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 * Gettext bindtextdomain wrapper.
26 * Wrapper solves differences between php versions in order to provide
27 * ngettext support. Should be used if translation uses ngettext
29 * @param string $domain gettext domain name
30 * @param string $dir directory that contains all translations
31 * @return string path to translation directory
33 function sq_bindtextdomain($domain,$dir) {
34 global $l10n, $gettext_flags, $sm_notAlias;
36 if ($gettext_flags==7) {
37 // gettext extension without ngettext
38 if (substr($dir, -1) != '/') $dir .= '/';
39 $mofile=$dir . $sm_notAlias . '/LC_MESSAGES/' . $domain . '.mo';
40 $input = new FileReader($mofile);
41 $l10n[$domain] = new gettext_reader($input);
44 $dir=bindtextdomain($domain,$dir);
50 * Gettext textdomain wrapper.
51 * Makes sure that gettext_domain global is modified.
52 * @param string $name gettext domain name
53 * @return string gettext domain name
55 function sq_textdomain($domain) {
56 global $gettext_domain;
57 $gettext_domain=textdomain($domain);
58 return $gettext_domain;
62 * Converts string from given charset to charset, that can be displayed by user translation.
64 * Function by default returns html encoded strings, if translation uses different encoding.
65 * If Japanese translation is used - function returns string converted to euc-jp
66 * If iconv or recode functions are enabled and translation uses utf-8 - function returns utf-8 encoded string.
67 * If $charset is not supported - function returns unconverted string.
69 * sanitizing of html tags is also done by this function.
71 * @param string $charset
72 * @param string $string Text to be decoded
73 * @return string decoded string
75 function charset_decode ($charset, $string) {
76 global $languages, $squirrelmail_language, $default_charset;
77 global $use_php_recode, $use_php_iconv, $aggressive_decoding;
79 if (isset($languages[$squirrelmail_language]['XTRA_CODE']) &&
80 function_exists($languages[$squirrelmail_language]['XTRA_CODE'] . '_decode')) {
81 $string = call_user_func($languages[$squirrelmail_language]['XTRA_CODE'] . '_decode', $string);
84 $charset = strtolower($charset);
88 // Variables that allow to use functions without function_exist() calls
89 if (! isset($use_php_recode) ||
$use_php_recode=="" ) {
90 $use_php_recode=false; }
91 if (! isset($use_php_iconv) ||
$use_php_iconv=="" ) {
92 $use_php_iconv=false; }
94 // Don't do conversion if charset is the same.
95 if ( $charset == strtolower($default_charset) )
96 return htmlspecialchars($string);
98 // catch iso-8859-8-i thing
99 if ( $charset == "iso-8859-8-i" )
100 $charset = "iso-8859-8";
103 * Recode converts html special characters automatically if you use
104 * 'charset..html' decoding. There is no documented way to put -d option
105 * into php recode function call.
107 if ( $use_php_recode ) {
108 if ( $default_charset == "utf-8" ) {
109 // other charsets can be converted to utf-8 without loss.
110 // and output string is smaller
111 $string = recode_string($charset . "..utf-8",$string);
112 return htmlspecialchars($string);
114 $string = recode_string($charset . "..html",$string);
115 // recode does not convert single quote, htmlspecialchars does.
116 $string = str_replace("'", ''', $string);
121 // iconv functions does not have html target and can be used only with utf-8
122 if ( $use_php_iconv && $default_charset=='utf-8') {
123 $string = iconv($charset,$default_charset,$string);
124 return htmlspecialchars($string);
127 // If we don't use recode and iconv, we'll do it old way.
129 /* All HTML special characters are 7 bit and can be replaced first */
131 $string = htmlspecialchars ($string);
133 /* controls cpu and memory intensive decoding cycles */
134 if (! isset($aggressive_decoding) ||
$aggressive_decoding=="" ) {
135 $aggressive_decoding=false; }
137 $decode=fixcharset($charset);
138 $decodefile=SM_PATH
. 'functions/decode/' . $decode . '.php';
139 if (file_exists($decodefile)) {
140 include_once($decodefile);
141 $ret = call_user_func('charset_decode_'.$decode, $string);
149 * Converts html string to given charset
150 * @param string $string
151 * @param string $charset
152 * @param boolean $htmlencode keep htmlspecialchars encoding
155 function charset_encode($string,$charset,$htmlencode=true) {
156 global $default_charset;
158 // Undo html special chars
159 if (! $htmlencode ) {
160 $string = str_replace(array('&','>','<','"'),array('&','>','<','"'),$string);
163 $encode=fixcharset($charset);
164 $encodefile=SM_PATH
. 'functions/encode/' . $encode . '.php';
165 if (file_exists($encodefile)) {
166 include_once($encodefile);
167 $ret = call_user_func('charset_encode_'.$encode, $string);
169 include_once(SM_PATH
. 'functions/encode/us_ascii.php');
170 $ret = charset_encode_us_ascii($string);
176 * Combined decoding and encoding functions
178 * If conversion is done to charset different that utf-8, unsupported symbols
179 * will be replaced with question marks.
180 * @param string $in_charset initial charset
181 * @param string $string string that has to be converted
182 * @param string $out_charset final charset
183 * @param boolean $htmlencode keep htmlspecialchars encoding
184 * @return string converted string
186 function charset_convert($in_charset,$string,$out_charset,$htmlencode=true) {
187 $string=charset_decode($in_charset,$string);
188 $string=charset_encode($string,$out_charset,$htmlencode);
193 * Makes charset name suitable for decoding cycles
195 * @param string $charset Name of charset
196 * @return string $charset Adjusted name of charset
198 function fixcharset($charset) {
199 // minus removed from function names
200 $charset=str_replace('-','_',$charset);
202 // windows-125x and cp125x charsets
203 $charset=str_replace('windows_','cp',$charset);
206 $charset=str_replace('ibm','cp',$charset);
208 // iso-8859-8-i -> iso-8859-8
209 // use same cycle until I'll find differences
210 $charset=str_replace('iso_8859_8_i','iso_8859_8',$charset);
216 * Set up the language to be output
217 * if $do_search is true, then scan the browser information
218 * for a possible language that we know
220 * Function sets system locale environment (LC_ALL, LANG, LANGUAGE),
221 * gettext translation bindings and html header information.
