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'] . '_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($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 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     $ret = $string;
 132   }
 133   return( $ret );
 134 }
 135
 136 /**
 137  * Combined decoding and encoding functions
 138  *
 139  * If conversion is done to charset different that utf-8, unsupported symbols
 140  * will be replaced with question marks.
 141  * @param string $in_charset initial charset
 142  * @param string $string string that has to be converted
 143  * @param string $out_charset final charset
 144  * @param boolean $htmlencode keep htmlspecialchars encoding
 145  * @return string converted string
 146  */
 147 function charset_convert($in_charset,$string,$out_charset,$htmlencode=true) {
 148   $string=charset_decode($in_charset,$string);
 149   $string=charset_encode($string,$out_charset,$htmlencode);
 150   return $string;
 151 }
 152
 153 /**
 154  * Makes charset name suitable for decoding cycles
 155  *
 156  * @param string $charset Name of charset
 157  * @return string $charset Adjusted name of charset
 158  */
 159 function fixcharset($charset) {
 160     // minus removed from function names
 161     $charset=str_replace('-','_',$charset);
 162
 163     // windows-125x and cp125x charsets
 164     $charset=str_replace('windows_','cp',$charset);
 165
 166     // ibm > cp
 167     $charset=str_replace('ibm','cp',$charset);
 168
 169     // iso-8859-8-i -> iso-8859-8
 170     // use same cycle until I'll find differences
 171     $charset=str_replace('iso_8859_8_i','iso_8859_8',$charset);
 172
 173     return $charset;
 174 }
 175
 176 /**
 177  * Set up the language to be output
 178  * if $do_search is true, then scan the browser information
 179  * for a possible language that we know
 180  *
 181  * Function sets system locale environment (LC_ALL, LANG, LANGUAGE),
 182  * gettext translation bindings and html header information.
 183  *
 184  * Function returns error codes, if there is some fatal error.
 185  *  0 = no error,
 186  *  1 = mbstring support is not present,
 187  *  2 = mbstring support is not present, user's translation reverted to en_US.
 188  *
 189  * @param string $sm_language translation used by user's interface
 190  * @param bool $do_search use browser's preferred language detection functions. Defaults to false.
 191  * @param bool $default set $sm_language to $squirrelmail_default_language if language detection fails or language is not set. Defaults to false.
 192  * @return int function execution error codes.
 193  */
 194 function set_up_language($sm_language, $do_search = false, $default = false) {
 195
 196     static $SetupAlready = 0;
 197     global $use_gettext, $languages,
 198            $squirrelmail_language, $squirrelmail_default_language,
 199            $sm_notAlias, $username, $data_dir;
 200
 201     if ($SetupAlready) {
 202         return;
 203     }
 204
 205     $SetupAlready = TRUE;
 206     sqgetGlobalVar('HTTP_ACCEPT_LANGUAGE',  $accept_lang, SQ_SERVER);
 207
 208     if ($do_search && ! $sm_language && isset($accept_lang)) {
 209         $sm_language = substr($accept_lang, 0, 2);
 210     }
 211
 212     if ((!$sm_language||$default) && isset($squirrelmail_default_language)) {
 213         $squirrelmail_language = $squirrelmail_default_language;
 214         $sm_language = $squirrelmail_default_language;
 215     }
 216     $sm_notAlias = $sm_language;
 217
 218     // Catching removed translation
 219     // System reverts to English translation if user prefs contain translation
 220     // that is not available in $languages array
 221     if (!isset($languages[$sm_notAlias])) {
 222       $sm_notAlias="en_US";
 223     }
 224
 225     while (isset($languages[$sm_notAlias]['ALIAS'])) {
 226         $sm_notAlias = $languages[$sm_notAlias]['ALIAS'];
 227     }
 228
 229     if ( isset($sm_language) &&
 230          $use_gettext &&
 231          $sm_language != '' &&
 232          isset($languages[$sm_notAlias]['CHARSET']) ) {
 233         bindtextdomain( 'squirrelmail', SM_PATH . 'locale/' );
 234         textdomain( 'squirrelmail' );
 235         if (function_exists('bind_textdomain_codeset')) {
 236           if ($sm_notAlias == 'ja_JP') {
 237             bind_textdomain_codeset ("squirrelmail", 'EUC-JP');
 238             } else {
 239               bind_textdomain_codeset ("squirrelmail", $languages[$sm_notAlias]['CHARSET'] );
 240             }
 241         }
 242         if (isset($languages[$sm_notAlias]['LOCALE'])){
 243           $longlocale=$languages[$sm_notAlias]['LOCALE'];
 244         } else {
 245           $longlocale=$sm_notAlias;
 246         }
 247         if ( !ini_get('safe_mode') &&
 248              getenv( 'LC_ALL' ) != $longlocale ) {
 249             putenv( "LC_ALL=$longlocale" );
 250             putenv( "LANG=$longlocale" );
 251             putenv( "LANGUAGE=$longlocale" );
 252         }
 253         setlocale(LC_ALL, $longlocale);
 254
 255         // Set text direction/alignment variables
 256         if (isset($languages[$sm_notAlias]['DIR']) &&
 257             $languages[$sm_notAlias]['DIR'] == 'rtl') {
 258           /**
 259            * Text direction
 260            * @global string $text_direction
 261            */
 262           $text_direction='rtl';
 263           /**
 264            * Left alignment
 265            * @global string $left_align
 266            */
 267           $left_align='right';
 268           /**
 269            * Right alignment
 270            * @global string $right_align
 271            */
 272           $right_align='left';
 273         } else {
 274           $text_direction='ltr';
 275           $left_align='left';
 276           $right_align='right';
 277         }
 278
 279         $squirrelmail_language = $sm_notAlias;
 280         if ($squirrelmail_language == 'ja_JP') {
 281             header ('Content-Type: text/html; charset=EUC-JP');
 282             if (!function_exists('mb_internal_encoding')) {
 283               // Error messages can't be displayed here
 284               $error = 1;
 285               // Revert to English if possible.
 286               if (function_exists('setPref')  && $username!='' && $data_dir!="") {
 287                 setPref($data_dir, $username, 'language', "en_US");
 288                 $error = 2;
 289               }
 290               // stop further execution in order not to get php errors on mb_internal_encoding().
