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  */
  17
  18 require_once(SM_PATH . 'functions/global.php');
  19
  20 /* Decodes a string to the internal encoding from the given charset */
  21 function charset_decode ($charset, $string) {
  22     global $languages, $squirrelmail_language, $default_charset;
  23     global $use_php_recode, $use_php_iconv, $agresive_decoding;
  24
  25     if (isset($languages[$squirrelmail_language]['XTRA_CODE']) &&
  26         function_exists($languages[$squirrelmail_language]['XTRA_CODE'])) {
  27         $string = $languages[$squirrelmail_language]['XTRA_CODE']('decode', $string);
  28     }
  29
  30     $charset = strtolower($charset);
  31
  32     set_my_charset();
  33
  34     // Variables that allow to use functions without function_exist() calls
  35     if (! isset($use_php_recode) || $use_php_recode=="" ) {
  36              $use_php_recode=false; }
  37     if (! isset($use_php_iconv) || $use_php_iconv=="" ) {
  38          $use_php_iconv=false; }
  39
  40     // Don't do conversion if charset is the same.
  41     if ( $charset == strtolower($default_charset) )
  42           return htmlspecialchars($string);
  43
  44     // catch iso-8859-8-i thing
  45     if ( $charset == "iso-8859-8-i" )
  46               $charset = "iso-8859-8";
  47
  48     /*
  49      * Recode converts html special characters automatically if you use
  50      * 'charset..html' decoding. There is no documented way to put -d option
  51      * into php recode function call.
  52      */
  53     if ( $use_php_recode ) {
  54       if ( $default_charset == "utf-8" ) {
  55         // other charsets can be converted to utf-8 without loss.
  56         // and output string is smaller
  57         $string = recode_string($charset . "..utf-8",$string);
  58         return htmlspecialchars($string);
  59       } else {
  60         $string = recode_string($charset . "..html",$string);
  61         // recode does not convert single quote, htmlspecialchars does.
  62         $string = str_replace("'", '&#039;', $string);
  63         return $string;
  64       }
  65     }
  66
  67     // iconv functions does not have html target and can be used only with utf-8
  68     if ( $use_php_iconv && $default_charset=='utf-8') {
  69       $string = iconv($charset,$default_charset,$string);
  70       return htmlspecialchars($string);
  71     }
  72
  73     // If we don't use recode and iconv, we'll do it old way.
  74
  75     /* All HTML special characters are 7 bit and can be replaced first */
  76
  77     $string = htmlspecialchars ($string);
  78
  79     /* controls cpu and memory intensive decoding cycles */
  80     if (! isset($agresive_decoding) || $agresive_decoding=="" ) {
  81          $agresive_decoding=false; }
  82
  83     if (ereg('iso-8859-([[:digit:]]+)', $charset, $res)) {
  84         if ($res[1] == '1') {
  85             include_once(SM_PATH . 'functions/decode/iso8859-1.php');
  86             $ret = charset_decode_iso8859_1 ($string);
  87         } else if ($res[1] == '2') {
  88             include_once(SM_PATH . 'functions/decode/iso8859-2.php');
  89             $ret = charset_decode_iso8859_2 ($string);
  90         } else if ($res[1] == '3') {
  91             include_once(SM_PATH . 'functions/decode/iso8859-3.php');
  92             $ret = charset_decode_iso8859_3 ($string);
  93         } else if ($res[1] == '4') {
  94             include_once(SM_PATH . 'functions/decode/iso8859-4.php');
  95             $ret = charset_decode_iso8859_4 ($string);
  96         } else if ($res[1] == '5') {
  97             include_once(SM_PATH . 'functions/decode/iso8859-5.php');
  98             $ret = charset_decode_iso8859_5 ($string);
  99         } else if ($res[1] == '6') {
 100             include_once(SM_PATH . 'functions/decode/iso8859-6.php');
 101             $ret = charset_decode_iso8859_6 ($string);
 102         } else if ($res[1] == '7') {
 103             include_once(SM_PATH . 'functions/decode/iso8859-7.php');
 104             $ret = charset_decode_iso8859_7 ($string);
 105         } else if ($res[1] == '8') {
 106             include_once(SM_PATH . 'functions/decode/iso8859-8.php');
 107             $ret = charset_decode_iso8859_8 ($string);
 108         } else if ($res[1] == '9') {
 109             include_once(SM_PATH . 'functions/decode/iso8859-9.php');
 110             $ret = charset_decode_iso8859_9 ($string);
 111         } else if ($res[1] == '10') {
 112             include_once(SM_PATH . 'functions/decode/iso8859-10.php');
 113             $ret = charset_decode_iso8859_10 ($string);
 114         } else if ($res[1] == '11') {
 115             include_once(SM_PATH . 'functions/decode/iso8859-11.php');
 116             $ret = charset_decode_iso8859_11 ($string);
 117         } else if ($res[1] == '13') {
 118             include_once(SM_PATH . 'functions/decode/iso8859-13.php');
 119             $ret = charset_decode_iso8859_13 ($string);
 120         } else if ($res[1] == '14') {
 121             include_once(SM_PATH . 'functions/decode/iso8859-14.php');
 122             $ret = charset_decode_iso8859_14 ($string);
