6
* Copyright (c) 1999-2004 The SquirrelMail Project Team
7
* Licensed under the GNU GPL. For full terms see the file COPYING.
9
* This file contains variuos functions that are needed to do
10
* internationalization of SquirrelMail.
12
* Internally the output character set is used. Other characters are
13
* encoded using Unicode entities according to HTML 4.0.
15
* $Id: i18n.php,v 1.167 2004/01/29 19:38:47 tokul Exp $
16
* @package squirrelmail
19
/** Everything uses global.php... */
20
require_once(SM_PATH . 'functions/global.php');
23
* Converts string from given charset to charset, that can be displayed by user translation.
25
* Function by default returns html encoded strings, if translation uses different encoding.
26
* If Japanese translation is used - function returns string converted to euc-jp
27
* If iconv or recode functions are enabled and translation uses utf-8 - function returns utf-8 encoded string.
28
* If $charset is not supported - function returns unconverted string.
30
* sanitizing of html tags is also done by this function.
32
* @param string $charset
33
* @param string $string Text to be decoded
34
* @return string decoded string
36
function charset_decode ($charset, $string) {
37
global $languages, $squirrelmail_language, $default_charset;
38
global $use_php_recode, $use_php_iconv, $agresive_decoding;
40
if (isset($languages[$squirrelmail_language]['XTRA_CODE']) &&
41
function_exists($languages[$squirrelmail_language]['XTRA_CODE'])) {
42
$string = $languages[$squirrelmail_language]['XTRA_CODE']('decode', $string);
45
$charset = strtolower($charset);
49
// Variables that allow to use functions without function_exist() calls
50
if (! isset($use_php_recode) || $use_php_recode=="" ) {
51
$use_php_recode=false; }
52
if (! isset($use_php_iconv) || $use_php_iconv=="" ) {
53
$use_php_iconv=false; }
55
// Don't do conversion if charset is the same.
56
if ( $charset == strtolower($default_charset) )
57
return htmlspecialchars($string);
59
// catch iso-8859-8-i thing
60
if ( $charset == "iso-8859-8-i" )
61
$charset = "iso-8859-8";
64
* Recode converts html special characters automatically if you use
65
* 'charset..html' decoding. There is no documented way to put -d option
66
* into php recode function call.
68
if ( $use_php_recode ) {
69
if ( $default_charset == "utf-8" ) {
70
// other charsets can be converted to utf-8 without loss.
71
// and output string is smaller
72
$string = recode_string($charset . "..utf-8",$string);
73
return htmlspecialchars($string);
75
$string = recode_string($charset . "..html",$string);
76
// recode does not convert single quote, htmlspecialchars does.
77
$string = str_replace("'", ''', $string);
82
// iconv functions does not have html target and can be used only with utf-8
83
if ( $use_php_iconv && $default_charset=='utf-8') {
84
$string = iconv($charset,$default_charset,$string);
85
return htmlspecialchars($string);
88
// If we don't use recode and iconv, we'll do it old way.
90
/* All HTML special characters are 7 bit and can be replaced first */
92
$string = htmlspecialchars ($string);
94
/* controls cpu and memory intensive decoding cycles */
95
if (! isset($agresive_decoding) || $agresive_decoding=="" ) {
96
$agresive_decoding=false; }
98
$decode=fixcharset($charset);
99
$decodefile=SM_PATH . 'functions/decode/' . $decode . '.php';
100
if (file_exists($decodefile)) {
101
include_once($decodefile);
102
$ret = call_user_func('charset_decode_'.$decode, $string);
110
* Makes charset name suitable for decoding cycles
112
* @param string $charset Name of charset
113
* @return string $charset Adjusted name of charset
115
function fixcharset($charset) {
116
// minus removed from function names
117
$charset=str_replace('-','_',$charset);
119
// windows-125x and cp125x charsets
120
$charset=str_replace('windows_','cp',$charset);
123
$charset=str_replace('ibm','cp',$charset);
125
// iso-8859-8-i -> iso-8859-8
126
// use same cycle until I'll find differences
127
$charset=str_replace('iso_8859_8_i','iso_8859_8',$charset);
133
* Set up the language to be output
134
* if $do_search is true, then scan the browser information
135
* for a possible language that we know
137
* Function sets system locale environment (LC_ALL, LANG, LANGUAGE),
138
* gettext translation bindings and html header information.
