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[$sm_notAlias]['CHARSET']) ) {
 306         bindtextdomain( 'squirrelmail', SM_PATH . 'locale/' );
 307         textdomain( 'squirrelmail' );
 308         if (function_exists('bind_textdomain_codeset')) {
 309             if ($sm_notAlias == 'ja_JP') {
 310                 bind_textdomain_codeset ("squirrelmail", 'EUC-JP');
 311             } else {
 312                 bind_textdomain_codeset ("squirrelmail", $languages[$sm_notAlias]['CHARSET'] );
 313             }
 314         }
 315         if (isset($languages[$sm_notAlias]['LOCALE'])){
 316           $longlocale=$languages[$sm_notAlias]['LOCALE'];
 317         } else {
 318           $longlocale=$sm_notAlias;
 319         }
 320         if ( !ini_get('safe_mode') &&
 321              getenv( 'LC_ALL' ) != $longlocale ) {
 322             putenv( "LC_ALL=$longlocale" );
 323             putenv( "LANG=$longlocale" );
 324             putenv( "LANGUAGE=$longlocale" );
 325         }
 326         setlocale(LC_ALL, $longlocale);
 327         $squirrelmail_language = $sm_notAlias;
 328         if ($squirrelmail_language == 'ja_JP') {
 329             header ('Content-Type: text/html; charset=EUC-JP');
 330             if (!function_exists('mb_internal_encoding')) {
 331                 echo _("You need to have php4 installed with the multibyte string function enabled (using configure option --enable-mbstring).");
 332                 // Revert to English link has to be added.
 333                 // stop further execution in order not to get php errors on mb_internal_encoding().
 334                 return;
 335             }
 336             if (function_exists('mb_language')) {
 337                 mb_language('Japanese');
 338             }
 339             mb_internal_encoding('EUC-JP');
 340             mb_http_output('pass');
 341         } else {
 342         header( 'Content-Type: text/html; charset=' . $languages[$sm_notAlias]['CHARSET'] );
 343     }
 344 }
 345 }
 346
 347 function set_my_charset(){
 348
 349     /*
 350      * There can be a $default_charset setting in the
 351      * config.php file, but the user may have a different language
 352      * selected for a user interface. This function checks the
 353      * language selected by the user and tags the outgoing messages
 354      * with the appropriate charset corresponding to the language
 355      * selection. This is "more right" (tm), than just stamping the
 356      * message blindly with the system-wide $default_charset.
 357      */
 358     global $data_dir, $username, $default_charset, $languages, $squirrelmail_default_language;
 359
 360     $my_language = getPref($data_dir, $username, 'language');
 361     if (!$my_language) {
 362         $my_language = $squirrelmail_default_language ;
 363     }
 364     // Catch removed translation
 365     if (!isset($languages[$my_language])) {
 366       $my_language="en_US";
 367     }
 368     while (isset($languages[$my_language]['ALIAS'])) {
 369         $my_language = $languages[$my_language]['ALIAS'];
 370     }
 371     $my_charset = $languages[$my_language]['CHARSET'];
 372     if ($my_charset) {
 373         $default_charset = $my_charset;
 374     }
 375 }
 376
 377 /* ------------------------------ main --------------------------- */
 378
 379 global $squirrelmail_language, $languages, $use_gettext;
 380
 381 if (! isset($squirrelmail_language)) {
 382     $squirrelmail_language = '';
 383 }
 384
 385 /* This array specifies the available languages. */
 386 $languages['bg_BG']['NAME']    = 'Bulgarian';
 387 $languages['bg_BG']['ALTNAME'] = '&#1041;&#1098;&#1083;&#1075;&#1072;&#1088;&#1089;&#1082;&#1080;';
 388 $languages['bg_BG']['CHARSET'] = 'windows-1251';
 389 $languages['bg']['ALIAS'] = 'bg_BG';
 390
 391 $languages['ca_ES']['NAME']    = 'Catalan';
 392 $languages['ca_ES']['CHARSET'] = 'iso-8859-1';
 393 $languages['ca']['ALIAS'] = 'ca_ES';
 394
 395 $languages['cs_CZ']['NAME']    = 'Czech';
 396 $languages['cs_CZ']['ALTNAME'] = '&#268;e&scaron;tina';
 397 $languages['cs_CZ']['CHARSET'] = 'iso-8859-2';
 398 $languages['cs']['ALIAS']      = 'cs_CZ';
 399
 400 $languages['cy_GB']['NAME']    = 'Welsh';
 401 $languages['cy_GB']['ALTNAME'] = 'Cymraeg';
 402 $languages['cy_GB']['CHARSET'] = 'iso-8859-1';
 403 $languages['cy']['ALIAS'] = 'cy_GB';
 404
 405 // Danish locale is da_DK.
