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') {
 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
 372 if ( file_exists( SM_PATH . 'locale/ca_ES') ) {
 373     // The glibc locale is ca_ES.
 374     $languages['ca_ES']['NAME']    = 'Catalan';
 375     $languages['ca_ES']['CHARSET'] = 'iso-8859-1';
 376     $languages['ca']['ALIAS'] = 'ca_ES';
 377 }
 378
 379 if ( file_exists( SM_PATH . 'locale/cs_CZ') ) {
 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
 386 if ( file_exists( SM_PATH . 'locale/da_DK') ) {
 387     // Danish locale is da_DK.
 388     $languages['da_DK']['NAME']    = 'Danish';
 389     $languages['da_DK']['ALTNAME'] = 'Dansk';
 390     $languages['da_DK']['CHARSET'] = 'iso-8859-1';
 391     $languages['da']['ALIAS'] = 'da_DK';
 392 }
 393
 394 if ( file_exists( SM_PATH . 'locale/de_DE') ) {
 395     $languages['de_DE']['NAME']    = 'German';
 396     $languages['de_DE']['ALTNAME']    = 'Deutsch';
 397     $languages['de_DE']['CHARSET'] = 'iso-8859-1';
 398     $languages['de']['ALIAS'] = 'de_DE';
 399 }
 400
 401 // There is no en_EN! There is en_US, en_BR, en_AU, and so forth,
 402 // but who cares about !US, right? Right? :)
 403
 404 if ( file_exists( SM_PATH . 'locale/el_GR') ) {
 405     $languages['el_GR']['NAME']    = 'Greek';
 406     $languages['el_GR']['ALTNAME'] = '&Epsilon;&lambda;&lambda;&eta;&nu;&iota;&kappa;&#940;';
 407     $languages['el_GR']['CHARSET'] = 'iso-8859-7';
 408     $languages['el']['ALIAS'] = 'el_GR';
 409 }
 410
 411 $languages['en_US']['NAME']    = 'English';
 412 $languages['en_US']['CHARSET'] = 'iso-8859-1';
 413 $languages['en']['ALIAS'] = 'en_US';
 414
 415 if ( file_exists( SM_PATH . 'locale/es_ES') ) {
 416     $languages['es_ES']['NAME']    = 'Spanish';
 417     $languages['es_ES']['ALTNAME'] = 'Espa&ntilde;ol';
 418     $languages['es_ES']['CHARSET'] = 'iso-8859-1';
 419     $languages['es']['ALIAS'] = 'es_ES';
 420 }
 421 if ( file_exists( SM_PATH . 'locale/et_EE') ) {
 422     $languages['et_EE']['NAME']    = 'Estonian';
 423     $languages['et_EE']['CHARSET'] = 'iso-8859-15';
 424     $languages['et']['ALIAS'] = 'et_EE';
 425 }
 426 if ( file_exists( SM_PATH . 'locale/fo_FO') ) {
 427     $languages['fo_FO']['NAME']    = 'Faroese';
 428     $languages['fo_FO']['CHARSET'] = 'iso-8859-1';
 429     $languages['fo']['ALIAS'] = 'fo_FO';
 430 }
 431 if ( file_exists( SM_PATH . 'locale/fi_FI') ) {
 432     $languages['fi_FI']['NAME']    = 'Finnish';
 433     $languages['fi_FI']['ALTNAME'] = 'Suomi';
 434     $languages['fi_FI']['CHARSET'] = 'iso-8859-1';
 435     $languages['fi']['ALIAS'] = 'fi_FI';
 436 }
 437 if ( file_exists( SM_PATH . 'locale/fr_FR') ) {
 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 if ( file_exists( SM_PATH . 'locale/hr_HR') ) {
 444     $languages['hr_HR']['NAME']    = 'Croatian';
 445     $languages['hr_HR']['CHARSET'] = 'iso-8859-2';
 446     $languages['hr']['ALIAS'] = 'hr_HR';
 447 }
 448 if ( file_exists( SM_PATH . 'locale/hu_HU') ) {
 449     $languages['hu_HU']['NAME']    = 'Hungarian';
