5d5d818ec25745a71791abae5fc681b277863cd5
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, $aggressive_decoding;
41 if (isset($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($aggressive_decoding) ||
$aggressive_decoding=="" ) {
97 $aggressive_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);
131 include_once(SM_PATH
. 'functions/encode/us_ascii.php');
132 $ret = charset_encode_us_ascii($string);
138 * Combined decoding and encoding functions
140 * If conversion is done to charset different that utf-8, unsupported symbols
141 * will be replaced with question marks.
142 * @param string $in_charset initial charset
143 * @param string $string string that has to be converted
144 * @param string $out_charset final charset
145 * @param boolean $htmlencode keep htmlspecialchars encoding
146 * @return string converted string
148 function charset_convert($in_charset,$string,$out_charset,$htmlencode=true) {
149 $string=charset_decode($in_charset,$string);
150 $string=charset_encode($string,$out_charset,$htmlencode);
155 * Makes charset name suitable for decoding cycles
157 * @param string $charset Name of charset
158 * @return string $charset Adjusted name of charset
160 function fixcharset($charset) {
161 // minus removed from function names
162 $charset=str_replace('-','_',$charset);
164 // windows-125x and cp125x charsets
165 $charset=str_replace('windows_','cp',$charset);
168 $charset=str_replace('ibm','cp',$charset);
170 // iso-8859-8-i -> iso-8859-8
171 // use same cycle until I'll find differences
172 $charset=str_replace('iso_8859_8_i','iso_8859_8',$charset);
178 * Set up the language to be output
179 * if $do_search is true, then scan the browser information
180 * for a possible language that we know
182 * Function sets system locale environment (LC_ALL, LANG, LANGUAGE),
183 * gettext translation bindings and html header information.
185 * Function returns error codes, if there is some fatal error.
187 * 1 = mbstring support is not present,
188 * 2 = mbstring support is not present, user's translation reverted to en_US.
190 * @param string $sm_language translation used by user's interface
191 * @param bool $do_search use browser's preferred language detection functions. Defaults to false.
192 * @param bool $default set $sm_language to $squirrelmail_default_language if language detection fails or language is not set. Defaults to false.
193 * @return int function execution error codes.
195 function set_up_language($sm_language, $do_search = false, $default = false) {
197 static $SetupAlready = 0;
198 global $use_gettext, $languages,
199 $squirrelmail_language, $squirrelmail_default_language, $default_charset,
200 $sm_notAlias, $username, $data_dir;
206 $SetupAlready = TRUE;
207 sqgetGlobalVar('HTTP_ACCEPT_LANGUAGE', $accept_lang, SQ_SERVER
);
209 if ($do_search && ! $sm_language && isset($accept_lang)) {
210 $sm_language = substr($accept_lang, 0, 2);
213 if ((!$sm_language||
$default) && isset($squirrelmail_default_language)) {
214 $squirrelmail_language = $squirrelmail_default_language;
215 $sm_language = $squirrelmail_default_language;
217 $sm_notAlias = $sm_language;
219 // Catching removed translation
220 // System reverts to English translation if user prefs contain translation
221 // that is not available in $languages array
222 if (!isset($languages[$sm_notAlias])) {
223 $sm_notAlias="en_US";
226 while (isset($languages[$sm_notAlias]['ALIAS'])) {
227 $sm_notAlias = $languages[$sm_notAlias]['ALIAS'];
230 if ( isset($sm_language) &&
232 $sm_language != '' &&
233 isset($languages[$sm_notAlias]['CHARSET']) ) {
234 bindtextdomain( 'squirrelmail', SM_PATH
. 'locale/' );
235 textdomain( 'squirrelmail' );
236 if (function_exists('bind_textdomain_codeset')) {
237 if ($sm_notAlias == 'ja_JP') {
238 bind_textdomain_codeset ("squirrelmail", 'EUC-JP');
240 bind_textdomain_codeset ("squirrelmail", $languages[$sm_notAlias]['CHARSET'] );
243 if (isset($languages[$sm_notAlias]['LOCALE'])){
244 $longlocale=$languages[$sm_notAlias]['LOCALE'];
246 $longlocale=$sm_notAlias;
248 if ( !ini_get('safe_mode') &&
249 getenv( 'LC_ALL' ) != $longlocale ) {
250 putenv( "LC_ALL=$longlocale" );
251 putenv( "LANG=$longlocale" );
252 putenv( "LANGUAGE=$longlocale" );
254 setlocale(LC_ALL
, $longlocale);
256 // Set text direction/alignment variables
257 if (isset($languages[$sm_notAlias]['DIR']) &&
258 $languages[$sm_notAlias]['DIR'] == 'rtl') {
261 * @global string $text_direction
263 $text_direction='rtl';
266 * @global string $left_align
271 * @global string $right_align
275 $text_direction='ltr';
277 $right_align='right';
280 $squirrelmail_language = $sm_notAlias;
281 if ($squirrelmail_language == 'ja_JP') {
282 header ('Content-Type: text/html; charset=EUC-JP');
283 if (!function_exists('mb_internal_encoding')) {
284 // Error messages can't be displayed here
286 // Revert to English if possible.
287 if (function_exists('setPref') && $username!='' && $data_dir!="") {
288 setPref($data_dir, $username, 'language', "en_US");
291 // stop further execution in order not to get php errors on mb_internal_encoding().
