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  * Decodes a string to the internal encoding from the given charset
  24  *
  25  * @param string $charset
  26  * @param string $string Text to be decoded
  27  * @return string Decoded text
  28  */
  29 function charset_decode ($charset, $string) {
  30     global $languages, $squirrelmail_language, $default_charset;
  31     global $use_php_recode, $use_php_iconv, $agresive_decoding;
  32
  33     if (isset($languages[$squirrelmail_language]['XTRA_CODE']) &&
  34         function_exists($languages[$squirrelmail_language]['XTRA_CODE'])) {
  35         $string = $languages[$squirrelmail_language]['XTRA_CODE']('decode', $string);
  36     }
  37
  38     $charset = strtolower($charset);
  39
  40     set_my_charset();
  41
  42     // Variables that allow to use functions without function_exist() calls
  43     if (! isset($use_php_recode) || $use_php_recode=="" ) {
  44              $use_php_recode=false; }
  45     if (! isset($use_php_iconv) || $use_php_iconv=="" ) {
  46          $use_php_iconv=false; }
  47
  48     // Don't do conversion if charset is the same.
  49     if ( $charset == strtolower($default_charset) )
  50           return htmlspecialchars($string);
  51
  52     // catch iso-8859-8-i thing
  53     if ( $charset == "iso-8859-8-i" )
  54               $charset = "iso-8859-8";
  55
  56     /*
  57      * Recode converts html special characters automatically if you use
  58      * 'charset..html' decoding. There is no documented way to put -d option
  59      * into php recode function call.
  60      */
  61     if ( $use_php_recode ) {
  62       if ( $default_charset == "utf-8" ) {
  63         // other charsets can be converted to utf-8 without loss.
  64         // and output string is smaller
  65         $string = recode_string($charset . "..utf-8",$string);
  66         return htmlspecialchars($string);
  67       } else {
  68         $string = recode_string($charset . "..html",$string);
  69         // recode does not convert single quote, htmlspecialchars does.
  70         $string = str_replace("'", '&#039;', $string);
  71         return $string;
  72       }
  73     }
  74
  75     // iconv functions does not have html target and can be used only with utf-8
  76     if ( $use_php_iconv && $default_charset=='utf-8') {
  77       $string = iconv($charset,$default_charset,$string);
  78       return htmlspecialchars($string);
  79     }
  80
  81     // If we don't use recode and iconv, we'll do it old way.
  82
  83     /* All HTML special characters are 7 bit and can be replaced first */
  84
  85     $string = htmlspecialchars ($string);
  86
  87     /* controls cpu and memory intensive decoding cycles */
  88     if (! isset($agresive_decoding) || $agresive_decoding=="" ) {
  89          $agresive_decoding=false; }
  90
  91     if (ereg('iso-8859-([[:digit:]]+)', $charset, $res)) {
  92         if ($res[1] == '1') {
  93             include_once(SM_PATH . 'functions/decode/iso8859-1.php');
  94             $ret = charset_decode_iso8859_1 ($string);
  95         } else if ($res[1] == '2') {
  96             include_once(SM_PATH . 'functions/decode/iso8859-2.php');
  97             $ret = charset_decode_iso8859_2 ($string);
  98         } else if ($res[1] == '3') {
  99             include_once(SM_PATH . 'functions/decode/iso8859-3.php');
 100             $ret = charset_decode_iso8859_3 ($string);
 101         } else if ($res[1] == '4') {
 102             include_once(SM_PATH . 'functions/decode/iso8859-4.php');
 103             $ret = charset_decode_iso8859_4 ($string);
 104         } else if ($res[1] == '5') {
 105             include_once(SM_PATH . 'functions/decode/iso8859-5.php');
 106             $ret = charset_decode_iso8859_5 ($string);
 107         } else if ($res[1] == '6') {
 108             include_once(SM_PATH . 'functions/decode/iso8859-6.php');
 109             $ret = charset_decode_iso8859_6 ($string);
 110         } else if ($res[1] == '7') {
 111             include_once(SM_PATH . 'functions/decode/iso8859-7.php');
 112             $ret = charset_decode_iso8859_7 ($string);
 113         } else if ($res[1] == '8') {
 114             include_once(SM_PATH . 'functions/decode/iso8859-8.php');
 115             $ret = charset_decode_iso8859_8 ($string);
 116         } else if ($res[1] == '9') {
 117             include_once(SM_PATH . 'functions/decode/iso8859-9.php');
 118             $ret = charset_decode_iso8859_9 ($string);
 119         } else if ($res[1] == '10') {
 120             include_once(SM_PATH . 'functions/decode/iso8859-10.php');
 121             $ret = charset_decode_iso8859_10 ($string);
 122         } else if ($res[1] == '11') {
 123             include_once(SM_PATH . 'functions/decode/iso8859-11.php');
 124             $ret = charset_decode_iso8859_11 ($string);
 125         } else if ($res[1] == '13') {
 126             include_once(SM_PATH . 'functions/decode/iso8859-13.php');
 127             $ret = charset_decode_iso8859_13 ($string);
 128         } else if ($res[1] == '14') {
 129             include_once(SM_PATH . 'functions/decode/iso8859-14.php');
 130             $ret = charset_decode_iso8859_14 ($string);