223 * Function returns error codes, if there is some fatal error.
225 * 1 = mbstring support is not present,
226 * 2 = mbstring support is not present, user's translation reverted to en_US.
228 * @param string $sm_language translation used by user's interface
229 * @param bool $do_search use browser's preferred language detection functions. Defaults to false.
230 * @param bool $default set $sm_language to $squirrelmail_default_language if language detection fails or language is not set. Defaults to false.
231 * @return int function execution error codes.
233 function set_up_language($sm_language, $do_search = false, $default = false) {
235 static $SetupAlready = 0;
236 global $use_gettext, $languages,
237 $squirrelmail_language, $squirrelmail_default_language, $default_charset,
238 $sm_notAlias, $username, $data_dir;
244 $SetupAlready = TRUE;
245 sqgetGlobalVar('HTTP_ACCEPT_LANGUAGE', $accept_lang, SQ_SERVER
);
247 if ($do_search && ! $sm_language && isset($accept_lang)) {
248 $sm_language = substr($accept_lang, 0, 2);
251 if ((!$sm_language||
$default) && isset($squirrelmail_default_language)) {
252 $squirrelmail_language = $squirrelmail_default_language;
253 $sm_language = $squirrelmail_default_language;
255 $sm_notAlias = $sm_language;
257 // Catching removed translation
258 // System reverts to English translation if user prefs contain translation
259 // that is not available in $languages array
260 if (!isset($languages[$sm_notAlias])) {
261 $sm_notAlias="en_US";
264 while (isset($languages[$sm_notAlias]['ALIAS'])) {
265 $sm_notAlias = $languages[$sm_notAlias]['ALIAS'];
268 if ( isset($sm_language) &&
270 $sm_language != '' &&
271 isset($languages[$sm_notAlias]['CHARSET']) ) {
272 sq_bindtextdomain( 'squirrelmail', SM_PATH
. 'locale/' );
273 sq_textdomain( 'squirrelmail' );
274 if (function_exists('bind_textdomain_codeset')) {
275 if ($sm_notAlias == 'ja_JP') {
276 bind_textdomain_codeset ("squirrelmail", 'EUC-JP');
278 bind_textdomain_codeset ("squirrelmail", $languages[$sm_notAlias]['CHARSET'] );
281 if (isset($languages[$sm_notAlias]['LOCALE'])){
282 $longlocale=$languages[$sm_notAlias]['LOCALE'];
284 $longlocale=$sm_notAlias;
286 if ( !ini_get('safe_mode') &&
287 getenv( 'LC_ALL' ) != $longlocale ) {
288 putenv( "LC_ALL=$longlocale" );
289 putenv( "LANG=$longlocale" );
290 putenv( "LANGUAGE=$longlocale" );
291 if ($sm_notAlias=='tr_TR') putenv( "LC_CTYPE=C" );
293 setlocale(LC_ALL
, $longlocale);
294 if ($sm_notAlias=='tr_TR') setlocale(LC_CTYPE
,'C');
296 // Set text direction/alignment variables
297 if (isset($languages[$sm_notAlias]['DIR']) &&
298 $languages[$sm_notAlias]['DIR'] == 'rtl') {
301 * @global string $text_direction
303 $text_direction='rtl';
306 * @global string $left_align
311 * @global string $right_align
315 $text_direction='ltr';
317 $right_align='right';
320 $squirrelmail_language = $sm_notAlias;
321 if ($squirrelmail_language == 'ja_JP') {
322 header ('Content-Type: text/html; charset=EUC-JP');
323 if (!function_exists('mb_internal_encoding')) {
324 // Error messages can't be displayed here
326 // Revert to English if possible.
327 if (function_exists('setPref') && $username!='' && $data_dir!="") {
328 setPref($data_dir, $username, 'language', "en_US");
331 // stop further execution in order not to get php errors on mb_internal_encoding().
334 if (function_exists('mb_language')) {
335 mb_language('Japanese');
337 mb_internal_encoding('EUC-JP');
338 mb_http_output('pass');
339 } elseif ($squirrelmail_language == 'en_US') {
340 header( 'Content-Type: text/html; charset=' . $default_charset );
342 header( 'Content-Type: text/html; charset=' . $languages[$sm_notAlias]['CHARSET'] );
349 * Sets default_charset variable according to the one that is used by user's translations.
351 * Function changes global $default_charset variable in order to be sure, that it
352 * contains charset used by user's translation. Sanity of $squirrelmail_default_language
353 * and $default_charset combination provided in SquirrelMail config is also tested.
355 * There can be a $default_charset setting in the
356 * config.php file, but the user may have a different language
357 * selected for a user interface. This function checks the
358 * language selected by the user and tags the outgoing messages
359 * with the appropriate charset corresponding to the language
360 * selection. This is "more right" (tm), than just stamping the
361 * message blindly with the system-wide $default_charset.
363 function set_my_charset(){
364 global $data_dir, $username, $default_charset, $languages, $squirrelmail_default_language;
366 $my_language = getPref($data_dir, $username, 'language');
368 $my_language = $squirrelmail_default_language ;
370 // Catch removed translation
371 if (!isset($languages[$my_language])) {
372 $my_language="en_US";
374 while (isset($languages[$my_language]['ALIAS'])) {
375 $my_language = $languages[$my_language]['ALIAS'];
377 $my_charset = $languages[$my_language]['CHARSET'];
378 if ($my_language!='en_US') {
379 $default_charset = $my_charset;
383 /* ------------------------------ main --------------------------- */
385 global $squirrelmail_language, $languages, $use_gettext;
387 if (! isset($squirrelmail_language)) {
388 $squirrelmail_language = '';
392 * Array specifies the available translations.