294 if (function_exists('mb_language')) {
295 mb_language('Japanese');
297 mb_internal_encoding('EUC-JP');
298 mb_http_output('pass');
299 } elseif ($squirrelmail_language == 'en_US') {
300 header( 'Content-Type: text/html; charset=' . $default_charset );
302 header( 'Content-Type: text/html; charset=' . $languages[$sm_notAlias]['CHARSET'] );
309 * Sets default_charset variable according to the one that is used by user's translations.
311 * Function changes global $default_charset variable in order to be sure, that it
312 * contains charset used by user's translation. Sanity of $squirrelmail_default_language
313 * and $default_charset combination provided in SquirrelMail config is also tested.
315 * There can be a $default_charset setting in the
316 * config.php file, but the user may have a different language
317 * selected for a user interface. This function checks the
318 * language selected by the user and tags the outgoing messages
319 * with the appropriate charset corresponding to the language
320 * selection. This is "more right" (tm), than just stamping the
321 * message blindly with the system-wide $default_charset.
323 function set_my_charset(){
324 global $data_dir, $username, $default_charset, $languages, $squirrelmail_default_language;
326 $my_language = getPref($data_dir, $username, 'language');
328 $my_language = $squirrelmail_default_language ;
330 // Catch removed translation
331 if (!isset($languages[$my_language])) {
332 $my_language="en_US";
334 while (isset($languages[$my_language]['ALIAS'])) {
335 $my_language = $languages[$my_language]['ALIAS'];
337 $my_charset = $languages[$my_language]['CHARSET'];
338 if ($my_language!='en_US') {
339 $default_charset = $my_charset;
343 /* ------------------------------ main --------------------------- */
345 global $squirrelmail_language, $languages, $use_gettext;
347 if (! isset($squirrelmail_language)) {
348 $squirrelmail_language = '';
352 * Array specifies the available translations.
354 * Structure of array:
355 * $languages['language']['variable'] = 'value'
357 * Possible 'variable' names:
358 * NAME - Translation name in English
359 * CHARSET - Encoding used by translation
360 * ALIAS - used when 'language' is only short name and 'value' should provide long language name
361 * ALTNAME - Native translation name. Any 8bit symbols must be html encoded.
362 * LOCALE - Full locale name (in xx_XX.charset format)
363 * DIR - Text direction. Used to define Right-to-Left languages. Possible values 'rtl' or 'ltr'. If undefined - defaults to 'ltr'
364 * XTRA_CODE - translation uses special functions. See doc/i18n.txt
366 * Each 'language' definition requires NAME+CHARSET or ALIAS variables.
369 * @global array $languages
371 $languages['bg_BG']['NAME'] = 'Bulgarian';
372 $languages['bg_BG']['ALTNAME'] = 'Български';
373 $languages['bg_BG']['CHARSET'] = 'windows-1251';
374 $languages['bg_BG']['LOCALE'] = 'bg_BG.CP1251';
375 $languages['bg']['ALIAS'] = 'bg_BG';
377 $languages['ca_ES']['NAME'] = 'Catalan';
378 $languages['ca_ES']['CHARSET'] = 'iso-8859-1';
379 $languages['ca_ES']['LOCALE'] = 'ca_ES.ISO8859-1';
380 $languages['ca']['ALIAS'] = 'ca_ES';
382 $languages['cs_CZ']['NAME'] = 'Czech';
383 $languages['cs_CZ']['ALTNAME'] = 'Čeština';
384 $languages['cs_CZ']['CHARSET'] = 'iso-8859-2';
385 $languages['cs_CZ']['LOCALE'] = 'cs_CZ.ISO8859-2';
386 $languages['cs']['ALIAS'] = 'cs_CZ';
388 $languages['cy_GB']['NAME'] = 'Welsh';
389 $languages['cy_GB']['ALTNAME'] = 'Cymraeg';
390 $languages['cy_GB']['CHARSET'] = 'iso-8859-1';
391 $languages['cy_GB']['LOCALE'] = 'cy_GB.ISO8859-1';
392 $languages['cy']['ALIAS'] = 'cy_GB';
394 // Danish locale is da_DK.
