<?php
/**
- * i18n.php
+ * functions/i18n.php
*
- * Copyright (c) 1999-2003 The SquirrelMail Project Team
+ * Copyright (c) 1999-2004 The SquirrelMail Project Team
* Licensed under the GNU GPL. For full terms see the file COPYING.
*
* This file contains variuos functions that are needed to do
* Internally the output character set is used. Other characters are
* encoded using Unicode entities according to HTML 4.0.
*
- * $Id$
+ * @version $Id$
+ * @package squirrelmail
+ * @subpackage i18n
*/
+/** Everything uses global.php... */
require_once(SM_PATH . 'functions/global.php');
-/* Decodes a string to the internal encoding from the given charset */
+/**
+ * Converts string from given charset to charset, that can be displayed by user translation.
+ *
+ * Function by default returns html encoded strings, if translation uses different encoding.
+ * If Japanese translation is used - function returns string converted to euc-jp
+ * If iconv or recode functions are enabled and translation uses utf-8 - function returns utf-8 encoded string.
+ * If $charset is not supported - function returns unconverted string.
+ *
+ * sanitizing of html tags is also done by this function.
+ *
+ * @param string $charset
+ * @param string $string Text to be decoded
+ * @return string decoded string
+ */
function charset_decode ($charset, $string) {
- global $languages, $squirrelmail_language;
+ global $languages, $squirrelmail_language, $default_charset;
+ global $use_php_recode, $use_php_iconv, $agresive_decoding;
if (isset($languages[$squirrelmail_language]['XTRA_CODE']) &&
function_exists($languages[$squirrelmail_language]['XTRA_CODE'])) {
$string = $languages[$squirrelmail_language]['XTRA_CODE']('decode', $string);
}
- /* All HTML special characters are 7 bit and can be replaced first */
-
- $string = htmlspecialchars ($string);
-
$charset = strtolower($charset);
- set_my_charset() ;
-
- if (ereg('iso-8859-([[:digit:]]+)', $charset, $res)) {
- if ($res[1] == '1') {
- $ret = charset_decode_iso_8859_1 ($string);
- } else if ($res[1] == '2') {
- $ret = charset_decode_iso_8859_2 ($string);
- } else if ($res[1] == '4') {
- $ret = charset_decode_iso_8859_4 ($string);
- } else if ($res[1] == '5') {
- $ret = charset_decode_iso_8859_5 ($string);
- } else if ($res[1] == '7') {
- $ret = charset_decode_iso_8859_7 ($string);
- } else if ($res[1] == '9') {
- $ret = charset_decode_iso_8859_9 ($string);
- } else if ($res[1] == '13') {
- $ret = charset_decode_iso_8859_13 ($string);
- } else if ($res[1] == '15') {
- $ret = charset_decode_iso_8859_15 ($string);
- } else {
- $ret = charset_decode_iso_8859_default ($string);
- }
- } else if ($charset == 'ns_4551-1') {
- $ret = charset_decode_ns_4551_1 ($string);
- } else if ($charset == 'koi8-r') {
- $ret = charset_decode_koi8r ($string);
- } else if ($charset == 'windows-1251') {
- $ret = charset_decode_windows_1251 ($string);
- } else if ($charset == 'windows-1253') {
- $ret = charset_decode_windows_1253 ($string);
- } else if ($charset == 'windows-1254') {
- $ret = charset_decode_windows_1254 ($string);
- } else if ($charset == 'windows-1257') {
- $ret = charset_decode_windows_1257 ($string);
- } else if ($charset == 'utf-8') {
- $ret = charset_decode_utf8 ($string);
- } else {
- $ret = $string;
- }
- return( $ret );
-}
-
-/*
- iso-8859-1 is the same as Latin 1 and is normally used
- in western europe.
- */
-function charset_decode_iso_8859_1 ($string) {
- global $default_charset;
-
- if (strtolower($default_charset) <> 'iso-8859-1') {
- /* Only do the slow convert if there are 8-bit characters */
- if (ereg("[\200-\377]", $string)) {
- $string = str_replace("\201", '', $string);
- $string = str_replace("\202", '‚', $string);
- $string = str_replace("\203", 'ƒ', $string);
- $string = str_replace("\204", '„', $string);
- $string = str_replace("\205", '…', $string);
- $string = str_replace("\206", '†', $string);
- $string = str_replace("\207", '‡', $string);
- $string = str_replace("\210", 'ˆ', $string);
- $string = str_replace("\211", '‰', $string);
- $string = str_replace("\212", 'Š', $string);
- $string = str_replace("\213", '‹', $string);
- $string = str_replace("\214", 'Œ', $string);
- $string = str_replace("\215", '', $string);
- $string = str_replace("\216", 'Ž', $string);
- $string = str_replace("\217", '', $string);
- $string = str_replace("\220", '', $string);
- $string = str_replace("\221", '‘', $string);
- $string = str_replace("\222", '’', $string);
- $string = str_replace("\223", '“', $string);
- $string = str_replace("\224", '”', $string);
- $string = str_replace("\225", '•', $string);
- $string = str_replace("\226", '–', $string);
- $string = str_replace("\227", '—', $string);
- $string = str_replace("\230", '˜', $string);
- $string = str_replace("\231", '™', $string);
- $string = str_replace("\232", 'š', $string);
- $string = str_replace("\233", '›', $string);
- $string = str_replace("\234", 'œ', $string);
- $string = str_replace("\235", '', $string);
- $string = str_replace("\236", 'ž', $string);
- $string = str_replace("\237", 'Ÿ', $string);
- $string = str_replace("\240", ' ', $string);
- $string = str_replace("\241", '¡', $string);
- $string = str_replace("\242", '¢', $string);
- $string = str_replace("\243", '£', $string);
- $string = str_replace("\244", '¤', $string);
- $string = str_replace("\245", '¥', $string);
- $string = str_replace("\246", '¦', $string);
- $string = str_replace("\247", '§', $string);
- $string = str_replace("\250", '¨', $string);
- $string = str_replace("\251", '©', $string);
- $string = str_replace("\252", 'ª', $string);
- $string = str_replace("\253", '«', $string);
- $string = str_replace("\254", '¬', $string);
- $string = str_replace("\255", '­', $string);
- $string = str_replace("\256", '®', $string);
- $string = str_replace("\257", '¯', $string);
- $string = str_replace("\260", '°', $string);
- $string = str_replace("\261", '±', $string);
- $string = str_replace("\262", '²', $string);
- $string = str_replace("\263", '³', $string);
- $string = str_replace("\264", '´', $string);
- $string = str_replace("\265", 'µ', $string);
- $string = str_replace("\266", '¶', $string);
- $string = str_replace("\267", '·', $string);
- $string = str_replace("\270", '¸', $string);
- $string = str_replace("\271", '¹', $string);
- $string = str_replace("\272", 'º', $string);
- $string = str_replace("\273", '»', $string);
- $string = str_replace("\274", '¼', $string);
- $string = str_replace("\275", '½', $string);
- $string = str_replace("\276", '¾', $string);
- $string = str_replace("\277", '¿', $string);
- $string = str_replace("\300", 'À', $string);
- $string = str_replace("\301", 'Á', $string);
- $string = str_replace("\302", 'Â', $string);
- $string = str_replace("\303", 'Ã', $string);
- $string = str_replace("\304", 'Ä', $string);
- $string = str_replace("\305", 'Å', $string);
- $string = str_replace("\306", 'Æ', $string);
- $string = str_replace("\307", 'Ç', $string);
- $string = str_replace("\310", 'È', $string);
- $string = str_replace("\311", 'É', $string);
- $string = str_replace("\312", 'Ê', $string);
- $string = str_replace("\313", 'Ë', $string);
- $string = str_replace("\314", 'Ì', $string);
- $string = str_replace("\315", 'Í', $string);
- $string = str_replace("\316", 'Î', $string);
- $string = str_replace("\317", 'Ï', $string);
- $string = str_replace("\320", 'Ð', $string);
- $string = str_replace("\321", 'Ñ', $string);
- $string = str_replace("\322", 'Ò', $string);
- $string = str_replace("\323", 'Ó', $string);
- $string = str_replace("\324", 'Ô', $string);
- $string = str_replace("\325", 'Õ', $string);
- $string = str_replace("\326", 'Ö', $string);
- $string = str_replace("\327", '×', $string);
- $string = str_replace("\330", 'Ø', $string);
- $string = str_replace("\331", 'Ù', $string);
- $string = str_replace("\332", 'Ú', $string);
- $string = str_replace("\333", 'Û', $string);
- $string = str_replace("\334", 'Ü', $string);
- $string = str_replace("\335", 'Ý', $string);
- $string = str_replace("\336", 'Þ', $string);
- $string = str_replace("\337", 'ß', $string);
- $string = str_replace("\340", 'à', $string);
- $string = str_replace("\341", 'á', $string);
- $string = str_replace("\342", 'â', $string);
- $string = str_replace("\343", 'ã', $string);
- $string = str_replace("\344", 'ä', $string);
- $string = str_replace("\345", 'å', $string);
- $string = str_replace("\346", 'æ', $string);
- $string = str_replace("\347", 'ç', $string);
- $string = str_replace("\350", 'è', $string);
- $string = str_replace("\351", 'é', $string);
- $string = str_replace("\352", 'ê', $string);
- $string = str_replace("\353", 'ë', $string);
- $string = str_replace("\354", 'ì', $string);
- $string = str_replace("\355", 'í', $string);
- $string = str_replace("\356", 'î', $string);
- $string = str_replace("\357", 'ï', $string);
- $string = str_replace("\360", 'ð', $string);
- $string = str_replace("\361", 'ñ', $string);
- $string = str_replace("\362", 'ò', $string);
- $string = str_replace("\363", 'ó', $string);
- $string = str_replace("\364", 'ô', $string);
- $string = str_replace("\365", 'õ', $string);
- $string = str_replace("\366", 'ö', $string);
- $string = str_replace("\367", '÷', $string);
- $string = str_replace("\370", 'ø', $string);
- $string = str_replace("\371", 'ù', $string);
- $string = str_replace("\372", 'ú', $string);
- $string = str_replace("\373", 'û', $string);
- $string = str_replace("\374", 'ü', $string);
- $string = str_replace("\375", 'ý', $string);
