X-Git-Url: https://vcs.fsf.org/?a=blobdiff_plain;f=functions%2Fi18n.php;h=764188e7353f66b8fe367ff156737accc527b775;hb=969a0af6a44fbaea7d56f542f067277109546516;hp=c7b5618428955a26a6f485890e4a806687af45f9;hpb=e7ab8c9da136be7565e4b686841d95370b286896;p=squirrelmail.git

diff --git a/functions/i18n.php b/functions/i18n.php
index c7b56184..764188e7 100644
--- a/functions/i18n.php
+++ b/functions/i18n.php
@@ -3,7 +3,7 @@
 /**
  * i18n.php
  *
- * Copyright (c) 1999-2002 The SquirrelMail Project Team
+ * Copyright (c) 1999-2003 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
@@ -15,6 +15,8 @@
  * $Id$
  */
 
+require_once(SM_PATH . 'functions/global.php');
+
 /* Decodes a string to the internal encoding from the given charset */
 function charset_decode ($charset, $string) {
     global $languages, $squirrelmail_language;
@@ -25,10 +27,13 @@ function charset_decode ($charset, $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);
@@ -36,8 +41,12 @@ function charset_decode ($charset, $string) {
             $ret = charset_decode_iso_8859_2 ($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 ($res[1] == '15') {
@@ -50,7 +59,15 @@ function charset_decode ($charset, $string) {
     } else if ($charset == 'koi8-r') {
         $ret = charset_decode_koi8r ($string);
     } else if ($charset == 'windows-1251') {
-        $ret = charset_decode_koi8r ($string);
+        $ret = charset_decode_windows_1251 ($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 = $string;
     }
@@ -408,49 +425,71 @@ function charset_decode_iso_8859_2 ($string) {
 }
 
 /* 
-   iso-8859-4 is Baltic codeset used in some email clients 
-   instead of iso-8859-13 in Lithuania 
-   only Lithuanian charactes are added.
+ ISO/IEC 8859-4:1998 Latin Alphabet No. 4
 */
 
 function charset_decode_iso_8859_4 ($string) {
-    // latin capital a with ogonek
-    $string = str_replace ("\241", 'Ą', $string);
-    // latin capital c with caron
-    $string = str_replace ("\310", 'Č', $string);
-    // latin capital e with ogonek
-    $string = str_replace ("\312", 'Ę', $string);
-    // latin capital e with dot above
-    $string = str_replace ("\314", 'Ė', $string);
-    // latin capital i with ogonek
-    $string = str_replace ("\307", 'Į', $string);
-    // latin capital s with caron
-    $string = str_replace ("\251", 'Š', $string);
-    // latin capital u with ogonek
-    $string = str_replace ("\331", 'Ų', $string);
-    // latin capital u with macron
-    $string = str_replace ("\336", 'Ū', $string);
-    // latin capital z with caron
-    $string = str_replace ("\256", 'Ž', $string);
-    // latin small a with ogonek
-    $string = str_replace ("\261", 'ą', $string);
-    // latin small c with caron
-    $string = str_replace ("\350", 'č', $string);
-    // latin small e with ogonek
-    $string = str_replace ("\352", 'ę', $string);
-    // latin small e with dot above
-    $string = str_replace ("\354", 'ė', $string);
-    // latin small i with ogonek
-    $string = str_replace ("\347", 'į', $string);
-    // latin small s with caron
-    $string = str_replace ("\271", 'š', $string);
-    // latin small u with ogonek
-    $string = str_replace ("\371", 'ų', $string);
-    // latin small u with macron
-    $string = str_replace ("\376", 'ū', $string);
-    // latin small z with caron
-    $string = str_replace ("\276", 'ž', $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));
 }
 
@@ -492,7 +531,7 @@ function charset_decode_iso_8859_7 ($string) {
      * ISO-8859-7 characters from 11/04 (0xB4) to 11/06 (0xB6)
      * These are Unicode 900-902
      */
-    $string = preg_replace("/([\264-\266])/","'&#' . (ord(\\1)+720)",$string);
+    $string = preg_replace("/([\264-\266])/e","'&#' . (ord('\\1')+720);",$string);
     
