source: documentation/trunk/packages/dokuwiki-2011-05-25a/inc/utf8.php@ 30098

<?php
/**
 * UTF8 helper functions
 *
 * @license    LGPL 2.1 (http://www.gnu.org/copyleft/lesser.html)
 * @author     Andreas Gohr <[email protected]>
 */

/**
 * check for mb_string support
 */
if(!defined('UTF8_MBSTRING')){
    if(function_exists('mb_substr') && !defined('UTF8_NOMBSTRING')){
        define('UTF8_MBSTRING',1);
    }else{
        define('UTF8_MBSTRING',0);
    }
}

if(UTF8_MBSTRING){ mb_internal_encoding('UTF-8'); }

if(!function_exists('utf8_isASCII')){
    /**
     * Checks if a string contains 7bit ASCII only
     *
     * @author Andreas Haerter <[email protected]>
     */
    function utf8_isASCII($str){
        return (preg_match('/(?:[^\x00-\x7F])/', $str) !== 1);
    }
}

if(!function_exists('utf8_strip')){
    /**
     * Strips all highbyte chars
     *
     * Returns a pure ASCII7 string
     *
     * @author Andreas Gohr <[email protected]>
     */
    function utf8_strip($str){
        $ascii = '';
        $len = strlen($str);
        for($i=0; $i<$len; $i++){
            if(ord($str{$i}) <128){
                $ascii .= $str{$i};
            }
        }
        return $ascii;
    }
}

if(!function_exists('utf8_check')){
    /**
     * Tries to detect if a string is in Unicode encoding
     *
     * @author <[email protected]>
     * @link   http://www.php.net/manual/en/function.utf8-encode.php
     */
    function utf8_check($Str) {
        $len = strlen($Str);
        for ($i=0; $i<$len; $i++) {
            $b = ord($Str[$i]);
            if ($b < 0x80) continue; # 0bbbbbbb
            elseif (($b & 0xE0) == 0xC0) $n=1; # 110bbbbb
            elseif (($b & 0xF0) == 0xE0) $n=2; # 1110bbbb
            elseif (($b & 0xF8) == 0xF0) $n=3; # 11110bbb
            elseif (($b & 0xFC) == 0xF8) $n=4; # 111110bb
            elseif (($b & 0xFE) == 0xFC) $n=5; # 1111110b
            else return false; # Does not match any model

            for ($j=0; $j<$n; $j++) { # n bytes matching 10bbbbbb follow ?
                if ((++$i == $len) || ((ord($Str[$i]) & 0xC0) != 0x80))
                    return false;
            }
        }
        return true;
    }
}

if(!function_exists('utf8_strlen')){
    /**
     * Unicode aware replacement for strlen()
     *
     * utf8_decode() converts characters that are not in ISO-8859-1
     * to '?', which, for the purpose of counting, is alright - It's
     * even faster than mb_strlen.
     *
     * @author <chernyshevsky at hotmail dot com>
     * @see    strlen()
     * @see    utf8_decode()
     */
    function utf8_strlen($string){
        return strlen(utf8_decode($string));
    }
}

if(!function_exists('utf8_substr')){
    /**
     * UTF-8 aware alternative to substr
     *
     * Return part of a string given character offset (and optionally length)
     *
     * @author Harry Fuecks <[email protected]>
     * @author Chris Smith <[email protected]>
     * @param string
     * @param integer number of UTF-8 characters offset (from left)
     * @param integer (optional) length in UTF-8 characters from offset
     * @return mixed string or false if failure
     */
    function utf8_substr($str, $offset, $length = null) {
        if(UTF8_MBSTRING){
            if( $length === null ){
                return mb_substr($str, $offset);
            }else{
                return mb_substr($str, $offset, $length);
            }
        }

        /*
         * Notes:
         *
         * no mb string support, so we'll use pcre regex's with 'u' flag
         * pcre only supports repetitions of less than 65536, in order to accept up to MAXINT values for
         * offset and length, we'll repeat a group of 65535 characters when needed (ok, up to MAXINT-65536)
         *
         * substr documentation states false can be returned in some cases (e.g. offset > string length)
         * mb_substr never returns false, it will return an empty string instead.
         *
         * calculating the number of characters in the string is a relatively expensive operation, so
         * we only carry it out when necessary. It isn't necessary for +ve offsets and no specified length
         */

        // cast parameters to appropriate types to avoid multiple notices/warnings
        $str = (string)$str;                          // generates E_NOTICE for PHP4 objects, but not PHP5 objects
        $offset = (int)$offset;
        if (!is_null($length)) $length = (int)$length;

        // handle trivial cases
        if ($length === 0) return '';
        if ($offset < 0 && $length < 0 && $length < $offset) return '';

        $offset_pattern = '';
        $length_pattern = '';

        // normalise -ve offsets (we could use a tail anchored pattern, but they are horribly slow!)
        if ($offset < 0) {
            $strlen = strlen(utf8_decode($str));        // see notes
            $offset = $strlen + $offset;
            if ($offset < 0) $offset = 0;
        }

        // establish a pattern for offset, a non-captured group equal in length to offset
        if ($offset > 0) {
            $Ox = (int)($offset/65535);
            $Oy = $offset%65535;

            if ($Ox) $offset_pattern = '(?:.{65535}){'.$Ox.'}';
            $offset_pattern = '^(?:'.$offset_pattern.'.{'.$Oy.'})';
        } else {
            $offset_pattern = '^';                      // offset == 0; just anchor the pattern
        }

        // establish a pattern for length
        if (is_null($length)) {
            $length_pattern = '(.*)$';                  // the rest of the string
        } else {

            if (!isset($strlen)) $strlen = strlen(utf8_decode($str));    // see notes
            if ($offset > $strlen) return '';           // another trivial case

            if ($length > 0) {

                $length = min($strlen-$offset, $length);  // reduce any length that would go passed the end of the string

                $Lx = (int)($length/65535);
                $Ly = $length%65535;

                // +ve length requires ... a captured group of length characters
                if ($Lx) $length_pattern = '(?:.{65535}){'.$Lx.'}';
                    $length_pattern = '('.$length_pattern.'.{'.$Ly.'})';

            } else if ($length < 0) {

                if ($length < ($offset - $strlen)) return '';

                $Lx = (int)((-$length)/65535);
                $Ly = (-$length)%65535;

                // -ve length requires ... capture everything except a group of -length characters
                //                         anchored at the tail-end of the string
                if ($Lx) $length_pattern = '(?:.{65535}){'.$Lx.'}';
                $length_pattern = '(.*)(?:'.$length_pattern.'.{'.$Ly.'})$';
            }
        }

        if (!preg_match('#'.$offset_pattern.$length_pattern.'#us',$str,$match)) return '';
        return $match[1];
    }
}

if(!function_exists('utf8_substr_replace')){
    /**
     * Unicode aware replacement for substr_replace()
     *
     * @author Andreas Gohr <[email protected]>
     * @see    substr_replace()
     */
    function utf8_substr_replace($string, $replacement, $start , $length=0 ){
        $ret = '';
        if($start>0) $ret .= utf8_substr($string, 0, $start);
        $ret .= $replacement;
        $ret .= utf8_substr($string, $start+$length);
        return $ret;
    }
}

if(!function_exists('utf8_ltrim')){
    /**
     * Unicode aware replacement for ltrim()
     *
     * @author Andreas Gohr <[email protected]>
     * @see    ltrim()
     * @return string
     */
    function utf8_ltrim($str,$charlist=''){
        if($charlist == '') return ltrim($str);

        //quote charlist for use in a characterclass
        $charlist = preg_replace('!([\\\\\\-\\]\\[/])!','\\\${1}',$charlist);

        return preg_replace('/^['.$charlist.']+/u','',$str);
    }
}

if(!function_exists('utf8_rtrim')){
    /**
     * Unicode aware replacement for rtrim()
     *
     * @author Andreas Gohr <[email protected]>
     * @see    rtrim()
     * @return string
     */
    function  utf8_rtrim($str,$charlist=''){
        if($charlist == '') return rtrim($str);

