X-Git-Url: https://vcs.fsf.org/?a=blobdiff_plain;f=functions%2Fi18n.php;h=77a6abe61a399898d829ffe47569efb6011867be;hb=1c9787d6f621a437859d7a2a3924a63d580e8be0;hp=e0375e651d28fcae6edc776ab58b25e53900b2c8;hpb=a5970d71e3c1a8409dbd12ff933869db038e2433;p=squirrelmail.git

diff --git a/functions/i18n.php b/functions/i18n.php
index e0375e65..77a6abe6 100644
--- a/functions/i18n.php
+++ b/functions/i18n.php
@@ -1,9 +1,9 @@
 <?php
 
 /**
- * i18n.php
+ * SquirrelMail internationalization functions
  *
- * 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
@@ -12,19 +12,27 @@
  * 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 $string Text to be decoded
- * @return string Decoded text
+ * @return string decoded string
  */
 function charset_decode ($charset, $string) {
     global $languages, $squirrelmail_language, $default_charset;
@@ -41,7 +49,7 @@ function charset_decode ($charset, $string) {
 
     // Variables that allow to use functions without function_exist() calls
     if (! isset($use_php_recode) || $use_php_recode=="" ) {
-	     $use_php_recode=false; }
+      $use_php_recode=false; }
     if (! isset($use_php_iconv) || $use_php_iconv=="" ) {
          $use_php_iconv=false; }
 
@@ -60,15 +68,15 @@ function charset_decode ($charset, $string) {
      */
     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);
+        // 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("'", '&#039;', $string);
-	return $string;
+        $string = recode_string($charset . "..html",$string);
+        // recode does not convert single quote, htmlspecialchars does.
+        $string = str_replace("'", '&#039;', $string);
+        return $string;
       }
     }
 
@@ -88,187 +96,100 @@ function charset_decode ($charset, $string) {
     if (! isset($agresive_decoding) || $agresive_decoding=="" ) {
          $agresive_decoding=false; }
 