     /* 11/07 (0xB7) Middle dot is the same in iso-8859-1 */
     $string = str_replace("\267", '·', $string);
@@ -501,7 +540,7 @@ function charset_decode_iso_8859_7 ($string) {
      * ISO-8859-7 characters from 11/08 (0xB8) to 11/10 (0xBA)
      * These are Unicode 900-902
      */
-    $string = preg_replace("/([\270-\272])/","'&#' . (ord(\\1)+720)",$string);
+    $string = preg_replace("/([\270-\272])/e","'&#' . (ord('\\1')+720);",$string);
 
     /*
      * 11/11 (0xBB) Right angle quotation mark is the same as in
@@ -510,54 +549,114 @@ function charset_decode_iso_8859_7 ($string) {
     $string = str_replace("\273", '»', $string);
 
     /* And now the rest of the charset */
-    $string = preg_replace("/([\274-\376])/","'&#' . (ord(\\1)+720)",$string);
+    $string = preg_replace("/([\274-\376])/e","'&#'.(ord('\\1')+720);",$string);
 
     return $string;
 }
 
 /*
- iso-8859-13 codeset used in Lithuania
- only Lithuanian charactes are added.
+ 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) {
-    // latin capital a with ogonek
-    $string = str_replace ("\300", 'Ą', $string);
-    // latin capital c with caron
-    $string = str_replace ("\310", 'Č', $string);
-    // latin capital e with ogonek
-    $string = str_replace ("\306", 'Ę', $string);
-    // latin capital e with dot above
-    $string = str_replace ("\313", 'Ė', $string);
-    // latin capital i with ogonek
-    $string = str_replace ("\301", 'Į', $string);
-    // latin capital s with caron
-    $string = str_replace ("\320", 'Š', $string);
-    // latin capital u with ogonek
-    $string = str_replace ("\330", 'Ų', $string);
-    // latin capital u with macron
-    $string = str_replace ("\333", 'Ū', $string);
-    // latin capital z with caron
-    $string = str_replace ("\336", 'Ž', $string);
-    // latin small a with ogonek
-    $string = str_replace ("\340", 'ą', $string);
-    // latin small c with caron
-    $string = str_replace ("\350", 'č', $string);
-    // latin small e with ogonek
-    $string = str_replace ("\346", 'ę', $string);
-    // latin small e with dot above
-    $string = str_replace ("\353", 'ė', $string);
-    // latin small i with ogonek
-    $string = str_replace ("\341", 'į', $string);
-    // latin small s with caron
-    $string = str_replace ("\360", 'š', $string);
-    // latin small u with ogonek
-    $string = str_replace ("\370", 'ų', $string);
-    // latin small u with macron
-    $string = str_replace ("\373", 'ū', $string);
-    // latin small z with caron
-    $string = str_replace ("\376", 'ž', $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));
 }
 
@@ -776,6 +875,234 @@ function charset_decode_koi8r ($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));
+}
+
+/*
+ windows-1253 (Greek)
+ */
+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($string));
+}
+
+
+/*
+ windows-1257 (BaltRim)
+ */
+function charset_decode_windows_1257 ($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));
+}
+
+/* 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);
+}
+
+
 
 /*
  * Set up the language to be output
@@ -785,17 +1112,19 @@ function charset_decode_koi8r ($string) {
 function set_up_language($sm_language, $do_search = false) {
 
     static $SetupAlready = 0;
-    global $HTTP_ACCEPT_LANGUAGE, $use_gettext, $languages,
+    global $use_gettext, $languages,
            $squirrelmail_language, $squirrelmail_default_language,
            $sm_notAlias;
 
     if ($SetupAlready) {
         return;
     }
+
     $SetupAlready = TRUE;
+    sqgetGlobalVar('HTTP_ACCEPT_LANGUAGE',  $accept_lang, SQ_SERVER);
 