        //quote charlist for use in a characterclass
        $charlist = preg_replace('!([\\\\\\-\\]\\[/])!','\\\${1}',$charlist);

        return preg_replace('/['.$charlist.']+$/u','',$str);
    }
}

if(!function_exists('utf8_trim')){
    /**
     * Unicode aware replacement for trim()
     *
     * @author Andreas Gohr <[email protected]>
     * @see    trim()
     * @return string
     */
    function  utf8_trim($str,$charlist='') {
        if($charlist == '') return trim($str);

        return utf8_ltrim(utf8_rtrim($str,$charlist),$charlist);
    }
}

if(!function_exists('utf8_strtolower')){
    /**
     * This is a unicode aware replacement for strtolower()
     *
     * Uses mb_string extension if available
     *
     * @author Leo Feyer <[email protected]>
     * @see    strtolower()
     * @see    utf8_strtoupper()
     */
    function utf8_strtolower($string){
        if(UTF8_MBSTRING) return mb_strtolower($string,'utf-8');

        global $UTF8_UPPER_TO_LOWER;
        return strtr($string,$UTF8_UPPER_TO_LOWER);
    }
}

if(!function_exists('utf8_strtoupper')){
    /**
     * This is a unicode aware replacement for strtoupper()
     *
     * Uses mb_string extension if available
     *
     * @author Leo Feyer <[email protected]>
     * @see    strtoupper()
     * @see    utf8_strtoupper()
     */
    function utf8_strtoupper($string){
        if(UTF8_MBSTRING) return mb_strtoupper($string,'utf-8');

        global $UTF8_LOWER_TO_UPPER;
        return strtr($string,$UTF8_LOWER_TO_UPPER);
    }
}

if(!function_exists('utf8_ucfirst')){
    /**
     * UTF-8 aware alternative to ucfirst
     * Make a string's first character uppercase
     *
     * @author Harry Fuecks
     * @param string
     * @return string with first character as upper case (if applicable)
     */
    function utf8_ucfirst($str){
        switch ( utf8_strlen($str) ) {
            case 0:
                return '';
            case 1:
                return utf8_strtoupper($str);
            default:
                preg_match('/^(.{1})(.*)$/us', $str, $matches);
                return utf8_strtoupper($matches[1]).$matches[2];
        }
    }
}

if(!function_exists('utf8_ucwords')){
    /**
     * UTF-8 aware alternative to ucwords
     * Uppercase the first character of each word in a string
     *
     * @author Harry Fuecks
     * @param string
     * @return string with first char of each word uppercase
     * @see http://www.php.net/ucwords
     */
    function utf8_ucwords($str) {
        // Note: [\x0c\x09\x0b\x0a\x0d\x20] matches;
        // form feeds, horizontal tabs, vertical tabs, linefeeds and carriage returns
        // This corresponds to the definition of a "word" defined at http://www.php.net/ucwords
        $pattern = '/(^|([\x0c\x09\x0b\x0a\x0d\x20]+))([^\x0c\x09\x0b\x0a\x0d\x20]{1})[^\x0c\x09\x0b\x0a\x0d\x20]*/u';

        return preg_replace_callback($pattern, 'utf8_ucwords_callback',$str);
    }

    /**
     * Callback function for preg_replace_callback call in utf8_ucwords
     * You don't need to call this yourself
     *
     * @author Harry Fuecks
     * @param array of matches corresponding to a single word
     * @return string with first char of the word in uppercase
     * @see utf8_ucwords
     * @see utf8_strtoupper
     */
    function utf8_ucwords_callback($matches) {
        $leadingws = $matches[2];
        $ucfirst = utf8_strtoupper($matches[3]);
        $ucword = utf8_substr_replace(ltrim($matches[0]),$ucfirst,0,1);
        return $leadingws . $ucword;
    }
}

if(!function_exists('utf8_deaccent')){
    /**
     * Replace accented UTF-8 characters by unaccented ASCII-7 equivalents
     *
     * Use the optional parameter to just deaccent lower ($case = -1) or upper ($case = 1)
     * letters. Default is to deaccent both cases ($case = 0)
     *
     * @author Andreas Gohr <[email protected]>
     */
    function utf8_deaccent($string,$case=0){
        if($case <= 0){
            global $UTF8_LOWER_ACCENTS;
            $string = strtr($string,$UTF8_LOWER_ACCENTS);
        }
        if($case >= 0){
            global $UTF8_UPPER_ACCENTS;
            $string = strtr($string,$UTF8_UPPER_ACCENTS);
        }
        return $string;
    }
}

if(!function_exists('utf8_romanize')){
    /**
     * Romanize a non-latin string
     *
     * @author Andreas Gohr <[email protected]>
     */
    function utf8_romanize($string){
        if(utf8_isASCII($string)) return $string; //nothing to do

        global $UTF8_ROMANIZATION;
        return strtr($string,$UTF8_ROMANIZATION);
    }
}

if(!function_exists('utf8_stripspecials')){
    /**
     * Removes special characters (nonalphanumeric) from a UTF-8 string
     *
     * This function adds the controlchars 0x00 to 0x19 to the array of
     * stripped chars (they are not included in $UTF8_SPECIAL_CHARS)
     *
     * @author Andreas Gohr <[email protected]>
     * @param  string $string     The UTF8 string to strip of special chars
     * @param  string $repl       Replace special with this string
     * @param  string $additional Additional chars to strip (used in regexp char class)
     */
    function utf8_stripspecials($string,$repl='',$additional=''){
        global $UTF8_SPECIAL_CHARS;
        global $UTF8_SPECIAL_CHARS2;

        static $specials = null;
        if(is_null($specials)){
            #$specials = preg_quote(unicode_to_utf8($UTF8_SPECIAL_CHARS), '/');
            $specials = preg_quote($UTF8_SPECIAL_CHARS2, '/');
        }

        return preg_replace('/['.$additional.'\x00-\x19'.$specials.']/u',$repl,$string);
    }
}

if(!function_exists('utf8_strpos')){
    /**
     * This is an Unicode aware replacement for strpos
     *
     * @author Leo Feyer <[email protected]>
     * @see    strpos()
     * @param  string
     * @param  string
     * @param  integer
     * @return integer
     */
    function utf8_strpos($haystack, $needle, $offset=0){
        $comp = 0;
        $length = null;

        while (is_null($length) || $length < $offset) {
            $pos = strpos($haystack, $needle, $offset + $comp);

            if ($pos === false)
                return false;

            $length = utf8_strlen(substr($haystack, 0, $pos));

            if ($length < $offset)
                $comp = $pos - $length;
        }

        return $length;
    }
}

if(!function_exists('utf8_tohtml')){
    /**
     * Encodes UTF-8 characters to HTML entities
     *
     * @author Tom N Harris <[email protected]>
     * @author <vpribish at shopping dot com>
     * @link   http://www.php.net/manual/en/function.utf8-decode.php
     */
    function utf8_tohtml ($str) {
        $ret = '';
        foreach (utf8_to_unicode($str) as $cp) {
            if ($cp < 0x80)
                $ret .= chr($cp);
            elseif ($cp < 0x100)
                $ret .= "&#$cp;";
            else
                $ret .= '&#x'.dechex($cp).';';
        }
        return $ret;
    }
}

if(!function_exists('utf8_unhtml')){
    /**
     * Decodes HTML entities to UTF-8 characters
     *
     * Convert any &#..; entity to a codepoint,
     * The entities flag defaults to only decoding numeric entities.
     * Pass HTML_ENTITIES and named entities, including &amp; &lt; etc.
     * are handled as well. Avoids the problem that would occur if you
     * had to decode "&amp;#38;&#38;amp;#38;"
     *
     * unhtmlspecialchars(utf8_unhtml($s)) -> "&#38;&#38;"
     * utf8_unhtml(unhtmlspecialchars($s)) -> "&&amp#38;"
     * what it should be                   -> "&#38;&amp#38;"
     *
     * @author Tom N Harris <[email protected]>
     * @param  string  $str      UTF-8 encoded string
     * @param  boolean $entities Flag controlling decoding of named entities.
     * @return UTF-8 encoded string with numeric (and named) entities replaced.
     */
    function utf8_unhtml($str, $entities=null) {
        static $decoder = null;
        if (is_null($decoder))
            $decoder = new utf8_entity_decoder();
        if (is_null($entities))
            return preg_replace_callback('/(&#([Xx])?([0-9A-Za-z]+);)/m',
                                         'utf8_decode_numeric', $str);
        else
            return preg_replace_callback('/&(#)?([Xx])?([0-9A-Za-z]+);/m',
                                         array(&$decoder, 'decode'), $str);
    }
}

if(!function_exists('utf8_decode_numeric')){
    function utf8_decode_numeric($ent) {
        switch ($ent[2]) {
            case 'X':
            case 'x':
                $cp = hexdec($ent[3]);
                break;
            default:
                $cp = intval($ent[3]);
                break;
        }
        return unicode_to_utf8(array($cp));
    }
}

if(!class_exists('utf8_entity_decoder')){
    class utf8_entity_decoder {
        var $table;
        function utf8_entity_decoder() {
            $table = get_html_translation_table(HTML_ENTITIES);
            $table = array_flip($table);
            $this->table = array_map(array(&$this,'makeutf8'), $table);
        }
        function makeutf8($c) {
            return unicode_to_utf8(array(ord($c)));
        }
        function decode($ent) {
            if ($ent[1] == '#') {
                return utf8_decode_numeric($ent);
            } elseif (array_key_exists($ent[0],$this->table)) {
                return $this->table[$ent[0]];
            } else {
                return $ent[0];
            }
        }
    }
}

if(!function_exists('utf8_to_unicode')){
    /**
     * Takes an UTF-8 string and returns an array of ints representing the
     * Unicode characters. Astral planes are supported ie. the ints in the
     * output can be > 0xFFFF. Occurrances of the BOM are ignored. Surrogates
     * are not allowed.
     *
     * If $strict is set to true the function returns false if the input
     * string isn't a valid UTF-8 octet sequence and raises a PHP error at
     * level E_USER_WARNING
     *
     * Note: this function has been modified slightly in this library to
     * trigger errors on encountering bad bytes
     *
     * @author <[email protected]>
     * @author Harry Fuecks <[email protected]>
     * @param  string  UTF-8 encoded string
     * @param  boolean Check for invalid sequences?
     * @return mixed array of unicode code points or false if UTF-8 invalid
     * @see    unicode_to_utf8
     * @link   http://hsivonen.iki.fi/php-utf8/
     * @link   http://sourceforge.net/projects/phputf8/
     */
    function utf8_to_unicode($str,$strict=false) {
        $mState = 0;     // cached expected number of octets after the current octet
                         // until the beginning of the next UTF8 character sequence
        $mUcs4  = 0;     // cached Unicode character
        $mBytes = 1;     // cached expected number of octets in the current sequence

