functions/i18n.php

   1 <?php
   2
   3 /**
   4  * i18n.php
   5  *
   6  * Copyright (c) 1999-2003 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  * $Id$
  16  * @package squirrelmail
  17  */
  18
  19 /** Everything uses global.php... */
  20 require_once(SM_PATH . 'functions/global.php');
  21
  22 /**
  23  * Converts string from given charset to charset, that can be displayed by user translation.
  24  *
  25  * Function by default returns html encoded strings, if translation uses different encoding.
  26  * If Japanese translation is used - function returns string converted to euc-jp
  27  * If iconv or recode functions are enabled and translation uses utf-8 - function returns utf-8 encoded string.
  28  * If $charset is not supported - function returns unconverted string.
  29  *
  30  * sanitizing of html tags is also done by this function.
  31  *
  32  * @param string $charset
  33  * @param string $string Text to be decoded
  34  * @return string decoded string
  35  */
  36 function charset_decode ($charset, $string) {
  37     global $languages, $squirrelmail_language, $default_charset;
  38     global $use_php_recode, $use_php_iconv, $agresive_decoding;
  39
  40     if (isset($languages[$squirrelmail_language]['XTRA_CODE']) &&
  41         function_exists($languages[$squirrelmail_language]['XTRA_CODE'])) {
  42         $string = $languages[$squirrelmail_language]['XTRA_CODE']('decode', $string);
  43     }
  44
  45     $charset = strtolower($charset);
  46
  47     set_my_charset();
  48
  49     // Variables that allow to use functions without function_exist() calls
  50     if (! isset($use_php_recode) || $use_php_recode=="" ) {
  51              $use_php_recode=false; }
  52     if (! isset($use_php_iconv) || $use_php_iconv=="" ) {
  53          $use_php_iconv=false; }
  54
  55     // Don't do conversion if charset is the same.
  56     if ( $charset == strtolower($default_charset) )
  57           return htmlspecialchars($string);
  58
  59     // catch iso-8859-8-i thing
  60     if ( $charset == "iso-8859-8-i" )
  61               $charset = "iso-8859-8";
  62
  63     /*
  64      * Recode converts html special characters automatically if you use
  65      * 'charset..html' decoding. There is no documented way to put -d option
  66      * into php recode function call.
  67      */
  68     if ( $use_php_recode ) {
  69       if ( $default_charset == "utf-8" ) {
  70         // other charsets can be converted to utf-8 without loss.
  71         // and output string is smaller
  72         $string = recode_string($charset . "..utf-8",$string);
  73         return htmlspecialchars($string);
  74       } else {
  75         $string = recode_string($charset . "..html",$string);
  76         // recode does not convert single quote, htmlspecialchars does.
  77         $string = str_replace("'", '&#039;', $string);
  78         return $string;
  79       }
  80     }
  81
  82     // iconv functions does not have html target and can be used only with utf-8
  83     if ( $use_php_iconv && $default_charset=='utf-8') {
  84       $string = iconv($charset,$default_charset,$string);
  85       return htmlspecialchars($string);
  86     }
  87
  88     // If we don't use recode and iconv, we'll do it old way.
  89
  90     /* All HTML special characters are 7 bit and can be replaced first */
  91
  92     $string = htmlspecialchars ($string);
  93
  94     /* controls cpu and memory intensive decoding cycles */
  95     if (! isset($agresive_decoding) || $agresive_decoding=="" ) {
  96          $agresive_decoding=false; }
  97
  98     if (ereg('iso-8859-([[:digit:]]+)', $charset, $res)) {
  99         if ($res[1] == '1') {
 100             include_once(SM_PATH . 'functions/decode/iso8859-1.php');
 101             $ret = charset_decode_iso8859_1 ($string);
 102         } else if ($res[1] == '2') {
 103             include_once(SM_PATH . 'functions/decode/iso8859-2.php');
 104             $ret = charset_decode_iso8859_2 ($string);
 105         } else if ($res[1] == '3') {
 106             include_once(SM_PATH . 'functions/decode/iso8859-3.php');
 107             $ret = charset_decode_iso8859_3 ($string);
 108         } else if ($res[1] == '4') {
 109             include_once(SM_PATH . 'functions/decode/iso8859-4.php');
 110             $ret = charset_decode_iso8859_4 ($string);
 111         } else if ($res[1] == '5') {
 112             include_once(SM_PATH . 'functions/decode/iso8859-5.php');
 113             $ret = charset_decode_iso8859_5 ($string);
 114         } else if ($res[1] == '6') {
 115             include_once(SM_PATH . 'functions/decode/iso8859-6.php');
 116             $ret = charset_decode_iso8859_6 ($string);
 117         } else if ($res[1] == '7') {
 118             include_once(SM_PATH . 'functions/decode/iso8859-7.php');
 119             $ret = charset_decode_iso8859_7 ($string);
 120         } else if ($res[1] == '8') {
 121             include_once(SM_PATH . 'functions/decode/iso8859-8.php');
 122             $ret = charset_decode_iso8859_8 ($string);
 123         } else if ($res[1] == '9') {
 124             include_once(SM_PATH . 'functions/decode/iso8859-9.php');
 125             $ret = charset_decode_iso8859_9 ($string);
 126         } else if ($res[1] == '10') {
 127             include_once(SM_PATH . 'functions/decode/iso8859-10.php');
 128             $ret = charset_decode_iso8859_10 ($string);
 129         } else if ($res[1] == '11') {
 130             include_once(SM_PATH . 'functions/decode/iso8859-11.php');
 131             $ret = charset_decode_iso8859_11 ($string);
 132         } else if ($res[1] == '13') {
 133             include_once(SM_PATH . 'functions/decode/iso8859-13.php');