-    if (ereg('iso-8859-([[:digit:]]+)', $charset, $res)) {
-        if ($res[1] == '1') {
-	    include_once(SM_PATH . 'functions/decode/iso8859-1.php');
-            $ret = charset_decode_iso8859_1 ($string);
-        } else if ($res[1] == '2') {
-	    include_once(SM_PATH . 'functions/decode/iso8859-2.php');
-            $ret = charset_decode_iso8859_2 ($string);
-        } else if ($res[1] == '3') {
-	    include_once(SM_PATH . 'functions/decode/iso8859-3.php');
-            $ret = charset_decode_iso8859_3 ($string);
-        } else if ($res[1] == '4') {
-	    include_once(SM_PATH . 'functions/decode/iso8859-4.php');
-            $ret = charset_decode_iso8859_4 ($string);
-        } else if ($res[1] == '5') {
-	    include_once(SM_PATH . 'functions/decode/iso8859-5.php');
-            $ret = charset_decode_iso8859_5 ($string);
-        } else if ($res[1] == '6') {
-	    include_once(SM_PATH . 'functions/decode/iso8859-6.php');
-            $ret = charset_decode_iso8859_6 ($string);
-        } else if ($res[1] == '7') {
-	    include_once(SM_PATH . 'functions/decode/iso8859-7.php');
-            $ret = charset_decode_iso8859_7 ($string);
-        } else if ($res[1] == '8') {
-	    include_once(SM_PATH . 'functions/decode/iso8859-8.php');
-            $ret = charset_decode_iso8859_8 ($string);
-        } else if ($res[1] == '9') {
-	    include_once(SM_PATH . 'functions/decode/iso8859-9.php');
-            $ret = charset_decode_iso8859_9 ($string);
-        } else if ($res[1] == '10') {
-	    include_once(SM_PATH . 'functions/decode/iso8859-10.php');
-            $ret = charset_decode_iso8859_10 ($string);
-        } else if ($res[1] == '11') {
-	    include_once(SM_PATH . 'functions/decode/iso8859-11.php');
-            $ret = charset_decode_iso8859_11 ($string);
-        } else if ($res[1] == '13') {
-	    include_once(SM_PATH . 'functions/decode/iso8859-13.php');
-            $ret = charset_decode_iso8859_13 ($string);
-        } else if ($res[1] == '14') {
-	    include_once(SM_PATH . 'functions/decode/iso8859-14.php');
-            $ret = charset_decode_iso8859_14 ($string);
-        } else if ($res[1] == '15') {
-	    include_once(SM_PATH . 'functions/decode/iso8859-15.php');
-            $ret = charset_decode_iso8859_15 ($string);
-        } else if ($res[1] == '16') {
-	    include_once(SM_PATH . 'functions/decode/iso8859-16.php');
-            $ret = charset_decode_iso8859_16 ($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') {
-        include_once(SM_PATH . 'functions/decode/koi8-r.php');
-        $ret = charset_decode_koi8r ($string);
-    } else if ($charset == 'koi8-u') {
-        include_once(SM_PATH . 'functions/decode/koi8-u.php');
-        $ret = charset_decode_koi8u ($string);
-    } else if ($charset == 'windows-1250') {
-        include_once(SM_PATH . 'functions/decode/cp1250.php');
-        $ret = charset_decode_cp1250 ($string);
-    } else if ($charset == 'windows-1251') {
-        include_once(SM_PATH . 'functions/decode/cp1251.php');
-        $ret = charset_decode_cp1251 ($string);
-    } else if ($charset == 'windows-1252') {
-        include_once(SM_PATH . 'functions/decode/cp1252.php');
-        $ret = charset_decode_cp1252 ($string);
-    } else if ($charset == 'windows-1253') {
-        include_once(SM_PATH . 'functions/decode/cp1253.php');
-	$ret = charset_decode_cp1253 ($string);
-    } else if ($charset == 'windows-1254') {
-        include_once(SM_PATH . 'functions/decode/cp1254.php');
-	$ret = charset_decode_cp1254 ($string);
-    } else if ($charset == 'windows-1255') {
-        include_once(SM_PATH . 'functions/decode/cp1255.php');
-	$ret = charset_decode_cp1255 ($string);
-    } else if ($charset == 'windows-1256') {
-        include_once(SM_PATH . 'functions/decode/cp1256.php');
-	$ret = charset_decode_cp1256 ($string);
-    } else if ($charset == 'windows-1257') {
-        include_once(SM_PATH . 'functions/decode/cp1257.php');
-        $ret = charset_decode_cp1257 ($string);
-    } else if ($charset == 'windows-1258') {
-        include_once(SM_PATH . 'functions/decode/cp1258.php');
-        $ret = charset_decode_cp1258 ($string);
-    } else if ($charset == 'x-mac-roman') {
-        include_once(SM_PATH . 'functions/decode/cp10000.php');
-        $ret = charset_decode_cp10000 ($string);
-    } else if ($charset == 'x-mac-greek') {
-        include_once(SM_PATH . 'functions/decode/cp10006.php');
-        $ret = charset_decode_cp10006 ($string);
-    } else if ($charset == 'x-mac-cyrillic') {
-        include_once(SM_PATH . 'functions/decode/cp10007.php');
-        $ret = charset_decode_cp10007 ($string);
-    } else if ($charset == 'x-mac-ukrainian') {
-        include_once(SM_PATH . 'functions/decode/cp10017.php');
-        $ret = charset_decode_cp10017 ($string);
-    } else if ($charset == 'x-mac-centraleurroman') {
-        include_once(SM_PATH . 'functions/decode/cp10029.php');
-        $ret = charset_decode_cp10029 ($string);
-    } else if ($charset == 'x-mac-icelandic') {
-        include_once(SM_PATH . 'functions/decode/cp10079.php');
-        $ret = charset_decode_cp10079 ($string);
-    } else if ($charset == 'x-mac-turkish') {
-        include_once(SM_PATH . 'functions/decode/cp10081.php');
-        $ret = charset_decode_cp10081 ($string);
-    } else if ($charset == 'ibm855') {
-        include_once(SM_PATH . 'functions/decode/cp855.php');
-        $ret = charset_decode_cp855 ($string);
-    } else if ($charset == 'ibm866') {
-        include_once(SM_PATH . 'functions/decode/cp866.php');
-        $ret = charset_decode_cp866 ($string);
-    } else if ($charset == 'iso-ir-111') {
-        include_once(SM_PATH . 'functions/decode/iso-ir-111.php');
-        $ret = charset_decode_iso_ir_111 ($string);
-    } else if ($charset == 'tis-620') {
-        include_once(SM_PATH . 'functions/decode/tis620.php');
-        $ret = charset_decode_tis620 ($string);
-    } else if ($charset == 'big5' and $agresive_decoding ) {
-        include_once(SM_PATH . 'functions/decode/big5.php');
-        $ret = charset_decode_big5 ($string);
-    } else if ($charset == 'gb2312' and $agresive_decoding ) {
-        include_once(SM_PATH . 'functions/decode/gb2312.php');
-        $ret = charset_decode_gb2312 ($string);
-    } else if ($charset == 'utf-8' && $squirrelmail_language != 'ja_JP') {
-        include_once(SM_PATH . 'functions/decode/utf-8.php');
-	$ret = charset_decode_utf8 ($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;
+      $ret = $string;
     }
     return( $ret );
 }
 
