functions/i18n.php

   1 <?php
   2
   3 /**
   4  * SquirrelMail internationalization functions
   5  *
   6  * Copyright (c) 1999-2004 The SquirrelMail Project Team
   7  * Licensed under the GNU GPL. For full terms see the file COPYING.
   8  *
   9  * This file contains variuos functions that are needed to do
  10  * internationalization of SquirrelMail.
  11  *
  12  * Internally the output character set is used. Other characters are
  13  * encoded using Unicode entities according to HTML 4.0.
  14  *
  15  * @version $Id$
  16  * @package squirrelmail
  17  * @subpackage i18n
  18  */
  19
  20 /** Everything uses global.php... */
  21 require_once(SM_PATH . 'functions/global.php');
  22
  23 /**
  24  * Converts string from given charset to charset, that can be displayed by user translation.
  25  *
  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.
  30  *
  31  * sanitizing of html tags is also done by this function.
  32  *
  33  * @param string $charset
  34  * @param string $string Text to be decoded
  35  * @return string decoded string
  36  */
  37 function charset_decode ($charset, $string) {
  38     global $languages, $squirrelmail_language, $default_charset;
  39     global $use_php_recode, $use_php_iconv, $agresive_decoding;
  40
  41     if (isset($languages[$squirrelmail_language]['XTRA_CODE']) &&
  42         function_exists($languages[$squirrelmail_language]['XTRA_CODE'])) {
  43         $string = $languages[$squirrelmail_language]['XTRA_CODE']('decode', $string);
  44     }
  45
  46     $charset = strtolower($charset);
  47
  48     set_my_charset();
  49
  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; }
  55
  56     // Don't do conversion if charset is the same.
  57     if ( $charset == strtolower($default_charset) )
  58           return htmlspecialchars($string);
  59
  60     // catch iso-8859-8-i thing
  61     if ( $charset == "iso-8859-8-i" )
  62               $charset = "iso-8859-8";
  63
  64     /*
  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.
  68      */
  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);
  75       } else {
  76         $string = recode_string($charset . "..html",$string);
  77         // recode does not convert single quote, htmlspecialchars does.
  78         $string = str_replace("'", '&#039;', $string);
  79         return $string;
  80       }
  81     }
  82
  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);
  87     }
  88
  89     // If we don't use recode and iconv, we'll do it old way.
  90
  91     /* All HTML special characters are 7 bit and can be replaced first */
  92
  93     $string = htmlspecialchars ($string);
  94
  95     /* controls cpu and memory intensive decoding cycles */
  96     if (! isset($agresive_decoding) || $agresive_decoding=="" ) {
  97          $agresive_decoding=false; }
  98
  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);
 104     } else {
 105       $ret = $string;
 106     }
 107     return( $ret );
 108 }
 109
 110 /**
 111  * Converts html string to given charset
 112  * @param string $string
 113  * @param string $charset
 114  * @param string
 115  */
 116 function charset_encode($string,$charset) {
 117   global $default_charset;
 118
 119   $encode=fixcharset($charset);
 120   $encodefile=SM_PATH . 'functions/encode/' . $encode . '.php';
 121   if (file_exists($encodefile)) {
 122     include_once($encodefile);
 123     $ret = call_user_func('charset_encode_'.$encode, $string);
 124   } else {
 125     $ret = $string;
 126   }
 127   return( $ret );
 128 }
 129
 130 /**
 131  * Combined decoding and encoding functions
 132  *
 133  * If conversion is done to charset different that utf-8, unsupported symbols
 134  * will be replaced with question marks.
 135  * @param string $in_charset initial charset
 136  * @param string $string string that has to be converted
 137  * @param string $out_charset final charset
 138  * @return string converted string
 139  */
 140 function charset_convert($in_charset,$string,$out_charset) {
 141   $string=charset_decode($in_charset,$string);
 142   $string=charset_encode($string,$out_charset);
 143   return $string;
 144 }
 145
 146 /**
 147  * Makes charset name suitable for decoding cycles
 148  *
 149  * @param string $charset Name of charset
 150  * @return string $charset Adjusted name of charset
 151  */
 152 function fixcharset($charset) {
 153     // minus removed from function names
 154     $charset=str_replace('-','_',$charset);
 155
 156     // windows-125x and cp125x charsets
 157     $charset=str_replace('windows_','cp',$charset);
 158
 159     // ibm > cp
 160     $charset=str_replace('ibm','cp',$charset);
 161
 162     // iso-8859-8-i -> iso-8859-8
 163     // use same cycle until I'll find differences
 164     $charset=str_replace('iso_8859_8_i','iso_8859_8',$charset);
 165
 166     return $charset;
 167 }
 168
 169 /**
 170  * Set up the language to be output
 171  * if $do_search is true, then scan the browser information
 172  * for a possible language that we know
 173  *
 174  * Function sets system locale environment (LC_ALL, LANG, LANGUAGE),
 175  * gettext translation bindings and html header information.
 176  *
 177  * Function returns error codes, if there is some fatal error.
 178  *  0 = no error,
 179  *  1 = mbstring support is not present,
 180  *  2 = mbstring support is not present, user's translation reverted to en_US.
 181  *
 182  * @param string $sm_language translation used by user's interface
 183  * @param bool $do_search use browser's preferred language detection functions. Defaults to false.
 184  * @param bool $default set $sm_language to $squirrelmail_default_language if language detection fails or language is not set. Defaults to false.
 185  * @return int function execution error codes.