 134             $ret = charset_decode_iso8859_13 ($string);
 135         } else if ($res[1] == '14') {
 136             include_once(SM_PATH . 'functions/decode/iso8859-14.php');
 137             $ret = charset_decode_iso8859_14 ($string);
 138         } else if ($res[1] == '15') {
 139             include_once(SM_PATH . 'functions/decode/iso8859-15.php');
 140             $ret = charset_decode_iso8859_15 ($string);
 141         } else if ($res[1] == '16') {
 142             include_once(SM_PATH . 'functions/decode/iso8859-16.php');
 143             $ret = charset_decode_iso8859_16 ($string);
 144         } else {
 145             $ret = charset_decode_iso_8859_default ($string);
 146         }
 147     } else if ($charset == 'ns_4551-1') {
 148         $ret = charset_decode_ns_4551_1 ($string);
 149     } else if ($charset == 'koi8-r') {
 150         include_once(SM_PATH . 'functions/decode/koi8-r.php');
 151         $ret = charset_decode_koi8r ($string);
 152     } else if ($charset == 'koi8-u') {
 153         include_once(SM_PATH . 'functions/decode/koi8-u.php');
 154         $ret = charset_decode_koi8u ($string);
 155     } else if ($charset == 'windows-1250') {
 156         include_once(SM_PATH . 'functions/decode/cp1250.php');
 157         $ret = charset_decode_cp1250 ($string);
 158     } else if ($charset == 'windows-1251') {
 159         include_once(SM_PATH . 'functions/decode/cp1251.php');
 160         $ret = charset_decode_cp1251 ($string);
 161     } else if ($charset == 'windows-1252') {
 162         include_once(SM_PATH . 'functions/decode/cp1252.php');
 163         $ret = charset_decode_cp1252 ($string);
 164     } else if ($charset == 'windows-1253') {
 165         include_once(SM_PATH . 'functions/decode/cp1253.php');
 166         $ret = charset_decode_cp1253 ($string);
 167     } else if ($charset == 'windows-1254') {
 168         include_once(SM_PATH . 'functions/decode/cp1254.php');
 169         $ret = charset_decode_cp1254 ($string);
 170     } else if ($charset == 'windows-1255') {
 171         include_once(SM_PATH . 'functions/decode/cp1255.php');
 172         $ret = charset_decode_cp1255 ($string);
 173     } else if ($charset == 'windows-1256') {
 174         include_once(SM_PATH . 'functions/decode/cp1256.php');
 175         $ret = charset_decode_cp1256 ($string);
 176     } else if ($charset == 'windows-1257') {
 177         include_once(SM_PATH . 'functions/decode/cp1257.php');
 178         $ret = charset_decode_cp1257 ($string);
 179     } else if ($charset == 'windows-1258') {
 180         include_once(SM_PATH . 'functions/decode/cp1258.php');
 181         $ret = charset_decode_cp1258 ($string);
 182     } else if ($charset == 'x-mac-roman') {
 183         include_once(SM_PATH . 'functions/decode/cp10000.php');
 184         $ret = charset_decode_cp10000 ($string);
 185     } else if ($charset == 'x-mac-greek') {
 186         include_once(SM_PATH . 'functions/decode/cp10006.php');
 187         $ret = charset_decode_cp10006 ($string);
 188     } else if ($charset == 'x-mac-cyrillic') {
 189         include_once(SM_PATH . 'functions/decode/cp10007.php');
 190         $ret = charset_decode_cp10007 ($string);
 191     } else if ($charset == 'x-mac-ukrainian') {
 192         include_once(SM_PATH . 'functions/decode/cp10017.php');
 193         $ret = charset_decode_cp10017 ($string);
 194     } else if ($charset == 'x-mac-centraleurroman') {
 195         include_once(SM_PATH . 'functions/decode/cp10029.php');
 196         $ret = charset_decode_cp10029 ($string);
 197     } else if ($charset == 'x-mac-icelandic') {
 198         include_once(SM_PATH . 'functions/decode/cp10079.php');
 199         $ret = charset_decode_cp10079 ($string);
 200     } else if ($charset == 'x-mac-turkish') {
 201         include_once(SM_PATH . 'functions/decode/cp10081.php');
 202         $ret = charset_decode_cp10081 ($string);
 203     } else if ($charset == 'ibm855') {
 204         include_once(SM_PATH . 'functions/decode/cp855.php');
 205         $ret = charset_decode_cp855 ($string);
 206     } else if ($charset == 'ibm866') {
 207         include_once(SM_PATH . 'functions/decode/cp866.php');
 208         $ret = charset_decode_cp866 ($string);
 209     } else if ($charset == 'iso-ir-111') {
 210         include_once(SM_PATH . 'functions/decode/iso-ir-111.php');
 211         $ret = charset_decode_iso_ir_111 ($string);
 212     } else if ($charset == 'tis-620') {
 213         include_once(SM_PATH . 'functions/decode/tis620.php');
 214         $ret = charset_decode_tis620 ($string);
 215     } else if ($charset == 'big5' and $agresive_decoding ) {
 216         include_once(SM_PATH . 'functions/decode/big5.php');
 217         $ret = charset_decode_big5 ($string);
 218     } else if ($charset == 'gb2312' and $agresive_decoding ) {
 219         include_once(SM_PATH . 'functions/decode/gb2312.php');
 220         $ret = charset_decode_gb2312 ($string);
 221     } else if ($charset == 'utf-8' && $squirrelmail_language != 'ja_JP') {
 222         include_once(SM_PATH . 'functions/decode/utf-8.php');
 223         $ret = charset_decode_utf8 ($string);
 224     } else {
 225         $ret = $string;
 226     }
 227     return( $ret );
 228 }
 229
 230
 231 /**
 232  * 8bit cleanup functions.
 233  *
 234  * Replaces all 8 bit characters from ISO-8859 character sets with '?'
 235  * Legacy function used for unsupported ISO-8859 charsets
 236  *
 237  * @param string $string string that has to be cleaned
 238  * @return string cleaned string
 239  */
 240 function charset_decode_iso_8859_default ($string) {
 241     return (strtr($string, "\240\241\242\243\244\245\246\247".
 242                     "\250\251\252\253\254\255\256\257".