 131         } else if ($res[1] == '15') {
 132             include_once(SM_PATH . 'functions/decode/iso8859-15.php');
 133             $ret = charset_decode_iso8859_15 ($string);
 134         } else if ($res[1] == '16') {
 135             include_once(SM_PATH . 'functions/decode/iso8859-16.php');
 136             $ret = charset_decode_iso8859_16 ($string);
 137         } else {
 138             $ret = charset_decode_iso_8859_default ($string);
 139         }
 140     } else if ($charset == 'ns_4551-1') {
 141         $ret = charset_decode_ns_4551_1 ($string);
 142     } else if ($charset == 'koi8-r') {
 143         include_once(SM_PATH . 'functions/decode/koi8-r.php');
 144         $ret = charset_decode_koi8r ($string);
 145     } else if ($charset == 'koi8-u') {
 146         include_once(SM_PATH . 'functions/decode/koi8-u.php');
 147         $ret = charset_decode_koi8u ($string);
 148     } else if ($charset == 'windows-1250') {
 149         include_once(SM_PATH . 'functions/decode/cp1250.php');
 150         $ret = charset_decode_cp1250 ($string);
 151     } else if ($charset == 'windows-1251') {
 152         include_once(SM_PATH . 'functions/decode/cp1251.php');
 153         $ret = charset_decode_cp1251 ($string);
 154     } else if ($charset == 'windows-1252') {
 155         include_once(SM_PATH . 'functions/decode/cp1252.php');
 156         $ret = charset_decode_cp1252 ($string);
 157     } else if ($charset == 'windows-1253') {
 158         include_once(SM_PATH . 'functions/decode/cp1253.php');
 159         $ret = charset_decode_cp1253 ($string);
 160     } else if ($charset == 'windows-1254') {
 161         include_once(SM_PATH . 'functions/decode/cp1254.php');
 162         $ret = charset_decode_cp1254 ($string);
 163     } else if ($charset == 'windows-1255') {
 164         include_once(SM_PATH . 'functions/decode/cp1255.php');
 165         $ret = charset_decode_cp1255 ($string);
 166     } else if ($charset == 'windows-1256') {
 167         include_once(SM_PATH . 'functions/decode/cp1256.php');
 168         $ret = charset_decode_cp1256 ($string);
 169     } else if ($charset == 'windows-1257') {
 170         include_once(SM_PATH . 'functions/decode/cp1257.php');
 171         $ret = charset_decode_cp1257 ($string);
 172     } else if ($charset == 'windows-1258') {
 173         include_once(SM_PATH . 'functions/decode/cp1258.php');
 174         $ret = charset_decode_cp1258 ($string);
 175     } else if ($charset == 'x-mac-roman') {
 176         include_once(SM_PATH . 'functions/decode/cp10000.php');
 177         $ret = charset_decode_cp10000 ($string);
 178     } else if ($charset == 'x-mac-greek') {
 179         include_once(SM_PATH . 'functions/decode/cp10006.php');
 180         $ret = charset_decode_cp10006 ($string);
 181     } else if ($charset == 'x-mac-cyrillic') {
 182         include_once(SM_PATH . 'functions/decode/cp10007.php');
 183         $ret = charset_decode_cp10007 ($string);
 184     } else if ($charset == 'x-mac-ukrainian') {
 185         include_once(SM_PATH . 'functions/decode/cp10017.php');
 186         $ret = charset_decode_cp10017 ($string);
 187     } else if ($charset == 'x-mac-centraleurroman') {
 188         include_once(SM_PATH . 'functions/decode/cp10029.php');
 189         $ret = charset_decode_cp10029 ($string);
 190     } else if ($charset == 'x-mac-icelandic') {
 191         include_once(SM_PATH . 'functions/decode/cp10079.php');
 192         $ret = charset_decode_cp10079 ($string);
 193     } else if ($charset == 'x-mac-turkish') {
 194         include_once(SM_PATH . 'functions/decode/cp10081.php');
 195         $ret = charset_decode_cp10081 ($string);
 196     } else if ($charset == 'ibm855') {
 197         include_once(SM_PATH . 'functions/decode/cp855.php');
 198         $ret = charset_decode_cp855 ($string);
 199     } else if ($charset == 'ibm866') {
 200         include_once(SM_PATH . 'functions/decode/cp866.php');
 201         $ret = charset_decode_cp866 ($string);
 202     } else if ($charset == 'iso-ir-111') {
 203         include_once(SM_PATH . 'functions/decode/iso-ir-111.php');
 204         $ret = charset_decode_iso_ir_111 ($string);
 205     } else if ($charset == 'tis-620') {
 206         include_once(SM_PATH . 'functions/decode/tis620.php');
 207         $ret = charset_decode_tis620 ($string);
 208     } else if ($charset == 'big5' and $agresive_decoding ) {
 209         include_once(SM_PATH . 'functions/decode/big5.php');
 210         $ret = charset_decode_big5 ($string);
 211     } else if ($charset == 'gb2312' and $agresive_decoding ) {
 212         include_once(SM_PATH . 'functions/decode/gb2312.php');
 213         $ret = charset_decode_gb2312 ($string);
 214     } else if ($charset == 'utf-8' && $squirrelmail_language != 'ja_JP') {
 215         include_once(SM_PATH . 'functions/decode/utf-8.php');
 216         $ret = charset_decode_utf8 ($string);
 217     } else {
 218         $ret = $string;
 219     }
 220     return( $ret );
 221 }
 222
 223
 224 /* Remove all 8 bit characters from all other ISO-8859 character sets */
 225 function charset_decode_iso_8859_default ($string) {
 226     return (strtr($string, "\240\241\242\243\244\245\246\247".
