forked from goldendict/goldendict
-
Notifications
You must be signed in to change notification settings - Fork 0
/
bgl_babylon.cc
834 lines (723 loc) · 23.8 KB
/
bgl_babylon.cc
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
/***************************************************************************
* Copyright (C) 2007 by Raul Fernandes and Karl Grill *
* *
* This program is free software; you can redistribute it and/or modify *
* it under the terms of the GNU General Public License as published by *
* the Free Software Foundation; either version 2 of the License, or *
* (at your option) any later version. *
* *
* This program 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 General Public License for more details. *
* *
* You should have received a copy of the GNU General Public License *
* along with this program; if not, write to the *
* Free Software Foundation, Inc., *
* 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. *
***************************************************************************/
/* Various improvements were made by Konstantin Isakov for the GoldenDict
* program. */
#include "bgl_babylon.hh"
#include <algorithm>
#include <stdlib.h>
#include <string.h>
#include <stdio.h>
#include <iconv.h>
#include <QTextDocument>
#include "gddebug.hh"
#include "ufile.hh"
#include "iconv.hh"
#include "htmlescape.hh"
#include <QString>
#include <QDebug>
#include "dictionary.hh"
#ifdef _WIN32
#include <io.h>
#define DUP _dup
#else
#define DUP dup
#endif
using std::string;
DEF_EX_STR( exCantReadFile, "Can't read file", Dictionary::Ex )
DEF_EX( exUserAbort, "User abort", Dictionary::Ex )
DEF_EX( exIconv, "Iconv library error", Dictionary::Ex )
DEF_EX( exAllocation, "Error memory allocation", Dictionary::Ex )
Babylon::Babylon( std::string filename ) :
m_filename( filename )
{
file = NULL;
}
Babylon::~Babylon()
{
close();
}
bool Babylon::open()
{
FILE *f;
unsigned char buf[6];
int i;
f = gd_fopen( m_filename.c_str(), "rb" );
if( f == NULL )
return false;
i = fread( buf, 1, 6, f );
/* First four bytes: BGL signature 0x12340001 or 0x12340002 (big-endian) */
if( i < 6 || memcmp( buf, "\x12\x34\x00", 3 ) || buf[3] == 0 || buf[3] > 2 )
{
fclose( f );
return false;
}
/* Calculate position of gz header */
i = buf[4] << 8 | buf[5];
if( i < 6 )
{
fclose( f );
return false;
}
if( fseek( f, i, SEEK_SET ) ) /* can't seek - emulate */
for(int j=0;j < i - 6;j++) fgetc( f );
if( ferror( f ) || feof( f ) )
{
fclose( f );
return false;
}
/* we need to flush the file because otherwise some nfs mounts don't seem
* to properly update the file position for the following reopen */
fflush( f );
#ifdef Q_OS_MAC
/* Under Mac OS X the above technique don't set reopen position properly */
int fn = DUP( fileno( f ) );
lseek( fn, i, SEEK_SET );
file = gzdopen( fn, "r" );
#else
file = gzdopen( DUP( fileno( f ) ), "r" );
#endif
fclose( f );
if( file == NULL )
return false;
return true;
}
void Babylon::close()
{
if ( file )
{
gzclose( file );
file = 0;
}
}
bool Babylon::readBlock( bgl_block &block )
{
if( gzeof( file ) || file == NULL )
return false;
block.length = bgl_readnum( 1 );
block.type = block.length & 0xf;
if( block.type == 4 ) return false; // end of file marker
block.length >>= 4;
block.length = block.length < 4 ? bgl_readnum( block.length + 1 ) : block.length - 4 ;
if( block.length )
{
block.data = (char *)malloc( block.length );