 243                     "\260\261\262\263\264\265\266\267".
 244                     "\270\271\272\273\274\275\276\277".
 245                     "\300\301\302\303\304\305\306\307".
 246                     "\310\311\312\313\314\315\316\317".
 247                     "\320\321\322\323\324\325\326\327".
 248                     "\330\331\332\333\334\335\336\337".
 249                     "\340\341\342\343\344\345\346\347".
 250                     "\350\351\352\353\354\355\356\357".
 251                     "\360\361\362\363\364\365\366\367".
 252                     "\370\371\372\373\374\375\376\377",
 253                     "????????????????????????????????????????".
 254                     "????????????????????????????????????????".
 255                     "????????????????????????????????????????".
 256                     "????????"));
 257
 258 }
 259
 260 /**
 261  * ns_4551_1 decoding function
 262  *
 263  * This is the same as ISO-646-NO and is used by some
 264  * Microsoft programs when sending Norwegian characters
 265  *
 266  * @param string $string
 267  * @return string
 268  */
 269 function charset_decode_ns_4551_1 ($string) {
 270     /*
 271      * These characters are:
 272      * Latin capital letter AE
 273      * Latin capital letter O with stroke
 274      * Latin capital letter A with ring above
 275      * and the same as small letters
 276      */
 277     return strtr ($string, "[\\]{|}", "ÆØÅæøå");
 278 }
 279
 280
 281 /**
 282  * Set up the language to be output
 283  * if $do_search is true, then scan the browser information
 284  * for a possible language that we know
 285  *
 286  * Function sets system locale environment (LC_ALL, LANG, LANGUAGE),
 287  * gettext translation bindings and html header information.
 288  *
 289  * Function returns error codes, if there is some fatal error.
 290  *  0 = no error,
 291  *  1 = mbstring support is not present,
 292  *  2 = mbstring support is not present, user's translation reverted to en_US.
 293  *
 294  * @param string $sm_language translation used by user's interface
 295  * @param bool $do_search use browser's preferred language detection functions. Defaults to false.
 296  * @param bool $default set $sm_language to $squirrelmail_default_language if language detection fails or language is not set. Defaults to false.
 297  * @return int function execution error codes.
 298  */
 299 function set_up_language($sm_language, $do_search = false, $default = false) {
 300
 301     static $SetupAlready = 0;
 302     global $use_gettext, $languages,
 303            $squirrelmail_language, $squirrelmail_default_language,
 304            $sm_notAlias, $username, $data_dir;
 305
 306     if ($SetupAlready) {
 307         return;
 308     }
 309
 310     $SetupAlready = TRUE;
 311     sqgetGlobalVar('HTTP_ACCEPT_LANGUAGE',  $accept_lang, SQ_SERVER);
 312
 313     if ($do_search && ! $sm_language && isset($accept_lang)) {
 314         $sm_language = substr($accept_lang, 0, 2);
 315     }
 316
 317     if ((!$sm_language||$default) && isset($squirrelmail_default_language)) {
 318         $squirrelmail_language = $squirrelmail_default_language;
 319         $sm_language = $squirrelmail_default_language;
 320     }
 321     $sm_notAlias = $sm_language;
 322
 323     // Catching removed translation
 324     // System reverts to English translation if user prefs contain translation
 325     // that is not available in $languages array (admin removed directory
 326     // with that translation)
 327     if (!isset($languages[$sm_notAlias])) {
 328       $sm_notAlias="en_US";
 329     }
 330
 331     while (isset($languages[$sm_notAlias]['ALIAS'])) {
 332         $sm_notAlias = $languages[$sm_notAlias]['ALIAS'];
 333     }
 334
 335     if ( isset($sm_language) &&
 336          $use_gettext &&
 337          $sm_language != '' &&
 338          isset($languages[$sm_notAlias]['CHARSET']) ) {
 339         bindtextdomain( 'squirrelmail', SM_PATH . 'locale/' );
 340         textdomain( 'squirrelmail' );
 341         if (function_exists('bind_textdomain_codeset')) {
 342             if ($sm_notAlias == 'ja_JP') {
 343                 bind_textdomain_codeset ("squirrelmail", 'EUC-JP');
 344             } else {
 345                 bind_textdomain_codeset ("squirrelmail", $languages[$sm_notAlias]['CHARSET'] );
 346             }
 347         }
 348         if (isset($languages[$sm_notAlias]['LOCALE'])){
 349           $longlocale=$languages[$sm_notAlias]['LOCALE'];
 350         } else {
 351           $longlocale=$sm_notAlias;
 352         }
 353         if ( !ini_get('safe_mode') &&
 354              getenv( 'LC_ALL' ) != $longlocale ) {
 355             putenv( "LC_ALL=$longlocale" );
 356             putenv( "LANG=$longlocale" );
 357             putenv( "LANGUAGE=$longlocale" );
 358         }
 359         setlocale(LC_ALL, $longlocale);
 360         $squirrelmail_language = $sm_notAlias;
 361         if ($squirrelmail_language == 'ja_JP') {
 362             header ('Content-Type: text/html; charset=EUC-JP');
 363             if (!function_exists('mb_internal_encoding')) {
 364                 // Error messages can't be displayed here
 365                 $error = 1;
 366                 // Revert to English if possible.
 367                 if (function_exists('setPref')  && $username!='' && $data_dir!="") {
 368                     setPref($data_dir, $username, 'language', "en_US");
 369                     $error = 2;
 370                 }
 371                 // stop further execution in order not to get php errors on mb_internal_encoding().
 372                 return $error;
 373             }
 374             if (function_exists('mb_language')) {
 375                 mb_language('Japanese');
 376             }
 377             mb_internal_encoding('EUC-JP');
 378             mb_http_output('pass');
 379         } else {
 380         header( 'Content-Type: text/html; charset=' . $languages[$sm_notAlias]['CHARSET'] );
 381     }
 382 }
 383     return 0;
 384 }
 385
 386 /**
 387  * Sets default_charset variable according to the one that is used by user's translations.