        $out = array();

        $len = strlen($str);

        for($i = 0; $i < $len; $i++) {

            $in = ord($str{$i});

            if ( $mState == 0) {

                // When mState is zero we expect either a US-ASCII character or a
                // multi-octet sequence.
                if (0 == (0x80 & ($in))) {
                    // US-ASCII, pass straight through.
                    $out[] = $in;
                    $mBytes = 1;

                } else if (0xC0 == (0xE0 & ($in))) {
                    // First octet of 2 octet sequence
                    $mUcs4 = ($in);
                    $mUcs4 = ($mUcs4 & 0x1F) << 6;
                    $mState = 1;
                    $mBytes = 2;

                } else if (0xE0 == (0xF0 & ($in))) {
                    // First octet of 3 octet sequence
                    $mUcs4 = ($in);
                    $mUcs4 = ($mUcs4 & 0x0F) << 12;
                    $mState = 2;
                    $mBytes = 3;

                } else if (0xF0 == (0xF8 & ($in))) {
                    // First octet of 4 octet sequence
                    $mUcs4 = ($in);
                    $mUcs4 = ($mUcs4 & 0x07) << 18;
                    $mState = 3;
                    $mBytes = 4;

                } else if (0xF8 == (0xFC & ($in))) {
                    /* First octet of 5 octet sequence.
                     *
                     * This is illegal because the encoded codepoint must be either
                     * (a) not the shortest form or
                     * (b) outside the Unicode range of 0-0x10FFFF.
                     * Rather than trying to resynchronize, we will carry on until the end
                     * of the sequence and let the later error handling code catch it.
                     */
                    $mUcs4 = ($in);
                    $mUcs4 = ($mUcs4 & 0x03) << 24;
                    $mState = 4;
                    $mBytes = 5;

                } else if (0xFC == (0xFE & ($in))) {
                    // First octet of 6 octet sequence, see comments for 5 octet sequence.
                    $mUcs4 = ($in);
                    $mUcs4 = ($mUcs4 & 1) << 30;
                    $mState = 5;
                    $mBytes = 6;

                } elseif($strict) {
                    /* Current octet is neither in the US-ASCII range nor a legal first
                     * octet of a multi-octet sequence.
                     */
                    trigger_error(
                            'utf8_to_unicode: Illegal sequence identifier '.
                                'in UTF-8 at byte '.$i,
                            E_USER_WARNING
                        );
                    return false;

                }

            } else {

                // When mState is non-zero, we expect a continuation of the multi-octet
                // sequence
                if (0x80 == (0xC0 & ($in))) {

                    // Legal continuation.
                    $shift = ($mState - 1) * 6;
                    $tmp = $in;
                    $tmp = ($tmp & 0x0000003F) << $shift;
                    $mUcs4 |= $tmp;

                    /**
                     * End of the multi-octet sequence. mUcs4 now contains the final
                     * Unicode codepoint to be output
                     */
                    if (0 == --$mState) {

                        /*
                         * Check for illegal sequences and codepoints.
                         */
                        // From Unicode 3.1, non-shortest form is illegal
                        if (((2 == $mBytes) && ($mUcs4 < 0x0080)) ||
                            ((3 == $mBytes) && ($mUcs4 < 0x0800)) ||
                            ((4 == $mBytes) && ($mUcs4 < 0x10000)) ||
                            (4 < $mBytes) ||
                            // From Unicode 3.2, surrogate characters are illegal
                            (($mUcs4 & 0xFFFFF800) == 0xD800) ||
                            // Codepoints outside the Unicode range are illegal
                            ($mUcs4 > 0x10FFFF)) {

                            if($strict){
                                trigger_error(
                                        'utf8_to_unicode: Illegal sequence or codepoint '.
                                            'in UTF-8 at byte '.$i,
                                        E_USER_WARNING
                                    );

                                return false;
                            }

                        }

                        if (0xFEFF != $mUcs4) {
                            // BOM is legal but we don't want to output it
                            $out[] = $mUcs4;
                        }

                        //initialize UTF8 cache
                        $mState = 0;
                        $mUcs4  = 0;
                        $mBytes = 1;
                    }

                } elseif($strict) {
                    /**
                     *((0xC0 & (*in) != 0x80) && (mState != 0))
                     * Incomplete multi-octet sequence.
                     */
                    trigger_error(
                            'utf8_to_unicode: Incomplete multi-octet '.
                            '   sequence in UTF-8 at byte '.$i,
                            E_USER_WARNING
                        );

                    return false;
                }
            }
        }
        return $out;
    }
}

if(!function_exists('unicode_to_utf8')){
    /**
     * Takes an array of ints representing the Unicode characters and returns
     * a UTF-8 string. Astral planes are supported ie. the ints in the
     * input can be > 0xFFFF. Occurrances of the BOM are ignored. Surrogates
     * are not allowed.
     *
     * If $strict is set to true the function returns false if the input
     * array contains ints that represent surrogates or are outside the
     * Unicode range and raises a PHP error at level E_USER_WARNING
     *
     * Note: this function has been modified slightly in this library to use
     * output buffering to concatenate the UTF-8 string (faster) as well as
     * reference the array by it's keys
     *
     * @param  array of unicode code points representing a string
     * @param  boolean Check for invalid sequences?
     * @return mixed UTF-8 string or false if array contains invalid code points
     * @author <[email protected]>
     * @author Harry Fuecks <[email protected]>
     * @see    utf8_to_unicode
     * @link   http://hsivonen.iki.fi/php-utf8/
     * @link   http://sourceforge.net/projects/phputf8/
     */
    function unicode_to_utf8($arr,$strict=false) {
        if (!is_array($arr)) return '';
        ob_start();

        foreach (array_keys($arr) as $k) {

            if ( ($arr[$k] >= 0) && ($arr[$k] <= 0x007f) ) {
                # ASCII range (including control chars)

                echo chr($arr[$k]);

            } else if ($arr[$k] <= 0x07ff) {
                # 2 byte sequence

                echo chr(0xc0 | ($arr[$k] >> 6));
                echo chr(0x80 | ($arr[$k] & 0x003f));

            } else if($arr[$k] == 0xFEFF) {
                # Byte order mark (skip)

                // nop -- zap the BOM

            } else if ($arr[$k] >= 0xD800 && $arr[$k] <= 0xDFFF) {
                # Test for illegal surrogates

                // found a surrogate
                if($strict){
                    trigger_error(
                        'unicode_to_utf8: Illegal surrogate '.
                            'at index: '.$k.', value: '.$arr[$k],
                        E_USER_WARNING
                        );
                    return false;
                }

            } else if ($arr[$k] <= 0xffff) {
                # 3 byte sequence

                echo chr(0xe0 | ($arr[$k] >> 12));
                echo chr(0x80 | (($arr[$k] >> 6) & 0x003f));
                echo chr(0x80 | ($arr[$k] & 0x003f));

            } else if ($arr[$k] <= 0x10ffff) {
                # 4 byte sequence

                echo chr(0xf0 | ($arr[$k] >> 18));
                echo chr(0x80 | (($arr[$k] >> 12) & 0x3f));
                echo chr(0x80 | (($arr[$k] >> 6) & 0x3f));
                echo chr(0x80 | ($arr[$k] & 0x3f));

            } elseif($strict) {

                trigger_error(
                    'unicode_to_utf8: Codepoint out of Unicode range '.
                        'at index: '.$k.', value: '.$arr[$k],
                    E_USER_WARNING
                    );

                // out of range
                return false;
            }
        }

        $result = ob_get_contents();
        ob_end_clean();
        return $result;
    }
}

if(!function_exists('utf8_to_utf16be')){
    /**
     * UTF-8 to UTF-16BE conversion.
     *
     * Maybe really UCS-2 without mb_string due to utf8_to_unicode limits
     */
    function utf8_to_utf16be(&$str, $bom = false) {
        $out = $bom ? "\xFE\xFF" : '';
        if(UTF8_MBSTRING) return $out.mb_convert_encoding($str,'UTF-16BE','UTF-8');