 450     $languages['hu_HU']['ALTNAME'] = 'Magyar';
 451     $languages['hu_HU']['CHARSET'] = 'iso-8859-2';
 452     $languages['hu']['ALIAS'] = 'hu_HU';
 453 }
 454 if ( file_exists( SM_PATH . 'locale/id_ID') ) {
 455     $languages['id_ID']['NAME']    = 'Indonesian';
 456     $languages['id_ID']['ALTNAME'] = 'Bahasa Indonesia';
 457     $languages['id_ID']['CHARSET'] = 'iso-8859-1';
 458     $languages['id']['ALIAS'] = 'id_ID';
 459 }
 460 if ( file_exists( SM_PATH . 'locale/is_IS') ) {
 461     $languages['is_IS']['NAME']    = 'Icelandic';
 462     $languages['is_IS']['ALTNAME'] = '&Iacute;slenska';
 463     $languages['is_IS']['CHARSET'] = 'iso-8859-1';
 464     $languages['is']['ALIAS'] = 'is_IS';
 465 }
 466 if ( file_exists( SM_PATH . 'locale/it_IT') ) {
 467     $languages['it_IT']['NAME']    = 'Italian';
 468     $languages['it_IT']['CHARSET'] = 'iso-8859-1';
 469     $languages['it']['ALIAS'] = 'it_IT';
 470 }
 471 if ( file_exists( SM_PATH . 'locale/ja_JP') ) {
 472     $languages['ja_JP']['NAME']    = 'Japanese';
 473     $languages['ja_JP']['ALTNAME'] = '&#26085;&#26412;&#35486;';
 474     $languages['ja_JP']['CHARSET'] = 'iso-2022-jp';
 475     $languages['ja_JP']['XTRA_CODE'] = 'japanese_charset_xtra';
 476     $languages['ja']['ALIAS'] = 'ja_JP';
 477 }
 478 if ( file_exists( SM_PATH . 'locale/ko_KR') ) {
 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 if ( file_exists( SM_PATH . 'locale/nl_NL') ) {
 485     $languages['nl_NL']['NAME']    = 'Dutch';
 486     $languages['nl_NL']['ALTNAME'] = 'Nederlands';
 487     $languages['nl_NL']['CHARSET'] = 'iso-8859-1';
 488     $languages['nl']['ALIAS'] = 'nl_NL';
 489 }
 490 if ( file_exists( SM_PATH . 'locale/ms_MY') ) {
 491     $languages['ms_MY']['NAME']    = 'Malay';
 492     $languages['ms_MY']['ALTNAME'] = 'Bahasa Melayu';
 493     $languages['ms_MY']['CHARSET'] = 'iso-8859-1';
 494     $languages['my']['ALIAS'] = 'ms_MY';
 495 }
 496
 497 if ( file_exists( SM_PATH . 'locale/no_NO') ) {
 498     $languages['no_NO']['NAME']    = 'Norwegian (Bokm&aring;l)';
 499     $languages['no_NO']['ALTNAME'] = 'Norsk (Bokm&aring;l)';
 500     $languages['no_NO']['CHARSET'] = 'iso-8859-1';
 501     $languages['no']['ALIAS'] = 'no_NO';
 502 }
 503 if ( file_exists( SM_PATH . 'locale/nn_NO') ) {
 504     $languages['nn_NO']['NAME']    = 'Norwegian (Nynorsk)';
 505     $languages['nn_NO']['ALTNAME'] = 'Norsk (Nynorsk)';
 506     $languages['nn_NO']['CHARSET'] = 'iso-8859-1';
 507 }
 508 if ( file_exists( SM_PATH . 'locale/pl_PL') ) {
 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 if ( file_exists( SM_PATH . 'locale/pt_PT') ) {
 515     $languages['pt_PT']['NAME'] = 'Portuguese (Portugal)';
 516     $languages['pt_PT']['CHARSET'] = 'iso-8859-1';
 517     $languages['pt']['ALIAS'] = 'pt_PT';
 518 }
 519 if ( file_exists( SM_PATH . 'locale/pt_BR') ) {
 520     $languages['pt_BR']['NAME']    = 'Portuguese (Brazil)';
 521     $languages['pt_BR']['ALTNAME'] = 'Portugu&ecirc;s do Brasil';
