || str[pos] == '\'')
				pos++;

                            // end ?
                            if ( pos == ( int )str.length() ) break;
			    uint endpos = pos;
			    while( endpos < str.length() &&
                                   (str[endpos] != ' ' && str[endpos] != '"' && str[endpos] != '\''
                                    && str[endpos] != ';' && str[endpos] != '>') )
				endpos++;
			    enc = str.mid(pos, endpos-pos);
#ifdef DECODE_DEBUG
			    kdDebug( 6005 ) << "Decoder: found charset: " << enc.data() << endl;
#endif
			    setEncoding(enc, EncodingFromMetaTag);
			    if( m_type == EncodingFromMetaTag ) goto found;

                            if ( endpos >= str.length() || str[endpos] == '/' || str[endpos] == '>' ) break;

			    pos = endpos + 1;
			}
		    }
                    case ID_SCRIPT:
                    case (ID_SCRIPT+ID_CLOSE_TAG):
                    case ID_NOSCRIPT:
                    case (ID_NOSCRIPT+ID_CLOSE_TAG):
                    case ID_STYLE:
                    case (ID_STYLE+ID_CLOSE_TAG):
                    case ID_LINK:
                    case (ID_LINK+ID_CLOSE_TAG):
                    case ID_OBJECT:
                    case (ID_OBJECT+ID_CLOSE_TAG):
                    case ID_TITLE:
                    case (ID_TITLE+ID_CLOSE_TAG):
                    case ID_BASE:
                    case (ID_BASE+ID_CLOSE_TAG):
                    case ID_HTML:
                    case ID_HEAD:
                    case 0:
                    case (0 + ID_CLOSE_TAG ):
                        break;
                    case ID_BODY:
                    case (ID_HEAD+ID_CLOSE_TAG):
                        body = true;
#ifdef DECODE_DEBUG
			kdDebug( 6005 ) << "Decoder: no charset found. Id=" << id << endl;
#endif
                        goto found;
                    default:
                        // Invalid tag in head. Let's be a little tolerant
                        invalid++;
                        if (invalid > 2)  {
                            body = true;
#ifdef DECODE_DEBUG
                            kdDebug( 6005 ) << "Decoder: no charset found. Id=" << id << endl;
#endif
                            goto found;
                        }
                    }
                }
                else
                    ptr++;
            }
            if (invalid > 0) {
                body = true;
                goto found;
            }
            return TQString::null;
        }
    }

 found:
    if (m_type == DefaultEncoding)
    {
#ifdef DECODE_DEBUG
	kdDebug( 6005 ) << "Decoder: use auto-detect (" << strlen(data) << ")" << endl;
#endif

        switch ( m_autoDetectLanguage) {
        case Decoder::Arabic:
            enc = automaticDetectionForArabic( (const unsigned char*) data, len );
            break;
        case Decoder::Baltic:
            enc = automaticDetectionForBaltic( (const unsigned char*) data, len );
            break;
        case Decoder::CentralEuropean:
            enc = automaticDetectionForCentralEuropean( (const unsigned char*) data, len );
            break;
        case Decoder::Russian:
        case Decoder::Ukrainian:
            enc = automaticDetectionForCyrillic( (const unsigned char*) data, len, m_autoDetectLanguage );
            break;
        case Decoder::Greek:
            enc = automaticDetectionForGreek( (const unsigned char*) data, len );
            break;
        case Decoder::Hebrew:
            enc = automaticDetectionForHebrew( (const unsigned char*) data, len );
            break;
        case Decoder::Japanese:
            enc = automaticDetectionForJapanese( (const unsigned char*) data, len );
            break;
        case Decoder::Turkish:
            enc = automaticDetectionForTurkish( (const unsigned char*) data, len );
            break;
        case Decoder::WesternEuropean:
            enc = automaticDetectionForWesternEuropean( (const unsigned char*) data, len );
            break;
        case Decoder::SemiautomaticDetection:
        case Decoder::Chinese:
        case Decoder::Korean:
        case Decoder::Thai:
        case Decoder::Unicode:
            // huh. somethings broken in this code ### FIXME
            enc = 0; //Reset invalid codec we tried, so we get back to latin1 fallback.
            break;
        }

#ifdef DECODE_DEBUG
        kdDebug( 6005 ) << "Decoder: auto detect encoding is " << enc.data() << endl;
#endif
        if ( !enc.isEmpty() )
            setEncoding( enc.data(), AutoDetectedEncoding);
    }