        $uni = utf8_to_unicode($str);
        foreach($uni as $cp){
            $out .= pack('n',$cp);
        }
        return $out;
    }
}

if(!function_exists('utf16be_to_utf8')){
    /**
     * UTF-8 to UTF-16BE conversion.
     *
     * Maybe really UCS-2 without mb_string due to utf8_to_unicode limits
     */
    function utf16be_to_utf8(&$str) {
        $uni = unpack('n*',$str);
        return unicode_to_utf8($uni);
    }
}

if(!function_exists('utf8_bad_replace')){
    /**
     * Replace bad bytes with an alternative character
     *
     * ASCII character is recommended for replacement char
     *
     * PCRE Pattern to locate bad bytes in a UTF-8 string
     * Comes from W3 FAQ: Multilingual Forms
     * Note: modified to include full ASCII range including control chars
     *
     * @author Harry Fuecks <[email protected]>
     * @see http://www.w3.org/International/questions/qa-forms-utf-8
     * @param string to search
     * @param string to replace bad bytes with (defaults to '?') - use ASCII
     * @return string
     */
    function utf8_bad_replace($str, $replace = '') {
        $UTF8_BAD =
         '([\x00-\x7F]'.                          # ASCII (including control chars)
         '|[\xC2-\xDF][\x80-\xBF]'.               # non-overlong 2-byte
         '|\xE0[\xA0-\xBF][\x80-\xBF]'.           # excluding overlongs
         '|[\xE1-\xEC\xEE\xEF][\x80-\xBF]{2}'.    # straight 3-byte
         '|\xED[\x80-\x9F][\x80-\xBF]'.           # excluding surrogates
         '|\xF0[\x90-\xBF][\x80-\xBF]{2}'.        # planes 1-3
         '|[\xF1-\xF3][\x80-\xBF]{3}'.            # planes 4-15
         '|\xF4[\x80-\x8F][\x80-\xBF]{2}'.        # plane 16
         '|(.{1}))';                              # invalid byte
        ob_start();
        while (preg_match('/'.$UTF8_BAD.'/S', $str, $matches)) {
            if ( !isset($matches[2])) {
                echo $matches[0];
            } else {
                echo $replace;
            }
            $str = substr($str,strlen($matches[0]));
        }
        $result = ob_get_contents();
        ob_end_clean();
        return $result;
    }
}

if(!function_exists('utf8_correctIdx')){
    /**
     * adjust a byte index into a utf8 string to a utf8 character boundary
     *
     * @param $str   string   utf8 character string
     * @param $i     int      byte index into $str
     * @param $next  bool     direction to search for boundary,
     *                           false = up (current character)
     *                           true = down (next character)
     *
     * @return int            byte index into $str now pointing to a utf8 character boundary
     *
     * @author       chris smith <[email protected]>
     */
    function utf8_correctIdx(&$str,$i,$next=false) {

        if ($i <= 0) return 0;

        $limit = strlen($str);
        if ($i>=$limit) return $limit;

        if ($next) {
            while (($i<$limit) && ((ord($str[$i]) & 0xC0) == 0x80)) $i++;
        } else {
            while ($i && ((ord($str[$i]) & 0xC0) == 0x80)) $i--;
        }