- $string = str_replace("\376", 'þ', $string);
- $string = str_replace("\377", 'ÿ', $string);
- }
- }
+ set_my_charset();
- return ($string);
-}
-
-/* iso-8859-2 is used for some eastern European languages */
-function charset_decode_iso_8859_2 ($string) {
- global $default_charset;
-
- if (strtolower($default_charset) == 'iso-8859-2')
- return $string;
-
- /* Only do the slow convert if there are 8-bit characters */
- if (! ereg("[\200-\377]", $string))
- return $string;
-
- /* NO-BREAK SPACE */
- $string = str_replace("\240", ' ', $string);
- /* LATIN CAPITAL LETTER A WITH OGONEK */
- $string = str_replace("\241", 'Ą', $string);
- /* BREVE */
- $string = str_replace("\242", '˘', $string);
- // LATIN CAPITAL LETTER L WITH STROKE
- $string = str_replace("\243", 'Ł', $string);
- // CURRENCY SIGN
- $string = str_replace("\244", '¤', $string);
- // LATIN CAPITAL LETTER L WITH CARON
- $string = str_replace("\245", 'Ľ', $string);
- // LATIN CAPITAL LETTER S WITH ACUTE
- $string = str_replace("\246", 'Ś', $string);
- // SECTION SIGN
- $string = str_replace("\247", '§', $string);
- // DIAERESIS
- $string = str_replace("\250", '¨', $string);
- // LATIN CAPITAL LETTER S WITH CARON
- $string = str_replace("\251", 'Š', $string);
- // LATIN CAPITAL LETTER S WITH CEDILLA
- $string = str_replace("\252", 'Ş', $string);
- // LATIN CAPITAL LETTER T WITH CARON
- $string = str_replace("\253", 'Ť', $string);
- // LATIN CAPITAL LETTER Z WITH ACUTE
- $string = str_replace("\254", 'Ź', $string);
- // SOFT HYPHEN
- $string = str_replace("\255", '­', $string);
- // LATIN CAPITAL LETTER Z WITH CARON
- $string = str_replace("\256", 'Ž', $string);
- // LATIN CAPITAL LETTER Z WITH DOT ABOVE
- $string = str_replace("\257", 'Ż', $string);
- // DEGREE SIGN
- $string = str_replace("\260", '°', $string);
- // LATIN SMALL LETTER A WITH OGONEK
- $string = str_replace("\261", 'ą', $string);
- // OGONEK
- $string = str_replace("\262", '˛', $string);
- // LATIN SMALL LETTER L WITH STROKE
- $string = str_replace("\263", 'ł', $string);
- // ACUTE ACCENT
- $string = str_replace("\264", '´', $string);
- // LATIN SMALL LETTER L WITH CARON
- $string = str_replace("\265", 'ľ', $string);
- // LATIN SMALL LETTER S WITH ACUTE
- $string = str_replace("\266", 'ś', $string);
- // CARON
- $string = str_replace("\267", 'ˇ', $string);
- // CEDILLA
- $string = str_replace("\270", '¸', $string);
- // LATIN SMALL LETTER S WITH CARON
- $string = str_replace("\271", 'š', $string);
- // LATIN SMALL LETTER S WITH CEDILLA
- $string = str_replace("\272", 'ş', $string);
- // LATIN SMALL LETTER T WITH CARON
- $string = str_replace("\273", 'ť', $string);
- // LATIN SMALL LETTER Z WITH ACUTE
- $string = str_replace("\274", 'ź', $string);
- // DOUBLE ACUTE ACCENT
- $string = str_replace("\275", '˝', $string);
- // LATIN SMALL LETTER Z WITH CARON
- $string = str_replace("\276", 'ž', $string);
- // LATIN SMALL LETTER Z WITH DOT ABOVE
- $string = str_replace("\277", 'ż', $string);
- // LATIN CAPITAL LETTER R WITH ACUTE
- $string = str_replace("\300", 'Ŕ', $string);
- // LATIN CAPITAL LETTER A WITH ACUTE
- $string = str_replace("\301", 'Á', $string);
- // LATIN CAPITAL LETTER A WITH CIRCUMFLEX
- $string = str_replace("\302", 'Â', $string);
- // LATIN CAPITAL LETTER A WITH BREVE
- $string = str_replace("\303", 'Ă', $string);
- // LATIN CAPITAL LETTER A WITH DIAERESIS
- $string = str_replace("\304", 'Ä', $string);
- // LATIN CAPITAL LETTER L WITH ACUTE
- $string = str_replace("\305", 'Ĺ', $string);
- // LATIN CAPITAL LETTER C WITH ACUTE
- $string = str_replace("\306", 'Ć', $string);
- // LATIN CAPITAL LETTER C WITH CEDILLA
- $string = str_replace("\307", 'Ç', $string);
- // LATIN CAPITAL LETTER C WITH CARON
- $string = str_replace("\310", 'Č', $string);
- // LATIN CAPITAL LETTER E WITH ACUTE
- $string = str_replace("\311", 'É', $string);
- // LATIN CAPITAL LETTER E WITH OGONEK
- $string = str_replace("\312", 'Ę', $string);
- // LATIN CAPITAL LETTER E WITH DIAERESIS
- $string = str_replace("\313", 'Ë', $string);
- // LATIN CAPITAL LETTER E WITH CARON
- $string = str_replace("\314", 'Ě', $string);
- // LATIN CAPITAL LETTER I WITH ACUTE
- $string = str_replace("\315", 'Í', $string);
- // LATIN CAPITAL LETTER I WITH CIRCUMFLEX
- $string = str_replace("\316", 'Î', $string);
- // LATIN CAPITAL LETTER D WITH CARON
- $string = str_replace("\317", 'Ď', $string);
- // LATIN CAPITAL LETTER D WITH STROKE
- $string = str_replace("\320", 'Đ', $string);
- // LATIN CAPITAL LETTER N WITH ACUTE
- $string = str_replace("\321", 'Ń', $string);
- // LATIN CAPITAL LETTER N WITH CARON
- $string = str_replace("\322", 'Ň', $string);
- // LATIN CAPITAL LETTER O WITH ACUTE
- $string = str_replace("\323", 'Ó', $string);
- // LATIN CAPITAL LETTER O WITH CIRCUMFLEX
- $string = str_replace("\324", 'Ô', $string);
- // LATIN CAPITAL LETTER O WITH DOUBLE ACUTE
- $string = str_replace("\325", 'Ő', $string);
- // LATIN CAPITAL LETTER O WITH DIAERESIS
- $string = str_replace("\326", 'Ö', $string);
- // MULTIPLICATION SIGN
- $string = str_replace("\327", '×', $string);
- // LATIN CAPITAL LETTER R WITH CARON
- $string = str_replace("\330", 'Ř', $string);
- // LATIN CAPITAL LETTER U WITH RING ABOVE
- $string = str_replace("\331", 'Ů', $string);
- // LATIN CAPITAL LETTER U WITH ACUTE
- $string = str_replace("\332", 'Ú', $string);
- // LATIN CAPITAL LETTER U WITH DOUBLE ACUTE
- $string = str_replace("\333", 'Ű', $string);
- // LATIN CAPITAL LETTER U WITH DIAERESIS
- $string = str_replace("\334", 'Ü', $string);
- // LATIN CAPITAL LETTER Y WITH ACUTE
- $string = str_replace("\335", 'Ý', $string);
- // LATIN CAPITAL LETTER T WITH CEDILLA
- $string = str_replace("\336", 'Ţ', $string);
- // LATIN SMALL LETTER SHARP S
- $string = str_replace("\337", 'ß', $string);
- // LATIN SMALL LETTER R WITH ACUTE
- $string = str_replace("\340", 'ŕ', $string);
- // LATIN SMALL LETTER A WITH ACUTE
- $string = str_replace("\341", 'á', $string);
- // LATIN SMALL LETTER A WITH CIRCUMFLEX
- $string = str_replace("\342", 'â', $string);
- // LATIN SMALL LETTER A WITH BREVE
- $string = str_replace("\343", 'ă', $string);
- // LATIN SMALL LETTER A WITH DIAERESIS
- $string = str_replace("\344", 'ä', $string);
- // LATIN SMALL LETTER L WITH ACUTE
- $string = str_replace("\345", 'ĺ', $string);
- // LATIN SMALL LETTER C WITH ACUTE
- $string = str_replace("\346", 'ć', $string);
- // LATIN SMALL LETTER C WITH CEDILLA
- $string = str_replace("\347", 'ç', $string);
- // LATIN SMALL LETTER C WITH CARON
- $string = str_replace("\350", 'č', $string);
- // LATIN SMALL LETTER E WITH ACUTE
- $string = str_replace("\351", 'é', $string);
- // LATIN SMALL LETTER E WITH OGONEK
- $string = str_replace("\352", 'ę', $string);
- // LATIN SMALL LETTER E WITH DIAERESIS
- $string = str_replace("\353", 'ë', $string);
- // LATIN SMALL LETTER E WITH CARON
- $string = str_replace("\354", 'ě', $string);
- // LATIN SMALL LETTER I WITH ACUTE
- $string = str_replace("\355", 'í', $string);
- // LATIN SMALL LETTER I WITH CIRCUMFLEX
- $string = str_replace("\356", 'î', $string);
- // LATIN SMALL LETTER D WITH CARON
- $string = str_replace("\357", 'ď', $string);
- // LATIN SMALL LETTER D WITH STROKE
- $string = str_replace("\360", 'đ', $string);
- // LATIN SMALL LETTER N WITH ACUTE
- $string = str_replace("\361", 'ń', $string);
- // LATIN SMALL LETTER N WITH CARON
- $string = str_replace("\362", 'ň', $string);
- // LATIN SMALL LETTER O WITH ACUTE
- $string = str_replace("\363", 'ó', $string);
- // LATIN SMALL LETTER O WITH CIRCUMFLEX
- $string = str_replace("\364", 'ô', $string);
- // LATIN SMALL LETTER O WITH DOUBLE ACUTE
- $string = str_replace("\365", 'ő', $string);
- // LATIN SMALL LETTER O WITH DIAERESIS
- $string = str_replace("\366", 'ö', $string);
- // DIVISION SIGN
- $string = str_replace("\367", '÷', $string);
- // LATIN SMALL LETTER R WITH CARON
- $string = str_replace("\370", 'ř', $string);
- // LATIN SMALL LETTER U WITH RING ABOVE
- $string = str_replace("\371", 'ů', $string);
- // LATIN SMALL LETTER U WITH ACUTE
- $string = str_replace("\372", 'ú', $string);
- // LATIN SMALL LETTER U WITH DOUBLE ACUTE
- $string = str_replace("\373", 'ű', $string);
- // LATIN SMALL LETTER U WITH DIAERESIS
- $string = str_replace("\374", 'ü', $string);
- // LATIN SMALL LETTER Y WITH ACUTE
- $string = str_replace("\375", 'ý', $string);
- // LATIN SMALL LETTER T WITH CEDILLA
- $string = str_replace("\376", 'ţ', $string);
- // DOT ABOVE
- $string = str_replace("\377", '˙', $string);
-
- return $string;
-}
+ // Variables that allow to use functions without function_exist() calls
+ if (! isset($use_php_recode) || $use_php_recode=="" ) {
+ $use_php_recode=false; }
+ if (! isset($use_php_iconv) || $use_php_iconv=="" ) {
+ $use_php_iconv=false; }
-/*
- ISO/IEC 8859-4:1998 Latin Alphabet No. 4
-*/
-
-function charset_decode_iso_8859_4 ($string) {
- global $default_charset;
-
- if (strtolower($default_charset) == 'iso-8859-4')
- return $string;
-
- /* Only do the slow convert if there are 8-bit characters */
- if (! ereg("[\200-\377]", $string))
- return $string;
-
- $string = str_replace ("\241", 'Ą', $string);
- $string = str_replace ("\242", 'ĸ', $string);
- $string = str_replace ("\243", 'Ŗ', $string);
- $string = str_replace ("\245", 'Ĩ', $string);
- $string = str_replace ("\246", 'Ļ', $string);
- $string = str_replace ("\251", 'Š', $string);
- $string = str_replace ("\252", 'Ē', $string);
- $string = str_replace ("\253", 'Ģ', $string);
- $string = str_replace ("\254", 'Ŧ', $string);