 123         } else if ($res[1] == '15') {
 124             include_once(SM_PATH . 'functions/decode/iso8859-15.php');
 125             $ret = charset_decode_iso8859_15 ($string);
 126         } else if ($res[1] == '16') {
 127             include_once(SM_PATH . 'functions/decode/iso8859-16.php');
 128             $ret = charset_decode_iso8859_16 ($string);
 129         } else {
 130             $ret = charset_decode_iso_8859_default ($string);
 131         }
 132     } else if ($charset == 'ns_4551-1') {
 133         $ret = charset_decode_ns_4551_1 ($string);
 134     } else if ($charset == 'koi8-r') {
 135         include_once(SM_PATH . 'functions/decode/koi8-r.php');
 136         $ret = charset_decode_koi8r ($string);
 137     } else if ($charset == 'koi8-u') {
 138         include_once(SM_PATH . 'functions/decode/koi8-u.php');
 139         $ret = charset_decode_koi8u ($string);
 140     } else if ($charset == 'windows-1250') {
 141         include_once(SM_PATH . 'functions/decode/cp1250.php');
 142         $ret = charset_decode_cp1250 ($string);
 143     } else if ($charset == 'windows-1251') {
 144         include_once(SM_PATH . 'functions/decode/cp1251.php');
 145         $ret = charset_decode_cp1251 ($string);
 146     } else if ($charset == 'windows-1252') {
 147         include_once(SM_PATH . 'functions/decode/cp1252.php');
 148         $ret = charset_decode_cp1252 ($string);
 149     } else if ($charset == 'windows-1253') {
 150         include_once(SM_PATH . 'functions/decode/cp1253.php');
 151         $ret = charset_decode_cp1253 ($string);
 152     } else if ($charset == 'windows-1254') {
 153         include_once(SM_PATH . 'functions/decode/cp1254.php');
 154         $ret = charset_decode_cp1254 ($string);
 155     } else if ($charset == 'windows-1255') {
 156         include_once(SM_PATH . 'functions/decode/cp1255.php');
 157         $ret = charset_decode_cp1255 ($string);
 158     } else if ($charset == 'windows-1256') {
 159         include_once(SM_PATH . 'functions/decode/cp1256.php');
 160         $ret = charset_decode_cp1256 ($string);
 161     } else if ($charset == 'windows-1257') {
 162         include_once(SM_PATH . 'functions/decode/cp1257.php');
 163         $ret = charset_decode_cp1257 ($string);
 164     } else if ($charset == 'windows-1258') {
 165         include_once(SM_PATH . 'functions/decode/cp1258.php');
 166         $ret = charset_decode_cp1258 ($string);
 167     } else if ($charset == 'x-mac-roman') {
 168         include_once(SM_PATH . 'functions/decode/cp10000.php');
 169         $ret = charset_decode_cp10000 ($string);
 170     } else if ($charset == 'x-mac-greek') {
 171         include_once(SM_PATH . 'functions/decode/cp10006.php');
 172         $ret = charset_decode_cp10006 ($string);
 173     } else if ($charset == 'x-mac-cyrillic') {
 174         include_once(SM_PATH . 'functions/decode/cp10007.php');
 175         $ret = charset_decode_cp10007 ($string);
 176     } else if ($charset == 'x-mac-ukrainian') {
 177         include_once(SM_PATH . 'functions/decode/cp10017.php');
 178         $ret = charset_decode_cp10017 ($string);
 179     } else if ($charset == 'x-mac-centraleurroman') {
 180         include_once(SM_PATH . 'functions/decode/cp10029.php');
 181         $ret = charset_decode_cp10029 ($string);
 182     } else if ($charset == 'x-mac-icelandic') {
 183         include_once(SM_PATH . 'functions/decode/cp10079.php');
 184         $ret = charset_decode_cp10079 ($string);
 185     } else if ($charset == 'x-mac-turkish') {
 186         include_once(SM_PATH . 'functions/decode/cp10081.php');
 187         $ret = charset_decode_cp10081 ($string);
 188     } else if ($charset == 'ibm855') {
 189         include_once(SM_PATH . 'functions/decode/cp855.php');
 190         $ret = charset_decode_cp855 ($string);
 191     } else if ($charset == 'ibm866') {
 192         include_once(SM_PATH . 'functions/decode/cp866.php');
 193         $ret = charset_decode_cp866 ($string);
 194     } else if ($charset == 'iso-ir-111') {
 195         include_once(SM_PATH . 'functions/decode/iso-ir-111.php');
 196         $ret = charset_decode_iso_ir_111 ($string);
 197     } else if ($charset == 'tis-620') {
 198         include_once(SM_PATH . 'functions/decode/tis620.php');
 199         $ret = charset_decode_tis620 ($string);
 200     } else if ($charset == 'big5' and $agresive_decoding ) {
 201         include_once(SM_PATH . 'functions/decode/big5.php');
 202         $ret = charset_decode_big5 ($string);
 203     } else if ($charset == 'gb2312' and $agresive_decoding ) {
 204         include_once(SM_PATH . 'functions/decode/gb2312.php');
 205         $ret = charset_decode_gb2312 ($string);
 206     } else if ($charset == 'utf-8' && $squirrelmail_language != 'ja_JP') {
 207         include_once(SM_PATH . 'functions/decode/utf-8.php');
 208         $ret = charset_decode_utf8 ($string);
 209     } else {
 210         $ret = $string;
 211     }
 212     return( $ret );
 213 }
 214
 215
 216 /* Remove all 8 bit characters from all other ISO-8859 character sets */
 217 function charset_decode_iso_8859_default ($string) {
 218     return (strtr($string, "\240\241\242\243\244\245\246\247".