394 * Structure of array:
395 * $languages['language']['variable'] = 'value'
397 * Possible 'variable' names:
398 * NAME - Translation name in English
399 * CHARSET - Encoding used by translation
400 * ALIAS - used when 'language' is only short name and 'value' should provide long language name
401 * ALTNAME - Native translation name. Any 8bit symbols must be html encoded.
402 * LOCALE - Full locale name (in xx_XX.charset format)
403 * DIR - Text direction. Used to define Right-to-Left languages. Possible values 'rtl' or 'ltr'. If undefined - defaults to 'ltr'
404 * XTRA_CODE - translation uses special functions. See doc/i18n.txt
406 * Each 'language' definition requires NAME+CHARSET or ALIAS variables.
409 * @global array $languages
411 $languages['bg_BG']['NAME'] = 'Bulgarian';
412 $languages['bg_BG']['ALTNAME'] = 'Български';
413 $languages['bg_BG']['CHARSET'] = 'windows-1251';
414 $languages['bg_BG']['LOCALE'] = 'bg_BG.CP1251';
415 $languages['bg']['ALIAS'] = 'bg_BG';
417 $languages['bn_IN']['NAME'] = 'Bengali';
418 $languages['bn_IN']['CHARSET'] = 'utf-8';
419 $languages['bn_IN']['LOCALE'] = 'bn_IN.UTF-8';
420 $languages['bn']['ALIAS'] = 'bn_IN';
422 $languages['ca_ES']['NAME'] = 'Catalan';
423 $languages['ca_ES']['CHARSET'] = 'iso-8859-1';
424 $languages['ca_ES']['LOCALE'] = 'ca_ES.ISO8859-1';
425 $languages['ca']['ALIAS'] = 'ca_ES';
427 $languages['cs_CZ']['NAME'] = 'Czech';
428 $languages['cs_CZ']['ALTNAME'] = 'Čeština';
429 $languages['cs_CZ']['CHARSET'] = 'iso-8859-2';
430 $languages['cs_CZ']['LOCALE'] = 'cs_CZ.ISO8859-2';
431 $languages['cs']['ALIAS'] = 'cs_CZ';
433 $languages['cy_GB']['NAME'] = 'Welsh';
434 $languages['cy_GB']['ALTNAME'] = 'Cymraeg';
435 $languages['cy_GB']['CHARSET'] = 'iso-8859-1';
436 $languages['cy_GB']['LOCALE'] = 'cy_GB.ISO8859-1';
437 $languages['cy']['ALIAS'] = 'cy_GB';
439 // Danish locale is da_DK.
440 $languages['da_DK']['NAME'] = 'Danish';
441 $languages['da_DK']['ALTNAME'] = 'Dansk';
442 $languages['da_DK']['CHARSET'] = 'iso-8859-1';
443 $languages['da_DK']['LOCALE'] = 'da_DK.ISO8859-1';
444 $languages['da']['ALIAS'] = 'da_DK';
446 $languages['de_DE']['NAME'] = 'German';
447 $languages['de_DE']['ALTNAME'] = 'Deutsch';
448 $languages['de_DE']['CHARSET'] = 'iso-8859-1';
449 $languages['de_DE']['LOCALE'] = 'de_DE.ISO8859-1';
450 $languages['de']['ALIAS'] = 'de_DE';
452 $languages['el_GR']['NAME'] = 'Greek';
453 $languages['el_GR']['ALTNAME'] = 'Ελληνικά';
454 $languages['el_GR']['CHARSET'] = 'iso-8859-7';
455 $languages['el_GR']['LOCALE'] = 'el_GR.ISO8859-7';
456 $languages['el']['ALIAS'] = 'el_GR';
458 $languages['en_GB']['NAME'] = 'British';
459 $languages['en_GB']['CHARSET'] = 'iso-8859-15';
460 $languages['en_GB']['LOCALE'] = 'en_GB.ISO8859-15';
462 $languages['en_US']['NAME'] = 'English';
463 $languages['en_US']['CHARSET'] = 'iso-8859-1';
464 $languages['en_US']['LOCALE'] = 'en_US.ISO8859-1';
465 $languages['en']['ALIAS'] = 'en_US';
467 $languages['es_ES']['NAME'] = 'Spanish';
468 $languages['es_ES']['ALTNAME'] = 'Español';
469 $languages['es_ES']['CHARSET'] = 'iso-8859-1';
470 $languages['es_ES']['LOCALE'] = 'es_ES.ISO8859-1';
471 $languages['es']['ALIAS'] = 'es_ES';
473 $languages['et_EE']['NAME'] = 'Estonian';
474 $languages['et_EE']['CHARSET'] = 'iso-8859-15';
475 $languages['et_EE']['LOCALE'] = 'et_EE.ISO8859-15';
476 $languages['et']['ALIAS'] = 'et_EE';
478 $languages['eu_ES']['NAME'] = 'Basque';
479 $languages['eu_ES']['CHARSET'] = 'iso-8859-1';
480 $languages['eu_ES']['LOCALE'] = 'eu_ES.ISO8859-1';
481 $languages['eu']['ALIAS'] = 'eu_ES';
483 $languages['fo_FO']['NAME'] = 'Faroese';
484 $languages['fo_FO']['CHARSET'] = 'iso-8859-1';
485 $languages['fo_FO']['LOCALE'] = 'fo_FO.ISO8859-1';
486 $languages['fo']['ALIAS'] = 'fo_FO';
488 $languages['fi_FI']['NAME'] = 'Finnish';
489 $languages['fi_FI']['ALTNAME'] = 'Suomi';
490 $languages['fi_FI']['CHARSET'] = 'iso-8859-1';
491 $languages['fi_FI']['LOCALE'] = 'fi_FI.ISO8859-1';
492 $languages['fi']['ALIAS'] = 'fi_FI';
494 $languages['fr_FR']['NAME'] = 'French';
495 $languages['fr_FR']['ALTNAME'] = 'Français';
496 $languages['fr_FR']['CHARSET'] = 'iso-8859-1';
497 $languages['fr_FR']['LOCALE'] = 'fr_FR.ISO8859-1';