 522     $languages['pt_BR']['CHARSET'] = 'iso-8859-1';
 523 }
 524 if ( file_exists( SM_PATH . 'locale/ru_RU') ) {
 525     $languages['ru_RU']['NAME']    = 'Russian';
 526     $languages['ru_RU']['ALTNAME'] = '&#1056;&#1091;&#1089;&#1089;&#1082;&#1080;&#1081;';
 527     $languages['ru_RU']['CHARSET'] = 'utf-8';
 528     $languages['ru_RU']['LOCALE'] = 'ru_RU.UTF-8';
 529     $languages['ru']['ALIAS'] = 'ru_RU';
 530 }
 531 if ( file_exists( SM_PATH . 'locale/sr_YU') ) {
 532     $languages['sr_YU']['NAME']    = 'Serbian';
 533     $languages['sr_YU']['ALTNAME'] = 'Srpski';
 534     $languages['sr_YU']['CHARSET'] = 'iso-8859-2';
 535     $languages['sr']['ALIAS'] = 'sr_YU';
 536 }
 537 if ( file_exists( SM_PATH . 'locale/sv_SE') ) {
 538     $languages['sv_SE']['NAME']    = 'Swedish';
 539     $languages['sv_SE']['ALTNAME'] = 'Svenska';
 540     $languages['sv_SE']['CHARSET'] = 'iso-8859-1';
 541     $languages['sv']['ALIAS'] = 'sv_SE';
 542 }
 543 if ( file_exists( SM_PATH . 'locale/tr_TR') ) {
 544     $languages['tr_TR']['NAME']    = 'Turkish';
 545     $languages['tr_TR']['CHARSET'] = 'iso-8859-9';
 546     $languages['tr']['ALIAS'] = 'tr_TR';
 547 }
 548 if ( file_exists( SM_PATH . 'locale/zh_TW') ) {
 549     $languages['zh_TW']['NAME']    = 'Chinese Trad';
 550     $languages['zh_TW']['CHARSET'] = 'big5';
 551     $languages['tw']['ALIAS'] = 'zh_TW';
 552 }
 553 if ( file_exists( SM_PATH . 'locale/zh_CN') ) {
 554     $languages['zh_CN']['NAME']    = 'Chinese Simp';
 555     $languages['zh_CN']['CHARSET'] = 'gb2312';
 556     $languages['cn']['ALIAS'] = 'zh_CN';
 557 }
 558 if ( file_exists( SM_PATH . 'locale/sk_SK') ) {
 559     $languages['sk_SK']['NAME']     = 'Slovak';
 560     $languages['sk_SK']['CHARSET']  = 'iso-8859-2';
 561     $languages['sk']['ALIAS']       = 'sk_SK';
 562 }
 563 if ( file_exists( SM_PATH . 'locale/ro_RO') ) {
 564     $languages['ro_RO']['NAME']    = 'Romanian';
 565     $languages['ro_RO']['ALTNAME'] = 'Rom&acirc;n&#259;';
 566     $languages['ro_RO']['CHARSET'] = 'iso-8859-2';
 567     $languages['ro']['ALIAS'] = 'ro_RO';
 568 }
 569 if ( file_exists( SM_PATH . 'locale/th_TH') ) {
 570     $languages['th_TH']['NAME']    = 'Thai';
 571     $languages['th_TH']['CHARSET'] = 'tis-620';
 572     $languages['th']['ALIAS'] = 'th_TH';
 573 }
 574 if ( file_exists( SM_PATH . 'locale/lt_LT') ) {
 575     $languages['lt_LT']['NAME']    = 'Lithuanian';
 576     $languages['lt_LT']['ALTNAME'] = 'Lietuvi&#371;';
 577     $languages['lt_LT']['CHARSET'] = 'utf-8';
 578     $languages['lt_LT']['LOCALE'] = 'lt_LT.UTF-8';
 579     $languages['lt']['ALIAS'] = 'lt_LT';
 580 }
 581 if ( file_exists( SM_PATH . 'locale/sl_SI') ) {
 582     $languages['sl_SI']['NAME']    = 'Slovenian';
 583     $languages['sl_SI']['ALTNAME'] = 'Sloven&scaron;&#269;ina';
 584     $languages['sl_SI']['CHARSET'] = 'iso-8859-2';
 585     $languages['sl']['ALIAS'] = 'sl_SI';
 586 }
 587 if ( file_exists( SM_PATH . 'locale/bg_BG') ) {
 588     $languages['bg_BG']['NAME']    = 'Bulgarian';