 227                     "\250\251\252\253\254\255\256\257".
 228                     "\260\261\262\263\264\265\266\267".
 229                     "\270\271\272\273\274\275\276\277".
 230                     "\300\301\302\303\304\305\306\307".
 231                     "\310\311\312\313\314\315\316\317".
 232                     "\320\321\322\323\324\325\326\327".
 233                     "\330\331\332\333\334\335\336\337".
 234                     "\340\341\342\343\344\345\346\347".
 235                     "\350\351\352\353\354\355\356\357".
 236                     "\360\361\362\363\364\365\366\367".
 237                     "\370\371\372\373\374\375\376\377",
 238                     "????????????????????????????????????????".
 239                     "????????????????????????????????????????".
 240                     "????????????????????????????????????????".
 241                     "????????"));
 242
 243 }
 244
 245 /*
 246  * This is the same as ISO-646-NO and is used by some
 247  * Microsoft programs when sending Norwegian characters
 248  */
 249 function charset_decode_ns_4551_1 ($string) {
 250     /*
 251      * These characters are:
 252      * Latin capital letter AE
 253      * Latin capital letter O with stroke
 254      * Latin capital letter A with ring above
 255      * and the same as small letters
 256      */
 257     return strtr ($string, "[\\]{|}", "ÆØÅæøå");
 258 }
 259
 260
 261 /*
 262  * Set up the language to be output
 263  * if $do_search is true, then scan the browser information
 264  * for a possible language that we know
 265  */
 266 function set_up_language($sm_language, $do_search = false, $default = false) {
 267
 268     static $SetupAlready = 0;
 269     global $use_gettext, $languages,
 270            $squirrelmail_language, $squirrelmail_default_language,
 271            $sm_notAlias;
 272
 273     if ($SetupAlready) {
 274         return;
 275     }
 276
 277     $SetupAlready = TRUE;
 278     sqgetGlobalVar('HTTP_ACCEPT_LANGUAGE',  $accept_lang, SQ_SERVER);
 279
 280     if ($do_search && ! $sm_language && isset($accept_lang)) {
 281         $sm_language = substr($accept_lang, 0, 2);
 282     }
 283
 284     if ((!$sm_language||$default) && isset($squirrelmail_default_language)) {
 285         $squirrelmail_language = $squirrelmail_default_language;
 286         $sm_language = $squirrelmail_default_language;
 287     }
 288     $sm_notAlias = $sm_language;
 289
 290     // Catching removed translation
 291     // System reverts to English translation if user prefs contain translation
 292     // that is not available in $languages array (admin removed directory
 293     // with that translation)
 294     if (!isset($languages[$sm_notAlias])) {
 295       $sm_notAlias="en_US";
 296     }
 297
 298     while (isset($languages[$sm_notAlias]['ALIAS'])) {
 299         $sm_notAlias = $languages[$sm_notAlias]['ALIAS'];
 300     }
 301
 302     if ( isset($sm_language) &&
 303          $use_gettext &&
 304          $sm_language != '' &&
 305          isset($languages[$sm_notAlias]['CHARSET']) ) {
 306         bindtextdomain( 'squirrelmail', SM_PATH . 'locale/' );
 307         textdomain( 'squirrelmail' );
 308         if (function_exists('bind_textdomain_codeset')) {
 309              bind_textdomain_codeset ("squirrelmail", $languages[$sm_notAlias]['CHARSET'] );
 310         }
 311         if (isset($languages[$sm_notAlias]['LOCALE'])){
 312           $longlocale=$languages[$sm_notAlias]['LOCALE'];
 313         } else {
 314           $longlocale=$sm_notAlias;
 315         }
 316         if ( !ini_get('safe_mode') &&
 317              getenv( 'LC_ALL' ) != $longlocale ) {
 318             putenv( "LC_ALL=$longlocale" );
 319             putenv( "LANG=$longlocale" );
 320             putenv( "LANGUAGE=$longlocale" );
 321         }
 322         setlocale(LC_ALL, $longlocale);
 323         $squirrelmail_language = $sm_notAlias;
 324         if ($squirrelmail_language == 'ja_JP' && function_exists('mb_detect_encoding') ) {
 325             header ('Content-Type: text/html; charset=EUC-JP');
 326             if (!function_exists('mb_internal_encoding')) {
 327                 echo _("You need to have php4 installed with the multibyte string function enabled (using configure option --enable-mbstring).");
 328             }
 329             if (function_exists('mb_language')) {
 330                 mb_language('Japanese');
 331             }
 332             mb_internal_encoding('EUC-JP');
 333             mb_http_output('pass');
 334         } else {
 335         header( 'Content-Type: text/html; charset=' . $languages[$sm_notAlias]['CHARSET'] );
 336     }
 337 }
 338 }
 339
 340 function set_my_charset(){
 341
 342     /*
 343      * There can be a $default_charset setting in the
 344      * config.php file, but the user may have a different language
 345      * selected for a user interface. This function checks the
 346      * language selected by the user and tags the outgoing messages
 347      * with the appropriate charset corresponding to the language
 348      * selection. This is "more right" (tm), than just stamping the
 349      * message blindly with the system-wide $default_charset.
