81
82
{N_("Turkish (IBM-857)"), "IBM857" },
82
83
{N_("Turkish (ISO-8859-9)"), "ISO-8859-9" },
83
84
{N_("Turkish (Windows-1254)"), "windows-1254" },
84
{N_("Unicode (UTF-7)"), "UTF-7" },
85
//{N_("Unicode (UTF-7)"), "UTF-7" },
85
86
{N_("Unicode (UTF-8)"), "UTF-8" },
87
{N_("Unicode (UTF-16BE)"), "UTF-16BE" },
88
{N_("Unicode (UTF-16LE)"), "UTF-16LE" },
88
//{N_("Unicode (UTF-16BE)"), "UTF-16BE" },
89
//{N_("Unicode (UTF-16LE)"), "UTF-16LE" },
89
90
//{N_("Unicode (UTF-32BE)"), "UTF-32BE" },
90
91
//{N_("Unicode (UTF-32LE)"), "UTF-32LE" },
92
93
{N_("Vietnamese (VISCII)"), "VISCII" },
93
94
{N_("Vietnamese (Windows-1258)"), "windows-1258" },
94
95
{N_("Visual Hebrew (ISO-8859-8)"), "ISO-8859-8" },
184
186
/* "C" is plain ascii */
185
187
insert_locales (encodings, "ASCII", "C", NULL);
189
insert_locales (encodings, "windows-1256", "ar", NULL); // 2006.12.31 - For testing with Arabic
191
insert_locales (encodings, "ISO-8859-6", "ar", NULL);
187
193
insert_locales (encodings, "ARMSCII-8", "by", NULL);
188
194
insert_locales (encodings, "BIG5", "zh_TW", NULL);
189
195
insert_locales (encodings, "CP1251", "be", "bg", NULL);
196
202
insert_locales (encodings, "EUC-KR", "ko", NULL);
197
203
/*insert_locales (encodings, "GEORGIAN-ACADEMY", NULL);*/
198
204
insert_locales (encodings, "GEORGIAN-PS", "ka", NULL);
199
insert_locales (encodings, "ISO-8859-1", "br", "ca", "da", "de", "en", "es", "eu", "fi", "fr", "gl", "it", "nl", "wa", "no", "pt", "pt", "sv", NULL);
205
insert_locales (encodings, "ISO-8859-1", "br", "ca", "da", "de", "en", "es", "eu", "fi", "fr", "gl", "it", "nl", "wa", "nb", "nn", "pt", "pt", "sv", NULL);
207
insert_locales (encodings, "windows-1250", "cs", "hr", "hu", "pl", "ro", "sk", "sl", "sq", "sr", NULL);
200
209
insert_locales (encodings, "ISO-8859-2", "cs", "hr", "hu", "pl", "ro", "sk", "sl", "sq", "sr", NULL);
201
211
insert_locales (encodings, "ISO-8859-3", "eo", NULL);
202
212
insert_locales (encodings, "ISO-8859-5", "mk", "sp", NULL);
214
insert_locales (encodings, "windows-1253", "el", NULL);
203
216
insert_locales (encodings, "ISO-8859-7", "el", NULL);
219
insert_locales (encodings, "windows-1254", "tr", NULL);
204
221
insert_locales (encodings, "ISO-8859-9", "tr", NULL);
205
223
insert_locales (encodings, "ISO-8859-13", "lt", "lv", "mi", NULL);
206
224
insert_locales (encodings, "ISO-8859-14", "ga", "cy", NULL);
207
225
insert_locales (encodings, "ISO-8859-15", "et", NULL);
227
insert_locales (encodings, "windows-1251", "ru", NULL);
208
229
insert_locales (encodings, "KOI8-R", "ru", NULL);
209
231
insert_locales (encodings, "KOI8-U", "uk", NULL);
210
232
if (check_locale ("TCVN-5712")) {
211
233
insert_locales (encodings, "TCVN-5712", "vi", NULL);
259
284
* Return the locale from LANG if exists, else from LC_ALL
261
286
* http://www.opengroup.org/onlinepubs/009695399/basedefs/xbd_chap08.html#tag_08_02
264
289
* This variable shall determine the locale category for native language,
265
290
* local customs, and coded character set in the absence of the LC_ALL and
266
291
* other LC_* ( LC_COLLATE , LC_CTYPE , LC_MESSAGES , LC_MONETARY , LC_NUMERIC ,
267
* LC_TIME ) environment variables. This can be used by applications to
292
* LC_TIME ) environment variables. This can be used by applications to
268
293
* determine the language to use for error messages and instructions, collating
269
294
* sequences, date formats, and so on.
310
335
* This variable shall determine the locale category for date and time formatting
311
336
* information. It affects the behavior of the time functions in strftime().
312
337
* Additional semantics of this variable, if any, are implementation-defined.