498 $languages['fr']['ALIAS'] = 'fr_FR';
500 $languages['hr_HR']['NAME'] = 'Croatian';
501 $languages['hr_HR']['CHARSET'] = 'iso-8859-2';
502 $languages['hr_HR']['LOCALE'] = 'hr_HR.ISO8859-2';
503 $languages['hr']['ALIAS'] = 'hr_HR';
505 $languages['hu_HU']['NAME'] = 'Hungarian';
506 $languages['hu_HU']['ALTNAME'] = 'Magyar';
507 $languages['hu_HU']['CHARSET'] = 'iso-8859-2';
508 $languages['hu_HU']['LOCALE'] = 'hu_HU.ISO8859-2';
509 $languages['hu']['ALIAS'] = 'hu_HU';
511 $languages['id_ID']['NAME'] = 'Indonesian';
512 $languages['id_ID']['ALTNAME'] = 'Bahasa Indonesia';
513 $languages['id_ID']['CHARSET'] = 'iso-8859-1';
514 $languages['id_ID']['LOCALE'] = 'id_ID.ISO8859-1';
515 $languages['id']['ALIAS'] = 'id_ID';
517 $languages['is_IS']['NAME'] = 'Icelandic';
518 $languages['is_IS']['ALTNAME'] = 'Íslenska';
519 $languages['is_IS']['CHARSET'] = 'iso-8859-1';
520 $languages['is_IS']['LOCALE'] = 'is_IS.ISO8859-1';
521 $languages['is']['ALIAS'] = 'is_IS';
523 $languages['it_IT']['NAME'] = 'Italian';
524 $languages['it_IT']['CHARSET'] = 'iso-8859-1';
525 $languages['it_IT']['LOCALE'] = 'it_IT.ISO8859-1';
526 $languages['it']['ALIAS'] = 'it_IT';
528 $languages['ja_JP']['NAME'] = 'Japanese';
529 $languages['ja_JP']['ALTNAME'] = '日本語';
530 $languages['ja_JP']['CHARSET'] = 'iso-2022-jp';
531 $languages['ja_JP']['LOCALE'] = 'ja_JP.EUC-JP';
532 $languages['ja_JP']['XTRA_CODE'] = 'japanese_xtra';
533 $languages['ja']['ALIAS'] = 'ja_JP';
535 $languages['ko_KR']['NAME'] = 'Korean';
536 $languages['ko_KR']['CHARSET'] = 'euc-KR';
537 $languages['ko_KR']['LOCALE'] = 'ko_KR.EUC-KR';
538 $languages['ko_KR']['XTRA_CODE'] = 'korean_xtra';
539 $languages['ko']['ALIAS'] = 'ko_KR';
541 $languages['lt_LT']['NAME'] = 'Lithuanian';
542 $languages['lt_LT']['ALTNAME'] = 'Lietuvių';
543 $languages['lt_LT']['CHARSET'] = 'utf-8';
544 $languages['lt_LT']['LOCALE'] = 'lt_LT.UTF-8';
545 $languages['lt']['ALIAS'] = 'lt_LT';
547 $languages['nl_NL']['NAME'] = 'Dutch';
548 $languages['nl_NL']['ALTNAME'] = 'Nederlands';
549 $languages['nl_NL']['CHARSET'] = 'iso-8859-1';
550 $languages['nl_NL']['LOCALE'] = 'nl_NL.ISO8859-1';
551 $languages['nl']['ALIAS'] = 'nl_NL';
553 $languages['ms_MY']['NAME'] = 'Malay';
554 $languages['ms_MY']['ALTNAME'] = 'Bahasa Melayu';
555 $languages['ms_MY']['CHARSET'] = 'iso-8859-1';
556 $languages['ms_MY']['LOCALE'] = 'ms_MY.ISO8859-1';
557 $languages['my']['ALIAS'] = 'ms_MY';
559 $languages['nb_NO']['NAME'] = 'Norwegian (Bokmål)';
560 $languages['nb_NO']['ALTNAME'] = 'Norsk (Bokmål)';
561 $languages['nb_NO']['CHARSET'] = 'iso-8859-1';
562 $languages['nb_NO']['LOCALE'] = 'nb_NO.ISO8859-1';
563 $languages['nb']['ALIAS'] = 'nb_NO';
565 $languages['nn_NO']['NAME'] = 'Norwegian (Nynorsk)';
566 $languages['nn_NO']['ALTNAME'] = 'Norsk (Nynorsk)';
567 $languages['nn_NO']['CHARSET'] = 'iso-8859-1';
568 $languages['nn_NO']['LOCALE'] = 'nn_NO.ISO8859-1';
570 $languages['pl_PL']['NAME'] = 'Polish';
571 $languages['pl_PL']['ALTNAME'] = 'Polski';
572 $languages['pl_PL']['CHARSET'] = 'iso-8859-2';
573 $languages['pl_PL']['LOCALE'] = 'pl_PL.ISO8859-2';
574 $languages['pl']['ALIAS'] = 'pl_PL';
576 $languages['pt_PT']['NAME'] = 'Portuguese (Portugal)';
577 $languages['pt_PT']['CHARSET'] = 'iso-8859-1';
578 $languages['pt_PT']['LOCALE'] = 'pt_PT.ISO8859-1';
579 $languages['pt']['ALIAS'] = 'pt_PT';
581 $languages['pt_BR']['NAME'] = 'Portuguese (Brazil)';
582 $languages['pt_BR']['ALTNAME'] = 'Português do Brasil';
583 $languages['pt_BR']['CHARSET'] = 'iso-8859-1';
584 $languages['pt_BR']['LOCALE'] = 'pt_BR.ISO8859-1';
586 $languages['ro_RO']['NAME'] = 'Romanian';
587 $languages['ro_RO']['ALTNAME'] = 'Română';
588 $languages['ro_RO']['CHARSET'] = 'iso-8859-2';
589 $languages['ro_RO']['LOCALE'] = 'ro_RO.ISO8859-2';
590 $languages['ro']['ALIAS'] = 'ro_RO';
592 $languages['ru_RU']['NAME'] = 'Russian';
593 $languages['ru_RU']['ALTNAME'] = 'Русский';
594 $languages['ru_RU']['CHARSET'] = 'utf-8';
595 $languages['ru_RU']['LOCALE'] = 'ru_RU.UTF-8';
596 $languages['ru']['ALIAS'] = 'ru_RU';
598 $languages['sk_SK']['NAME'] = 'Slovak';
599 $languages['sk_SK']['CHARSET'] = 'iso-8859-2';
600 $languages['sk_SK']['LOCALE'] = 'sk_SK.ISO8859-2';