 186  */
 187 function set_up_language($sm_language, $do_search = false, $default = false) {
 188
 189     static $SetupAlready = 0;
 190     global $use_gettext, $languages,
 191            $squirrelmail_language, $squirrelmail_default_language,
 192            $sm_notAlias, $username, $data_dir;
 193
 194     if ($SetupAlready) {
 195         return;
 196     }
 197
 198     $SetupAlready = TRUE;
 199     sqgetGlobalVar('HTTP_ACCEPT_LANGUAGE',  $accept_lang, SQ_SERVER);
 200
 201     if ($do_search && ! $sm_language && isset($accept_lang)) {
 202         $sm_language = substr($accept_lang, 0, 2);
 203     }
 204
 205     if ((!$sm_language||$default) && isset($squirrelmail_default_language)) {
 206         $squirrelmail_language = $squirrelmail_default_language;
 207         $sm_language = $squirrelmail_default_language;
 208     }
 209     $sm_notAlias = $sm_language;
 210
 211     // Catching removed translation
 212     // System reverts to English translation if user prefs contain translation
 213     // that is not available in $languages array
 214     if (!isset($languages[$sm_notAlias])) {
 215       $sm_notAlias="en_US";
 216     }
 217
 218     while (isset($languages[$sm_notAlias]['ALIAS'])) {
 219         $sm_notAlias = $languages[$sm_notAlias]['ALIAS'];
 220     }
 221
 222     if ( isset($sm_language) &&
 223          $use_gettext &&
 224          $sm_language != '' &&
 225          isset($languages[$sm_notAlias]['CHARSET']) ) {
 226         bindtextdomain( 'squirrelmail', SM_PATH . 'locale/' );
 227         textdomain( 'squirrelmail' );
 228         if (function_exists('bind_textdomain_codeset')) {
 229           if ($sm_notAlias == 'ja_JP') {
 230             bind_textdomain_codeset ("squirrelmail", 'EUC-JP');
 231             } else {
 232               bind_textdomain_codeset ("squirrelmail", $languages[$sm_notAlias]['CHARSET'] );
 233             }
 234         }
 235         if (isset($languages[$sm_notAlias]['LOCALE'])){
 236           $longlocale=$languages[$sm_notAlias]['LOCALE'];
 237         } else {
 238           $longlocale=$sm_notAlias;
 239         }
 240         if ( !ini_get('safe_mode') &&
 241              getenv( 'LC_ALL' ) != $longlocale ) {
 242             putenv( "LC_ALL=$longlocale" );
 243             putenv( "LANG=$longlocale" );
 244             putenv( "LANGUAGE=$longlocale" );
 245         }
 246         setlocale(LC_ALL, $longlocale);
 247
 248         // Set text direction/alignment variables
 249         if (isset($languages[$sm_notAlias]['DIR']) &&
 250             $languages[$sm_notAlias]['DIR'] == 'rtl') {
 251           /**
 252            * Text direction
 253            * @global string $text_direction
 254            */
 255           $text_direction='rtl';
 256           /**
 257            * Left alignment
 258            * @global string $left_align
 259            */
 260           $left_align='right';
 261           /**
 262            * Right alignment
 263            * @global string $right_align
 264            */
 265           $right_align='left';
 266         } else {
 267           $text_direction='ltr';
 268           $left_align='left';
 269           $right_align='right';
 270         }
 271
 272         $squirrelmail_language = $sm_notAlias;
 273         if ($squirrelmail_language == 'ja_JP') {
 274             header ('Content-Type: text/html; charset=EUC-JP');
 275             if (!function_exists('mb_internal_encoding')) {
 276               // Error messages can't be displayed here
 277               $error = 1;
 278               // Revert to English if possible.
 279               if (function_exists('setPref')  && $username!='' && $data_dir!="") {
 280                 setPref($data_dir, $username, 'language', "en_US");
 281                 $error = 2;
 282               }
 283               // stop further execution in order not to get php errors on mb_internal_encoding().
 284               return $error;
 285             }
 286             if (function_exists('mb_language')) {
 287                 mb_language('Japanese');
 288             }
 289             mb_internal_encoding('EUC-JP');
 290             mb_http_output('pass');
 291         } else {
 292         header( 'Content-Type: text/html; charset=' . $languages[$sm_notAlias]['CHARSET'] );
 293     }
 294 }
 295     return 0;
 296 }
 297
 298 /**
 299  * Sets default_charset variable according to the one that is used by user's translations.
 300  *
 301  * Function changes global $default_charset variable in order to be sure, that it
 302  * contains charset used by user's translation. Sanity of $squirrelmail_default_language
 303  * and $default_charset combination provided in SquirrelMail config is also tested.
 304  *
 305  * There can be a $default_charset setting in the
 306  * config.php file, but the user may have a different language
 307  * selected for a user interface. This function checks the
 308  * language selected by the user and tags the outgoing messages
 309  * with the appropriate charset corresponding to the language
 310  * selection. This is "more right" (tm), than just stamping the
 311  * message blindly with the system-wide $default_charset.
 312  */
 313 function set_my_charset(){
 314     global $data_dir, $username, $default_charset, $languages, $squirrelmail_default_language;
 315
 316     $my_language = getPref($data_dir, $username, 'language');
 317     if (!$my_language) {
 318         $my_language = $squirrelmail_default_language ;
 319     }
 320     // Catch removed translation
 321     if (!isset($languages[$my_language])) {
 322       $my_language="en_US";
 323     }
 324     while (isset($languages[$my_language]['ALIAS'])) {
 325         $my_language = $languages[$my_language]['ALIAS'];
 326     }
 327     $my_charset = $languages[$my_language]['CHARSET'];
 328     if ($my_charset) {
 329         $default_charset = $my_charset;
 330     }
 331 }
 332
 333 /* ------------------------------ main --------------------------- */
 334
 335 global $squirrelmail_language, $languages, $use_gettext;
 336
 337 if (! isset($squirrelmail_language)) {
 338     $squirrelmail_language = '';
 339 }
 340
 341 /**
 342  * Array specifies the available translations.
