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, $aggressive_decoding;
  40
  41     if (isset($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);
  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($aggressive_decoding) || $aggressive_decoding=="" ) {
  97          $aggressive_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 boolean $htmlencode keep htmlspecialchars encoding
 115  * @param string
 116  */
 117 function charset_encode($string,$charset,$htmlencode=true) {
 118   global $default_charset;
 119
 120   // Undo html special chars
 121   if (! $htmlencode ) {
 122       $string = str_replace(array('&amp;','&gt;','&lt;','&quot;'),array('&','>','<','"'),$string);
 123   }
 124
 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);
 130   } else {
 131       include_once(SM_PATH . 'functions/encode/us_ascii.php');
 132       $ret = charset_encode_us_ascii($string);
 133   }
 134   return( $ret );
 135 }
 136
 137 /**
 138  * Combined decoding and encoding functions
 139  *
 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 $htmlencode keep htmlspecialchars encoding
 146  * @return string converted string
 147  */
 148 function charset_convert($in_charset,$string,$out_charset,$htmlencode=true) {
 149     $string=charset_decode($in_charset,$string);
 150     $string=charset_encode($string,$out_charset,$htmlencode);
 151     return $string;
 152 }
 153
 154 /**
 155  * Makes charset name suitable for decoding cycles
 156  *
 157  * @param string $charset Name of charset
 158  * @return string $charset Adjusted name of charset
 159  */
 160 function fixcharset($charset) {
 161     // minus removed from function names
 162     $charset=str_replace('-','_',$charset);
 163
 164     // windows-125x and cp125x charsets
 165     $charset=str_replace('windows_','cp',$charset);
 166
 167     // ibm > cp
 168     $charset=str_replace('ibm','cp',$charset);
 169
 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);
 173
 174     return $charset;
 175 }
 176
 177 /**
 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
 181  *
 182  * Function sets system locale environment (LC_ALL, LANG, LANGUAGE),
 183  * gettext translation bindings and html header information.
 184  *
 185  * Function returns error codes, if there is some fatal error.
 186  *  0 = no error,
 187  *  1 = mbstring support is not present,
 188  *  2 = mbstring support is not present, user's translation reverted to en_US.
 189  *
 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 $squirrelmail_default_language if language detection fails or language is not set. Defaults to false.
 193  * @return int function execution error codes.
 194  */
 195 function set_up_language($sm_language, $do_search = false, $default = false) {
 196
 197     static $SetupAlready = 0;
 198     global $use_gettext, $languages,
 199            $squirrelmail_language, $squirrelmail_default_language,
 200            $sm_notAlias, $username, $data_dir;
 201
 202     if ($SetupAlready) {
 203         return;
 204     }
 205
 206     $SetupAlready = TRUE;
 207     sqgetGlobalVar('HTTP_ACCEPT_LANGUAGE',  $accept_lang, SQ_SERVER);
 208
 209     if ($do_search && ! $sm_language && isset($accept_lang)) {
 210         $sm_language = substr($accept_lang, 0, 2);
 211     }
 212
 213     if ((!$sm_language||$default) && isset($squirrelmail_default_language)) {
 214         $squirrelmail_language = $squirrelmail_default_language;
 215         $sm_language = $squirrelmail_default_language;
 216     }
 217     $sm_notAlias = $sm_language;
 218
 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       $sm_notAlias="en_US";
 224     }
 225
 226     while (isset($languages[$sm_notAlias]['ALIAS'])) {
 227         $sm_notAlias = $languages[$sm_notAlias]['ALIAS'];
 228     }
 229
 230     if ( isset($sm_language) &&
 231          $use_gettext &&
 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');
 239             } else {
 240               bind_textdomain_codeset ("squirrelmail", $languages[$sm_notAlias]['CHARSET'] );
 241             }
 242         }
 243         if (isset($languages[$sm_notAlias]['LOCALE'])){
 244           $longlocale=$languages[$sm_notAlias]['LOCALE'];
 245         } else {
 246           $longlocale=$sm_notAlias;
 247         }
 248         if ( !ini_get('safe_mode') &&
 249              getenv( 'LC_ALL' ) != $longlocale ) {
 250             putenv( "LC_ALL=$longlocale" );
 251             putenv( "LANG=$longlocale" );
 252             putenv( "LANGUAGE=$longlocale" );
 253         }
 254         setlocale(LC_ALL, $longlocale);
 255
 256         // Set text direction/alignment variables
 257         if (isset($languages[$sm_notAlias]['DIR']) &&
 258             $languages[$sm_notAlias]['DIR'] == 'rtl') {
 259           /**
 260            * Text direction
 261            * @global string $text_direction
 262            */
 263           $text_direction='rtl';
 264           /**
 265            * Left alignment
 266            * @global string $left_align
 267            */
 268           $left_align='right';
 269           /**
 270            * Right alignment
 271            * @global string $right_align
 272            */
 273           $right_align='left';
 274         } else {
 275           $text_direction='ltr';
 276           $left_align='left';
 277           $right_align='right';
 278         }
 279
 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
 285               $error = 1;
 286               // Revert to English if possible.
 287               if (function_exists('setPref')  && $username!='' && $data_dir!="") {
 288                 setPref($data_dir, $username, 'language', "en_US");
 289                 $error = 2;
 290               }
 291               // stop further execution in order not to get php errors on mb_internal_encoding().
 292               return $error;
 293             }
 294             if (function_exists('mb_language')) {
 295                 mb_language('Japanese');
 296             }
 297             mb_internal_encoding('EUC-JP');
 298             mb_http_output('pass');
 299         } else {
 300         header( 'Content-Type: text/html; charset=' . $languages[$sm_notAlias]['CHARSET'] );
 301     }
 302 }
 303     return 0;
 304 }
 305
 306 /**
 307  * Sets default_charset variable according to the one that is used by user's translations.
 308  *
 309  * Function changes global $default_charset variable in order to be sure, that it
 310  * contains charset used by user's translation. Sanity of $squirrelmail_default_language
 311  * and $default_charset combination provided in SquirrelMail config is also tested.
 312  *
 313  * There can be a $default_charset setting in the
 314  * config.php file, but the user may have a different language
 315  * selected for a user interface. This function checks the
 316  * language selected by the user and tags the outgoing messages
 317  * with the appropriate charset corresponding to the language
 318  * selection. This is "more right" (tm), than just stamping the
 319  * message blindly with the system-wide $default_charset.