if( !block.data )
throw exAllocation();
unsigned res = gzread( file, block.data, block.length );
if( block.length != res )
{
free( block.data );
block.length = 0;
gzclearerr( file );
return false;
}
}
return true;
}
unsigned int Babylon::bgl_readnum( int bytes )
{
unsigned char buf[4];
unsigned val = 0;
if ( bytes < 1 || bytes > 4 ) return (0);
int res = gzread( file, buf, bytes );
if( res != bytes )
{
gzclearerr( file );
return 4; // Read error - return end of file marker
}
for(int i=0;i<bytes;i++) val= (val << 8) | buf[i];
return val;
}
bool Babylon::read(std::string &source_charset, std::string &target_charset)
{
if( file == NULL ) return false;
bgl_block block;
unsigned int pos;
unsigned int type;
std::string headword;
std::string definition;
bool isUtf8File = false;
m_sourceCharset = source_charset;
m_targetCharset = target_charset;
m_numEntries = 0;
while( readBlock( block ) )
{
headword.clear();
definition.clear();
switch( block.type )
{
case 0:
switch( block.data[0] )
{
case 8:
type = (unsigned int)block.data[2];
if( type == 67 ) type = 1;
if( type > 64 ) type -= 65;
if ( type >= 14 )
type = 0;
m_defaultCharset = bgl_charset[type];
break;
default:
break;
}
break;
case 1:
case 7:
case 10:
case 11:
// Only count entries
m_numEntries++;
break;
case 3:
pos = 2;
switch( block.data[1] )
{
case 1:
headword.reserve( block.length - 2 );
for(unsigned int a=0;a<block.length-2;a++) headword += block.data[pos++];
m_title = headword;
break;
case 2:
headword.reserve( block.length - 2 );
for(unsigned int a=0;a<block.length-2;a++) headword += block.data[pos++];
m_author = headword;
break;
case 3:
headword.reserve( block.length - 2 );
for(unsigned int a=0;a<block.length-2;a++) headword += block.data[pos++];
m_email = headword;
break;
case 4:
headword.reserve( block.length - 2 );
for(unsigned int a=0;a<block.length-2;a++) headword += block.data[pos++];
m_copyright = headword;
break;
case 7:
m_sourceLang = bgl_language[(unsigned char)(block.data[5])];
//m_sourceLang = headword;
break;
case 8:
m_targetLang = bgl_language[(unsigned char)(block.data[5])];
//m_targetLang = headword;
break;
case 9:
headword.reserve( block.length - 2 );
for(unsigned int a=0;a<block.length-2;a++) {
if (block.data[pos] == '\r') {
} else if (block.data[pos] == '\n') {
headword += "<br>";
} else {
headword += block.data[pos];
}
pos++;
}
m_description = headword;
break;
case 11:
icon.resize( block.length - 2 );
memcpy( &icon.front(), &(block.data[ 2 ]), icon.size() );
break;
case 17:
if ( block.length >= 5 && ( (unsigned char) block.data[ 4 ] & 0x80 ) != 0 )
isUtf8File = true;
break;
case 26:
type = (unsigned int)block.data[2];
if( type == 67 ) type = 1;
if( type > 64 ) type -= 65;
if ( type >= 14 )
type = 0;
if (m_sourceCharset.empty())
m_sourceCharset = bgl_charset[type];
break;
case 27:
type = (unsigned int)block.data[2];
if( type == 67 ) type = 1;
if( type > 64 ) type -= 65;
if ( type >= 14 )
type = 0;
if (m_targetCharset.empty())
m_targetCharset = bgl_charset[type];
break;
default:
break;
}
break;
default:
;
}
if( block.length ) free( block.data );
}
gzseek( file, 0, SEEK_SET );
if ( isUtf8File )
{
//FDPRINTF( stderr, "%s: utf8 file.\n", m_title.c_str() );
m_defaultCharset = "UTF-8";
m_sourceCharset = "UTF-8";
m_targetCharset = "UTF-8";
}
convertToUtf8( m_title, TARGET_CHARSET );
convertToUtf8( m_author, TARGET_CHARSET );
convertToUtf8( m_email, TARGET_CHARSET );
