4 * SquirrelMail internationalization functions
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.
16 * @package squirrelmail
20 /** Everything uses global.php... */
21 require_once(SM_PATH
. 'functions/global.php');
24 * Converts string from given charset to charset, that can be displayed by user translation.
26 * Function by default returns html encoded strings, if translation uses different encoding.
27 * If Japanese translation is used - function returns string converted to euc-jp
28 * If iconv or recode functions are enabled and translation uses utf-8 - function returns utf-8 encoded string.
29 * If $charset is not supported - function returns unconverted string.
31 * sanitizing of html tags is also done by this function.
33 * @param string $charset
34 * @param string $string Text to be decoded
35 * @return string decoded string
37 function charset_decode ($charset, $string) {
38 global $languages, $squirrelmail_language, $default_charset;
39 global $use_php_recode, $use_php_iconv, $agresive_decoding;
41 if (isset($languages[$squirrelmail_language]['XTRA_CODE']) &&
42 function_exists($languages[$squirrelmail_language]['XTRA_CODE'] . '_decode')) {
43 $string = call_user_func($languages[$squirrelmail_language]['XTRA_CODE'] . '_decode', $string);
46 $charset = strtolower($charset);
50 // Variables that allow to use functions without function_exist() calls
51 if (! isset($use_php_recode) ||
$use_php_recode=="" ) {
52 $use_php_recode=false; }
53 if (! isset($use_php_iconv) ||
$use_php_iconv=="" ) {
54 $use_php_iconv=false; }
56 // Don't do conversion if charset is the same.
57 if ( $charset == strtolower($default_charset) )
58 return htmlspecialchars($string);
60 // catch iso-8859-8-i thing
61 if ( $charset == "iso-8859-8-i" )
62 $charset = "iso-8859-8";
65 * Recode converts html special characters automatically if you use
66 * 'charset..html' decoding. There is no documented way to put -d option
67 * into php recode function call.
69 if ( $use_php_recode ) {
70 if ( $default_charset == "utf-8" ) {
71 // other charsets can be converted to utf-8 without loss.
72 // and output string is smaller
73 $string = recode_string($charset . "..utf-8",$string);
74 return htmlspecialchars($string);
76 $string = recode_string($charset . "..html",$string);
77 // recode does not convert single quote, htmlspecialchars does.
78 $string = str_replace("'", ''', $string);
83 // iconv functions does not have html target and can be used only with utf-8
84 if ( $use_php_iconv && $default_charset=='utf-8') {
85 $string = iconv($charset,$default_charset,$string);
86 return htmlspecialchars($string);
89 // If we don't use recode and iconv, we'll do it old way.
91 /* All HTML special characters are 7 bit and can be replaced first */
93 $string = htmlspecialchars ($string);
95 /* controls cpu and memory intensive decoding cycles */
96 if (! isset($agresive_decoding) ||
$agresive_decoding=="" ) {
97 $agresive_decoding=false; }
99 $decode=fixcharset($charset);
100 $decodefile=SM_PATH
. 'functions/decode/' . $decode . '.php';
101 if (file_exists($decodefile)) {
102 include_once($decodefile);
103 $ret = call_user_func('charset_decode_'.$decode, $string);
111 * Converts html string to given charset
112 * @param string $string
113 * @param string $charset
114 * @param boolean $htmlencode keep htmlspecialchars encoding
117 function charset_encode($string,$charset,$htmlencode=true) {
118 global $default_charset;
120 // Undo html special chars
121 if (! $htmlencode ) {
122 $string = str_replace(array('&','>','<','"'),array('&','>','<','"'),$string);
125 $encode=fixcharset($charset);
126 $encodefile=SM_PATH
. 'functions/encode/' . $encode . '.php';
127 if (file_exists($encodefile)) {
128 include_once($encodefile);
129 $ret = call_user_func('charset_encode_'.$encode, $string);
137 * Combined decoding and encoding functions
139 * If conversion is done to charset different that utf-8, unsupported symbols
140 * will be replaced with question marks.
141 * @param string $in_charset initial charset
142 * @param string $string string that has to be converted
143 * @param string $out_charset final charset
144 * @param boolean $htmlencode keep htmlspecialchars encoding
145 * @return string converted string
147 function charset_convert($in_charset,$string,$out_charset,$htmlencode=true) {
148 $string=charset_decode($in_charset,$string);
149 $string=charset_encode($string,$out_charset,$htmlencode);
154 * Makes charset name suitable for decoding cycles
156 * @param string $charset Name of charset
157 * @return string $charset Adjusted name of charset
159 function fixcharset($charset) {
160 // minus removed from function names
161 $charset=str_replace('-','_',$charset);
163 // windows-125x and cp125x charsets
164 $charset=str_replace('windows_','cp',$charset);
167 $charset=str_replace('ibm','cp',$charset);
169 // iso-8859-8-i -> iso-8859-8
170 // use same cycle until I'll find differences
171 $charset=str_replace('iso_8859_8_i','iso_8859_8',$charset);
177 * Set up the language to be output
178 * if $do_search is true, then scan the browser information
179 * for a possible language that we know
181 * Function sets system locale environment (LC_ALL, LANG, LANGUAGE),
182 * gettext translation bindings and html header information.
184 * Function returns error codes, if there is some fatal error.
186 * 1 = mbstring support is not present,
187 * 2 = mbstring support is not present, user's translation reverted to en_US.
189 * @param string $sm_language translation used by user's interface
190 * @param bool $do_search use browser's preferred language detection functions. Defaults to false.
191 * @param bool $default set $sm_language to $squirrelmail_default_language if language detection fails or language is not set. Defaults to false.
192 * @return int function execution error codes.