 388  *
 389  * Function changes global $default_charset variable in order to be sure, that it
 390  * contains charset used by user's translation. Sanity of $squirrelmail_default_language
 391  * and $default_charset combination provided in SquirrelMail config is also tested.
 392  *
 393  * There can be a $default_charset setting in the
 394  * config.php file, but the user may have a different language
 395  * selected for a user interface. This function checks the
 396  * language selected by the user and tags the outgoing messages
 397  * with the appropriate charset corresponding to the language
 398  * selection. This is "more right" (tm), than just stamping the
 399  * message blindly with the system-wide $default_charset.
 400  */
 401 function set_my_charset(){
 402     global $data_dir, $username, $default_charset, $languages, $squirrelmail_default_language;
 403
 404     $my_language = getPref($data_dir, $username, 'language');
 405     if (!$my_language) {
 406         $my_language = $squirrelmail_default_language ;
 407     }
 408     // Catch removed translation
 409     if (!isset($languages[$my_language])) {
 410       $my_language="en_US";
 411     }
 412     while (isset($languages[$my_language]['ALIAS'])) {
 413         $my_language = $languages[$my_language]['ALIAS'];
 414     }
 415     $my_charset = $languages[$my_language]['CHARSET'];
 416     if ($my_charset) {
 417         $default_charset = $my_charset;
 418     }
 419 }
 420
 421 /* ------------------------------ main --------------------------- */
 422
 423 global $squirrelmail_language, $languages, $use_gettext;
 424
 425 if (! isset($squirrelmail_language)) {
 426     $squirrelmail_language = '';
 427 }
 428
 429 /**
 430  * Array specifies the available translations.
 431  *
 432  * Structure of array:
 433  * $languages['language']['variable'] = 'value'
 434  *
 435  * Possible 'variable' names:
 436  *  NAME      - Translation name in English
 437  *  CHARSET   - Encoding used by translation
 438  *  ALIAS     - used when 'language' is only short name and 'value' should provide long language name
 439  *  ALTNAME   - Native translation name. Any 8bit symbols must be html encoded.
 440  *  LOCALE    - Full locale name (in xx_XX.charset format)
 441  *  DIR       - Text direction. Used to define Right-to-Left languages. Possible values 'rtl' or 'ltr'. If undefined - defaults to 'ltr'
 442  *  XTRA_CODE - translation uses special functions. 'value' provides name of that extra function
 443  *
 444  * Each 'language' definition requires NAME+CHARSET or ALIAS variables.
 445  *
 446  * @name $languages
 447  * @global $languages
 448  */
 449 $languages['bg_BG']['NAME']    = 'Bulgarian';
 450 $languages['bg_BG']['ALTNAME'] = '&#1041;&#1098;&#1083;&#1075;&#1072;&#1088;&#1089;&#1082;&#1080;';
 451 $languages['bg_BG']['CHARSET'] = 'windows-1251';
 452 $languages['bg']['ALIAS'] = 'bg_BG';
 453
 454 $languages['ca_ES']['NAME']    = 'Catalan';
 455 $languages['ca_ES']['CHARSET'] = 'iso-8859-1';
 456 $languages['ca']['ALIAS'] = 'ca_ES';
 457
 458 $languages['cs_CZ']['NAME']    = 'Czech';
 459 $languages['cs_CZ']['ALTNAME'] = '&#268;e&scaron;tina';
 460 $languages['cs_CZ']['CHARSET'] = 'iso-8859-2';
 461 $languages['cs']['ALIAS']      = 'cs_CZ';
 462
 463 $languages['cy_GB']['NAME']    = 'Welsh';
 464 $languages['cy_GB']['ALTNAME'] = 'Cymraeg';
 465 $languages['cy_GB']['CHARSET'] = 'iso-8859-1';
 466 $languages['cy']['ALIAS'] = 'cy_GB';
 467
 468 // Danish locale is da_DK.
 469 $languages['da_DK']['NAME']    = 'Danish';
 470 $languages['da_DK']['ALTNAME'] = 'Dansk';
 471 $languages['da_DK']['CHARSET'] = 'iso-8859-1';
 472 $languages['da']['ALIAS'] = 'da_DK';
 473
 474 $languages['de_DE']['NAME']    = 'German';
 475 $languages['de_DE']['ALTNAME']    = 'Deutsch';
 476 $languages['de_DE']['CHARSET'] = 'iso-8859-1';
 477 $languages['de']['ALIAS'] = 'de_DE';
 478
 479 $languages['el_GR']['NAME']    = 'Greek';
 480 $languages['el_GR']['ALTNAME'] = '&Epsilon;&lambda;&lambda;&eta;&nu;&iota;&kappa;&#940;';
 481 $languages['el_GR']['CHARSET'] = 'iso-8859-7';
 482 $languages['el']['ALIAS'] = 'el_GR';
 483
 484 // There is no en_EN! There is en_US, en_BR, en_AU, and so forth,