 219                     "\250\251\252\253\254\255\256\257".
 220                     "\260\261\262\263\264\265\266\267".
 221                     "\270\271\272\273\274\275\276\277".
 222                     "\300\301\302\303\304\305\306\307".
 223                     "\310\311\312\313\314\315\316\317".
 224                     "\320\321\322\323\324\325\326\327".
 225                     "\330\331\332\333\334\335\336\337".
 226                     "\340\341\342\343\344\345\346\347".
 227                     "\350\351\352\353\354\355\356\357".
 228                     "\360\361\362\363\364\365\366\367".
 229                     "\370\371\372\373\374\375\376\377",
 230                     "????????????????????????????????????????".
 231                     "????????????????????????????????????????".
 232                     "????????????????????????????????????????".
 233                     "????????"));
 234
 235 }
 236
 237 /*
 238  * This is the same as ISO-646-NO and is used by some
 239  * Microsoft programs when sending Norwegian characters
 240  */
 241 function charset_decode_ns_4551_1 ($string) {
 242     /*
 243      * These characters are:
 244      * Latin capital letter AE
 245      * Latin capital letter O with stroke
 246      * Latin capital letter A with ring above
 247      * and the same as small letters
 248      */
 249     return strtr ($string, "[\\]{|}", "ÆØÅæøå");
 250 }
 251
 252
 253 /*
 254  * Set up the language to be output
 255  * if $do_search is true, then scan the browser information
 256  * for a possible language that we know
 257  */
 258 function set_up_language($sm_language, $do_search = false, $default = false) {
 259
 260     static $SetupAlready = 0;
 261     global $use_gettext, $languages,
 262            $squirrelmail_language, $squirrelmail_default_language,
 263            $sm_notAlias;
 264
 265     if ($SetupAlready) {
 266         return;
 267     }
 268
 269     $SetupAlready = TRUE;
 270     sqgetGlobalVar('HTTP_ACCEPT_LANGUAGE',  $accept_lang, SQ_SERVER);
 271
 272     if ($do_search && ! $sm_language && isset($accept_lang)) {
 273         $sm_language = substr($accept_lang, 0, 2);
 274     }
 275
 276     if ((!$sm_language||$default) && isset($squirrelmail_default_language)) {
 277         $squirrelmail_language = $squirrelmail_default_language;
 278         $sm_language = $squirrelmail_default_language;
 279     }
 280     $sm_notAlias = $sm_language;
 281
 282     // Catching removed translation
 283     // System reverts to English translation if user prefs contain translation
 284     // that is not available in $languages array (admin removed directory
 285     // with that translation)
 286     if (!isset($languages[$sm_notAlias])) {
 287       $sm_notAlias="en_US";
 288     }
 289
 290     while (isset($languages[$sm_notAlias]['ALIAS'])) {
 291         $sm_notAlias = $languages[$sm_notAlias]['ALIAS'];
 292     }
 293
 294     if ( isset($sm_language) &&
 295          $use_gettext &&
 296          $sm_language != '' &&
 297          isset($languages[$sm_notAlias]['CHARSET']) ) {
 298         bindtextdomain( 'squirrelmail', SM_PATH . 'locale/' );
 299         textdomain( 'squirrelmail' );
 300         if (function_exists('bind_textdomain_codeset')) {
 301              bind_textdomain_codeset ("squirrelmail", $languages[$sm_notAlias]['CHARSET'] );
 302         }
 303         if (isset($languages[$sm_notAlias]['LOCALE'])){
 304           $longlocale=$languages[$sm_notAlias]['LOCALE'];
 305         } else {
 306           $longlocale=$sm_notAlias;
 307         }
 308         if ( !ini_get('safe_mode') &&
 309              getenv( 'LC_ALL' ) != $longlocale ) {
 310             putenv( "LC_ALL=$longlocale" );
 311             putenv( "LANG=$longlocale" );
 312             putenv( "LANGUAGE=$longlocale" );
 313         }
 314         setlocale(LC_ALL, $longlocale);
 315         $squirrelmail_language = $sm_notAlias;
 316         if ($squirrelmail_language == 'ja_JP' && function_exists('mb_detect_encoding') ) {
 317             header ('Content-Type: text/html; charset=EUC-JP');
 318             if (!function_exists('mb_internal_encoding')) {
 319                 echo _("You need to have php4 installed with the multibyte string function enabled (using configure option --enable-mbstring).");
 320             }
 321             if (function_exists('mb_language')) {
 322                 mb_language('Japanese');
 323             }
 324             mb_internal_encoding('EUC-JP');
 325             mb_http_output('pass');
 326         } else {
 327         header( 'Content-Type: text/html; charset=' . $languages[$sm_notAlias]['CHARSET'] );
 328     }
 329 }
 330 }
 331
 332 function set_my_charset(){
 333
 334     /*
 335      * There can be a $default_charset setting in the
 336      * config.php file, but the user may have a different language
 337      * selected for a user interface. This function checks the
 338      * language selected by the user and tags the outgoing messages
 339      * with the appropriate charset corresponding to the language
 340      * selection. This is "more right" (tm), than just stamping the
 341      * message blindly with the system-wide $default_charset.