 343  *
 344  * Structure of array:
 345  * $languages['language']['variable'] = 'value'
 346  *
 347  * Possible 'variable' names:
 348  *  NAME      - Translation name in English
 349  *  CHARSET   - Encoding used by translation
 350  *  ALIAS     - used when 'language' is only short name and 'value' should provide long language name
 351  *  ALTNAME   - Native translation name. Any 8bit symbols must be html encoded.
 352  *  LOCALE    - Full locale name (in xx_XX.charset format)
 353  *  DIR       - Text direction. Used to define Right-to-Left languages. Possible values 'rtl' or 'ltr'. If undefined - defaults to 'ltr'
 354  *  XTRA_CODE - translation uses special functions. 'value' provides name of that extra function
 355  *
 356  * Each 'language' definition requires NAME+CHARSET or ALIAS variables.
 357  *
 358  * @name $languages
 359  * @global array $languages
 360  */
 361 $languages['bg_BG']['NAME']    = 'Bulgarian';
 362 $languages['bg_BG']['ALTNAME'] = '&#1041;&#1098;&#1083;&#1075;&#1072;&#1088;&#1089;&#1082;&#1080;';
 363 $languages['bg_BG']['CHARSET'] = 'windows-1251';
 364 $languages['bg_BG']['LOCALE']  = 'bg_BG.CP1251';
 365 $languages['bg']['ALIAS'] = 'bg_BG';
 366
 367 $languages['ca_ES']['NAME']    = 'Catalan';
 368 $languages['ca_ES']['CHARSET'] = 'iso-8859-1';
 369 $languages['ca_ES']['LOCALE']  = 'ca_ES.ISO8859-1';
 370 $languages['ca']['ALIAS'] = 'ca_ES';
 371
 372 $languages['cs_CZ']['NAME']    = 'Czech';
 373 $languages['cs_CZ']['ALTNAME'] = '&#268;e&scaron;tina';
 374 $languages['cs_CZ']['CHARSET'] = 'iso-8859-2';
 375 $languages['cs_CZ']['LOCALE']  = 'cs_CZ.ISO8859-2';
 376 $languages['cs']['ALIAS']      = 'cs_CZ';
 377
 378 $languages['cy_GB']['NAME']    = 'Welsh';
 379 $languages['cy_GB']['ALTNAME'] = 'Cymraeg';
 380 $languages['cy_GB']['CHARSET'] = 'iso-8859-1';
 381 $languages['cy_GB']['LOCALE']  = 'cy_GB.ISO8859-1';
 382 $languages['cy']['ALIAS'] = 'cy_GB';
 383
 384 // Danish locale is da_DK.
 385 $languages['da_DK']['NAME']    = 'Danish';
 386 $languages['da_DK']['ALTNAME'] = 'Dansk';
 387 $languages['da_DK']['CHARSET'] = 'iso-8859-1';
 388 $languages['da_DK']['LOCALE']  = 'da_DK.ISO8859-1';
 389 $languages['da']['ALIAS'] = 'da_DK';
 390
 391 $languages['de_DE']['NAME']    = 'German';
 392 $languages['de_DE']['ALTNAME']    = 'Deutsch';
 393 $languages['de_DE']['CHARSET'] = 'iso-8859-1';
 394 $languages['de_DE']['LOCALE']  = 'de_DE.ISO8859-1';
 395 $languages['de']['ALIAS'] = 'de_DE';
 396
 397 $languages['el_GR']['NAME']    = 'Greek';
 398 $languages['el_GR']['ALTNAME'] = '&Epsilon;&lambda;&lambda;&eta;&nu;&iota;&kappa;&#940;';
 399 $languages['el_GR']['CHARSET'] = 'iso-8859-7';
 400 $languages['el_GR']['LOCALE']  = 'el_GR.ISO8859-7';
 401 $languages['el']['ALIAS'] = 'el_GR';
 402
 403 $languages['en_GB']['NAME']    = 'British';
 404 $languages['en_GB']['CHARSET'] = 'iso-8859-15';
 405 $languages['en_GB']['LOCALE']  = 'en_GB.ISO8859-15';
 406
 407 $languages['en_US']['NAME']    = 'English';
 408 $languages['en_US']['CHARSET'] = 'iso-8859-1';
 409 $languages['en_US']['LOCALE']  = 'en_US.ISO8859-1';
 410 $languages['en']['ALIAS'] = 'en_US';
 411
 412 $languages['es_ES']['NAME']    = 'Spanish';
 413 $languages['es_ES']['ALTNAME'] = 'Espa&ntilde;ol';
 414 $languages['es_ES']['CHARSET'] = 'iso-8859-1';
 415 $languages['es_ES']['LOCALE']  = 'es_ES.ISO8859-1';
 416 $languages['es']['ALIAS'] = 'es_ES';
 417
 418 $languages['et_EE']['NAME']    = 'Estonian';
 419 $languages['et_EE']['CHARSET'] = 'iso-8859-15';
 420 $languages['et_EE']['LOCALE']  = 'et_EE.ISO8859-15';
 421 $languages['et']['ALIAS'] = 'et_EE';
 422
 423 $languages['fo_FO']['NAME']    = 'Faroese';
 424 $languages['fo_FO']['CHARSET'] = 'iso-8859-1';
 425 $languages['fo_FO']['LOCALE']  = 'fo_FO.ISO8859-1';
 426 $languages['fo']['ALIAS'] = 'fo_FO';
 427
 428 $languages['fi_FI']['NAME']    = 'Finnish';
 429 $languages['fi_FI']['ALTNAME'] = 'Suomi';
 430 $languages['fi_FI']['CHARSET'] = 'iso-8859-1';
 431 $languages['fi_FI']['LOCALE']  = 'fi_FI.ISO8859-1';
 432 $languages['fi']['ALIAS'] = 'fi_FI';
 433
 434 $languages['fr_FR']['NAME']    = 'French';