601 $languages['sk']['ALIAS'] = 'sk_SK';
603 $languages['sl_SI']['NAME'] = 'Slovenian';
604 $languages['sl_SI']['ALTNAME'] = 'Slovenščina';
605 $languages['sl_SI']['CHARSET'] = 'iso-8859-2';
606 $languages['sl_SI']['LOCALE'] = 'sl_SI.ISO8859-2';
607 $languages['sl']['ALIAS'] = 'sl_SI';
609 $languages['sr_YU']['NAME'] = 'Serbian';
610 $languages['sr_YU']['ALTNAME'] = 'Srpski';
611 $languages['sr_YU']['CHARSET'] = 'iso-8859-2';
612 $languages['sr_YU']['LOCALE'] = 'sr_YU.ISO8859-2';
613 $languages['sr']['ALIAS'] = 'sr_YU';
615 $languages['sv_SE']['NAME'] = 'Swedish';
616 $languages['sv_SE']['ALTNAME'] = 'Svenska';
617 $languages['sv_SE']['CHARSET'] = 'iso-8859-1';
618 $languages['sv_SE']['LOCALE'] = 'sv_SE.ISO8859-1';
619 $languages['sv']['ALIAS'] = 'sv_SE';
621 $languages['th_TH']['NAME'] = 'Thai';
622 $languages['th_TH']['CHARSET'] = 'tis-620';
623 $languages['th_TH']['LOCALE'] = 'th_TH.TIS-620';
624 $languages['th']['ALIAS'] = 'th_TH';
626 $languages['tl_PH']['NAME'] = 'Tagalog';
627 $languages['tl_PH']['CHARSET'] = 'iso-8859-1';
628 $languages['tl_PH']['LOCALE'] = 'tl_PH.ISO8859-1';
629 $languages['tl']['ALIAS'] = 'tl_PH';
631 $languages['tr_TR']['NAME'] = 'Turkish';
632 $languages['tr_TR']['CHARSET'] = 'iso-8859-9';
633 $languages['tr_TR']['LOCALE'] = 'tr_TR.ISO8859-9';
634 $languages['tr']['ALIAS'] = 'tr_TR';
636 $languages['zh_TW']['NAME'] = 'Chinese Trad';
637 $languages['zh_TW']['CHARSET'] = 'big5';
638 $languages['zh_TW']['LOCALE'] = 'zh_TW.BIG5';
639 $languages['tw']['ALIAS'] = 'zh_TW';
641 $languages['zh_CN']['NAME'] = 'Chinese Simp';
642 $languages['zh_CN']['CHARSET'] = 'gb2312';
643 $languages['zh_CN']['LOCALE'] = 'zh_CN.GB2312';
644 $languages['cn']['ALIAS'] = 'zh_CN';
646 $languages['uk_UA']['NAME'] = 'Ukrainian';
647 $languages['uk_UA']['CHARSET'] = 'koi8-u';
648 $languages['uk_UA']['LOCALE'] = 'uk_UA.KOI8-U';
649 $languages['uk']['ALIAS'] = 'uk_UA';
651 $languages['ru_UA']['NAME'] = 'Russian (Ukrainian)';
652 $languages['ru_UA']['CHARSET'] = 'koi8-r';
653 $languages['ru_UA']['LOCALE'] = 'ru_UA.KOI8-R';
656 $languages['vi_VN']['NAME'] = 'Vietnamese';
657 $languages['vi_VN']['CHARSET'] = 'utf-8';
658 $languages['vi']['ALIAS'] = 'vi_VN';
661 // Right to left languages
662 $languages['ar']['NAME'] = 'Arabic';
663 $languages['ar']['CHARSET'] = 'windows-1256';
664 $languages['ar']['DIR'] = 'rtl';
666 $languages['fa_IR']['NAME'] = 'Farsi';
667 $languages['fa_IR']['CHARSET'] = 'utf-8';
668 $languages['fa_IR']['DIR'] = 'rtl';
669 $languages['fa_IR']['LOCALE'] = 'fa_IR.UTF-8';
670 $languages['fa']['ALIAS'] = 'fa_IR';
672 $languages['he_IL']['NAME'] = 'Hebrew';
673 $languages['he_IL']['CHARSET'] = 'windows-1255';
674 $languages['he_IL']['LOCALE'] = 'he_IL.CP1255';
675 $languages['he_IL']['DIR'] = 'rtl';
676 $languages['he']['ALIAS'] = 'he_IL';
678 $languages['ug']['NAME'] = 'Uighur';
679 $languages['ug']['CHARSET'] = 'utf-8';
680 $languages['ug']['DIR'] = 'rtl';
682 /* Detect whether gettext is installed. */
684 if (function_exists('_')) {
687 if (function_exists('bindtextdomain')) {
690 if (function_exists('textdomain')) {
693 if (function_exists('ngettext')) {
697 /* If gettext is fully loaded, cool */
698 if ($gettext_flags == 15) {
702 /* If ngettext support is missing, load it */
703 elseif ($gettext_flags == 7) {
705 // load internal ngettext functions
706 include_once(SM_PATH
. 'class/l10n.class.php');
707 include_once(SM_PATH
. 'functions/ngettext.php');
710 /* If we can fake gettext, try that */
711 elseif ($gettext_flags == 0) {
713 include_once(SM_PATH
. 'functions/gettext.php');
715 /* Uh-ho. A weird install */
716 if (! $gettext_flags & 1) {
718 * Function is used as replacement in broken installs
725 if (! $gettext_flags & 2) {
727 * Function is used as replacement in broken installs
730 function bindtextdomain() {
734 if (! $gettext_flags & 4) {
736 * Function is used as replacemet in broken installs
739 function textdomain() {
743 if (! $gettext_flags & 8) {
745 * Function is used as replacemet in broken installs
748 function ngettext($str,$str2,$number) {
760 * Japanese charset extra function
762 * Action performed by function is defined by first argument.