 342      */
 343     global $data_dir, $username, $default_charset, $languages, $squirrelmail_default_language;
 344
 345     $my_language = getPref($data_dir, $username, 'language');
 346     if (!$my_language) {
 347         $my_language = $squirrelmail_default_language ;
 348     }
 349     // Catch removed translation
 350     if (!isset($languages[$my_language])) {
 351       $my_language="en_US";
 352     }
 353     while (isset($languages[$my_language]['ALIAS'])) {
 354         $my_language = $languages[$my_language]['ALIAS'];
 355     }
 356     $my_charset = $languages[$my_language]['CHARSET'];
 357     if ($my_charset) {
 358         $default_charset = $my_charset;
 359     }
 360 }
 361
 362 /* ------------------------------ main --------------------------- */
 363
 364 global $squirrelmail_language, $languages, $use_gettext;
 365
 366 if (! isset($squirrelmail_language)) {
 367     $squirrelmail_language = '';
 368 }
 369
 370 /* This array specifies the available languages. */
 371 $languages['bg_BG']['NAME']    = 'Bulgarian';
 372 $languages['bg_BG']['ALTNAME'] = '&#1041;&#1098;&#1083;&#1075;&#1072;&#1088;&#1089;&#1082;&#1080;';
 373 $languages['bg_BG']['CHARSET'] = 'windows-1251';
 374 $languages['bg']['ALIAS'] = 'bg_BG';
 375
 376 $languages['ca_ES']['NAME']    = 'Catalan';
 377 $languages['ca_ES']['CHARSET'] = 'iso-8859-1';
 378 $languages['ca']['ALIAS'] = 'ca_ES';
 379
 380 $languages['cs_CZ']['NAME']    = 'Czech';
 381 $languages['cs_CZ']['ALTNAME'] = '&#268;e&scaron;tina';
 382 $languages['cs_CZ']['CHARSET'] = 'iso-8859-2';
 383 $languages['cs']['ALIAS']      = 'cs_CZ';
 384
 385 $languages['cy_GB']['NAME']    = 'Welsh';
 386 $languages['cy_GB']['ALTNAME'] = 'Cymraeg';
 387 $languages['cy_GB']['CHARSET'] = 'iso-8859-1';
 388 $languages['cy']['ALIAS'] = 'cy_GB';
 389
 390 // Danish locale is da_DK.
 391 $languages['da_DK']['NAME']    = 'Danish';
 392 $languages['da_DK']['ALTNAME'] = 'Dansk';
 393 $languages['da_DK']['CHARSET'] = 'iso-8859-1';
 394 $languages['da']['ALIAS'] = 'da_DK';
 395
 396 $languages['de_DE']['NAME']    = 'German';
 397 $languages['de_DE']['ALTNAME']    = 'Deutsch';
 398 $languages['de_DE']['CHARSET'] = 'iso-8859-1';
 399 $languages['de']['ALIAS'] = 'de_DE';
 400
 401 $languages['el_GR']['NAME']    = 'Greek';
 402 $languages['el_GR']['ALTNAME'] = '&Epsilon;&lambda;&lambda;&eta;&nu;&iota;&kappa;&#940;';
 403 $languages['el_GR']['CHARSET'] = 'iso-8859-7';
 404 $languages['el']['ALIAS'] = 'el_GR';
 405
 406 // There is no en_EN! There is en_US, en_BR, en_AU, and so forth,
 407 // but who cares about !US, right? Right? :)
 408 $languages['en_US']['NAME']    = 'English';
 409 $languages['en_US']['CHARSET'] = 'iso-8859-1';
 410 $languages['en']['ALIAS'] = 'en_US';
 411
 412 $languages['es_ES']['NAME']    = 'Spanish';
 413 $languages['es_ES']['ALTNAME'] = 'Espa&ntilde;ol';
 414 $languages['es_ES']['CHARSET'] = 'iso-8859-1';
 415 $languages['es']['ALIAS'] = 'es_ES';
 416
 417 $languages['et_EE']['NAME']    = 'Estonian';
 418 $languages['et_EE']['CHARSET'] = 'iso-8859-15';
 419 $languages['et']['ALIAS'] = 'et_EE';
 420
 421 $languages['fo_FO']['NAME']    = 'Faroese';
 422 $languages['fo_FO']['CHARSET'] = 'iso-8859-1';
 423 $languages['fo']['ALIAS'] = 'fo_FO';
 424
 425 $languages['fi_FI']['NAME']    = 'Finnish';
 426 $languages['fi_FI']['ALTNAME'] = 'Suomi';
 427 $languages['fi_FI']['CHARSET'] = 'iso-8859-1';
 428 $languages['fi']['ALIAS'] = 'fi_FI';
 429
 430 $languages['fr_FR']['NAME']    = 'French';
 431 $languages['fr_FR']['ALTNAME'] = 'Fran&#231;ais';
 432 $languages['fr_FR']['CHARSET'] = 'iso-8859-1';
 433 $languages['fr']['ALIAS'] = 'fr_FR';
 434
 435 $languages['hr_HR']['NAME']    = 'Croatian';
 436 $languages['hr_HR']['CHARSET'] = 'iso-8859-2';
 437 $languages['hr']['ALIAS'] = 'hr_HR';
 438
 439 $languages['hu_HU']['NAME']    = 'Hungarian';
 440 $languages['hu_HU']['ALTNAME'] = 'Magyar';
 441 $languages['hu_HU']['CHARSET'] = 'iso-8859-2';
 442 $languages['hu']['ALIAS'] = 'hu_HU';
 443
 444 $languages['id_ID']['NAME']    = 'Indonesian';
 445 $languages['id_ID']['ALTNAME'] = 'Bahasa Indonesia';