- $string = str_replace ("\256", 'Ž', $string);
- $string = str_replace ("\261", 'ą', $string);
- $string = str_replace ("\262", '˛', $string);
- $string = str_replace ("\263", 'ŗ', $string);
- $string = str_replace ("\265", 'ĩ', $string);
- $string = str_replace ("\266", 'ļ', $string);
- $string = str_replace ("\267", 'ˇ', $string);
- $string = str_replace ("\271", 'š', $string);
- $string = str_replace ("\272", 'ē', $string);
- $string = str_replace ("\273", 'ģ', $string);
- $string = str_replace ("\274", 'ŧ', $string);
- $string = str_replace ("\275", 'Ŋ', $string);
- $string = str_replace ("\276", 'ž', $string);
- $string = str_replace ("\277", 'ŋ', $string);
- $string = str_replace ("\300", 'Ā', $string);
- $string = str_replace ("\307", 'Į', $string);
- $string = str_replace ("\310", 'Č', $string);
- $string = str_replace ("\312", 'Ę', $string);
- $string = str_replace ("\314", 'Ė', $string);
- $string = str_replace ("\317", 'Ī', $string);
- $string = str_replace ("\320", 'Đ', $string);
- $string = str_replace ("\321", 'Ņ', $string);
- $string = str_replace ("\322", 'Ō', $string);
- $string = str_replace ("\323", 'Ķ', $string);
- $string = str_replace ("\331", 'Ų', $string);
- $string = str_replace ("\335", 'Ũ', $string);
- $string = str_replace ("\336", 'Ū', $string);
- $string = str_replace ("\340", 'ā', $string);
- $string = str_replace ("\347", 'į', $string);
- $string = str_replace ("\350", 'č', $string);
- $string = str_replace ("\352", 'ę', $string);
- $string = str_replace ("\354", 'ė', $string);
- $string = str_replace ("\357", 'ī', $string);
- $string = str_replace ("\360", 'đ', $string);
- $string = str_replace ("\361", 'ņ', $string);
- $string = str_replace ("\362", 'ō', $string);
- $string = str_replace ("\363", 'ķ', $string);
- $string = str_replace ("\371", 'ų', $string);
- $string = str_replace ("\375", 'ũ', $string);
- $string = str_replace ("\376", 'ū', $string);
- $string = str_replace ("\377", '˙', $string);
-
- // rest of charset is the same as ISO-8859-1
- return (charset_decode_iso_8859_1($string));
-}
+ // Don't do conversion if charset is the same.
+ if ( $charset == strtolower($default_charset) )
+ return htmlspecialchars($string);
-/* iso-8859-7 is Greek. */
-function charset_decode_iso_8859_7 ($string) {
- global $default_charset;
+ // catch iso-8859-8-i thing
+ if ( $charset == "iso-8859-8-i" )
+ $charset = "iso-8859-8";
- if (strtolower($default_charset) == 'iso-8859-7') {
- return $string;
+ /*
+ * Recode converts html special characters automatically if you use
+ * 'charset..html' decoding. There is no documented way to put -d option
+ * into php recode function call.
+ */
+ if ( $use_php_recode ) {
+ if ( $default_charset == "utf-8" ) {
+ // other charsets can be converted to utf-8 without loss.
+ // and output string is smaller
+ $string = recode_string($charset . "..utf-8",$string);
+ return htmlspecialchars($string);
+ } else {
+ $string = recode_string($charset . "..html",$string);
+ // recode does not convert single quote, htmlspecialchars does.
+ $string = str_replace("'", ''', $string);
+ return $string;
+ }
}
- /* Only do the slow convert if there are 8-bit characters */
- if (!ereg("[\200-\377]", $string)) {
- return $string;
+ // iconv functions does not have html target and can be used only with utf-8
+ if ( $use_php_iconv && $default_charset=='utf-8') {
+ $string = iconv($charset,$default_charset,$string);
+ return htmlspecialchars($string);
}
- /* Some diverse characters in the beginning */
- $string = str_replace("\240", ' ', $string);
- $string = str_replace("\241", '‘', $string);
- $string = str_replace("\242", '’', $string);
- $string = str_replace("\243", '£', $string);
- $string = str_replace("\246", '¦', $string);
- $string = str_replace("\247", '§', $string);
- $string = str_replace("\250", '¨', $string);
- $string = str_replace("\251", '©', $string);
- $string = str_replace("\253", '«', $string);
- $string = str_replace("\254", '¬', $string);
- $string = str_replace("\255", '­', $string);
- $string = str_replace("\257", '―', $string);
- $string = str_replace("\260", '°', $string);
- $string = str_replace("\261", '±', $string);
- $string = str_replace("\262", '²', $string);
- $string = str_replace("\263", '³', $string);
-
- /* Horizontal bar (parentheki pavla) */
- $string = str_replace ("\257", '―', $string);
+ // If we don't use recode and iconv, we'll do it old way.
- /*
- * ISO-8859-7 characters from 11/04 (0xB4) to 11/06 (0xB6)
- * These are Unicode 900-902
- */
- $string = preg_replace("/([\264-\266])/e","'&#' . (ord('\\1')+720);",$string);
+ /* All HTML special characters are 7 bit and can be replaced first */
- /* 11/07 (0xB7) Middle dot is the same in iso-8859-1 */
- $string = str_replace("\267", '·', $string);
-
- /*
- * ISO-8859-7 characters from 11/08 (0xB8) to 11/10 (0xBA)
- * These are Unicode 900-902
- */
- $string = preg_replace("/([\270-\272])/e","'&#' . (ord('\\1')+720);",$string);
-
- /*
- * 11/11 (0xBB) Right angle quotation mark is the same as in
- * iso-8859-1
- */
- $string = str_replace("\273", '»', $string);
-
- /* And now the rest of the charset */
- $string = preg_replace("/([\274-\376])/e","'&#'.(ord('\\1')+720);",$string);
-
- return $string;
-}
-
-/*
- ISOIEC 8859-9:1999 Latin Alphabet No. 5
-
-*/
-function charset_decode_iso_8859_9 ($string) {
- global $default_charset;
-
- if (strtolower($default_charset) == 'iso-8859-9')
- return $string;
-
- /* Only do the slow convert if there are 8-bit characters */
- if (! ereg("[\200-\377]", $string))
- return $string;
-
- // latin capital letter g with breve 208->286
- $string = str_replace("\320", 'Ğ', $string);
- // latin capital letter i with dot above 221->304
- $string = str_replace("\335", 'İ', $string);
- // latin capital letter s with cedilla 222->350
- $string = str_replace("\336", 'Ş', $string);
- // latin small letter g with breve 240->287
- $string = str_replace("\360", 'ğ', $string);
- // latin small letter dotless i 253->305
- $string = str_replace("\375", 'ı', $string);
- // latin small letter s with cedilla 254->351
- $string = str_replace("\376", 'ş', $string);
-
- // rest of charset is the same as ISO-8859-1
- return (charset_decode_iso_8859_1($string));
-}
-
-
-/*
- ISO/IEC 8859-13:1998 Latin Alphabet No. 7 (Baltic Rim)
-*/
-function charset_decode_iso_8859_13 ($string) {
- global $default_charset;
-
- if (strtolower($default_charset) == 'iso-8859-13')
- return $string;
-
- /* Only do the slow convert if there are 8-bit characters */
- if (! ereg("[\200-\377]", $string))
- return $string;
-
- $string = str_replace ("\241", '”', $string);
- $string = str_replace ("\245", '„', $string);
- $string = str_replace ("\250", 'Ø', $string);
- $string = str_replace ("\252", 'Ŗ', $string);
- $string = str_replace ("\257", 'Æ', $string);
- $string = str_replace ("\264", '“', $string);
- $string = str_replace ("\270", 'ø', $string);
- $string = str_replace ("\272", 'ŗ', $string);
- $string = str_replace ("\277", 'æ', $string);
- $string = str_replace ("\300", 'Ą', $string);
- $string = str_replace ("\301", 'Į', $string);
- $string = str_replace ("\302", 'Ā', $string);
- $string = str_replace ("\303", 'Ć', $string);
- $string = str_replace ("\306", 'Ę', $string);
- $string = str_replace ("\307", 'Ē', $string);
- $string = str_replace ("\310", 'Č', $string);
- $string = str_replace ("\312", 'Ź', $string);
- $string = str_replace ("\313", 'Ė', $string);
- $string = str_replace ("\314", 'Ģ', $string);
- $string = str_replace ("\315", 'Ķ', $string);
- $string = str_replace ("\316", 'Ī', $string);
- $string = str_replace ("\317", 'Ļ', $string);
- $string = str_replace ("\320", 'Š', $string);
- $string = str_replace ("\321", 'Ń', $string);
- $string = str_replace ("\322", 'Ņ', $string);
- $string = str_replace ("\324", 'Ō', $string);
- $string = str_replace ("\330", 'Ų', $string);
- $string = str_replace ("\331", 'Ł', $string);
- $string = str_replace ("\332", 'Ś', $string);
- $string = str_replace ("\333", 'Ū', $string);
- $string = str_replace ("\335", 'Ż', $string);
- $string = str_replace ("\336", 'Ž', $string);
- $string = str_replace ("\340", 'ą', $string);
- $string = str_replace ("\341", 'į', $string);
- $string = str_replace ("\342", 'ā', $string);
- $string = str_replace ("\343", 'ć', $string);
- $string = str_replace ("\346", 'ę', $string);
- $string = str_replace ("\347", 'ē', $string);
- $string = str_replace ("\350", 'č', $string);
- $string = str_replace ("\352", 'ź', $string);
- $string = str_replace ("\353", 'ė', $string);
- $string = str_replace ("\354", 'ģ', $string);
- $string = str_replace ("\355", 'ķ', $string);
- $string = str_replace ("\356", 'ī', $string);
- $string = str_replace ("\357", 'ļ', $string);
- $string = str_replace ("\360", 'š', $string);
- $string = str_replace ("\361", 'ń', $string);
- $string = str_replace ("\362", 'ņ', $string);
- $string = str_replace ("\364", 'ō', $string);
- $string = str_replace ("\370", 'ų', $string);
- $string = str_replace ("\371", 'ł', $string);
- $string = str_replace ("\372", 'ś', $string);
- $string = str_replace ("\373", 'ū', $string);
- $string = str_replace ("\375", 'ż', $string);
- $string = str_replace ("\376", 'ž', $string);
- $string = str_replace ("\377", '’', $string);
-
- // rest of charset is the same as ISO-8859-1
- return (charset_decode_iso_8859_1($string));
-}
-
-/*
- * iso-8859-15 is Latin 9 and has very much the same use as Latin 1
- * but has the Euro symbol and some characters needed for French.