 320  */
 321 function set_my_charset(){
 322     global $data_dir, $username, $default_charset, $languages, $squirrelmail_default_language;
 323
 324     $my_language = getPref($data_dir, $username, 'language');
 325     if (!$my_language) {
 326         $my_language = $squirrelmail_default_language ;
 327     }
 328     // Catch removed translation
 329     if (!isset($languages[$my_language])) {
 330       $my_language="en_US";
 331     }
 332     while (isset($languages[$my_language]['ALIAS'])) {
 333         $my_language = $languages[$my_language]['ALIAS'];
 334     }
 335     $my_charset = $languages[$my_language]['CHARSET'];
 336     if ($my_charset) {
 337         $default_charset = $my_charset;
 338     }
 339 }
 340
 341 /* ------------------------------ main --------------------------- */
 342
 343 global $squirrelmail_language, $languages, $use_gettext;
 344
 345 if (! isset($squirrelmail_language)) {
 346     $squirrelmail_language = '';
 347 }
 348
 349 /**
 350  * Array specifies the available translations.
 351  *
 352  * Structure of array:
 353  * $languages['language']['variable'] = 'value'
 354  *
 355  * Possible 'variable' names:
 356  *  NAME      - Translation name in English
 357  *  CHARSET   - Encoding used by translation
 358  *  ALIAS     - used when 'language' is only short name and 'value' should provide long language name
 359  *  ALTNAME   - Native translation name. Any 8bit symbols must be html encoded.
 360  *  LOCALE    - Full locale name (in xx_XX.charset format)
 361  *  DIR       - Text direction. Used to define Right-to-Left languages. Possible values 'rtl' or 'ltr'. If undefined - defaults to 'ltr'
 362  *  XTRA_CODE - translation uses special functions. See doc/i18n.txt
 363  *
 364  * Each 'language' definition requires NAME+CHARSET or ALIAS variables.
 365  *
 366  * @name $languages
 367  * @global array $languages
 368  */
 369 $languages['bg_BG']['NAME']    = 'Bulgarian';
 370 $languages['bg_BG']['ALTNAME'] = '&#1041;&#1098;&#1083;&#1075;&#1072;&#1088;&#1089;&#1082;&#1080;';
 371 $languages['bg_BG']['CHARSET'] = 'windows-1251';
 372 $languages['bg_BG']['LOCALE']  = 'bg_BG.CP1251';
 373 $languages['bg']['ALIAS'] = 'bg_BG';
 374
 375 $languages['ca_ES']['NAME']    = 'Catalan';
 376 $languages['ca_ES']['CHARSET'] = 'iso-8859-1';
 377 $languages['ca_ES']['LOCALE']  = 'ca_ES.ISO8859-1';
 378 $languages['ca']['ALIAS'] = 'ca_ES';
 379
 380 $languages['cs_CZ']['NAME']    = 'Czech';
 381 $languages['cs_CZ']['ALTNAME'] = '&#268;e&scaron;tina';
 382 $languages['cs_CZ']['CHARSET'] = 'iso-8859-2';
 383 $languages['cs_CZ']['LOCALE']  = 'cs_CZ.ISO8859-2';
 384 $languages['cs']['ALIAS']      = 'cs_CZ';
 385
 386 $languages['cy_GB']['NAME']    = 'Welsh';
 387 $languages['cy_GB']['ALTNAME'] = 'Cymraeg';
 388 $languages['cy_GB']['CHARSET'] = 'iso-8859-1';
 389 $languages['cy_GB']['LOCALE']  = 'cy_GB.ISO8859-1';
 390 $languages['cy']['ALIAS'] = 'cy_GB';
 391
 392 // Danish locale is da_DK.
 393 $languages['da_DK']['NAME']    = 'Danish';
 394 $languages['da_DK']['ALTNAME'] = 'Dansk';
 395 $languages['da_DK']['CHARSET'] = 'iso-8859-1';
 396 $languages['da_DK']['LOCALE']  = 'da_DK.ISO8859-1';
 397 $languages['da']['ALIAS'] = 'da_DK';
 398
 399 $languages['de_DE']['NAME']    = 'German';
 400 $languages['de_DE']['ALTNAME']    = 'Deutsch';
 401 $languages['de_DE']['CHARSET'] = 'iso-8859-1';
 402 $languages['de_DE']['LOCALE']  = 'de_DE.ISO8859-1';
 403 $languages['de']['ALIAS'] = 'de_DE';
 404
 405 $languages['el_GR']['NAME']    = 'Greek';
 406 $languages['el_GR']['ALTNAME'] = '&Epsilon;&lambda;&lambda;&eta;&nu;&iota;&kappa;&#940;';
 407 $languages['el_GR']['CHARSET'] = 'iso-8859-7';
 408 $languages['el_GR']['LOCALE']  = 'el_GR.ISO8859-7';
 409 $languages['el']['ALIAS'] = 'el_GR';
 410
 411 $languages['en_GB']['NAME']    = 'British';
 412 $languages['en_GB']['CHARSET'] = 'iso-8859-15';
 413 $languages['en_GB']['LOCALE']  = 'en_GB.ISO8859-15';
 414
 415 $languages['en_US']['NAME']    = 'English';
 416 $languages['en_US']['CHARSET'] = 'iso-8859-1';
 417 $languages['en_US']['LOCALE']  = 'en_US.ISO8859-1';
 418 $languages['en']['ALIAS'] = 'en_US';
 419
 420 $languages['es_ES']['NAME']    = 'Spanish';
 421 $languages['es_ES']['ALTNAME'] = 'Espa&ntilde;ol';
 422 $languages['es_ES']['CHARSET'] = 'iso-8859-1';
 423 $languages['es_ES']['LOCALE']  = 'es_ES.ISO8859-1';
 424 $languages['es']['ALIAS'] = 'es_ES';
 425
 426 $languages['et_EE']['NAME']    = 'Estonian';
 427 $languages['et_EE']['CHARSET'] = 'iso-8859-15';
 428 $languages['et_EE']['LOCALE']  = 'et_EE.ISO8859-15';
 429 $languages['et']['ALIAS'] = 'et_EE';
 430
 431 $languages['eu_ES']['NAME']    = 'Basque';
 432 $languages['eu_ES']['CHARSET'] = 'iso-8859-1';
 433 $languages['eu_ES']['LOCALE']  = 'eu_ES.ISO8859-1';
 434 $languages['eu']['ALIAS'] = 'eu_ES';
 435