        return $i;
    }
}

// only needed if no mb_string available
if(!UTF8_MBSTRING){
    /**
     * UTF-8 Case lookup table
     *
     * This lookuptable defines the upper case letters to their correspponding
     * lower case letter in UTF-8
     *
     * @author Andreas Gohr <[email protected]>
     */
    global $UTF8_LOWER_TO_UPPER;
    if(empty($UTF8_LOWER_TO_UPPER)) $UTF8_LOWER_TO_UPPER = array(
            ""=>"",""=>"",""=>"",""=>"",""=>"",""=>"",""=>"",""=>"",""=>"",""=>"",
            ""=>"",""=>"",""=>"",""=>"",""=>"",""=>"",""=>"",""=>"",""=>"",""=>"",
            ""=>"","
"=>"",""=>"",""=>"",""=>"",""=>"","ῳ"=>"á¿Œ","á¿¥"=>"Ῥ","á¿¡"=>"á¿©","ῑ"=>"Ῑ",
            "ῐ"=>"Ῐ","ῃ"=>"ῌ","៟"=>"Ι","៳"=>"៌","៱"=>"៹","៰"=>"៞","៧"=>"៯","៊"=>"៮","៥"=>"៭","ៀ"=>"៬",
            "៣"=>"៫","២"=>"៪","១"=>"៩","ៗ"=>"៟","៖"=>"៞","៕"=>"៝","។"=>"ៜ","៓"=>"៛","្"=>"៚","៑"=>"៙",
            "័"=>"៘","ះ"=>"៏","ំ"=>"៎","ៅ
"=>"៍","ោ"=>"៌","ៃ"=>"់","ែ"=>"៊","េ"=>"៉","ៀ"=>"ៈ","᜜"=>"á¿»",
            "ᜌ"=>"Ὼ","᜻"=>"á¿«","᜺"=>"Ὺ","᜹"=>"Ό","᜞"=>"á¿ž","᜷"=>"Ί","᜶"=>"Ὶ","᜵"=>"Ή","ᜎ"=>"Ὴ","ᜳ"=>"Έ",
            "ᜲ"=>"Ὲ","ᜱ"=>"៻","ᜰ"=>"៺","ᜧ"=>"ᜯ","ᜊ"=>"ᜮ","ᜥ"=>"ᜭ","ᜀ"=>"ᜬ","ᜣ"=>"ᜫ","ᜢ"=>"ᜪ","ᜡ"=>"ᜩ",
            "᜗"=>"ᜟ","᜕"=>"᜝","ᜓ"=>"᜛","ᜑ"=>"᜙","ᜅ
"=>"ᜍ","ᜄ"=>"ᜌ","ᜃ"=>"ᜋ","ᜂ"=>"ᜊ","ᜁ"=>"ᜉ","ᜀ"=>"ᜈ",
            "ጷ"=>"ጿ","ጶ"=>"ጟ","ጵ"=>"ጜ","ጎ"=>"ጌ","ጳ"=>"ጻ","ጲ"=>"ጺ","ጱ"=>"ጹ","ጰ"=>"ጞ","ጧ"=>"ጯ","ጊ"=>"ጮ",
            "ጥ"=>"ጭ","ጀ"=>"ጬ","ጣ"=>"ጫ","ጢ"=>"ጪ","ጡ"=>"ጩ","ጕ"=>"ጝ","ጔ"=>"ጜ","ጓ"=>"ጛ","ጒ"=>"ጚ","጑"=>"ጙ",
            "ጐ"=>"ጘ","ጇ"=>"ጏ","ጆ"=>"ጎ","ጅ
"=>"ግ","ጄ"=>"ጌ","ጃ"=>"ጋ","ጂ"=>"ጊ","ጁ"=>"ጉ","ጀ"=>"ገ","ỹ"=>"Ở",
            "ỷ"=>"Ỷ","ỵ"=>"Ỏ","ỳ"=>"Ỳ","ự"=>"Ự","ữ"=>"Ữ","ử"=>"Ử","ừ"=>"Ừ","ứ"=>"Ớ","ủ"=>"Ị","ụ"=>"Ề",
            "ợ"=>"Ợ","ỡ"=>"Ỡ","ở"=>"Ở","ờ"=>"Ờ","ớ"=>"Ớ","ộ"=>"Ộ","ỗ"=>"Ỗ","ổ"=>"Ổ","ồ"=>"Ồ","ố"=>"Ố",
            "ỏ"=>"Ỏ","ọ"=>"Ọ","ị"=>"Ị","ỉ"=>"Ỉ","ệ"=>"Ệ","ễ
"=>"Ễ","ể"=>"Ể","ề"=>"Ề","ế"=>"ẟ","ẜ"=>"Ẍ",
            "ẻ"=>"Ẻ","ẹ"=>"ẞ","ặ"=>"Ặ","ẵ"=>"Ẏ","ẳ"=>"Ẳ","ằ"=>"Ằ","ắ"=>"Ắ","ậ"=>"Ậ","ẫ"=>"Ẫ","ẩ"=>"ẚ",
            "ầ"=>"Ẋ","ấ"=>"Ẁ","ả"=>"Ả","ạ"=>"Ạ","ẛ"=>"á¹ ","ẕ"=>"Ẕ","ẓ"=>"Ẓ","ẑ"=>"Ẑ","ẏ"=>"Ẏ","ẍ"=>"Ẍ",
            "ẋ"=>"Ẋ","ẉ"=>"Ẉ","ẇ"=>"Ẇ","ẅ
"=>"Ẅ","ẃ"=>"Ẃ","ẁ"=>"Ẁ","ṿ"=>"ṟ","Ṝ"=>"Ṍ","á¹»"=>"Ṻ","á¹¹"=>"Ṟ",
            "ṷ"=>"Ṷ","ṵ"=>"Ṏ","ṳ"=>"Ṳ","ṱ"=>"Ṱ","ṯ"=>"Ṯ","ṭ"=>"Ṭ","ṫ"=>"Ṫ","ṩ"=>"Ṛ","ṧ"=>"Ṋ","ṥ"=>"Ṁ",
            "ṣ"=>"Ṣ","ṡ"=>"Ṡ","ṟ"=>"Ṟ","ṝ"=>"Ṝ","ṛ"=>"Ṛ","ṙ"=>"Ṙ","ṗ"=>"Ṗ","ṕ"=>"Ṕ","ṓ"=>"Ṓ","ṑ"=>"Ṑ",
            "ṏ"=>"Ṏ","ṍ"=>"Ṍ","ṋ"=>"Ṋ","ṉ"=>"Ṉ","ṇ"=>"Ṇ","ṅ
"=>"Ṅ","ṃ"=>"Ṃ","ṁ"=>"Ṁ","áž¿"=>"ស","ážœ"=>"ឌ",
            "ុ"=>"ឺ","ឹ"=>"ឞ","ិ"=>"ា","឵"=>"ណ","ឳ"=>"ឲ","ឱ"=>"ឰ","ឯ"=>"ឮ","ឭ"=>"ឬ","ឫ"=>"ឪ","ឩ"=>"រ",
            "ឧ"=>"ដ","ឥ"=>"ក","ឣ"=>"អ","áž¡"=>"áž ","ᾟ"=>"ᾞ","ឝ"=>"ᾜ","ᾛ"=>"ᾚ","ᾙ"=>"ម","ᾗ"=>"ᾖ","ᾕ"=>"ᾔ",
            "ᾓ"=>"ᾒ","ᾑ"=>"ᾐ","ᾏ"=>"ᾎ","ᾍ"=>"ᾌ","ᾋ"=>"ᾊ","ᾉ"=>"ᾈ","ᾇ"=>"ᾆ","ᾅ
"=>"ᾄ","ᾃ"=>"ᾂ","ᾁ"=>"ᾀ",
            "ֆ"=>"Ֆ","օ
"=>"Օ","ք"=>"Ք","փ"=>"Փ","ւ"=>"Ւ","ց"=>"Ց","ր"=>"Ր","Õ¿"=>"Տ","ÕŸ"=>"Վ","Õœ"=>"Ս",
            "ÕŒ"=>"Ռ","Õ»"=>"Ջ","Õº"=>"Պ","Õ¹"=>"Չ","Õž"=>"Ո","Õ·"=>"Շ","Õ¶"=>"Ն","Õµ"=>"Յ
","ÕŽ"=>"Մ","Õ³"=>"Ճ",
            "Õ²"=>"Ղ","Õ±"=>"Ձ","Õ°"=>"Հ","Õ¯"=>"Ô¿","Õ®"=>"ÔŸ","Õ­"=>"Ôœ","Õ¬"=>"ÔŒ","Õ«"=>"Ô»","Õª"=>"Ôº","Õ©"=>"Ô¹",
            "Õš"=>"Ôž","Õ§"=>"Ô·","ÕŠ"=>"Ô¶","Õ¥"=>"Ôµ","Õ€"=>"ÔŽ","Õ£"=>"Ô³","Õ¢"=>"Ô²","Õ¡"=>"Ô±","ԏ"=>"Ԏ","ԍ"=>"Ԍ",
            "ԋ"=>"Ԋ","ԉ"=>"Ԉ","ԇ"=>"Ԇ","ԅ
"=>"Ԅ","ԃ"=>"Ԃ","ԁ"=>"Ԁ","Ó¹"=>"Óž","Óµ"=>"ÓŽ","Ó³"=>"Ó²","Ó±"=>"Ó°",
            "Ó¯"=>"Ó®","Ó­"=>"Ó¬","Ó«"=>"Óª","Ó©"=>"Óš","Ó§"=>"ÓŠ","Ó¥"=>"Ó€","Ó£"=>"Ó¢","Ó¡"=>"Ó ","ӟ"=>"Ӟ","ӝ"=>"Ӝ",
            "ӛ"=>"Ӛ","ә"=>"Ә","ӗ"=>"Ӗ","ӕ"=>"Ӕ","ӓ"=>"Ӓ","ӑ"=>"Ӑ","ӎ"=>"Ӎ","ӌ"=>"Ӌ","ӊ"=>"Ӊ","ӈ"=>"Ӈ",
            "ӆ"=>"Ӆ
","ӄ"=>"Ӄ","ӂ"=>"Ӂ","Ò¿"=>"ÒŸ","Òœ"=>"ÒŒ","Ò»"=>"Òº","Ò¹"=>"Òž","Ò·"=>"Ò¶","Òµ"=>"ÒŽ","Ò³"=>"Ò²",