convertToUtf8( m_copyright, TARGET_CHARSET );
convertToUtf8( m_description, TARGET_CHARSET );
GD_DPRINTF("Default charset: %s\nSource Charset: %s\nTargetCharset: %s\n", m_defaultCharset.c_str(), m_sourceCharset.c_str(), m_targetCharset.c_str());
return true;
}
bgl_entry Babylon::readEntry( ResourceHandler * resourceHandler )
{
bgl_entry entry;
if( file == NULL )
{
entry.headword = "";
return entry;
}
bgl_block block;
unsigned int len, pos;
unsigned int alts_num;
std::string headword, displayedHeadword;
std::string definition;
std::string temp;
std::vector<std::string> alternates;
std::string alternate;
std::string root;
bool defBodyEnded = false;
std::string transcription;
while( readBlock( block ) )
{
switch( block.type )
{
case 2:
{
pos = 0;
len = (unsigned char)block.data[pos++];
if( pos + len > block.length )
break;
std::string filename( block.data+pos, len );
//if (filename != "8EAF66FD.bmp" && filename != "C2EEF3F6.html") {
pos += len;
if ( resourceHandler )
resourceHandler->handleBabylonResource( filename,
block.data + pos,
block.length - pos );
#if 0
FILE *ifile = gd_fopen(filename.c_str(), "w");
fwrite(block.data + pos, 1, block.length -pos, ifile);
fclose(ifile);
#endif
break;
}
case 1:
case 7:
case 10:
case 11:
alternate.clear();
headword.clear();
displayedHeadword.clear();
root.clear();
definition.clear();
temp.clear();
pos = 0;
// Headword
if( block.type == 11 )
{
pos = 1;
len = 0;
if( pos + 4 > block.length )
break;
for( int i = 0; i < 4; i++ )
{
len = len << 8;
len |= (unsigned char)block.data[ pos++ ];
}
}
else
{
len = (unsigned char)block.data[pos++];
}
if( pos + len > block.length )
break;
headword.reserve( len );
for(unsigned int a=0;a<len;a++)
headword += block.data[pos++];
convertToUtf8( headword, SOURCE_CHARSET );
// Try to repair malformed headwords
if( headword.find( "&#" ) != string::npos )
headword = Html::unescapeUtf8( headword );
if( block.type == 11 )
{
// Alternate forms
if( pos + 4 >= block.length )
break;
alts_num = 0;
for( int i = 0; i < 4; i++ )
{
alts_num = alts_num << 8;
alts_num |= (unsigned char)block.data[ pos++ ];
}
for( unsigned j = 0; j < alts_num; j++ )
{
len = 0;
if( pos + 4 > block.length )
break;
for( int i = 0; i < 4; i++ )
{
len = len << 8;
len |= (unsigned char)block.data[ pos++ ];
}
if( pos + len >= block.length )
break;
alternate.reserve( len );
for(unsigned int a=0;a<len;a++) alternate += block.data[pos++];
convertToUtf8( alternate, SOURCE_CHARSET );
// Try to repair malformed forms
if( alternate.find( "&#" ) != string::npos )
alternate = Html::unescapeUtf8( alternate );
alternates.push_back( alternate );
alternate.clear();
}
}
// Definition
if( block.type == 11 )
{
len = 0;
if( pos + 4 > block.length )
break;
for( int i = 0; i < 4; i++ )
{
len = len << 8;
len |= (unsigned char)block.data[ pos++ ];
}
}
else
{
len = (unsigned char)block.data[pos++] << 8;
len |= (unsigned char)block.data[pos++];
}
if( pos + len > block.length )
break;
definition.reserve( len );
for(unsigned int a=0;a<len;a++)
{
if( (unsigned char)block.data[pos] == 0x0a )
{
definition += "<br>";
pos++;
}
else if ( (unsigned char)block.data[pos] == 6 )
{
// Something
pos += 2;
++a;
definition += " ";
}
else if ( (unsigned char)block.data[pos] >= 0x40 &&
len - a >= 2 &&
(unsigned char)block.data[pos + 1 ] == 0x18 )
{
// Hidden displayed headword (a displayed headword which
// contains some garbage and shouldn't probably be visible).