 436 $languages['fo_FO']['NAME']    = 'Faroese';
 437 $languages['fo_FO']['CHARSET'] = 'iso-8859-1';
 438 $languages['fo_FO']['LOCALE']  = 'fo_FO.ISO8859-1';
 439 $languages['fo']['ALIAS'] = 'fo_FO';
 440
 441 $languages['fi_FI']['NAME']    = 'Finnish';
 442 $languages['fi_FI']['ALTNAME'] = 'Suomi';
 443 $languages['fi_FI']['CHARSET'] = 'iso-8859-1';
 444 $languages['fi_FI']['LOCALE']  = 'fi_FI.ISO8859-1';
 445 $languages['fi']['ALIAS'] = 'fi_FI';
 446
 447 $languages['fr_FR']['NAME']    = 'French';
 448 $languages['fr_FR']['ALTNAME'] = 'Fran&#231;ais';
 449 $languages['fr_FR']['CHARSET'] = 'iso-8859-1';
 450 $languages['fr_FR']['LOCALE']  = 'fr_FR.ISO8859-1';
 451 $languages['fr']['ALIAS'] = 'fr_FR';
 452
 453 $languages['hr_HR']['NAME']    = 'Croatian';
 454 $languages['hr_HR']['CHARSET'] = 'iso-8859-2';
 455 $languages['hr_HR']['LOCALE']  = 'hr_HR.ISO8859-2';
 456 $languages['hr']['ALIAS'] = 'hr_HR';
 457
 458 $languages['hu_HU']['NAME']    = 'Hungarian';
 459 $languages['hu_HU']['ALTNAME'] = 'Magyar';
 460 $languages['hu_HU']['CHARSET'] = 'iso-8859-2';
 461 $languages['hu_HU']['LOCALE']  = 'hu_HU.ISO8859-2';
 462 $languages['hu']['ALIAS'] = 'hu_HU';
 463
 464 $languages['id_ID']['NAME']    = 'Indonesian';
 465 $languages['id_ID']['ALTNAME'] = 'Bahasa Indonesia';
 466 $languages['id_ID']['CHARSET'] = 'iso-8859-1';
 467 $languages['id_ID']['LOCALE']  = 'id_ID.ISO8859-1';
 468 $languages['id']['ALIAS'] = 'id_ID';
 469
 470 $languages['is_IS']['NAME']    = 'Icelandic';
 471 $languages['is_IS']['ALTNAME'] = '&Iacute;slenska';
 472 $languages['is_IS']['CHARSET'] = 'iso-8859-1';
 473 $languages['is_IS']['LOCALE']  = 'is_IS.ISO8859-1';
 474 $languages['is']['ALIAS'] = 'is_IS';
 475
 476 $languages['it_IT']['NAME']    = 'Italian';
 477 $languages['it_IT']['CHARSET'] = 'iso-8859-1';
 478 $languages['it_IT']['LOCALE']  = 'it_IT.ISO8859-1';
 479 $languages['it']['ALIAS'] = 'it_IT';
 480
 481 $languages['ja_JP']['NAME']    = 'Japanese';
 482 $languages['ja_JP']['ALTNAME'] = '&#26085;&#26412;&#35486;';
 483 $languages['ja_JP']['CHARSET'] = 'iso-2022-jp';
 484 $languages['ja_JP']['LOCALE'] = 'ja_JP.EUC-JP';
 485 $languages['ja_JP']['XTRA_CODE'] = 'japanese_xtra';
 486 $languages['ja']['ALIAS'] = 'ja_JP';
 487
 488 $languages['ko_KR']['NAME']    = 'Korean';
 489 $languages['ko_KR']['CHARSET'] = 'euc-KR';
 490 $languages['ko_KR']['LOCALE']  = 'ko_KR.EUC-KR';
 491 $languages['ko_KR']['XTRA_CODE'] = 'korean_xtra';
 492 $languages['ko']['ALIAS'] = 'ko_KR';
 493
 494 $languages['lt_LT']['NAME']    = 'Lithuanian';
 495 $languages['lt_LT']['ALTNAME'] = 'Lietuvi&#371;';
 496 $languages['lt_LT']['CHARSET'] = 'utf-8';
 497 $languages['lt_LT']['LOCALE'] = 'lt_LT.UTF-8';
 498 $languages['lt']['ALIAS'] = 'lt_LT';
 499
 500 $languages['nl_NL']['NAME']    = 'Dutch';
 501 $languages['nl_NL']['ALTNAME'] = 'Nederlands';
 502 $languages['nl_NL']['CHARSET'] = 'iso-8859-1';
 503 $languages['nl_NL']['LOCALE']  = 'nl_NL.ISO8859-1';
 504 $languages['nl']['ALIAS'] = 'nl_NL';
 505
 506 $languages['ms_MY']['NAME']    = 'Malay';
 507 $languages['ms_MY']['ALTNAME'] = 'Bahasa Melayu';
 508 $languages['ms_MY']['CHARSET'] = 'iso-8859-1';
 509 $languages['ms_MY']['LOCALE']  = 'ms_MY.ISO8859-1';
 510 $languages['my']['ALIAS'] = 'ms_MY';
 511
 512 $languages['nb_NO']['NAME']    = 'Norwegian (Bokm&aring;l)';
 513 $languages['nb_NO']['ALTNAME'] = 'Norsk (Bokm&aring;l)';
 514 $languages['nb_NO']['CHARSET'] = 'iso-8859-1';
 515 $languages['nb_NO']['LOCALE']  = 'nb_NO.ISO8859-1';
 516 $languages['nb']['ALIAS'] = 'nb_NO';
 517
 518 $languages['nn_NO']['NAME']    = 'Norwegian (Nynorsk)';
 519 $languages['nn_NO']['ALTNAME'] = 'Norsk (Nynorsk)';
 520 $languages['nn_NO']['CHARSET'] = 'iso-8859-1';
 521 $languages['nn_NO']['LOCALE']  = 'nn_NO.ISO8859-1';
 522
 523 $languages['pl_PL']['NAME']    = 'Polish';
 524 $languages['pl_PL']['ALTNAME'] = 'Polski';
 525 $languages['pl_PL']['CHARSET'] = 'iso-8859-2';
 526 $languages['pl_PL']['LOCALE']  = 'pl_PL.ISO8859-2';
 527 $languages['pl']['ALIAS'] = 'pl_PL';
 528
 529 $languages['pt_PT']['NAME'] = 'Portuguese (Portugal)';
 530 $languages['pt_PT']['CHARSET'] = 'iso-8859-1';
 531 $languages['pt_PT']['LOCALE']  = 'pt_PT.ISO8859-1';
 532 $languages['pt']['ALIAS'] = 'pt_PT';
 533
 534 $languages['pt_BR']['NAME']    = 'Portuguese (Brazil)';
 535 $languages['pt_BR']['ALTNAME'] = 'Portugu&ecirc;s do Brasil';
 536 $languages['pt_BR']['CHARSET'] = 'iso-8859-1';
 537 $languages['pt_BR']['LOCALE']  = 'pt_BR.ISO8859-1';
 538
 539 $languages['ro_RO']['NAME']    = 'Romanian';
 540 $languages['ro_RO']['ALTNAME'] = 'Rom&acirc;n&#259;';
 541 $languages['ro_RO']['CHARSET'] = 'iso-8859-2';
 542 $languages['ro_RO']['LOCALE']  = 'ro_RO.ISO8859-2';
 543 $languages['ro']['ALIAS'] = 'ro_RO';
 544
 545 $languages['ru_RU']['NAME']    = 'Russian';