194 function set_up_language($sm_language, $do_search = false, $default = false) {
196 static $SetupAlready = 0;
197 global $use_gettext, $languages,
198 $squirrelmail_language, $squirrelmail_default_language,
199 $sm_notAlias, $username, $data_dir;
205 $SetupAlready = TRUE;
206 sqgetGlobalVar('HTTP_ACCEPT_LANGUAGE', $accept_lang, SQ_SERVER
);
208 if ($do_search && ! $sm_language && isset($accept_lang)) {
209 $sm_language = substr($accept_lang, 0, 2);
212 if ((!$sm_language||
$default) && isset($squirrelmail_default_language)) {
213 $squirrelmail_language = $squirrelmail_default_language;
214 $sm_language = $squirrelmail_default_language;
216 $sm_notAlias = $sm_language;
218 // Catching removed translation
219 // System reverts to English translation if user prefs contain translation
220 // that is not available in $languages array
221 if (!isset($languages[$sm_notAlias])) {
222 $sm_notAlias="en_US";
225 while (isset($languages[$sm_notAlias]['ALIAS'])) {
226 $sm_notAlias = $languages[$sm_notAlias]['ALIAS'];
229 if ( isset($sm_language) &&
231 $sm_language != '' &&
232 isset($languages[$sm_notAlias]['CHARSET']) ) {
233 bindtextdomain( 'squirrelmail', SM_PATH
. 'locale/' );
234 textdomain( 'squirrelmail' );
235 if (function_exists('bind_textdomain_codeset')) {
236 if ($sm_notAlias == 'ja_JP') {
237 bind_textdomain_codeset ("squirrelmail", 'EUC-JP');
239 bind_textdomain_codeset ("squirrelmail", $languages[$sm_notAlias]['CHARSET'] );
242 if (isset($languages[$sm_notAlias]['LOCALE'])){
243 $longlocale=$languages[$sm_notAlias]['LOCALE'];
245 $longlocale=$sm_notAlias;
247 if ( !ini_get('safe_mode') &&
248 getenv( 'LC_ALL' ) != $longlocale ) {
249 putenv( "LC_ALL=$longlocale" );
250 putenv( "LANG=$longlocale" );
251 putenv( "LANGUAGE=$longlocale" );
253 setlocale(LC_ALL
, $longlocale);
255 // Set text direction/alignment variables
256 if (isset($languages[$sm_notAlias]['DIR']) &&
257 $languages[$sm_notAlias]['DIR'] == 'rtl') {
260 * @global string $text_direction
262 $text_direction='rtl';
265 * @global string $left_align
270 * @global string $right_align
274 $text_direction='ltr';
276 $right_align='right';
279 $squirrelmail_language = $sm_notAlias;
280 if ($squirrelmail_language == 'ja_JP') {
281 header ('Content-Type: text/html; charset=EUC-JP');
282 if (!function_exists('mb_internal_encoding')) {
283 // Error messages can't be displayed here
285 // Revert to English if possible.
286 if (function_exists('setPref') && $username!='' && $data_dir!="") {
287 setPref($data_dir, $username, 'language', "en_US");
290 // stop further execution in order not to get php errors on mb_internal_encoding().
293 if (function_exists('mb_language')) {
294 mb_language('Japanese');
296 mb_internal_encoding('EUC-JP');
297 mb_http_output('pass');
299 header( 'Content-Type: text/html; charset=' . $languages[$sm_notAlias]['CHARSET'] );
306 * Sets default_charset variable according to the one that is used by user's translations.
308 * Function changes global $default_charset variable in order to be sure, that it
309 * contains charset used by user's translation. Sanity of $squirrelmail_default_language
310 * and $default_charset combination provided in SquirrelMail config is also tested.
312 * There can be a $default_charset setting in the
313 * config.php file, but the user may have a different language
314 * selected for a user interface. This function checks the
315 * language selected by the user and tags the outgoing messages
316 * with the appropriate charset corresponding to the language
317 * selection. This is "more right" (tm), than just stamping the
318 * message blindly with the system-wide $default_charset.
320 function set_my_charset(){
321 global $data_dir, $username, $default_charset, $languages, $squirrelmail_default_language;
323 $my_language = getPref($data_dir, $username, 'language');
325 $my_language = $squirrelmail_default_language ;
327 // Catch removed translation
328 if (!isset($languages[$my_language])) {
329 $my_language="en_US";
331 while (isset($languages[$my_language]['ALIAS'])) {
332 $my_language = $languages[$my_language]['ALIAS'];
334 $my_charset = $languages[$my_language]['CHARSET'];
336 $default_charset = $my_charset;
340 /* ------------------------------ main --------------------------- */
342 global $squirrelmail_language, $languages, $use_gettext;
344 if (! isset($squirrelmail_language)) {
345 $squirrelmail_language = '';
349 * Array specifies the available translations.
351 * Structure of array:
352 * $languages['language']['variable'] = 'value'
354 * Possible 'variable' names:
355 * NAME - Translation name in English
356 * CHARSET - Encoding used by translation
357 * ALIAS - used when 'language' is only short name and 'value' should provide long language name
358 * ALTNAME - Native translation name. Any 8bit symbols must be html encoded.
359 * LOCALE - Full locale name (in xx_XX.charset format)
360 * DIR - Text direction. Used to define Right-to-Left languages. Possible values 'rtl' or 'ltr'. If undefined - defaults to 'ltr'
361 * XTRA_CODE - translation uses special functions. See doc/i18n.txt
363 * Each 'language' definition requires NAME+CHARSET or ALIAS variables.