- */
-function charset_decode_iso_8859_15 ($string) {
- // Euro sign
- $string = str_replace ("\244", '€', $string);
- // Latin capital letter S with caron
- $string = str_replace ("\246", 'Š', $string);
- // Latin small letter s with caron
- $string = str_replace ("\250", 'š', $string);
- // Latin capital letter Z with caron
- $string = str_replace ("\264", 'Ž', $string);
- // Latin small letter z with caron
- $string = str_replace ("\270", 'ž', $string);
- // Latin capital ligature OE
- $string = str_replace ("\274", 'Œ', $string);
- // Latin small ligature oe
- $string = str_replace ("\275", 'œ', $string);
- // Latin capital letter Y with diaeresis
- $string = str_replace ("\276", 'Ÿ', $string);
-
- return (charset_decode_iso_8859_1($string));
-}
-
-/* ISO-8859-5 is Cyrillic */
-function charset_decode_iso_8859_5 ($string) {
- // Convert to KOI8-R, then return this decoded.
- $string = convert_cyr_string($string, 'i', 'k');
- return charset_decode_koi8r($string);
-}
-
-/* Remove all 8 bit characters from all other ISO-8859 character sets */
-function charset_decode_iso_8859_default ($string) {
- return (strtr($string, "\240\241\242\243\244\245\246\247".
- "\250\251\252\253\254\255\256\257".
- "\260\261\262\263\264\265\266\267".
- "\270\271\272\273\274\275\276\277".
- "\300\301\302\303\304\305\306\307".
- "\310\311\312\313\314\315\316\317".
- "\320\321\322\323\324\325\326\327".
- "\330\331\332\333\334\335\336\337".
- "\340\341\342\343\344\345\346\347".
- "\350\351\352\353\354\355\356\357".
- "\360\361\362\363\364\365\366\367".
- "\370\371\372\373\374\375\376\377",
- "????????????????????????????????????????".
- "????????????????????????????????????????".
- "????????????????????????????????????????".
- "????????"));
-
-}
-
-/*
- * This is the same as ISO-646-NO and is used by some
- * Microsoft programs when sending Norwegian characters
- */
-function charset_decode_ns_4551_1 ($string) {
- /*
- * These characters are:
- * Latin capital letter AE
- * Latin capital letter O with stroke
- * Latin capital letter A with ring above
- * and the same as small letters
- */
- return strtr ($string, "[\\]{|}", "ÆØÅæøå");
-}
+ $string = htmlspecialchars ($string);
-/*
- * KOI8-R is used to encode Russian mail (Cyrrilic). Defined in RFC
- * 1489.
- */
-function charset_decode_koi8r ($string) {
- global $default_charset;
+ /* controls cpu and memory intensive decoding cycles */
+ if (! isset($agresive_decoding) || $agresive_decoding=="" ) {
+ $agresive_decoding=false; }
- if ($default_charset == 'koi8-r') {
- return $string;
+ $decode=fixcharset($charset);
+ $decodefile=SM_PATH . 'functions/decode/' . $decode . '.php';
+ if (file_exists($decodefile)) {
+ include_once($decodefile);
+ $ret = call_user_func('charset_decode_'.$decode, $string);
+ } else {
+ $ret = $string;
}
-
- /*
- * Convert to Unicode HTML entities.
- * This code is rather ineffective.
- */
- $string = str_replace("\200", '─', $string);
- $string = str_replace("\201", '│', $string);
- $string = str_replace("\202", '┌', $string);
- $string = str_replace("\203", '┐', $string);
- $string = str_replace("\204", '└', $string);
- $string = str_replace("\205", '┘', $string);
- $string = str_replace("\206", '├', $string);
- $string = str_replace("\207", '┤', $string);
- $string = str_replace("\210", '┬', $string);
- $string = str_replace("\211", '┴', $string);
- $string = str_replace("\212", '┼', $string);
- $string = str_replace("\213", '▀', $string);
- $string = str_replace("\214", '▄', $string);
- $string = str_replace("\215", '█', $string);
- $string = str_replace("\216", '▌', $string);
- $string = str_replace("\217", '▐', $string);
- $string = str_replace("\220", '░', $string);
- $string = str_replace("\221", '▒', $string);
- $string = str_replace("\222", '▓', $string);
- $string = str_replace("\223", '⌠', $string);
- $string = str_replace("\224", '■', $string);
- $string = str_replace("\225", '∙', $string);
- $string = str_replace("\226", '√', $string);
- $string = str_replace("\227", '≈', $string);
- $string = str_replace("\230", '≤', $string);
- $string = str_replace("\231", '≥', $string);
- $string = str_replace("\232", ' ', $string);
- $string = str_replace("\233", '⌡', $string);
- $string = str_replace("\234", '°', $string);
- $string = str_replace("\235", '²', $string);
- $string = str_replace("\236", '·', $string);
- $string = str_replace("\237", '÷', $string);
- $string = str_replace("\240", '═', $string);
- $string = str_replace("\241", '║', $string);
- $string = str_replace("\242", '╒', $string);
- $string = str_replace("\243", 'ё', $string);
- $string = str_replace("\244", '╓', $string);
- $string = str_replace("\245", '╔', $string);
- $string = str_replace("\246", '╕', $string);
- $string = str_replace("\247", '╖', $string);
- $string = str_replace("\250", '╗', $string);
- $string = str_replace("\251", '╘', $string);
- $string = str_replace("\252", '╙', $string);
- $string = str_replace("\253", '╚', $string);
- $string = str_replace("\254", '╛', $string);
- $string = str_replace("\255", '╜', $string);
- $string = str_replace("\256", '╝', $string);
- $string = str_replace("\257", '╞', $string);
- $string = str_replace("\260", '╟', $string);
- $string = str_replace("\261", '╠', $string);
- $string = str_replace("\262", '╡', $string);
- $string = str_replace("\263", 'Ё', $string);
- $string = str_replace("\264", '╢', $string);
- $string = str_replace("\265", '╣', $string);
- $string = str_replace("\266", '╤', $string);
- $string = str_replace("\267", '╥', $string);
- $string = str_replace("\270", '╦', $string);
- $string = str_replace("\271", '╧', $string);
- $string = str_replace("\272", '╨', $string);
- $string = str_replace("\273", '╩', $string);
- $string = str_replace("\274", '╪', $string);
- $string = str_replace("\275", '╫', $string);
- $string = str_replace("\276", '╬', $string);
- $string = str_replace("\277", '©', $string);
- $string = str_replace("\300", 'ю', $string);
- $string = str_replace("\301", 'а', $string);
- $string = str_replace("\302", 'б', $string);
- $string = str_replace("\303", 'ц', $string);
- $string = str_replace("\304", 'д', $string);
- $string = str_replace("\305", 'е', $string);
- $string = str_replace("\306", 'ф', $string);
- $string = str_replace("\307", 'г', $string);
- $string = str_replace("\310", 'х', $string);
- $string = str_replace("\311", 'и', $string);
- $string = str_replace("\312", 'й', $string);
- $string = str_replace("\313", 'к', $string);
- $string = str_replace("\314", 'л', $string);
- $string = str_replace("\315", 'м', $string);
- $string = str_replace("\316", 'н', $string);
- $string = str_replace("\317", 'о', $string);
- $string = str_replace("\320", 'п', $string);
- $string = str_replace("\321", 'я', $string);
- $string = str_replace("\322", 'р', $string);
- $string = str_replace("\323", 'с', $string);
- $string = str_replace("\324", 'т', $string);
- $string = str_replace("\325", 'у', $string);
- $string = str_replace("\326", 'ж', $string);
- $string = str_replace("\327", 'в', $string);
- $string = str_replace("\330", 'ь', $string);
- $string = str_replace("\331", 'ы', $string);
- $string = str_replace("\332", 'з', $string);
- $string = str_replace("\333", 'ш', $string);
- $string = str_replace("\334", 'э', $string);
- $string = str_replace("\335", 'щ', $string);
- $string = str_replace("\336", 'ч', $string);
- $string = str_replace("\337", 'ъ', $string);
- $string = str_replace("\340", 'Ю', $string);
- $string = str_replace("\341", 'А', $string);
- $string = str_replace("\342", 'Б', $string);
- $string = str_replace("\343", 'Ц', $string);
- $string = str_replace("\344", 'Д', $string);
- $string = str_replace("\345", 'Е', $string);
- $string = str_replace("\346", 'Ф', $string);
- $string = str_replace("\347", 'Г', $string);
- $string = str_replace("\350", 'Х', $string);
- $string = str_replace("\351", 'И', $string);
- $string = str_replace("\352", 'Й', $string);
- $string = str_replace("\353", 'К', $string);
- $string = str_replace("\354", 'Л', $string);
- $string = str_replace("\355", 'М', $string);
- $string = str_replace("\356", 'Н', $string);
- $string = str_replace("\357", 'О', $string);
- $string = str_replace("\360", 'П', $string);
- $string = str_replace("\361", 'Я', $string);
- $string = str_replace("\362", 'Р', $string);
- $string = str_replace("\363", 'С', $string);
- $string = str_replace("\364", 'Т', $string);
- $string = str_replace("\365", 'У', $string);
- $string = str_replace("\366", 'Ж', $string);
- $string = str_replace("\367", 'В', $string);
- $string = str_replace("\370", 'Ь', $string);
- $string = str_replace("\371", 'Ы', $string);
- $string = str_replace("\372", 'З', $string);
- $string = str_replace("\373", 'Ш', $string);
- $string = str_replace("\374", 'Э', $string);
- $string = str_replace("\375", 'Щ', $string);
- $string = str_replace("\376", 'Ч', $string);
- $string = str_replace("\377", 'Ъ', $string);
-
- return $string;
-}
-
-/*
- windows-1254 (Turks)
- */
-function charset_decode_windows_1254 ($string) {
- global $default_charset;
-
- if (strtolower($default_charset) == 'windows-1254')
- return $string;
-
- /* Only do the slow convert if there are 8-bit characters */
- if (! ereg("[\200-\377]", $string))
- return $string;
-
- // Euro sign 128 -> 8364