 435 $languages['fr_FR']['ALTNAME'] = 'Fran&#231;ais';
 436 $languages['fr_FR']['CHARSET'] = 'iso-8859-1';
 437 $languages['fr_FR']['LOCALE']  = 'fr_FR.ISO8859-1';
 438 $languages['fr']['ALIAS'] = 'fr_FR';
 439
 440 $languages['hr_HR']['NAME']    = 'Croatian';
 441 $languages['hr_HR']['CHARSET'] = 'iso-8859-2';
 442 $languages['hr_HR']['LOCALE']  = 'hr_HR.ISO8859-2';
 443 $languages['hr']['ALIAS'] = 'hr_HR';
 444
 445 $languages['hu_HU']['NAME']    = 'Hungarian';
 446 $languages['hu_HU']['ALTNAME'] = 'Magyar';
 447 $languages['hu_HU']['CHARSET'] = 'iso-8859-2';
 448 $languages['hu_HU']['LOCALE']  = 'hu_HU.ISO8859-2';
 449 $languages['hu']['ALIAS'] = 'hu_HU';
 450
 451 $languages['id_ID']['NAME']    = 'Indonesian';
 452 $languages['id_ID']['ALTNAME'] = 'Bahasa Indonesia';
 453 $languages['id_ID']['CHARSET'] = 'iso-8859-1';
 454 $languages['id_ID']['LOCALE']  = 'id_ID.ISO8859-1';
 455 $languages['id']['ALIAS'] = 'id_ID';
 456
 457 $languages['is_IS']['NAME']    = 'Icelandic';
 458 $languages['is_IS']['ALTNAME'] = '&Iacute;slenska';
 459 $languages['is_IS']['CHARSET'] = 'iso-8859-1';
 460 $languages['is_IS']['LOCALE']  = 'is_IS.ISO8859-1';
 461 $languages['is']['ALIAS'] = 'is_IS';
 462
 463 $languages['it_IT']['NAME']    = 'Italian';
 464 $languages['it_IT']['CHARSET'] = 'iso-8859-1';
 465 $languages['it_IT']['LOCALE']  = 'it_IT.ISO8859-1';
 466 $languages['it']['ALIAS'] = 'it_IT';
 467
 468 $languages['ja_JP']['NAME']    = 'Japanese';
 469 $languages['ja_JP']['ALTNAME'] = '&#26085;&#26412;&#35486;';
 470 $languages['ja_JP']['CHARSET'] = 'iso-2022-jp';
 471 $languages['ja_JP']['LOCALE'] = 'ja_JP.EUC-JP';
 472 $languages['ja_JP']['XTRA_CODE'] = 'japanese_charset_xtra';
 473 $languages['ja']['ALIAS'] = 'ja_JP';
 474
 475 $languages['ko_KR']['NAME']    = 'Korean';
 476 $languages['ko_KR']['CHARSET'] = 'euc-KR';
 477 $languages['ko_KR']['LOCALE']  = 'ko_KR.EUC-KR';
 478 $languages['ko_KR']['XTRA_CODE'] = 'korean_charset_xtra';
 479 $languages['ko']['ALIAS'] = 'ko_KR';
 480
 481 $languages['lt_LT']['NAME']    = 'Lithuanian';
 482 $languages['lt_LT']['ALTNAME'] = 'Lietuvi&#371;';
 483 $languages['lt_LT']['CHARSET'] = 'utf-8';
 484 $languages['lt_LT']['LOCALE'] = 'lt_LT.UTF-8';
 485 $languages['lt']['ALIAS'] = 'lt_LT';
 486
 487 $languages['nl_NL']['NAME']    = 'Dutch';
 488 $languages['nl_NL']['ALTNAME'] = 'Nederlands';
 489 $languages['nl_NL']['CHARSET'] = 'iso-8859-1';
 490 $languages['nl_NL']['LOCALE']  = 'nl_NL.ISO8859-1';
 491 $languages['nl']['ALIAS'] = 'nl_NL';
 492
 493 $languages['ms_MY']['NAME']    = 'Malay';
 494 $languages['ms_MY']['ALTNAME'] = 'Bahasa Melayu';
 495 $languages['ms_MY']['CHARSET'] = 'iso-8859-1';
 496 $languages['ms_MY']['LOCALE']  = 'ms_MY.ISO8859-1';
 497 $languages['my']['ALIAS'] = 'ms_MY';
 498
 499 $languages['nb_NO']['NAME']    = 'Norwegian (Bokm&aring;l)';
 500 $languages['nb_NO']['ALTNAME'] = 'Norsk (Bokm&aring;l)';
 501 $languages['nb_NO']['CHARSET'] = 'iso-8859-1';
 502 $languages['nb_NO']['LOCALE']  = 'nb_NO.ISO8859-1';
 503 $languages['nb']['ALIAS'] = 'nb_NO';
 504
 505 $languages['nn_NO']['NAME']    = 'Norwegian (Nynorsk)';
 506 $languages['nn_NO']['ALTNAME'] = 'Norsk (Nynorsk)';
 507 $languages['nn_NO']['CHARSET'] = 'iso-8859-1';
 508 $languages['nn_NO']['LOCALE']  = 'nn_NO.ISO8859-1';
 509
 510 $languages['pl_PL']['NAME']    = 'Polish';
 511 $languages['pl_PL']['ALTNAME'] = 'Polski';
 512 $languages['pl_PL']['CHARSET'] = 'iso-8859-2';
 513 $languages['pl_PL']['LOCALE']  = 'pl_PL.ISO8859-2';
 514 $languages['pl']['ALIAS'] = 'pl_PL';
 515
 516 $languages['pt_PT']['NAME'] = 'Portuguese (Portugal)';
 517 $languages['pt_PT']['CHARSET'] = 'iso-8859-1';
 518 $languages['pt_PT']['LOCALE']  = 'pt_PT.ISO8859-1';
 519 $languages['pt']['ALIAS'] = 'pt_PT';
 520
 521 $languages['pt_BR']['NAME']    = 'Portuguese (Brazil)';
 522 $languages['pt_BR']['ALTNAME'] = 'Portugu&ecirc;s do Brasil';
 523 $languages['pt_BR']['CHARSET'] = 'iso-8859-1';
 524 $languages['pt_BR']['LOCALE']  = 'pt_BR.ISO8859-1';
 525
 526 $languages['ro_RO']['NAME']    = 'Romanian';
 527 $languages['ro_RO']['ALTNAME'] = 'Rom&acirc;n&#259;';