    // if we still haven't found an encoding latin1 will be used...
    // this is according to HTML4.0 specs
    if (!m_codec)
    {
        if(enc.isEmpty()) enc = "iso8859-1";
        m_codec = TQTextCodec::codecForName(enc);
        // be sure not to crash
        if(!m_codec) {
            m_codec = TQTextCodec::codecForMib(4);
            enc = "iso8859-1";
        }
        delete m_decoder;
        m_decoder = m_codec->makeDecoder();
    }
    TQString out;

    if(!buffer.isEmpty() && enc != "ISO-10646-UCS-2") {
        out = m_decoder->toUnicode(buffer, buffer.length());
        buffer = "";
    } else {
        if(m_codec->mibEnum() != 1000) // utf16
        {
            // ### hack for a bug in TQTextCodec. It cut's the input stream
            // in case there are \0 in it. ZDNET has them inside... :-(
            char *d = const_cast<char *>(data);
            int i = len - 1;
            while(i >= 0) {
                if(*(d+i) == 0) *(d+i) = ' ';
                i--;
            }
        }
        out = m_decoder->toUnicode(data, len);
    }

    return out;
}

TQString Decoder::flush() const
{
    return m_decoder->toUnicode(buffer, buffer.length());
}

TQCString Decoder::automaticDetectionForArabic( const unsigned char* ptr, int size )
{
    for ( int i = 0; i < size; ++i ) {
        if ( ( ptr[ i ] >= 0x80 && ptr[ i ] <= 0x9F ) || ptr[ i ] == 0xA1 || ptr[ i ] == 0xA2 || ptr[ i ] == 0xA3
             || ( ptr[ i ] >= 0xA5 && ptr[ i ] <= 0xAB ) || ( ptr[ i ] >= 0xAE && ptr[ i ] <= 0xBA )
             || ptr[ i ] == 0xBC || ptr[ i ] == 0xBD || ptr[ i ] == 0xBE || ptr[ i ] == 0xC0
             || ( ptr[ i ] >= 0xDB && ptr[ i ] <= 0xDF ) || ( ptr[ i ] >= 0xF3 ) ) {
            return "cp1256";
        }
    }

    return "iso-8859-6";
}

TQCString Decoder::automaticDetectionForBaltic( const unsigned char* ptr, int size )
{
    for ( int i = 0; i < size; ++i ) {
        if ( ( ptr[ i ] >= 0x80 && ptr[ i ] <= 0x9E ) )
             return "cp1257";

        if ( ptr[ i ] == 0xA1 || ptr[ i ] == 0xA5 )
            return "iso-8859-13";
    }

    return "iso-8859-13";
}

TQCString Decoder::automaticDetectionForCentralEuropean(const unsigned char* ptr, int size )
{
    TQCString charset = TQCString();
    for ( int i = 0; i < size; ++i ) {
        if ( ptr[ i ] >= 0x80 && ptr[ i ] <= 0x9F ) {
            if ( ptr[ i ] == 0x81 || ptr[ i ] == 0x83 || ptr[ i ] == 0x90 || ptr[ i ] == 0x98 )
                return "ibm852";

            if ( i + 1 > size )
                return "cp1250";
            else { // maybe ibm852 ?
                charset = "cp1250";
                continue;
            }
        }
        if ( ptr[ i ] == 0xA5 || ptr[ i ] == 0xAE || ptr[ i ] == 0xBE || ptr[ i ] == 0xC3 || ptr[ i ] == 0xD0 || ptr[ i ] == 0xE3 || ptr[ i ] == 0xF0 ) {
            if ( i + 1 > size )
                return "iso-8859-2";
            else {  // maybe ibm852 ?
                if ( charset.isNull() )
                    charset = "iso-8859-2";
                continue;
            }
        }
    }

    if ( charset.isNull() )
        charset = "iso-8859-3";

    return charset.data();
}

TQCString Decoder::automaticDetectionForCyrillic( const unsigned char* ptr, int size, AutoDetectLanguage _language )
{
    int koi_st=0;
    int cp1251_st=0;

//     int koi_na=0;
//     int cp1251_na=0;

    int koi_o_capital=0;
    int koi_o=0;
    int cp1251_o_capital=0;
    int cp1251_o=0;

    int koi_a_capital=0;
    int koi_a=0;
    int cp1251_a_capital=0;
    int cp1251_a=0;

    int koi_i_capital=0;
    int koi_i=0;
    int cp1251_i_capital=0;
    int cp1251_i=0;

    int cp1251_small_range=0;
    int koi_small_range=0;
    int ibm866_small_range=0;

    int i;
    for (i=1; (i<size) && (cp1251_small_range+koi_small_range<1000) ;++i)
    {
        if (ptr[i]>0xdf)
        {
            ++cp1251_small_range;

            if (ptr[i]==0xee)//small o
                ++cp1251_o;
            else if (ptr[i]==0xe0)//small a
                ++cp1251_a;
            else if (ptr[i]==0xe8)//small i
                ++cp1251_i;
            else if (ptr[i]==0xf2 && ptr[i-1]==0xf1)//small st
                ++cp1251_st;

            else if (ptr[i]==0xef)
                ++koi_o_capital;
            else if (ptr[i]==0xe1)
                ++koi_a_capital;
            else if (ptr[i]==0xe9)
                ++koi_i_capital;