395 $languages['da_DK']['NAME'] = 'Danish';
396 $languages['da_DK']['ALTNAME'] = 'Dansk';
397 $languages['da_DK']['CHARSET'] = 'iso-8859-1';
398 $languages['da_DK']['LOCALE'] = 'da_DK.ISO8859-1';
399 $languages['da']['ALIAS'] = 'da_DK';
401 $languages['de_DE']['NAME'] = 'German';
402 $languages['de_DE']['ALTNAME'] = 'Deutsch';
403 $languages['de_DE']['CHARSET'] = 'iso-8859-1';
404 $languages['de_DE']['LOCALE'] = 'de_DE.ISO8859-1';
405 $languages['de']['ALIAS'] = 'de_DE';
407 $languages['el_GR']['NAME'] = 'Greek';
408 $languages['el_GR']['ALTNAME'] = 'Ελληνικά';
409 $languages['el_GR']['CHARSET'] = 'iso-8859-7';
410 $languages['el_GR']['LOCALE'] = 'el_GR.ISO8859-7';
411 $languages['el']['ALIAS'] = 'el_GR';
413 $languages['en_GB']['NAME'] = 'British';
414 $languages['en_GB']['CHARSET'] = 'iso-8859-15';
415 $languages['en_GB']['LOCALE'] = 'en_GB.ISO8859-15';
417 $languages['en_US']['NAME'] = 'English';
418 $languages['en_US']['CHARSET'] = 'iso-8859-1';
419 $languages['en_US']['LOCALE'] = 'en_US.ISO8859-1';
420 $languages['en']['ALIAS'] = 'en_US';
422 $languages['es_ES']['NAME'] = 'Spanish';
423 $languages['es_ES']['ALTNAME'] = 'Español';
424 $languages['es_ES']['CHARSET'] = 'iso-8859-1';
425 $languages['es_ES']['LOCALE'] = 'es_ES.ISO8859-1';
426 $languages['es']['ALIAS'] = 'es_ES';
428 $languages['et_EE']['NAME'] = 'Estonian';
429 $languages['et_EE']['CHARSET'] = 'iso-8859-15';
430 $languages['et_EE']['LOCALE'] = 'et_EE.ISO8859-15';
431 $languages['et']['ALIAS'] = 'et_EE';
433 $languages['eu_ES']['NAME'] = 'Basque';
434 $languages['eu_ES']['CHARSET'] = 'iso-8859-1';
435 $languages['eu_ES']['LOCALE'] = 'eu_ES.ISO8859-1';
436 $languages['eu']['ALIAS'] = 'eu_ES';
438 $languages['fo_FO']['NAME'] = 'Faroese';
439 $languages['fo_FO']['CHARSET'] = 'iso-8859-1';
440 $languages['fo_FO']['LOCALE'] = 'fo_FO.ISO8859-1';
441 $languages['fo']['ALIAS'] = 'fo_FO';
443 $languages['fi_FI']['NAME'] = 'Finnish';
444 $languages['fi_FI']['ALTNAME'] = 'Suomi';
445 $languages['fi_FI']['CHARSET'] = 'iso-8859-1';
446 $languages['fi_FI']['LOCALE'] = 'fi_FI.ISO8859-1';
447 $languages['fi']['ALIAS'] = 'fi_FI';
449 $languages['fr_FR']['NAME'] = 'French';
450 $languages['fr_FR']['ALTNAME'] = 'Français';
451 $languages['fr_FR']['CHARSET'] = 'iso-8859-1';
452 $languages['fr_FR']['LOCALE'] = 'fr_FR.ISO8859-1';
453 $languages['fr']['ALIAS'] = 'fr_FR';
455 $languages['hr_HR']['NAME'] = 'Croatian';
456 $languages['hr_HR']['CHARSET'] = 'iso-8859-2';
457 $languages['hr_HR']['LOCALE'] = 'hr_HR.ISO8859-2';
458 $languages['hr']['ALIAS'] = 'hr_HR';
460 $languages['hu_HU']['NAME'] = 'Hungarian';
461 $languages['hu_HU']['ALTNAME'] = 'Magyar';
462 $languages['hu_HU']['CHARSET'] = 'iso-8859-2';
463 $languages['hu_HU']['LOCALE'] = 'hu_HU.ISO8859-2';
464 $languages['hu']['ALIAS'] = 'hu_HU';
466 $languages['id_ID']['NAME'] = 'Indonesian';
467 $languages['id_ID']['ALTNAME'] = 'Bahasa Indonesia';
468 $languages['id_ID']['CHARSET'] = 'iso-8859-1';
469 $languages['id_ID']['LOCALE'] = 'id_ID.ISO8859-1';
470 $languages['id']['ALIAS'] = 'id_ID';
472 $languages['is_IS']['NAME'] = 'Icelandic';
473 $languages['is_IS']['ALTNAME'] = 'Íslenska';
474 $languages['is_IS']['CHARSET'] = 'iso-8859-1';
475 $languages['is_IS']['LOCALE'] = 'is_IS.ISO8859-1';
476 $languages['is']['ALIAS'] = 'is_IS';
478 $languages['it_IT']['NAME'] = 'Italian';
479 $languages['it_IT']['CHARSET'] = 'iso-8859-1';
480 $languages['it_IT']['LOCALE'] = 'it_IT.ISO8859-1';
481 $languages['it']['ALIAS'] = 'it_IT';
483 $languages['ja_JP']['NAME'] = 'Japanese';