-    if ($do_search && ! $sm_language && isset($HTTP_ACCEPT_LANGUAGE)) {
-        $sm_language = substr($HTTP_ACCEPT_LANGUAGE, 0, 2);
+    if ($do_search && ! $sm_language && isset($accept_lang)) {
+        $sm_language = substr($accept_lang, 0, 2);
     }
     
     if (!$sm_language && isset($squirrelmail_default_language)) {
@@ -811,8 +1140,11 @@ function set_up_language($sm_language, $do_search = false) {
          $use_gettext &&
          $sm_language != '' &&
          isset($languages[$sm_notAlias]['CHARSET']) ) {
-        bindtextdomain( 'squirrelmail', '../locale/' );
+        bindtextdomain( 'squirrelmail', SM_PATH . 'locale/' );
         textdomain( 'squirrelmail' );
+	if (function_exists('bind_textdomain_codeset')) {
+	     bind_textdomain_codeset ("squirrelmail", $languages[$sm_notAlias]['CHARSET'] );
+	}
         if ( !ini_get('safe_mode') &&
              getenv( 'LC_ALL' ) != $sm_notAlias ) {
             putenv( "LC_ALL=$sm_notAlias" );
@@ -824,7 +1156,10 @@ function set_up_language($sm_language, $do_search = false) {
         if ($squirrelmail_language == 'ja_JP' && function_exists('mb_detect_encoding') ) {
             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 --with-mbstring).");
+                echo _("You need to have php4 installed with the multibyte string function enabled (using configure option --enable-mbstring).");
+            }
+            if (function_exists('mb_language')) {
+                mb_language('Japanese');
             }
             mb_internal_encoding('EUC-JP');
             mb_http_output('pass');
@@ -845,11 +1180,11 @@ function set_my_charset(){
      * 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;
+    global $data_dir, $username, $default_charset, $languages, $squirrelmail_default_language;
 
     $my_language = getPref($data_dir, $username, 'language');
     if (!$my_language) {
-        return;
+        $my_language = $squirrelmail_default_language ;
     }
     while (isset($languages[$my_language]['ALIAS'])) {
         $my_language = $languages[$my_language]['ALIAS'];
@@ -893,6 +1228,10 @@ $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']['CHARSET'] = 'iso-8859-7';
+$languages['el']['ALIAS'] = 'el_GR';
+
 $languages['en_US']['NAME']    = 'English';
 $languages['en_US']['CHARSET'] = 'iso-8859-1';
 $languages['en']['ALIAS'] = 'en_US';
@@ -979,13 +1318,13 @@ $languages['tr_TR']['NAME']    = 'Turkish';
 $languages['tr_TR']['CHARSET'] = 'iso-8859-9';
 $languages['tr']['ALIAS'] = 'tr_TR';
 
-$languages['zh_TW']['NAME']    = 'Taiwan';
+$languages['zh_TW']['NAME']    = 'Chinese Trad';
 $languages['zh_TW']['CHARSET'] = 'big5';
 $languages['tw']['ALIAS'] = 'zh_TW';
 
-$languages['zh_TW']['NAME']    = 'Chinese';
-$languages['zh_TW']['CHARSET'] = 'gb2312';
-$languages['tw']['ALIAS'] = 'zh_CN';
+$languages['zh_CN']['NAME']    = 'Chinese Simp';
+$languages['zh_CN']['CHARSET'] = 'gb2312';
+$languages['cn']['ALIAS'] = 'zh_CN';
 
 $languages['sk_SK']['NAME']     = 'Slovak';
 $languages['sk_SK']['CHARSET']  = 'iso-8859-2';
@@ -1000,7 +1339,7 @@ $languages['th_TH']['CHARSET'] = 'tis-620';
 $languages['th']['ALIAS'] = 'th_TH';
 
 $languages['lt_LT']['NAME']    = 'Lithuanian';
-$languages['lt_LT']['CHARSET'] = 'iso-8859-13';
+$languages['lt_LT']['CHARSET'] = 'windows-1257';
 $languages['lt']['ALIAS'] = 'lt_LT';
 