 546 $languages['ru_RU']['ALTNAME'] = '&#1056;&#1091;&#1089;&#1089;&#1082;&#1080;&#1081;';
 547 $languages['ru_RU']['CHARSET'] = 'utf-8';
 548 $languages['ru_RU']['LOCALE']  = 'ru_RU.UTF-8';
 549 $languages['ru']['ALIAS'] = 'ru_RU';
 550
 551 $languages['sk_SK']['NAME']    = 'Slovak';
 552 $languages['sk_SK']['CHARSET'] = 'iso-8859-2';
 553 $languages['sk_SK']['LOCALE']  = 'sk_SK.ISO8859-2';
 554 $languages['sk']['ALIAS'] = 'sk_SK';
 555
 556 $languages['sl_SI']['NAME']    = 'Slovenian';
 557 $languages['sl_SI']['ALTNAME'] = 'Sloven&scaron;&#269;ina';
 558 $languages['sl_SI']['CHARSET'] = 'iso-8859-2';
 559 $languages['sl_SI']['LOCALE']  = 'sl_SI.ISO8859-2';
 560 $languages['sl']['ALIAS'] = 'sl_SI';
 561
 562 $languages['sr_YU']['NAME']    = 'Serbian';
 563 $languages['sr_YU']['ALTNAME'] = 'Srpski';
 564 $languages['sr_YU']['CHARSET'] = 'iso-8859-2';
 565 $languages['sr_YU']['LOCALE']  = 'sr_YU.ISO8859-2';
 566 $languages['sr']['ALIAS'] = 'sr_YU';
 567
 568 $languages['sv_SE']['NAME']    = 'Swedish';
 569 $languages['sv_SE']['ALTNAME'] = 'Svenska';
 570 $languages['sv_SE']['CHARSET'] = 'iso-8859-1';
 571 $languages['sv_SE']['LOCALE']  = 'sv_SE.ISO8859-1';
 572 $languages['sv']['ALIAS'] = 'sv_SE';
 573
 574 $languages['th_TH']['NAME']    = 'Thai';
 575 $languages['th_TH']['CHARSET'] = 'tis-620';
 576 $languages['th_TH']['LOCALE']  = 'th_TH.TIS-620';
 577 $languages['th']['ALIAS'] = 'th_TH';
 578
 579 $languages['tl_PH']['NAME']    = 'Tagalog';
 580 $languages['tl_PH']['CHARSET'] = 'iso-8859-1';
 581 $languages['tl_PH']['LOCALE']  = 'tl_PH.ISO8859-1';
 582 $languages['tl']['ALIAS'] = 'tl_PH';
 583
 584 $languages['tr_TR']['NAME']    = 'Turkish';
 585 $languages['tr_TR']['CHARSET'] = 'iso-8859-9';
 586 $languages['tr_TR']['LOCALE']  = 'tr_TR.ISO8859-9';
 587 $languages['tr']['ALIAS'] = 'tr_TR';
 588
 589 $languages['zh_TW']['NAME']    = 'Chinese Trad';
 590 $languages['zh_TW']['CHARSET'] = 'big5';
 591 $languages['zh_TW']['LOCALE']  = 'zh_TW.BIG5';
 592 $languages['tw']['ALIAS'] = 'zh_TW';
 593
 594 $languages['zh_CN']['NAME']    = 'Chinese Simp';
 595 $languages['zh_CN']['CHARSET'] = 'gb2312';
 596 $languages['zh_CN']['LOCALE']  = 'zh_CN.GB2312';
 597 $languages['cn']['ALIAS'] = 'zh_CN';
 598
 599 $languages['uk_UA']['NAME']    = 'Ukrainian';
 600 $languages['uk_UA']['CHARSET'] = 'koi8-u';
 601 $languages['uk_UA']['LOCALE']  = 'uk_UA.KOI8-U';
 602 $languages['uk']['ALIAS'] = 'uk_UA';
 603
 604 $languages['ru_UA']['NAME']    = 'Russian (Ukrainian)';
 605 $languages['ru_UA']['CHARSET'] = 'koi8-r';
 606 $languages['ru_UA']['LOCALE']  = 'ru_UA.KOI8-R';
 607
 608 /*
 609 $languages['vi_VN']['NAME']    = 'Vietnamese';
 610 $languages['vi_VN']['CHARSET'] = 'utf-8';
 611 $languages['vi']['ALIAS'] = 'vi_VN';
 612 */
 613
 614 // Right to left languages
 615 $languages['ar']['NAME']    = 'Arabic';
 616 $languages['ar']['CHARSET'] = 'windows-1256';
 617 $languages['ar']['DIR']     = 'rtl';
 618
 619 $languages['fa_IR']['NAME']    = 'Farsi';
 620 $languages['fa_IR']['CHARSET'] = 'utf-8';
 621 $languages['fa_IR']['DIR']     = 'rtl';
 622 $languages['fa_IR']['LOCALE']  = 'fa_IR.UTF-8';
 623 $languages['fa']['ALIAS']      = 'fa_IR';
 624
 625 $languages['he_IL']['NAME']    = 'Hebrew';
 626 $languages['he_IL']['CHARSET'] = 'windows-1255';
 627 $languages['he_IL']['LOCALE']  = 'he_IL.CP1255';
 628 $languages['he_IL']['DIR']     = 'rtl';
 629 $languages['he']['ALIAS']      = 'he_IL';
 630
 631 $languages['ug']['NAME']    = 'Uighur';
 632 $languages['ug']['CHARSET'] = 'utf-8';
 633 $languages['ug']['DIR']     = 'rtl';
 634
 635 /* Detect whether gettext is installed. */
 636 $gettext_flags = 0;
 637 if (function_exists('_')) {
 638     $gettext_flags += 1;
 639 }
 640 if (function_exists('bindtextdomain')) {
 641     $gettext_flags += 2;
 642 }
 643 if (function_exists('textdomain')) {
 644     $gettext_flags += 4;
 645 }
 646
 647 /* If gettext is fully loaded, cool */
 648 if ($gettext_flags == 7) {
 649     $use_gettext = true;
 650 }
 651 /* If we can fake gettext, try that */
 652 elseif ($gettext_flags == 0) {
 653     $use_gettext = true;
 654     include_once(SM_PATH . 'functions/gettext.php');
 655 } else {
 656     /* Uh-ho.  A weird install */
 657     if (! $gettext_flags & 1) {
 658       /**
 659        * Function is used as replacement in broken installs
 660        * @ignore
 661        */
 662         function _($str) {
 663             return $str;
 664         }
 665     }
 666     if (! $gettext_flags & 2) {
 667       /**
 668        * Function is used as replacement in broken installs
 669        * @ignore
 670        */
 671         function bindtextdomain() {
 672             return;
 673         }
 674     }
 675     if (! $gettext_flags & 4) {
 676       /**
 677        * Function is used as replacemet in broken installs
 678        * @ignore
 679        */
 680         function textdomain() {