 485 // but who cares about !US, right? Right? :)
 486 $languages['en_US']['NAME']    = 'English';
 487 $languages['en_US']['CHARSET'] = 'iso-8859-1';
 488 $languages['en']['ALIAS'] = 'en_US';
 489
 490 $languages['es_ES']['NAME']    = 'Spanish';
 491 $languages['es_ES']['ALTNAME'] = 'Espa&ntilde;ol';
 492 $languages['es_ES']['CHARSET'] = 'iso-8859-1';
 493 $languages['es']['ALIAS'] = 'es_ES';
 494
 495 $languages['et_EE']['NAME']    = 'Estonian';
 496 $languages['et_EE']['CHARSET'] = 'iso-8859-15';
 497 $languages['et']['ALIAS'] = 'et_EE';
 498
 499 $languages['fo_FO']['NAME']    = 'Faroese';
 500 $languages['fo_FO']['CHARSET'] = 'iso-8859-1';
 501 $languages['fo']['ALIAS'] = 'fo_FO';
 502
 503 $languages['fi_FI']['NAME']    = 'Finnish';
 504 $languages['fi_FI']['ALTNAME'] = 'Suomi';
 505 $languages['fi_FI']['CHARSET'] = 'iso-8859-1';
 506 $languages['fi']['ALIAS'] = 'fi_FI';
 507
 508 $languages['fr_FR']['NAME']    = 'French';
 509 $languages['fr_FR']['ALTNAME'] = 'Fran&#231;ais';
 510 $languages['fr_FR']['CHARSET'] = 'iso-8859-1';
 511 $languages['fr']['ALIAS'] = 'fr_FR';
 512
 513 $languages['hr_HR']['NAME']    = 'Croatian';
 514 $languages['hr_HR']['CHARSET'] = 'iso-8859-2';
 515 $languages['hr']['ALIAS'] = 'hr_HR';
 516
 517 $languages['hu_HU']['NAME']    = 'Hungarian';
 518 $languages['hu_HU']['ALTNAME'] = 'Magyar';
 519 $languages['hu_HU']['CHARSET'] = 'iso-8859-2';
 520 $languages['hu']['ALIAS'] = 'hu_HU';
 521
 522 $languages['id_ID']['NAME']    = 'Indonesian';
 523 $languages['id_ID']['ALTNAME'] = 'Bahasa Indonesia';
 524 $languages['id_ID']['CHARSET'] = 'iso-8859-1';
 525 $languages['id']['ALIAS'] = 'id_ID';
 526
 527 $languages['is_IS']['NAME']    = 'Icelandic';
 528 $languages['is_IS']['ALTNAME'] = '&Iacute;slenska';
 529 $languages['is_IS']['CHARSET'] = 'iso-8859-1';
 530 $languages['is']['ALIAS'] = 'is_IS';
 531
 532 $languages['it_IT']['NAME']    = 'Italian';
 533 $languages['it_IT']['CHARSET'] = 'iso-8859-1';
 534 $languages['it']['ALIAS'] = 'it_IT';
 535
 536 $languages['ja_JP']['NAME']    = 'Japanese';
 537 $languages['ja_JP']['ALTNAME'] = '&#26085;&#26412;&#35486;';
 538 $languages['ja_JP']['CHARSET'] = 'iso-2022-jp';
 539 $languages['ja_JP']['LOCALE'] = 'ja_JP.EUC-JP';
 540 $languages['ja_JP']['XTRA_CODE'] = 'japanese_charset_xtra';
 541 $languages['ja']['ALIAS'] = 'ja_JP';
 542
 543 $languages['ko_KR']['NAME']    = 'Korean';
 544 $languages['ko_KR']['CHARSET'] = 'euc-KR';
 545 $languages['ko_KR']['XTRA_CODE'] = 'korean_charset_xtra';
 546 $languages['ko']['ALIAS'] = 'ko_KR';
 547
 548 $languages['lt_LT']['NAME']    = 'Lithuanian';
 549 $languages['lt_LT']['ALTNAME'] = 'Lietuvi&#371;';
 550 $languages['lt_LT']['CHARSET'] = 'utf-8';
 551 $languages['lt_LT']['LOCALE'] = 'lt_LT.UTF-8';
 552 $languages['lt']['ALIAS'] = 'lt_LT';
 553
 554 $languages['nl_NL']['NAME']    = 'Dutch';
 555 $languages['nl_NL']['ALTNAME'] = 'Nederlands';
 556 $languages['nl_NL']['CHARSET'] = 'iso-8859-1';
 557 $languages['nl']['ALIAS'] = 'nl_NL';
 558
 559 $languages['ms_MY']['NAME']    = 'Malay';
 560 $languages['ms_MY']['ALTNAME'] = 'Bahasa Melayu';
 561 $languages['ms_MY']['CHARSET'] = 'iso-8859-1';
 562 $languages['my']['ALIAS'] = 'ms_MY';
 563
 564 $languages['no_NO']['NAME']    = 'Norwegian (Bokm&aring;l)';
 565 $languages['no_NO']['ALTNAME'] = 'Norsk (Bokm&aring;l)';
 566 $languages['no_NO']['CHARSET'] = 'iso-8859-1';
 567 $languages['no']['ALIAS'] = 'no_NO';
 568
 569 $languages['nn_NO']['NAME']    = 'Norwegian (Nynorsk)';
 570 $languages['nn_NO']['ALTNAME'] = 'Norsk (Nynorsk)';
 571 $languages['nn_NO']['CHARSET'] = 'iso-8859-1';
 572
 573 $languages['pl_PL']['NAME']    = 'Polish';
 574 $languages['pl_PL']['ALTNAME'] = 'Polski';
 575 $languages['pl_PL']['CHARSET'] = 'iso-8859-2';
 576 $languages['pl']['ALIAS'] = 'pl_PL';
 577
 578 $languages['pt_PT']['NAME'] = 'Portuguese (Portugal)';
 579 $languages['pt_PT']['CHARSET'] = 'iso-8859-1';
 580 $languages['pt']['ALIAS'] = 'pt_PT';
 581
 582 $languages['pt_BR']['NAME']    = 'Portuguese (Brazil)';
 583 $languages['pt_BR']['ALTNAME'] = 'Portugu&ecirc;s do Brasil';
 584 $languages['pt_BR']['CHARSET'] = 'iso-8859-1';
 585