- $string = str_replace("\200", '€', $string);
- // Single low-9 quotation mark 130 -> 8218
- $string = str_replace("\202", '‚', $string);
- // latin small letter f with hook 131 -> 402
- $string = str_replace("\203", 'ƒ', $string);
- // Double low-9 quotation mark 132 -> 8222
- $string = str_replace("\204", '„', $string);
- // horizontal ellipsis 133 -> 8230
- $string = str_replace("\205", '…', $string);
- // dagger 134 -> 8224
- $string = str_replace("\206", '†', $string);
- // double dagger 135 -> 8225
- $string = str_replace("\207", '‡', $string);
- // modifier letter circumflex accent 136->710
- $string = str_replace("\210", 'ˆ', $string);
- // per mille sign 137 -> 8240
- $string = str_replace("\211", '‰', $string);
- // latin capital letter s with caron 138 -> 352
- $string = str_replace("\212", 'Š', $string);
- // single left-pointing angle quotation mark 139 -> 8249
- $string = str_replace("\213", '‹', $string);
- // latin capital ligature oe 140 -> 338
- $string = str_replace("\214", 'Œ', $string);
- // left single quotation mark 145 -> 8216
- $string = str_replace("\221", '‘', $string);
- // right single quotation mark 146 -> 8217
- $string = str_replace("\222", '’', $string);
- // left double quotation mark 147 -> 8220
- $string = str_replace("\223", '“', $string);
- // right double quotation mark 148 -> 8221
- $string = str_replace("\224", '”', $string);
- // bullet 149 -> 8226
- $string = str_replace("\225", '•', $string);
- // en dash 150 -> 8211
- $string = str_replace("\226", '–', $string);
- // em dash 151 -> 8212
- $string = str_replace("\227", '—', $string);
- // small tilde 152 -> 732
- $string = str_replace("\230", '˜', $string);
- // trade mark sign 153 -> 8482
- $string = str_replace("\231", '™', $string);
- // latin small letter s with caron 154 -> 353
- $string = str_replace("\232", 'š', $string);
- // single right-pointing angle quotation mark 155 -> 8250
- $string = str_replace("\233", '›', $string);
- // latin small ligature oe 156 -> 339
- $string = str_replace("\234", 'œ', $string);
- // latin capital letter y with diaresis 159->376
- $string = str_replace("\237", 'Ÿ', $string);
- // latin capital letter g with breve 208->286
- $string = str_replace("\320", 'Ğ', $string);
- // latin capital letter i with dot above 221->304
- $string = str_replace("\335", 'İ', $string);
- // latin capital letter s with cedilla 222->350
- $string = str_replace("\336", 'Ş', $string);
- // latin small letter g with breve 240->287
- $string = str_replace("\360", 'ğ', $string);
- // latin small letter dotless i 253->305
- $string = str_replace("\375", 'ı', $string);
- // latin small letter s with cedilla 254->351
- $string = str_replace("\376", 'ş', $string);
-
- // Rest of charset is like iso-8859-1
- return (charset_decode_iso_8859_1($string));
+ return( $ret );
}
-
-/*
- windows-1253 (Greek)
+
+/**
+ * Makes charset name suitable for decoding cycles
+ *
+ * @param string $charset Name of charset
+ * @return string $charset Adjusted name of charset
*/
-function charset_decode_windows_1253 ($string) {
- global $default_charset;
-
- if (strtolower($default_charset) == 'windows-1253')
- return $string;
-
- /* Only do the slow convert if there are 8-bit characters */
- if (! ereg("[\200-\377]", $string))
- return $string;
-
- $string = str_replace("\200", '€', $string);
- $string = str_replace("\202", '‚', $string);
- $string = str_replace("\203", 'ƒ', $string);
- $string = str_replace("\204", '„', $string);
- $string = str_replace("\205", '…', $string);
- $string = str_replace("\206", '†', $string);
- $string = str_replace("\207", '‡', $string);
- $string = str_replace("\211", '‰', $string);
- $string = str_replace("\213", '‹', $string);
- $string = str_replace("\221", '‘', $string);
- $string = str_replace("\222", '’', $string);
- $string = str_replace("\223", '“', $string);
- $string = str_replace("\224", '”', $string);
- $string = str_replace("\225", '•', $string);
- $string = str_replace("\226", '–', $string);
- $string = str_replace("\227", '—', $string);
- $string = str_replace("\231", '™', $string);
- $string = str_replace("\233", '›', $string);
- $string = str_replace("\241", '΅', $string);
- $string = str_replace("\242", 'Ά', $string);
- $string = str_replace ("\257", '―', $string);
- $string = str_replace("\264", '΄', $string);
- $string = str_replace("\270", 'Έ', $string);
- $string = str_replace ("\271", 'Ή', $string);
- $string = str_replace ("\272", 'Ί', $string);
- $string = str_replace ("\274", 'Ό', $string);
- // cycle for 190-254 symbols
- $string = preg_replace("/([\274-\376])/e","'&#' . (ord('\\1')+720);",$string);
-
- // Rest of charset is like iso-8859-1
- return (charset_decode_iso_8859_1($string));
-}
+function fixcharset($charset) {
+ // minus removed from function names
+ $charset=str_replace('-','_',$charset);
+
+ // windows-125x and cp125x charsets
+ $charset=str_replace('windows_','cp',$charset);
+ // ibm > cp
+ $charset=str_replace('ibm','cp',$charset);
-/*
- windows-1257 (BaltRim)
- */
-function charset_decode_windows_1257 ($string) {
- global $default_charset;
-
- if (strtolower($default_charset) == 'windows-1257')
- return $string;
-
- /* Only do the slow convert if there are 8-bit characters */
- if (! ereg("[\200-\377]", $string))
- return $string;
-
- $string = str_replace("\200", '€', $string);
- $string = str_replace("\202", '‚', $string);
- $string = str_replace("\204", '„', $string);
- $string = str_replace("\205", '…', $string);
- $string = str_replace("\206", '†', $string);
- $string = str_replace("\207", '‡', $string);
- $string = str_replace("\211", '‰', $string);
- $string = str_replace("\213", '‹', $string);
- $string = str_replace("\215", '¨', $string);
- $string = str_replace("\216", 'ˇ', $string);
- $string = str_replace("\217", '¸', $string);
- $string = str_replace("\221", '‘', $string);
- $string = str_replace("\222", '’', $string);
- $string = str_replace("\223", '“', $string);
- $string = str_replace("\224", '”', $string);
- $string = str_replace("\225", '•', $string);
- $string = str_replace("\226", '–', $string);
- $string = str_replace("\227", '—', $string);
- $string = str_replace("\231", '™', $string);
- $string = str_replace("\233", '›', $string);
- $string = str_replace("\235", '¯', $string);
- $string = str_replace("\236", '˛', $string);
- $string = str_replace ("\250", 'Ø', $string);
- $string = str_replace ("\252", 'Ŗ', $string);
- $string = str_replace ("\257", 'Æ', $string);
- $string = str_replace ("\270", 'ø', $string);
- $string = str_replace ("\272", 'ŗ', $string);
- $string = str_replace ("\277", 'æ', $string);
- $string = str_replace ("\300", 'Ą', $string);
- $string = str_replace ("\301", 'Į', $string);
- $string = str_replace ("\302", 'Ā', $string);
- $string = str_replace ("\303", 'Ć', $string);
- $string = str_replace ("\306", 'Ę', $string);
- $string = str_replace ("\307", 'Ē', $string);
- $string = str_replace ("\310", 'Č', $string);
- $string = str_replace ("\312", 'Ź', $string);
- $string = str_replace ("\313", 'Ė', $string);
- $string = str_replace ("\314", 'Ģ', $string);
- $string = str_replace ("\315", 'Ķ', $string);
- $string = str_replace ("\316", 'Ī', $string);
- $string = str_replace ("\317", 'Ļ', $string);
- $string = str_replace ("\320", 'Š', $string);
- $string = str_replace ("\321", 'Ń', $string);
- $string = str_replace ("\322", 'Ņ', $string);
- $string = str_replace ("\324", 'Ō', $string);
- $string = str_replace ("\330", 'Ų', $string);
- $string = str_replace ("\331", 'Ł', $string);
- $string = str_replace ("\332", 'Ŕ', $string);
- $string = str_replace ("\333", 'Ū', $string);
- $string = str_replace ("\335", 'Ż', $string);
- $string = str_replace ("\336", 'Ž', $string);
- $string = str_replace ("\340", 'ą', $string);
- $string = str_replace ("\341", 'į', $string);
- $string = str_replace ("\342", 'ā', $string);
- $string = str_replace ("\343", 'ć', $string);
- $string = str_replace ("\346", 'ę', $string);
- $string = str_replace ("\347", 'ē', $string);
- $string = str_replace ("\350", 'č', $string);
- $string = str_replace ("\352", 'ź', $string);
- $string = str_replace ("\353", 'ė', $string);
- $string = str_replace ("\354", 'ģ', $string);
- $string = str_replace ("\355", 'ķ', $string);
- $string = str_replace ("\356", 'ī', $string);
- $string = str_replace ("\357", 'ļ', $string);
- $string = str_replace ("\360", 'š', $string);
- $string = str_replace ("\361", 'ń', $string);
- $string = str_replace ("\362", 'ņ', $string);
- $string = str_replace ("\364", 'ō', $string);
- $string = str_replace ("\370", 'ų', $string);
- $string = str_replace ("\371", 'ł', $string);
- $string = str_replace ("\372", 'ś', $string);
- $string = str_replace ("\373", 'ū', $string);
- $string = str_replace ("\375", 'ż', $string);
- $string = str_replace ("\376", 'ž', $string);
- $string = str_replace ("\377", '˙', $string);
-
- // Rest of charset is like iso-8859-1
- return (charset_decode_iso_8859_1($string));
-}
+ // iso-8859-8-i -> iso-8859-8
+ // use same cycle until I'll find differences
+ $charset=str_replace('iso_8859_8_i','iso_8859_8',$charset);
-/* windows-1251 is Microsoft Cyrillic encoding */
-function charset_decode_windows_1251 ($string) {
- // Convert to KOI8-R, then return this decoded.