 446 $languages['id_ID']['CHARSET'] = 'iso-8859-1';
 447 $languages['id']['ALIAS'] = 'id_ID';
 448
 449 $languages['is_IS']['NAME']    = 'Icelandic';
 450 $languages['is_IS']['ALTNAME'] = '&Iacute;slenska';
 451 $languages['is_IS']['CHARSET'] = 'iso-8859-1';
 452 $languages['is']['ALIAS'] = 'is_IS';
 453
 454 $languages['it_IT']['NAME']    = 'Italian';
 455 $languages['it_IT']['CHARSET'] = 'iso-8859-1';
 456 $languages['it']['ALIAS'] = 'it_IT';
 457
 458 $languages['ja_JP']['NAME']    = 'Japanese';
 459 $languages['ja_JP']['ALTNAME'] = '&#26085;&#26412;&#35486;';
 460 $languages['ja_JP']['CHARSET'] = 'iso-2022-jp';
 461 $languages['ja_JP']['XTRA_CODE'] = 'japanese_charset_xtra';
 462 $languages['ja']['ALIAS'] = 'ja_JP';
 463
 464 $languages['ko_KR']['NAME']    = 'Korean';
 465 $languages['ko_KR']['CHARSET'] = 'euc-KR';
 466 $languages['ko_KR']['XTRA_CODE'] = 'korean_charset_xtra';
 467 $languages['ko']['ALIAS'] = 'ko_KR';
 468
 469 $languages['lt_LT']['NAME']    = 'Lithuanian';
 470 $languages['lt_LT']['ALTNAME'] = 'Lietuvi&#371;';
 471 $languages['lt_LT']['CHARSET'] = 'utf-8';
 472 $languages['lt_LT']['LOCALE'] = 'lt_LT.UTF-8';
 473 $languages['lt']['ALIAS'] = 'lt_LT';
 474
 475 $languages['nl_NL']['NAME']    = 'Dutch';
 476 $languages['nl_NL']['ALTNAME'] = 'Nederlands';
 477 $languages['nl_NL']['CHARSET'] = 'iso-8859-1';
 478 $languages['nl']['ALIAS'] = 'nl_NL';
 479
 480 $languages['ms_MY']['NAME']    = 'Malay';
 481 $languages['ms_MY']['ALTNAME'] = 'Bahasa Melayu';
 482 $languages['ms_MY']['CHARSET'] = 'iso-8859-1';
 483 $languages['my']['ALIAS'] = 'ms_MY';
 484
 485 $languages['no_NO']['NAME']    = 'Norwegian (Bokm&aring;l)';
 486 $languages['no_NO']['ALTNAME'] = 'Norsk (Bokm&aring;l)';
 487 $languages['no_NO']['CHARSET'] = 'iso-8859-1';
 488 $languages['no']['ALIAS'] = 'no_NO';
 489
 490 $languages['nn_NO']['NAME']    = 'Norwegian (Nynorsk)';
 491 $languages['nn_NO']['ALTNAME'] = 'Norsk (Nynorsk)';
 492 $languages['nn_NO']['CHARSET'] = 'iso-8859-1';
 493
 494 $languages['pl_PL']['NAME']    = 'Polish';
 495 $languages['pl_PL']['ALTNAME'] = 'Polski';
 496 $languages['pl_PL']['CHARSET'] = 'iso-8859-2';
 497 $languages['pl']['ALIAS'] = 'pl_PL';
 498
 499 $languages['pt_PT']['NAME'] = 'Portuguese (Portugal)';
 500 $languages['pt_PT']['CHARSET'] = 'iso-8859-1';
 501 $languages['pt']['ALIAS'] = 'pt_PT';
 502
 503 $languages['pt_BR']['NAME']    = 'Portuguese (Brazil)';
 504 $languages['pt_BR']['ALTNAME'] = 'Portugu&ecirc;s do Brasil';
 505 $languages['pt_BR']['CHARSET'] = 'iso-8859-1';
 506
 507 $languages['ro_RO']['NAME']    = 'Romanian';
 508 $languages['ro_RO']['ALTNAME'] = 'Rom&acirc;n&#259;';
 509 $languages['ro_RO']['CHARSET'] = 'iso-8859-2';
 510 $languages['ro']['ALIAS'] = 'ro_RO';
 511
 512 $languages['ru_RU']['NAME']    = 'Russian';
 513 $languages['ru_RU']['ALTNAME'] = '&#1056;&#1091;&#1089;&#1089;&#1082;&#1080;&#1081;';
 514 $languages['ru_RU']['CHARSET'] = 'utf-8';
 515 $languages['ru_RU']['LOCALE'] = 'ru_RU.UTF-8';
 516 $languages['ru']['ALIAS'] = 'ru_RU';
 517
 518 $languages['sk_SK']['NAME']     = 'Slovak';
 519 $languages['sk_SK']['CHARSET']  = 'iso-8859-2';
 520 $languages['sk']['ALIAS']       = 'sk_SK';
 521
 522 $languages['sl_SI']['NAME']    = 'Slovenian';
 523 $languages['sl_SI']['ALTNAME'] = 'Sloven&scaron;&#269;ina';
 524 $languages['sl_SI']['CHARSET'] = 'iso-8859-2';
 525 $languages['sl']['ALIAS'] = 'sl_SI';
 526
 527 $languages['sr_YU']['NAME']    = 'Serbian';
 528 $languages['sr_YU']['ALTNAME'] = 'Srpski';
 529 $languages['sr_YU']['CHARSET'] = 'iso-8859-2';
 530 $languages['sr']['ALIAS'] = 'sr_YU';
 531
 532 $languages['sv_SE']['NAME']    = 'Swedish';
 533 $languages['sv_SE']['ALTNAME'] = 'Svenska';
 534 $languages['sv_SE']['CHARSET'] = 'iso-8859-1';
 535 $languages['sv']['ALIAS'] = 'sv_SE';
 536
 537 $languages['th_TH']['NAME']    = 'Thai';
 538 $languages['th_TH']['CHARSET'] = 'tis-620';
 539 $languages['th']['ALIAS'] = 'th_TH';
 540
 541 $languages['tr_TR']['NAME']    = 'Turkish';
 542 $languages['tr_TR']['CHARSET'] = 'iso-8859-9';
 543 $languages['tr']['ALIAS'] = 'tr_TR';