 291               return $error;
 292             }
 293             if (function_exists('mb_language')) {
 294                 mb_language('Japanese');
 295             }
 296             mb_internal_encoding('EUC-JP');
 297             mb_http_output('pass');
 298         } else {
 299         header( 'Content-Type: text/html; charset=' . $languages[$sm_notAlias]['CHARSET'] );
 300     }
 301 }
 302     return 0;
 303 }
 304
 305 /**
 306  * Sets default_charset variable according to the one that is used by user's translations.
 307  *
 308  * Function changes global $default_charset variable in order to be sure, that it
 309  * contains charset used by user's translation. Sanity of $squirrelmail_default_language
 310  * and $default_charset combination provided in SquirrelMail config is also tested.
 311  *
 312  * There can be a $default_charset setting in the
 313  * config.php file, but the user may have a different language
 314  * selected for a user interface. This function checks the
 315  * language selected by the user and tags the outgoing messages
 316  * with the appropriate charset corresponding to the language
 317  * selection. This is "more right" (tm), than just stamping the
 318  * message blindly with the system-wide $default_charset.
 319  */
 320 function set_my_charset(){
 321     global $data_dir, $username, $default_charset, $languages, $squirrelmail_default_language;
 322
 323     $my_language = getPref($data_dir, $username, 'language');
 324     if (!$my_language) {
 325         $my_language = $squirrelmail_default_language ;
 326     }
 327     // Catch removed translation
 328     if (!isset($languages[$my_language])) {
 329       $my_language="en_US";
 330     }
 331     while (isset($languages[$my_language]['ALIAS'])) {
 332         $my_language = $languages[$my_language]['ALIAS'];
 333     }
 334     $my_charset = $languages[$my_language]['CHARSET'];
 335     if ($my_charset) {
 336         $default_charset = $my_charset;
 337     }
 338 }
 339
 340 /* ------------------------------ main --------------------------- */
 341
 342 global $squirrelmail_language, $languages, $use_gettext;
 343
 344 if (! isset($squirrelmail_language)) {
 345     $squirrelmail_language = '';
 346 }
 347
 348 /**
 349  * Array specifies the available translations.
 350  *
 351  * Structure of array:
 352  * $languages['language']['variable'] = 'value'
 353  *
 354  * Possible 'variable' names:
 355  *  NAME      - Translation name in English
 356  *  CHARSET   - Encoding used by translation
 357  *  ALIAS     - used when 'language' is only short name and 'value' should provide long language name
 358  *  ALTNAME   - Native translation name. Any 8bit symbols must be html encoded.
 359  *  LOCALE    - Full locale name (in xx_XX.charset format)
 360  *  DIR       - Text direction. Used to define Right-to-Left languages. Possible values 'rtl' or 'ltr'. If undefined - defaults to 'ltr'
 361  *  XTRA_CODE - translation uses special functions. See doc/i18n.txt
 362  *
 363  * Each 'language' definition requires NAME+CHARSET or ALIAS variables.
 364  *
 365  * @name $languages
 366  * @global array $languages
 367  */
 368 $languages['bg_BG']['NAME']    = 'Bulgarian';
 369 $languages['bg_BG']['ALTNAME'] = '&#1041;&#1098;&#1083;&#1075;&#1072;&#1088;&#1089;&#1082;&#1080;';
 370 $languages['bg_BG']['CHARSET'] = 'windows-1251';
 371 $languages['bg_BG']['LOCALE']  = 'bg_BG.CP1251';
 372 $languages['bg']['ALIAS'] = 'bg_BG';
 373
 374 $languages['ca_ES']['NAME']    = 'Catalan';
 375 $languages['ca_ES']['CHARSET'] = 'iso-8859-1';
 376 $languages['ca_ES']['LOCALE']  = 'ca_ES.ISO8859-1';
 377 $languages['ca']['ALIAS'] = 'ca_ES';
 378
 379 $languages['cs_CZ']['NAME']    = 'Czech';
 380 $languages['cs_CZ']['ALTNAME'] = '&#268;e&scaron;tina';
 381 $languages['cs_CZ']['CHARSET'] = 'iso-8859-2';
 382 $languages['cs_CZ']['LOCALE']  = 'cs_CZ.ISO8859-2';
 383 $languages['cs']['ALIAS']      = 'cs_CZ';
 384
 385 $languages['cy_GB']['NAME']    = 'Welsh';
 386 $languages['cy_GB']['ALTNAME'] = 'Cymraeg';
 387 $languages['cy_GB']['CHARSET'] = 'iso-8859-1';
 388 $languages['cy_GB']['LOCALE']  = 'cy_GB.ISO8859-1';
 389 $languages['cy']['ALIAS'] = 'cy_GB';
 390
 391 // Danish locale is da_DK.