 681             return;
 682         }
 683     }
 684 }
 685
 686
 687 /**
 688  * Japanese charset extra function
 689  *
 690  * Action performed by function is defined by first argument.
 691  * Default return value is defined by second argument.
 692  * Use of third argument depends on action.
 693  *
 694  * @param string $action action performed by this function.
 695  *    possible values:
 696  *  decode - convert returned string to euc-jp. third argument unused
 697  *  encode - convert returned string to jis. third argument unused
 698  *  strimwidth - third argument=$width. trims string to $width symbols.
 699  *  encodeheader - create base64 encoded header in iso-2022-jp. third argument unused
 700  *  decodeheader - return human readable string from mime header. string is returned in euc-jp. third argument unused
 701  *  downloadfilename - third argument $useragent. Arguments provide browser info. Returns shift-jis or euc-jp encoded file name
 702  *  wordwrap - third argument=$wrap. wraps text at $wrap symbols
 703  *  utf7-imap_encode - returns string converted from euc-jp to utf7-imap. third argument unused
 704  *  utf7-imap_decode - returns string converted from utf7-imap to euc-jp. third argument unused
 705  * @param string $ret default return value
 706  */
 707 function japanese_xtra() {
 708     $ret = func_get_arg(1);  /* default return value */
 709     if (function_exists('mb_detect_encoding')) {
 710         switch (func_get_arg(0)) { /* action */
 711         case 'decode':
 712             $detect_encoding = @mb_detect_encoding($ret);
 713             if ($detect_encoding == 'JIS' ||
 714                 $detect_encoding == 'EUC-JP' ||
 715                 $detect_encoding == 'SJIS' ||
 716                 $detect_encoding == 'UTF-8') {
 717
 718                 $ret = mb_convert_kana(mb_convert_encoding($ret, 'EUC-JP', 'AUTO'), "KV");
 719             }
 720             break;
 721         case 'encode':
 722             $detect_encoding = @mb_detect_encoding($ret);
 723             if ($detect_encoding == 'JIS' ||
 724                 $detect_encoding == 'EUC-JP' ||
 725                 $detect_encoding == 'SJIS' ||
 726                 $detect_encoding == 'UTF-8') {
 727
 728                 $ret = mb_convert_encoding(mb_convert_kana($ret, "KV"), 'JIS', 'AUTO');
 729             }
 730             break;
 731         case 'strimwidth':
 732             $width = func_get_arg(2);
 733             $ret = mb_strimwidth($ret, 0, $width, '...');
 734             break;
 735         case 'encodeheader':
 736             $result = '';
 737             if (strlen($ret) > 0) {
 738                 $tmpstr = mb_substr($ret, 0, 1);
 739                 $prevcsize = strlen($tmpstr);
 740                 for ($i = 1; $i < mb_strlen($ret); $i++) {
 741                     $tmp = mb_substr($ret, $i, 1);
 742                     if (strlen($tmp) == $prevcsize) {
 743                         $tmpstr .= $tmp;
 744                     } else {
 745                         if ($prevcsize == 1) {
 746                             $result .= $tmpstr;
 747                         } else {
 748                             $result .= str_replace(' ', '',
 749                                                    mb_encode_mimeheader($tmpstr,'iso-2022-jp','B',''));
 750                         }
 751                         $tmpstr = $tmp;
 752                         $prevcsize = strlen($tmp);
 753                     }
 754                 }
 755                 if (strlen($tmpstr)) {
 756                     if (strlen(mb_substr($tmpstr, 0, 1)) == 1)
 757                         $result .= $tmpstr;
 758                     else
 759                         $result .= str_replace(' ', '',
 760                                                mb_encode_mimeheader($tmpstr,'iso-2022-jp','B',''));
 761                 }
 762             }
 763             $ret = $result;
 764             break;
 765         case 'decodeheader':
 766             $ret = str_replace("\t", "", $ret);
 767             if (eregi('=\\?([^?]+)\\?(q|b)\\?([^?]+)\\?=', $ret))
 768                 $ret = @mb_decode_mimeheader($ret);
 769             $ret = @mb_convert_encoding($ret, 'EUC-JP', 'AUTO');
 770             break;
 771         case 'downloadfilename':
 772             $useragent = func_get_arg(2);
 773             if (strstr($useragent, 'Windows') !== false ||
 774                 strstr($useragent, 'Mac_') !== false) {
 775                 $ret = mb_convert_encoding($ret, 'SJIS', 'AUTO');
 776             } else {
 777                 $ret = mb_convert_encoding($ret, 'EUC-JP', 'AUTO');
 778 }
 779             break;
 780         case 'wordwrap':
 781             $no_begin = "\x21\x25\x29\x2c\x2e\x3a\x3b\x3f\x5d\x7d\xa1\xf1\xa1\xeb\xa1" .