 586 $languages['ro_RO']['NAME']    = 'Romanian';
 587 $languages['ro_RO']['ALTNAME'] = 'Rom&acirc;n&#259;';
 588 $languages['ro_RO']['CHARSET'] = 'iso-8859-2';
 589 $languages['ro']['ALIAS'] = 'ro_RO';
 590
 591 $languages['ru_RU']['NAME']    = 'Russian';
 592 $languages['ru_RU']['ALTNAME'] = '&#1056;&#1091;&#1089;&#1089;&#1082;&#1080;&#1081;';
 593 $languages['ru_RU']['CHARSET'] = 'utf-8';
 594 $languages['ru_RU']['LOCALE'] = 'ru_RU.UTF-8';
 595 $languages['ru']['ALIAS'] = 'ru_RU';
 596
 597 $languages['sk_SK']['NAME']     = 'Slovak';
 598 $languages['sk_SK']['CHARSET']  = 'iso-8859-2';
 599 $languages['sk']['ALIAS']       = 'sk_SK';
 600
 601 $languages['sl_SI']['NAME']    = 'Slovenian';
 602 $languages['sl_SI']['ALTNAME'] = 'Sloven&scaron;&#269;ina';
 603 $languages['sl_SI']['CHARSET'] = 'iso-8859-2';
 604 $languages['sl']['ALIAS'] = 'sl_SI';
 605
 606 $languages['sr_YU']['NAME']    = 'Serbian';
 607 $languages['sr_YU']['ALTNAME'] = 'Srpski';
 608 $languages['sr_YU']['CHARSET'] = 'iso-8859-2';
 609 $languages['sr']['ALIAS'] = 'sr_YU';
 610
 611 $languages['sv_SE']['NAME']    = 'Swedish';
 612 $languages['sv_SE']['ALTNAME'] = 'Svenska';
 613 $languages['sv_SE']['CHARSET'] = 'iso-8859-1';
 614 $languages['sv']['ALIAS'] = 'sv_SE';
 615
 616 $languages['th_TH']['NAME']    = 'Thai';
 617 $languages['th_TH']['CHARSET'] = 'tis-620';
 618 $languages['th']['ALIAS'] = 'th_TH';
 619
 620 $languages['tr_TR']['NAME']    = 'Turkish';
 621 $languages['tr_TR']['CHARSET'] = 'iso-8859-9';
 622 $languages['tr']['ALIAS'] = 'tr_TR';
 623
 624 $languages['zh_TW']['NAME']    = 'Chinese Trad';
 625 $languages['zh_TW']['CHARSET'] = 'big5';
 626 $languages['tw']['ALIAS'] = 'zh_TW';
 627
 628 $languages['zh_CN']['NAME']    = 'Chinese Simp';
 629 $languages['zh_CN']['CHARSET'] = 'gb2312';
 630 $languages['cn']['ALIAS'] = 'zh_CN';
 631
 632 /*
 633 $languages['uk_UA']['NAME']    = 'Ukrainian';
 634 $languages['uk_UA']['CHARSET'] = 'koi8-u';
 635 $languages['uk']['ALIAS'] = 'uk_UA';
 636 */
 637 /*
 638 if ( file_exists( SM_PATH . 'locale/vi_VN') ) {
 639     $languages['vi_VN']['NAME']    = 'Vietnamese';
 640     $languages['vi_VN']['CHARSET'] = 'utf-8';
 641     $languages['vi']['ALIAS'] = 'vi_VN';
 642 }
 643 */
 644
 645 // Right to left languages
 646 $languages['ar']['NAME']    = 'Arabic';
 647 $languages['ar']['CHARSET'] = 'windows-1256';
 648 $languages['ar']['DIR']     = 'rtl';
 649
 650 $languages['he_IL']['NAME']    = 'Hebrew';
 651 $languages['he_IL']['CHARSET'] = 'windows-1255';
 652 $languages['he_IL']['DIR']     = 'rtl';
 653 $languages['he']['ALIAS']      = 'he_IL';
 654
 655 /* Detect whether gettext is installed. */
 656 $gettext_flags = 0;
 657 if (function_exists('_')) {
 658     $gettext_flags += 1;
 659 }
 660 if (function_exists('bindtextdomain')) {
 661     $gettext_flags += 2;
 662 }
 663 if (function_exists('textdomain')) {
 664     $gettext_flags += 4;
 665 }
 666
 667 /* If gettext is fully loaded, cool */
 668 if ($gettext_flags == 7) {
 669     $use_gettext = true;
 670 }
 671 /* If we can fake gettext, try that */
 672 elseif ($gettext_flags == 0) {
 673     $use_gettext = true;
 674     include_once(SM_PATH . 'functions/gettext.php');
 675 } else {
 676     /* Uh-ho.  A weird install */
 677     if (! $gettext_flags & 1) {
 678         function _($str) {
 679             return $str;
 680         }
 681     }
 682     if (! $gettext_flags & 2) {
 683         function bindtextdomain() {
 684             return;
 685         }
 686     }
 687     if (! $gettext_flags & 4) {
 688         function textdomain() {
 689             return;
 690         }
 691     }
 692 }
 693
 694
 695 /**
 696  * Japanese charset extra function
 697  *
 698  * Action performed by function is defined by first argument.
 699  * Default return value is defined by second argument.
 700  * Use of third argument depends on action.
 701  *
 702  * @param string action performed by this function.
 703  *    possible values:
 704  *      decode - convert returned string to euc-jp. third argument unused
 705  *      encode - convert returned string to jis. third argument unused
 706  *      strimwidth - third argument=$width. trims string to $width symbols.