 350      */
 351     global $data_dir, $username, $default_charset, $languages, $squirrelmail_default_language;
 352
 353     $my_language = getPref($data_dir, $username, 'language');
 354     if (!$my_language) {
 355         $my_language = $squirrelmail_default_language ;
 356     }
 357     // Catch removed translation
 358     if (!isset($languages[$my_language])) {
 359       $my_language="en_US";
 360     }
 361     while (isset($languages[$my_language]['ALIAS'])) {
 362         $my_language = $languages[$my_language]['ALIAS'];
 363     }
 364     $my_charset = $languages[$my_language]['CHARSET'];
 365     if ($my_charset) {
 366         $default_charset = $my_charset;
 367     }
 368 }
 369
 370 /* ------------------------------ main --------------------------- */
 371
 372 global $squirrelmail_language, $languages, $use_gettext;
 373
 374 if (! isset($squirrelmail_language)) {
 375     $squirrelmail_language = '';
 376 }
 377
 378 /* This array specifies the available languages. */
 379 $languages['bg_BG']['NAME']    = 'Bulgarian';
 380 $languages['bg_BG']['ALTNAME'] = '&#1041;&#1098;&#1083;&#1075;&#1072;&#1088;&#1089;&#1082;&#1080;';
 381 $languages['bg_BG']['CHARSET'] = 'windows-1251';
 382 $languages['bg']['ALIAS'] = 'bg_BG';
 383
 384 $languages['ca_ES']['NAME']    = 'Catalan';
 385 $languages['ca_ES']['CHARSET'] = 'iso-8859-1';
 386 $languages['ca']['ALIAS'] = 'ca_ES';
 387
 388 $languages['cs_CZ']['NAME']    = 'Czech';
 389 $languages['cs_CZ']['ALTNAME'] = '&#268;e&scaron;tina';
 390 $languages['cs_CZ']['CHARSET'] = 'iso-8859-2';
 391 $languages['cs']['ALIAS']      = 'cs_CZ';
 392
 393 $languages['cy_GB']['NAME']    = 'Welsh';
 394 $languages['cy_GB']['ALTNAME'] = 'Cymraeg';
 395 $languages['cy_GB']['CHARSET'] = 'iso-8859-1';
 396 $languages['cy']['ALIAS'] = 'cy_GB';
 397
 398 // Danish locale is da_DK.
 399 $languages['da_DK']['NAME']    = 'Danish';
 400 $languages['da_DK']['ALTNAME'] = 'Dansk';
 401 $languages['da_DK']['CHARSET'] = 'iso-8859-1';
 402 $languages['da']['ALIAS'] = 'da_DK';
 403
 404 $languages['de_DE']['NAME']    = 'German';
 405 $languages['de_DE']['ALTNAME']    = 'Deutsch';
 406 $languages['de_DE']['CHARSET'] = 'iso-8859-1';
 407 $languages['de']['ALIAS'] = 'de_DE';
 408
 409 $languages['el_GR']['NAME']    = 'Greek';
 410 $languages['el_GR']['ALTNAME'] = '&Epsilon;&lambda;&lambda;&eta;&nu;&iota;&kappa;&#940;';
 411 $languages['el_GR']['CHARSET'] = 'iso-8859-7';
 412 $languages['el']['ALIAS'] = 'el_GR';
 413
 414 // There is no en_EN! There is en_US, en_BR, en_AU, and so forth,
 415 // but who cares about !US, right? Right? :)
 416 $languages['en_US']['NAME']    = 'English';
 417 $languages['en_US']['CHARSET'] = 'iso-8859-1';
 418 $languages['en']['ALIAS'] = 'en_US';
 419
 420 $languages['es_ES']['NAME']    = 'Spanish';
 421 $languages['es_ES']['ALTNAME'] = 'Espa&ntilde;ol';
 422 $languages['es_ES']['CHARSET'] = 'iso-8859-1';
 423 $languages['es']['ALIAS'] = 'es_ES';
 424
 425 $languages['et_EE']['NAME']    = 'Estonian';
 426 $languages['et_EE']['CHARSET'] = 'iso-8859-15';
 427 $languages['et']['ALIAS'] = 'et_EE';
 428
 429 $languages['fo_FO']['NAME']    = 'Faroese';
 430 $languages['fo_FO']['CHARSET'] = 'iso-8859-1';
 431 $languages['fo']['ALIAS'] = 'fo_FO';
 432
 433 $languages['fi_FI']['NAME']    = 'Finnish';
 434 $languages['fi_FI']['ALTNAME'] = 'Suomi';
 435 $languages['fi_FI']['CHARSET'] = 'iso-8859-1';
 436 $languages['fi']['ALIAS'] = 'fi_FI';
 437
 438 $languages['fr_FR']['NAME']    = 'French';
 439 $languages['fr_FR']['ALTNAME'] = 'Fran&#231;ais';
 440 $languages['fr_FR']['CHARSET'] = 'iso-8859-1';
 441 $languages['fr']['ALIAS'] = 'fr_FR';
 442
 443 $languages['hr_HR']['NAME']    = 'Croatian';
 444 $languages['hr_HR']['CHARSET'] = 'iso-8859-2';
 445 $languages['hr']['ALIAS'] = 'hr_HR';
 446
 447 $languages['hu_HU']['NAME']    = 'Hungarian';
 448 $languages['hu_HU']['ALTNAME'] = 'Magyar';
 449 $languages['hu_HU']['CHARSET'] = 'iso-8859-2';
 450 $languages['hu']['ALIAS'] = 'hu_HU';
 451
 452 $languages['id_ID']['NAME']    = 'Indonesian';
 453 $languages['id_ID']['ALTNAME'] = 'Bahasa Indonesia';