 406 $languages['da_DK']['NAME']    = 'Danish';
 407 $languages['da_DK']['ALTNAME'] = 'Dansk';
 408 $languages['da_DK']['CHARSET'] = 'iso-8859-1';
 409 $languages['da']['ALIAS'] = 'da_DK';
 410
 411 $languages['de_DE']['NAME']    = 'German';
 412 $languages['de_DE']['ALTNAME']    = 'Deutsch';
 413 $languages['de_DE']['CHARSET'] = 'iso-8859-1';
 414 $languages['de']['ALIAS'] = 'de_DE';
 415
 416 $languages['el_GR']['NAME']    = 'Greek';
 417 $languages['el_GR']['ALTNAME'] = '&Epsilon;&lambda;&lambda;&eta;&nu;&iota;&kappa;&#940;';
 418 $languages['el_GR']['CHARSET'] = 'iso-8859-7';
 419 $languages['el']['ALIAS'] = 'el_GR';
 420
 421 // There is no en_EN! There is en_US, en_BR, en_AU, and so forth,
 422 // but who cares about !US, right? Right? :)
 423 $languages['en_US']['NAME']    = 'English';
 424 $languages['en_US']['CHARSET'] = 'iso-8859-1';
 425 $languages['en']['ALIAS'] = 'en_US';
 426
 427 $languages['es_ES']['NAME']    = 'Spanish';
 428 $languages['es_ES']['ALTNAME'] = 'Espa&ntilde;ol';
 429 $languages['es_ES']['CHARSET'] = 'iso-8859-1';
 430 $languages['es']['ALIAS'] = 'es_ES';
 431
 432 $languages['et_EE']['NAME']    = 'Estonian';
 433 $languages['et_EE']['CHARSET'] = 'iso-8859-15';
 434 $languages['et']['ALIAS'] = 'et_EE';
 435
 436 $languages['fo_FO']['NAME']    = 'Faroese';
 437 $languages['fo_FO']['CHARSET'] = 'iso-8859-1';
 438 $languages['fo']['ALIAS'] = 'fo_FO';
 439
 440 $languages['fi_FI']['NAME']    = 'Finnish';
 441 $languages['fi_FI']['ALTNAME'] = 'Suomi';
 442 $languages['fi_FI']['CHARSET'] = 'iso-8859-1';
 443 $languages['fi']['ALIAS'] = 'fi_FI';
 444
 445 $languages['fr_FR']['NAME']    = 'French';
 446 $languages['fr_FR']['ALTNAME'] = 'Fran&#231;ais';
 447 $languages['fr_FR']['CHARSET'] = 'iso-8859-1';
 448 $languages['fr']['ALIAS'] = 'fr_FR';
 449
 450 $languages['hr_HR']['NAME']    = 'Croatian';
 451 $languages['hr_HR']['CHARSET'] = 'iso-8859-2';
 452 $languages['hr']['ALIAS'] = 'hr_HR';
 453
 454 $languages['hu_HU']['NAME']    = 'Hungarian';
 455 $languages['hu_HU']['ALTNAME'] = 'Magyar';
 456 $languages['hu_HU']['CHARSET'] = 'iso-8859-2';
 457 $languages['hu']['ALIAS'] = 'hu_HU';
 458
 459 $languages['id_ID']['NAME']    = 'Indonesian';
 460 $languages['id_ID']['ALTNAME'] = 'Bahasa Indonesia';
 461 $languages['id_ID']['CHARSET'] = 'iso-8859-1';
 462 $languages['id']['ALIAS'] = 'id_ID';
 463
 464 $languages['is_IS']['NAME']    = 'Icelandic';
 465 $languages['is_IS']['ALTNAME'] = '&Iacute;slenska';
 466 $languages['is_IS']['CHARSET'] = 'iso-8859-1';
 467 $languages['is']['ALIAS'] = 'is_IS';
 468
 469 $languages['it_IT']['NAME']    = 'Italian';
 470 $languages['it_IT']['CHARSET'] = 'iso-8859-1';
 471 $languages['it']['ALIAS'] = 'it_IT';
 472
 473 $languages['ja_JP']['NAME']    = 'Japanese';
 474 $languages['ja_JP']['ALTNAME'] = '&#26085;&#26412;&#35486;';
 475 $languages['ja_JP']['CHARSET'] = 'iso-2022-jp';
 476 $languages['ja_JP']['XTRA_CODE'] = 'japanese_charset_xtra';
 477 $languages['ja']['ALIAS'] = 'ja_JP';
 478