 528 $languages['ro_RO']['CHARSET'] = 'iso-8859-2';
 529 $languages['ro_RO']['LOCALE']  = 'ro_RO.ISO8859-2';
 530 $languages['ro']['ALIAS'] = 'ro_RO';
 531
 532 $languages['ru_RU']['NAME']    = 'Russian';
 533 $languages['ru_RU']['ALTNAME'] = '&#1056;&#1091;&#1089;&#1089;&#1082;&#1080;&#1081;';
 534 $languages['ru_RU']['CHARSET'] = 'utf-8';
 535 $languages['ru_RU']['LOCALE']  = 'ru_RU.UTF-8';
 536 $languages['ru']['ALIAS'] = 'ru_RU';
 537
 538 $languages['sk_SK']['NAME']    = 'Slovak';
 539 $languages['sk_SK']['CHARSET'] = 'iso-8859-2';
 540 $languages['sk_SK']['LOCALE']  = 'sk_SK.ISO8859-2';
 541 $languages['sk']['ALIAS'] = 'sk_SK';
 542
 543 $languages['sl_SI']['NAME']    = 'Slovenian';
 544 $languages['sl_SI']['ALTNAME'] = 'Sloven&scaron;&#269;ina';
 545 $languages['sl_SI']['CHARSET'] = 'iso-8859-2';
 546 $languages['sl_SI']['LOCALE']  = 'sl_SI.ISO8859-2';
 547 $languages['sl']['ALIAS'] = 'sl_SI';
 548
 549 $languages['sr_YU']['NAME']    = 'Serbian';
 550 $languages['sr_YU']['ALTNAME'] = 'Srpski';
 551 $languages['sr_YU']['CHARSET'] = 'iso-8859-2';
 552 $languages['sr_YU']['LOCALE']  = 'sr_YU.ISO8859-2';
 553 $languages['sr']['ALIAS'] = 'sr_YU';
 554
 555 $languages['sv_SE']['NAME']    = 'Swedish';
 556 $languages['sv_SE']['ALTNAME'] = 'Svenska';
 557 $languages['sv_SE']['CHARSET'] = 'iso-8859-1';
 558 $languages['sv_SE']['LOCALE']  = 'sv_SE.ISO8859-1';
 559 $languages['sv']['ALIAS'] = 'sv_SE';
 560
 561 $languages['th_TH']['NAME']    = 'Thai';
 562 $languages['th_TH']['CHARSET'] = 'tis-620';
 563 $languages['th_TH']['LOCALE']  = 'th_TH.TIS-620';
 564 $languages['th']['ALIAS'] = 'th_TH';
 565
 566 $languages['tl_PH']['NAME']    = 'Tagalog';
 567 $languages['tl_PH']['CHARSET'] = 'iso-8859-1';
 568 $languages['tl_PH']['LOCALE']  = 'tl_PH.ISO8859-1';
 569 $languages['tl']['ALIAS'] = 'tl_PH';
 570
 571 $languages['tr_TR']['NAME']    = 'Turkish';
 572 $languages['tr_TR']['CHARSET'] = 'iso-8859-9';
 573 $languages['tr_TR']['LOCALE']  = 'tr_TR.ISO8859-9';
 574 $languages['tr']['ALIAS'] = 'tr_TR';
 575
 576 $languages['zh_TW']['NAME']    = 'Chinese Trad';
 577 $languages['zh_TW']['CHARSET'] = 'big5';
 578 $languages['zh_TW']['LOCALE']  = 'zh_TW.BIG5';
 579 $languages['tw']['ALIAS'] = 'zh_TW';
 580
 581 $languages['zh_CN']['NAME']    = 'Chinese Simp';
 582 $languages['zh_CN']['CHARSET'] = 'gb2312';
 583 $languages['zh_CN']['LOCALE']  = 'zh_CN.GB2312';
 584 $languages['cn']['ALIAS'] = 'zh_CN';
 585
 586 $languages['uk_UA']['NAME']    = 'Ukrainian';
 587 $languages['uk_UA']['CHARSET'] = 'koi8-u';
 588 $languages['uk_UA']['LOCALE']  = 'uk_UA.KOI8-U';
 589 $languages['uk']['ALIAS'] = 'uk_UA';
 590
 591 $languages['ru_UA']['NAME']    = 'Russian (Ukrainian)';
 592 $languages['ru_UA']['CHARSET'] = 'koi8-r';
 593 $languages['ru_UA']['LOCALE']  = 'ru_UA.KOI8-R';
 594
 595 /*
 596 $languages['vi_VN']['NAME']    = 'Vietnamese';
 597 $languages['vi_VN']['CHARSET'] = 'utf-8';
 598 $languages['vi']['ALIAS'] = 'vi_VN';
 599 */
 600
 601 // Right to left languages
 602 $languages['ar']['NAME']    = 'Arabic';
 603 $languages['ar']['CHARSET'] = 'windows-1256';
 604 $languages['ar']['DIR']     = 'rtl';
 605
 606 $languages['fa_IR']['NAME']    = 'Farsi';
 607 $languages['fa_IR']['CHARSET'] = 'utf-8';
 608 $languages['fa_IR']['DIR']     = 'rtl';
 609 $languages['fa_IR']['LOCALE']  = 'fa_IR.UTF-8';
 610 $languages['fa']['ALIAS']      = 'fa_IR';
 611
 612 $languages['he_IL']['NAME']    = 'Hebrew';
 613 $languages['he_IL']['CHARSET'] = 'windows-1255';
 614 $languages['he_IL']['LOCALE']  = 'he_IL.CP1255';
 615 $languages['he_IL']['DIR']     = 'rtl';
 616 $languages['he']['ALIAS']      = 'he_IL';
 617
 618 /* Detect whether gettext is installed. */
 619 $gettext_flags = 0;
 620 if (function_exists('_')) {
 621     $gettext_flags += 1;
 622 }
 623 if (function_exists('bindtextdomain')) {
 624     $gettext_flags += 2;
 625 }
 626 if (function_exists('textdomain')) {
 627     $gettext_flags += 4;
 628 }
 629
 630 /* If gettext is fully loaded, cool */
 631 if ($gettext_flags == 7) {
 632     $use_gettext = true;
 633 }
 634 /* If we can fake gettext, try that */