 782                 "\xc7\xa1\xc9\xa2\xf3\xa1\xec\xa1\xed\xa1\xee\xa1\xa2\xa1\xa3\xa1\xb9" .
 783                 "\xa1\xd3\xa1\xd5\xa1\xd7\xa1\xd9\xa1\xdb\xa1\xcd\xa4\xa1\xa4\xa3\xa4" .
 784                 "\xa5\xa4\xa7\xa4\xa9\xa4\xc3\xa4\xe3\xa4\xe5\xa4\xe7\xa4\xee\xa1\xab" .
 785                 "\xa1\xac\xa1\xb5\xa1\xb6\xa5\xa1\xa5\xa3\xa5\xa5\xa5\xa7\xa5\xa9\xa5" .
 786                 "\xc3\xa5\xe3\xa5\xe5\xa5\xe7\xa5\xee\xa5\xf5\xa5\xf6\xa1\xa6\xa1\xbc" .
 787                 "\xa1\xb3\xa1\xb4\xa1\xaa\xa1\xf3\xa1\xcb\xa1\xa4\xa1\xa5\xa1\xa7\xa1" .
 788                 "\xa8\xa1\xa9\xa1\xcf\xa1\xd1";
 789             $no_end = "\x5c\x24\x28\x5b\x7b\xa1\xf2\x5c\xa1\xc6\xa1\xc8\xa1\xd2\xa1" .
 790                 "\xd4\xa1\xd6\xa1\xd8\xa1\xda\xa1\xcc\xa1\xf0\xa1\xca\xa1\xce\xa1\xd0\xa1\xef";
 791             $wrap = func_get_arg(2);
 792
 793             if (strlen($ret) >= $wrap &&
 794                 substr($ret, 0, 1) != '>' &&
 795                 strpos($ret, 'http://') === FALSE &&
 796                 strpos($ret, 'https://') === FALSE &&
 797                 strpos($ret, 'ftp://') === FALSE) {
 798
 799                 $ret = mb_convert_kana($ret, "KV");
 800
 801                 $line_new = '';
 802                 $ptr = 0;
 803
 804                 while ($ptr < strlen($ret) - 1) {
 805                     $l = mb_strcut($ret, $ptr, $wrap);
 806                     $ptr += strlen($l);
 807                     $tmp = $l;
 808
 809                     $l = mb_strcut($ret, $ptr, 2);
 810                     while (strlen($l) != 0 && mb_strpos($no_begin, $l) !== FALSE ) {
 811                         $tmp .= $l;
 812                         $ptr += strlen($l);
 813                         $l = mb_strcut($ret, $ptr, 1);
 814                     }
 815                     $line_new .= $tmp;
 816                     if ($ptr < strlen($ret) - 1)
 817                         $line_new .= "\n";
 818                 }
 819                 $ret = $line_new;
 820             }
 821             break;
 822         case 'utf7-imap_encode':
 823             $ret = mb_convert_encoding($ret, 'UTF7-IMAP', 'EUC-JP');
 824             break;
 825         case 'utf7-imap_decode':
 826             $ret = mb_convert_encoding($ret, 'EUC-JP', 'UTF7-IMAP');
 827             break;
 828         }
 829     }
 830     return $ret;
 831 }
 832
 833 /**************************
 834  * Japanese extra functions
 835  **************************/
 836
 837 /**
 838  * Japanese decoding function
 839  *
 840  * converts string to euc-jp, if string uses JIS, EUC-JP, ShiftJIS or UTF-8
 841  * charset. Needs mbstring support in php.
 842  * @param string $ret text, that has to be converted
 843  * @return string converted string
 844  * @since 1.5.1
 845  */
 846 function japanese_xtra_decode($ret) {
 847     if (function_exists('mb_detect_encoding')) {
 848         $detect_encoding = @mb_detect_encoding($ret);
 849         if ($detect_encoding == 'JIS' ||
 850             $detect_encoding == 'EUC-JP' ||
 851             $detect_encoding == 'SJIS' ||
 852             $detect_encoding == 'UTF-8') {
 853
 854             $ret = mb_convert_kana(mb_convert_encoding($ret, 'EUC-JP', 'AUTO'), "KV");
 855         }
 856     }
 857     return $ret;
 858 }
 859
 860 /**
 861  * Japanese encoding function
 862  *
 863  * converts string to jis, if string uses JIS, EUC-JP, ShiftJIS or UTF-8
 864  * charset. Needs mbstring support in php.
 865  * @param string $ret text, that has to be converted
 866  * @return string converted text
 867  * @since 1.5.1
 868  */
 869 function japanese_xtra_encode($ret) {
 870     if (function_exists('mb_detect_encoding')) {
 871         $detect_encoding = @mb_detect_encoding($ret);
 872         if ($detect_encoding == 'JIS' ||
 873             $detect_encoding == 'EUC-JP' ||
 874             $detect_encoding == 'SJIS' ||
 875             $detect_encoding == 'UTF-8') {
 876
 877             $ret = mb_convert_encoding(mb_convert_kana($ret, "KV"), 'JIS', 'AUTO');
 878         }
 879     }
 880     return $ret;
 881 }
 882
 883 /**
 884  * Japanese header encoding function
 885  *
 886  * creates base64 encoded header in iso-2022-jp charset
 887  * @param string $ret text, that has to be converted
 888  * @return string mime base64 encoded string
 889  * @since 1.5.1
 890  */
 891 function japanese_xtra_encodeheader($ret) {
 892     if (function_exists('mb_detect_encoding')) {
 893         $result = '';
 894         if (strlen($ret) > 0) {
 895             $tmpstr = mb_substr($ret, 0, 1);
 896             $prevcsize = strlen($tmpstr);
 897             for ($i = 1; $i < mb_strlen($ret); $i++) {
 898                 $tmp = mb_substr($ret, $i, 1);
 899                 if (strlen($tmp) == $prevcsize) {
 900                     $tmpstr .= $tmp;
 901                 } else {
 902                     if ($prevcsize == 1) {
 903                         $result .= $tmpstr;
 904                     } else {
 905                         $result .= str_replace(' ', '',
 906                                                mb_encode_mimeheader($tmpstr,'iso-2022-jp','B',''));
 907                     }
 908                     $tmpstr = $tmp;
 909                     $prevcsize = strlen($tmp);
 910                 }
 911             }
 912             if (strlen($tmpstr)) {
 913                 if (strlen(mb_substr($tmpstr, 0, 1)) == 1)
 914                     $result .= $tmpstr;
 915                 else
 916                     $result .= str_replace(' ', '',
 917                                            mb_encode_mimeheader($tmpstr,'iso-2022-jp','B',''));
 918             }
 919         }
 920         $ret = $result;
 921     }
 922     return $ret;
 923 }
 924
 925 /**
 926  * Japanese header decoding function
 927  *
 928  * return human readable string from mime header. string is returned in euc-jp
 929  * charset.