366 * @global array $languages
368 $languages['bg_BG']['NAME'] = 'Bulgarian';
369 $languages['bg_BG']['ALTNAME'] = 'Български';
370 $languages['bg_BG']['CHARSET'] = 'windows-1251';
371 $languages['bg_BG']['LOCALE'] = 'bg_BG.CP1251';
372 $languages['bg']['ALIAS'] = 'bg_BG';
374 $languages['ca_ES']['NAME'] = 'Catalan';
375 $languages['ca_ES']['CHARSET'] = 'iso-8859-1';
376 $languages['ca_ES']['LOCALE'] = 'ca_ES.ISO8859-1';
377 $languages['ca']['ALIAS'] = 'ca_ES';
379 $languages['cs_CZ']['NAME'] = 'Czech';
380 $languages['cs_CZ']['ALTNAME'] = 'Čeština';
381 $languages['cs_CZ']['CHARSET'] = 'iso-8859-2';
382 $languages['cs_CZ']['LOCALE'] = 'cs_CZ.ISO8859-2';
383 $languages['cs']['ALIAS'] = 'cs_CZ';
385 $languages['cy_GB']['NAME'] = 'Welsh';
386 $languages['cy_GB']['ALTNAME'] = 'Cymraeg';
387 $languages['cy_GB']['CHARSET'] = 'iso-8859-1';
388 $languages['cy_GB']['LOCALE'] = 'cy_GB.ISO8859-1';
389 $languages['cy']['ALIAS'] = 'cy_GB';
391 // Danish locale is da_DK.
392 $languages['da_DK']['NAME'] = 'Danish';
393 $languages['da_DK']['ALTNAME'] = 'Dansk';
394 $languages['da_DK']['CHARSET'] = 'iso-8859-1';
395 $languages['da_DK']['LOCALE'] = 'da_DK.ISO8859-1';
396 $languages['da']['ALIAS'] = 'da_DK';
398 $languages['de_DE']['NAME'] = 'German';
399 $languages['de_DE']['ALTNAME'] = 'Deutsch';
400 $languages['de_DE']['CHARSET'] = 'iso-8859-1';
401 $languages['de_DE']['LOCALE'] = 'de_DE.ISO8859-1';
402 $languages['de']['ALIAS'] = 'de_DE';
404 $languages['el_GR']['NAME'] = 'Greek';
405 $languages['el_GR']['ALTNAME'] = 'Ελληνικά';
406 $languages['el_GR']['CHARSET'] = 'iso-8859-7';
407 $languages['el_GR']['LOCALE'] = 'el_GR.ISO8859-7';
408 $languages['el']['ALIAS'] = 'el_GR';
410 $languages['en_GB']['NAME'] = 'British';
411 $languages['en_GB']['CHARSET'] = 'iso-8859-15';
412 $languages['en_GB']['LOCALE'] = 'en_GB.ISO8859-15';
414 $languages['en_US']['NAME'] = 'English';
415 $languages['en_US']['CHARSET'] = 'iso-8859-1';
416 $languages['en_US']['LOCALE'] = 'en_US.ISO8859-1';
417 $languages['en']['ALIAS'] = 'en_US';
419 $languages['es_ES']['NAME'] = 'Spanish';
420 $languages['es_ES']['ALTNAME'] = 'Español';
421 $languages['es_ES']['CHARSET'] = 'iso-8859-1';
422 $languages['es_ES']['LOCALE'] = 'es_ES.ISO8859-1';
423 $languages['es']['ALIAS'] = 'es_ES';
425 $languages['et_EE']['NAME'] = 'Estonian';
426 $languages['et_EE']['CHARSET'] = 'iso-8859-15';
427 $languages['et_EE']['LOCALE'] = 'et_EE.ISO8859-15';
428 $languages['et']['ALIAS'] = 'et_EE';
430 $languages['eu_ES']['NAME'] = 'Basque';
431 $languages['eu_ES']['CHARSET'] = 'iso-8859-1';
432 $languages['eu_ES']['LOCALE'] = 'eu_ES.ISO8859-1';
433 $languages['eu']['ALIAS'] = 'eu_ES';
435 $languages['fo_FO']['NAME'] = 'Faroese';
436 $languages['fo_FO']['CHARSET'] = 'iso-8859-1';
437 $languages['fo_FO']['LOCALE'] = 'fo_FO.ISO8859-1';
438 $languages['fo']['ALIAS'] = 'fo_FO';
440 $languages['fi_FI']['NAME'] = 'Finnish';
441 $languages['fi_FI']['ALTNAME'] = 'Suomi';
442 $languages['fi_FI']['CHARSET'] = 'iso-8859-1';
443 $languages['fi_FI']['LOCALE'] = 'fi_FI.ISO8859-1';
444 $languages['fi']['ALIAS'] = 'fi_FI';
446 $languages['fr_FR']['NAME'] = 'French';
447 $languages['fr_FR']['ALTNAME'] = 'Français';
448 $languages['fr_FR']['CHARSET'] = 'iso-8859-1';
449 $languages['fr_FR']['LOCALE'] = 'fr_FR.ISO8859-1';
450 $languages['fr']['ALIAS'] = 'fr_FR';
452 $languages['hr_HR']['NAME'] = 'Croatian';
453 $languages['hr_HR']['CHARSET'] = 'iso-8859-2';
454 $languages['hr_HR']['LOCALE'] = 'hr_HR.ISO8859-2';
455 $languages['hr']['ALIAS'] = 'hr_HR';
457 $languages['hu_HU']['NAME'] = 'Hungarian';
458 $languages['hu_HU']['ALTNAME'] = 'Magyar';
459 $languages['hu_HU']['CHARSET'] = 'iso-8859-2';
460 $languages['hu_HU']['LOCALE'] = 'hu_HU.ISO8859-2';
461 $languages['hu']['ALIAS'] = 'hu_HU';
463 $languages['id_ID']['NAME'] = 'Indonesian';
464 $languages['id_ID']['ALTNAME'] = 'Bahasa Indonesia';