 392 $languages['da_DK']['NAME']    = 'Danish';
 393 $languages['da_DK']['ALTNAME'] = 'Dansk';
 394 $languages['da_DK']['CHARSET'] = 'iso-8859-1';
 395 $languages['da_DK']['LOCALE']  = 'da_DK.ISO8859-1';
 396 $languages['da']['ALIAS'] = 'da_DK';
 397
 398 $languages['de_DE']['NAME']    = 'German';
 399 $languages['de_DE']['ALTNAME']    = 'Deutsch';
 400 $languages['de_DE']['CHARSET'] = 'iso-8859-1';
 401 $languages['de_DE']['LOCALE']  = 'de_DE.ISO8859-1';
 402 $languages['de']['ALIAS'] = 'de_DE';
 403
 404 $languages['el_GR']['NAME']    = 'Greek';
 405 $languages['el_GR']['ALTNAME'] = '&Epsilon;&lambda;&lambda;&eta;&nu;&iota;&kappa;&#940;';
 406 $languages['el_GR']['CHARSET'] = 'iso-8859-7';
 407 $languages['el_GR']['LOCALE']  = 'el_GR.ISO8859-7';
 408 $languages['el']['ALIAS'] = 'el_GR';
 409
 410 $languages['en_GB']['NAME']    = 'British';
 411 $languages['en_GB']['CHARSET'] = 'iso-8859-15';
 412 $languages['en_GB']['LOCALE']  = 'en_GB.ISO8859-15';
 413
 414 $languages['en_US']['NAME']    = 'English';
 415 $languages['en_US']['CHARSET'] = 'iso-8859-1';
 416 $languages['en_US']['LOCALE']  = 'en_US.ISO8859-1';
 417 $languages['en']['ALIAS'] = 'en_US';
 418
 419 $languages['es_ES']['NAME']    = 'Spanish';
 420 $languages['es_ES']['ALTNAME'] = 'Espa&ntilde;ol';
 421 $languages['es_ES']['CHARSET'] = 'iso-8859-1';
 422 $languages['es_ES']['LOCALE']  = 'es_ES.ISO8859-1';
 423 $languages['es']['ALIAS'] = 'es_ES';
 424
 425 $languages['et_EE']['NAME']    = 'Estonian';
 426 $languages['et_EE']['CHARSET'] = 'iso-8859-15';
 427 $languages['et_EE']['LOCALE']  = 'et_EE.ISO8859-15';
 428 $languages['et']['ALIAS'] = 'et_EE';
 429
 430 $languages['eu_ES']['NAME']    = 'Basque';
 431 $languages['eu_ES']['CHARSET'] = 'iso-8859-1';
 432 $languages['eu_ES']['LOCALE']  = 'eu_ES.ISO8859-1';
 433 $languages['eu']['ALIAS'] = 'eu_ES';
 434
 435 $languages['fo_FO']['NAME']    = 'Faroese';
 436 $languages['fo_FO']['CHARSET'] = 'iso-8859-1';
 437 $languages['fo_FO']['LOCALE']  = 'fo_FO.ISO8859-1';
 438 $languages['fo']['ALIAS'] = 'fo_FO';
 439
 440 $languages['fi_FI']['NAME']    = 'Finnish';
 441 $languages['fi_FI']['ALTNAME'] = 'Suomi';
 442 $languages['fi_FI']['CHARSET'] = 'iso-8859-1';
 443 $languages['fi_FI']['LOCALE']  = 'fi_FI.ISO8859-1';
 444 $languages['fi']['ALIAS'] = 'fi_FI';
 445
 446 $languages['fr_FR']['NAME']    = 'French';
 447 $languages['fr_FR']['ALTNAME'] = 'Fran&#231;ais';
 448 $languages['fr_FR']['CHARSET'] = 'iso-8859-1';
 449 $languages['fr_FR']['LOCALE']  = 'fr_FR.ISO8859-1';
 450 $languages['fr']['ALIAS'] = 'fr_FR';
 451
 452 $languages['hr_HR']['NAME']    = 'Croatian';
 453 $languages['hr_HR']['CHARSET'] = 'iso-8859-2';
 454 $languages['hr_HR']['LOCALE']  = 'hr_HR.ISO8859-2';
 455 $languages['hr']['ALIAS'] = 'hr_HR';
 456
 457 $languages['hu_HU']['NAME']    = 'Hungarian';
 458 $languages['hu_HU']['ALTNAME'] = 'Magyar';
 459 $languages['hu_HU']['CHARSET'] = 'iso-8859-2';
 460 $languages['hu_HU']['LOCALE']  = 'hu_HU.ISO8859-2';
 461 $languages['hu']['ALIAS'] = 'hu_HU';
 462
 463 $languages['id_ID']['NAME']    = 'Indonesian';
 464 $languages['id_ID']['ALTNAME'] = 'Bahasa Indonesia';
 465 $languages['id_ID']['CHARSET'] = 'iso-8859-1';
 466 $languages['id_ID']['LOCALE']  = 'id_ID.ISO8859-1';
 467 $languages['id']['ALIAS'] = 'id_ID';
 468
 469 $languages['is_IS']['NAME']    = 'Icelandic';
 470 $languages['is_IS']['ALTNAME'] = '&Iacute;slenska';
 471 $languages['is_IS']['CHARSET'] = 'iso-8859-1';
 472 $languages['is_IS']['LOCALE']  = 'is_IS.ISO8859-1';
 473 $languages['is']['ALIAS'] = 'is_IS';
 474
 475 $languages['it_IT']['NAME']    = 'Italian';
 476 $languages['it_IT']['CHARSET'] = 'iso-8859-1';
 477 $languages['it_IT']['LOCALE']  = 'it_IT.ISO8859-1';
 478 $languages['it']['ALIAS'] = 'it_IT';
 479
 480 $languages['ja_JP']['NAME']    = 'Japanese';
 481 $languages['ja_JP']['ALTNAME'] = '&#26085;&#26412;&#35486;';
 482 $languages['ja_JP']['CHARSET'] = 'iso-2022-jp';
 483 $languages['ja_JP']['LOCALE'] = 'ja_JP.EUC-JP';
 484 $languages['ja_JP']['XTRA_CODE'] = 'japanese_xtra';
 485 $languages['ja']['ALIAS'] = 'ja_JP';
 486
 487 $languages['ko_KR']['NAME']    = 'Korean';
 488 $languages['ko_KR']['CHARSET'] = 'euc-KR';
 489 $languages['ko_KR']['LOCALE']  = 'ko_KR.EUC-KR';
 490 $languages['ko_KR']['XTRA_CODE'] = 'korean_xtra';
 491 $languages['ko']['ALIAS'] = 'ko_KR';
 492
 493 $languages['lt_LT']['NAME']    = 'Lithuanian';
 494 $languages['lt_LT']['ALTNAME'] = 'Lietuvi&#371;';
 495 $languages['lt_LT']['CHARSET'] = 'utf-8';
 496 $languages['lt_LT']['LOCALE'] = 'lt_LT.UTF-8';
 497 $languages['lt']['ALIAS'] = 'lt_LT';
 498
 499 $languages['nl_NL']['NAME']    = 'Dutch';