 930  * @param string $ret header string
 931  * @return string decoded header string
 932  * @since 1.5.1
 933  */
 934 function japanese_xtra_decodeheader($ret) {
 935     if (function_exists('mb_detect_encoding')) {
 936         $ret = str_replace("\t", "", $ret);
 937         if (eregi('=\\?([^?]+)\\?(q|b)\\?([^?]+)\\?=', $ret))
 938             $ret = @mb_decode_mimeheader($ret);
 939         $ret = @mb_convert_encoding($ret, 'EUC-JP', 'AUTO');
 940     }
 941     return $ret;
 942 }
 943
 944 /**
 945  * Japanese downloaded filename processing function
 946  *
 947  * Returns shift-jis or euc-jp encoded file name
 948  * @param string $ret string
 949  * @param string $useragent browser
 950  * @return string converted string
 951  * @since 1.5.1
 952  */
 953 function japanese_xtra_downloadfilename($ret,$useragent) {
 954     if (function_exists('mb_detect_encoding')) {
 955         if (strstr($useragent, 'Windows') !== false ||
 956             strstr($useragent, 'Mac_') !== false) {
 957             $ret = mb_convert_encoding($ret, 'SJIS', 'AUTO');
 958         } else {
 959             $ret = mb_convert_encoding($ret, 'EUC-JP', 'AUTO');
 960         }
 961     }
 962     return $ret;
 963 }
 964
 965 /**
 966  * Japanese wordwrap function
 967  *
 968  * wraps text at set number of symbols
 969  * @param string $ret text
 970  * @param integer $wrap number of symbols per line
 971  * @return string wrapped text
 972  * @since 1.5.1
 973  */
 974 function japanese_xtra_wordwrap($ret,$wrap) {
 975     if (function_exists('mb_detect_encoding')) {
 976         $no_begin = "\x21\x25\x29\x2c\x2e\x3a\x3b\x3f\x5d\x7d\xa1\xf1\xa1\xeb\xa1" .
 977             "\xc7\xa1\xc9\xa2\xf3\xa1\xec\xa1\xed\xa1\xee\xa1\xa2\xa1\xa3\xa1\xb9" .
 978             "\xa1\xd3\xa1\xd5\xa1\xd7\xa1\xd9\xa1\xdb\xa1\xcd\xa4\xa1\xa4\xa3\xa4" .
 979             "\xa5\xa4\xa7\xa4\xa9\xa4\xc3\xa4\xe3\xa4\xe5\xa4\xe7\xa4\xee\xa1\xab" .
 980             "\xa1\xac\xa1\xb5\xa1\xb6\xa5\xa1\xa5\xa3\xa5\xa5\xa5\xa7\xa5\xa9\xa5" .
 981             "\xc3\xa5\xe3\xa5\xe5\xa5\xe7\xa5\xee\xa5\xf5\xa5\xf6\xa1\xa6\xa1\xbc" .
 982             "\xa1\xb3\xa1\xb4\xa1\xaa\xa1\xf3\xa1\xcb\xa1\xa4\xa1\xa5\xa1\xa7\xa1" .
 983             "\xa8\xa1\xa9\xa1\xcf\xa1\xd1";
 984         $no_end = "\x5c\x24\x28\x5b\x7b\xa1\xf2\x5c\xa1\xc6\xa1\xc8\xa1\xd2\xa1" .
 985             "\xd4\xa1\xd6\xa1\xd8\xa1\xda\xa1\xcc\xa1\xf0\xa1\xca\xa1\xce\xa1\xd0\xa1\xef";
 986
 987         if (strlen($ret) >= $wrap &&
 988             substr($ret, 0, 1) != '>' &&
 989             strpos($ret, 'http://') === FALSE &&
 990             strpos($ret, 'https://') === FALSE &&
 991             strpos($ret, 'ftp://') === FALSE) {
 992
 993             $ret = mb_convert_kana($ret, "KV");
 994
 995             $line_new = '';
 996             $ptr = 0;
 997
 998             while ($ptr < strlen($ret) - 1) {
 999                 $l = mb_strcut($ret, $ptr, $wrap);
1000                 $ptr += strlen($l);
1001                 $tmp = $l;
1002
1003                 $l = mb_strcut($ret, $ptr, 2);
1004                 while (strlen($l) != 0 && mb_strpos($no_begin, $l) !== FALSE ) {
1005                     $tmp .= $l;
1006                     $ptr += strlen($l);
1007                     $l = mb_strcut($ret, $ptr, 1);
1008                 }
1009                 $line_new .= $tmp;
1010                 if ($ptr < strlen($ret) - 1)
1011                     $line_new .= "\n";
1012             }
1013             $ret = $line_new;
1014         }
1015     }
1016     return $ret;
1017 }
1018
1019 /**
1020  * Japanese imap folder name encoding function
1021  *
1022  * converts folder name from euc-jp to utf7-imap
1023  * @param string $ret folder name
1024  * @return string converted folder name
1025  * @since 1.5.1
1026  */
1027 function japanese_xtra_utf7_imap_encode($ret){
1028     if (function_exists('mb_detect_encoding')) {
1029         $ret = mb_convert_encoding($ret, 'UTF7-IMAP', 'EUC-JP');
1030     }
1031     return $ret;
1032 }
1033
1034 /**
1035  * Japanese imap folder name decoding function
1036  *
1037  * converts folder name from utf7-imap to euc-jp.