 479 $languages['ko_KR']['NAME']    = 'Korean';
 480 $languages['ko_KR']['CHARSET'] = 'euc-KR';
 481 $languages['ko_KR']['XTRA_CODE'] = 'korean_charset_xtra';
 482 $languages['ko']['ALIAS'] = 'ko_KR';
 483
 484 $languages['lt_LT']['NAME']    = 'Lithuanian';
 485 $languages['lt_LT']['ALTNAME'] = 'Lietuvi&#371;';
 486 $languages['lt_LT']['CHARSET'] = 'utf-8';
 487 $languages['lt_LT']['LOCALE'] = 'lt_LT.UTF-8';
 488 $languages['lt']['ALIAS'] = 'lt_LT';
 489
 490 $languages['nl_NL']['NAME']    = 'Dutch';
 491 $languages['nl_NL']['ALTNAME'] = 'Nederlands';
 492 $languages['nl_NL']['CHARSET'] = 'iso-8859-1';
 493 $languages['nl']['ALIAS'] = 'nl_NL';
 494
 495 $languages['ms_MY']['NAME']    = 'Malay';
 496 $languages['ms_MY']['ALTNAME'] = 'Bahasa Melayu';
 497 $languages['ms_MY']['CHARSET'] = 'iso-8859-1';
 498 $languages['my']['ALIAS'] = 'ms_MY';
 499
 500 $languages['no_NO']['NAME']    = 'Norwegian (Bokm&aring;l)';
 501 $languages['no_NO']['ALTNAME'] = 'Norsk (Bokm&aring;l)';
 502 $languages['no_NO']['CHARSET'] = 'iso-8859-1';
 503 $languages['no']['ALIAS'] = 'no_NO';
 504
 505 $languages['nn_NO']['NAME']    = 'Norwegian (Nynorsk)';
 506 $languages['nn_NO']['ALTNAME'] = 'Norsk (Nynorsk)';
 507 $languages['nn_NO']['CHARSET'] = 'iso-8859-1';
 508
 509 $languages['pl_PL']['NAME']    = 'Polish';
 510 $languages['pl_PL']['ALTNAME'] = 'Polski';
 511 $languages['pl_PL']['CHARSET'] = 'iso-8859-2';
 512 $languages['pl']['ALIAS'] = 'pl_PL';
 513
 514 $languages['pt_PT']['NAME'] = 'Portuguese (Portugal)';
 515 $languages['pt_PT']['CHARSET'] = 'iso-8859-1';
 516 $languages['pt']['ALIAS'] = 'pt_PT';
 517
 518 $languages['pt_BR']['NAME']    = 'Portuguese (Brazil)';
 519 $languages['pt_BR']['ALTNAME'] = 'Portugu&ecirc;s do Brasil';
 520 $languages['pt_BR']['CHARSET'] = 'iso-8859-1';
 521
 522 $languages['ro_RO']['NAME']    = 'Romanian';
 523 $languages['ro_RO']['ALTNAME'] = 'Rom&acirc;n&#259;';
 524 $languages['ro_RO']['CHARSET'] = 'iso-8859-2';
 525 $languages['ro']['ALIAS'] = 'ro_RO';
 526
 527 $languages['ru_RU']['NAME']    = 'Russian';
 528 $languages['ru_RU']['ALTNAME'] = '&#1056;&#1091;&#1089;&#1089;&#1082;&#1080;&#1081;';
 529 $languages['ru_RU']['CHARSET'] = 'utf-8';
 530 $languages['ru_RU']['LOCALE'] = 'ru_RU.UTF-8';
 531 $languages['ru']['ALIAS'] = 'ru_RU';
 532
 533 $languages['sk_SK']['NAME']     = 'Slovak';
 534 $languages['sk_SK']['CHARSET']  = 'iso-8859-2';
 535 $languages['sk']['ALIAS']       = 'sk_SK';
 536
 537 $languages['sl_SI']['NAME']    = 'Slovenian';
 538 $languages['sl_SI']['ALTNAME'] = 'Sloven&scaron;&#269;ina';
 539 $languages['sl_SI']['CHARSET'] = 'iso-8859-2';
 540 $languages['sl']['ALIAS'] = 'sl_SI';
 541
 542 $languages['sr_YU']['NAME']    = 'Serbian';
 543 $languages['sr_YU']['ALTNAME'] = 'Srpski';
 544 $languages['sr_YU']['CHARSET'] = 'iso-8859-2';
 545 $languages['sr']['ALIAS'] = 'sr_YU';
 546
 547 $languages['sv_SE']['NAME']    = 'Swedish';
 548 $languages['sv_SE']['ALTNAME'] = 'Svenska';
 549 $languages['sv_SE']['CHARSET'] = 'iso-8859-1';