140
* Function returns error codes, if there is some fatal error.
142
* 1 = mbstring support is not present,
143
* 2 = mbstring support is not present, user's translation reverted to en_US.
145
* @param string $sm_language translation used by user's interface
146
* @param bool $do_search use browser's preferred language detection functions. Defaults to false.
147
* @param bool $default set $sm_language to $squirrelmail_default_language if language detection fails or language is not set. Defaults to false.
148
* @return int function execution error codes.
150
function set_up_language($sm_language, $do_search = false, $default = false) {
152
static $SetupAlready = 0;
153
global $use_gettext, $languages,
154
$squirrelmail_language, $squirrelmail_default_language,
155
$sm_notAlias, $username, $data_dir;
161
$SetupAlready = TRUE;
162
sqgetGlobalVar('HTTP_ACCEPT_LANGUAGE', $accept_lang, SQ_SERVER);
164
if ($do_search && ! $sm_language && isset($accept_lang)) {
165
$sm_language = substr($accept_lang, 0, 2);
168
if ((!$sm_language||$default) && isset($squirrelmail_default_language)) {
169
$squirrelmail_language = $squirrelmail_default_language;
170
$sm_language = $squirrelmail_default_language;
172
$sm_notAlias = $sm_language;
174
// Catching removed translation
175
// System reverts to English translation if user prefs contain translation
176
// that is not available in $languages array
177
if (!isset($languages[$sm_notAlias])) {
178
$sm_notAlias="en_US";
181
while (isset($languages[$sm_notAlias]['ALIAS'])) {
182
$sm_notAlias = $languages[$sm_notAlias]['ALIAS'];
185
if ( isset($sm_language) &&
187
$sm_language != '' &&
188
isset($languages[$sm_notAlias]['CHARSET']) ) {
189
bindtextdomain( 'squirrelmail', SM_PATH . 'locale/' );
190
textdomain( 'squirrelmail' );
191
if (function_exists('bind_textdomain_codeset')) {
192
if ($sm_notAlias == 'ja_JP') {
193
bind_textdomain_codeset ("squirrelmail", 'EUC-JP');
195
bind_textdomain_codeset ("squirrelmail", $languages[$sm_notAlias]['CHARSET'] );
198
if (isset($languages[$sm_notAlias]['LOCALE'])){
199
$longlocale=$languages[$sm_notAlias]['LOCALE'];
201
$longlocale=$sm_notAlias;
203
if ( !ini_get('safe_mode') &&
204
getenv( 'LC_ALL' ) != $longlocale ) {
205
putenv( "LC_ALL=$longlocale" );
206
putenv( "LANG=$longlocale" );
207
putenv( "LANGUAGE=$longlocale" );
209
setlocale(LC_ALL, $longlocale);
211
// Set text direction/alignment variables
212
if (isset($languages[$sm_notAlias]['DIR']) &&
213
$languages[$sm_notAlias]['DIR'] == 'rtl') {
214
$text_direction='rtl';
218
$text_direction='ltr';
220
$right_align='right';
223
$squirrelmail_language = $sm_notAlias;
224
if ($squirrelmail_language == 'ja_JP') {
225
header ('Content-Type: text/html; charset=EUC-JP');
226
if (!function_exists('mb_internal_encoding')) {
227
// Error messages can't be displayed here
229
// Revert to English if possible.
230
if (function_exists('setPref') && $username!='' && $data_dir!="") {
231
setPref($data_dir, $username, 'language', "en_US");
234
// stop further execution in order not to get php errors on mb_internal_encoding().
237
if (function_exists('mb_language')) {
238
mb_language('Japanese');
240
mb_internal_encoding('EUC-JP');
241
mb_http_output('pass');
243
header( 'Content-Type: text/html; charset=' . $languages[$sm_notAlias]['CHARSET'] );
250
* Sets default_charset variable according to the one that is used by user's translations.