- $string = convert_cyr_string($string, 'w', 'k');
- return charset_decode_koi8r($string);
+ return $charset;
}
-
-
-/*
+/**
* Set up the language to be output
* if $do_search is true, then scan the browser information
* for a possible language that we know
+ *
+ * Function sets system locale environment (LC_ALL, LANG, LANGUAGE),
+ * gettext translation bindings and html header information.
+ *
+ * Function returns error codes, if there is some fatal error.
+ * 0 = no error,
+ * 1 = mbstring support is not present,
+ * 2 = mbstring support is not present, user's translation reverted to en_US.
+ *
+ * @param string $sm_language translation used by user's interface
+ * @param bool $do_search use browser's preferred language detection functions. Defaults to false.
+ * @param bool $default set $sm_language to $squirrelmail_default_language if language detection fails or language is not set. Defaults to false.
+ * @return int function execution error codes.
*/
-function set_up_language($sm_language, $do_search = false) {
+function set_up_language($sm_language, $do_search = false, $default = false) {
static $SetupAlready = 0;
global $use_gettext, $languages,
$squirrelmail_language, $squirrelmail_default_language,
- $sm_notAlias;
+ $sm_notAlias, $username, $data_dir;
if ($SetupAlready) {
return;
$sm_language = substr($accept_lang, 0, 2);
}
- if (!$sm_language && isset($squirrelmail_default_language)) {
+ if ((!$sm_language||$default) && isset($squirrelmail_default_language)) {
$squirrelmail_language = $squirrelmail_default_language;
$sm_language = $squirrelmail_default_language;
}
$sm_notAlias = $sm_language;
+
+ // Catching removed translation
+ // System reverts to English translation if user prefs contain translation
+ // that is not available in $languages array
+ if (!isset($languages[$sm_notAlias])) {
+ $sm_notAlias="en_US";
+ }
+
while (isset($languages[$sm_notAlias]['ALIAS'])) {
$sm_notAlias = $languages[$sm_notAlias]['ALIAS'];
}
bindtextdomain( 'squirrelmail', SM_PATH . 'locale/' );
textdomain( 'squirrelmail' );
if (function_exists('bind_textdomain_codeset')) {
- bind_textdomain_codeset ("squirrelmail", $languages[$sm_notAlias]['CHARSET'] );
+ if ($sm_notAlias == 'ja_JP') {
+ bind_textdomain_codeset ("squirrelmail", 'EUC-JP');
+ } else {
+ bind_textdomain_codeset ("squirrelmail", $languages[$sm_notAlias]['CHARSET'] );
+ }
+ }
+ if (isset($languages[$sm_notAlias]['LOCALE'])){
+ $longlocale=$languages[$sm_notAlias]['LOCALE'];
+ } else {
+ $longlocale=$sm_notAlias;
}
if ( !ini_get('safe_mode') &&
- getenv( 'LC_ALL' ) != $sm_notAlias ) {
- putenv( "LC_ALL=$sm_notAlias" );
- putenv( "LANG=$sm_notAlias" );
- putenv( "LANGUAGE=$sm_notAlias" );
+ getenv( 'LC_ALL' ) != $longlocale ) {
+ putenv( "LC_ALL=$longlocale" );
+ putenv( "LANG=$longlocale" );
+ putenv( "LANGUAGE=$longlocale" );
}
- setlocale(LC_ALL, $sm_notAlias);
- $squirrelmail_language = $sm_notAlias;
- if ($squirrelmail_language == 'ja_JP' && function_exists('mb_detect_encoding') ) {
+ setlocale(LC_ALL, $longlocale);
+
+ // Set text direction/alignment variables
+ if (isset($languages[$sm_notAlias]['DIR']) &&
+ $languages[$sm_notAlias]['DIR'] == 'rtl') {
+ /**
+ * Text direction
+ * @global string $text_direction
+ */
+ $text_direction='rtl';
+ /**
+ * Left alignment
+ * @global string $left_align
+ */
+ $left_align='right';
+ /**
+ * Right alignment
+ * @global string $right_align
+ */
+ $right_align='left';
+ } else {
+ $text_direction='ltr';
+ $left_align='left';
+ $right_align='right';
+ }
+
+ $squirrelmail_language = $sm_notAlias;
+ if ($squirrelmail_language == 'ja_JP') {
header ('Content-Type: text/html; charset=EUC-JP');
if (!function_exists('mb_internal_encoding')) {
- echo _("You need to have php4 installed with the multibyte string function enabled (using configure option --enable-mbstring).");
+ // Error messages can't be displayed here
+ $error = 1;
+ // Revert to English if possible.
+ if (function_exists('setPref') && $username!='' && $data_dir!="") {
+ setPref($data_dir, $username, 'language', "en_US");
+ $error = 2;
+ }
+ // stop further execution in order not to get php errors on mb_internal_encoding().
+ return $error;
}
if (function_exists('mb_language')) {
mb_language('Japanese');
header( 'Content-Type: text/html; charset=' . $languages[$sm_notAlias]['CHARSET'] );
}
}
+ return 0;
}
+/**
+ * Sets default_charset variable according to the one that is used by user's translations.
+ *
+ * Function changes global $default_charset variable in order to be sure, that it
+ * contains charset used by user's translation. Sanity of $squirrelmail_default_language
+ * and $default_charset combination provided in SquirrelMail config is also tested.
+ *
+ * There can be a $default_charset setting in the
+ * config.php file, but the user may have a different language
+ * selected for a user interface. This function checks the
+ * language selected by the user and tags the outgoing messages
+ * with the appropriate charset corresponding to the language
+ * selection. This is "more right" (tm), than just stamping the
+ * message blindly with the system-wide $default_charset.
+ */
function set_my_charset(){
-
- /*
- * There can be a $default_charset setting in the
- * config.php file, but the user may have a different language
- * selected for a user interface. This function checks the
- * language selected by the user and tags the outgoing messages
- * with the appropriate charset corresponding to the language
- * selection. This is "more right" (tm), than just stamping the
- * message blindly with the system-wide $default_charset.
- */
global $data_dir, $username, $default_charset, $languages, $squirrelmail_default_language;
$my_language = getPref($data_dir, $username, 'language');
if (!$my_language) {
$my_language = $squirrelmail_default_language ;
}
+ // Catch removed translation
+ if (!isset($languages[$my_language])) {
+ $my_language="en_US";
+ }
while (isset($languages[$my_language]['ALIAS'])) {
$my_language = $languages[$my_language]['ALIAS'];
}
$squirrelmail_language = '';
}
-/* This array specifies the available languages. */
-
-// The glibc locale is ca_ES.
+/**
+ * Array specifies the available translations.
+ *
+ * Structure of array:
+ * $languages['language']['variable'] = 'value'
+ *
+ * Possible 'variable' names:
+ * NAME - Translation name in English
+ * CHARSET - Encoding used by translation
+ * ALIAS - used when 'language' is only short name and 'value' should provide long language name
+ * ALTNAME - Native translation name. Any 8bit symbols must be html encoded.
+ * LOCALE - Full locale name (in xx_XX.charset format)
+ * DIR - Text direction. Used to define Right-to-Left languages. Possible values 'rtl' or 'ltr'. If undefined - defaults to 'ltr'
+ * XTRA_CODE - translation uses special functions. 'value' provides name of that extra function
+ *
+ * Each 'language' definition requires NAME+CHARSET or ALIAS variables.
+ *
+ * @name $languages
+ * @global array $languages
+ */
+$languages['bg_BG']['NAME'] = 'Bulgarian';
+$languages['bg_BG']['ALTNAME'] = 'Български';
+$languages['bg_BG']['CHARSET'] = 'windows-1251';
+$languages['bg_BG']['LOCALE'] = 'bg_BG.CP1251';
+$languages['bg']['ALIAS'] = 'bg_BG';
$languages['ca_ES']['NAME'] = 'Catalan';
$languages['ca_ES']['CHARSET'] = 'iso-8859-1';
+$languages['ca_ES']['LOCALE'] = 'ca_ES.ISO8859-1';
$languages['ca']['ALIAS'] = 'ca_ES';
$languages['cs_CZ']['NAME'] = 'Czech';
+$languages['cs_CZ']['ALTNAME'] = 'Čeština';
$languages['cs_CZ']['CHARSET'] = 'iso-8859-2';
+$languages['cs_CZ']['LOCALE'] = 'cs_CZ.ISO8859-2';
$languages['cs']['ALIAS'] = 'cs_CZ';
-// Danish locale is da_DK.
+$languages['cy_GB']['NAME'] = 'Welsh';
+$languages['cy_GB']['ALTNAME'] = 'Cymraeg';
+$languages['cy_GB']['CHARSET'] = 'iso-8859-1';
+$languages['cy_GB']['LOCALE'] = 'cy_GB.ISO8859-1';
+$languages['cy']['ALIAS'] = 'cy_GB';
+// Danish locale is da_DK.