 550 $languages['sv']['ALIAS'] = 'sv_SE';
 551
 552 $languages['th_TH']['NAME']    = 'Thai';
 553 $languages['th_TH']['CHARSET'] = 'tis-620';
 554 $languages['th']['ALIAS'] = 'th_TH';
 555
 556 $languages['tr_TR']['NAME']    = 'Turkish';
 557 $languages['tr_TR']['CHARSET'] = 'iso-8859-9';
 558 $languages['tr']['ALIAS'] = 'tr_TR';
 559
 560 $languages['zh_TW']['NAME']    = 'Chinese Trad';
 561 $languages['zh_TW']['CHARSET'] = 'big5';
 562 $languages['tw']['ALIAS'] = 'zh_TW';
 563
 564 $languages['zh_CN']['NAME']    = 'Chinese Simp';
 565 $languages['zh_CN']['CHARSET'] = 'gb2312';
 566 $languages['cn']['ALIAS'] = 'zh_CN';
 567
 568 /*
 569 $languages['uk_UA']['NAME']    = 'Ukrainian';
 570 $languages['uk_UA']['CHARSET'] = 'koi8-u';
 571 $languages['uk']['ALIAS'] = 'uk_UA';
 572 */
 573 /*
 574 if ( file_exists( SM_PATH . 'locale/vi_VN') ) {
 575     $languages['vi_VN']['NAME']    = 'Vietnamese';
 576     $languages['vi_VN']['CHARSET'] = 'utf-8';
 577     $languages['vi']['ALIAS'] = 'vi_VN';
 578 }
 579 */
 580
 581 // Right to left languages
 582 $languages['ar']['NAME']    = 'Arabic';
 583 $languages['ar']['CHARSET'] = 'windows-1256';
 584 $languages['ar']['DIR']     = 'rtl';
 585
 586 $languages['he_IL']['NAME']    = 'Hebrew';
 587 $languages['he_IL']['CHARSET'] = 'windows-1255';
 588 $languages['he_IL']['DIR']     = 'rtl';
 589 $languages['he']['ALIAS']      = 'he_IL';
 590
 591 /* Detect whether gettext is installed. */
 592 $gettext_flags = 0;
 593 if (function_exists('_')) {
 594     $gettext_flags += 1;
 595 }
 596 if (function_exists('bindtextdomain')) {
 597     $gettext_flags += 2;
 598 }
 599 if (function_exists('textdomain')) {
 600     $gettext_flags += 4;
 601 }
 602
 603 /* If gettext is fully loaded, cool */
 604 if ($gettext_flags == 7) {
 605     $use_gettext = true;
 606 }
 607 /* If we can fake gettext, try that */
 608 elseif ($gettext_flags == 0) {
 609     $use_gettext = true;
 610     include_once(SM_PATH . 'functions/gettext.php');
 611 } else {
 612     /* Uh-ho.  A weird install */
 613     if (! $gettext_flags & 1) {
 614         function _($str) {
 615             return $str;
 616         }
 617     }
 618     if (! $gettext_flags & 2) {
 619         function bindtextdomain() {
 620             return;
 621         }
 622     }
 623     if (! $gettext_flags & 4) {
 624         function textdomain() {
 625             return;
 626         }
 627     }
 628 }
 629
 630
 631 /*
 632  * Japanese charset extra function
 633  *
 634  */
 635 function japanese_charset_xtra() {
 636     $ret = func_get_arg(1);  /* default return value */
 637     if (function_exists('mb_detect_encoding')) {
 638         switch (func_get_arg(0)) { /* action */
 639         case 'decode':
 640             $detect_encoding = @mb_detect_encoding($ret);
 641             if ($detect_encoding == 'JIS' ||
 642                 $detect_encoding == 'EUC-JP' ||
 643                 $detect_encoding == 'SJIS' ||
 644                 $detect_encoding == 'UTF-8') {
 645