 544
 545 $languages['zh_TW']['NAME']    = 'Chinese Trad';
 546 $languages['zh_TW']['CHARSET'] = 'big5';
 547 $languages['tw']['ALIAS'] = 'zh_TW';
 548
 549 $languages['zh_CN']['NAME']    = 'Chinese Simp';
 550 $languages['zh_CN']['CHARSET'] = 'gb2312';
 551 $languages['cn']['ALIAS'] = 'zh_CN';
 552
 553 /*
 554 $languages['uk_UA']['NAME']    = 'Ukrainian';
 555 $languages['uk_UA']['CHARSET'] = 'koi8-u';
 556 $languages['uk']['ALIAS'] = 'uk_UA';
 557 */
 558 /*
 559 if ( file_exists( SM_PATH . 'locale/vi_VN') ) {
 560     $languages['vi_VN']['NAME']    = 'Vietnamese';
 561     $languages['vi_VN']['CHARSET'] = 'utf-8';
 562     $languages['vi']['ALIAS'] = 'vi_VN';
 563 }
 564 */
 565
 566 // Right to left languages
 567 $languages['ar']['NAME']    = 'Arabic';
 568 $languages['ar']['CHARSET'] = 'windows-1256';
 569 $languages['ar']['DIR']     = 'rtl';
 570
 571 $languages['he_IL']['NAME']    = 'Hebrew';
 572 $languages['he_IL']['CHARSET'] = 'windows-1255';
 573 $languages['he_IL']['DIR']     = 'rtl';
 574 $languages['he']['ALIAS']      = 'he_IL';
 575
 576 /* Detect whether gettext is installed. */
 577 $gettext_flags = 0;
 578 if (function_exists('_')) {
 579     $gettext_flags += 1;
 580 }
 581 if (function_exists('bindtextdomain')) {
 582     $gettext_flags += 2;
 583 }
 584 if (function_exists('textdomain')) {
 585     $gettext_flags += 4;
 586 }
 587
 588 /* If gettext is fully loaded, cool */
 589 if ($gettext_flags == 7) {
 590     $use_gettext = true;
 591 }
 592 /* If we can fake gettext, try that */
 593 elseif ($gettext_flags == 0) {
 594     $use_gettext = true;
 595     include_once(SM_PATH . 'functions/gettext.php');
 596 } else {
 597     /* Uh-ho.  A weird install */
 598     if (! $gettext_flags & 1) {
 599         function _($str) {
 600             return $str;
 601         }
 602     }
 603     if (! $gettext_flags & 2) {
 604         function bindtextdomain() {
 605             return;
 606         }
 607     }
 608     if (! $gettext_flags & 4) {
 609         function textdomain() {
 610             return;
 611         }
 612     }
 613 }
 614
 615
 616 /*
 617  * Japanese charset extra function
 618  *
 619  */
 620 function japanese_charset_xtra() {
 621     $ret = func_get_arg(1);  /* default return value */
 622     if (function_exists('mb_detect_encoding')) {
 623         switch (func_get_arg(0)) { /* action */
 624         case 'decode':
 625             $detect_encoding = @mb_detect_encoding($ret);
 626             if ($detect_encoding == 'JIS' ||
 627                 $detect_encoding == 'EUC-JP' ||
 628                 $detect_encoding == 'SJIS' ||
 629                 $detect_encoding == 'UTF-8') {
 630
 631                 $ret = mb_convert_kana(mb_convert_encoding($ret, 'EUC-JP', 'AUTO'), "KV");
 632             }
 633             break;
 634         case 'encode':
 635             $detect_encoding = @mb_detect_encoding($ret);
 636             if ($detect_encoding == 'JIS' ||
 637                 $detect_encoding == 'EUC-JP' ||
 638                 $detect_encoding == 'SJIS' ||
 639                 $detect_encoding == 'UTF-8') {
 640
 641                 $ret = mb_convert_encoding(mb_convert_kana($ret, "KV"), 'JIS', 'AUTO');
 642             }
 643             break;
 644         case 'strimwidth':
 645             $width = func_get_arg(2);
 646             $ret = mb_strimwidth($ret, 0, $width, '...');
 647             break;
 648         case 'encodeheader':
 649             $result = '';
 650             if (strlen($ret) > 0) {
 651                 $tmpstr = mb_substr($ret, 0, 1);
 652                 $prevcsize = strlen($tmpstr);
 653                 for ($i = 1; $i < mb_strlen($ret); $i++) {
 654                     $tmp = mb_substr($ret, $i, 1);
 655                     if (strlen($tmp) == $prevcsize) {
 656                         $tmpstr .= $tmp;
 657                     } else {
 658                         if ($prevcsize == 1) {
 659                             $result .= $tmpstr;
 660                         } else {
 661                             $result .= str_replace(' ', '',