 $languages['sl_SI']['NAME']    = 'Slovenian';
@@ -1011,13 +1350,29 @@ $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';
+$languages['uk']['ALIAS'] = 'uk_UA';
+
+$languages['cy_GB']['NAME']    = 'Welsh';
+$languages['cy_GB']['CHARSET'] = 'iso-8859-1';
+$languages['cy']['ALIAS'] = 'cy_GB';
+
+
 // Right to left languages
 
-$languages['he_HE']['NAME']    = 'Hebrew';
-$languages['he_HE']['CHARSET'] = 'windows-1255';
-$languages['he_HE']['DIR']     = 'rtl';
-$languages['he']['ALIAS']      = 'he_HE';
+$languages['ar']['NAME']    = 'Arabic';
+$languages['ar']['CHARSET'] = 'windows-1256';
+$languages['ar']['DIR']     = 'rtl';
+
+$languages['he_IL']['NAME']    = 'Hebrew';
+$languages['he_IL']['CHARSET'] = 'windows-1255';
+$languages['he_IL']['DIR']     = 'rtl';
+$languages['he']['ALIAS']      = 'he_IL';
 
+$languages['vi_VN']['NAME']    = 'Vietnamese';
+$languages['vi_VN']['CHARSET'] = 'utf-8';
+$languages['vi']['ALIAS'] = 'vi_VN';
 
 /* Detect whether gettext is installed. */
 $gettext_flags = 0;
@@ -1058,6 +1413,39 @@ elseif ($gettext_flags == 0) {
     }
 }
 
+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
@@ -1068,21 +1456,23 @@ function japanese_charset_xtra() {
     if (function_exists('mb_detect_encoding')) {
         switch (func_get_arg(0)) { /* action */
         case 'decode':
-            $detect_encoding = mb_detect_encoding($ret);
+            $detect_encoding = @mb_detect_encoding($ret);
             if ($detect_encoding == 'JIS' ||
                 $detect_encoding == 'EUC-JP' ||
-                $detect_encoding == 'SJIS') {
+                $detect_encoding == 'SJIS' ||
+                $detect_encoding == 'UTF-8') {
                 
-                $ret = mb_convert_encoding($ret, 'EUC-JP', 'AUTO');
+                $ret = mb_convert_kana(mb_convert_encoding($ret, 'EUC-JP', 'AUTO'), "KV");
             }
             break;
         case 'encode':
-            $detect_encoding = mb_detect_encoding($ret);
+            $detect_encoding = @mb_detect_encoding($ret);
             if ($detect_encoding == 'JIS' ||
                 $detect_encoding == 'EUC-JP' ||
-                $detect_encoding == 'SJIS') {
+                $detect_encoding == 'SJIS' ||
+                $detect_encoding == 'UTF-8') {
                 