 646                 $ret = mb_convert_kana(mb_convert_encoding($ret, 'EUC-JP', 'AUTO'), "KV");
 647             }
 648             break;
 649         case 'encode':
 650             $detect_encoding = @mb_detect_encoding($ret);
 651             if ($detect_encoding == 'JIS' ||
 652                 $detect_encoding == 'EUC-JP' ||
 653                 $detect_encoding == 'SJIS' ||
 654                 $detect_encoding == 'UTF-8') {
 655
 656                 $ret = mb_convert_encoding(mb_convert_kana($ret, "KV"), 'JIS', 'AUTO');
 657             }
 658             break;
 659         case 'strimwidth':
 660             $width = func_get_arg(2);
 661             $ret = mb_strimwidth($ret, 0, $width, '...');
 662             break;
 663         case 'encodeheader':
 664             $result = '';
 665             if (strlen($ret) > 0) {
 666                 $tmpstr = mb_substr($ret, 0, 1);
 667                 $prevcsize = strlen($tmpstr);
 668                 for ($i = 1; $i < mb_strlen($ret); $i++) {
 669                     $tmp = mb_substr($ret, $i, 1);
 670                     if (strlen($tmp) == $prevcsize) {
 671                         $tmpstr .= $tmp;
 672                     } else {
 673                         if ($prevcsize == 1) {
 674                             $result .= $tmpstr;
 675                         } else {
 676                             $result .= str_replace(' ', '',
 677                                                    mb_encode_mimeheader($tmpstr,'iso-2022-jp','B',''));
 678                         }
 679                         $tmpstr = $tmp;
 680                         $prevcsize = strlen($tmp);
 681                     }
 682                 }
 683                 if (strlen($tmpstr)) {
 684                     if (strlen(mb_substr($tmpstr, 0, 1)) == 1)
 685                         $result .= $tmpstr;
 686                     else
 687                         $result .= str_replace(' ', '',
 688                                                mb_encode_mimeheader($tmpstr,'iso-2022-jp','B',''));
 689                 }
 690             }
 691             $ret = $result;
 692             break;
 693         case 'decodeheader':
 694             $ret = str_replace("\t", "", $ret);
 695             if (eregi('=\\?([^?]+)\\?(q|b)\\?([^?]+)\\?=', $ret))
 696                 $ret = @mb_decode_mimeheader($ret);
 697             $ret = @mb_convert_encoding($ret, 'EUC-JP', 'AUTO');
 698             break;
 699         case 'downloadfilename':
 700             $useragent = func_get_arg(2);
 701             if (strstr($useragent, 'Windows') !== false ||
 702                 strstr($useragent, 'Mac_') !== false) {
 703                 $ret = mb_convert_encoding($ret, 'SJIS', 'AUTO');
 704             } else {
 705                 $ret = mb_convert_encoding($ret, 'EUC-JP', 'AUTO');
 706 }
 707             break;
 708         case 'wordwrap':
 709             $no_begin = "\x21\x25\x29\x2c\x2e\x3a\x3b\x3f\x5d\x7d\xa1\xf1\xa1\xeb\xa1" .
