functions/i18n.php

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