-                $ret = mb_convert_encoding($ret, 'JIS', 'AUTO');
+                $ret = mb_convert_encoding(mb_convert_kana($ret, "KV"), 'JIS', 'AUTO');
             }
             break;
         case 'strimwidth':
@@ -1102,7 +1492,8 @@ function japanese_charset_xtra() {
                         if ($prevcsize == 1) {
                             $result .= $tmpstr;
                         } else {
-                            $result .= mb_encode_mimeheader($tmpstr);
+                            $result .= str_replace(' ', '', 
+                                                   mb_encode_mimeheader($tmpstr,'iso-2022-jp','B',''));
                         }
                         $tmpstr = $tmp;
                         $prevcsize = strlen($tmp);
@@ -1112,17 +1503,17 @@ function japanese_charset_xtra() {
                     if (strlen(mb_substr($tmpstr, 0, 1)) == 1)
                         $result .= $tmpstr;
                     else
-                        $result .= mb_encode_mimeheader($tmpstr);
+                        $result .= str_replace(' ', '',
+                                               mb_encode_mimeheader($tmpstr,'iso-2022-jp','B',''));
                 }
             }
             $ret = $result;
-            //$ret = mb_encode_mimeheader($ret);
             break;
         case 'decodeheader':
             $ret = str_replace("\t", "", $ret);
             if (eregi('=\\?([^?]+)\\?(q|b)\\?([^?]+)\\?=', $ret))
-                $ret = mb_decode_mimeheader($ret);
-            $ret = mb_convert_encoding($ret, 'EUC-JP', 'AUTO');
+                $ret = @mb_decode_mimeheader($ret);
+            $ret = @mb_convert_encoding($ret, 'EUC-JP', 'AUTO');
             break;
         case 'downloadfilename':
             $useragent = func_get_arg(2);
@@ -1133,6 +1524,54 @@ function japanese_charset_xtra() {
                 $ret = mb_convert_encoding($ret, 'EUC-JP', 'AUTO');
 }
             break;
+        case 'wordwrap':
+            $no_begin = "\x21\x25\x29\x2c\x2e\x3a\x3b\x3f\x5d\x7d\xa1\xf1\xa1\xeb\xa1" .
+                "\xc7\xa1\xc9\xa2\xf3\xa1\xec\xa1\xed\xa1\xee\xa1\xa2\xa1\xa3\xa1\xb9" .
+                "\xa1\xd3\xa1\xd5\xa1\xd7\xa1\xd9\xa1\xdb\xa1\xcd\xa4\xa1\xa4\xa3\xa4" .
+                "\xa5\xa4\xa7\xa4\xa9\xa4\xc3\xa4\xe3\xa4\xe5\xa4\xe7\xa4\xee\xa1\xab" .
+                "\xa1\xac\xa1\xb5\xa1\xb6\xa5\xa1\xa5\xa3\xa5\xa5\xa5\xa7\xa5\xa9\xa5" .
+                "\xc3\xa5\xe3\xa5\xe5\xa5\xe7\xa5\xee\xa5\xf5\xa5\xf6\xa1\xa6\xa1\xbc" .
+                "\xa1\xb3\xa1\xb4\xa1\xaa\xa1\xf3\xa1\xcb\xa1\xa4\xa1\xa5\xa1\xa7\xa1" .
+                "\xa8\xa1\xa9\xa1\xcf\xa1\xd1";
+            $no_end = "\x5c\x24\x28\x5b\x7b\xa1\xf2\x5c\xa1\xc6\xa1\xc8\xa1\xd2\xa1" .
+                "\xd4\xa1\xd6\xa1\xd8\xa1\xda\xa1\xcc\xa1\xf0\xa1\xca\xa1\xce\xa1\xd0\xa1\xef";
+            $wrap = func_get_arg(2);
+            
+            if (strlen($ret) >= $wrap && 
+                substr($ret, 0, 1) != '>' &&
+                strpos($ret, 'http://') === FALSE &&
+                strpos($ret, 'https://') === FALSE &&
+                strpos($ret, 'ftp://') === FALSE) {
+                
+                $ret = mb_convert_kana($ret, "KV");
+
+                $line_new = '';
+                $ptr = 0;
+                
+                while ($ptr < strlen($ret) - 1) {
+                    $l = mb_strcut($ret, $ptr, $wrap);
+                    $ptr += strlen($l);
+                    $tmp = $l;
+                    
+                    $l = mb_strcut($ret, $ptr, 2);
+                    while (strlen($l) != 0 && mb_strpos($no_begin, $l) !== FALSE ) {
+                        $tmp .= $l;
+                        $ptr += strlen($l);
+                        $l = mb_strcut($ret, $ptr, 1);
+                    }
+                    $line_new .= $tmp;
+                    if ($ptr < strlen($ret) - 1)
+                        $line_new .= "\n";
+                }
+                $ret = $line_new;
+            }
+            break;
+        case 'utf7-imap_encode':
+            $ret = mb_convert_encoding($ret, 'UTF7-IMAP', 'EUC-JP');
+            break;
+        case 'utf7-imap_decode':
+            $ret = mb_convert_encoding($ret, 'EUC-JP', 'UTF7-IMAP');
+            break;
         }
     }
     return $ret;
@@ -1166,4 +1605,4 @@ function korean_charset_xtra() {
     return $ret;
 }
 
-?>
+?>
\ No newline at end of file