1038  * @param string $ret folder name in utf7-imap
1039  * @return string converted folder name
1040  * @since 1.5.1
1041  */
1042 function japanese_xtra_utf7_imap_decode($ret) {
1043     if (function_exists('mb_detect_encoding')) {
1044         $ret = mb_convert_encoding($ret, 'EUC-JP', 'UTF7-IMAP');
1045     }
1046     return $ret;
1047 }
1048
1049 /**
1050  * Japanese string trimming function
1051  *
1052  * trims string to defined number of symbols
1053  * @param string $ret string
1054  * @param integer $width number of symbols
1055  * @return string trimmed string
1056  * @since 1.5.1
1057  */
1058 function japanese_xtra_strimwidth($ret,$width) {
1059     if (function_exists('mb_detect_encoding')) {
1060         $ret = mb_strimwidth($ret, 0, $width, '...');
1061     }
1062     return $ret;
1063 }
1064
1065 /********************************
1066  * Korean charset extra functions
1067  ********************************/
1068
1069 /**
1070  * Korean downloaded filename processing functions
1071  *
1072  * @param string default return value
1073  * @return string
1074  */
1075 function korean_xtra_downloadfilename($ret) {
1076     $ret = str_replace("\x0D\x0A", '', $ret);  /* Hanmail's CR/LF Clear */
1077     for ($i=0;$i<strlen($ret);$i++) {
1078         if ($ret[$i] >= "\xA1" && $ret[$i] <= "\xFE") {   /* 0xA1 - 0XFE are Valid */
1079             $i++;
1080             continue;
1081         } else if (($ret[$i] >= 'a' && $ret[$i] <= 'z') || /* From Original ereg_replace in download.php */
1082                    ($ret[$i] >= 'A' && $ret[$i] <= 'Z') ||
1083                    ($ret[$i] == '.') || ($ret[$i] == '-')) {
1084             continue;
1085         } else {
1086             $ret[$i] = '_';
1087         }
1088     }
1089     return $ret;
1090 }
1091
1092 /**
1093  * Replaces non-braking spaces inserted by some browsers with regular space
1094  *
1095  * This function can be used to replace non-braking space symbols
1096  * that are inserted in forms by some browsers instead of normal
1097  * space symbol.
1098  *
1099  * @param string $string Text that needs to be cleaned
1100  * @param string $charset Charset used in text
1101  * @return string Cleaned text
1102  */
1103 function cleanup_nbsp($string,$charset) {
1104
1105   // reduce number of case statements
1106   if (stristr('iso-8859-',substr($charset,0,9))){
1107     $output_charset="iso-8859-x";
1108   }
1109   if (stristr('windows-125',substr($charset,0,11))){
1110     $output_charset="cp125x";
1111   }
1112   if (stristr('koi8',substr($charset,0,4))){
1113     $output_charset="koi8-x";
1114   }
1115   if (! isset($output_charset)){
1116     $output_charset=strtolower($charset);
1117   }
1118
1119 // where is non-braking space symbol
1120 switch($output_charset):
1121  case "iso-8859-x":
1122  case "cp125x":
1123  case "iso-2022-jp":
1124   $nbsp="\xA0";
1125   break;
1126  case "koi8-x":
1127    $nbsp="\x9A";
1128    break;
1129  case "utf-8":
1130    $nbsp="\xC2\xA0";
1131    break;
1132  default:
1133    // don't change string if charset is unmatched
1134    return $string;
1135 endswitch;
1136
1137 // return space instead of non-braking space.
1138  return str_replace($nbsp,' ',$string);
1139 }
1140
1141 /**
1142  * Function informs if it is safe to convert given charset to the one that is used by user.
1143  *
1144  * It is safe to use conversion only if user uses utf-8 encoding and when
1145  * converted charset is similar to the one that is used by user.
1146  *
1147  * @param string $input_charset Charset of text that needs to be converted
1148  * @return bool is it possible to convert to user's charset
1149  */
1150 function is_conversion_safe($input_charset) {
1151   global $languages, $sm_notAlias, $default_charset, $loosy_encoding;
1152
1153     if (isset($loosy_encoding) && $loosy_encoding )
1154         return true;
1155
1156  // convert to lower case
1157  $input_charset = strtolower($input_charset);
1158
1159  // Is user's locale Unicode based ?
1160  if ( $default_charset == "utf-8" ) {
1161    return true;
1162  }
1163
1164  // Charsets that are similar
1165 switch ($default_charset):
1166 case "windows-1251":
1167       if ( $input_charset == "iso-8859-5" ||
1168            $input_charset == "koi8-r" ||
1169            $input_charset == "koi8-u" ) {
1170         return true;
1171      } else {
1172         return false;
1173      }
1174 case "windows-1257":
1175   if ( $input_charset == "iso-8859-13" ||
1176        $input_charset == "iso-8859-4" ) {
1177     return true;
1178   } else {
1179     return false;
1180   }
1181 case "iso-8859-4":
1182   if ( $input_charset == "iso-8859-13" ||
1183        $input_charset == "windows-1257" ) {
1184      return true;
1185   } else {
1186      return false;
1187   }
1188 case "iso-8859-5":
1189   if ( $input_charset == "windows-1251" ||
1190        $input_charset == "koi8-r" ||
1191        $input_charset == "koi8-u" ) {
1192      return true;
1193   } else {
1194      return false;
1195   }
1196 case "iso-8859-13":
1197   if ( $input_charset == "iso-8859-4" ||
1198        $input_charset == "windows-1257" ) {
1199      return true;
1200   } else {
1201      return false;
1202   }
1203 case "koi8-r":
1204   if ( $input_charset == "windows-1251" ||
1205        $input_charset == "iso-8859-5" ||
1206        $input_charset == "koi8-u" ) {
1207      return true;
1208   } else {
1209      return false;
1210   }
1211 case "koi8-u":
1212   if ( $input_charset == "windows-1251" ||
1213        $input_charset == "iso-8859-5" ||
1214        $input_charset == "koi8-r" ) {
1215      return true;
1216   } else {
1217      return false;
1218   }
1219 default:
1220    return false;
1221 endswitch;
1222 }
1223 ?>