315
340
* The values of locale categories shall be determined by a precedence order; the
316
341
* first condition met below determines the value:
318
343
* 1. If the LC_ALL environment variable is defined and is not null, the value
319
344
* of LC_ALL shall be used.
320
345
* 2. If the LC_* environment variable ( LC_COLLATE , LC_CTYPE , LC_MESSAGES ,
375
400
gchar *escaped_str = g_strescape(string, NULL);
376
401
if (display_error)
378
g_warning("convert_string(): Failed conversion from charset '%s' to '%s'. "
379
"String '%s'. Errcode %d (%s).\n",
403
Log_Print(LOG_ERROR,"convert_string(): Failed conversion from charset '%s' to '%s'. "
404
"String '%s'. Errcode %d (%s).",
380
405
from_codeset, to_codeset, escaped_str, error->code, error->message);
382
407
g_free(escaped_str);
383
408
g_error_free(error);
384
// Return the input string without converting it. If the string is
409
// Return the input string without converting it. If the string is
385
410
// displayed in the UI, it must be in UTF-8!
386
411
if ( (g_ascii_strcasecmp(to_codeset, "UTF-8"))
387
412
|| (g_utf8_validate(string, -1, NULL)) )
393
418
// Patch from Alexey Illarionov:
394
419
// g_convert returns null-terminated string only with one \0 at the
395
// end. It can cause some garbage at the end of a string for UTF-16.
420
// end. It can cause some garbage at the end of a string for UTF-16.
396
421
// The second \0 should be set manually.
397
422
output = g_realloc(output, bytes_written + 2);
398
423
if (output != NULL)
399
424
output[bytes_written] = output[bytes_written + 1] = 0;
402
427
//g_print("from %s => len: %d, string: '%s'\n (%x %x %x %x %x %x %x %x)\n",from_codeset,length,string,string[0],string[1],string[2],string[3],string[4],string[5],string[6],string[7]);
403
428
//g_print("to %s => len: %d, output: '%s'\n (%x %x %x %x %x %x %x %x)\n\n",to_codeset,bytes_written+2,output,output[0],output[1],output[2],output[3],output[4],output[5],output[6],output[7]);
424
449
const gchar *usercharset;
425
450
gchar *escaped_str = g_strescape(string, NULL);
426
451
g_get_charset(&usercharset);
427
g_warning("convert_to_utf8(): Failed conversion from charset '%s'. "
428
"String '%s'. Errcode %d (%s).\n",
452
Log_Print(LOG_ERROR,"convert_to_utf8(): Failed conversion from charset '%s'. "
453
"String '%s'. Errcode %d (%s).",
429
454
usercharset, escaped_str, error->code, error->message);
430
455
g_free(escaped_str);
432
457
if (g_utf8_validate(string, -1, NULL))
433
g_warning("convert_to_utf8(): String was valid UTF-8.\n");
458
Log_Print(LOG_ERROR,"convert_to_utf8(): String was valid UTF-8.");
435
g_warning("convert_to_utf8(): String was INVALID UTF-8.\n");
460
Log_Print(LOG_ERROR,"convert_to_utf8(): String was INVALID UTF-8.");
437
462
g_error_free(error);
438
463
return g_strdup(string);
456
481
const gchar *usercharset;
457
482
gchar *escaped_str = g_strescape(string, NULL);
458
483
g_get_charset(&usercharset);
459
g_warning("convert_from_utf8(): Failed conversion to charset '%s'. "
460
"String '%s'. Errcode %d (%s).\n",
484
Log_Print(LOG_ERROR,"convert_from_utf8(): Failed conversion to charset '%s'. "
485
"String '%s'. Errcode %d (%s).",
461
486
usercharset, escaped_str, error->code, error->message);
462
487
g_free(escaped_str);
464
489
if (g_utf8_validate(string, -1, NULL))
465
g_warning("convert_from_utf8(): String was valid UTF-8.\n");
490
Log_Print(LOG_ERROR,"convert_from_utf8(): String was valid UTF-8.");
467
g_warning("convert_from_utf8(): String was INVALID UTF-8.\n");
492
Log_Print(LOG_ERROR,"convert_from_utf8(): String was INVALID UTF-8.");
469
494
g_error_free(error);
470
495
return g_strdup(string);
544
569
//const gchar *filename_encoding = NULL;
546
571
if (!string) return NULL;
548
573
// Get system encoding from LANG if found (ex : fr_FR.UTF-8 => UTF-8)
549
574
if (get_locale())
550
575
char_encoding = strchr(get_locale(), '.');
552
577
if (char_encoding)
553
578
char_encoding = char_encoding+1; // Skip the '.'