465 $languages['id_ID']['CHARSET'] = 'iso-8859-1';
466 $languages['id_ID']['LOCALE'] = 'id_ID.ISO8859-1';
467 $languages['id']['ALIAS'] = 'id_ID';
469 $languages['is_IS']['NAME'] = 'Icelandic';
470 $languages['is_IS']['ALTNAME'] = 'Íslenska';
471 $languages['is_IS']['CHARSET'] = 'iso-8859-1';
472 $languages['is_IS']['LOCALE'] = 'is_IS.ISO8859-1';
473 $languages['is']['ALIAS'] = 'is_IS';
475 $languages['it_IT']['NAME'] = 'Italian';
476 $languages['it_IT']['CHARSET'] = 'iso-8859-1';
477 $languages['it_IT']['LOCALE'] = 'it_IT.ISO8859-1';
478 $languages['it']['ALIAS'] = 'it_IT';
480 $languages['ja_JP']['NAME'] = 'Japanese';
481 $languages['ja_JP']['ALTNAME'] = '日本語';
482 $languages['ja_JP']['CHARSET'] = 'iso-2022-jp';
483 $languages['ja_JP']['LOCALE'] = 'ja_JP.EUC-JP';
484 $languages['ja_JP']['XTRA_CODE'] = 'japanese_xtra';
485 $languages['ja']['ALIAS'] = 'ja_JP';
487 $languages['ko_KR']['NAME'] = 'Korean';
488 $languages['ko_KR']['CHARSET'] = 'euc-KR';
489 $languages['ko_KR']['LOCALE'] = 'ko_KR.EUC-KR';
490 $languages['ko_KR']['XTRA_CODE'] = 'korean_xtra';
491 $languages['ko']['ALIAS'] = 'ko_KR';
493 $languages['lt_LT']['NAME'] = 'Lithuanian';
494 $languages['lt_LT']['ALTNAME'] = 'Lietuvių';
495 $languages['lt_LT']['CHARSET'] = 'utf-8';
496 $languages['lt_LT']['LOCALE'] = 'lt_LT.UTF-8';
497 $languages['lt']['ALIAS'] = 'lt_LT';
499 $languages['nl_NL']['NAME'] = 'Dutch';
500 $languages['nl_NL']['ALTNAME'] = 'Nederlands';
501 $languages['nl_NL']['CHARSET'] = 'iso-8859-1';
502 $languages['nl_NL']['LOCALE'] = 'nl_NL.ISO8859-1';
503 $languages['nl']['ALIAS'] = 'nl_NL';
505 $languages['ms_MY']['NAME'] = 'Malay';
506 $languages['ms_MY']['ALTNAME'] = 'Bahasa Melayu';
507 $languages['ms_MY']['CHARSET'] = 'iso-8859-1';
508 $languages['ms_MY']['LOCALE'] = 'ms_MY.ISO8859-1';
509 $languages['my']['ALIAS'] = 'ms_MY';
511 $languages['nb_NO']['NAME'] = 'Norwegian (Bokmål)';
512 $languages['nb_NO']['ALTNAME'] = 'Norsk (Bokmål)';
513 $languages['nb_NO']['CHARSET'] = 'iso-8859-1';
514 $languages['nb_NO']['LOCALE'] = 'nb_NO.ISO8859-1';
515 $languages['nb']['ALIAS'] = 'nb_NO';
517 $languages['nn_NO']['NAME'] = 'Norwegian (Nynorsk)';
518 $languages['nn_NO']['ALTNAME'] = 'Norsk (Nynorsk)';
519 $languages['nn_NO']['CHARSET'] = 'iso-8859-1';
520 $languages['nn_NO']['LOCALE'] = 'nn_NO.ISO8859-1';
522 $languages['pl_PL']['NAME'] = 'Polish';
523 $languages['pl_PL']['ALTNAME'] = 'Polski';
524 $languages['pl_PL']['CHARSET'] = 'iso-8859-2';
525 $languages['pl_PL']['LOCALE'] = 'pl_PL.ISO8859-2';
526 $languages['pl']['ALIAS'] = 'pl_PL';
528 $languages['pt_PT']['NAME'] = 'Portuguese (Portugal)';
529 $languages['pt_PT']['CHARSET'] = 'iso-8859-1';
530 $languages['pt_PT']['LOCALE'] = 'pt_PT.ISO8859-1';
531 $languages['pt']['ALIAS'] = 'pt_PT';
533 $languages['pt_BR']['NAME'] = 'Portuguese (Brazil)';
534 $languages['pt_BR']['ALTNAME'] = 'Português do Brasil';
535 $languages['pt_BR']['CHARSET'] = 'iso-8859-1';
536 $languages['pt_BR']['LOCALE'] = 'pt_BR.ISO8859-1';
538 $languages['ro_RO']['NAME'] = 'Romanian';
539 $languages['ro_RO']['ALTNAME'] = 'Română';
540 $languages['ro_RO']['CHARSET'] = 'iso-8859-2';
541 $languages['ro_RO']['LOCALE'] = 'ro_RO.ISO8859-2';
542 $languages['ro']['ALIAS'] = 'ro_RO';
544 $languages['ru_RU']['NAME'] = 'Russian';
545 $languages['ru_RU']['ALTNAME'] = 'Русский';
546 $languages['ru_RU']['CHARSET'] = 'utf-8';
547 $languages['ru_RU']['LOCALE'] = 'ru_RU.UTF-8';
548 $languages['ru']['ALIAS'] = 'ru_RU';
550 $languages['sk_SK']['NAME'] = 'Slovak';
551 $languages['sk_SK']['CHARSET'] = 'iso-8859-2';
552 $languages['sk_SK']['LOCALE'] = 'sk_SK.ISO8859-2';
553 $languages['sk']['ALIAS'] = 'sk_SK';
555 $languages['sl_SI']['NAME'] = 'Slovenian';
556 $languages['sl_SI']['ALTNAME'] = 'Slovenščina';
557 $languages['sl_SI']['CHARSET'] = 'iso-8859-2';
558 $languages['sl_SI']['LOCALE'] = 'sl_SI.ISO8859-2';
559 $languages['sl']['ALIAS'] = 'sl_SI';