252
* Function changes global $default_charset variable in order to be sure, that it
253
* contains charset used by user's translation. Sanity of $squirrelmail_default_language
254
* and $default_charset combination provided in SquirrelMail config is also tested.
256
* There can be a $default_charset setting in the
257
* config.php file, but the user may have a different language
258
* selected for a user interface. This function checks the
259
* language selected by the user and tags the outgoing messages
260
* with the appropriate charset corresponding to the language
261
* selection. This is "more right" (tm), than just stamping the
262
* message blindly with the system-wide $default_charset.
264
function set_my_charset(){
265
global $data_dir, $username, $default_charset, $languages, $squirrelmail_default_language;
267
$my_language = getPref($data_dir, $username, 'language');
269
$my_language = $squirrelmail_default_language ;
271
// Catch removed translation
272
if (!isset($languages[$my_language])) {
273
$my_language="en_US";
275
while (isset($languages[$my_language]['ALIAS'])) {
276
$my_language = $languages[$my_language]['ALIAS'];
278
$my_charset = $languages[$my_language]['CHARSET'];
280
$default_charset = $my_charset;
284
/* ------------------------------ main --------------------------- */
286
global $squirrelmail_language, $languages, $use_gettext;
288
if (! isset($squirrelmail_language)) {
289
$squirrelmail_language = '';
293
* Array specifies the available translations.
295
* Structure of array:
296
* $languages['language']['variable'] = 'value'
298
* Possible 'variable' names:
299
* NAME - Translation name in English
300
* CHARSET - Encoding used by translation
301
* ALIAS - used when 'language' is only short name and 'value' should provide long language name
302
* ALTNAME - Native translation name. Any 8bit symbols must be html encoded.
303
* LOCALE - Full locale name (in xx_XX.charset format)
304
* DIR - Text direction. Used to define Right-to-Left languages. Possible values 'rtl' or 'ltr'. If undefined - defaults to 'ltr'
305
* XTRA_CODE - translation uses special functions. 'value' provides name of that extra function
307
* Each 'language' definition requires NAME+CHARSET or ALIAS variables.
312
$languages['bg_BG']['NAME'] = 'Bulgarian';
313
$languages['bg_BG']['ALTNAME'] = 'Български';
314
$languages['bg_BG']['CHARSET'] = 'windows-1251';
315
$languages['bg']['ALIAS'] = 'bg_BG';
317
$languages['ca_ES']['NAME'] = 'Catalan';
318
$languages['ca_ES']['CHARSET'] = 'iso-8859-1';
319
$languages['ca']['ALIAS'] = 'ca_ES';
321
$languages['cs_CZ']['NAME'] = 'Czech';
322
$languages['cs_CZ']['ALTNAME'] = 'Čeština';
323
$languages['cs_CZ']['CHARSET'] = 'iso-8859-2';
324
$languages['cs']['ALIAS'] = 'cs_CZ';
326
$languages['cy_GB']['NAME'] = 'Welsh';
327
$languages['cy_GB']['ALTNAME'] = 'Cymraeg';
328
$languages['cy_GB']['CHARSET'] = 'iso-8859-1';
329
$languages['cy']['ALIAS'] = 'cy_GB';
331
// Danish locale is da_DK.