            "Ò±"=>"Ò°","Ò¯"=>"Ò®","Ò­"=>"Ò¬","Ò«"=>"Òª","Ò©"=>"Òš","Ò§"=>"ÒŠ","Ò¥"=>"Ò€","Ò£"=>"Ò¢","Ò¡"=>"Ò ","ҟ"=>"Ҟ",
            "ҝ"=>"Ҝ","қ"=>"Қ","ҙ"=>"Ҙ","җ"=>"Җ","ҕ"=>"Ҕ","ғ"=>"Ғ","ґ"=>"Ґ","ҏ"=>"Ҏ","ҍ"=>"Ҍ","ҋ"=>"Ҋ",
            "ҁ"=>"Ҁ","Ñ¿"=>"ÑŸ","Ñœ"=>"ÑŒ","Ñ»"=>"Ѻ","ѹ"=>"Ñž","Ñ·"=>"Ѷ","ѵ"=>"ÑŽ","ѳ"=>"Ѳ","ѱ"=>"Ñ°","ѯ"=>"Ñ®",
            "Ñ­"=>"Ѭ","Ñ«"=>"Ѫ","Ñ©"=>"Ñš","ѧ"=>"ÑŠ","Ñ¥"=>"Ñ€","Ñ£"=>"Ñ¢","Ñ¡"=>"Ñ ","џ"=>"Џ","ў"=>"Ў","ѝ"=>"Ѝ",
            "ќ"=>"Ќ","ћ"=>"Ћ","њ"=>"Њ","љ"=>"Љ","ј"=>"Ј","ї"=>"Ї","і"=>"І","ѕ"=>"Ѕ
","є"=>"Є","ѓ"=>"Ѓ",
            "ђ"=>"Ђ","ё"=>"Ё","ѐ"=>"Ѐ","я"=>"Я","ю"=>"Ю","э"=>"Э","ь"=>"Ь","ы"=>"Ы","ъ"=>"Ъ","щ"=>"Щ",
            "ш"=>"К","ч"=>"Ч","ц"=>"Њ","х
"=>"Ð¥","ф"=>"Ѐ","у"=>"У","т"=>"Т","с"=>"С","р"=>"Ð ","п"=>"П",
            "П"=>"О","Ðœ"=>"Н","ÐŒ"=>"М","л"=>"Л","к"=>"К","й"=>"Й","О"=>"И","з"=>"З","ж"=>"Ж","е"=>"Е",
            "ÐŽ"=>"Д","г"=>"Г","в"=>"В","б"=>"Б","а"=>"А","ϵ"=>"Ε","ϲ"=>"Σ","ϱ"=>"Ρ","Ï°"=>"Κ","ϯ"=>"Ï®",
            "Ï­"=>"Ϭ","Ï«"=>"Ϫ","Ï©"=>"Ïš","ϧ"=>"ÏŠ","Ï¥"=>"Ï€","Ï£"=>"Ï¢","Ï¡"=>"Ï ","ϟ"=>"Ϟ","ϝ"=>"Ϝ","ϛ"=>"Ϛ",
            "ϙ"=>"Ϙ","ϖ"=>"Î ","ϕ"=>"Ί","ϑ"=>"Θ","ϐ"=>"Β","ώ"=>"Ώ","ύ"=>"Ύ","ό"=>"Ό","ϋ"=>"Ϋ","ϊ"=>"Ϊ",
            "ω"=>"Ω","ψ"=>"Κ","χ"=>"Χ","φ"=>"Ί","υ
"=>"Î¥","τ"=>"΀","σ"=>"Σ","ς"=>"Σ","ρ"=>"Ρ","π"=>"Î ",
            "ο"=>"Ο","Ο"=>"Ξ","Îœ"=>"Ν","ÎŒ"=>"Μ","λ"=>"Λ","κ"=>"Κ","ι"=>"Ι","Ξ"=>"Θ","η"=>"Η","ζ"=>"Ζ",
            "ε"=>"Ε","ÎŽ"=>"Δ","γ"=>"Γ","β"=>"Β","α"=>"Α","ί"=>"Ί","ή"=>"Ή","έ"=>"Έ","ά"=>"Ά","ʒ"=>"Æ·",
            "ʋ"=>"Ʋ","ʊ"=>"Ʊ","ʈ"=>"Æ®","ʃ"=>"Æ©","ʀ"=>"ÆŠ","ɵ"=>"Ɵ","ɲ"=>"Ɲ","ɯ"=>"Ɯ","É©"=>"Ɩ","Éš"=>"Ɨ",
            "ɣ"=>"Ɣ","ɛ"=>"Ɛ","ə"=>"Ə","ɗ"=>"Ɗ","ɖ"=>"Ɖ","ɔ"=>"Ɔ","ɓ"=>"Ɓ","ȳ"=>"Ȳ","ȱ"=>"Ȱ","ȯ"=>"Ȯ",
            "È­"=>"Ȭ","È«"=>"Ȫ","È©"=>"Èš","ȧ"=>"ÈŠ","È¥"=>"È€","È£"=>"È¢","ȟ"=>"Ȟ","ȝ"=>"Ȝ","ț"=>"Ț","ș"=>"Ș",
            "ȗ"=>"Ȗ","ȕ"=>"Ȕ","ȓ"=>"Ȓ","ȑ"=>"Ȑ","ȏ"=>"Ȏ","ȍ"=>"Ȍ","ȋ"=>"Ȋ","ȉ"=>"Ȉ","ȇ"=>"Ȇ","ȅ
"=>"Ȅ",
            "ȃ"=>"Ȃ","ȁ"=>"Ȁ","Ç¿"=>"ÇŸ","Çœ"=>"ÇŒ","Ç»"=>"Ǻ","ǹ"=>"Çž","ǵ"=>"ÇŽ","dz"=>"Dz","ǯ"=>"Ç®","Ç­"=>"Ǭ",
            "Ç«"=>"Ǫ","Ç©"=>"Çš","ǧ"=>"ÇŠ","Ç¥"=>"Ç€","Ç£"=>"Ç¢","Ç¡"=>"Ç ","ǟ"=>"Ǟ","ǝ"=>"Ǝ","ǜ"=>"Ǜ","ǚ"=>"Ǚ",
            "ǘ"=>"Ǘ","ǖ"=>"Ǖ","ǔ"=>"Ǔ","ǒ"=>"Ǒ","ǐ"=>"Ǐ","ǎ"=>"Ǎ","nj"=>"Nj","lj"=>"Lj","dž"=>"Dž
","Æ¿"=>"Ç·",
            "Æœ"=>"ÆŒ","ƹ"=>"Æž","ƶ"=>"Ƶ","ÆŽ"=>"Ƴ","Æ°"=>"Ư","Æ­"=>"Ƭ","Æš"=>"Ƨ","Æ¥"=>"Æ€","Æ£"=>"Æ¢","Æ¡"=>"Æ ",
            "ƞ"=>"È ","ƙ"=>"Ƙ","ƕ"=>"Ƕ","ƒ"=>"Ƒ","ƌ"=>"Ƌ","ƈ"=>"Ƈ","ƅ
"=>"Ƅ","ƃ"=>"Ƃ","Å¿"=>"S","ÅŸ"=>"Åœ",
            "Ō"=>"Ż","ź"=>"Ź","ŷ"=>"Ŷ","ŵ"=>"Ŏ","ų"=>"Ų","ű"=>"Ű","ů"=>"Ů","ŭ"=>"Ŭ","ū"=>"Ū","ũ"=>"Ś",
            "ŧ"=>"ÅŠ","Å¥"=>"Å€","Å£"=>"Å¢","Å¡"=>"Å ","ş"=>"Ş","ŝ"=>"Ŝ","ś"=>"Ś","ř"=>"Ř","ŗ"=>"Ŗ","ŕ"=>"Ŕ",
            "œ"=>"Œ","ő"=>"Ő","ŏ"=>"Ŏ","ō"=>"Ō","ŋ"=>"Ŋ","ň"=>"Ň","ņ"=>"Ņ
","ń"=>"Ń","ł"=>"Ł","ŀ"=>"Ŀ",
            "ğ"=>"Ĝ","Č"=>"Ļ","ĺ"=>"Ĺ","ķ"=>"Ķ","ĵ"=>"Ď","ij"=>"IJ","ı"=>"I","į"=>"Į","ĭ"=>"Ĭ","ī"=>"Ī",
            "Ä©"=>"Äš","ħ"=>"ÄŠ","Ä¥"=>"Ä€","Ä£"=>"Ä¢","Ä¡"=>"Ä ","ğ"=>"Ğ","ĝ"=>"Ĝ","ě"=>"Ě","ę"=>"Ę","ė"=>"Ė",
            "ĕ"=>"Ĕ","ē"=>"Ē","đ"=>"Đ","ď"=>"Ď","č"=>"Č","ċ"=>"Ċ","ĉ"=>"Ĉ","ć"=>"Ć","ą
"=>"Ą","ă"=>"Ă",
            "ā"=>"Ā","ÿ"=>"Åž","ß"=>"Þ","Ãœ"=>"Ý","ÃŒ"=>"Ü","û"=>"Û","ú"=>"Ú","ù"=>"Ù","Þ"=>"Ø","ö"=>"Ö",
            "õ"=>"Õ","ÃŽ"=>"Ô","ó"=>"Ó","ò"=>"Ò","ñ"=>"Ñ","ð"=>"Ð","ï"=>"Ï","î"=>"Î","í"=>"Í","ì"=>"Ì",
            "ë"=>"Ë","ê"=>"Ê","é"=>"É","Ú"=>"È","ç"=>"Ç","Ê"=>"Æ","Ã¥"=>"Å
","À"=>"Ä","ã"=>"Ã","â"=>"Â",
            "á"=>"Á","à "=>"À","µ"=>"Μ","z"=>"Z","y"=>"Y","x"=>"X","w"=>"W","v"=>"V","u"=>"U","t"=>"T",
            "s"=>"S","r"=>"R","q"=>"Q","p"=>"P","o"=>"O","n"=>"N","m"=>"M","l"=>"L","k"=>"K","j"=>"J",
            "i"=>"I","h"=>"H","g"=>"G","f"=>"F","e"=>"E","d"=>"D","c"=>"C","b"=>"B","a"=>"A"
                );