 589     $languages['bg_BG']['ALTNAME'] = '&#1041;&#1098;&#1083;&#1075;&#1072;&#1088;&#1089;&#1082;&#1080;';
 590     $languages['bg_BG']['CHARSET'] = 'windows-1251';
 591     $languages['bg']['ALIAS'] = 'bg_BG';
 592 }
 593 /*
 594 if ( file_exists( SM_PATH . 'locale/uk_UA') ) {
 595     $languages['uk_UA']['NAME']    = 'Ukrainian';
 596     $languages['uk_UA']['CHARSET'] = 'koi8-u';
 597     $languages['uk']['ALIAS'] = 'uk_UA';
 598 }
 599 */
 600 if ( file_exists( SM_PATH . 'locale/cy_GB') ) {
 601     $languages['cy_GB']['NAME']    = 'Welsh';
 602     $languages['cy_GB']['ALTNAME'] = 'Cymraeg';
 603     $languages['cy_GB']['CHARSET'] = 'iso-8859-1';
 604     $languages['cy']['ALIAS'] = 'cy_GB';
 605 }
 606 /*
 607 if ( file_exists( SM_PATH . 'locale/vi_VN') ) {
 608     $languages['vi_VN']['NAME']    = 'Vietnamese';
 609     $languages['vi_VN']['CHARSET'] = 'utf-8';
 610     $languages['vi']['ALIAS'] = 'vi_VN';
 611 }
 612 */
 613 // Right to left languages
 614 if ( file_exists( SM_PATH . 'locale/ar') ) {
 615     $languages['ar']['NAME']    = 'Arabic';
 616     $languages['ar']['CHARSET'] = 'windows-1256';
 617     $languages['ar']['DIR']     = 'rtl';
 618 }
 619 if ( file_exists( SM_PATH . 'locale/he_IL') ) {
 620     $languages['he_IL']['NAME']    = 'Hebrew';
 621     $languages['he_IL']['CHARSET'] = 'windows-1255';
 622     $languages['he_IL']['DIR']     = 'rtl';
 623     $languages['he']['ALIAS']      = 'he_IL';
 624 }
 625
 626 /* Detect whether gettext is installed. */
 627 $gettext_flags = 0;
 628 if (function_exists('_')) {
 629     $gettext_flags += 1;
 630 }
 631 if (function_exists('bindtextdomain')) {
 632     $gettext_flags += 2;
 633 }
 634 if (function_exists('textdomain')) {
 635     $gettext_flags += 4;
 636 }
 637
 638 /* If gettext is fully loaded, cool */
 639 if ($gettext_flags == 7) {
 640     $use_gettext = true;
 641 }
 642 /* If we can fake gettext, try that */
 643 elseif ($gettext_flags == 0) {
 644     $use_gettext = true;
 645     include_once(SM_PATH . 'functions/gettext.php');
 646 } else {
 647     /* Uh-ho.  A weird install */
 648     if (! $gettext_flags & 1) {
 649         function _($str) {
 650             return $str;
 651         }
 652     }
 653     if (! $gettext_flags & 2) {
 654         function bindtextdomain() {
 655             return;
 656         }
 657     }
 658     if (! $gettext_flags & 4) {
 659         function textdomain() {
 660             return;
 661         }
 662     }
 663 }
 664
 665
 666 /*
 667  * Japanese charset extra function
 668  *
 669  */
 670 function japanese_charset_xtra() {
 671     $ret = func_get_arg(1);  /* default return value */
 672     if (function_exists('mb_detect_encoding')) {
 673         switch (func_get_arg(0)) { /* action */
 674         case 'decode':
 675             $detect_encoding = @mb_detect_encoding($ret);
 676             if ($detect_encoding == 'JIS' ||
 677                 $detect_encoding == 'EUC-JP' ||
 678                 $detect_encoding == 'SJIS' ||
 679                 $detect_encoding == 'UTF-8') {