 454 $languages['id_ID']['CHARSET'] = 'iso-8859-1';
 455 $languages['id']['ALIAS'] = 'id_ID';
 456
 457 $languages['is_IS']['NAME']    = 'Icelandic';
 458 $languages['is_IS']['ALTNAME'] = '&Iacute;slenska';
 459 $languages['is_IS']['CHARSET'] = 'iso-8859-1';
 460 $languages['is']['ALIAS'] = 'is_IS';
 461
 462 $languages['it_IT']['NAME']    = 'Italian';
 463 $languages['it_IT']['CHARSET'] = 'iso-8859-1';
 464 $languages['it']['ALIAS'] = 'it_IT';
 465
 466 $languages['ja_JP']['NAME']    = 'Japanese';
 467 $languages['ja_JP']['ALTNAME'] = '&#26085;&#26412;&#35486;';
 468 $languages['ja_JP']['CHARSET'] = 'iso-2022-jp';
 469 $languages['ja_JP']['XTRA_CODE'] = 'japanese_charset_xtra';
 470 $languages['ja']['ALIAS'] = 'ja_JP';
 471
 472 $languages['ko_KR']['NAME']    = 'Korean';
 473 $languages['ko_KR']['CHARSET'] = 'euc-KR';
 474 $languages['ko_KR']['XTRA_CODE'] = 'korean_charset_xtra';
 475 $languages['ko']['ALIAS'] = 'ko_KR';
 476
 477 $languages['lt_LT']['NAME']    = 'Lithuanian';
 478 $languages['lt_LT']['ALTNAME'] = 'Lietuvi&#371;';
 479 $languages['lt_LT']['CHARSET'] = 'utf-8';
 480 $languages['lt_LT']['LOCALE'] = 'lt_LT.UTF-8';
 481 $languages['lt']['ALIAS'] = 'lt_LT';
 482
 483 $languages['nl_NL']['NAME']    = 'Dutch';
 484 $languages['nl_NL']['ALTNAME'] = 'Nederlands';
 485 $languages['nl_NL']['CHARSET'] = 'iso-8859-1';
 486 $languages['nl']['ALIAS'] = 'nl_NL';
 487
 488 $languages['ms_MY']['NAME']    = 'Malay';
 489 $languages['ms_MY']['ALTNAME'] = 'Bahasa Melayu';
 490 $languages['ms_MY']['CHARSET'] = 'iso-8859-1';
 491 $languages['my']['ALIAS'] = 'ms_MY';
 492
 493 $languages['no_NO']['NAME']    = 'Norwegian (Bokm&aring;l)';
 494 $languages['no_NO']['ALTNAME'] = 'Norsk (Bokm&aring;l)';
 495 $languages['no_NO']['CHARSET'] = 'iso-8859-1';
 496 $languages['no']['ALIAS'] = 'no_NO';
 497
 498 $languages['nn_NO']['NAME']    = 'Norwegian (Nynorsk)';
 499 $languages['nn_NO']['ALTNAME'] = 'Norsk (Nynorsk)';
 500 $languages['nn_NO']['CHARSET'] = 'iso-8859-1';
 501
 502 $languages['pl_PL']['NAME']    = 'Polish';
 503 $languages['pl_PL']['ALTNAME'] = 'Polski';
 504 $languages['pl_PL']['CHARSET'] = 'iso-8859-2';
 505 $languages['pl']['ALIAS'] = 'pl_PL';
 506
 507 $languages['pt_PT']['NAME'] = 'Portuguese (Portugal)';
 508 $languages['pt_PT']['CHARSET'] = 'iso-8859-1';
 509 $languages['pt']['ALIAS'] = 'pt_PT';
 510
 511 $languages['pt_BR']['NAME']    = 'Portuguese (Brazil)';
 512 $languages['pt_BR']['ALTNAME'] = 'Portugu&ecirc;s do Brasil';
 513 $languages['pt_BR']['CHARSET'] = 'iso-8859-1';
 514
 515 $languages['ro_RO']['NAME']    = 'Romanian';
 516 $languages['ro_RO']['ALTNAME'] = 'Rom&acirc;n&#259;';
 517 $languages['ro_RO']['CHARSET'] = 'iso-8859-2';
 518 $languages['ro']['ALIAS'] = 'ro_RO';
 519
 520 $languages['ru_RU']['NAME']    = 'Russian';
 521 $languages['ru_RU']['ALTNAME'] = '&#1056;&#1091;&#1089;&#1089;&#1082;&#1080;&#1081;';
 522 $languages['ru_RU']['CHARSET'] = 'utf-8';
 523 $languages['ru_RU']['LOCALE'] = 'ru_RU.UTF-8';
 524 $languages['ru']['ALIAS'] = 'ru_RU';
 525
 526 $languages['sk_SK']['NAME']     = 'Slovak';
 527 $languages['sk_SK']['CHARSET']  = 'iso-8859-2';
 528 $languages['sk']['ALIAS']       = 'sk_SK';
 529
 530 $languages['sl_SI']['NAME']    = 'Slovenian';
 531 $languages['sl_SI']['ALTNAME'] = 'Sloven&scaron;&#269;ina';
 532 $languages['sl_SI']['CHARSET'] = 'iso-8859-2';
 533 $languages['sl']['ALIAS'] = 'sl_SI';
 534
 535 $languages['sr_YU']['NAME']    = 'Serbian';
 536 $languages['sr_YU']['ALTNAME'] = 'Srpski';
 537 $languages['sr_YU']['CHARSET'] = 'iso-8859-2';
 538 $languages['sr']['ALIAS'] = 'sr_YU';
 539
 540 $languages['sv_SE']['NAME']    = 'Swedish';
 541 $languages['sv_SE']['ALTNAME'] = 'Svenska';
 542 $languages['sv_SE']['CHARSET'] = 'iso-8859-1';
 543 $languages['sv']['ALIAS'] = 'sv_SE';
 544
 545 $languages['th_TH']['NAME']    = 'Thai';
 546 $languages['th_TH']['CHARSET'] = 'tis-620';
 547 $languages['th']['ALIAS'] = 'th_TH';
 548
 549 $languages['tr_TR']['NAME']    = 'Turkish';
 550 $languages['tr_TR']['CHARSET'] = 'iso-8859-9';
 551 $languages['tr']['ALIAS'] = 'tr_TR';