763 * Default return value is defined by second argument.
764 * Use of third argument depends on action.
766 * @param string $action action performed by this function.
768 * decode - convert returned string to euc-jp. third argument unused
769 * encode - convert returned string to jis. third argument unused
770 * strimwidth - third argument=$width. trims string to $width symbols.
771 * encodeheader - create base64 encoded header in iso-2022-jp. third argument unused
772 * decodeheader - return human readable string from mime header. string is returned in euc-jp. third argument unused
773 * downloadfilename - third argument $useragent. Arguments provide browser info. Returns shift-jis or euc-jp encoded file name
774 * wordwrap - third argument=$wrap. wraps text at $wrap symbols
775 * utf7-imap_encode - returns string converted from euc-jp to utf7-imap. third argument unused
776 * utf7-imap_decode - returns string converted from utf7-imap to euc-jp. third argument unused
777 * @param string $ret default return value
779 function japanese_xtra() {
780 $ret = func_get_arg(1); /* default return value */
781 if (function_exists('mb_detect_encoding')) {
782 switch (func_get_arg(0)) { /* action */
784 $detect_encoding = @mb_detect_encoding
($ret);
785 if ($detect_encoding == 'JIS' ||
786 $detect_encoding == 'EUC-JP' ||
787 $detect_encoding == 'SJIS' ||
788 $detect_encoding == 'UTF-8') {
790 $ret = mb_convert_kana(mb_convert_encoding($ret, 'EUC-JP', 'AUTO'), "KV");
794 $detect_encoding = @mb_detect_encoding
($ret);
795 if ($detect_encoding == 'JIS' ||
796 $detect_encoding == 'EUC-JP' ||
797 $detect_encoding == 'SJIS' ||
798 $detect_encoding == 'UTF-8') {
800 $ret = mb_convert_encoding(mb_convert_kana($ret, "KV"), 'JIS', 'AUTO');
804 $width = func_get_arg(2);
805 $ret = mb_strimwidth($ret, 0, $width, '...');
809 if (strlen($ret) > 0) {
810 $tmpstr = mb_substr($ret, 0, 1);
811 $prevcsize = strlen($tmpstr);
812 for ($i = 1; $i < mb_strlen($ret); $i++
) {
813 $tmp = mb_substr($ret, $i, 1);
814 if (strlen($tmp) == $prevcsize) {
817 if ($prevcsize == 1) {
820 $result .= str_replace(' ', '',
821 mb_encode_mimeheader($tmpstr,'iso-2022-jp','B',''));
824 $prevcsize = strlen($tmp);
827 if (strlen($tmpstr)) {
828 if (strlen(mb_substr($tmpstr, 0, 1)) == 1)
831 $result .= str_replace(' ', '',
832 mb_encode_mimeheader($tmpstr,'iso-2022-jp','B',''));
838 $ret = str_replace("\t", "", $ret);
839 if (eregi('=\\?([^?]+)\\?(q|b)\\?([^?]+)\\?=', $ret))
840 $ret = @mb_decode_mimeheader
($ret);
841 $ret = @mb_convert_encoding
($ret, 'EUC-JP', 'AUTO');
843 case 'downloadfilename':
844 $useragent = func_get_arg(2);
845 if (strstr($useragent, 'Windows') !== false ||
846 strstr($useragent, 'Mac_') !== false) {
847 $ret = mb_convert_encoding($ret, 'SJIS', 'AUTO');
849 $ret = mb_convert_encoding($ret, 'EUC-JP', 'AUTO');
853 $no_begin = "\x21\x25\x29\x2c\x2e\x3a\x3b\x3f\x5d\x7d\xa1\xf1\xa1\xeb\xa1" .
854 "\xc7\xa1\xc9\xa2\xf3\xa1\xec\xa1\xed\xa1\xee\xa1\xa2\xa1\xa3\xa1\xb9" .
855 "\xa1\xd3\xa1\xd5\xa1\xd7\xa1\xd9\xa1\xdb\xa1\xcd\xa4\xa1\xa4\xa3\xa4" .
856 "\xa5\xa4\xa7\xa4\xa9\xa4\xc3\xa4\xe3\xa4\xe5\xa4\xe7\xa4\xee\xa1\xab" .
857 "\xa1\xac\xa1\xb5\xa1\xb6\xa5\xa1\xa5\xa3\xa5\xa5\xa5\xa7\xa5\xa9\xa5" .
858 "\xc3\xa5\xe3\xa5\xe5\xa5\xe7\xa5\xee\xa5\xf5\xa5\xf6\xa1\xa6\xa1\xbc" .
859 "\xa1\xb3\xa1\xb4\xa1\xaa\xa1\xf3\xa1\xcb\xa1\xa4\xa1\xa5\xa1\xa7\xa1" .
860 "\xa8\xa1\xa9\xa1\xcf\xa1\xd1";
861 $no_end = "\x5c\x24\x28\x5b\x7b\xa1\xf2\x5c\xa1\xc6\xa1\xc8\xa1\xd2\xa1" .