 710                 "\xc7\xa1\xc9\xa2\xf3\xa1\xec\xa1\xed\xa1\xee\xa1\xa2\xa1\xa3\xa1\xb9" .
 711                 "\xa1\xd3\xa1\xd5\xa1\xd7\xa1\xd9\xa1\xdb\xa1\xcd\xa4\xa1\xa4\xa3\xa4" .
 712                 "\xa5\xa4\xa7\xa4\xa9\xa4\xc3\xa4\xe3\xa4\xe5\xa4\xe7\xa4\xee\xa1\xab" .
 713                 "\xa1\xac\xa1\xb5\xa1\xb6\xa5\xa1\xa5\xa3\xa5\xa5\xa5\xa7\xa5\xa9\xa5" .
 714                 "\xc3\xa5\xe3\xa5\xe5\xa5\xe7\xa5\xee\xa5\xf5\xa5\xf6\xa1\xa6\xa1\xbc" .
 715                 "\xa1\xb3\xa1\xb4\xa1\xaa\xa1\xf3\xa1\xcb\xa1\xa4\xa1\xa5\xa1\xa7\xa1" .
 716                 "\xa8\xa1\xa9\xa1\xcf\xa1\xd1";
 717             $no_end = "\x5c\x24\x28\x5b\x7b\xa1\xf2\x5c\xa1\xc6\xa1\xc8\xa1\xd2\xa1" .
 718                 "\xd4\xa1\xd6\xa1\xd8\xa1\xda\xa1\xcc\xa1\xf0\xa1\xca\xa1\xce\xa1\xd0\xa1\xef";
 719             $wrap = func_get_arg(2);
 720
 721             if (strlen($ret) >= $wrap &&
 722                 substr($ret, 0, 1) != '>' &&
 723                 strpos($ret, 'http://') === FALSE &&
 724                 strpos($ret, 'https://') === FALSE &&
 725                 strpos($ret, 'ftp://') === FALSE) {
 726
 727                 $ret = mb_convert_kana($ret, "KV");
 728
 729                 $line_new = '';
 730                 $ptr = 0;
 731
 732                 while ($ptr < strlen($ret) - 1) {
 733                     $l = mb_strcut($ret, $ptr, $wrap);
 734                     $ptr += strlen($l);
 735                     $tmp = $l;
 736
 737                     $l = mb_strcut($ret, $ptr, 2);
 738                     while (strlen($l) != 0 && mb_strpos($no_begin, $l) !== FALSE ) {
 739                         $tmp .= $l;
 740                         $ptr += strlen($l);
 741                         $l = mb_strcut($ret, $ptr, 1);
 742                     }
 743                     $line_new .= $tmp;
 744                     if ($ptr < strlen($ret) - 1)
 745                         $line_new .= "\n";
 746                 }
 747                 $ret = $line_new;
 748             }
 749             break;
 750         case 'utf7-imap_encode':
 751             $ret = mb_convert_encoding($ret, 'UTF7-IMAP', 'EUC-JP');
 752             break;
 753         case 'utf7-imap_decode':
 754             $ret = mb_convert_encoding($ret, 'EUC-JP', 'UTF7-IMAP');
 755             break;
 756         }
 757     }
 758     return $ret;
 759 }
 760
 761
 762 /*
 763  * Korean charset extra function
 764  * Hangul(Korean Character) Attached File Name Fix.
 765  */
 766 function korean_charset_xtra() {
 767
 768     $ret = func_get_arg(1);  /* default return value */
 769     if (func_get_arg(0) == 'downloadfilename') { /* action */
 770         $ret = str_replace("\x0D\x0A", '', $ret);  /* Hanmail's CR/LF Clear */
 771         for ($i=0;$i<strlen($ret);$i++) {
 772             if ($ret[$i] >= "\xA1" && $ret[$i] <= "\xFE") {   /* 0xA1 - 0XFE are Valid */
 773                 $i++;
 774                 continue;
 775             } else if (($ret[$i] >= 'a' && $ret[$i] <= 'z') || /* From Original ereg_replace in download.php */
 776                        ($ret[$i] >= 'A' && $ret[$i] <= 'Z') ||
 777                        ($ret[$i] == '.') || ($ret[$i] == '-')) {
 778                 continue;
 779             } else {
 780                 $ret[$i] = '_';
 781             }
 782         }
 783
 784     }
 785
 786     return $ret;
 787 }
 788
 789 /**
 790  * Replaces non-braking spaces inserted by some browsers with regular space
 791  *
 792  * This function can be used to replace non-braking space symbols
 793  * that are inserted in forms by some browsers instead of normal
 794  * space symbol.