 552
 553 $languages['zh_TW']['NAME']    = 'Chinese Trad';
 554 $languages['zh_TW']['CHARSET'] = 'big5';
 555 $languages['tw']['ALIAS'] = 'zh_TW';
 556
 557 $languages['zh_CN']['NAME']    = 'Chinese Simp';
 558 $languages['zh_CN']['CHARSET'] = 'gb2312';
 559 $languages['cn']['ALIAS'] = 'zh_CN';
 560
 561 /*
 562 $languages['uk_UA']['NAME']    = 'Ukrainian';
 563 $languages['uk_UA']['CHARSET'] = 'koi8-u';
 564 $languages['uk']['ALIAS'] = 'uk_UA';
 565 */
 566 /*
 567 if ( file_exists( SM_PATH . 'locale/vi_VN') ) {
 568     $languages['vi_VN']['NAME']    = 'Vietnamese';
 569     $languages['vi_VN']['CHARSET'] = 'utf-8';
 570     $languages['vi']['ALIAS'] = 'vi_VN';
 571 }
 572 */
 573
 574 // Right to left languages
 575 $languages['ar']['NAME']    = 'Arabic';
 576 $languages['ar']['CHARSET'] = 'windows-1256';
 577 $languages['ar']['DIR']     = 'rtl';
 578
 579 $languages['he_IL']['NAME']    = 'Hebrew';
 580 $languages['he_IL']['CHARSET'] = 'windows-1255';
 581 $languages['he_IL']['DIR']     = 'rtl';
 582 $languages['he']['ALIAS']      = 'he_IL';
 583
 584 /* Detect whether gettext is installed. */
 585 $gettext_flags = 0;
 586 if (function_exists('_')) {
 587     $gettext_flags += 1;
 588 }
 589 if (function_exists('bindtextdomain')) {
 590     $gettext_flags += 2;
 591 }
 592 if (function_exists('textdomain')) {
 593     $gettext_flags += 4;
 594 }
 595
 596 /* If gettext is fully loaded, cool */
 597 if ($gettext_flags == 7) {
 598     $use_gettext = true;
 599 }
 600 /* If we can fake gettext, try that */
 601 elseif ($gettext_flags == 0) {
 602     $use_gettext = true;
 603     include_once(SM_PATH . 'functions/gettext.php');
 604 } else {
 605     /* Uh-ho.  A weird install */
 606     if (! $gettext_flags & 1) {
 607         function _($str) {
 608             return $str;
 609         }
 610     }
 611     if (! $gettext_flags & 2) {
 612         function bindtextdomain() {
 613             return;
 614         }
 615     }
 616     if (! $gettext_flags & 4) {
 617         function textdomain() {
 618             return;
 619         }
 620     }
 621 }
 622
 623
 624 /*
 625  * Japanese charset extra function
 626  *
 627  */
 628 function japanese_charset_xtra() {
 629     $ret = func_get_arg(1);  /* default return value */
 630     if (function_exists('mb_detect_encoding')) {
 631         switch (func_get_arg(0)) { /* action */
 632         case 'decode':
 633             $detect_encoding = @mb_detect_encoding($ret);
 634             if ($detect_encoding == 'JIS' ||
 635                 $detect_encoding == 'EUC-JP' ||
 636                 $detect_encoding == 'SJIS' ||
 637                 $detect_encoding == 'UTF-8') {
 638
 639                 $ret = mb_convert_kana(mb_convert_encoding($ret, 'EUC-JP', 'AUTO'), "KV");
 640             }
 641             break;
 642         case 'encode':
 643             $detect_encoding = @mb_detect_encoding($ret);
 644             if ($detect_encoding == 'JIS' ||
 645                 $detect_encoding == 'EUC-JP' ||
 646                 $detect_encoding == 'SJIS' ||
 647                 $detect_encoding == 'UTF-8') {
 648
 649                 $ret = mb_convert_encoding(mb_convert_kana($ret, "KV"), 'JIS', 'AUTO');
 650             }
 651             break;
 652         case 'strimwidth':
 653             $width = func_get_arg(2);
 654             $ret = mb_strimwidth($ret, 0, $width, '...');
 655             break;
 656         case 'encodeheader':
 657             $result = '';
 658             if (strlen($ret) > 0) {
 659                 $tmpstr = mb_substr($ret, 0, 1);
 660                 $prevcsize = strlen($tmpstr);
 661                 for ($i = 1; $i < mb_strlen($ret); $i++) {
 662                     $tmp = mb_substr($ret, $i, 1);
 663                     if (strlen($tmp) == $prevcsize) {
 664                         $tmpstr .= $tmp;
 665                     } else {
 666                         if ($prevcsize == 1) {
 667                             $result .= $tmpstr;
 668                         } else {
 669                             $result .= str_replace(' ', '',