 707  *      encodeheader - create base64 encoded header in iso-2022-jp. third argument unused
 708  *      decodeheader - return human readable string from mime header. string is returned in euc-jp. third argument unused
 709  *      downloadfilename - third argument $useragent. Arguments provide browser info. Returns shift-jis or euc-jp encoded file name
 710  *      wordwrap - third argument=$wrap. wraps text at $wrap symbols
 711  *      utf7-imap_encode - returns string converted from euc-jp to utf7-imap. third argument unused
 712  *      utf7-imap_decode - returns string converted from utf7-imap to euc-jp. third argument unused
 713  * @param string default return value
 714  */
 715 function japanese_charset_xtra() {
 716     $ret = func_get_arg(1);  /* default return value */
 717     if (function_exists('mb_detect_encoding')) {
 718         switch (func_get_arg(0)) { /* action */
 719         case 'decode':
 720             $detect_encoding = @mb_detect_encoding($ret);
 721             if ($detect_encoding == 'JIS' ||
 722                 $detect_encoding == 'EUC-JP' ||
 723                 $detect_encoding == 'SJIS' ||
 724                 $detect_encoding == 'UTF-8') {
 725
 726                 $ret = mb_convert_kana(mb_convert_encoding($ret, 'EUC-JP', 'AUTO'), "KV");
 727             }
 728             break;
 729         case 'encode':
 730             $detect_encoding = @mb_detect_encoding($ret);
 731             if ($detect_encoding == 'JIS' ||
 732                 $detect_encoding == 'EUC-JP' ||
 733                 $detect_encoding == 'SJIS' ||
 734                 $detect_encoding == 'UTF-8') {
 735
 736                 $ret = mb_convert_encoding(mb_convert_kana($ret, "KV"), 'JIS', 'AUTO');
 737             }
 738             break;
 739         case 'strimwidth':
 740             $width = func_get_arg(2);
 741             $ret = mb_strimwidth($ret, 0, $width, '...');
 742             break;
 743         case 'encodeheader':
 744             $result = '';
 745             if (strlen($ret) > 0) {
 746                 $tmpstr = mb_substr($ret, 0, 1);
 747                 $prevcsize = strlen($tmpstr);
 748                 for ($i = 1; $i < mb_strlen($ret); $i++) {
 749                     $tmp = mb_substr($ret, $i, 1);
 750                     if (strlen($tmp) == $prevcsize) {
 751                         $tmpstr .= $tmp;
 752                     } else {
 753                         if ($prevcsize == 1) {
 754                             $result .= $tmpstr;
 755                         } else {
 756                             $result .= str_replace(' ', '',
 757                                                    mb_encode_mimeheader($tmpstr,'iso-2022-jp','B',''));
 758                         }
 759                         $tmpstr = $tmp;
 760                         $prevcsize = strlen($tmp);
 761                     }
 762                 }
 763                 if (strlen($tmpstr)) {
 764                     if (strlen(mb_substr($tmpstr, 0, 1)) == 1)
 765                         $result .= $tmpstr;
 766                     else
 767                         $result .= str_replace(' ', '',
 768                                                mb_encode_mimeheader($tmpstr,'iso-2022-jp','B',''));
 769                 }
 770             }
 771             $ret = $result;
 772             break;
 773         case 'decodeheader':
 774             $ret = str_replace("\t", "", $ret);
 775             if (eregi('=\\?([^?]+)\\?(q|b)\\?([^?]+)\\?=', $ret))
 776                 $ret = @mb_decode_mimeheader($ret);
 777             $ret = @mb_convert_encoding($ret, 'EUC-JP', 'AUTO');
 778             break;
 779         case 'downloadfilename':
 780             $useragent = func_get_arg(2);
 781             if (strstr($useragent, 'Windows') !== false ||
 782                 strstr($useragent, 'Mac_') !== false) {
 783                 $ret = mb_convert_encoding($ret, 'SJIS', 'AUTO');
 784             } else {
 785                 $ret = mb_convert_encoding($ret, 'EUC-JP', 'AUTO');
 786 }
 787             break;
 788         case 'wordwrap':
 789             $no_begin = "\x21\x25\x29\x2c\x2e\x3a\x3b\x3f\x5d\x7d\xa1\xf1\xa1\xeb\xa1" .
 790                 "\xc7\xa1\xc9\xa2\xf3\xa1\xec\xa1\xed\xa1\xee\xa1\xa2\xa1\xa3\xa1\xb9" .
 791                 "\xa1\xd3\xa1\xd5\xa1\xd7\xa1\xd9\xa1\xdb\xa1\xcd\xa4\xa1\xa4\xa3\xa4" .
 792                 "\xa5\xa4\xa7\xa4\xa9\xa4\xc3\xa4\xe3\xa4\xe5\xa4\xe7\xa4\xee\xa1\xab" .
 793                 "\xa1\xac\xa1\xb5\xa1\xb6\xa5\xa1\xa5\xa3\xa5\xa5\xa5\xa7\xa5\xa9\xa5" .
 794                 "\xc3\xa5\xe3\xa5\xe5\xa5\xe7\xa5\xee\xa5\xf5\xa5\xf6\xa1\xa6\xa1\xbc" .
 795                 "\xa1\xb3\xa1\xb4\xa1\xaa\xa1\xf3\xa1\xcb\xa1\xa4\xa1\xa5\xa1\xa7\xa1" .
 796                 "\xa8\xa1\xa9\xa1\xcf\xa1\xd1";
 797             $no_end = "\x5c\x24\x28\x5b\x7b\xa1\xf2\x5c\xa1\xc6\xa1\xc8\xa1\xd2\xa1" .
 798                 "\xd4\xa1\xd6\xa1\xd8\xa1\xda\xa1\xcc\xa1\xf0\xa1\xca\xa1\xce\xa1\xd0\xa1\xef";
 799             $wrap = func_get_arg(2);
 800
 801             if (strlen($ret) >= $wrap &&
 802                 substr($ret, 0, 1) != '>' &&
 803                 strpos($ret, 'http://') === FALSE &&
 804                 strpos($ret, 'https://') === FALSE &&
 805                 strpos($ret, 'ftp://') === FALSE) {
 806
 807                 $ret = mb_convert_kana($ret, "KV");
 808
 809                 $line_new = '';
 810                 $ptr = 0;
 811
 812                 while ($ptr < strlen($ret) - 1) {
 813                     $l = mb_strcut($ret, $ptr, $wrap);
 814                     $ptr += strlen($l);
 815                     $tmp = $l;
 816
 817                     $l = mb_strcut($ret, $ptr, 2);
 818                     while (strlen($l) != 0 && mb_strpos($no_begin, $l) !== FALSE ) {
 819                         $tmp .= $l;
 820                         $ptr += strlen($l);
 821                         $l = mb_strcut($ret, $ptr, 1);
 822                     }
 823                     $line_new .= $tmp;
 824                     if ($ptr < strlen($ret) - 1)
 825                         $line_new .= "\n";
 826                 }
 827                 $ret = $line_new;
 828             }
 829             break;
 830         case 'utf7-imap_encode':
 831             $ret = mb_convert_encoding($ret, 'UTF7-IMAP', 'EUC-JP');
 832             break;
 833         case 'utf7-imap_decode':
 834             $ret = mb_convert_encoding($ret, 'EUC-JP', 'UTF7-IMAP');
 835             break;
 836         }
 837     }
 838     return $ret;
 839 }
 840
 841
 842 /**
 843  * Korean charset extra functions
 844  *
 845  * Action performed by function is defined by first argument.