 680
 681                 $ret = mb_convert_kana(mb_convert_encoding($ret, 'EUC-JP', 'AUTO'), "KV");
 682             }
 683             break;
 684         case 'encode':
 685             $detect_encoding = @mb_detect_encoding($ret);
 686             if ($detect_encoding == 'JIS' ||
 687                 $detect_encoding == 'EUC-JP' ||
 688                 $detect_encoding == 'SJIS' ||
 689                 $detect_encoding == 'UTF-8') {
 690
 691                 $ret = mb_convert_encoding(mb_convert_kana($ret, "KV"), 'JIS', 'AUTO');
 692             }
 693             break;
 694         case 'strimwidth':
 695             $width = func_get_arg(2);
 696             $ret = mb_strimwidth($ret, 0, $width, '...');
 697             break;
 698         case 'encodeheader':
 699             $result = '';
 700             if (strlen($ret) > 0) {
 701                 $tmpstr = mb_substr($ret, 0, 1);
 702                 $prevcsize = strlen($tmpstr);
 703                 for ($i = 1; $i < mb_strlen($ret); $i++) {
 704                     $tmp = mb_substr($ret, $i, 1);
 705                     if (strlen($tmp) == $prevcsize) {
 706                         $tmpstr .= $tmp;
 707                     } else {
 708                         if ($prevcsize == 1) {
 709                             $result .= $tmpstr;
 710                         } else {
 711                             $result .= str_replace(' ', '',
 712                                                    mb_encode_mimeheader($tmpstr,'iso-2022-jp','B',''));
 713                         }
 714                         $tmpstr = $tmp;
 715                         $prevcsize = strlen($tmp);
 716                     }
 717                 }
 718                 if (strlen($tmpstr)) {
 719                     if (strlen(mb_substr($tmpstr, 0, 1)) == 1)
 720                         $result .= $tmpstr;
 721                     else
 722                         $result .= str_replace(' ', '',
 723                                                mb_encode_mimeheader($tmpstr,'iso-2022-jp','B',''));
 724                 }
 725             }
 726             $ret = $result;
 727             break;
 728         case 'decodeheader':
 729             $ret = str_replace("\t", "", $ret);
 730             if (eregi('=\\?([^?]+)\\?(q|b)\\?([^?]+)\\?=', $ret))
 731                 $ret = @mb_decode_mimeheader($ret);
 732             $ret = @mb_convert_encoding($ret, 'EUC-JP', 'AUTO');
 733             break;
 734         case 'downloadfilename':
 735             $useragent = func_get_arg(2);
 736             if (strstr($useragent, 'Windows') !== false ||
 737                 strstr($useragent, 'Mac_') !== false) {
 738                 $ret = mb_convert_encoding($ret, 'SJIS', 'AUTO');
 739             } else {
 740                 $ret = mb_convert_encoding($ret, 'EUC-JP', 'AUTO');
 741 }
 742             break;
 743         case 'wordwrap':
 744             $no_begin = "\x21\x25\x29\x2c\x2e\x3a\x3b\x3f\x5d\x7d\xa1\xf1\xa1\xeb\xa1" .