 635 elseif ($gettext_flags == 0) {
 636     $use_gettext = true;
 637     include_once(SM_PATH . 'functions/gettext.php');
 638 } else {
 639     /* Uh-ho.  A weird install */
 640     if (! $gettext_flags & 1) {
 641       /**
 642        * Function is used as replacement in broken installs
 643        * @ignore
 644        */
 645         function _($str) {
 646             return $str;
 647         }
 648     }
 649     if (! $gettext_flags & 2) {
 650       /**
 651        * Function is used as replacement in broken installs
 652        * @ignore
 653        */
 654         function bindtextdomain() {
 655             return;
 656         }
 657     }
 658     if (! $gettext_flags & 4) {
 659       /**
 660        * Function is used as replacemet in broken installs
 661        * @ignore
 662        */
 663         function textdomain() {
 664             return;
 665         }
 666     }
 667 }
 668
 669
 670 /**
 671  * Japanese charset extra function
 672  *
 673  * Action performed by function is defined by first argument.
 674  * Default return value is defined by second argument.
 675  * Use of third argument depends on action.
 676  *
 677  * @param string $action action performed by this function.
 678  *    possible values:
 679  *  decode - convert returned string to euc-jp. third argument unused
 680  *  encode - convert returned string to jis. third argument unused
 681  *  strimwidth - third argument=$width. trims string to $width symbols.
 682  *  encodeheader - create base64 encoded header in iso-2022-jp. third argument unused
 683  *  decodeheader - return human readable string from mime header. string is returned in euc-jp. third argument unused
 684  *  downloadfilename - third argument $useragent. Arguments provide browser info. Returns shift-jis or euc-jp encoded file name
 685  *  wordwrap - third argument=$wrap. wraps text at $wrap symbols
 686  *  utf7-imap_encode - returns string converted from euc-jp to utf7-imap. third argument unused
 687  *  utf7-imap_decode - returns string converted from utf7-imap to euc-jp. third argument unused
 688  * @param string $ret default return value
 689  */
 690 function japanese_charset_xtra() {
 691     $ret = func_get_arg(1);  /* default return value */
 692     if (function_exists('mb_detect_encoding')) {
 693         switch (func_get_arg(0)) { /* action */
 694         case 'decode':
 695             $detect_encoding = @mb_detect_encoding($ret);
 696             if ($detect_encoding == 'JIS' ||
 697                 $detect_encoding == 'EUC-JP' ||
 698                 $detect_encoding == 'SJIS' ||
 699                 $detect_encoding == 'UTF-8') {
 700
 701                 $ret = mb_convert_kana(mb_convert_encoding($ret, 'EUC-JP', 'AUTO'), "KV");
 702             }
 703             break;
 704         case 'encode':
 705             $detect_encoding = @mb_detect_encoding($ret);
 706             if ($detect_encoding == 'JIS' ||
 707                 $detect_encoding == 'EUC-JP' ||
 708                 $detect_encoding == 'SJIS' ||
 709                 $detect_encoding == 'UTF-8') {
 710
 711                 $ret = mb_convert_encoding(mb_convert_kana($ret, "KV"), 'JIS', 'AUTO');
 712             }
 713             break;
 714         case 'strimwidth':
 715             $width = func_get_arg(2);
 716             $ret = mb_strimwidth($ret, 0, $width, '...');
 717             break;
 718         case 'encodeheader':
 719             $result = '';
 720             if (strlen($ret) > 0) {
 721                 $tmpstr = mb_substr($ret, 0, 1);
 722                 $prevcsize = strlen($tmpstr);
 723                 for ($i = 1; $i < mb_strlen($ret); $i++) {
 724                     $tmp = mb_substr($ret, $i, 1);
 725                     if (strlen($tmp) == $prevcsize) {
 726                         $tmpstr .= $tmp;
 727                     } else {
 728                         if ($prevcsize == 1) {
 729                             $result .= $tmpstr;
 730                         } else {
 731                             $result .= str_replace(' ', '',