 670                                                    mb_encode_mimeheader($tmpstr,'iso-2022-jp','B',''));
 671                         }
 672                         $tmpstr = $tmp;
 673                         $prevcsize = strlen($tmp);
 674                     }
 675                 }
 676                 if (strlen($tmpstr)) {
 677                     if (strlen(mb_substr($tmpstr, 0, 1)) == 1)
 678                         $result .= $tmpstr;
 679                     else
 680                         $result .= str_replace(' ', '',
 681                                                mb_encode_mimeheader($tmpstr,'iso-2022-jp','B',''));
 682                 }
 683             }
 684             $ret = $result;
 685             break;
 686         case 'decodeheader':
 687             $ret = str_replace("\t", "", $ret);
 688             if (eregi('=\\?([^?]+)\\?(q|b)\\?([^?]+)\\?=', $ret))
 689                 $ret = @mb_decode_mimeheader($ret);
 690             $ret = @mb_convert_encoding($ret, 'EUC-JP', 'AUTO');
 691             break;
 692         case 'downloadfilename':
 693             $useragent = func_get_arg(2);
 694             if (strstr($useragent, 'Windows') !== false ||
 695                 strstr($useragent, 'Mac_') !== false) {
 696                 $ret = mb_convert_encoding($ret, 'SJIS', 'AUTO');
 697             } else {
 698                 $ret = mb_convert_encoding($ret, 'EUC-JP', 'AUTO');
 699 }
 700             break;
 701         case 'wordwrap':
 702             $no_begin = "\x21\x25\x29\x2c\x2e\x3a\x3b\x3f\x5d\x7d\xa1\xf1\xa1\xeb\xa1" .
 703                 "\xc7\xa1\xc9\xa2\xf3\xa1\xec\xa1\xed\xa1\xee\xa1\xa2\xa1\xa3\xa1\xb9" .
 704                 "\xa1\xd3\xa1\xd5\xa1\xd7\xa1\xd9\xa1\xdb\xa1\xcd\xa4\xa1\xa4\xa3\xa4" .
 705                 "\xa5\xa4\xa7\xa4\xa9\xa4\xc3\xa4\xe3\xa4\xe5\xa4\xe7\xa4\xee\xa1\xab" .
 706                 "\xa1\xac\xa1\xb5\xa1\xb6\xa5\xa1\xa5\xa3\xa5\xa5\xa5\xa7\xa5\xa9\xa5" .
 707                 "\xc3\xa5\xe3\xa5\xe5\xa5\xe7\xa5\xee\xa5\xf5\xa5\xf6\xa1\xa6\xa1\xbc" .
 708                 "\xa1\xb3\xa1\xb4\xa1\xaa\xa1\xf3\xa1\xcb\xa1\xa4\xa1\xa5\xa1\xa7\xa1" .
 709                 "\xa8\xa1\xa9\xa1\xcf\xa1\xd1";
 710             $no_end = "\x5c\x24\x28\x5b\x7b\xa1\xf2\x5c\xa1\xc6\xa1\xc8\xa1\xd2\xa1" .
 711                 "\xd4\xa1\xd6\xa1\xd8\xa1\xda\xa1\xcc\xa1\xf0\xa1\xca\xa1\xce\xa1\xd0\xa1\xef";
 712             $wrap = func_get_arg(2);
 713
 714             if (strlen($ret) >= $wrap &&
 715                 substr($ret, 0, 1) != '>' &&
 716                 strpos($ret, 'http://') === FALSE &&
 717                 strpos($ret, 'https://') === FALSE &&
 718                 strpos($ret, 'ftp://') === FALSE) {
 719
 720                 $ret = mb_convert_kana($ret, "KV");
 721
 722                 $line_new = '';
 723                 $ptr = 0;
 724
 725                 while ($ptr < strlen($ret) - 1) {
 726                     $l = mb_strcut($ret, $ptr, $wrap);
 727                     $ptr += strlen($l);
 728                     $tmp = $l;
 729
 730                     $l = mb_strcut($ret, $ptr, 2);
 731                     while (strlen($l) != 0 && mb_strpos($no_begin, $l) !== FALSE ) {
 732                         $tmp .= $l;
 733                         $ptr += strlen($l);
 734                         $l = mb_strcut($ret, $ptr, 1);
 735                     }
 736                     $line_new .= $tmp;
 737                     if ($ptr < strlen($ret) - 1)
 738                         $line_new .= "\n";
 739                 }
 740                 $ret = $line_new;
 741             }
 742             break;
 743         case 'utf7-imap_encode':
 744             $ret = mb_convert_encoding($ret, 'UTF7-IMAP', 'EUC-JP');
 745             break;
 746         case 'utf7-imap_decode':
 747             $ret = mb_convert_encoding($ret, 'EUC-JP', 'UTF7-IMAP');
 748             break;
 749         }
 750     }
 751     return $ret;
 752 }
 753
 754
 755 /*
 756  * Korean charset extra function
 757  * Hangul(Korean Character) Attached File Name Fix.