561 $languages['sr_YU']['NAME'] = 'Serbian';
562 $languages['sr_YU']['ALTNAME'] = 'Srpski';
563 $languages['sr_YU']['CHARSET'] = 'iso-8859-2';
564 $languages['sr_YU']['LOCALE'] = 'sr_YU.ISO8859-2';
565 $languages['sr']['ALIAS'] = 'sr_YU';
567 $languages['sv_SE']['NAME'] = 'Swedish';
568 $languages['sv_SE']['ALTNAME'] = 'Svenska';
569 $languages['sv_SE']['CHARSET'] = 'iso-8859-1';
570 $languages['sv_SE']['LOCALE'] = 'sv_SE.ISO8859-1';
571 $languages['sv']['ALIAS'] = 'sv_SE';
573 $languages['th_TH']['NAME'] = 'Thai';
574 $languages['th_TH']['CHARSET'] = 'tis-620';
575 $languages['th_TH']['LOCALE'] = 'th_TH.TIS-620';
576 $languages['th']['ALIAS'] = 'th_TH';
578 $languages['tl_PH']['NAME'] = 'Tagalog';
579 $languages['tl_PH']['CHARSET'] = 'iso-8859-1';
580 $languages['tl_PH']['LOCALE'] = 'tl_PH.ISO8859-1';
581 $languages['tl']['ALIAS'] = 'tl_PH';
583 $languages['tr_TR']['NAME'] = 'Turkish';
584 $languages['tr_TR']['CHARSET'] = 'iso-8859-9';
585 $languages['tr_TR']['LOCALE'] = 'tr_TR.ISO8859-9';
586 $languages['tr']['ALIAS'] = 'tr_TR';
588 $languages['zh_TW']['NAME'] = 'Chinese Trad';
589 $languages['zh_TW']['CHARSET'] = 'big5';
590 $languages['zh_TW']['LOCALE'] = 'zh_TW.BIG5';
591 $languages['tw']['ALIAS'] = 'zh_TW';
593 $languages['zh_CN']['NAME'] = 'Chinese Simp';
594 $languages['zh_CN']['CHARSET'] = 'gb2312';
595 $languages['zh_CN']['LOCALE'] = 'zh_CN.GB2312';
596 $languages['cn']['ALIAS'] = 'zh_CN';
598 $languages['uk_UA']['NAME'] = 'Ukrainian';
599 $languages['uk_UA']['CHARSET'] = 'koi8-u';
600 $languages['uk_UA']['LOCALE'] = 'uk_UA.KOI8-U';
601 $languages['uk']['ALIAS'] = 'uk_UA';
603 $languages['ru_UA']['NAME'] = 'Russian (Ukrainian)';
604 $languages['ru_UA']['CHARSET'] = 'koi8-r';
605 $languages['ru_UA']['LOCALE'] = 'ru_UA.KOI8-R';
608 $languages['vi_VN']['NAME'] = 'Vietnamese';
609 $languages['vi_VN']['CHARSET'] = 'utf-8';
610 $languages['vi']['ALIAS'] = 'vi_VN';
613 // Right to left languages
614 $languages['ar']['NAME'] = 'Arabic';
615 $languages['ar']['CHARSET'] = 'windows-1256';
616 $languages['ar']['DIR'] = 'rtl';
618 $languages['fa_IR']['NAME'] = 'Farsi';
619 $languages['fa_IR']['CHARSET'] = 'utf-8';
620 $languages['fa_IR']['DIR'] = 'rtl';
621 $languages['fa_IR']['LOCALE'] = 'fa_IR.UTF-8';
622 $languages['fa']['ALIAS'] = 'fa_IR';
624 $languages['he_IL']['NAME'] = 'Hebrew';
625 $languages['he_IL']['CHARSET'] = 'windows-1255';
626 $languages['he_IL']['LOCALE'] = 'he_IL.CP1255';
627 $languages['he_IL']['DIR'] = 'rtl';
628 $languages['he']['ALIAS'] = 'he_IL';
630 $languages['ug']['NAME'] = 'Uighur';
631 $languages['ug']['CHARSET'] = 'utf-8';
632 $languages['ug']['DIR'] = 'rtl';
634 /* Detect whether gettext is installed. */
636 if (function_exists('_')) {
639 if (function_exists('bindtextdomain')) {
642 if (function_exists('textdomain')) {
646 /* If gettext is fully loaded, cool */
647 if ($gettext_flags == 7) {
650 /* If we can fake gettext, try that */
651 elseif ($gettext_flags == 0) {
653 include_once(SM_PATH
. 'functions/gettext.php');
655 /* Uh-ho. A weird install */
656 if (! $gettext_flags & 1) {
658 * Function is used as replacement in broken installs
665 if (! $gettext_flags & 2) {
667 * Function is used as replacement in broken installs
670 function bindtextdomain() {
674 if (! $gettext_flags & 4) {
676 * Function is used as replacemet in broken installs
679 function textdomain() {
687 * Japanese charset extra function
689 * Action performed by function is defined by first argument.
690 * Default return value is defined by second argument.
691 * Use of third argument depends on action.
693 * @param string $action action performed by this function.
695 * decode - convert returned string to euc-jp. third argument unused
696 * encode - convert returned string to jis. third argument unused
697 * strimwidth - third argument=$width. trims string to $width symbols.