-
-/* 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",
-                    "????????????????????????????????????????".
-                    "????????????????????????????????????????".
-                    "????????????????????????????????????????".
-                    "????????"));
-
+/**
+ * Converts html string to given charset
+ * @param string $string
+ * @param string $charset
+ * @param string 
+ */
+function charset_encode($string,$charset) {
+  global $default_charset;
+
+  $encode=fixcharset($charset);
+  $encodefile=SM_PATH . 'functions/encode/' . $encode . '.php';
+  if (file_exists($encodefile)) {
+    include_once($encodefile);
+    $ret = call_user_func('charset_encode_'.$encode, $string);
+  } else {
+    $ret = $string;
+  }
+  return( $ret );
 }
 
-/*
- * This is the same as ISO-646-NO and is used by some
- * Microsoft programs when sending Norwegian characters
+/**
+ * Combined decoding and encoding functions
+ *
+ * If conversion is done to charset different that utf-8, unsupported symbols
+ * will be replaced with question marks.
+ * @param string $in_charset initial charset
+ * @param string $string string that has to be converted
+ * @param string $out_charset final charset
+ * @return string converted string
  */
-function charset_decode_ns_4551_1 ($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 ($string, "[\\]{|}", "ÆØÅæøå");
+function charset_convert($in_charset,$string,$out_charset) {
+  $string=charset_decode($in_charset,$string);
+  $string=charset_encode($string,$out_charset);
+  return $string;
 }
 
+/**
+ * Makes charset name suitable for decoding cycles
+ *
+ * @param string $charset Name of charset
+ * @return string $charset Adjusted name of charset
+ */
+function fixcharset($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);
+
+    // 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);
+
+    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, $default = false) {
 
     static $SetupAlready = 0;
     global $use_gettext, $languages,
            $squirrelmail_language, $squirrelmail_default_language,
-           $sm_notAlias;
+           $sm_notAlias, $username, $data_dir;
 
     if ($SetupAlready) {
         return;
@@ -289,8 +210,7 @@ function set_up_language($sm_language, $do_search = false, $default = false) {
  
     // Catching removed translation
     // System reverts to English translation if user prefs contain translation
-    // that is not available in $languages array (admin removed directory
-    // with that translation)
+    // that is not available in $languages array
     if (!isset($languages[$sm_notAlias])) {
       $sm_notAlias="en_US";
     }
@@ -305,33 +225,63 @@ function set_up_language($sm_language, $do_search = false, $default = false) {
          isset($languages[$sm_notAlias]['CHARSET']) ) {
         bindtextdomain( 'squirrelmail', SM_PATH . 'locale/' );
         textdomain( 'squirrelmail' );
-	if (function_exists('bind_textdomain_codeset')) {
-            if ($sm_notAlias == 'ja_JP') {
-        	bind_textdomain_codeset ("squirrelmail", 'EUC-JP');
+        if (function_exists('bind_textdomain_codeset')) {
+          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;
-	}
+              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' ) != $longlocale ) {
             putenv( "LC_ALL=$longlocale" );
             putenv( "LANG=$longlocale" );
             putenv( "LANGUAGE=$longlocale" );
         }
-	setlocale(LC_ALL, $longlocale);
-	$squirrelmail_language = $sm_notAlias;
+        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).");
-		// Revert to English link has to be added.
-		// stop further execution in order not to get php errors on mb_internal_encoding().
-		return;
+              // 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 $error;
             }
             if (function_exists('mb_language')) {
                 mb_language('Japanese');
@@ -342,19 +292,25 @@ function set_up_language($sm_language, $do_search = false, $default = false) {
         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, $username, 'language');
@@ -382,103 +338,145 @@ if (! isset($squirrelmail_language)) {
     $squirrelmail_language = '';
 }
 