unsigned length = (unsigned char)block.data[ pos ] - 0x3F;
if ( length > len - a - 2 )
{
GD_FDPRINTF( stderr, "Hidden displayed headword is too large %s\n", headword.c_str() );
pos += len - a;
break;
}
pos += length + 2;
a += length + 1;
}
else if ( (unsigned char)block.data[pos] == 0x18 )
{
// Displayed headword
unsigned length = (unsigned char)block.data[ pos + 1 ];
if ( length > len - a - 2 )
{
GD_FDPRINTF( stderr, "Displayed headword's length is too large for headword %s\n", headword.c_str() );
pos += len - a;
break;
}
displayedHeadword = std::string( block.data + pos + 2, length );
pos += length + 2;
a += length + 1;
}
else
if ( block.data[ pos ] == 0x28 && defBodyEnded &&
len - a >= 3 )
{
// 2-byte sized displayed headword
unsigned length = (unsigned char)block.data[ pos + 1 ];
length <<= 8;
length += (unsigned char)block.data[ pos + 2 ];
if ( length > len - a - 3 )
{
GD_FDPRINTF( stderr, "2-byte sized displayed headword for %s is too large\n", headword.c_str() );
pos += len - a;
break;
}
displayedHeadword = std::string( block.data + pos + 3, length );
pos += length + 3;
a += length + 2;
}
else if ( (unsigned char)block.data[pos] == 0x50 && len - a - 1 >= 2 &&
(unsigned char)block.data[pos + 1 ] == 0x1B )
{
// 1-byte-sized transcription
unsigned length = (unsigned char)block.data[pos + 2 ];
if ( length > len - a - 3 )
{
GD_FDPRINTF( stderr, "1-byte-sized transcription's length is too large for headword %s\n", headword.c_str() );
pos += len - a;
break;
}
if( m_targetCharset.compare( "UTF-8" ) != 0 )
{
try
{
transcription = Iconv::toUtf8( "CP1252", block.data + pos + 3, length );
}
catch( Iconv::Ex & e )
{
qWarning( "Bgl: charset convertion error, no trancription processing's done: %s\n", e.what() );
transcription = std::string( block.data + pos + 3, length );
}
}
else
transcription = std::string( block.data + pos + 3, length );
pos += length + 3;
a += length + 2;
}
else if ( (unsigned char)block.data[pos] == 0x60 && len - a - 1 >= 3 &&
(unsigned char)block.data[pos + 1 ] == 0x1B )
{
// 2-byte-sized transcription
unsigned length = (unsigned char)block.data[pos + 2 ];
length <<= 8;
length += (unsigned char)block.data[pos + 3 ];
if ( length > len - a - 4)
{
GD_FDPRINTF( stderr, "2-byte-sized transcription's length is too large for headword %s\n", headword.c_str() );
pos += len - a;
break;
}
if( m_targetCharset.compare( "UTF-8" ) != 0 )
{
try
{
transcription = Iconv::toUtf8( "CP1252", block.data + pos + 4, length );
}
catch( Iconv::Ex & e )
{
qWarning( "Bgl: charset convertion error, no trancription processing's done: %s\n", e.what() );
transcription = std::string( block.data + pos + 4, length );
}
}
else
transcription = std::string( block.data + pos + 4, length );
pos += length + 4;
a += length + 3;
}
else if ( (unsigned char)block.data[pos] >= 0x40 &&
len - a >= 2 &&
(unsigned char)block.data[pos + 1 ] == 0x1B )
{
// Hidden transcription (a transcription which is usually the same
// as the headword and shouldn't probably be visible).
unsigned length = (unsigned char)block.data[ pos ] - 0x3F;
if ( length > len - a - 2 )
{
GD_FDPRINTF( stderr, "Hidden transcription is too large %s\n", headword.c_str() );
pos += len - a;
break;
}
pos += length + 2;
a += length + 1;
}
else if ( (unsigned char)block.data[pos] == 0x1E )
{
// Resource reference begin marker
definition += m_resourcePrefix;
++pos;
}
else if ( (unsigned char)block.data[pos] == 0x1F )
{
// Resource reference end marker
++pos;
}
else if( (unsigned char)block.data[pos] < 0x20 )
{
if( a <= len - 3 && block.data[pos] == 0x14 && block.data[pos+1] == 0x02 ) {
int index = (unsigned char)block.data[pos+2] - 0x30;
if (index >= 0 && index <= 10) {
definition = "<span class=\"bglpos\">" + partOfSpeech[index] + "</span> " + definition;
}
pos += 3;
a += 2;
//pos += len - a;
//break;
}
else
if (block.data[pos] == 0x14) {
defBodyEnded = true; // Presumably
pos++;
} else if ((unsigned char)block.data[pos] == 0x1A){
unsigned length = (unsigned char)block.data[ pos + 1 ];
if (length <= 10){// 0x1A identifies two different data types.