332
$languages['da_DK']['NAME'] = 'Danish';
333
$languages['da_DK']['ALTNAME'] = 'Dansk';
334
$languages['da_DK']['CHARSET'] = 'iso-8859-1';
335
$languages['da']['ALIAS'] = 'da_DK';
337
$languages['de_DE']['NAME'] = 'German';
338
$languages['de_DE']['ALTNAME'] = 'Deutsch';
339
$languages['de_DE']['CHARSET'] = 'iso-8859-1';
340
$languages['de']['ALIAS'] = 'de_DE';
342
$languages['el_GR']['NAME'] = 'Greek';
343
$languages['el_GR']['ALTNAME'] = 'Ελληνικά';
344
$languages['el_GR']['CHARSET'] = 'iso-8859-7';
345
$languages['el']['ALIAS'] = 'el_GR';
347
$languages['en_GB']['NAME'] = 'British';
348
$languages['en_GB']['CHARSET'] = 'iso-8859-15';
349
$languages['en_GB']['LOCALE'] = 'en_GB.ISO-8859-15';
351
$languages['en_US']['NAME'] = 'English';
352
$languages['en_US']['CHARSET'] = 'iso-8859-1';
353
$languages['en']['ALIAS'] = 'en_US';
355
$languages['es_ES']['NAME'] = 'Spanish';
356
$languages['es_ES']['ALTNAME'] = 'Español';
357
$languages['es_ES']['CHARSET'] = 'iso-8859-1';
358
$languages['es']['ALIAS'] = 'es_ES';
360
$languages['et_EE']['NAME'] = 'Estonian';
361
$languages['et_EE']['CHARSET'] = 'iso-8859-15';
362
$languages['et']['ALIAS'] = 'et_EE';
364
$languages['fo_FO']['NAME'] = 'Faroese';
365
$languages['fo_FO']['CHARSET'] = 'iso-8859-1';
366
$languages['fo']['ALIAS'] = 'fo_FO';
368
$languages['fi_FI']['NAME'] = 'Finnish';
369
$languages['fi_FI']['ALTNAME'] = 'Suomi';
370
$languages['fi_FI']['CHARSET'] = 'iso-8859-1';
371
$languages['fi']['ALIAS'] = 'fi_FI';
373
$languages['fr_FR']['NAME'] = 'French';
374
$languages['fr_FR']['ALTNAME'] = 'Français';
375
$languages['fr_FR']['CHARSET'] = 'iso-8859-1';
376
$languages['fr']['ALIAS'] = 'fr_FR';
378
$languages['hr_HR']['NAME'] = 'Croatian';
379
$languages['hr_HR']['CHARSET'] = 'iso-8859-2';
380
$languages['hr']['ALIAS'] = 'hr_HR';
382
$languages['hu_HU']['NAME'] = 'Hungarian';
383
$languages['hu_HU']['ALTNAME'] = 'Magyar';
384
$languages['hu_HU']['CHARSET'] = 'iso-8859-2';
385
$languages['hu']['ALIAS'] = 'hu_HU';
387
$languages['id_ID']['NAME'] = 'Indonesian';
388
$languages['id_ID']['ALTNAME'] = 'Bahasa Indonesia';
389
$languages['id_ID']['CHARSET'] = 'iso-8859-1';
390
$languages['id']['ALIAS'] = 'id_ID';
392
$languages['is_IS']['NAME'] = 'Icelandic';
393
$languages['is_IS']['ALTNAME'] = 'Íslenska';
394
$languages['is_IS']['CHARSET'] = 'iso-8859-1';
395
$languages['is']['ALIAS'] = 'is_IS';
397
$languages['it_IT']['NAME'] = 'Italian';
398
$languages['it_IT']['CHARSET'] = 'iso-8859-1';
399
$languages['it']['ALIAS'] = 'it_IT';
401
$languages['ja_JP']['NAME'] = 'Japanese';
402
$languages['ja_JP']['ALTNAME'] = '日本語';
403
$languages['ja_JP']['CHARSET'] = 'iso-2022-jp';
404
$languages['ja_JP']['LOCALE'] = 'ja_JP.EUC-JP';
405
$languages['ja_JP']['XTRA_CODE'] = 'japanese_charset_xtra';
406
$languages['ja']['ALIAS'] = 'ja_JP';
408
$languages['ko_KR']['NAME'] = 'Korean';
409
$languages['ko_KR']['CHARSET'] = 'euc-KR';
410
$languages['ko_KR']['XTRA_CODE'] = 'korean_charset_xtra';