 745                 "\xc7\xa1\xc9\xa2\xf3\xa1\xec\xa1\xed\xa1\xee\xa1\xa2\xa1\xa3\xa1\xb9" .
 746                 "\xa1\xd3\xa1\xd5\xa1\xd7\xa1\xd9\xa1\xdb\xa1\xcd\xa4\xa1\xa4\xa3\xa4" .
 747                 "\xa5\xa4\xa7\xa4\xa9\xa4\xc3\xa4\xe3\xa4\xe5\xa4\xe7\xa4\xee\xa1\xab" .
 748                 "\xa1\xac\xa1\xb5\xa1\xb6\xa5\xa1\xa5\xa3\xa5\xa5\xa5\xa7\xa5\xa9\xa5" .
 749                 "\xc3\xa5\xe3\xa5\xe5\xa5\xe7\xa5\xee\xa5\xf5\xa5\xf6\xa1\xa6\xa1\xbc" .
 750                 "\xa1\xb3\xa1\xb4\xa1\xaa\xa1\xf3\xa1\xcb\xa1\xa4\xa1\xa5\xa1\xa7\xa1" .
 751                 "\xa8\xa1\xa9\xa1\xcf\xa1\xd1";
 752             $no_end = "\x5c\x24\x28\x5b\x7b\xa1\xf2\x5c\xa1\xc6\xa1\xc8\xa1\xd2\xa1" .
 753                 "\xd4\xa1\xd6\xa1\xd8\xa1\xda\xa1\xcc\xa1\xf0\xa1\xca\xa1\xce\xa1\xd0\xa1\xef";
 754             $wrap = func_get_arg(2);
 755
 756             if (strlen($ret) >= $wrap &&
 757                 substr($ret, 0, 1) != '>' &&
 758                 strpos($ret, 'http://') === FALSE &&
 759                 strpos($ret, 'https://') === FALSE &&
 760                 strpos($ret, 'ftp://') === FALSE) {
 761
 762                 $ret = mb_convert_kana($ret, "KV");
 763
 764                 $line_new = '';
 765                 $ptr = 0;
 766
 767                 while ($ptr < strlen($ret) - 1) {
 768                     $l = mb_strcut($ret, $ptr, $wrap);
 769                     $ptr += strlen($l);
 770                     $tmp = $l;
 771
 772                     $l = mb_strcut($ret, $ptr, 2);
 773                     while (strlen($l) != 0 && mb_strpos($no_begin, $l) !== FALSE ) {
 774                         $tmp .= $l;
 775                         $ptr += strlen($l);
 776                         $l = mb_strcut($ret, $ptr, 1);
 777                     }
 778                     $line_new .= $tmp;
 779                     if ($ptr < strlen($ret) - 1)
 780                         $line_new .= "\n";
 781                 }
 782                 $ret = $line_new;
 783             }
 784             break;
 785         case 'utf7-imap_encode':
 786             $ret = mb_convert_encoding($ret, 'UTF7-IMAP', 'EUC-JP');
 787             break;
 788         case 'utf7-imap_decode':
 789             $ret = mb_convert_encoding($ret, 'EUC-JP', 'UTF7-IMAP');
 790             break;
 791         }
 792     }
 793     return $ret;
 794 }
 795
 796
 797 /*
 798  * Korean charset extra function
 799  * Hangul(Korean Character) Attached File Name Fix.