 795  *
 796  * @param string $string Text that needs to be cleaned
 797  * @param string $charset Charset used in text
 798  * @return string Cleaned text
 799  */
 800 function cleanup_nbsp($string,$charset) {
 801
 802   // reduce number of case statements
 803   if (stristr('iso-8859-',substr($charset,0,9))){
 804     $output_charset="iso-8859-x";
 805   }
 806   if (stristr('windows-125',substr($charset,0,11))){
 807     $output_charset="cp125x";
 808   }
 809   if (stristr('koi8',substr($charset,0,4))){
 810     $output_charset="koi8-x";
 811   }
 812   if (! isset($output_charset)){
 813     $output_charset=strtolower($charset);
 814   }
 815
 816 // where is non-braking space symbol
 817 switch($output_charset):
 818  case "iso-8859-x":
 819  case "cp125x":
 820  case "iso-2022-jp":
 821   $nbsp="\xA0";
 822   break;
 823  case "koi8-x":
 824    $nbsp="\x9A";
 825    break;
 826  case "utf-8":
 827    $nbsp="\xC2\xA0";
 828    break;
 829  default:
 830    // don't change string if charset is unmatched
 831    return $string;
 832 endswitch;
 833
 834 // return space instead of non-braking space.
 835  return str_replace($nbsp,' ',$string);
 836 }
 837
 838 /**
 839  * Function informs if it is safe to convert given charset to the one that is used by user.
 840  *
 841  * It is safe to use conversion only if user uses utf-8 encoding and when
 842  * converted charset is similar to the one that is used by user.
 843  *
 844  * @param string $input_charset Charset of text that needs to be converted
 845  * @return bool is it possible to convert to user's charset
 846  */
 847 function is_conversion_safe($input_charset) {
 848   global $languages, $sm_notAlias, $default_charset;
 849
 850  // convert to lower case
 851  $input_charset = strtolower($input_charset);
 852
 853  // Is user's locale Unicode based ?
 854  if ( $default_charset == "utf-8" ) {
 855    return true;
 856  }
 857
 858  // Charsets that are similar
 859 switch ($default_charset):
 860 case "windows-1251":
 861       if ( $input_charset == "iso-8859-5" ||
 862            $input_charset == "koi8-r" ||
 863            $input_charset == "koi8-u" ) {
 864         return true;
 865      } else {
 866         return false;
 867      }
 868 case "windows-1257":
 869   if ( $input_charset == "iso-8859-13" ||
 870          $input_charset == "iso-8859-4" ) {
 871     return true;
 872   } else {
 873     return false;
 874   }
 875 case "iso-8859-4":
 876   if ( $input_charset == "iso-8859-13" ||
 877          $input_charset == "windows-1257" ) {
 878      return true;
 879   } else {
 880      return false;
 881   }
 882 case "iso-8859-5":
 883   if ( $input_charset == "windows-1251" ||
 884          $input_charset == "koi8-r" ||
 885          $input_charset == "koi8-u" ) {
 886      return true;
 887   } else {
 888      return false;
 889   }
 890 case "iso-8859-13":
 891   if ( $input_charset == "iso-8859-4" ||
 892        $input_charset == "windows-1257" ) {
 893      return true;
 894   } else {
 895      return false;
 896   }
 897 case "koi8-r":
 898   if ( $input_charset == "windows-1251" ||
 899          $input_charset == "iso-8859-5" ||
 900          $input_charset == "koi8-u" ) {
 901      return true;
 902   } else {
 903      return false;
 904   }
 905 case "koi8-u":
 906   if ( $input_charset == "windows-1251" ||
 907         $input_charset == "iso-8859-5" ||
 908         $input_charset == "koi8-r" ) {
 909      return true;
 910   } else {
 911      return false;
 912   }
 913 default:
 914    return false;
 915 endswitch;
 916 }
 917 ?>