484 $languages['ja_JP']['ALTNAME'] = '日本語';
485 $languages['ja_JP']['CHARSET'] = 'iso-2022-jp';
486 $languages['ja_JP']['LOCALE'] = 'ja_JP.EUC-JP';
487 $languages['ja_JP']['XTRA_CODE'] = 'japanese_xtra';
488 $languages['ja']['ALIAS'] = 'ja_JP';
490 $languages['ko_KR']['NAME'] = 'Korean';
491 $languages['ko_KR']['CHARSET'] = 'euc-KR';
492 $languages['ko_KR']['LOCALE'] = 'ko_KR.EUC-KR';
493 $languages['ko_KR']['XTRA_CODE'] = 'korean_xtra';
494 $languages['ko']['ALIAS'] = 'ko_KR';
496 $languages['lt_LT']['NAME'] = 'Lithuanian';
497 $languages['lt_LT']['ALTNAME'] = 'Lietuvių';
498 $languages['lt_LT']['CHARSET'] = 'utf-8';
499 $languages['lt_LT']['LOCALE'] = 'lt_LT.UTF-8';
500 $languages['lt']['ALIAS'] = 'lt_LT';
502 $languages['nl_NL']['NAME'] = 'Dutch';
503 $languages['nl_NL']['ALTNAME'] = 'Nederlands';
504 $languages['nl_NL']['CHARSET'] = 'iso-8859-1';
505 $languages['nl_NL']['LOCALE'] = 'nl_NL.ISO8859-1';
506 $languages['nl']['ALIAS'] = 'nl_NL';
508 $languages['ms_MY']['NAME'] = 'Malay';
509 $languages['ms_MY']['ALTNAME'] = 'Bahasa Melayu';
510 $languages['ms_MY']['CHARSET'] = 'iso-8859-1';
511 $languages['ms_MY']['LOCALE'] = 'ms_MY.ISO8859-1';
512 $languages['my']['ALIAS'] = 'ms_MY';
514 $languages['nb_NO']['NAME'] = 'Norwegian (Bokmål)';
515 $languages['nb_NO']['ALTNAME'] = 'Norsk (Bokmål)';
516 $languages['nb_NO']['CHARSET'] = 'iso-8859-1';
517 $languages['nb_NO']['LOCALE'] = 'nb_NO.ISO8859-1';
518 $languages['nb']['ALIAS'] = 'nb_NO';
520 $languages['nn_NO']['NAME'] = 'Norwegian (Nynorsk)';
521 $languages['nn_NO']['ALTNAME'] = 'Norsk (Nynorsk)';
522 $languages['nn_NO']['CHARSET'] = 'iso-8859-1';
523 $languages['nn_NO']['LOCALE'] = 'nn_NO.ISO8859-1';
525 $languages['pl_PL']['NAME'] = 'Polish';
526 $languages['pl_PL']['ALTNAME'] = 'Polski';
527 $languages['pl_PL']['CHARSET'] = 'iso-8859-2';
528 $languages['pl_PL']['LOCALE'] = 'pl_PL.ISO8859-2';
529 $languages['pl']['ALIAS'] = 'pl_PL';
531 $languages['pt_PT']['NAME'] = 'Portuguese (Portugal)';
532 $languages['pt_PT']['CHARSET'] = 'iso-8859-1';
533 $languages['pt_PT']['LOCALE'] = 'pt_PT.ISO8859-1';
534 $languages['pt']['ALIAS'] = 'pt_PT';
536 $languages['pt_BR']['NAME'] = 'Portuguese (Brazil)';
537 $languages['pt_BR']['ALTNAME'] = 'Português do Brasil';
538 $languages['pt_BR']['CHARSET'] = 'iso-8859-1';
539 $languages['pt_BR']['LOCALE'] = 'pt_BR.ISO8859-1';
541 $languages['ro_RO']['NAME'] = 'Romanian';
542 $languages['ro_RO']['ALTNAME'] = 'Română';
543 $languages['ro_RO']['CHARSET'] = 'iso-8859-2';
544 $languages['ro_RO']['LOCALE'] = 'ro_RO.ISO8859-2';
545 $languages['ro']['ALIAS'] = 'ro_RO';
547 $languages['ru_RU']['NAME'] = 'Russian';
548 $languages['ru_RU']['ALTNAME'] = 'Русский';
549 $languages['ru_RU']['CHARSET'] = 'utf-8';
550 $languages['ru_RU']['LOCALE'] = 'ru_RU.UTF-8';
551 $languages['ru']['ALIAS'] = 'ru_RU';
553 $languages['sk_SK']['NAME'] = 'Slovak';
554 $languages['sk_SK']['CHARSET'] = 'iso-8859-2';
555 $languages['sk_SK']['LOCALE'] = 'sk_SK.ISO8859-2';
556 $languages['sk']['ALIAS'] = 'sk_SK';
558 $languages['sl_SI']['NAME'] = 'Slovenian';
559 $languages['sl_SI']['ALTNAME'] = 'Slovenščina';
560 $languages['sl_SI']['CHARSET'] = 'iso-8859-2';
561 $languages['sl_SI']['LOCALE'] = 'sl_SI.ISO8859-2';
562 $languages['sl']['ALIAS'] = 'sl_SI';
564 $languages['sr_YU']['NAME'] = 'Serbian';
565 $languages['sr_YU']['ALTNAME'] = 'Srpski';
566 $languages['sr_YU']['CHARSET'] = 'iso-8859-2';
567 $languages['sr_YU']['LOCALE'] = 'sr_YU.ISO8859-2';
568 $languages['sr']['ALIAS'] = 'sr_YU';
570 $languages['sv_SE']['NAME'] = 'Swedish';