 500 $languages['nl_NL']['ALTNAME'] = 'Nederlands';
 501 $languages['nl_NL']['CHARSET'] = 'iso-8859-1';
 502 $languages['nl_NL']['LOCALE']  = 'nl_NL.ISO8859-1';
 503 $languages['nl']['ALIAS'] = 'nl_NL';
 504
 505 $languages['ms_MY']['NAME']    = 'Malay';
 506 $languages['ms_MY']['ALTNAME'] = 'Bahasa Melayu';
 507 $languages['ms_MY']['CHARSET'] = 'iso-8859-1';
 508 $languages['ms_MY']['LOCALE']  = 'ms_MY.ISO8859-1';
 509 $languages['my']['ALIAS'] = 'ms_MY';
 510
 511 $languages['nb_NO']['NAME']    = 'Norwegian (Bokm&aring;l)';
 512 $languages['nb_NO']['ALTNAME'] = 'Norsk (Bokm&aring;l)';
 513 $languages['nb_NO']['CHARSET'] = 'iso-8859-1';
 514 $languages['nb_NO']['LOCALE']  = 'nb_NO.ISO8859-1';
 515 $languages['nb']['ALIAS'] = 'nb_NO';
 516
 517 $languages['nn_NO']['NAME']    = 'Norwegian (Nynorsk)';
 518 $languages['nn_NO']['ALTNAME'] = 'Norsk (Nynorsk)';
 519 $languages['nn_NO']['CHARSET'] = 'iso-8859-1';
 520 $languages['nn_NO']['LOCALE']  = 'nn_NO.ISO8859-1';
 521
 522 $languages['pl_PL']['NAME']    = 'Polish';
 523 $languages['pl_PL']['ALTNAME'] = 'Polski';
 524 $languages['pl_PL']['CHARSET'] = 'iso-8859-2';
 525 $languages['pl_PL']['LOCALE']  = 'pl_PL.ISO8859-2';
 526 $languages['pl']['ALIAS'] = 'pl_PL';
 527
 528 $languages['pt_PT']['NAME'] = 'Portuguese (Portugal)';
 529 $languages['pt_PT']['CHARSET'] = 'iso-8859-1';
 530 $languages['pt_PT']['LOCALE']  = 'pt_PT.ISO8859-1';
 531 $languages['pt']['ALIAS'] = 'pt_PT';
 532
 533 $languages['pt_BR']['NAME']    = 'Portuguese (Brazil)';
 534 $languages['pt_BR']['ALTNAME'] = 'Portugu&ecirc;s do Brasil';
 535 $languages['pt_BR']['CHARSET'] = 'iso-8859-1';
 536 $languages['pt_BR']['LOCALE']  = 'pt_BR.ISO8859-1';
 537
 538 $languages['ro_RO']['NAME']    = 'Romanian';
 539 $languages['ro_RO']['ALTNAME'] = 'Rom&acirc;n&#259;';
 540 $languages['ro_RO']['CHARSET'] = 'iso-8859-2';
 541 $languages['ro_RO']['LOCALE']  = 'ro_RO.ISO8859-2';
 542 $languages['ro']['ALIAS'] = 'ro_RO';
 543
 544 $languages['ru_RU']['NAME']    = 'Russian';
 545 $languages['ru_RU']['ALTNAME'] = '&#1056;&#1091;&#1089;&#1089;&#1082;&#1080;&#1081;';
 546 $languages['ru_RU']['CHARSET'] = 'utf-8';
 547 $languages['ru_RU']['LOCALE']  = 'ru_RU.UTF-8';
 548 $languages['ru']['ALIAS'] = 'ru_RU';
 549
 550 $languages['sk_SK']['NAME']    = 'Slovak';
 551 $languages['sk_SK']['CHARSET'] = 'iso-8859-2';
 552 $languages['sk_SK']['LOCALE']  = 'sk_SK.ISO8859-2';
 553 $languages['sk']['ALIAS'] = 'sk_SK';
 554
 555 $languages['sl_SI']['NAME']    = 'Slovenian';
 556 $languages['sl_SI']['ALTNAME'] = 'Sloven&scaron;&#269;ina';
 557 $languages['sl_SI']['CHARSET'] = 'iso-8859-2';
 558 $languages['sl_SI']['LOCALE']  = 'sl_SI.ISO8859-2';
 559 $languages['sl']['ALIAS'] = 'sl_SI';
 560
 561 $languages['sr_YU']['NAME']    = 'Serbian';
 562 $languages['sr_YU']['ALTNAME'] = 'Srpski';
 563 $languages['sr_YU']['CHARSET'] = 'iso-8859-2';
 564 $languages['sr_YU']['LOCALE']  = 'sr_YU.ISO8859-2';
 565 $languages['sr']['ALIAS'] = 'sr_YU';
 566
 567 $languages['sv_SE']['NAME']    = 'Swedish';
 568 $languages['sv_SE']['ALTNAME'] = 'Svenska';
 569 $languages['sv_SE']['CHARSET'] = 'iso-8859-1';
 570 $languages['sv_SE']['LOCALE']  = 'sv_SE.ISO8859-1';
 571 $languages['sv']['ALIAS'] = 'sv_SE';
 572
 573 $languages['th_TH']['NAME']    = 'Thai';
 574 $languages['th_TH']['CHARSET'] = 'tis-620';
 575 $languages['th_TH']['LOCALE']  = 'th_TH.TIS-620';
 576 $languages['th']['ALIAS'] = 'th_TH';
 577
 578 $languages['tl_PH']['NAME']    = 'Tagalog';
 579 $languages['tl_PH']['CHARSET'] = 'iso-8859-1';
 580 $languages['tl_PH']['LOCALE']  = 'tl_PH.ISO8859-1';
 581 $languages['tl']['ALIAS'] = 'tl_PH';
 582
 583 $languages['tr_TR']['NAME']    = 'Turkish';
 584 $languages['tr_TR']['CHARSET'] = 'iso-8859-9';
 585 $languages['tr_TR']['LOCALE']  = 'tr_TR.ISO8859-9';
 586 $languages['tr']['ALIAS'] = 'tr_TR';
 587
 588 $languages['zh_TW']['NAME']    = 'Chinese Trad';
 589 $languages['zh_TW']['CHARSET'] = 'big5';
 590 $languages['zh_TW']['LOCALE']  = 'zh_TW.BIG5';
 591 $languages['tw']['ALIAS'] = 'zh_TW';
 592
 593 $languages['zh_CN']['NAME']    = 'Chinese Simp';
 594 $languages['zh_CN']['CHARSET'] = 'gb2312';
 595 $languages['zh_CN']['LOCALE']  = 'zh_CN.GB2312';
 596 $languages['cn']['ALIAS'] = 'zh_CN';
 597
 598 $languages['uk_UA']['NAME']    = 'Ukrainian';
 599 $languages['uk_UA']['CHARSET'] = 'koi8-u';
 600 $languages['uk_UA']['LOCALE']  = 'uk_UA.KOI8-U';
 601 $languages['uk']['ALIAS'] = 'uk_UA';
 602
 603 $languages['ru_UA']['NAME']    = 'Russian (Ukrainian)';
 604 $languages['ru_UA']['CHARSET'] = 'koi8-r';
 605 $languages['ru_UA']['LOCALE']  = 'ru_UA.KOI8-R';
 606
 607 /*
 608 $languages['vi_VN']['NAME']    = 'Vietnamese';