 732                                                    mb_encode_mimeheader($tmpstr,'iso-2022-jp','B',''));
 733                         }
 734                         $tmpstr = $tmp;
 735                         $prevcsize = strlen($tmp);
 736                     }
 737                 }
 738                 if (strlen($tmpstr)) {
 739                     if (strlen(mb_substr($tmpstr, 0, 1)) == 1)
 740                         $result .= $tmpstr;
 741                     else
 742                         $result .= str_replace(' ', '',
 743                                                mb_encode_mimeheader($tmpstr,'iso-2022-jp','B',''));
 744                 }
 745             }
 746             $ret = $result;
 747             break;
 748         case 'decodeheader':
 749             $ret = str_replace("\t", "", $ret);
 750             if (eregi('=\\?([^?]+)\\?(q|b)\\?([^?]+)\\?=', $ret))
 751                 $ret = @mb_decode_mimeheader($ret);
 752             $ret = @mb_convert_encoding($ret, 'EUC-JP', 'AUTO');
 753             break;
 754         case 'downloadfilename':
 755             $useragent = func_get_arg(2);
 756             if (strstr($useragent, 'Windows') !== false ||
 757                 strstr($useragent, 'Mac_') !== false) {
 758                 $ret = mb_convert_encoding($ret, 'SJIS', 'AUTO');
 759             } else {
 760                 $ret = mb_convert_encoding($ret, 'EUC-JP', 'AUTO');
 761 }
 762             break;
 763         case 'wordwrap':
 764             $no_begin = "\x21\x25\x29\x2c\x2e\x3a\x3b\x3f\x5d\x7d\xa1\xf1\xa1\xeb\xa1" .
 765                 "\xc7\xa1\xc9\xa2\xf3\xa1\xec\xa1\xed\xa1\xee\xa1\xa2\xa1\xa3\xa1\xb9" .
 766                 "\xa1\xd3\xa1\xd5\xa1\xd7\xa1\xd9\xa1\xdb\xa1\xcd\xa4\xa1\xa4\xa3\xa4" .
 767                 "\xa5\xa4\xa7\xa4\xa9\xa4\xc3\xa4\xe3\xa4\xe5\xa4\xe7\xa4\xee\xa1\xab" .
 768                 "\xa1\xac\xa1\xb5\xa1\xb6\xa5\xa1\xa5\xa3\xa5\xa5\xa5\xa7\xa5\xa9\xa5" .
 769                 "\xc3\xa5\xe3\xa5\xe5\xa5\xe7\xa5\xee\xa5\xf5\xa5\xf6\xa1\xa6\xa1\xbc" .
 770                 "\xa1\xb3\xa1\xb4\xa1\xaa\xa1\xf3\xa1\xcb\xa1\xa4\xa1\xa5\xa1\xa7\xa1" .
 771                 "\xa8\xa1\xa9\xa1\xcf\xa1\xd1";
 772             $no_end = "\x5c\x24\x28\x5b\x7b\xa1\xf2\x5c\xa1\xc6\xa1\xc8\xa1\xd2\xa1" .
 773                 "\xd4\xa1\xd6\xa1\xd8\xa1\xda\xa1\xcc\xa1\xf0\xa1\xca\xa1\xce\xa1\xd0\xa1\xef";
 774             $wrap = func_get_arg(2);
 775
 776             if (strlen($ret) >= $wrap &&
 777                 substr($ret, 0, 1) != '>' &&
 778                 strpos($ret, 'http://') === FALSE &&
 779                 strpos($ret, 'https://') === FALSE &&
 780                 strpos($ret, 'ftp://') === FALSE) {
 781
 782                 $ret = mb_convert_kana($ret, "KV");
 783
 784                 $line_new = '';
 785                 $ptr = 0;
 786
 787                 while ($ptr < strlen($ret) - 1) {
 788                     $l = mb_strcut($ret, $ptr, $wrap);
 789                     $ptr += strlen($l);
 790                     $tmp = $l;
 791
 792                     $l = mb_strcut($ret, $ptr, 2);
 793                     while (strlen($l) != 0 && mb_strpos($no_begin, $l) !== FALSE ) {
 794                         $tmp .= $l;
 795                         $ptr += strlen($l);
 796                         $l = mb_strcut($ret, $ptr, 1);
 797                     }
 798                     $line_new .= $tmp;
 799                     if ($ptr < strlen($ret) - 1)
 800                         $line_new .= "\n";
 801                 }
 802                 $ret = $line_new;
 803             }
 804             break;
 805         case 'utf7-imap_encode':
 806             $ret = mb_convert_encoding($ret, 'UTF7-IMAP', 'EUC-JP');
 807             break;
 808         case 'utf7-imap_decode':
 809             $ret = mb_convert_encoding($ret, 'EUC-JP', 'UTF7-IMAP');
 810             break;
 811         }
 812     }
 813     return $ret;
 814 }
 815
 816
 817 /**
 818  * Korean charset extra functions
 819  *
 820  * Action performed by function is defined by first argument.