698 * encodeheader - create base64 encoded header in iso-2022-jp. third argument unused
699 * decodeheader - return human readable string from mime header. string is returned in euc-jp. third argument unused
700 * downloadfilename - third argument $useragent. Arguments provide browser info. Returns shift-jis or euc-jp encoded file name
701 * wordwrap - third argument=$wrap. wraps text at $wrap symbols
702 * utf7-imap_encode - returns string converted from euc-jp to utf7-imap. third argument unused
703 * utf7-imap_decode - returns string converted from utf7-imap to euc-jp. third argument unused
704 * @param string $ret default return value
706 function japanese_xtra() {
707 $ret = func_get_arg(1); /* default return value */
708 if (function_exists('mb_detect_encoding')) {
709 switch (func_get_arg(0)) { /* action */
711 $detect_encoding = @mb_detect_encoding
($ret);
712 if ($detect_encoding == 'JIS' ||
713 $detect_encoding == 'EUC-JP' ||
714 $detect_encoding == 'SJIS' ||
715 $detect_encoding == 'UTF-8') {
717 $ret = mb_convert_kana(mb_convert_encoding($ret, 'EUC-JP', 'AUTO'), "KV");
721 $detect_encoding = @mb_detect_encoding
($ret);
722 if ($detect_encoding == 'JIS' ||
723 $detect_encoding == 'EUC-JP' ||
724 $detect_encoding == 'SJIS' ||
725 $detect_encoding == 'UTF-8') {
727 $ret = mb_convert_encoding(mb_convert_kana($ret, "KV"), 'JIS', 'AUTO');
731 $width = func_get_arg(2);
732 $ret = mb_strimwidth($ret, 0, $width, '...');
736 if (strlen($ret) > 0) {
737 $tmpstr = mb_substr($ret, 0, 1);
738 $prevcsize = strlen($tmpstr);
739 for ($i = 1; $i < mb_strlen($ret); $i++
) {
740 $tmp = mb_substr($ret, $i, 1);
741 if (strlen($tmp) == $prevcsize) {
744 if ($prevcsize == 1) {
747 $result .= str_replace(' ', '',
748 mb_encode_mimeheader($tmpstr,'iso-2022-jp','B',''));
751 $prevcsize = strlen($tmp);
754 if (strlen($tmpstr)) {
755 if (strlen(mb_substr($tmpstr, 0, 1)) == 1)
758 $result .= str_replace(' ', '',
759 mb_encode_mimeheader($tmpstr,'iso-2022-jp','B',''));
765 $ret = str_replace("\t", "", $ret);
766 if (eregi('=\\?([^?]+)\\?(q|b)\\?([^?]+)\\?=', $ret))
767 $ret = @mb_decode_mimeheader
($ret);
768 $ret = @mb_convert_encoding
($ret, 'EUC-JP', 'AUTO');
770 case 'downloadfilename':
771 $useragent = func_get_arg(2);
772 if (strstr($useragent, 'Windows') !== false ||
773 strstr($useragent, 'Mac_') !== false) {
774 $ret = mb_convert_encoding($ret, 'SJIS', 'AUTO');
776 $ret = mb_convert_encoding($ret, 'EUC-JP', 'AUTO');
780 $no_begin = "\x21\x25\x29\x2c\x2e\x3a\x3b\x3f\x5d\x7d\xa1\xf1\xa1\xeb\xa1" .
781 "\xc7\xa1\xc9\xa2\xf3\xa1\xec\xa1\xed\xa1\xee\xa1\xa2\xa1\xa3\xa1\xb9" .
782 "\xa1\xd3\xa1\xd5\xa1\xd7\xa1\xd9\xa1\xdb\xa1\xcd\xa4\xa1\xa4\xa3\xa4" .
783 "\xa5\xa4\xa7\xa4\xa9\xa4\xc3\xa4\xe3\xa4\xe5\xa4\xe7\xa4\xee\xa1\xab" .
784 "\xa1\xac\xa1\xb5\xa1\xb6\xa5\xa1\xa5\xa3\xa5\xa5\xa5\xa7\xa5\xa9\xa5" .
785 "\xc3\xa5\xe3\xa5\xe5\xa5\xe7\xa5\xee\xa5\xf5\xa5\xf6\xa1\xa6\xa1\xbc" .
786 "\xa1\xb3\xa1\xb4\xa1\xaa\xa1\xf3\xa1\xcb\xa1\xa4\xa1\xa5\xa1\xa7\xa1" .
787 "\xa8\xa1\xa9\xa1\xcf\xa1\xd1";
788 $no_end = "\x5c\x24\x28\x5b\x7b\xa1\xf2\x5c\xa1\xc6\xa1\xc8\xa1\xd2\xa1" .
789 "\xd4\xa1\xd6\xa1\xd8\xa1\xda\xa1\xcc\xa1\xf0\xa1\xca\xa1\xce\xa1\xd0\xa1\xef";
790 $wrap = func_get_arg(2);
792 if (strlen($ret) >= $wrap &&
793 substr($ret, 0, 1) != '>' &&
794 strpos($ret, 'http://') === FALSE &&
795 strpos($ret, 'https://') === FALSE &&
796 strpos($ret, 'ftp://') === FALSE) {
798 $ret = mb_convert_kana($ret, "KV");
803 while ($ptr < strlen($ret) - 1) {
804 $l = mb_strcut($ret, $ptr, $wrap);
808 $l = mb_strcut($ret, $ptr, 2);
809 while (strlen($l) != 0 && mb_strpos($no_begin, $l) !== FALSE ) {
812 $l = mb_strcut($ret, $ptr, 1);
815 if ($ptr < strlen($ret) - 1)
821 case 'utf7-imap_encode':
822 $ret = mb_convert_encoding($ret, 'UTF7-IMAP', 'EUC-JP');
824 case 'utf7-imap_decode':
825 $ret = mb_convert_encoding($ret, 'EUC-JP', 'UTF7-IMAP');
832 /**************************
833 * Japanese extra functions
834 **************************/
837 * Japanese decoding function
839 * converts string to euc-jp, if string uses JIS, EUC-JP, ShiftJIS or UTF-8
840 * charset. Needs mbstring support in php.