 609 $languages['vi_VN']['CHARSET'] = 'utf-8';
 610 $languages['vi']['ALIAS'] = 'vi_VN';
 611 */
 612
 613 // Right to left languages
 614 $languages['ar']['NAME']    = 'Arabic';
 615 $languages['ar']['CHARSET'] = 'windows-1256';
 616 $languages['ar']['DIR']     = 'rtl';
 617
 618 $languages['fa_IR']['NAME']    = 'Farsi';
 619 $languages['fa_IR']['CHARSET'] = 'utf-8';
 620 $languages['fa_IR']['DIR']     = 'rtl';
 621 $languages['fa_IR']['LOCALE']  = 'fa_IR.UTF-8';
 622 $languages['fa']['ALIAS']      = 'fa_IR';
 623
 624 $languages['he_IL']['NAME']    = 'Hebrew';
 625 $languages['he_IL']['CHARSET'] = 'windows-1255';
 626 $languages['he_IL']['LOCALE']  = 'he_IL.CP1255';
 627 $languages['he_IL']['DIR']     = 'rtl';
 628 $languages['he']['ALIAS']      = 'he_IL';
 629
 630 /* Detect whether gettext is installed. */
 631 $gettext_flags = 0;
 632 if (function_exists('_')) {
 633     $gettext_flags += 1;
 634 }
 635 if (function_exists('bindtextdomain')) {
 636     $gettext_flags += 2;
 637 }
 638 if (function_exists('textdomain')) {
 639     $gettext_flags += 4;
 640 }
 641
 642 /* If gettext is fully loaded, cool */
 643 if ($gettext_flags == 7) {
 644     $use_gettext = true;
 645 }
 646 /* If we can fake gettext, try that */
 647 elseif ($gettext_flags == 0) {
 648     $use_gettext = true;
 649     include_once(SM_PATH . 'functions/gettext.php');
 650 } else {
 651     /* Uh-ho.  A weird install */
 652     if (! $gettext_flags & 1) {
 653       /**
 654        * Function is used as replacement in broken installs
 655        * @ignore
 656        */
 657         function _($str) {
 658             return $str;
 659         }
 660     }
 661     if (! $gettext_flags & 2) {
 662       /**
 663        * Function is used as replacement in broken installs
 664        * @ignore
 665        */
 666         function bindtextdomain() {
 667             return;
 668         }
 669     }
 670     if (! $gettext_flags & 4) {
 671       /**
 672        * Function is used as replacemet in broken installs
 673        * @ignore
 674        */
 675         function textdomain() {
 676             return;
 677         }
 678     }
 679 }
 680
 681
 682 /**
 683  * Japanese charset extra function
 684  *
 685  * Action performed by function is defined by first argument.
 686  * Default return value is defined by second argument.
 687  * Use of third argument depends on action.
 688  *
 689  * @param string $action action performed by this function.
 690  *    possible values:
 691  *  decode - convert returned string to euc-jp. third argument unused
 692  *  encode - convert returned string to jis. third argument unused
 693  *  strimwidth - third argument=$width. trims string to $width symbols.
 694  *  encodeheader - create base64 encoded header in iso-2022-jp. third argument unused
 695  *  decodeheader - return human readable string from mime header. string is returned in euc-jp. third argument unused
 696  *  downloadfilename - third argument $useragent. Arguments provide browser info. Returns shift-jis or euc-jp encoded file name
 697  *  wordwrap - third argument=$wrap. wraps text at $wrap symbols
 698  *  utf7-imap_encode - returns string converted from euc-jp to utf7-imap. third argument unused
 699  *  utf7-imap_decode - returns string converted from utf7-imap to euc-jp. third argument unused
 700  * @param string $ret default return value
 701  */
 702 function japanese_xtra() {
 703     $ret = func_get_arg(1);  /* default return value */
 704     if (function_exists('mb_detect_encoding')) {
 705         switch (func_get_arg(0)) { /* action */
 706         case 'decode':
 707             $detect_encoding = @mb_detect_encoding($ret);
 708             if ($detect_encoding == 'JIS' ||
 709                 $detect_encoding == 'EUC-JP' ||
 710                 $detect_encoding == 'SJIS' ||
 711                 $detect_encoding == 'UTF-8') {
 712
 713                 $ret = mb_convert_kana(mb_convert_encoding($ret, 'EUC-JP', 'AUTO'), "KV");
 714             }
 715             break;
 716         case 'encode':
 717             $detect_encoding = @mb_detect_encoding($ret);
 718             if ($detect_encoding == 'JIS' ||
 719                 $detect_encoding == 'EUC-JP' ||
 720                 $detect_encoding == 'SJIS' ||
 721                 $detect_encoding == 'UTF-8') {
 722
 723                 $ret = mb_convert_encoding(mb_convert_kana($ret, "KV"), 'JIS', 'AUTO');
 724             }
 725             break;
 726         case 'strimwidth':
 727             $width = func_get_arg(2);
 728             $ret = mb_strimwidth($ret, 0, $width, '...');
 729             break;
 730         case 'encodeheader':