862 "\xd4\xa1\xd6\xa1\xd8\xa1\xda\xa1\xcc\xa1\xf0\xa1\xca\xa1\xce\xa1\xd0\xa1\xef";
863 $wrap = func_get_arg(2);
865 if (strlen($ret) >= $wrap &&
866 substr($ret, 0, 1) != '>' &&
867 strpos($ret, 'http://') === FALSE &&
868 strpos($ret, 'https://') === FALSE &&
869 strpos($ret, 'ftp://') === FALSE) {
871 $ret = mb_convert_kana($ret, "KV");
876 while ($ptr < strlen($ret) - 1) {
877 $l = mb_strcut($ret, $ptr, $wrap);
881 $l = mb_strcut($ret, $ptr, 2);
882 while (strlen($l) != 0 && mb_strpos($no_begin, $l) !== FALSE ) {
885 $l = mb_strcut($ret, $ptr, 1);
888 if ($ptr < strlen($ret) - 1)
894 case 'utf7-imap_encode':
895 $ret = mb_convert_encoding($ret, 'UTF7-IMAP', 'EUC-JP');
897 case 'utf7-imap_decode':
898 $ret = mb_convert_encoding($ret, 'EUC-JP', 'UTF7-IMAP');
905 /**************************
906 * Japanese extra functions
907 **************************/
910 * Japanese decoding function
912 * converts string to euc-jp, if string uses JIS, EUC-JP, ShiftJIS or UTF-8
913 * charset. Needs mbstring support in php.
914 * @param string $ret text, that has to be converted
915 * @return string converted string
918 function japanese_xtra_decode($ret) {
919 if (function_exists('mb_detect_encoding')) {
920 $detect_encoding = @mb_detect_encoding
($ret);
921 if ($detect_encoding == 'JIS' ||
922 $detect_encoding == 'EUC-JP' ||
923 $detect_encoding == 'SJIS' ||
924 $detect_encoding == 'UTF-8') {
926 $ret = mb_convert_kana(mb_convert_encoding($ret, 'EUC-JP', 'AUTO'), "KV");
933 * Japanese encoding function
935 * converts string to jis, if string uses JIS, EUC-JP, ShiftJIS or UTF-8
936 * charset. Needs mbstring support in php.
937 * @param string $ret text, that has to be converted
938 * @return string converted text
941 function japanese_xtra_encode($ret) {
942 if (function_exists('mb_detect_encoding')) {
943 $detect_encoding = @mb_detect_encoding
($ret);
944 if ($detect_encoding == 'JIS' ||
945 $detect_encoding == 'EUC-JP' ||
946 $detect_encoding == 'SJIS' ||
947 $detect_encoding == 'UTF-8') {
949 $ret = mb_convert_encoding(mb_convert_kana($ret, "KV"), 'JIS', 'AUTO');
956 * Japanese header encoding function
958 * creates base64 encoded header in iso-2022-jp charset
959 * @param string $ret text, that has to be converted
960 * @return string mime base64 encoded string
963 function japanese_xtra_encodeheader($ret) {
964 if (function_exists('mb_detect_encoding')) {
966 if (strlen($ret) > 0) {
967 $tmpstr = mb_substr($ret, 0, 1);
968 $prevcsize = strlen($tmpstr);
969 for ($i = 1; $i < mb_strlen($ret); $i++
) {
970 $tmp = mb_substr($ret, $i, 1);
971 if (strlen($tmp) == $prevcsize) {
974 if ($prevcsize == 1) {
977 $result .= str_replace(' ', '',
978 mb_encode_mimeheader($tmpstr,'iso-2022-jp','B',''));
981 $prevcsize = strlen($tmp);
984 if (strlen($tmpstr)) {
985 if (strlen(mb_substr($tmpstr, 0, 1)) == 1)
988 $result .= str_replace(' ', '',
989 mb_encode_mimeheader($tmpstr,'iso-2022-jp','B',''));
998 * Japanese header decoding function
1000 * return human readable string from mime header. string is returned in euc-jp
1002 * @param string $ret header string
1003 * @return string decoded header string
1006 function japanese_xtra_decodeheader($ret) {
1007 if (function_exists('mb_detect_encoding')) {
1008 $ret = str_replace("\t", "", $ret);
1009 if (eregi('=\\?([^?]+)\\?(q|b)\\?([^?]+)\\?=', $ret))
1010 $ret = @mb_decode_mimeheader
($ret);
1011 $ret = @mb_convert_encoding
($ret, 'EUC-JP', 'AUTO');
1017 * Japanese downloaded filename processing function
1019 * Returns shift-jis or euc-jp encoded file name
1020 * @param string $ret string
1021 * @param string $useragent browser
1022 * @return string converted string
1025 function japanese_xtra_downloadfilename($ret,$useragent) {
1026 if (function_exists('mb_detect_encoding')) {
1027 if (strstr($useragent, 'Windows') !== false ||
1028 strstr($useragent, 'Mac_') !== false) {
1029 $ret = mb_convert_encoding($ret, 'SJIS', 'AUTO');
1031 $ret = mb_convert_encoding($ret, 'EUC-JP', 'AUTO');
1038 * Japanese wordwrap function
1040 * wraps text at set number of symbols
1041 * @param string $ret text
1042 * @param integer $wrap number of symbols per line
1043 * @return string wrapped text
1046 function japanese_xtra_wordwrap($ret,$wrap) {
1047 if (function_exists('mb_detect_encoding')) {
1048 $no_begin = "\x21\x25\x29\x2c\x2e\x3a\x3b\x3f\x5d\x7d\xa1\xf1\xa1\xeb\xa1" .
1049 "\xc7\xa1\xc9\xa2\xf3\xa1\xec\xa1\xed\xa1\xee\xa1\xa2\xa1\xa3\xa1\xb9" .
1050 "\xa1\xd3\xa1\xd5\xa1\xd7\xa1\xd9\xa1\xdb\xa1\xcd\xa4\xa1\xa4\xa3\xa4" .
1051 "\xa5\xa4\xa7\xa4\xa9\xa4\xc3\xa4\xe3\xa4\xe5\xa4\xe7\xa4\xee\xa1\xab" .
1052 "\xa1\xac\xa1\xb5\xa1\xb6\xa5\xa1\xa5\xa3\xa5\xa5\xa5\xa7\xa5\xa9\xa5" .
1053 "\xc3\xa5\xe3\xa5\xe5\xa5\xe7\xa5\xee\xa5\xf5\xa5\xf6\xa1\xa6\xa1\xbc" .
1054 "\xa1\xb3\xa1\xb4\xa1\xaa\xa1\xf3\xa1\xcb\xa1\xa4\xa1\xa5\xa1\xa7\xa1" .