    /**
     * UTF-8 Case lookup table
     *
     * This lookuptable defines the lower case letters to their correspponding
     * upper case letter in UTF-8
     *
     * @author Andreas Gohr <[email protected]>
     */
    global $UTF8_UPPER_TO_LOWER;
    if(empty($UTF8_UPPER_TO_LOWER)) $UTF8_UPPER_TO_LOWER = array (
            ""=>"",""=>"",""=>"",""=>"",""=>"",""=>"",""=>"",""=>"",""=>"",""=>"",
            ""=>"",""=>"",""=>"",""=>"",""=>"",""=>"",""=>"",""=>"",""=>"",""=>"",
            ""=>"",""=>"
",""=>"",""=>"",""=>"",""=>"","á¿Œ"=>"ῳ","Ῥ"=>"á¿¥","á¿©"=>"á¿¡","Ῑ"=>"ῑ",
            "Ῐ"=>"ῐ","ῌ"=>"ῃ","Ι"=>"៟","៌"=>"៳","៹"=>"៱","៞"=>"៰","៯"=>"៧","៮"=>"៊","៭"=>"៥","៬"=>"ៀ",
            "៫"=>"៣","៪"=>"២","៩"=>"១","៟"=>"ៗ","៞"=>"៖","៝"=>"៕","ៜ"=>"។","៛"=>"៓","៚"=>"្","៙"=>"៑",
            "៘"=>"័","៏"=>"ះ","៎"=>"ំ","៍"=>"ៅ
","៌"=>"ោ","់"=>"ៃ","៊"=>"ែ","៉"=>"េ","ៈ"=>"ៀ","á¿»"=>"᜜",
            "Ὼ"=>"ᜌ","á¿«"=>"᜻","Ὺ"=>"᜺","Ό"=>"᜹","á¿ž"=>"᜞","Ί"=>"᜷","Ὶ"=>"᜶","Ή"=>"᜵","Ὴ"=>"ᜎ","Έ"=>"ᜳ",
            "Ὲ"=>"ᜲ","៻"=>"ᜱ","៺"=>"ᜰ","ᜯ"=>"ᜧ","ᜮ"=>"ᜊ","ᜭ"=>"ᜥ","ᜬ"=>"ᜀ","ᜫ"=>"ᜣ","ᜪ"=>"ᜢ","ᜩ"=>"ᜡ",
            "ᜟ"=>"᜗","᜝"=>"᜕","᜛"=>"ᜓ","᜙"=>"ᜑ","ᜍ"=>"ᜅ
","ᜌ"=>"ᜄ","ᜋ"=>"ᜃ","ᜊ"=>"ᜂ","ᜉ"=>"ᜁ","ᜈ"=>"ᜀ",
            "ጿ"=>"ጷ","ጟ"=>"ጶ","ጜ"=>"ጵ","ጌ"=>"ጎ","ጻ"=>"ጳ","ጺ"=>"ጲ","ጹ"=>"ጱ","ጞ"=>"ጰ","ጯ"=>"ጧ","ጮ"=>"ጊ",
            "ጭ"=>"ጥ","ጬ"=>"ጀ","ጫ"=>"ጣ","ጪ"=>"ጢ","ጩ"=>"ጡ","ጝ"=>"ጕ","ጜ"=>"ጔ","ጛ"=>"ጓ","ጚ"=>"ጒ","ጙ"=>"጑",
            "ጘ"=>"ጐ","ጏ"=>"ጇ","ጎ"=>"ጆ","ግ"=>"ጅ
","ጌ"=>"ጄ","ጋ"=>"ጃ","ጊ"=>"ጂ","ጉ"=>"ጁ","ገ"=>"ጀ","Ở"=>"ỹ",
            "Ỷ"=>"ỷ","Ỏ"=>"ỵ","Ỳ"=>"ỳ","Ự"=>"ự","Ữ"=>"ữ","Ử"=>"ử","Ừ"=>"ừ","Ớ"=>"ứ","Ị"=>"ủ","Ề"=>"ụ",
            "Ợ"=>"ợ","Ỡ"=>"ỡ","Ở"=>"ở","Ờ"=>"ờ","Ớ"=>"ớ","Ộ"=>"ộ","Ỗ"=>"ỗ","Ổ"=>"ổ","Ồ"=>"ồ","Ố"=>"ố",
            "Ỏ"=>"ỏ","Ọ"=>"ọ","Ị"=>"ị","Ỉ"=>"ỉ","Ệ"=>"ệ","Ễ"=>"ễ
","Ể"=>"ể","Ề"=>"ề","ẟ"=>"ế","Ẍ"=>"ẜ",
            "Ẻ"=>"ẻ","ẞ"=>"ẹ","Ặ"=>"ặ","Ẏ"=>"ẵ","Ẳ"=>"ẳ","Ằ"=>"ằ","Ắ"=>"ắ","Ậ"=>"ậ","Ẫ"=>"ẫ","ẚ"=>"ẩ",
            "Ẋ"=>"ầ","Ẁ"=>"ấ","Ả"=>"ả","Ạ"=>"ạ","á¹ "=>"ẛ","Ẕ"=>"ẕ","Ẓ"=>"ẓ","Ẑ"=>"ẑ","Ẏ"=>"ẏ","Ẍ"=>"ẍ",
            "Ẋ"=>"ẋ","Ẉ"=>"ẉ","Ẇ"=>"ẇ","Ẅ"=>"ẅ
","Ẃ"=>"ẃ","Ẁ"=>"ẁ","ṟ"=>"ṿ","Ṍ"=>"Ṝ","Ṻ"=>"á¹»","Ṟ"=>"á¹¹",
            "Ṷ"=>"ṷ","Ṏ"=>"ṵ","Ṳ"=>"ṳ","Ṱ"=>"ṱ","Ṯ"=>"ṯ","Ṭ"=>"ṭ","Ṫ"=>"ṫ","Ṛ"=>"ṩ","Ṋ"=>"ṧ","Ṁ"=>"ṥ",
            "Ṣ"=>"ṣ","Ṡ"=>"ṡ","Ṟ"=>"ṟ","Ṝ"=>"ṝ","Ṛ"=>"ṛ","Ṙ"=>"ṙ","Ṗ"=>"ṗ","Ṕ"=>"ṕ","Ṓ"=>"ṓ","Ṑ"=>"ṑ",
            "Ṏ"=>"ṏ","Ṍ"=>"ṍ","Ṋ"=>"ṋ","Ṉ"=>"ṉ","Ṇ"=>"ṇ","Ṅ"=>"ṅ
","Ṃ"=>"ṃ","Ṁ"=>"ṁ","ស"=>"áž¿","ឌ"=>"ážœ",
            "ឺ"=>"ុ","ឞ"=>"ឹ","ា"=>"ិ","ណ"=>"឵","ឲ"=>"ឳ","ឰ"=>"ឱ","ឮ"=>"ឯ","ឬ"=>"ឭ","ឪ"=>"ឫ","រ"=>"ឩ",
            "ដ"=>"ឧ","ក"=>"ឥ","អ"=>"ឣ","áž "=>"áž¡","ᾞ"=>"ᾟ","ᾜ"=>"ឝ","ᾚ"=>"ᾛ","ម"=>"ᾙ","ᾖ"=>"ᾗ","ᾔ"=>"ᾕ",
            "ᾒ"=>"ᾓ","ᾐ"=>"ᾑ","ᾎ"=>"ᾏ","ᾌ"=>"ᾍ","ᾊ"=>"ᾋ","ᾈ"=>"ᾉ","ᾆ"=>"ᾇ","ᾄ"=>"ᾅ
","ᾂ"=>"ᾃ","ᾀ"=>"ᾁ",
            "Ֆ"=>"ֆ","Օ"=>"օ
","Ք"=>"ք","Փ"=>"փ","Ւ"=>"ւ","Ց"=>"ց","Ր"=>"ր","Տ"=>"Õ¿","Վ"=>"ÕŸ","Ս"=>"Õœ",
            "Ռ"=>"ÕŒ","Ջ"=>"Õ»","Պ"=>"Õº","Չ"=>"Õ¹","Ո"=>"Õž","Շ"=>"Õ·","Ն"=>"Õ¶","Յ
"=>"Õµ","Մ"=>"ÕŽ","Ճ"=>"Õ³",
            "Ղ"=>"Õ²","Ձ"=>"Õ±","Հ"=>"Õ°","Ô¿"=>"Õ¯","ÔŸ"=>"Õ®","Ôœ"=>"Õ­","ÔŒ"=>"Õ¬","Ô»"=>"Õ«","Ôº"=>"Õª","Ô¹"=>"Õ©",
            "Ôž"=>"Õš","Ô·"=>"Õ§","Ô¶"=>"ÕŠ","Ôµ"=>"Õ¥","ÔŽ"=>"Õ€","Ô³"=>"Õ£","Ô²"=>"Õ¢","Ô±"=>"Õ¡","Ԏ"=>"ԏ","Ԍ"=>"ԍ",
            "Ԋ"=>"ԋ","Ԉ"=>"ԉ","Ԇ"=>"ԇ","Ԅ"=>"ԅ
","Ԃ"=>"ԃ","Ԁ"=>"ԁ","Óž"=>"Ó¹","ÓŽ"=>"Óµ","Ó²"=>"Ó³","Ó°"=>"Ó±",
            "Ó®"=>"Ó¯","Ó¬"=>"Ó­","Óª"=>"Ó«","Óš"=>"Ó©","ÓŠ"=>"Ó§","Ó€"=>"Ó¥","Ó¢"=>"Ó£","Ó "=>"Ó¡","Ӟ"=>"ӟ","Ӝ"=>"ӝ",
            "Ӛ"=>"ӛ","Ә"=>"ә","Ӗ"=>"ӗ","Ӕ"=>"ӕ","Ӓ"=>"ӓ","Ӑ"=>"ӑ","Ӎ"=>"ӎ","Ӌ"=>"ӌ","Ӊ"=>"ӊ","Ӈ"=>"ӈ",
            "Ӆ
"=>"ӆ","Ӄ"=>"ӄ","Ӂ"=>"ӂ","ÒŸ"=>"Ò¿","ÒŒ"=>"Òœ","Òº"=>"Ò»","Òž"=>"Ò¹","Ò¶"=>"Ò·","ÒŽ"=>"Òµ","Ò²"=>"Ò³",
            "Ò°"=>"Ò±","Ò®"=>"Ò¯","Ò¬"=>"Ò­","Òª"=>"Ò«","Òš"=>"Ò©","ÒŠ"=>"Ò§","Ò€"=>"Ò¥","Ò¢"=>"Ò£","Ò "=>"Ò¡","Ҟ"=>"ҟ",
            "Ҝ"=>"ҝ","Қ"=>"қ","Ҙ"=>"ҙ","Җ"=>"җ","Ҕ"=>"ҕ","Ғ"=>"ғ","Ґ"=>"ґ","Ҏ"=>"ҏ","Ҍ"=>"ҍ","Ҋ"=>"ҋ",