 731             $result = '';
 732             if (strlen($ret) > 0) {
 733                 $tmpstr = mb_substr($ret, 0, 1);
 734                 $prevcsize = strlen($tmpstr);
 735                 for ($i = 1; $i < mb_strlen($ret); $i++) {
 736                     $tmp = mb_substr($ret, $i, 1);
 737                     if (strlen($tmp) == $prevcsize) {
 738                         $tmpstr .= $tmp;
 739                     } else {
 740                         if ($prevcsize == 1) {
 741                             $result .= $tmpstr;
 742                         } else {
 743                             $result .= str_replace(' ', '',
 744                                                    mb_encode_mimeheader($tmpstr,'iso-2022-jp','B',''));
 745                         }
 746                         $tmpstr = $tmp;
 747                         $prevcsize = strlen($tmp);
 748                     }
 749                 }
 750                 if (strlen($tmpstr)) {
 751                     if (strlen(mb_substr($tmpstr, 0, 1)) == 1)
 752                         $result .= $tmpstr;
 753                     else
 754                         $result .= str_replace(' ', '',
 755                                                mb_encode_mimeheader($tmpstr,'iso-2022-jp','B',''));
 756                 }
 757             }
 758             $ret = $result;
 759             break;
 760         case 'decodeheader':
 761             $ret = str_replace("\t", "", $ret);
 762             if (eregi('=\\?([^?]+)\\?(q|b)\\?([^?]+)\\?=', $ret))
 763                 $ret = @mb_decode_mimeheader($ret);
 764             $ret = @mb_convert_encoding($ret, 'EUC-JP', 'AUTO');
 765             break;
 766         case 'downloadfilename':
 767             $useragent = func_get_arg(2);
 768             if (strstr($useragent, 'Windows') !== false ||
 769                 strstr($useragent, 'Mac_') !== false) {
 770                 $ret = mb_convert_encoding($ret, 'SJIS', 'AUTO');
 771             } else {
 772                 $ret = mb_convert_encoding($ret, 'EUC-JP', 'AUTO');
 773 }
 774             break;
 775         case 'wordwrap':
 776             $no_begin = "\x21\x25\x29\x2c\x2e\x3a\x3b\x3f\x5d\x7d\xa1\xf1\xa1\xeb\xa1" .
 777                 "\xc7\xa1\xc9\xa2\xf3\xa1\xec\xa1\xed\xa1\xee\xa1\xa2\xa1\xa3\xa1\xb9" .
 778                 "\xa1\xd3\xa1\xd5\xa1\xd7\xa1\xd9\xa1\xdb\xa1\xcd\xa4\xa1\xa4\xa3\xa4" .
 779                 "\xa5\xa4\xa7\xa4\xa9\xa4\xc3\xa4\xe3\xa4\xe5\xa4\xe7\xa4\xee\xa1\xab" .
 780                 "\xa1\xac\xa1\xb5\xa1\xb6\xa5\xa1\xa5\xa3\xa5\xa5\xa5\xa7\xa5\xa9\xa5" .
 781                 "\xc3\xa5\xe3\xa5\xe5\xa5\xe7\xa5\xee\xa5\xf5\xa5\xf6\xa1\xa6\xa1\xbc" .
 782                 "\xa1\xb3\xa1\xb4\xa1\xaa\xa1\xf3\xa1\xcb\xa1\xa4\xa1\xa5\xa1\xa7\xa1" .
 783                 "\xa8\xa1\xa9\xa1\xcf\xa1\xd1";
 784             $no_end = "\x5c\x24\x28\x5b\x7b\xa1\xf2\x5c\xa1\xc6\xa1\xc8\xa1\xd2\xa1" .
 785                 "\xd4\xa1\xd6\xa1\xd8\xa1\xda\xa1\xcc\xa1\xf0\xa1\xca\xa1\xce\xa1\xd0\xa1\xef";
 786             $wrap = func_get_arg(2);
 787
 788             if (strlen($ret) >= $wrap &&
 789                 substr($ret, 0, 1) != '>' &&
 790                 strpos($ret, 'http://') === FALSE &&
 791                 strpos($ret, 'https://') === FALSE &&
 792                 strpos($ret, 'ftp://') === FALSE) {
 793
 794                 $ret = mb_convert_kana($ret, "KV");
 795
 796                 $line_new = '';
 797                 $ptr = 0;
 798
 799                 while ($ptr < strlen($ret) - 1) {
 800                     $l = mb_strcut($ret, $ptr, $wrap);
 801                     $ptr += strlen($l);
 802                     $tmp = $l;
 803
 804                     $l = mb_strcut($ret, $ptr, 2);
 805                     while (strlen($l) != 0 && mb_strpos($no_begin, $l) !== FALSE ) {
 806                         $tmp .= $l;
 807                         $ptr += strlen($l);
 808                         $l = mb_strcut($ret, $ptr, 1);
 809                     }
 810                     $line_new .= $tmp;
 811                     if ($ptr < strlen($ret) - 1)
 812                         $line_new .= "\n";
 813                 }
 814                 $ret = $line_new;
 815             }
 816             break;
 817         case 'utf7-imap_encode':
 818             $ret = mb_convert_encoding($ret, 'UTF7-IMAP', 'EUC-JP');
 819             break;
 820         case 'utf7-imap_decode':
 821             $ret = mb_convert_encoding($ret, 'EUC-JP', 'UTF7-IMAP');
 822             break;
 823         }
 824     }
 825     return $ret;
 826 }
 827
 828 /**************************