841 * @param string $ret text, that has to be converted
842 * @return string converted string
845 function japanese_xtra_decode($ret) {
846 if (function_exists('mb_detect_encoding')) {
847 $detect_encoding = @mb_detect_encoding
($ret);
848 if ($detect_encoding == 'JIS' ||
849 $detect_encoding == 'EUC-JP' ||
850 $detect_encoding == 'SJIS' ||
851 $detect_encoding == 'UTF-8') {
853 $ret = mb_convert_kana(mb_convert_encoding($ret, 'EUC-JP', 'AUTO'), "KV");
860 * Japanese encoding function
862 * converts string to jis, if string uses JIS, EUC-JP, ShiftJIS or UTF-8
863 * charset. Needs mbstring support in php.
864 * @param string $ret text, that has to be converted
865 * @return string converted text
868 function japanese_xtra_encode($ret) {
869 if (function_exists('mb_detect_encoding')) {
870 $detect_encoding = @mb_detect_encoding
($ret);
871 if ($detect_encoding == 'JIS' ||
872 $detect_encoding == 'EUC-JP' ||
873 $detect_encoding == 'SJIS' ||
874 $detect_encoding == 'UTF-8') {
876 $ret = mb_convert_encoding(mb_convert_kana($ret, "KV"), 'JIS', 'AUTO');
883 * Japanese header encoding function
885 * creates base64 encoded header in iso-2022-jp charset
886 * @param string $ret text, that has to be converted
887 * @return string mime base64 encoded string
890 function japanese_xtra_encodeheader($ret) {
891 if (function_exists('mb_detect_encoding')) {
893 if (strlen($ret) > 0) {
894 $tmpstr = mb_substr($ret, 0, 1);
895 $prevcsize = strlen($tmpstr);
896 for ($i = 1; $i < mb_strlen($ret); $i++
) {
897 $tmp = mb_substr($ret, $i, 1);
898 if (strlen($tmp) == $prevcsize) {
901 if ($prevcsize == 1) {
904 $result .= str_replace(' ', '',
905 mb_encode_mimeheader($tmpstr,'iso-2022-jp','B',''));
908 $prevcsize = strlen($tmp);
911 if (strlen($tmpstr)) {
912 if (strlen(mb_substr($tmpstr, 0, 1)) == 1)
915 $result .= str_replace(' ', '',
916 mb_encode_mimeheader($tmpstr,'iso-2022-jp','B',''));
925 * Japanese header decoding function
927 * return human readable string from mime header. string is returned in euc-jp
929 * @param string $ret header string
930 * @return string decoded header string
933 function japanese_xtra_decodeheader($ret) {
934 if (function_exists('mb_detect_encoding')) {
935 $ret = str_replace("\t", "", $ret);
936 if (eregi('=\\?([^?]+)\\?(q|b)\\?([^?]+)\\?=', $ret))
937 $ret = @mb_decode_mimeheader
($ret);
938 $ret = @mb_convert_encoding
($ret, 'EUC-JP', 'AUTO');
944 * Japanese downloaded filename processing function
946 * Returns shift-jis or euc-jp encoded file name
947 * @param string $ret string
948 * @param string $useragent browser
949 * @return string converted string
952 function japanese_xtra_downloadfilename($ret,$useragent) {
953 if (function_exists('mb_detect_encoding')) {
954 if (strstr($useragent, 'Windows') !== false ||
955 strstr($useragent, 'Mac_') !== false) {
956 $ret = mb_convert_encoding($ret, 'SJIS', 'AUTO');
958 $ret = mb_convert_encoding($ret, 'EUC-JP', 'AUTO');
965 * Japanese wordwrap function
967 * wraps text at set number of symbols
968 * @param string $ret text
969 * @param integer $wrap number of symbols per line
970 * @return string wrapped text
973 function japanese_xtra_wordwrap($ret,$wrap) {
974 if (function_exists('mb_detect_encoding')) {
975 $no_begin = "\x21\x25\x29\x2c\x2e\x3a\x3b\x3f\x5d\x7d\xa1\xf1\xa1\xeb\xa1" .
976 "\xc7\xa1\xc9\xa2\xf3\xa1\xec\xa1\xed\xa1\xee\xa1\xa2\xa1\xa3\xa1\xb9" .
977 "\xa1\xd3\xa1\xd5\xa1\xd7\xa1\xd9\xa1\xdb\xa1\xcd\xa4\xa1\xa4\xa3\xa4" .
978 "\xa5\xa4\xa7\xa4\xa9\xa4\xc3\xa4\xe3\xa4\xe5\xa4\xe7\xa4\xee\xa1\xab" .
979 "\xa1\xac\xa1\xb5\xa1\xb6\xa5\xa1\xa5\xa3\xa5\xa5\xa5\xa7\xa5\xa9\xa5" .
980 "\xc3\xa5\xe3\xa5\xe5\xa5\xe7\xa5\xee\xa5\xf5\xa5\xf6\xa1\xa6\xa1\xbc" .
981 "\xa1\xb3\xa1\xb4\xa1\xaa\xa1\xf3\xa1\xcb\xa1\xa4\xa1\xa5\xa1\xa7\xa1" .
982 "\xa8\xa1\xa9\xa1\xcf\xa1\xd1";
983 $no_end = "\x5c\x24\x28\x5b\x7b\xa1\xf2\x5c\xa1\xc6\xa1\xc8\xa1\xd2\xa1" .