 846  * Default return value is defined by second argument.
 847  *
 848  * @param string action performed by this function.
 849  *    possible values:
 850  *      downloadfilename - Hangul(Korean Character) Attached File Name Fix.
 851  * @param string default return value
 852  */
 853 function korean_charset_xtra() {
 854
 855     $ret = func_get_arg(1);  /* default return value */
 856     if (func_get_arg(0) == 'downloadfilename') { /* action */
 857         $ret = str_replace("\x0D\x0A", '', $ret);  /* Hanmail's CR/LF Clear */
 858         for ($i=0;$i<strlen($ret);$i++) {
 859             if ($ret[$i] >= "\xA1" && $ret[$i] <= "\xFE") {   /* 0xA1 - 0XFE are Valid */
 860                 $i++;
 861                 continue;
 862             } else if (($ret[$i] >= 'a' && $ret[$i] <= 'z') || /* From Original ereg_replace in download.php */
 863                        ($ret[$i] >= 'A' && $ret[$i] <= 'Z') ||
 864                        ($ret[$i] == '.') || ($ret[$i] == '-')) {
 865                 continue;
 866             } else {
 867                 $ret[$i] = '_';
 868             }
 869         }
 870
 871     }
 872     return $ret;
 873 }
 874
 875 /**
 876  * Replaces non-braking spaces inserted by some browsers with regular space
 877  *
 878  * This function can be used to replace non-braking space symbols
 879  * that are inserted in forms by some browsers instead of normal
 880  * space symbol.
 881  *
 882  * @param string $string Text that needs to be cleaned
 883  * @param string $charset Charset used in text
 884  * @return string Cleaned text
 885  */
 886 function cleanup_nbsp($string,$charset) {
 887
 888   // reduce number of case statements
 889   if (stristr('iso-8859-',substr($charset,0,9))){
 890     $output_charset="iso-8859-x";
 891   }
 892   if (stristr('windows-125',substr($charset,0,11))){
 893     $output_charset="cp125x";
 894   }
 895   if (stristr('koi8',substr($charset,0,4))){
 896     $output_charset="koi8-x";
 897   }
 898   if (! isset($output_charset)){
 899     $output_charset=strtolower($charset);
 900   }
 901
 902 // where is non-braking space symbol
 903 switch($output_charset):
 904  case "iso-8859-x":
 905  case "cp125x":
 906  case "iso-2022-jp":
 907   $nbsp="\xA0";
 908   break;
 909  case "koi8-x":
 910    $nbsp="\x9A";
 911    break;
 912  case "utf-8":
 913    $nbsp="\xC2\xA0";
 914    break;
 915  default:
 916    // don't change string if charset is unmatched
 917    return $string;
 918 endswitch;
 919
 920 // return space instead of non-braking space.
 921  return str_replace($nbsp,' ',$string);
 922 }
 923
 924 /**
 925  * Function informs if it is safe to convert given charset to the one that is used by user.
 926  *
 927  * It is safe to use conversion only if user uses utf-8 encoding and when
 928  * converted charset is similar to the one that is used by user.
 929  *
 930  * @param string $input_charset Charset of text that needs to be converted
 931  * @return bool is it possible to convert to user's charset
 932  */
 933 function is_conversion_safe($input_charset) {
 934   global $languages, $sm_notAlias, $default_charset;
 935
 936  // convert to lower case
 937  $input_charset = strtolower($input_charset);
 938
 939  // Is user's locale Unicode based ?
 940  if ( $default_charset == "utf-8" ) {
 941    return true;
 942  }
 943
 944  // Charsets that are similar
 945 switch ($default_charset):
 946 case "windows-1251":
 947       if ( $input_charset == "iso-8859-5" ||
 948            $input_charset == "koi8-r" ||
 949            $input_charset == "koi8-u" ) {
 950         return true;
 951      } else {
 952         return false;
 953      }
 954 case "windows-1257":
 955   if ( $input_charset == "iso-8859-13" ||
 956          $input_charset == "iso-8859-4" ) {
 957     return true;
 958   } else {
 959     return false;
 960   }
 961 case "iso-8859-4":
 962   if ( $input_charset == "iso-8859-13" ||
 963          $input_charset == "windows-1257" ) {
 964      return true;
 965   } else {
 966      return false;
 967   }
 968 case "iso-8859-5":
 969   if ( $input_charset == "windows-1251" ||
 970          $input_charset == "koi8-r" ||
 971          $input_charset == "koi8-u" ) {
 972      return true;
 973   } else {
 974      return false;
 975   }
 976 case "iso-8859-13":
 977   if ( $input_charset == "iso-8859-4" ||
 978        $input_charset == "windows-1257" ) {
 979      return true;
 980   } else {
 981      return false;
 982   }
 983 case "koi8-r":
 984   if ( $input_charset == "windows-1251" ||
 985          $input_charset == "iso-8859-5" ||
 986          $input_charset == "koi8-u" ) {
 987      return true;
 988   } else {
 989      return false;
 990   }
 991 case "koi8-u":
 992   if ( $input_charset == "windows-1251" ||
 993         $input_charset == "iso-8859-5" ||
 994         $input_charset == "koi8-r" ) {
 995      return true;
 996   } else {
 997      return false;
 998   }
 999 default:
1000    return false;
1001 endswitch;
1002 }
1003 ?>