 662                                                    mb_encode_mimeheader($tmpstr,'iso-2022-jp','B',''));
 663                         }
 664                         $tmpstr = $tmp;
 665                         $prevcsize = strlen($tmp);
 666                     }
 667                 }
 668                 if (strlen($tmpstr)) {
 669                     if (strlen(mb_substr($tmpstr, 0, 1)) == 1)
 670                         $result .= $tmpstr;
 671                     else
 672                         $result .= str_replace(' ', '',
 673                                                mb_encode_mimeheader($tmpstr,'iso-2022-jp','B',''));
 674                 }
 675             }
 676             $ret = $result;
 677             break;
 678         case 'decodeheader':
 679             $ret = str_replace("\t", "", $ret);
 680             if (eregi('=\\?([^?]+)\\?(q|b)\\?([^?]+)\\?=', $ret))
 681                 $ret = @mb_decode_mimeheader($ret);
 682             $ret = @mb_convert_encoding($ret, 'EUC-JP', 'AUTO');
 683             break;
 684         case 'downloadfilename':
 685             $useragent = func_get_arg(2);
 686             if (strstr($useragent, 'Windows') !== false ||
 687                 strstr($useragent, 'Mac_') !== false) {
 688                 $ret = mb_convert_encoding($ret, 'SJIS', 'AUTO');
 689             } else {
 690                 $ret = mb_convert_encoding($ret, 'EUC-JP', 'AUTO');
 691 }
 692             break;
 693         case 'wordwrap':
 694             $no_begin = "\x21\x25\x29\x2c\x2e\x3a\x3b\x3f\x5d\x7d\xa1\xf1\xa1\xeb\xa1" .
 695                 "\xc7\xa1\xc9\xa2\xf3\xa1\xec\xa1\xed\xa1\xee\xa1\xa2\xa1\xa3\xa1\xb9" .
 696                 "\xa1\xd3\xa1\xd5\xa1\xd7\xa1\xd9\xa1\xdb\xa1\xcd\xa4\xa1\xa4\xa3\xa4" .
 697                 "\xa5\xa4\xa7\xa4\xa9\xa4\xc3\xa4\xe3\xa4\xe5\xa4\xe7\xa4\xee\xa1\xab" .
 698                 "\xa1\xac\xa1\xb5\xa1\xb6\xa5\xa1\xa5\xa3\xa5\xa5\xa5\xa7\xa5\xa9\xa5" .
 699                 "\xc3\xa5\xe3\xa5\xe5\xa5\xe7\xa5\xee\xa5\xf5\xa5\xf6\xa1\xa6\xa1\xbc" .
 700                 "\xa1\xb3\xa1\xb4\xa1\xaa\xa1\xf3\xa1\xcb\xa1\xa4\xa1\xa5\xa1\xa7\xa1" .
 701                 "\xa8\xa1\xa9\xa1\xcf\xa1\xd1";
 702             $no_end = "\x5c\x24\x28\x5b\x7b\xa1\xf2\x5c\xa1\xc6\xa1\xc8\xa1\xd2\xa1" .
 703                 "\xd4\xa1\xd6\xa1\xd8\xa1\xda\xa1\xcc\xa1\xf0\xa1\xca\xa1\xce\xa1\xd0\xa1\xef";
 704             $wrap = func_get_arg(2);
 705
 706             if (strlen($ret) >= $wrap &&
 707                 substr($ret, 0, 1) != '>' &&
 708                 strpos($ret, 'http://') === FALSE &&
 709                 strpos($ret, 'https://') === FALSE &&
 710                 strpos($ret, 'ftp://') === FALSE) {
 711
 712                 $ret = mb_convert_kana($ret, "KV");
 713
 714                 $line_new = '';
 715                 $ptr = 0;
 716
 717                 while ($ptr < strlen($ret) - 1) {
 718                     $l = mb_strcut($ret, $ptr, $wrap);
 719                     $ptr += strlen($l);
 720                     $tmp = $l;
 721
 722                     $l = mb_strcut($ret, $ptr, 2);
 723                     while (strlen($l) != 0 && mb_strpos($no_begin, $l) !== FALSE ) {
 724                         $tmp .= $l;
 725                         $ptr += strlen($l);
 726                         $l = mb_strcut($ret, $ptr, 1);
 727                     }
 728                     $line_new .= $tmp;
 729                     if ($ptr < strlen($ret) - 1)
 730                         $line_new .= "\n";
 731                 }
 732                 $ret = $line_new;
 733             }
 734             break;
 735         case 'utf7-imap_encode':
 736             $ret = mb_convert_encoding($ret, 'UTF7-IMAP', 'EUC-JP');
 737             break;
 738         case 'utf7-imap_decode':
 739             $ret = mb_convert_encoding($ret, 'EUC-JP', 'UTF7-IMAP');
 740             break;
 741         }
 742     }
 743     return $ret;
 744 }
 745
 746
 747 /*
 748  * Korean charset extra function
 749  * Hangul(Korean Character) Attached File Name Fix.