984 "\xd4\xa1\xd6\xa1\xd8\xa1\xda\xa1\xcc\xa1\xf0\xa1\xca\xa1\xce\xa1\xd0\xa1\xef";
986 if (strlen($ret) >= $wrap &&
987 substr($ret, 0, 1) != '>' &&
988 strpos($ret, 'http://') === FALSE &&
989 strpos($ret, 'https://') === FALSE &&
990 strpos($ret, 'ftp://') === FALSE) {
992 $ret = mb_convert_kana($ret, "KV");
997 while ($ptr < strlen($ret) - 1) {
998 $l = mb_strcut($ret, $ptr, $wrap);
1002 $l = mb_strcut($ret, $ptr, 2);
1003 while (strlen($l) != 0 && mb_strpos($no_begin, $l) !== FALSE ) {
1006 $l = mb_strcut($ret, $ptr, 1);
1009 if ($ptr < strlen($ret) - 1)
1019 * Japanese imap folder name encoding function
1021 * converts folder name from euc-jp to utf7-imap
1022 * @param string $ret folder name
1023 * @return string converted folder name
1026 function japanese_xtra_utf7_imap_encode($ret){
1027 if (function_exists('mb_detect_encoding')) {
1028 $ret = mb_convert_encoding($ret, 'UTF7-IMAP', 'EUC-JP');
1034 * Japanese imap folder name decoding function
1036 * converts folder name from utf7-imap to euc-jp.
1037 * @param string $ret folder name in utf7-imap
1038 * @return string converted folder name
1041 function japanese_xtra_utf7_imap_decode($ret) {
1042 if (function_exists('mb_detect_encoding')) {
1043 $ret = mb_convert_encoding($ret, 'EUC-JP', 'UTF7-IMAP');
1049 * Japanese string trimming function
1051 * trims string to defined number of symbols
1052 * @param string $ret string
1053 * @param integer $width number of symbols
1054 * @return string trimmed string
1057 function japanese_xtra_strimwidth($ret,$width) {
1058 if (function_exists('mb_detect_encoding')) {
1059 $ret = mb_strimwidth($ret, 0, $width, '...');
1064 /********************************
1065 * Korean charset extra functions
1066 ********************************/
1069 * Korean downloaded filename processing functions
1071 * @param string default return value
1074 function korean_xtra_downloadfilename($ret) {
1075 $ret = str_replace("\x0D\x0A", '', $ret); /* Hanmail's CR/LF Clear */
1076 for ($i=0;$i<strlen($ret);$i++
) {
1077 if ($ret[$i] >= "\xA1" && $ret[$i] <= "\xFE") { /* 0xA1 - 0XFE are Valid */
1080 } else if (($ret[$i] >= 'a' && $ret[$i] <= 'z') ||
/* From Original ereg_replace in download.php */
1081 ($ret[$i] >= 'A' && $ret[$i] <= 'Z') ||
1082 ($ret[$i] == '.') ||
($ret[$i] == '-')) {
1092 * Replaces non-braking spaces inserted by some browsers with regular space
1094 * This function can be used to replace non-braking space symbols
1095 * that are inserted in forms by some browsers instead of normal
1098 * @param string $string Text that needs to be cleaned
1099 * @param string $charset Charset used in text
1100 * @return string Cleaned text
1102 function cleanup_nbsp($string,$charset) {
1104 // reduce number of case statements
1105 if (stristr('iso-8859-',substr($charset,0,9))){
1106 $output_charset="iso-8859-x";
1108 if (stristr('windows-125',substr($charset,0,11))){
1109 $output_charset="cp125x";
1111 if (stristr('koi8',substr($charset,0,4))){
1112 $output_charset="koi8-x";
1114 if (! isset($output_charset)){
1115 $output_charset=strtolower($charset);
1118 // where is non-braking space symbol
1119 switch($output_charset):
1132 // don't change string if charset is unmatched
1136 // return space instead of non-braking space.
1137 return str_replace($nbsp,' ',$string);
1141 * Function informs if it is safe to convert given charset to the one that is used by user.
1143 * It is safe to use conversion only if user uses utf-8 encoding and when
1144 * converted charset is similar to the one that is used by user.
1146 * @param string $input_charset Charset of text that needs to be converted
1147 * @return bool is it possible to convert to user's charset
1149 function is_conversion_safe($input_charset) {
1150 global $languages, $sm_notAlias, $default_charset;
1152 // convert to lower case
1153 $input_charset = strtolower($input_charset);
1155 // Is user's locale Unicode based ?
1156 if ( $default_charset == "utf-8" ) {
1160 // Charsets that are similar
1161 switch ($default_charset):
1162 case "windows-1251":
1163 if ( $input_charset == "iso-8859-5" ||
1164 $input_charset == "koi8-r" ||
1165 $input_charset == "koi8-u" ) {
1170 case "windows-1257":
1171 if ( $input_charset == "iso-8859-13" ||
1172 $input_charset == "iso-8859-4" ) {
1178 if ( $input_charset == "iso-8859-13" ||
1179 $input_charset == "windows-1257" ) {
1185 if ( $input_charset == "windows-1251" ||
1186 $input_charset == "koi8-r" ||
1187 $input_charset == "koi8-u" ) {
1193 if ( $input_charset == "iso-8859-4" ||
1194 $input_charset == "windows-1257" ) {
1200 if ( $input_charset == "windows-1251" ||
1201 $input_charset == "iso-8859-5" ||
1202 $input_charset == "koi8-u" ) {
1208 if ( $input_charset == "windows-1251" ||
1209 $input_charset == "iso-8859-5" ||
1210 $input_charset == "koi8-r" ) {