 800  */
 801 function korean_charset_xtra() {
 802
 803     $ret = func_get_arg(1);  /* default return value */
 804     if (func_get_arg(0) == 'downloadfilename') { /* action */
 805         $ret = str_replace("\x0D\x0A", '', $ret);  /* Hanmail's CR/LF Clear */
 806         for ($i=0;$i<strlen($ret);$i++) {
 807             if ($ret[$i] >= "\xA1" && $ret[$i] <= "\xFE") {   /* 0xA1 - 0XFE are Valid */
 808                 $i++;
 809                 continue;
 810             } else if (($ret[$i] >= 'a' && $ret[$i] <= 'z') || /* From Original ereg_replace in download.php */
 811                        ($ret[$i] >= 'A' && $ret[$i] <= 'Z') ||
 812                        ($ret[$i] == '.') || ($ret[$i] == '-')) {
 813                 continue;
 814             } else {
 815                 $ret[$i] = '_';
 816             }
 817         }
 818
 819     }
 820
 821     return $ret;
 822 }
 823
 824 /*
 825  * This function can be used to replace non-braking space symbols
 826  * that are inserted in forms by some browsers instead of normal
 827  * space symbol.
 828  */
 829 function cleanup_nbsp($string,$charset) {
 830
 831   // reduce number of case statements
 832   if (stristr('iso-8859-',substr($charset,0,9))){
 833     $output_charset="iso-8859-x";
 834   }
 835   if (stristr('windows-125',substr($charset,0,11))){
 836     $output_charset="cp125x";
 837   }
 838   if (stristr('koi8',substr($charset,0,4))){
 839     $output_charset="koi8-x";
 840   }
 841   if (! isset($output_charset)){
 842     $output_charset=strtolower($charset);
 843   }
 844
 845 // where is non-braking space symbol
 846 switch($output_charset):
 847  case "iso-8859-x":
 848  case "cp125x":
 849  case "iso-2022-jp":
 850   $nbsp="\xA0";
 851   break;
 852  case "koi8-x":
 853    $nbsp="\x9A";
 854    break;
 855  case "utf-8":
 856    $nbsp="\xC2\xA0";
 857    break;
 858  default:
 859    // don't change string if charset is unmatched
 860    return $string;
 861 endswitch;
 862
 863 // return space instead of non-braking space.
 864  return str_replace($nbsp,' ',$string);
 865 }
 866
 867 function is_conversion_safe($input_charset) {
 868   global $languages, $sm_notAlias, $default_charset;
 869
 870  // convert to lower case
 871  $input_charset = strtolower($input_charset);
 872
 873  // Is user's locale Unicode based ?
 874  if ( $default_charset == "utf-8" ) {
 875    return true;
 876  }
 877
 878  // Charsets that are similar
 879 switch ($default_charset):
 880 case "windows-1251":
 881       if ( $input_charset == "iso-8859-5" ||
 882            $input_charset == "koi8-r" ||
 883            $input_charset == "koi8-u" ) {
 884         return true;
 885      } else {
 886         return false;
 887      }
 888 case "windows-1257":
 889   if ( $input_charset == "iso-8859-13" ||
 890          $input_charset == "iso-8859-4" ) {
 891     return true;
 892   } else {
 893     return false;
 894   }
 895 case "iso-8859-4":
 896   if ( $input_charset == "iso-8859-13" ||
 897          $input_charset == "windows-1257" ) {
 898      return true;
 899   } else {
 900      return false;
 901   }
 902 case "iso-8859-5":
 903   if ( $input_charset == "windows-1251" ||
 904          $input_charset == "koi8-r" ||
 905          $input_charset == "koi8-u" ) {
 906      return true;
 907   } else {
 908      return false;
 909   }
 910 case "iso-8859-13":
 911   if ( $input_charset == "iso-8859-4" ||
 912        $input_charset == "windows-1257" ) {
 913      return true;
 914   } else {
 915      return false;
 916   }
 917 case "koi8-r":
 918   if ( $input_charset == "windows-1251" ||
 919          $input_charset == "iso-8859-5" ||
 920          $input_charset == "koi8-u" ) {
 921      return true;
 922   } else {
 923      return false;
 924   }
 925 case "koi8-u":
 926   if ( $input_charset == "windows-1251" ||
 927         $input_charset == "iso-8859-5" ||
 928         $input_charset == "koi8-r" ) {
 929      return true;
 930   } else {
 931      return false;
 932   }
 933 default:
 934    return false;
 935 endswitch;
 936 }
 937 ?>