 750  */
 751 function korean_charset_xtra() {
 752
 753     $ret = func_get_arg(1);  /* default return value */
 754     if (func_get_arg(0) == 'downloadfilename') { /* action */
 755         $ret = str_replace("\x0D\x0A", '', $ret);  /* Hanmail's CR/LF Clear */
 756         for ($i=0;$i<strlen($ret);$i++) {
 757             if ($ret[$i] >= "\xA1" && $ret[$i] <= "\xFE") {   /* 0xA1 - 0XFE are Valid */
 758                 $i++;
 759                 continue;
 760             } else if (($ret[$i] >= 'a' && $ret[$i] <= 'z') || /* From Original ereg_replace in download.php */
 761                        ($ret[$i] >= 'A' && $ret[$i] <= 'Z') ||
 762                        ($ret[$i] == '.') || ($ret[$i] == '-')) {
 763                 continue;
 764             } else {
 765                 $ret[$i] = '_';
 766             }
 767         }
 768
 769     }
 770
 771     return $ret;
 772 }
 773
 774 /*
 775  * This function can be used to replace non-braking space symbols
 776  * that are inserted in forms by some browsers instead of normal
 777  * space symbol.
 778  */
 779 function cleanup_nbsp($string,$charset) {
 780
 781   // reduce number of case statements
 782   if (stristr('iso-8859-',substr($charset,0,9))){
 783     $output_charset="iso-8859-x";
 784   }
 785   if (stristr('windows-125',substr($charset,0,11))){
 786     $output_charset="cp125x";
 787   }
 788   if (stristr('koi8',substr($charset,0,4))){
 789     $output_charset="koi8-x";
 790   }
 791   if (! isset($output_charset)){
 792     $output_charset=strtolower($charset);
 793   }
 794
 795 // where is non-braking space symbol
 796 switch($output_charset):
 797  case "iso-8859-x":
 798  case "cp125x":
 799  case "iso-2022-jp":
 800   $nbsp="\xA0";
 801   break;
 802  case "koi8-x":
 803    $nbsp="\x9A";
 804    break;
 805  case "utf-8":
 806    $nbsp="\xC2\xA0";
 807    break;
 808  default:
 809    // don't change string if charset is unmatched
 810    return $string;
 811 endswitch;
 812
 813 // return space instead of non-braking space.
 814  return str_replace($nbsp,' ',$string);
 815 }
 816
 817 function is_conversion_safe($input_charset) {
 818   global $languages, $sm_notAlias, $default_charset;
 819
 820  // convert to lower case
 821  $input_charset = strtolower($input_charset);
 822
 823  // Is user's locale Unicode based ?
 824  if ( $default_charset == "utf-8" ) {
 825    return true;
 826  }
 827
 828  // Charsets that are similar
 829 switch ($default_charset):
 830 case "windows-1251":
 831       if ( $input_charset == "iso-8859-5" ||
 832            $input_charset == "koi8-r" ||
 833            $input_charset == "koi8-u" ) {
 834         return true;
 835      } else {
 836         return false;
 837      }
 838 case "windows-1257":
 839   if ( $input_charset == "iso-8859-13" ||
 840          $input_charset == "iso-8859-4" ) {
 841     return true;
 842   } else {
 843     return false;
 844   }
 845 case "iso-8859-4":
 846   if ( $input_charset == "iso-8859-13" ||
 847          $input_charset == "windows-1257" ) {
 848      return true;
 849   } else {
 850      return false;
 851   }
 852 case "iso-8859-5":
 853   if ( $input_charset == "windows-1251" ||
 854          $input_charset == "koi8-r" ||
 855          $input_charset == "koi8-u" ) {
 856      return true;
 857   } else {
 858      return false;
 859   }
 860 case "iso-8859-13":
 861   if ( $input_charset == "iso-8859-4" ||
 862        $input_charset == "windows-1257" ) {
 863      return true;
 864   } else {
 865      return false;
 866   }
 867 case "koi8-r":
 868   if ( $input_charset == "windows-1251" ||
 869          $input_charset == "iso-8859-5" ||
 870          $input_charset == "koi8-u" ) {
 871      return true;
 872   } else {
 873      return false;
 874   }
 875 case "koi8-u":
 876   if ( $input_charset == "windows-1251" ||
 877         $input_charset == "iso-8859-5" ||
 878         $input_charset == "koi8-r" ) {
 879      return true;
 880   } else {
 881      return false;
 882   }
 883 default:
 884    return false;
 885 endswitch;
 886 }
 887 ?>