 829  * Japanese extra functions
 830  **************************/
 831
 832 /**
 833  * Japanese decoding function
 834  * @since 1.5.1
 835  */
 836 function japanese_xtra_decode($ret) {
 837     if (function_exists('mb_detect_encoding')) {
 838         $detect_encoding = @mb_detect_encoding($ret);
 839         if ($detect_encoding == 'JIS' ||
 840             $detect_encoding == 'EUC-JP' ||
 841             $detect_encoding == 'SJIS' ||
 842             $detect_encoding == 'UTF-8') {
 843
 844             $ret = mb_convert_kana(mb_convert_encoding($ret, 'EUC-JP', 'AUTO'), "KV");
 845         }
 846     }
 847     return $ret;
 848 }
 849
 850 /**
 851  * Japanese encoding function
 852  * @since 1.5.1
 853  */
 854 function japanese_xtra_encode($ret) {
 855     if (function_exists('mb_detect_encoding')) {
 856         $detect_encoding = @mb_detect_encoding($ret);
 857         if ($detect_encoding == 'JIS' ||
 858             $detect_encoding == 'EUC-JP' ||
 859             $detect_encoding == 'SJIS' ||
 860             $detect_encoding == 'UTF-8') {
 861
 862             $ret = mb_convert_encoding(mb_convert_kana($ret, "KV"), 'JIS', 'AUTO');
 863         }
 864     }
 865     return $ret;
 866 }
 867
 868 /**
 869  * Japanese header encoding function
 870  * @since 1.5.1
 871  */
 872 function japanese_xtra_encodeheader($ret) {
 873     if (function_exists('mb_detect_encoding')) {
 874         $result = '';
 875         if (strlen($ret) > 0) {
 876             $tmpstr = mb_substr($ret, 0, 1);
 877             $prevcsize = strlen($tmpstr);
 878             for ($i = 1; $i < mb_strlen($ret); $i++) {
 879                 $tmp = mb_substr($ret, $i, 1);
 880                 if (strlen($tmp) == $prevcsize) {
 881                     $tmpstr .= $tmp;
 882                 } else {
 883                     if ($prevcsize == 1) {
 884                         $result .= $tmpstr;
 885                     } else {
 886                         $result .= str_replace(' ', '',
 887                                                mb_encode_mimeheader($tmpstr,'iso-2022-jp','B',''));
 888                     }
 889                     $tmpstr = $tmp;
 890                     $prevcsize = strlen($tmp);
 891                 }
 892             }
 893             if (strlen($tmpstr)) {
 894                 if (strlen(mb_substr($tmpstr, 0, 1)) == 1)
 895                     $result .= $tmpstr;
 896                 else
 897                     $result .= str_replace(' ', '',
 898                                            mb_encode_mimeheader($tmpstr,'iso-2022-jp','B',''));
 899             }
 900         }
 901         $ret = $result;
 902     }
 903     return $ret;
 904 }
 905
 906 /**
 907  * Japanese header decoding function
 908  * @since 1.5.1
 909  */
 910 function japanese_xtra_decodeheader($ret) {
 911     if (function_exists('mb_detect_encoding')) {
 912         $ret = str_replace("\t", "", $ret);
 913         if (eregi('=\\?([^?]+)\\?(q|b)\\?([^?]+)\\?=', $ret))
 914             $ret = @mb_decode_mimeheader($ret);
 915         $ret = @mb_convert_encoding($ret, 'EUC-JP', 'AUTO');
 916     }
 917     return $ret;
 918 }
 919
 920 /**
 921  * Japanese downloaded filename processing function
 922  * @since 1.5.1
 923  */
 924 function japanese_xtra_downloadfilename($ret,$useragent) {
 925     if (function_exists('mb_detect_encoding')) {
 926         if (strstr($useragent, 'Windows') !== false ||
 927             strstr($useragent, 'Mac_') !== false) {
 928             $ret = mb_convert_encoding($ret, 'SJIS', 'AUTO');
 929         } else {
 930             $ret = mb_convert_encoding($ret, 'EUC-JP', 'AUTO');
 931         }
 932     }
 933     return $ret;
 934 }
 935
 936 /**
 937  * Japanese wordwrap function
 938  *
 939  * @since 1.5.1
 940  */
 941 function japanese_xtra_wordwrap($ret,$wrap) {
 942     if (function_exists('mb_detect_encoding')) {
 943         $no_begin = "\x21\x25\x29\x2c\x2e\x3a\x3b\x3f\x5d\x7d\xa1\xf1\xa1\xeb\xa1" .
 944             "\xc7\xa1\xc9\xa2\xf3\xa1\xec\xa1\xed\xa1\xee\xa1\xa2\xa1\xa3\xa1\xb9" .
 945             "\xa1\xd3\xa1\xd5\xa1\xd7\xa1\xd9\xa1\xdb\xa1\xcd\xa4\xa1\xa4\xa3\xa4" .
 946             "\xa5\xa4\xa7\xa4\xa9\xa4\xc3\xa4\xe3\xa4\xe5\xa4\xe7\xa4\xee\xa1\xab" .
 947             "\xa1\xac\xa1\xb5\xa1\xb6\xa5\xa1\xa5\xa3\xa5\xa5\xa5\xa7\xa5\xa9\xa5" .
 948             "\xc3\xa5\xe3\xa5\xe5\xa5\xe7\xa5\xee\xa5\xf5\xa5\xf6\xa1\xa6\xa1\xbc" .
 949             "\xa1\xb3\xa1\xb4\xa1\xaa\xa1\xf3\xa1\xcb\xa1\xa4\xa1\xa5\xa1\xa7\xa1" .
 950             "\xa8\xa1\xa9\xa1\xcf\xa1\xd1";
 951         $no_end = "\x5c\x24\x28\x5b\x7b\xa1\xf2\x5c\xa1\xc6\xa1\xc8\xa1\xd2\xa1" .