411
$languages['ko']['ALIAS'] = 'ko_KR';
413
$languages['lt_LT']['NAME'] = 'Lithuanian';
414
$languages['lt_LT']['ALTNAME'] = 'Lietuvių';
415
$languages['lt_LT']['CHARSET'] = 'utf-8';
416
$languages['lt_LT']['LOCALE'] = 'lt_LT.UTF-8';
417
$languages['lt']['ALIAS'] = 'lt_LT';
419
$languages['nl_NL']['NAME'] = 'Dutch';
420
$languages['nl_NL']['ALTNAME'] = 'Nederlands';
421
$languages['nl_NL']['CHARSET'] = 'iso-8859-1';
422
$languages['nl']['ALIAS'] = 'nl_NL';
424
$languages['ms_MY']['NAME'] = 'Malay';
425
$languages['ms_MY']['ALTNAME'] = 'Bahasa Melayu';
426
$languages['ms_MY']['CHARSET'] = 'iso-8859-1';
427
$languages['my']['ALIAS'] = 'ms_MY';
429
$languages['no_NO']['NAME'] = 'Norwegian (Bokmål)';
430
$languages['no_NO']['ALTNAME'] = 'Norsk (Bokmål)';
431
$languages['no_NO']['CHARSET'] = 'iso-8859-1';
432
$languages['no']['ALIAS'] = 'no_NO';
434
$languages['nn_NO']['NAME'] = 'Norwegian (Nynorsk)';
435
$languages['nn_NO']['ALTNAME'] = 'Norsk (Nynorsk)';
436
$languages['nn_NO']['CHARSET'] = 'iso-8859-1';
438
$languages['pl_PL']['NAME'] = 'Polish';
439
$languages['pl_PL']['ALTNAME'] = 'Polski';
440
$languages['pl_PL']['CHARSET'] = 'iso-8859-2';
441
$languages['pl']['ALIAS'] = 'pl_PL';
443
$languages['pt_PT']['NAME'] = 'Portuguese (Portugal)';
444
$languages['pt_PT']['CHARSET'] = 'iso-8859-1';
445
$languages['pt']['ALIAS'] = 'pt_PT';
447
$languages['pt_BR']['NAME'] = 'Portuguese (Brazil)';
448
$languages['pt_BR']['ALTNAME'] = 'Português do Brasil';
449
$languages['pt_BR']['CHARSET'] = 'iso-8859-1';
451
$languages['ro_RO']['NAME'] = 'Romanian';
452
$languages['ro_RO']['ALTNAME'] = 'Română';
453
$languages['ro_RO']['CHARSET'] = 'iso-8859-2';
454
$languages['ro']['ALIAS'] = 'ro_RO';
456
$languages['ru_RU']['NAME'] = 'Russian';
457
$languages['ru_RU']['ALTNAME'] = 'Русский';
458
$languages['ru_RU']['CHARSET'] = 'utf-8';
459
$languages['ru_RU']['LOCALE'] = 'ru_RU.UTF-8';
460
$languages['ru']['ALIAS'] = 'ru_RU';
462
$languages['sk_SK']['NAME'] = 'Slovak';
463
$languages['sk_SK']['CHARSET'] = 'iso-8859-2';
464
$languages['sk']['ALIAS'] = 'sk_SK';
466
$languages['sl_SI']['NAME'] = 'Slovenian';
467
$languages['sl_SI']['ALTNAME'] = 'Slovenščina';
468
$languages['sl_SI']['CHARSET'] = 'iso-8859-2';
469
$languages['sl']['ALIAS'] = 'sl_SI';
471
$languages['sr_YU']['NAME'] = 'Serbian';
472
$languages['sr_YU']['ALTNAME'] = 'Srpski';
473
$languages['sr_YU']['CHARSET'] = 'iso-8859-2';
474
$languages['sr']['ALIAS'] = 'sr_YU';
476
$languages['sv_SE']['NAME'] = 'Swedish';
477
$languages['sv_SE']['ALTNAME'] = 'Svenska';
478
$languages['sv_SE']['CHARSET'] = 'iso-8859-1';
479
$languages['sv']['ALIAS'] = 'sv_SE';
481
$languages['th_TH']['NAME'] = 'Thai';
482
$languages['th_TH']['CHARSET'] = 'tis-620';
483
$languages['th']['ALIAS'] = 'th_TH';
485
$languages['tr_TR']['NAME'] = 'Turkish';
486
$languages['tr_TR']['CHARSET'] = 'iso-8859-9';
487
$languages['tr']['ALIAS'] = 'tr_TR';
489
$languages['zh_TW']['NAME'] = 'Chinese Trad';