        }
        else if (ptr[i]>0xbf)
        {
            ++koi_small_range;

            if (ptr[i]==0xcf)//small o
                ++koi_o;
            else if (ptr[i]==0xc1)//small a
                ++koi_a;
            else if (ptr[i]==0xc9)//small i
                ++koi_i;
            else if (ptr[i]==0xd4 && ptr[i-1]==0xd3)//small st
                ++koi_st;

            else if (ptr[i]==0xce)
                ++cp1251_o_capital;
            else if (ptr[i]==0xc0)
                ++cp1251_a_capital;
            else if (ptr[i]==0xc8)
                ++cp1251_i_capital;
        }
        else if (ptr[i]>0x9f && ptr[i]<0xaf) //first 16 letterz is 60%
            ++ibm866_small_range;

    }

    if (ibm866_small_range>cp1251_small_range+koi_small_range)
        return "ibm866"; //hehe this is a rare case :)

    TQCString koi_string = "koi8-u";
    TQCString cp1251_string = "cp1251";

    if (cp1251_st==0 && koi_st>1)
        return koi_string;
    if (koi_st==0 && cp1251_st>1)
        return cp1251_string;

    if (cp1251_st>0 && koi_st>0)
    {
        if (cp1251_st/koi_st>2)
            return cp1251_string;
        else if (koi_st/cp1251_st>2)
            return koi_string;
    }

    if (cp1251_a>koi_a && cp1251_o>koi_o && cp1251_i>koi_i)
        return cp1251_string;
    if (koi_a>cp1251_a && koi_o>cp1251_o && koi_i>cp1251_i)
        return koi_string;

    if (cp1251_a_capital>koi_a_capital && cp1251_o_capital>koi_o_capital && cp1251_i_capital>koi_i_capital)
        return cp1251_string;
    if (koi_a_capital>cp1251_a_capital && koi_o_capital>cp1251_o_capital && koi_i_capital>cp1251_i_capital)
        return koi_string;

    //fallback...
    if (cp1251_small_range>koi_small_range)
        return cp1251_string;
    else
        return koi_string;

}

TQCString Decoder::automaticDetectionForGreek( const unsigned char* ptr, int size )
{
    for ( int i = 0; i < size; ++i ) {
        if ( ptr[ i ] == 0x80 || ( ptr[ i ] >= 0x82 && ptr[ i ] <= 0x87 ) || ptr[ i ] == 0x89 || ptr[ i ] == 0x8B
             || ( ptr[ i ] >= 0x91 && ptr[ i ] <= 0x97 ) || ptr[ i ] == 0x99 || ptr[ i ] == 0x9B || ptr[ i ] == 0xA4
             || ptr[ i ] == 0xA5 || ptr[ i ] == 0xAE ) {
            return "cp1253";
        }
    }

    return "iso-8859-7";
}

TQCString Decoder::automaticDetectionForHebrew( const unsigned char* ptr, int size )
{
    for ( int i = 0; i < size; ++i ) {
        if ( ptr[ i ] == 0x80 || ( ptr[ i ] >= 0x82 && ptr[ i ] <= 0x89 ) || ptr[ i ] == 0x8B
             || ( ptr[ i ] >= 0x91 && ptr[ i ] <= 0x99 ) || ptr[ i ] == 0x9B || ptr[ i ] == 0xA1 || ( ptr[ i ] >= 0xBF && ptr[ i ] <= 0xC9 )
             || ( ptr[ i ] >= 0xCB && ptr[ i ] <= 0xD8 ) ) {
            return "cp1255";
        }

        if ( ptr[ i ] == 0xDF )
            return "iso-8859-8-i";
    }

    return "iso-8859-8-i";
}

TQCString Decoder::automaticDetectionForJapanese( const unsigned char* ptr, int size )
{
    if (!kc)
        kc = new JapaneseCode();

    switch ( kc->guess_jp( (const char*)ptr, size ) ) {
    case JapaneseCode::JIS:
        return "jis7";
    case JapaneseCode::EUC:
        return "eucjp";
    case JapaneseCode::SJIS:
        return "sjis";
     case JapaneseCode::UTF8:
        return "utf8";
    default:
        break;
    }

    return "";
}

TQCString Decoder::automaticDetectionForTurkish( const unsigned char* ptr, int size )
{
    for ( int i = 0; i < size; ++i ) {
        if ( ptr[ i ] == 0x80 || ( ptr[ i ] >= 0x82 && ptr[ i ] <= 0x8C ) || ( ptr[ i ] >= 0x91 && ptr[ i ] <= 0x9C ) || ptr[ i ] == 0x9F ) {
            return "cp1254";
        }
    }

    return "iso-8859-9";
}

TQCString Decoder::automaticDetectionForWesternEuropean( const unsigned char* ptr, int size )
{
    for ( int i = 0; i < size; ++i ) {
        if ( ptr[ i ] >= 0x80 && ptr[ i ] <= 0x9F )
            return "cp1252";
    }

    return "iso-8859-1"; //"iso-8859-15"; Which better at default ?
}


// -----------------------------------------------------------------------------
#undef DECODE_DEBUG