571 $languages['sv_SE']['ALTNAME'] = 'Svenska';
572 $languages['sv_SE']['CHARSET'] = 'iso-8859-1';
573 $languages['sv_SE']['LOCALE'] = 'sv_SE.ISO8859-1';
574 $languages['sv']['ALIAS'] = 'sv_SE';
576 $languages['th_TH']['NAME'] = 'Thai';
577 $languages['th_TH']['CHARSET'] = 'tis-620';
578 $languages['th_TH']['LOCALE'] = 'th_TH.TIS-620';
579 $languages['th']['ALIAS'] = 'th_TH';
581 $languages['tl_PH']['NAME'] = 'Tagalog';
582 $languages['tl_PH']['CHARSET'] = 'iso-8859-1';
583 $languages['tl_PH']['LOCALE'] = 'tl_PH.ISO8859-1';
584 $languages['tl']['ALIAS'] = 'tl_PH';
586 $languages['tr_TR']['NAME'] = 'Turkish';
587 $languages['tr_TR']['CHARSET'] = 'iso-8859-9';
588 $languages['tr_TR']['LOCALE'] = 'tr_TR.ISO8859-9';
589 $languages['tr']['ALIAS'] = 'tr_TR';
591 $languages['zh_TW']['NAME'] = 'Chinese Trad';
592 $languages['zh_TW']['CHARSET'] = 'big5';
593 $languages['zh_TW']['LOCALE'] = 'zh_TW.BIG5';
594 $languages['tw']['ALIAS'] = 'zh_TW';
596 $languages['zh_CN']['NAME'] = 'Chinese Simp';
597 $languages['zh_CN']['CHARSET'] = 'gb2312';
598 $languages['zh_CN']['LOCALE'] = 'zh_CN.GB2312';
599 $languages['cn']['ALIAS'] = 'zh_CN';
601 $languages['uk_UA']['NAME'] = 'Ukrainian';
602 $languages['uk_UA']['CHARSET'] = 'koi8-u';
603 $languages['uk_UA']['LOCALE'] = 'uk_UA.KOI8-U';
604 $languages['uk']['ALIAS'] = 'uk_UA';
606 $languages['ru_UA']['NAME'] = 'Russian (Ukrainian)';
607 $languages['ru_UA']['CHARSET'] = 'koi8-r';
608 $languages['ru_UA']['LOCALE'] = 'ru_UA.KOI8-R';
611 $languages['vi_VN']['NAME'] = 'Vietnamese';
612 $languages['vi_VN']['CHARSET'] = 'utf-8';
613 $languages['vi']['ALIAS'] = 'vi_VN';
616 // Right to left languages
617 $languages['ar']['NAME'] = 'Arabic';
618 $languages['ar']['CHARSET'] = 'windows-1256';
619 $languages['ar']['DIR'] = 'rtl';
621 $languages['fa_IR']['NAME'] = 'Farsi';
622 $languages['fa_IR']['CHARSET'] = 'utf-8';
623 $languages['fa_IR']['DIR'] = 'rtl';
624 $languages['fa_IR']['LOCALE'] = 'fa_IR.UTF-8';
625 $languages['fa']['ALIAS'] = 'fa_IR';
627 $languages['he_IL']['NAME'] = 'Hebrew';
628 $languages['he_IL']['CHARSET'] = 'windows-1255';
629 $languages['he_IL']['LOCALE'] = 'he_IL.CP1255';
630 $languages['he_IL']['DIR'] = 'rtl';
631 $languages['he']['ALIAS'] = 'he_IL';
633 $languages['ug']['NAME'] = 'Uighur';
634 $languages['ug']['CHARSET'] = 'utf-8';
635 $languages['ug']['DIR'] = 'rtl';
637 /* Detect whether gettext is installed. */
639 if (function_exists('_')) {
642 if (function_exists('bindtextdomain')) {
645 if (function_exists('textdomain')) {
649 /* If gettext is fully loaded, cool */
650 if ($gettext_flags == 7) {
653 /* If we can fake gettext, try that */
654 elseif ($gettext_flags == 0) {
656 include_once(SM_PATH
. 'functions/gettext.php');
658 /* Uh-ho. A weird install */
659 if (! $gettext_flags & 1) {
661 * Function is used as replacement in broken installs
668 if (! $gettext_flags & 2) {
670 * Function is used as replacement in broken installs
673 function bindtextdomain() {
677 if (! $gettext_flags & 4) {
679 * Function is used as replacemet in broken installs
682 function textdomain() {
690 * Japanese charset extra function
692 * Action performed by function is defined by first argument.
693 * Default return value is defined by second argument.
694 * Use of third argument depends on action.
696 * @param string $action action performed by this function.
698 * decode - convert returned string to euc-jp. third argument unused
699 * encode - convert returned string to jis. third argument unused
700 * strimwidth - third argument=$width. trims string to $width symbols.