490
$languages['zh_TW']['CHARSET'] = 'big5';
491
$languages['tw']['ALIAS'] = 'zh_TW';
493
$languages['zh_CN']['NAME'] = 'Chinese Simp';
494
$languages['zh_CN']['CHARSET'] = 'gb2312';
495
$languages['cn']['ALIAS'] = 'zh_CN';
498
$languages['uk_UA']['NAME'] = 'Ukrainian';
499
$languages['uk_UA']['CHARSET'] = 'koi8-u';
500
$languages['uk']['ALIAS'] = 'uk_UA';
503
if ( file_exists( SM_PATH . 'locale/vi_VN') ) {
504
$languages['vi_VN']['NAME'] = 'Vietnamese';
505
$languages['vi_VN']['CHARSET'] = 'utf-8';
506
$languages['vi']['ALIAS'] = 'vi_VN';
510
// Right to left languages
511
$languages['ar']['NAME'] = 'Arabic';
512
$languages['ar']['CHARSET'] = 'windows-1256';
513
$languages['ar']['DIR'] = 'rtl';
515
$languages['he_IL']['NAME'] = 'Hebrew';
516
$languages['he_IL']['CHARSET'] = 'windows-1255';
517
$languages['he_IL']['DIR'] = 'rtl';
518
$languages['he']['ALIAS'] = 'he_IL';
520
/* Detect whether gettext is installed. */
522
if (function_exists('_')) {
525
if (function_exists('bindtextdomain')) {
528
if (function_exists('textdomain')) {
532
/* If gettext is fully loaded, cool */
533
if ($gettext_flags == 7) {
536
/* If we can fake gettext, try that */
537
elseif ($gettext_flags == 0) {
539
include_once(SM_PATH . 'functions/gettext.php');
541
/* Uh-ho. A weird install */
542
if (! $gettext_flags & 1) {
547
if (! $gettext_flags & 2) {
548
function bindtextdomain() {
552
if (! $gettext_flags & 4) {
553
function textdomain() {
561
* Japanese charset extra function
563
* Action performed by function is defined by first argument.
564
* Default return value is defined by second argument.
565
* Use of third argument depends on action.
567
* @param string action performed by this function.
569
* decode - convert returned string to euc-jp. third argument unused
570
* encode - convert returned string to jis. third argument unused
571
* strimwidth - third argument=$width. trims string to $width symbols.
572
* encodeheader - create base64 encoded header in iso-2022-jp. third argument unused
573
* decodeheader - return human readable string from mime header. string is returned in euc-jp. third argument unused
574
* downloadfilename - third argument $useragent. Arguments provide browser info. Returns shift-jis or euc-jp encoded file name
575
* wordwrap - third argument=$wrap. wraps text at $wrap symbols
576
* utf7-imap_encode - returns string converted from euc-jp to utf7-imap. third argument unused
577
* utf7-imap_decode - returns string converted from utf7-imap to euc-jp. third argument unused
578
* @param string default return value
580
function japanese_charset_xtra() {
581
$ret = func_get_arg(1); /* default return value */
582
if (function_exists('mb_detect_encoding')) {
583
switch (func_get_arg(0)) { /* action */
585
$detect_encoding = @mb_detect_encoding($ret);
586
if ($detect_encoding == 'JIS' ||
587
$detect_encoding == 'EUC-JP' ||
588
$detect_encoding == 'SJIS' ||
589
$detect_encoding == 'UTF-8') {
591