// data about the Hebrew root should be shorter then
// 10 bytes, and in the other data type the byte
// after 0x1A is > 10 (at least it is in Bybylon's
// Hebrew dictionaries).
root = std::string( block.data + pos + 2, length );
std::reverse(root.begin(),root.end());
definition += " (" + root + ")";
pos += length + 2;
a += length + 1;
}
else
pos++;
} else {
definition += block.data[pos++];
}
}else definition += block.data[pos++];
}
convertToUtf8( definition, TARGET_CHARSET );
if( !transcription.empty() )
definition = std::string( "<span class=\"bgltrn\">" ) + transcription + "</span>" + definition;
if ( displayedHeadword.size() )
convertToUtf8( displayedHeadword, TARGET_CHARSET );
// Alternate forms
while( pos < block.length )
{
len = (unsigned char)block.data[pos++];
if( pos + len > block.length ) break;
alternate.reserve( len );
for(unsigned int a=0;a<len;a++) alternate += block.data[pos++];
convertToUtf8( alternate, SOURCE_CHARSET );
// Try to repair malformed forms
if( alternate.find( "&#" ) != string::npos )
alternate = Html::unescapeUtf8( alternate );
alternates.push_back( alternate );
alternate.clear();
}
// Try adding displayed headword to the list of alts
if ( headword != displayedHeadword )
{
// Only add displayed headword if the normal one has two or more digits.
// This would indicate some irregularity in it (like e.g. if it serves
// as some kind of an identifier instead of being an actual headword)
int totalDigits = 0;
for( char const * p = headword.c_str(); *p; ++p )
if ( *p >= '0' && *p <= '9' )
{
if ( ++totalDigits > 1 )
break;
}
if ( totalDigits > 1 )
{
// Ok, let's add it.
// Does it contain HTML? If it does, we need to strip it
if ( displayedHeadword.find( '<' ) != string::npos ||
displayedHeadword.find( '&' ) != string::npos )
{
string result = Html::unescapeUtf8( displayedHeadword );
if ( result != headword )
alternates.push_back( result );
}
else
alternates.push_back(displayedHeadword);
}
}
entry.headword = headword;
entry.displayedHeadword = displayedHeadword;
entry.definition = definition;
entry.alternates = alternates;
if( block.length ) free( block.data );
// Some dictionaries can in fact have an empty headword, so we
// make it non-empty here to differentiate between the end of entries.
if ( entry.headword.empty() )
entry.headword += ' ';
return entry;
break;
default:
;
}
if( block.length ) free( block.data );
}
entry.headword = "";
return entry;
}
void Babylon::convertToUtf8( std::string &s, unsigned int type )
{
if( s.size() < 1 ) return;
if( type > 2 ) return;
if( s.compare( 0, 13, "<charset c=U>") == 0 )
return;
std::string charset;
switch( type )
{
case DEFAULT_CHARSET:
if(!m_defaultCharset.empty()) charset = m_defaultCharset;
else charset = m_sourceCharset;
break;
case SOURCE_CHARSET:
if(!m_sourceCharset.empty()) charset = m_sourceCharset;
else charset = m_defaultCharset;
break;
case TARGET_CHARSET:
if(!m_targetCharset.empty()) charset = m_targetCharset;
else charset = m_defaultCharset;
break;
default:
;
}
if( charset == "UTF-8" )
return;
iconv_t cd = iconv_open( "UTF-8", charset.c_str() );
if( cd == (iconv_t)(-1) )
throw exIconv();
char *outbuf, *defbuf;
size_t inbufbytes, outbufbytes;
inbufbytes = s.size();
outbufbytes = s.size() * 6;
char *inbuf;
inbuf = (char *)s.data();
outbuf = (char*)malloc( outbufbytes + 1 );
if( !outbuf )
{
iconv_close( cd );
throw exAllocation();
}
memset( outbuf, '\0', outbufbytes + 1 );
defbuf = outbuf;
while (inbufbytes) {
if (iconv(cd, &inbuf, &inbufbytes, &outbuf, &outbufbytes) == (size_t)-1) {
gdWarning( "\"%s\" - error in iconv conversion\n", inbuf );
break;
// inbuf++;
// inbufbytes--;
}
}
// Flush the state. This fixes CP1255 problems.
iconv( cd, 0, 0, &outbuf, &outbufbytes );
if( inbufbytes == 0 )
s = std::string( defbuf );
free( defbuf );
iconv_close( cd );
}