 952             "\xd4\xa1\xd6\xa1\xd8\xa1\xda\xa1\xcc\xa1\xf0\xa1\xca\xa1\xce\xa1\xd0\xa1\xef";
 953
 954         if (strlen($ret) >= $wrap &&
 955             substr($ret, 0, 1) != '>' &&
 956             strpos($ret, 'http://') === FALSE &&
 957             strpos($ret, 'https://') === FALSE &&
 958             strpos($ret, 'ftp://') === FALSE) {
 959
 960             $ret = mb_convert_kana($ret, "KV");
 961
 962             $line_new = '';
 963             $ptr = 0;
 964
 965             while ($ptr < strlen($ret) - 1) {
 966                 $l = mb_strcut($ret, $ptr, $wrap);
 967                 $ptr += strlen($l);
 968                 $tmp = $l;
 969
 970                 $l = mb_strcut($ret, $ptr, 2);
 971                 while (strlen($l) != 0 && mb_strpos($no_begin, $l) !== FALSE ) {
 972                     $tmp .= $l;
 973                     $ptr += strlen($l);
 974                     $l = mb_strcut($ret, $ptr, 1);
 975                 }
 976                 $line_new .= $tmp;
 977                 if ($ptr < strlen($ret) - 1)
 978                     $line_new .= "\n";
 979             }
 980             $ret = $line_new;
 981         }
 982     }
 983     return $ret;
 984 }
 985
 986 /**
 987  * Japanese imap folder name encoding function
 988  * @since 1.5.1
 989  */
 990 function japanese_xtra_utf7_imap_encode($ret){
 991     if (function_exists('mb_detect_encoding')) {
 992         $ret = mb_convert_encoding($ret, 'UTF7-IMAP', 'EUC-JP');
 993     }
 994     return $ret;
 995 }
 996
 997 /**
 998  * Japanese imap folder name decoding function
 999  * @since 1.5.1
1000  */
1001 function japanese_xtra_utf7_imap_decode($ret) {
1002     if (function_exists('mb_detect_encoding')) {
1003         $ret = mb_convert_encoding($ret, 'EUC-JP', 'UTF7-IMAP');
1004     }
1005     return $ret;
1006 }
1007
1008 /**
1009  * Japanese string trimming function
1010  * @since 1.5.1
1011  */
1012 function japanese_xtra_strimwidth($ret,$width) {
1013     if (function_exists('mb_detect_encoding')) {
1014         $ret = mb_strimwidth($ret, 0, $width, '...');
1015     }
1016     return $ret;
1017 }
1018
1019 /********************************
1020  * Korean charset extra functions
1021  ********************************/
1022
1023 /**
1024  * Korean downloaded filename processing functions
1025  *
1026  * @param string default return value
1027  * @return string
1028  */
1029 function korean_xtra_downloadfilename($ret) {
1030     $ret = str_replace("\x0D\x0A", '', $ret);  /* Hanmail's CR/LF Clear */
1031     for ($i=0;$i<strlen($ret);$i++) {
1032         if ($ret[$i] >= "\xA1" && $ret[$i] <= "\xFE") {   /* 0xA1 - 0XFE are Valid */
1033             $i++;
1034             continue;
1035         } else if (($ret[$i] >= 'a' && $ret[$i] <= 'z') || /* From Original ereg_replace in download.php */
1036                    ($ret[$i] >= 'A' && $ret[$i] <= 'Z') ||
1037                    ($ret[$i] == '.') || ($ret[$i] == '-')) {
1038             continue;
1039         } else {
1040             $ret[$i] = '_';
1041         }
1042     }
1043     return $ret;
1044 }
1045
1046 /**
1047  * Replaces non-braking spaces inserted by some browsers with regular space
1048  *
1049  * This function can be used to replace non-braking space symbols
1050  * that are inserted in forms by some browsers instead of normal
1051  * space symbol.
1052  *
1053  * @param string $string Text that needs to be cleaned
1054  * @param string $charset Charset used in text
1055  * @return string Cleaned text
1056  */
1057 function cleanup_nbsp($string,$charset) {
1058
1059   // reduce number of case statements
1060   if (stristr('iso-8859-',substr($charset,0,9))){
1061     $output_charset="iso-8859-x";
1062   }
1063   if (stristr('windows-125',substr($charset,0,11))){
1064     $output_charset="cp125x";
1065   }
1066   if (stristr('koi8',substr($charset,0,4))){
1067     $output_charset="koi8-x";
1068   }
1069   if (! isset($output_charset)){
1070     $output_charset=strtolower($charset);
1071   }
1072
1073 // where is non-braking space symbol
1074 switch($output_charset):
1075  case "iso-8859-x":
1076  case "cp125x":
1077  case "iso-2022-jp":
1078   $nbsp="\xA0";
1079   break;
1080  case "koi8-x":
1081    $nbsp="\x9A";
1082    break;
1083  case "utf-8":
1084    $nbsp="\xC2\xA0";
1085    break;
1086  default:
1087    // don't change string if charset is unmatched
1088    return $string;
1089 endswitch;
1090
1091 // return space instead of non-braking space.
1092  return str_replace($nbsp,' ',$string);
1093 }
1094
1095 /**
1096  * Function informs if it is safe to convert given charset to the one that is used by user.
1097  *
1098  * It is safe to use conversion only if user uses utf-8 encoding and when
1099  * converted charset is similar to the one that is used by user.
1100  *
1101  * @param string $input_charset Charset of text that needs to be converted
1102  * @return bool is it possible to convert to user's charset
1103  */
1104 function is_conversion_safe($input_charset) {
1105   global $languages, $sm_notAlias, $default_charset;
1106
1107  // convert to lower case
1108  $input_charset = strtolower($input_charset);
1109
1110  // Is user's locale Unicode based ?
1111  if ( $default_charset == "utf-8" ) {
1112    return true;
1113  }
1114
1115  // Charsets that are similar
1116 switch ($default_charset):
1117 case "windows-1251":
1118       if ( $input_charset == "iso-8859-5" ||
1119            $input_charset == "koi8-r" ||
1120            $input_charset == "koi8-u" ) {
1121         return true;
1122      } else {
1123         return false;
1124      }
1125 case "windows-1257":
1126   if ( $input_charset == "iso-8859-13" ||
1127        $input_charset == "iso-8859-4" ) {
1128     return true;
1129   } else {
1130     return false;
1131   }
1132 case "iso-8859-4":
1133   if ( $input_charset == "iso-8859-13" ||
1134        $input_charset == "windows-1257" ) {
1135      return true;
1136   } else {
1137      return false;
1138   }
1139 case "iso-8859-5":
1140   if ( $input_charset == "windows-1251" ||
1141        $input_charset == "koi8-r" ||
1142        $input_charset == "koi8-u" ) {
1143      return true;
1144   } else {
1145      return false;
1146   }
1147 case "iso-8859-13":
1148   if ( $input_charset == "iso-8859-4" ||
1149        $input_charset == "windows-1257" ) {
1150      return true;
1151   } else {
1152      return false;
1153   }
1154 case "koi8-r":
1155   if ( $input_charset == "windows-1251" ||
1156        $input_charset == "iso-8859-5" ||
1157        $input_charset == "koi8-u" ) {
1158      return true;
1159   } else {
1160      return false;
1161   }
1162 case "koi8-u":
1163   if ( $input_charset == "windows-1251" ||
1164        $input_charset == "iso-8859-5" ||
1165        $input_charset == "koi8-r" ) {
1166      return true;
1167   } else {
1168      return false;
1169   }
1170 default:
1171    return false;
1172 endswitch;
1173 }
1174 ?>