701 * encodeheader - create base64 encoded header in iso-2022-jp. third argument unused
702 * decodeheader - return human readable string from mime header. string is returned in euc-jp. third argument unused
703 * downloadfilename - third argument $useragent. Arguments provide browser info. Returns shift-jis or euc-jp encoded file name
704 * wordwrap - third argument=$wrap. wraps text at $wrap symbols
705 * utf7-imap_encode - returns string converted from euc-jp to utf7-imap. third argument unused
706 * utf7-imap_decode - returns string converted from utf7-imap to euc-jp. third argument unused
707 * @param string $ret default return value
709 function japanese_xtra() {
710 $ret = func_get_arg(1); /* default return value */
711 if (function_exists('mb_detect_encoding')) {
712 switch (func_get_arg(0)) { /* action */
714 $detect_encoding = @mb_detect_encoding
($ret);
715 if ($detect_encoding == 'JIS' ||
716 $detect_encoding == 'EUC-JP' ||
717 $detect_encoding == 'SJIS' ||
718 $detect_encoding == 'UTF-8') {
720 $ret = mb_convert_kana(mb_convert_encoding($ret, 'EUC-JP', 'AUTO'), "KV");
724 $detect_encoding = @mb_detect_encoding
($ret);
725 if ($detect_encoding == 'JIS' ||
726 $detect_encoding == 'EUC-JP' ||
727 $detect_encoding == 'SJIS' ||
728 $detect_encoding == 'UTF-8') {
730 $ret = mb_convert_encoding(mb_convert_kana($ret, "KV"), 'JIS', 'AUTO');
734 $width = func_get_arg(2);
735 $ret = mb_strimwidth($ret, 0, $width, '...');
739 if (strlen($ret) > 0) {
740 $tmpstr = mb_substr($ret, 0, 1);
741 $prevcsize = strlen($tmpstr);
742 for ($i = 1; $i < mb_strlen($ret); $i++
) {
743 $tmp = mb_substr($ret, $i, 1);
744 if (strlen($tmp) == $prevcsize) {
747 if ($prevcsize == 1) {
750 $result .= str_replace(' ', '',
751 mb_encode_mimeheader($tmpstr,'iso-2022-jp','B',''));
754 $prevcsize = strlen($tmp);
757 if (strlen($tmpstr)) {
758 if (strlen(mb_substr($tmpstr, 0, 1)) == 1)
761 $result .= str_replace(' ', '',
762 mb_encode_mimeheader($tmpstr,'iso-2022-jp','B',''));
768 $ret = str_replace("\t", "", $ret);
769 if (eregi('=\\?([^?]+)\\?(q|b)\\?([^?]+)\\?=', $ret))
770 $ret = @mb_decode_mimeheader
($ret);
771 $ret = @mb_convert_encoding
($ret, 'EUC-JP', 'AUTO');
773 case 'downloadfilename':
774 $useragent = func_get_arg(2);
775 if (strstr($useragent, 'Windows') !== false ||
776 strstr($useragent, 'Mac_') !== false) {
777 $ret = mb_convert_encoding($ret, 'SJIS', 'AUTO');
779 $ret = mb_convert_encoding($ret, 'EUC-JP', 'AUTO');
783 $no_begin = "\x21\x25\x29\x2c\x2e\x3a\x3b\x3f\x5d\x7d\xa1\xf1\xa1\xeb\xa1" .
784 "\xc7\xa1\xc9\xa2\xf3\xa1\xec\xa1\xed\xa1\xee\xa1\xa2\xa1\xa3\xa1\xb9" .
785 "\xa1\xd3\xa1\xd5\xa1\xd7\xa1\xd9\xa1\xdb\xa1\xcd\xa4\xa1\xa4\xa3\xa4" .
786 "\xa5\xa4\xa7\xa4\xa9\xa4\xc3\xa4\xe3\xa4\xe5\xa4\xe7\xa4\xee\xa1\xab" .
787 "\xa1\xac\xa1\xb5\xa1\xb6\xa5\xa1\xa5\xa3\xa5\xa5\xa5\xa7\xa5\xa9\xa5" .
788 "\xc3\xa5\xe3\xa5\xe5\xa5\xe7\xa5\xee\xa5\xf5\xa5\xf6\xa1\xa6\xa1\xbc" .
789 "\xa1\xb3\xa1\xb4\xa1\xaa\xa1\xf3\xa1\xcb\xa1\xa4\xa1\xa5\xa1\xa7\xa1" .
790 "\xa8\xa1\xa9\xa1\xcf\xa1\xd1";
791 $no_end = "\x5c\x24\x28\x5b\x7b\xa1\xf2\x5c\xa1\xc6\xa1\xc8\xa1\xd2\xa1" .
792 "\xd4\xa1\xd6\xa1\xd8\xa1\xda\xa1\xcc\xa1\xf0\xa1\xca\xa1\xce\xa1\xd0\xa1\xef";
793 $wrap = func_get_arg(2);
795 if (strlen($ret) >= $wrap &&
796 substr($ret, 0, 1) != '>' &&
797 strpos($ret, 'http://') === FALSE &&
798 strpos($ret, 'https://') === FALSE &&
799 strpos($ret, 'ftp://') === FALSE) {
801 $ret = mb_convert_kana($ret, "KV");
806 while ($ptr < strlen($ret) - 1) {
807 $l = mb_strcut($ret, $ptr, $wrap);
811 $l = mb_strcut($ret, $ptr, 2);
812 while (strlen($l) != 0 && mb_strpos($no_begin, $l) !== FALSE ) {
815 $l = mb_strcut($ret, $ptr, 1);
818 if ($ptr < strlen($ret) - 1)
824 case 'utf7-imap_encode':
825 $ret = mb_convert_encoding($ret, 'UTF7-IMAP', 'EUC-JP');
827 case 'utf7-imap_decode':
828 $ret = mb_convert_encoding($ret, 'EUC-JP', 'UTF7-IMAP');
835 /**************************
836 * Japanese extra functions
837 **************************/
840 * Japanese decoding function
842 * converts string to euc-jp, if string uses JIS, EUC-JP, ShiftJIS or UTF-8
843 * charset. Needs mbstring support in php.
844 * @param string $ret text, that has to be converted
845 * @return string converted string
848 function japanese_xtra_decode($ret) {
849 if (function_exists('mb_detect_encoding')) {
850 $detect_encoding = @mb_detect_encoding
($ret);
851 if ($detect_encoding == 'JIS' ||
852 $detect_encoding == 'EUC-JP' ||
853 $detect_encoding == 'SJIS' ||
854 $detect_encoding == 'UTF-8') {
856 $ret = mb_convert_kana(mb_convert_encoding($ret, 'EUC-JP', 'AUTO'), "KV");
863 * Japanese encoding function
865 * converts string to jis, if string uses JIS, EUC-JP, ShiftJIS or UTF-8
866 * charset. Needs mbstring support in php.