$ret = mb_convert_kana(mb_convert_encoding($ret, 'EUC-JP', 'AUTO'), "KV");
595
$detect_encoding = @mb_detect_encoding($ret);
596
if ($detect_encoding == 'JIS' ||
597
$detect_encoding == 'EUC-JP' ||
598
$detect_encoding == 'SJIS' ||
599
$detect_encoding == 'UTF-8') {
601
$ret = mb_convert_encoding(mb_convert_kana($ret, "KV"), 'JIS', 'AUTO');
605
$width = func_get_arg(2);
606
$ret = mb_strimwidth($ret, 0, $width, '...');
610
if (strlen($ret) > 0) {
611
$tmpstr = mb_substr($ret, 0, 1);
612
$prevcsize = strlen($tmpstr);
613
for ($i = 1; $i < mb_strlen($ret); $i++) {
614
$tmp = mb_substr($ret, $i, 1);
615
if (strlen($tmp) == $prevcsize) {
618
if ($prevcsize == 1) {
621
$result .= str_replace(' ', '',
622
mb_encode_mimeheader($tmpstr,'iso-2022-jp','B',''));
625
$prevcsize = strlen($tmp);
628
if (strlen($tmpstr)) {
629
if (strlen(mb_substr($tmpstr, 0, 1)) == 1)
632
$result .= str_replace(' ', '',
633
mb_encode_mimeheader($tmpstr,'iso-2022-jp','B',''));
639
$ret = str_replace("\t", "", $ret);
640
if (eregi('=\\?([^?]+)\\?(q|b)\\?([^?]+)\\?=', $ret))
641
$ret = @mb_decode_mimeheader($ret);
642
$ret = @mb_convert_encoding($ret, 'EUC-JP', 'AUTO');
644
case 'downloadfilename':
645
$useragent = func_get_arg(2);
646
if (strstr($useragent, 'Windows') !== false ||
647
strstr($useragent, 'Mac_') !== false) {
648
$ret = mb_convert_encoding($ret, 'SJIS', 'AUTO');
650
$ret = mb_convert_encoding($ret, 'EUC-JP', 'AUTO');
654
$no_begin = "\x21\x25\x29\x2c\x2e\x3a\x3b\x3f\x5d\x7d\xa1\xf1\xa1\xeb\xa1" .
655
"\xc7\xa1\xc9\xa2\xf3\xa1\xec\xa1\xed\xa1\xee\xa1\xa2\xa1\xa3\xa1\xb9" .
656
"\xa1\xd3\xa1\xd5\xa1\xd7\xa1\xd9\xa1\xdb\xa1\xcd\xa4\xa1\xa4\xa3\xa4" .
657
"\xa5\xa4\xa7\xa4\xa9\xa4\xc3\xa4\xe3\xa4\xe5\xa4\xe7\xa4\xee\xa1\xab" .
658
"\xa1\xac\xa1\xb5\xa1\xb6\xa5\xa1\xa5\xa3\xa5\xa5\xa5\xa7\xa5\xa9\xa5" .
659
"\xc3\xa5\xe3\xa5\xe5\xa5\xe7\xa5\xee\xa5\xf5\xa5\xf6\xa1\xa6\xa1\xbc" .
660
"\xa1\xb3\xa1\xb4\xa1\xaa\xa1\xf3\xa1\xcb\xa1\xa4\xa1\xa5\xa1\xa7\xa1" .
661
"\xa8\xa1\xa9\xa1\xcf\xa1\xd1";
662
$no_end = "\x5c\x24\x28\x5b\x7b\xa1\xf2\x5c\xa1\xc6\xa1\xc8\xa1\xd2\xa1" .
663
"\xd4\xa1\xd6\xa1\xd8\xa1\xda\xa1\xcc\xa1\xf0\xa1\xca\xa1\xce\xa1\xd0\xa1\xef";
664
$wrap = func_get_arg(2);
666
if (strlen($ret) >= $wrap &&
667
substr($ret, 0, 1) != '>' &&
668
strpos($ret, 'http://') === FALSE &&
669
strpos($ret, 'https://') === FALSE &&
670
strpos($ret, 'ftp://') === FALSE) {
672
$ret = mb_convert_kana($ret, "KV");
677
while ($ptr < strlen($ret) - 1) {
678
$l = mb_strcut($ret, $ptr, $wrap);
682
$l = mb_strcut($ret, $ptr, 2);
683
while (strlen($l) != 0 && mb_strpos($no_begin, $l) !== FALSE ) {
686
$l = mb_strcut($ret, $ptr, 1);
689
if ($ptr < strlen($ret) - 1)
695
case 'utf7-imap_encode':
696
$ret = mb_convert_encoding($ret, 'UTF7-IMAP', 'EUC-JP');
698
case 'utf7-imap_decode':
699
$ret = mb_convert_encoding($ret, 'EUC-JP', 'UTF7-IMAP');
708
* Korean charset extra functions
710
* Action performed by function is defined by first argument.