$languages['da_DK']['NAME'] = 'Danish';
+$languages['da_DK']['ALTNAME'] = 'Dansk';
$languages['da_DK']['CHARSET'] = 'iso-8859-1';
+$languages['da_DK']['LOCALE'] = 'da_DK.ISO8859-1';
$languages['da']['ALIAS'] = 'da_DK';
-$languages['de_DE']['NAME'] = 'Deutsch';
+$languages['de_DE']['NAME'] = 'German';
+$languages['de_DE']['ALTNAME'] = 'Deutsch';
$languages['de_DE']['CHARSET'] = 'iso-8859-1';
+$languages['de_DE']['LOCALE'] = 'de_DE.ISO8859-1';
$languages['de']['ALIAS'] = 'de_DE';
-// There is no en_EN! There is en_US, en_BR, en_AU, and so forth,
-// but who cares about !US, right? Right? :)
-
$languages['el_GR']['NAME'] = 'Greek';
+$languages['el_GR']['ALTNAME'] = 'Ελληνικά';
$languages['el_GR']['CHARSET'] = 'iso-8859-7';
+$languages['el_GR']['LOCALE'] = 'el_GR.ISO8859-7';
$languages['el']['ALIAS'] = 'el_GR';
+$languages['en_GB']['NAME'] = 'British';
+$languages['en_GB']['CHARSET'] = 'iso-8859-15';
+$languages['en_GB']['LOCALE'] = 'en_GB.ISO8859-15';
+
$languages['en_US']['NAME'] = 'English';
$languages['en_US']['CHARSET'] = 'iso-8859-1';
+$languages['en_US']['LOCALE'] = 'en_US.ISO8859-1';
$languages['en']['ALIAS'] = 'en_US';
$languages['es_ES']['NAME'] = 'Spanish';
+$languages['es_ES']['ALTNAME'] = 'Español';
$languages['es_ES']['CHARSET'] = 'iso-8859-1';
+$languages['es_ES']['LOCALE'] = 'es_ES.ISO8859-1';
$languages['es']['ALIAS'] = 'es_ES';
$languages['et_EE']['NAME'] = 'Estonian';
$languages['et_EE']['CHARSET'] = 'iso-8859-15';
+$languages['et_EE']['LOCALE'] = 'et_EE.ISO8859-15';
$languages['et']['ALIAS'] = 'et_EE';
$languages['fo_FO']['NAME'] = 'Faroese';
$languages['fo_FO']['CHARSET'] = 'iso-8859-1';
+$languages['fo_FO']['LOCALE'] = 'fo_FO.ISO8859-1';
$languages['fo']['ALIAS'] = 'fo_FO';
$languages['fi_FI']['NAME'] = 'Finnish';
+$languages['fi_FI']['ALTNAME'] = 'Suomi';
$languages['fi_FI']['CHARSET'] = 'iso-8859-1';
+$languages['fi_FI']['LOCALE'] = 'fi_FI.ISO8859-1';
$languages['fi']['ALIAS'] = 'fi_FI';
$languages['fr_FR']['NAME'] = 'French';
+$languages['fr_FR']['ALTNAME'] = 'Français';
$languages['fr_FR']['CHARSET'] = 'iso-8859-1';
+$languages['fr_FR']['LOCALE'] = 'fr_FR.ISO8859-1';
$languages['fr']['ALIAS'] = 'fr_FR';
$languages['hr_HR']['NAME'] = 'Croatian';
$languages['hr_HR']['CHARSET'] = 'iso-8859-2';
+$languages['hr_HR']['LOCALE'] = 'hr_HR.ISO8859-2';
$languages['hr']['ALIAS'] = 'hr_HR';
$languages['hu_HU']['NAME'] = 'Hungarian';
+$languages['hu_HU']['ALTNAME'] = 'Magyar';
$languages['hu_HU']['CHARSET'] = 'iso-8859-2';
+$languages['hu_HU']['LOCALE'] = 'hu_HU.ISO8859-2';
$languages['hu']['ALIAS'] = 'hu_HU';
-$languages['id_ID']['NAME'] = 'Bahasa Indonesia';
+$languages['id_ID']['NAME'] = 'Indonesian';
+$languages['id_ID']['ALTNAME'] = 'Bahasa Indonesia';
$languages['id_ID']['CHARSET'] = 'iso-8859-1';
+$languages['id_ID']['LOCALE'] = 'id_ID.ISO8859-1';
$languages['id']['ALIAS'] = 'id_ID';
$languages['is_IS']['NAME'] = 'Icelandic';
+$languages['is_IS']['ALTNAME'] = 'Íslenska';
$languages['is_IS']['CHARSET'] = 'iso-8859-1';
+$languages['is_IS']['LOCALE'] = 'is_IS.ISO8859-1';
$languages['is']['ALIAS'] = 'is_IS';
$languages['it_IT']['NAME'] = 'Italian';
$languages['it_IT']['CHARSET'] = 'iso-8859-1';
+$languages['it_IT']['LOCALE'] = 'it_IT.ISO8859-1';
$languages['it']['ALIAS'] = 'it_IT';
$languages['ja_JP']['NAME'] = 'Japanese';
+$languages['ja_JP']['ALTNAME'] = '日本語';
$languages['ja_JP']['CHARSET'] = 'iso-2022-jp';
+$languages['ja_JP']['LOCALE'] = 'ja_JP.EUC-JP';
$languages['ja_JP']['XTRA_CODE'] = 'japanese_charset_xtra';
$languages['ja']['ALIAS'] = 'ja_JP';
$languages['ko_KR']['NAME'] = 'Korean';
$languages['ko_KR']['CHARSET'] = 'euc-KR';
+$languages['ko_KR']['LOCALE'] = 'ko_KR.EUC-KR';
$languages['ko_KR']['XTRA_CODE'] = 'korean_charset_xtra';
$languages['ko']['ALIAS'] = 'ko_KR';
+$languages['lt_LT']['NAME'] = 'Lithuanian';
+$languages['lt_LT']['ALTNAME'] = 'Lietuvių';
+$languages['lt_LT']['CHARSET'] = 'utf-8';
+$languages['lt_LT']['LOCALE'] = 'lt_LT.UTF-8';
+$languages['lt']['ALIAS'] = 'lt_LT';
+
$languages['nl_NL']['NAME'] = 'Dutch';
+$languages['nl_NL']['ALTNAME'] = 'Nederlands';
$languages['nl_NL']['CHARSET'] = 'iso-8859-1';
+$languages['nl_NL']['LOCALE'] = 'nl_NL.ISO8859-1';
$languages['nl']['ALIAS'] = 'nl_NL';
-$languages['no_NO']['NAME'] = 'Norwegian (Bokmål)';
-$languages['no_NO']['CHARSET'] = 'iso-8859-1';
-$languages['no']['ALIAS'] = 'no_NO';
+$languages['ms_MY']['NAME'] = 'Malay';
+$languages['ms_MY']['ALTNAME'] = 'Bahasa Melayu';
+$languages['ms_MY']['CHARSET'] = 'iso-8859-1';
+$languages['ms_MY']['LOCALE'] = 'ms_MY.ISO8859-1';
+$languages['my']['ALIAS'] = 'ms_MY';
+
+$languages['nb_NO']['NAME'] = 'Norwegian (Bokmål)';
+$languages['nb_NO']['ALTNAME'] = 'Norsk (Bokmål)';
+$languages['nb_NO']['CHARSET'] = 'iso-8859-1';
+$languages['nb_NO']['LOCALE'] = 'nb_NO.ISO8859-1';
+$languages['nb']['ALIAS'] = 'nb_NO';
+
$languages['nn_NO']['NAME'] = 'Norwegian (Nynorsk)';
+$languages['nn_NO']['ALTNAME'] = 'Norsk (Nynorsk)';
$languages['nn_NO']['CHARSET'] = 'iso-8859-1';
+$languages['nn_NO']['LOCALE'] = 'nn_NO.ISO8859-1';
$languages['pl_PL']['NAME'] = 'Polish';
+$languages['pl_PL']['ALTNAME'] = 'Polski';
$languages['pl_PL']['CHARSET'] = 'iso-8859-2';
+$languages['pl_PL']['LOCALE'] = 'pl_PL.ISO8859-2';
$languages['pl']['ALIAS'] = 'pl_PL';
$languages['pt_PT']['NAME'] = 'Portuguese (Portugal)';
$languages['pt_PT']['CHARSET'] = 'iso-8859-1';
+$languages['pt_PT']['LOCALE'] = 'pt_PT.ISO8859-1';
+$languages['pt']['ALIAS'] = 'pt_PT';
+
$languages['pt_BR']['NAME'] = 'Portuguese (Brazil)';
+$languages['pt_BR']['ALTNAME'] = 'Português do Brasil';
$languages['pt_BR']['CHARSET'] = 'iso-8859-1';
-$languages['pt']['ALIAS'] = 'pt_PT';
+$languages['pt_BR']['LOCALE'] = 'pt_BR.ISO8859-1';
+
+$languages['ro_RO']['NAME'] = 'Romanian';
+$languages['ro_RO']['ALTNAME'] = 'Română';
+$languages['ro_RO']['CHARSET'] = 'iso-8859-2';
+$languages['ro_RO']['LOCALE'] = 'ro_RO.ISO8859-2';
+$languages['ro']['ALIAS'] = 'ro_RO';
$languages['ru_RU']['NAME'] = 'Russian';
-$languages['ru_RU']['CHARSET'] = 'koi8-r';
+$languages['ru_RU']['ALTNAME'] = 'Русский';
+$languages['ru_RU']['CHARSET'] = 'utf-8';
+$languages['ru_RU']['LOCALE'] = 'ru_RU.UTF-8';
$languages['ru']['ALIAS'] = 'ru_RU';
+$languages['sk_SK']['NAME'] = 'Slovak';
+$languages['sk_SK']['CHARSET'] = 'iso-8859-2';
+$languages['sk_SK']['LOCALE'] = 'sk_SK.ISO8859-2';
+$languages['sk']['ALIAS'] = 'sk_SK';
+
+$languages['sl_SI']['NAME'] = 'Slovenian';
+$languages['sl_SI']['ALTNAME'] = 'Slovenščina';
+$languages['sl_SI']['CHARSET'] = 'iso-8859-2';
+$languages['sl_SI']['LOCALE'] = 'sl_SI.ISO8859-2';
+$languages['sl']['ALIAS'] = 'sl_SI';
+
$languages['sr_YU']['NAME'] = 'Serbian';
+$languages['sr_YU']['ALTNAME'] = 'Srpski';
$languages['sr_YU']['CHARSET'] = 'iso-8859-2';
+$languages['sr_YU']['LOCALE'] = 'sr_YU.ISO8859-2';
$languages['sr']['ALIAS'] = 'sr_YU';
$languages['sv_SE']['NAME'] = 'Swedish';
+$languages['sv_SE']['ALTNAME'] = 'Svenska';
$languages['sv_SE']['CHARSET'] = 'iso-8859-1';
+$languages['sv_SE']['LOCALE'] = 'sv_SE.ISO8859-1';
$languages['sv']['ALIAS'] = 'sv_SE';
+$languages['th_TH']['NAME'] = 'Thai';
+$languages['th_TH']['CHARSET'] = 'tis-620';
+$languages['th_TH']['LOCALE'] = 'th_TH.TIS-620';
+$languages['th']['ALIAS'] = 'th_TH';
+
+$languages['tl_PH']['NAME'] = 'Tagalog';
+$languages['tl_PH']['CHARSET'] = 'iso-8859-1';
+$languages['tl_PH']['LOCALE'] = 'tl_PH.ISO8859-1';
+$languages['tl']['ALIAS'] = 'tl_PH';
+
$languages['tr_TR']['NAME'] = 'Turkish';
$languages['tr_TR']['CHARSET'] = 'iso-8859-9';
+$languages['tr_TR']['LOCALE'] = 'tr_TR.ISO8859-9';
$languages['tr']['ALIAS'] = 'tr_TR';
$languages['zh_TW']['NAME'] = 'Chinese Trad';
$languages['zh_TW']['CHARSET'] = 'big5';
+$languages['zh_TW']['LOCALE'] = 'zh_TW.BIG5';
$languages['tw']['ALIAS'] = 'zh_TW';
$languages['zh_CN']['NAME'] = 'Chinese Simp';
$languages['zh_CN']['CHARSET'] = 'gb2312';
+$languages['zh_CN']['LOCALE'] = 'zh_CN.GB2312';
$languages['cn']['ALIAS'] = 'zh_CN';
-$languages['sk_SK']['NAME'] = 'Slovak';