867 * @param string $ret text, that has to be converted
868 * @return string converted text
871 function japanese_xtra_encode($ret) {
872 if (function_exists('mb_detect_encoding')) {
873 $detect_encoding = @mb_detect_encoding
($ret);
874 if ($detect_encoding == 'JIS' ||
875 $detect_encoding == 'EUC-JP' ||
876 $detect_encoding == 'SJIS' ||
877 $detect_encoding == 'UTF-8') {
879 $ret = mb_convert_encoding(mb_convert_kana($ret, "KV"), 'JIS', 'AUTO');
886 * Japanese header encoding function
888 * creates base64 encoded header in iso-2022-jp charset
889 * @param string $ret text, that has to be converted
890 * @return string mime base64 encoded string
893 function japanese_xtra_encodeheader($ret) {
894 if (function_exists('mb_detect_encoding')) {
896 if (strlen($ret) > 0) {
897 $tmpstr = mb_substr($ret, 0, 1);
898 $prevcsize = strlen($tmpstr);
899 for ($i = 1; $i < mb_strlen($ret); $i++
) {
900 $tmp = mb_substr($ret, $i, 1);
901 if (strlen($tmp) == $prevcsize) {
904 if ($prevcsize == 1) {
907 $result .= str_replace(' ', '',
908 mb_encode_mimeheader($tmpstr,'iso-2022-jp','B',''));
911 $prevcsize = strlen($tmp);
914 if (strlen($tmpstr)) {
915 if (strlen(mb_substr($tmpstr, 0, 1)) == 1)
918 $result .= str_replace(' ', '',
919 mb_encode_mimeheader($tmpstr,'iso-2022-jp','B',''));
928 * Japanese header decoding function
930 * return human readable string from mime header. string is returned in euc-jp
932 * @param string $ret header string
933 * @return string decoded header string
936 function japanese_xtra_decodeheader($ret) {
937 if (function_exists('mb_detect_encoding')) {
938 $ret = str_replace("\t", "", $ret);
939 if (eregi('=\\?([^?]+)\\?(q|b)\\?([^?]+)\\?=', $ret))
940 $ret = @mb_decode_mimeheader
($ret);
941 $ret = @mb_convert_encoding
($ret, 'EUC-JP', 'AUTO');
947 * Japanese downloaded filename processing function
949 * Returns shift-jis or euc-jp encoded file name
950 * @param string $ret string
951 * @param string $useragent browser
952 * @return string converted string
955 function japanese_xtra_downloadfilename($ret,$useragent) {
956 if (function_exists('mb_detect_encoding')) {
957 if (strstr($useragent, 'Windows') !== false ||
958 strstr($useragent, 'Mac_') !== false) {
959 $ret = mb_convert_encoding($ret, 'SJIS', 'AUTO');
961 $ret = mb_convert_encoding($ret, 'EUC-JP', 'AUTO');
968 * Japanese wordwrap function
970 * wraps text at set number of symbols
971 * @param string $ret text
972 * @param integer $wrap number of symbols per line
973 * @return string wrapped text
976 function japanese_xtra_wordwrap($ret,$wrap) {
977 if (function_exists('mb_detect_encoding')) {
978 $no_begin = "\x21\x25\x29\x2c\x2e\x3a\x3b\x3f\x5d\x7d\xa1\xf1\xa1\xeb\xa1" .
979 "\xc7\xa1\xc9\xa2\xf3\xa1\xec\xa1\xed\xa1\xee\xa1\xa2\xa1\xa3\xa1\xb9" .
980 "\xa1\xd3\xa1\xd5\xa1\xd7\xa1\xd9\xa1\xdb\xa1\xcd\xa4\xa1\xa4\xa3\xa4" .
981 "\xa5\xa4\xa7\xa4\xa9\xa4\xc3\xa4\xe3\xa4\xe5\xa4\xe7\xa4\xee\xa1\xab" .
982 "\xa1\xac\xa1\xb5\xa1\xb6\xa5\xa1\xa5\xa3\xa5\xa5\xa5\xa7\xa5\xa9\xa5" .
983 "\xc3\xa5\xe3\xa5\xe5\xa5\xe7\xa5\xee\xa5\xf5\xa5\xf6\xa1\xa6\xa1\xbc" .
984 "\xa1\xb3\xa1\xb4\xa1\xaa\xa1\xf3\xa1\xcb\xa1\xa4\xa1\xa5\xa1\xa7\xa1" .
985 "\xa8\xa1\xa9\xa1\xcf\xa1\xd1";
986 $no_end = "\x5c\x24\x28\x5b\x7b\xa1\xf2\x5c\xa1\xc6\xa1\xc8\xa1\xd2\xa1" .