 758  */
 759 function korean_charset_xtra() {
 760
 761     $ret = func_get_arg(1);  /* default return value */
 762     if (func_get_arg(0) == 'downloadfilename') { /* action */
 763         $ret = str_replace("\x0D\x0A", '', $ret);  /* Hanmail's CR/LF Clear */
 764         for ($i=0;$i<strlen($ret);$i++) {
 765             if ($ret[$i] >= "\xA1" && $ret[$i] <= "\xFE") {   /* 0xA1 - 0XFE are Valid */
 766                 $i++;
 767                 continue;
 768             } else if (($ret[$i] >= 'a' && $ret[$i] <= 'z') || /* From Original ereg_replace in download.php */
 769                        ($ret[$i] >= 'A' && $ret[$i] <= 'Z') ||
 770                        ($ret[$i] == '.') || ($ret[$i] == '-')) {
 771                 continue;
 772             } else {
 773                 $ret[$i] = '_';
 774             }
 775         }
 776
 777     }
 778
 779     return $ret;
 780 }
 781
 782 /*
 783  * This function can be used to replace non-braking space symbols
 784  * that are inserted in forms by some browsers instead of normal
 785  * space symbol.
 786  */
 787 function cleanup_nbsp($string,$charset) {
 788
 789   // reduce number of case statements
 790   if (stristr('iso-8859-',substr($charset,0,9))){
 791     $output_charset="iso-8859-x";
 792   }
 793   if (stristr('windows-125',substr($charset,0,11))){
 794     $output_charset="cp125x";
 795   }
 796   if (stristr('koi8',substr($charset,0,4))){
 797     $output_charset="koi8-x";
 798   }
 799   if (! isset($output_charset)){
 800     $output_charset=strtolower($charset);
 801   }
 802
 803 // where is non-braking space symbol
 804 switch($output_charset):
 805  case "iso-8859-x":
 806  case "cp125x":
 807  case "iso-2022-jp":
 808   $nbsp="\xA0";
 809   break;
 810  case "koi8-x":
 811    $nbsp="\x9A";
 812    break;
 813  case "utf-8":
 814    $nbsp="\xC2\xA0";
 815    break;
 816  default:
 817    // don't change string if charset is unmatched
 818    return $string;
 819 endswitch;
 820
 821 // return space instead of non-braking space.
 822  return str_replace($nbsp,' ',$string);
 823 }
 824
 825 function is_conversion_safe($input_charset) {
 826   global $languages, $sm_notAlias, $default_charset;
 827
 828  // convert to lower case
 829  $input_charset = strtolower($input_charset);
 830
 831  // Is user's locale Unicode based ?
 832  if ( $default_charset == "utf-8" ) {
 833    return true;
 834  }
 835
 836  // Charsets that are similar
 837 switch ($default_charset):
 838 case "windows-1251":
 839       if ( $input_charset == "iso-8859-5" ||
 840            $input_charset == "koi8-r" ||
 841            $input_charset == "koi8-u" ) {
 842         return true;
 843      } else {
 844         return false;
 845      }
 846 case "windows-1257":
 847   if ( $input_charset == "iso-8859-13" ||
 848          $input_charset == "iso-8859-4" ) {
 849     return true;
 850   } else {
 851     return false;
 852   }
 853 case "iso-8859-4":
 854   if ( $input_charset == "iso-8859-13" ||
 855          $input_charset == "windows-1257" ) {
 856      return true;
 857   } else {
 858      return false;
 859   }
 860 case "iso-8859-5":
 861   if ( $input_charset == "windows-1251" ||
 862          $input_charset == "koi8-r" ||
 863          $input_charset == "koi8-u" ) {
 864      return true;
 865   } else {
 866      return false;
 867   }
 868 case "iso-8859-13":
 869   if ( $input_charset == "iso-8859-4" ||
 870        $input_charset == "windows-1257" ) {
 871      return true;
 872   } else {
 873      return false;
 874   }
 875 case "koi8-r":
 876   if ( $input_charset == "windows-1251" ||
 877          $input_charset == "iso-8859-5" ||
 878          $input_charset == "koi8-u" ) {
 879      return true;
 880   } else {
 881      return false;
 882   }
 883 case "koi8-u":
 884   if ( $input_charset == "windows-1251" ||
 885         $input_charset == "iso-8859-5" ||
 886         $input_charset == "koi8-r" ) {
 887      return true;
 888   } else {
 889      return false;
 890   }
 891 default:
 892    return false;
 893 endswitch;
 894 }
 895 ?>