 821  * Default return value is defined by second argument.
 822  *
 823  * @param string action performed by this function.
 824  *    possible values:
 825  * downloadfilename - Hangul(Korean Character) Attached File Name Fix.
 826  * @param string default return value
 827  */
 828 function korean_charset_xtra() {
 829
 830     $ret = func_get_arg(1);  /* default return value */
 831     if (func_get_arg(0) == 'downloadfilename') { /* action */
 832         $ret = str_replace("\x0D\x0A", '', $ret);  /* Hanmail's CR/LF Clear */
 833         for ($i=0;$i<strlen($ret);$i++) {
 834             if ($ret[$i] >= "\xA1" && $ret[$i] <= "\xFE") {   /* 0xA1 - 0XFE are Valid */
 835                 $i++;
 836                 continue;
 837             } else if (($ret[$i] >= 'a' && $ret[$i] <= 'z') || /* From Original ereg_replace in download.php */
 838                        ($ret[$i] >= 'A' && $ret[$i] <= 'Z') ||
 839                        ($ret[$i] == '.') || ($ret[$i] == '-')) {
 840                 continue;
 841             } else {
 842                 $ret[$i] = '_';
 843             }
 844         }
 845
 846     }
 847     return $ret;
 848 }
 849
 850 /**
 851  * Replaces non-braking spaces inserted by some browsers with regular space
 852  *
 853  * This function can be used to replace non-braking space symbols
 854  * that are inserted in forms by some browsers instead of normal
 855  * space symbol.
 856  *
 857  * @param string $string Text that needs to be cleaned
 858  * @param string $charset Charset used in text
 859  * @return string Cleaned text
 860  */
 861 function cleanup_nbsp($string,$charset) {
 862
 863   // reduce number of case statements
 864   if (stristr('iso-8859-',substr($charset,0,9))){
 865     $output_charset="iso-8859-x";
 866   }
 867   if (stristr('windows-125',substr($charset,0,11))){
 868     $output_charset="cp125x";
 869   }
 870   if (stristr('koi8',substr($charset,0,4))){
 871     $output_charset="koi8-x";
 872   }
 873   if (! isset($output_charset)){
 874     $output_charset=strtolower($charset);
 875   }
 876
 877 // where is non-braking space symbol
 878 switch($output_charset):
 879  case "iso-8859-x":
 880  case "cp125x":
 881  case "iso-2022-jp":
 882   $nbsp="\xA0";
 883   break;
 884  case "koi8-x":
 885    $nbsp="\x9A";
 886    break;
 887  case "utf-8":
 888    $nbsp="\xC2\xA0";
 889    break;
 890  default:
 891    // don't change string if charset is unmatched
 892    return $string;
 893 endswitch;
 894
 895 // return space instead of non-braking space.
 896  return str_replace($nbsp,' ',$string);
 897 }
 898
 899 /**
 900  * Function informs if it is safe to convert given charset to the one that is used by user.
 901  *
 902  * It is safe to use conversion only if user uses utf-8 encoding and when
 903  * converted charset is similar to the one that is used by user.
 904  *
 905  * @param string $input_charset Charset of text that needs to be converted
 906  * @return bool is it possible to convert to user's charset
 907  */
 908 function is_conversion_safe($input_charset) {
 909   global $languages, $sm_notAlias, $default_charset;
 910
 911  // convert to lower case
 912  $input_charset = strtolower($input_charset);
 913
 914  // Is user's locale Unicode based ?
 915  if ( $default_charset == "utf-8" ) {
 916    return true;
 917  }
 918
 919  // Charsets that are similar
 920 switch ($default_charset):
 921 case "windows-1251":
 922       if ( $input_charset == "iso-8859-5" ||
 923            $input_charset == "koi8-r" ||
 924            $input_charset == "koi8-u" ) {
 925         return true;
 926      } else {
 927         return false;
 928      }
 929 case "windows-1257":
 930   if ( $input_charset == "iso-8859-13" ||
 931        $input_charset == "iso-8859-4" ) {
 932     return true;
 933   } else {
 934     return false;
 935   }
 936 case "iso-8859-4":
 937   if ( $input_charset == "iso-8859-13" ||
 938        $input_charset == "windows-1257" ) {
 939      return true;
 940   } else {
 941      return false;
 942   }
 943 case "iso-8859-5":
 944   if ( $input_charset == "windows-1251" ||
 945        $input_charset == "koi8-r" ||
 946        $input_charset == "koi8-u" ) {
 947      return true;
 948   } else {
 949      return false;
 950   }
 951 case "iso-8859-13":
 952   if ( $input_charset == "iso-8859-4" ||
 953        $input_charset == "windows-1257" ) {
 954      return true;
 955   } else {
 956      return false;
 957   }
 958 case "koi8-r":
 959   if ( $input_charset == "windows-1251" ||
 960        $input_charset == "iso-8859-5" ||
 961        $input_charset == "koi8-u" ) {
 962      return true;
 963   } else {
 964      return false;
 965   }
 966 case "koi8-u":
 967   if ( $input_charset == "windows-1251" ||
 968        $input_charset == "iso-8859-5" ||
 969        $input_charset == "koi8-r" ) {
 970      return true;
 971   } else {
 972      return false;
 973   }
 974 default:
 975    return false;
 976 endswitch;
 977 }
 978 ?>