987 "\xd4\xa1\xd6\xa1\xd8\xa1\xda\xa1\xcc\xa1\xf0\xa1\xca\xa1\xce\xa1\xd0\xa1\xef";
989 if (strlen($ret) >= $wrap &&
990 substr($ret, 0, 1) != '>' &&
991 strpos($ret, 'http://') === FALSE &&
992 strpos($ret, 'https://') === FALSE &&
993 strpos($ret, 'ftp://') === FALSE) {
995 $ret = mb_convert_kana($ret, "KV");
1000 while ($ptr < strlen($ret) - 1) {
1001 $l = mb_strcut($ret, $ptr, $wrap);
1005 $l = mb_strcut($ret, $ptr, 2);
1006 while (strlen($l) != 0 && mb_strpos($no_begin, $l) !== FALSE ) {
1009 $l = mb_strcut($ret, $ptr, 1);
1012 if ($ptr < strlen($ret) - 1)
1022 * Japanese imap folder name encoding function
1024 * converts folder name from euc-jp to utf7-imap
1025 * @param string $ret folder name
1026 * @return string converted folder name
1029 function japanese_xtra_utf7_imap_encode($ret){
1030 if (function_exists('mb_detect_encoding')) {
1031 $ret = mb_convert_encoding($ret, 'UTF7-IMAP', 'EUC-JP');
1037 * Japanese imap folder name decoding function
1039 * converts folder name from utf7-imap to euc-jp.
1040 * @param string $ret folder name in utf7-imap
1041 * @return string converted folder name
1044 function japanese_xtra_utf7_imap_decode($ret) {
1045 if (function_exists('mb_detect_encoding')) {
1046 $ret = mb_convert_encoding($ret, 'EUC-JP', 'UTF7-IMAP');
1052 * Japanese string trimming function
1054 * trims string to defined number of symbols
1055 * @param string $ret string
1056 * @param integer $width number of symbols
1057 * @return string trimmed string
1060 function japanese_xtra_strimwidth($ret,$width) {
1061 if (function_exists('mb_detect_encoding')) {
1062 $ret = mb_strimwidth($ret, 0, $width, '...');
1067 /********************************
1068 * Korean charset extra functions
1069 ********************************/
1072 * Korean downloaded filename processing functions
1074 * @param string default return value
1077 function korean_xtra_downloadfilename($ret) {
1078 $ret = str_replace("\x0D\x0A", '', $ret); /* Hanmail's CR/LF Clear */
1079 for ($i=0;$i<strlen($ret);$i++
) {
1080 if ($ret[$i] >= "\xA1" && $ret[$i] <= "\xFE") { /* 0xA1 - 0XFE are Valid */
1083 } else if (($ret[$i] >= 'a' && $ret[$i] <= 'z') ||
/* From Original ereg_replace in download.php */
1084 ($ret[$i] >= 'A' && $ret[$i] <= 'Z') ||
1085 ($ret[$i] == '.') ||
($ret[$i] == '-')) {
1095 * Replaces non-braking spaces inserted by some browsers with regular space
1097 * This function can be used to replace non-braking space symbols
1098 * that are inserted in forms by some browsers instead of normal
1101 * @param string $string Text that needs to be cleaned
1102 * @param string $charset Charset used in text
1103 * @return string Cleaned text
1105 function cleanup_nbsp($string,$charset) {
1107 // reduce number of case statements
1108 if (stristr('iso-8859-',substr($charset,0,9))){
1109 $output_charset="iso-8859-x";
1111 if (stristr('windows-125',substr($charset,0,11))){
1112 $output_charset="cp125x";
1114 if (stristr('koi8',substr($charset,0,4))){
1115 $output_charset="koi8-x";
1117 if (! isset($output_charset)){
1118 $output_charset=strtolower($charset);
1121 // where is non-braking space symbol
1122 switch($output_charset):
1135 // don't change string if charset is unmatched
1139 // return space instead of non-braking space.
1140 return str_replace($nbsp,' ',$string);
1144 * Function informs if it is safe to convert given charset to the one that is used by user.
1146 * It is safe to use conversion only if user uses utf-8 encoding and when
1147 * converted charset is similar to the one that is used by user.
1149 * @param string $input_charset Charset of text that needs to be converted
1150 * @return bool is it possible to convert to user's charset
1152 function is_conversion_safe($input_charset) {
1153 global $languages, $sm_notAlias, $default_charset, $loosy_encoding;
1155 if (isset($loosy_encoding) && $loosy_encoding )
1158 // convert to lower case
1159 $input_charset = strtolower($input_charset);
1161 // Is user's locale Unicode based ?
1162 if ( $default_charset == "utf-8" ) {
1166 // Charsets that are similar
1167 switch ($default_charset):
1168 case "windows-1251":
1169 if ( $input_charset == "iso-8859-5" ||
1170 $input_charset == "koi8-r" ||
1171 $input_charset == "koi8-u" ) {
1176 case "windows-1257":
1177 if ( $input_charset == "iso-8859-13" ||
1178 $input_charset == "iso-8859-4" ) {
1184 if ( $input_charset == "iso-8859-13" ||
1185 $input_charset == "windows-1257" ) {
1191 if ( $input_charset == "windows-1251" ||
1192 $input_charset == "koi8-r" ||
1193 $input_charset == "koi8-u" ) {
1199 if ( $input_charset == "iso-8859-4" ||
1200 $input_charset == "windows-1257" ) {
1206 if ( $input_charset == "windows-1251" ||
1207 $input_charset == "iso-8859-5" ||
1208 $input_charset == "koi8-u" ) {
1214 if ( $input_charset == "windows-1251" ||
1215 $input_charset == "iso-8859-5" ||
1216 $input_charset == "koi8-r" ) {