-/* This array specifies the available languages. */
+/**
+ * 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'] = '&#1041;&#1098;&#1083;&#1075;&#1072;&#1088;&#1089;&#1082;&#1080;';
 $languages['bg_BG']['CHARSET'] = 'windows-1251';
+$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'] = '&#268;e&scaron;tina';
 $languages['cs_CZ']['CHARSET'] = 'iso-8859-2';
+$languages['cs_CZ']['LOCALE']  = 'cs_CZ.ISO8859-2';
 $languages['cs']['ALIAS']      = 'cs_CZ';
 
 $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']    = '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';
 
 $languages['el_GR']['NAME']    = 'Greek';
 $languages['el_GR']['ALTNAME'] = '&Epsilon;&lambda;&lambda;&eta;&nu;&iota;&kappa;&#940;';
 $languages['el_GR']['CHARSET'] = 'iso-8859-7';
+$languages['el_GR']['LOCALE']  = 'el_GR.ISO8859-7';
 $languages['el']['ALIAS'] = 'el_GR';
 
-// There is no en_EN! There is en_US, en_BR, en_AU, and so forth, 
-// but who cares about !US, right? Right? :)
+$languages['en_GB']['NAME']    = 'British';
+$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'] = 'Espa&ntilde;ol';
 $languages['es_ES']['CHARSET'] = 'iso-8859-1';
+$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'] = 'Fran&#231;ais';
 $languages['fr_FR']['CHARSET'] = 'iso-8859-1';
+$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']    = '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'] = '&Iacute;slenska';
 $languages['is_IS']['CHARSET'] = 'iso-8859-1';
+$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'] = '&#26085;&#26412;&#35486;';
 $languages['ja_JP']['CHARSET'] = 'iso-2022-jp';
+$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']['XTRA_CODE'] = 'korean_charset_xtra';
+$languages['ko_KR']['LOCALE']  = 'ko_KR.EUC-KR';
+// Function does not provide all needed options
+// $languages['ko_KR']['XTRA_CODE'] = 'korean_charset_xtra';
 $languages['ko']['ALIAS'] = 'ko_KR';
 
 $languages['lt_LT']['NAME']    = 'Lithuanian';
@@ -490,92 +488,115 @@ $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['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';
 
-$languages['no_NO']['NAME']    = 'Norwegian (Bokm&aring;l)';
-$languages['no_NO']['ALTNAME'] = 'Norsk (Bokm&aring;l)';
-$languages['no_NO']['CHARSET'] = 'iso-8859-1';
-$languages['no']['ALIAS'] = 'no_NO';
+$languages['nb_NO']['NAME']    = 'Norwegian (Bokm&aring;l)';
+$languages['nb_NO']['ALTNAME'] = 'Norsk (Bokm&aring;l)';
+$languages['nb_NO']['CHARSET'] = 'iso-8859-1';
+$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'] = 'Portugu&ecirc;s do Brasil';
 $languages['pt_BR']['CHARSET'] = 'iso-8859-1';
+$languages['pt_BR']['LOCALE']  = 'pt_BR.ISO8859-1';
 
 $languages['ro_RO']['NAME']    = 'Romanian';
 $languages['ro_RO']['ALTNAME'] = 'Rom&acirc;n&#259;';
 $languages['ro_RO']['CHARSET'] = 'iso-8859-2';
+$languages['ro_RO']['LOCALE']  = 'ro_RO.ISO8859-2';
 $languages['ro']['ALIAS'] = 'ro_RO';
 