554
579
if (char_encoding)
558
583
if (FILENAME_CHARACTER_SET_OTHER)
560
585
ret = g_convert(string, -1, char_encoding, "UTF-8", NULL, NULL, &error);
562
587
}else if (FILENAME_CHARACTER_SET_APPROXIMATE)
564
589
// iconv_open (3):
659
* Function used when reading tags : we check if the string is valid UTF-8 (else
660
* it may cause problem in EasyTAG)
663
* - some Ogg Vorbis tags contain ISO-8859-1 characters instead of UTF-8).
664
* - some Flac tags may be probably encoded to ISO-8859-15 (by using for example
665
* "metaflac --no-utf8-convert ...") so we convert it from ISO-8859-1 to UTF-8.
667
* If not valid UTF-8, we try some conversion to try to get the correct string
668
* - conversion OK : returns the UTF-8 string (new allocated)
669
* - conversion KO : tries others encodings else returns an 'escaped' string
671
gchar *Try_To_Validate_Utf8_String (const gchar *string)
674
GError *error = NULL;
679
if (g_utf8_validate(string, -1, NULL))
681
// String already in UTF-8
682
ret = g_strdup(string);
685
const gchar *char_encoding;
687
// Get encoding associated to the locale without using UTF-8 (ex , if LANG=fr_FR.UTF-8 it will return ISO-8859-1)
688
char_encoding = get_encoding_from_locale(get_locale());
691
//g_print("> char_encoding: %s\n",char_encoding);
693
ret = g_convert(string, -1, "UTF-8", char_encoding, NULL, NULL, &error);
698
// Failing that, try ISO-8859-1
700
ret = g_convert(string, -1, "UTF-8", "ISO-8859-1", NULL, NULL, &error);
705
gchar *escaped_str = g_strescape(string, NULL);
706
Log_Print(LOG_ERROR,_("The string '%s' couldn't be converted into UTF-8 (%s)."),
707
escaped_str, error && error->message ? error->message : _("Invalid UTF-8"));
708
g_clear_error(&error);
632
719
void Charset_Populate_Combobox (GtkComboBox *combo, gchar *select_charset)
698
785
temp = convert_string("FOO", from, to, FALSE);
703
790
/*// Error in conversion
704
791
if (error && error->code == G_CONVERT_ERROR_NO_CONVERSION)
706
g_print("Conversion error from '%s' to '%s' (G_CONVERT_ERROR_NO_CONVERSION)\n",from,to);
793
Log_Print(LOG_ERROR,"Conversion error from '%s' to '%s' (G_CONVERT_ERROR_NO_CONVERSION)",from,to);
707
794
} else if (error && error->code == G_CONVERT_ERROR_ILLEGAL_SEQUENCE)
709
g_print("Conversion error from '%s' to '%s' (G_CONVERT_ERROR_ILLEGAL_SEQUENCE)\n",from,to);
796
Log_Print(LOG_ERROR,"Conversion error from '%s' to '%s' (G_CONVERT_ERROR_ILLEGAL_SEQUENCE)",from,to);
710
797
} else if (error && error->code == G_CONVERT_ERROR_FAILED)
712
g_print("Conversion error from '%s' to '%s' (G_CONVERT_ERROR_FAILED)\n",from,to);
799
Log_Print(LOG_ERROR,"Conversion error from '%s' to '%s' (G_CONVERT_ERROR_FAILED)",from,to);
713
800
} else if (error && error->code == G_CONVERT_ERROR_PARTIAL_INPUT)
715
g_print("Conversion error from '%s' to '%s' (G_CONVERT_ERROR_PARTIAL_INPUT)\n",from,to);
802
Log_Print(LOG_ERROR,"Conversion error from '%s' to '%s' (G_CONVERT_ERROR_PARTIAL_INPUT)",from,to);
716
803
} else if (error && error->code == G_CONVERT_ERROR_BAD_URI)
718
g_print("Conversion error from '%s' to '%s' (G_CONVERT_ERROR_BAD_URI)\n",from,to);
805
Log_Print(LOG_ERROR,"Conversion error from '%s' to '%s' (G_CONVERT_ERROR_BAD_URI)",from,to);
719
806
} else if (error && error->code == G_CONVERT_ERROR_NOT_ABSOLUTE_PATH)
721
g_print("Conversion error from '%s' to '%s' (G_CONVERT_ERROR_NOT_ABSOLUTE_PATH)\n",from,to);
808
Log_Print(LOG_ERROR,"Conversion error from '%s' to '%s' (G_CONVERT_ERROR_NOT_ABSOLUTE_PATH)",from,to);
724
g_print("Conversion error from '%s' to '%s' (unknown : %d)\n",from,to,error->code);
811
Log_Print(LOG_ERROR,"Conversion error from '%s' to '%s' (unknown : %d)",from,to,error->code);
728
815
g_error_free(error);*/
added
removed
src/charset.c