1055 "\xa8\xa1\xa9\xa1\xcf\xa1\xd1";
1056 $no_end = "\x5c\x24\x28\x5b\x7b\xa1\xf2\x5c\xa1\xc6\xa1\xc8\xa1\xd2\xa1" .
1057 "\xd4\xa1\xd6\xa1\xd8\xa1\xda\xa1\xcc\xa1\xf0\xa1\xca\xa1\xce\xa1\xd0\xa1\xef";
1059 if (strlen($ret) >= $wrap &&
1060 substr($ret, 0, 1) != '>' &&
1061 strpos($ret, 'http://') === FALSE &&
1062 strpos($ret, 'https://') === FALSE &&
1063 strpos($ret, 'ftp://') === FALSE) {
1065 $ret = mb_convert_kana($ret, "KV");
1070 while ($ptr < strlen($ret) - 1) {
1071 $l = mb_strcut($ret, $ptr, $wrap);
1075 $l = mb_strcut($ret, $ptr, 2);
1076 while (strlen($l) != 0 && mb_strpos($no_begin, $l) !== FALSE ) {
1079 $l = mb_strcut($ret, $ptr, 1);
1082 if ($ptr < strlen($ret) - 1)
1092 * Japanese imap folder name encoding function
1094 * converts folder name from euc-jp to utf7-imap
1095 * @param string $ret folder name
1096 * @return string converted folder name
1099 function japanese_xtra_utf7_imap_encode($ret){
1100 if (function_exists('mb_detect_encoding')) {
1101 $ret = mb_convert_encoding($ret, 'UTF7-IMAP', 'EUC-JP');
1107 * Japanese imap folder name decoding function
1109 * converts folder name from utf7-imap to euc-jp.
1110 * @param string $ret folder name in utf7-imap
1111 * @return string converted folder name
1114 function japanese_xtra_utf7_imap_decode($ret) {
1115 if (function_exists('mb_detect_encoding')) {
1116 $ret = mb_convert_encoding($ret, 'EUC-JP', 'UTF7-IMAP');
1122 * Japanese string trimming function
1124 * trims string to defined number of symbols
1125 * @param string $ret string
1126 * @param integer $width number of symbols
1127 * @return string trimmed string
1130 function japanese_xtra_strimwidth($ret,$width) {
1131 if (function_exists('mb_detect_encoding')) {
1132 $ret = mb_strimwidth($ret, 0, $width, '...');
1137 /********************************
1138 * Korean charset extra functions
1139 ********************************/
1142 * Korean downloaded filename processing functions
1144 * @param string default return value
1147 function korean_xtra_downloadfilename($ret) {
1148 $ret = str_replace("\x0D\x0A", '', $ret); /* Hanmail's CR/LF Clear */
1149 for ($i=0;$i<strlen($ret);$i++
) {
1150 if ($ret[$i] >= "\xA1" && $ret[$i] <= "\xFE") { /* 0xA1 - 0XFE are Valid */
1153 } else if (($ret[$i] >= 'a' && $ret[$i] <= 'z') ||
/* From Original ereg_replace in download.php */
1154 ($ret[$i] >= 'A' && $ret[$i] <= 'Z') ||
1155 ($ret[$i] == '.') ||
($ret[$i] == '-')) {
1165 * Replaces non-braking spaces inserted by some browsers with regular space
1167 * This function can be used to replace non-braking space symbols
1168 * that are inserted in forms by some browsers instead of normal
1171 * @param string $string Text that needs to be cleaned
1172 * @param string $charset Charset used in text
1173 * @return string Cleaned text
1175 function cleanup_nbsp($string,$charset) {
1177 // reduce number of case statements
1178 if (stristr('iso-8859-',substr($charset,0,9))){
1179 $output_charset="iso-8859-x";
1181 if (stristr('windows-125',substr($charset,0,11))){
1182 $output_charset="cp125x";
1184 if (stristr('koi8',substr($charset,0,4))){
1185 $output_charset="koi8-x";
1187 if (! isset($output_charset)){
1188 $output_charset=strtolower($charset);
1191 // where is non-braking space symbol
1192 switch($output_charset):
1205 // don't change string if charset is unmatched
1209 // return space instead of non-braking space.
1210 return str_replace($nbsp,' ',$string);
1214 * Function informs if it is safe to convert given charset to the one that is used by user.
1216 * It is safe to use conversion only if user uses utf-8 encoding and when
1217 * converted charset is similar to the one that is used by user.
1219 * @param string $input_charset Charset of text that needs to be converted
1220 * @return bool is it possible to convert to user's charset
1222 function is_conversion_safe($input_charset) {
1223 global $languages, $sm_notAlias, $default_charset, $lossy_encoding;
1225 if (isset($lossy_encoding) && $lossy_encoding )
1228 // convert to lower case
1229 $input_charset = strtolower($input_charset);
1231 // Is user's locale Unicode based ?
1232 if ( $default_charset == "utf-8" ) {
1236 // Charsets that are similar
1237 switch ($default_charset):
1238 case "windows-1251":
1239 if ( $input_charset == "iso-8859-5" ||
1240 $input_charset == "koi8-r" ||
1241 $input_charset == "koi8-u" ) {
1246 case "windows-1257":
1247 if ( $input_charset == "iso-8859-13" ||
1248 $input_charset == "iso-8859-4" ) {
1254 if ( $input_charset == "iso-8859-13" ||
1255 $input_charset == "windows-1257" ) {
1261 if ( $input_charset == "windows-1251" ||
1262 $input_charset == "koi8-r" ||
1263 $input_charset == "koi8-u" ) {
1269 if ( $input_charset == "iso-8859-4" ||
1270 $input_charset == "windows-1257" ) {
1276 if ( $input_charset == "windows-1251" ||
1277 $input_charset == "iso-8859-5" ||
1278 $input_charset == "koi8-u" ) {
1284 if ( $input_charset == "windows-1251" ||
1285 $input_charset == "iso-8859-5" ||
1286 $input_charset == "koi8-r" ) {