 $languages['ru_RU']['NAME']    = 'Russian';
 $languages['ru_RU']['ALTNAME'] = '&#1056;&#1091;&#1089;&#1089;&#1082;&#1080;&#1081;';
 $languages['ru_RU']['CHARSET'] = 'utf-8';
-$languages['ru_RU']['LOCALE'] = 'ru_RU.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';
-$languages['sk']['ALIAS']       = 'sk_SK';
+$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'] = 'Sloven&scaron;&#269;ina';
 $languages['sl_SI']['CHARSET'] = 'iso-8859-2';
+$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['uk_UA']['NAME']    = 'Ukrainian';
 $languages['uk_UA']['CHARSET'] = 'koi8-u';
+$languages['uk_UA']['LOCALE']  = 'uk_UA.KOI8-U';
 $languages['uk']['ALIAS'] = 'uk_UA';
-*/
+
+$languages['ru_UA']['NAME']    = 'Russian (Ukrainian)';
+$languages['ru_UA']['CHARSET'] = 'koi8-r';
+$languages['ru_UA']['LOCALE']  = 'ru_UA.KOI8-R';
+
 /*
-if ( file_exists( SM_PATH . 'locale/vi_VN') ) {
-    $languages['vi_VN']['NAME']    = 'Vietnamese';
-    $languages['vi_VN']['CHARSET'] = 'utf-8';
-    $languages['vi']['ALIAS'] = 'vi_VN';
-}
+$languages['vi_VN']['NAME']    = 'Vietnamese';
+$languages['vi_VN']['CHARSET'] = 'utf-8';
+$languages['vi']['ALIAS'] = 'vi_VN';
 */
 
 // Right to left languages
@@ -583,8 +604,15 @@ $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';
 
@@ -611,16 +639,28 @@ elseif ($gettext_flags == 0) {
 } else {
     /* Uh-ho.  A weird install */
     if (! $gettext_flags & 1) {
+      /**
+       * Function is used as replacement in broken installs
+       * @ignore
+       */
         function _($str) {
             return $str;
         }
     }
     if (! $gettext_flags & 2) {
+      /**
+       * Function is used as replacement in broken installs
+       * @ignore
+       */
         function bindtextdomain() {
             return;
         }
     }
     if (! $gettext_flags & 4) {
+      /**
+       * Function is used as replacemet in broken installs
+       * @ignore
+       */
         function textdomain() {
             return;
         }
@@ -628,9 +668,25 @@ elseif ($gettext_flags == 0) {
 }
 
 
-/*
+/**
  * 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 */
@@ -759,9 +815,16 @@ function japanese_charset_xtra() {
 }
 
 
-/*
- * 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() {
     
@@ -782,7 +845,6 @@ function korean_charset_xtra() {
         }
 
     }
-
     return $ret;
 }
 
@@ -859,30 +921,30 @@ function is_conversion_safe($input_charset) {
 switch ($default_charset):
 case "windows-1251":
       if ( $input_charset == "iso-8859-5" || 
-	   $input_charset == "koi8-r" ||
-	   $input_charset == "koi8-u" ) {
+           $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" ) {
+       $input_charset == "iso-8859-4" ) {
     return true;
   } else {
     return false;
   }
 case "iso-8859-4":
   if ( $input_charset == "iso-8859-13" || 
-	 $input_charset == "windows-1257" ) {
+       $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" ) {
+       $input_charset == "koi8-r" || 
+       $input_charset == "koi8-u" ) {
      return true;
   } else {
      return false;
@@ -896,16 +958,16 @@ case "iso-8859-13":
   }
 case "koi8-r":
   if ( $input_charset == "windows-1251" ||
-	 $input_charset == "iso-8859-5" || 
-	 $input_charset == "koi8-u" ) {
+       $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" ) {
+       $input_charset == "iso-8859-5" ||
+       $input_charset == "koi8-r" ) {
      return true;
   } else {
      return false;
@@ -914,4 +976,4 @@ default:
    return false;
 endswitch;
 }
-?>
+?>
\ No newline at end of file