711
* Default return value is defined by second argument.
713
* @param string action performed by this function.
715
* downloadfilename - Hangul(Korean Character) Attached File Name Fix.
716
* @param string default return value
718
function korean_charset_xtra() {
720
$ret = func_get_arg(1); /* default return value */
721
if (func_get_arg(0) == 'downloadfilename') { /* action */
722
$ret = str_replace("\x0D\x0A", '', $ret); /* Hanmail's CR/LF Clear */
723
for ($i=0;$i<strlen($ret);$i++) {
724
if ($ret[$i] >= "\xA1" && $ret[$i] <= "\xFE") { /* 0xA1 - 0XFE are Valid */
727
} else if (($ret[$i] >= 'a' && $ret[$i] <= 'z') || /* From Original ereg_replace in download.php */
728
($ret[$i] >= 'A' && $ret[$i] <= 'Z') ||
729
($ret[$i] == '.') || ($ret[$i] == '-')) {
741
* Replaces non-braking spaces inserted by some browsers with regular space
743
* This function can be used to replace non-braking space symbols
744
* that are inserted in forms by some browsers instead of normal
747
* @param string $string Text that needs to be cleaned
748
* @param string $charset Charset used in text
749
* @return string Cleaned text
751
function cleanup_nbsp($string,$charset) {
753
// reduce number of case statements
754
if (stristr('iso-8859-',substr($charset,0,9))){
755
$output_charset="iso-8859-x";
757
if (stristr('windows-125',substr($charset,0,11))){
758
$output_charset="cp125x";
760
if (stristr('koi8',substr($charset,0,4))){
761
$output_charset="koi8-x";
763
if (! isset($output_charset)){
764
$output_charset=strtolower($charset);
767
// where is non-braking space symbol
768
switch($output_charset):
781
// don't change string if charset is unmatched
785
// return space instead of non-braking space.
786
return str_replace($nbsp,' ',$string);
790
* Function informs if it is safe to convert given charset to the one that is used by user.
792
* It is safe to use conversion only if user uses utf-8 encoding and when
793
* converted charset is similar to the one that is used by user.
795
* @param string $input_charset Charset of text that needs to be converted
796
* @return bool is it possible to convert to user's charset
798
function is_conversion_safe($input_charset) {
799
global $languages, $sm_notAlias, $default_charset;
801
// convert to lower case
802
$input_charset = strtolower($input_charset);
804
// Is user's locale Unicode based ?
805
if ( $default_charset == "utf-8" ) {
809
// Charsets that are similar
810
switch ($default_charset):
812
if ( $input_charset == "iso-8859-5" ||
813
$input_charset == "koi8-r" ||
814
$input_charset == "koi8-u" ) {
820
if ( $input_charset == "iso-8859-13" ||
821
$input_charset == "iso-8859-4" ) {
827
if ( $input_charset == "iso-8859-13" ||
828
$input_charset == "windows-1257" ) {
834
if ( $input_charset == "windows-1251" ||
835
$input_charset == "koi8-r" ||
836
$input_charset == "koi8-u" ) {
842
if ( $input_charset == "iso-8859-4" ||
843
$input_charset == "windows-1257" ) {
849
if ( $input_charset == "windows-1251" ||
850
$input_charset == "iso-8859-5" ||
851
$input_charset == "koi8-u" ) {
857
if ( $input_charset == "windows-1251" ||
858
$input_charset == "iso-8859-5" ||
859
$input_charset == "koi8-r" ) {
b'\\ No newline at end of file'
added
removed
functions/i18n.php