-$languages['sk_SK']['CHARSET'] = 'iso-8859-2';
-$languages['sk']['ALIAS'] = 'sk_SK';
-
-$languages['ro_RO']['NAME'] = 'Romanian';
-$languages['ro_RO']['CHARSET'] = 'iso-8859-2';
-$languages['ro']['ALIAS'] = 'ro_RO';
-
-$languages['th_TH']['NAME'] = 'Thai';
-$languages['th_TH']['CHARSET'] = 'tis-620';
-$languages['th']['ALIAS'] = 'th_TH';
-
-$languages['lt_LT']['NAME'] = 'Lithuanian';
-$languages['lt_LT']['CHARSET'] = 'windows-1257';
-$languages['lt']['ALIAS'] = 'lt_LT';
-
-$languages['sl_SI']['NAME'] = 'Slovenian';
-$languages['sl_SI']['CHARSET'] = 'iso-8859-2';
-$languages['sl']['ALIAS'] = 'sl_SI';
-
-$languages['bg_BG']['NAME'] = 'Bulgarian';
-$languages['bg_BG']['CHARSET'] = 'windows-1251';
-$languages['bg']['ALIAS'] = 'bg_BG';
-
$languages['uk_UA']['NAME'] = 'Ukrainian';
$languages['uk_UA']['CHARSET'] = 'koi8-u';
+$languages['uk_UA']['LOCALE'] = 'uk_UA.KOI8-U';
$languages['uk']['ALIAS'] = 'uk_UA';
-$languages['cy_GB']['NAME'] = 'Welsh';
-$languages['cy_GB']['CHARSET'] = 'iso-8859-1';
-$languages['cy']['ALIAS'] = 'cy_GB';
+$languages['ru_UA']['NAME'] = 'Russian (Ukrainian)';
+$languages['ru_UA']['CHARSET'] = 'koi8-r';
+$languages['ru_UA']['LOCALE'] = 'ru_UA.KOI8-R';
+/*
$languages['vi_VN']['NAME'] = 'Vietnamese';
$languages['vi_VN']['CHARSET'] = 'utf-8';
$languages['vi']['ALIAS'] = 'vi_VN';
+*/
// Right to left languages
-
$languages['ar']['NAME'] = 'Arabic';
$languages['ar']['CHARSET'] = 'windows-1256';
$languages['ar']['DIR'] = 'rtl';
+$languages['fa_IR']['NAME'] = 'Farsi';
+$languages['fa_IR']['CHARSET'] = 'utf-8';
+$languages['fa_IR']['DIR'] = 'rtl';
+$languages['fa_IR']['LOCALE'] = 'fa_IR.UTF-8';
+$languages['fa']['ALIAS'] = 'fa_IR';
+
$languages['he_IL']['NAME'] = 'Hebrew';
$languages['he_IL']['CHARSET'] = 'windows-1255';
+$languages['he_IL']['LOCALE'] = 'he_IL.CP1255';
$languages['he_IL']['DIR'] = 'rtl';
$languages['he']['ALIAS'] = 'he_IL';
}
}
-function charset_decode_utf8 ($string) {
-/*
- Every decoded character consists of n bytes. First byte is octal
- 300-375, other bytes - always octals 200-277.
-
- \a\b characters are decoded to html code octdec(a-300)*64 + octdec(b-200)
- \a\b\c characters are decoded to html code octdec(a-340)*64*64 + octdec(b-200)*64 + octdec(c-200)
-
- decoding cycle is unfinished. please test and report problems to tokul@users.sourceforge.net
-*/
- global $default_charset, $languages, $sm_notAlias;
- if (strtolower($default_charset) == 'utf-8')
- return $string;
- if (strtolower($languages[$sm_notAlias]['CHARSET']) == 'utf-8')
- return $string;
-
- /* Only do the slow convert if there are 8-bit characters */
- if (! ereg("[\200-\377]", $string))
- return $string;
-
- // decode three byte unicode characters
- $string = preg_replace("/([\340-\357])([\200-\277])([\200-\277])/e",
- "'&#'.((ord('\\1')-224)*4096+(ord('\\2')-128)*64+(ord('\\3')-128)).';'",
- $string);
-
- // decode two byte unicode characters
- $string = preg_replace("/([\300-\337])([\200-\277])/e",
- "'&#'.((ord('\\1')-192)*64+(ord('\\2')-128)).';'",
- $string);
-
- return $string;
-}
-
-/*
+/**
* Japanese charset extra function
*
+ * Action performed by function is defined by first argument.
+ * Default return value is defined by second argument.
+ * Use of third argument depends on action.
+ *
+ * @param string $action action performed by this function.
+ * possible values:
+ * decode - convert returned string to euc-jp. third argument unused
+ * encode - convert returned string to jis. third argument unused
+ * strimwidth - third argument=$width. trims string to $width symbols.
+ * encodeheader - create base64 encoded header in iso-2022-jp. third argument unused
+ * decodeheader - return human readable string from mime header. string is returned in euc-jp. third argument unused
+ * downloadfilename - third argument $useragent. Arguments provide browser info. Returns shift-jis or euc-jp encoded file name
+ * wordwrap - third argument=$wrap. wraps text at $wrap symbols
+ * utf7-imap_encode - returns string converted from euc-jp to utf7-imap. third argument unused
+ * utf7-imap_decode - returns string converted from utf7-imap to euc-jp. third argument unused
+ * @param string $ret default return value
*/
function japanese_charset_xtra() {
$ret = func_get_arg(1); /* default return value */
}
-/*
- * Korean charset extra function
- * Hangul(Korean Character) Attached File Name Fix.
+/**
+ * Korean charset extra functions
+ *
+ * Action performed by function is defined by first argument.
+ * Default return value is defined by second argument.
+ *
+ * @param string action performed by this function.
+ * possible values:
+ * downloadfilename - Hangul(Korean Character) Attached File Name Fix.
+ * @param string default return value
*/
function korean_charset_xtra() {
}
}
-
return $ret;
}
+/**
+ * Replaces non-braking spaces inserted by some browsers with regular space
+ *
+ * This function can be used to replace non-braking space symbols
+ * that are inserted in forms by some browsers instead of normal
+ * space symbol.
+ *
+ * @param string $string Text that needs to be cleaned
+ * @param string $charset Charset used in text
+ * @return string Cleaned text
+ */
+function cleanup_nbsp($string,$charset) {
+
+ // reduce number of case statements
+ if (stristr('iso-8859-',substr($charset,0,9))){
+ $output_charset="iso-8859-x";
+ }
+ if (stristr('windows-125',substr($charset,0,11))){
+ $output_charset="cp125x";
+ }
+ if (stristr('koi8',substr($charset,0,4))){
+ $output_charset="koi8-x";
+ }
+ if (! isset($output_charset)){
+ $output_charset=strtolower($charset);
+ }
+
+// where is non-braking space symbol
+switch($output_charset):
+ case "iso-8859-x":
+ case "cp125x":
+ case "iso-2022-jp":
+ $nbsp="\xA0";
+ break;
+ case "koi8-x":
+ $nbsp="\x9A";
+ break;
+ case "utf-8":
+ $nbsp="\xC2\xA0";
+ break;
+ default:
+ // don't change string if charset is unmatched
+ return $string;
+endswitch;
+
+// return space instead of non-braking space.
+ return str_replace($nbsp,' ',$string);
+}
+
+/**
+ * Function informs if it is safe to convert given charset to the one that is used by user.
+ *
+ * It is safe to use conversion only if user uses utf-8 encoding and when
+ * converted charset is similar to the one that is used by user.
+ *
+ * @param string $input_charset Charset of text that needs to be converted
+ * @return bool is it possible to convert to user's charset
+ */
+function is_conversion_safe($input_charset) {
+ global $languages, $sm_notAlias, $default_charset;
+
+ // convert to lower case
+ $input_charset = strtolower($input_charset);
+
+ // Is user's locale Unicode based ?
+ if ( $default_charset == "utf-8" ) {
+ return true;
+ }
+
+ // Charsets that are similar
+switch ($default_charset):
+case "windows-1251":
+ if ( $input_charset == "iso-8859-5" ||
+ $input_charset == "koi8-r" ||
+ $input_charset == "koi8-u" ) {
+ return true;
+ } else {
+ return false;
+ }
+case "windows-1257":
+ if ( $input_charset == "iso-8859-13" ||
+ $input_charset == "iso-8859-4" ) {
+ return true;
+ } else {
+ return false;
+ }
+case "iso-8859-4":
+ if ( $input_charset == "iso-8859-13" ||
+ $input_charset == "windows-1257" ) {
+ return true;
+ } else {
+ return false;
+ }
+case "iso-8859-5":
+ if ( $input_charset == "windows-1251" ||
+ $input_charset == "koi8-r" ||
+ $input_charset == "koi8-u" ) {
+ return true;
+ } else {
+ return false;
+ }
+case "iso-8859-13":
+ if ( $input_charset == "iso-8859-4" ||
+ $input_charset == "windows-1257" ) {
+ return true;
+ } else {
+ return false;
+ }
+case "koi8-r":
+ if ( $input_charset == "windows-1251" ||
+ $input_charset == "iso-8859-5" ||
+ $input_charset == "koi8-u" ) {
+ return true;
+ } else {
+ return false;
+ }
+case "koi8-u":
+ if ( $input_charset == "windows-1251" ||
+ $input_charset == "iso-8859-5" ||
+ $input_charset == "koi8-r" ) {
+ return true;
+ } else {
+ return false;
+ }
+default:
+ return false;
+endswitch;
+}
?>
\ No newline at end of file