            "Ҁ"=>"ҁ","ÑŸ"=>"Ñ¿","ÑŒ"=>"Ñœ","Ѻ"=>"Ñ»","Ñž"=>"ѹ","Ѷ"=>"Ñ·","ÑŽ"=>"ѵ","Ѳ"=>"ѳ","Ñ°"=>"ѱ","Ñ®"=>"ѯ",
            "Ѭ"=>"Ñ­","Ѫ"=>"Ñ«","Ñš"=>"Ñ©","ÑŠ"=>"ѧ","Ñ€"=>"Ñ¥","Ñ¢"=>"Ñ£","Ñ "=>"Ñ¡","Џ"=>"џ","Ў"=>"ў","Ѝ"=>"ѝ",
            "Ќ"=>"ќ","Ћ"=>"ћ","Њ"=>"њ","Љ"=>"љ","Ј"=>"ј","Ї"=>"ї","І"=>"і","Ѕ
"=>"ѕ","Є"=>"є","Ѓ"=>"ѓ",
            "Ђ"=>"ђ","Ё"=>"ё","Ѐ"=>"ѐ","Я"=>"я","Ю"=>"ю","Э"=>"э","Ь"=>"ь","Ы"=>"ы","Ъ"=>"ъ","Щ"=>"щ",
            "К"=>"ш","Ч"=>"ч","Њ"=>"ц","Ð¥"=>"х
","Ѐ"=>"ф","У"=>"у","Т"=>"т","С"=>"с","Ð "=>"р","П"=>"п",
            "О"=>"П","Н"=>"Ðœ","М"=>"ÐŒ","Л"=>"л","К"=>"к","Й"=>"й","И"=>"О","З"=>"з","Ж"=>"ж","Е"=>"е",
            "Д"=>"ÐŽ","Г"=>"г","В"=>"в","Б"=>"б","А"=>"а","Ε"=>"ϵ","Σ"=>"ϲ","Ρ"=>"ϱ","Κ"=>"Ï°","Ï®"=>"ϯ",
            "Ϭ"=>"Ï­","Ϫ"=>"Ï«","Ïš"=>"Ï©","ÏŠ"=>"ϧ","Ï€"=>"Ï¥","Ï¢"=>"Ï£","Ï "=>"Ï¡","Ϟ"=>"ϟ","Ϝ"=>"ϝ","Ϛ"=>"ϛ",
            "Ϙ"=>"ϙ","Î "=>"ϖ","Ί"=>"ϕ","Θ"=>"ϑ","Β"=>"ϐ","Ώ"=>"ώ","Ύ"=>"ύ","Ό"=>"ό","Ϋ"=>"ϋ","Ϊ"=>"ϊ",
            "Ω"=>"ω","Κ"=>"ψ","Χ"=>"χ","Ί"=>"φ","Î¥"=>"υ
","΀"=>"τ","Σ"=>"σ","Σ"=>"ς","Ρ"=>"ρ","Î "=>"π",
            "Ο"=>"ο","Ξ"=>"Ο","Ν"=>"Îœ","Μ"=>"ÎŒ","Λ"=>"λ","Κ"=>"κ","Ι"=>"ι","Θ"=>"Ξ","Η"=>"η","Ζ"=>"ζ",
            "Ε"=>"ε","Δ"=>"ÎŽ","Γ"=>"γ","Β"=>"β","Α"=>"α","Ί"=>"ί","Ή"=>"ή","Έ"=>"έ","Ά"=>"ά","Æ·"=>"ʒ",
            "Ʋ"=>"ʋ","Ʊ"=>"ʊ","Æ®"=>"ʈ","Æ©"=>"ʃ","ÆŠ"=>"ʀ","Ɵ"=>"ɵ","Ɲ"=>"ɲ","Ɯ"=>"ɯ","Ɩ"=>"É©","Ɨ"=>"Éš",
            "Ɣ"=>"ɣ","Ɛ"=>"ɛ","Ə"=>"ə","Ɗ"=>"ɗ","Ɖ"=>"ɖ","Ɔ"=>"ɔ","Ɓ"=>"ɓ","Ȳ"=>"ȳ","Ȱ"=>"ȱ","Ȯ"=>"ȯ",
            "Ȭ"=>"È­","Ȫ"=>"È«","Èš"=>"È©","ÈŠ"=>"ȧ","È€"=>"È¥","È¢"=>"È£","Ȟ"=>"ȟ","Ȝ"=>"ȝ","Ț"=>"ț","Ș"=>"ș",
            "Ȗ"=>"ȗ","Ȕ"=>"ȕ","Ȓ"=>"ȓ","Ȑ"=>"ȑ","Ȏ"=>"ȏ","Ȍ"=>"ȍ","Ȋ"=>"ȋ","Ȉ"=>"ȉ","Ȇ"=>"ȇ","Ȅ"=>"ȅ
",
            "Ȃ"=>"ȃ","Ȁ"=>"ȁ","ÇŸ"=>"Ç¿","ÇŒ"=>"Çœ","Ǻ"=>"Ç»","Çž"=>"ǹ","ÇŽ"=>"ǵ","Dz"=>"dz","Ç®"=>"ǯ","Ǭ"=>"Ç­",
            "Ǫ"=>"Ç«","Çš"=>"Ç©","ÇŠ"=>"ǧ","Ç€"=>"Ç¥","Ç¢"=>"Ç£","Ç "=>"Ç¡","Ǟ"=>"ǟ","Ǝ"=>"ǝ","Ǜ"=>"ǜ","Ǚ"=>"ǚ",
            "Ǘ"=>"ǘ","Ǖ"=>"ǖ","Ǔ"=>"ǔ","Ǒ"=>"ǒ","Ǐ"=>"ǐ","Ǎ"=>"ǎ","Nj"=>"nj","Lj"=>"lj","Dž
"=>"dž","Ƿ"=>"ƿ",
            "ÆŒ"=>"Æœ","Æž"=>"ƹ","Ƶ"=>"ƶ","Ƴ"=>"ÆŽ","Ư"=>"Æ°","Ƭ"=>"Æ­","Ƨ"=>"Æš","Æ€"=>"Æ¥","Æ¢"=>"Æ£","Æ "=>"Æ¡",
            "È "=>"ƞ","Ƙ"=>"ƙ","Ƕ"=>"ƕ","Ƒ"=>"ƒ","Ƌ"=>"ƌ","Ƈ"=>"ƈ","Ƅ"=>"ƅ
","Ƃ"=>"ƃ","S"=>"Å¿","Åœ"=>"ÅŸ",
            "Ż"=>"Ō","Ź"=>"ź","Ŷ"=>"ŷ","Ŏ"=>"ŵ","Ų"=>"ų","Ű"=>"ű","Ů"=>"ů","Ŭ"=>"ŭ","Ū"=>"ū","Ś"=>"ũ",
            "ÅŠ"=>"ŧ","Å€"=>"Å¥","Å¢"=>"Å£","Å "=>"Å¡","Ş"=>"ş","Ŝ"=>"ŝ","Ś"=>"ś","Ř"=>"ř","Ŗ"=>"ŗ","Ŕ"=>"ŕ",
            "Œ"=>"œ","Ő"=>"ő","Ŏ"=>"ŏ","Ō"=>"ō","Ŋ"=>"ŋ","Ň"=>"ň","Ņ
"=>"ņ","Ń"=>"ń","Ł"=>"ł","Ŀ"=>"ŀ",
            "Ĝ"=>"ğ","Ļ"=>"Č","Ĺ"=>"ĺ","Ķ"=>"ķ","Ď"=>"ĵ","IJ"=>"ij","I"=>"ı","Į"=>"į","Ĭ"=>"ĭ","Ī"=>"ī",
            "Äš"=>"Ä©","ÄŠ"=>"ħ","Ä€"=>"Ä¥","Ä¢"=>"Ä£","Ä "=>"Ä¡","Ğ"=>"ğ","Ĝ"=>"ĝ","Ě"=>"ě","Ę"=>"ę","Ė"=>"ė",
            "Ĕ"=>"ĕ","Ē"=>"ē","Đ"=>"đ","Ď"=>"ď","Č"=>"č","Ċ"=>"ċ","Ĉ"=>"ĉ","Ć"=>"ć","Ą"=>"ą
","Ă"=>"ă",
            "Ā"=>"ā","Åž"=>"ÿ","Þ"=>"ß","Ý"=>"Ãœ","Ü"=>"ÃŒ","Û"=>"û","Ú"=>"ú","Ù"=>"ù","Ø"=>"Þ","Ö"=>"ö",
            "Õ"=>"õ","Ô"=>"ÃŽ","Ó"=>"ó","Ò"=>"ò","Ñ"=>"ñ","Ð"=>"ð","Ï"=>"ï","Î"=>"î","Í"=>"í","Ì"=>"ì",
            "Ë"=>"ë","Ê"=>"ê","É"=>"é","È"=>"Ú","Ç"=>"ç","Æ"=>"Ê","Å
"=>"Ã¥","Ä"=>"À","Ã"=>"ã","Â"=>"â",
            "Á"=>"á","À"=>"à ","Μ"=>"µ","Z"=>"z","Y"=>"y","X"=>"x","W"=>"w","V"=>"v","U"=>"u","T"=>"t",
            "S"=>"s","R"=>"r","Q"=>"q","P"=>"p","O"=>"o","N"=>"n","M"=>"m","L"=>"l","K"=>"k","J"=>"j",
            "I"=>"i","H"=>"h","G"=>"g","F"=>"f","E"=>"e","D"=>"d","C"=>"c","B"=>"b","A"=>"a"
                );
}; // end of case lookup tables

/**
 * UTF-8 lookup table for lower case accented letters
 *
 * This lookuptable defines replacements for accented characters from the ASCII-7
 * range. This are lower case letters only.
 *
 * @author Andreas Gohr <[email protected]>
 * @see    utf8_deaccent()
 */
global $UTF8_LOWER_ACCENTS;
if(empty($UTF8_LOWER_ACCENTS)) $UTF8_LOWER_ACCENTS = array(
  'à ' => 'a', 'ÃŽ' => 'o', 'ď' => 'd', 'ᾟ' => 'f', 'ë' => 'e', 'Å¡' => 's', 'Æ¡' => 'o',
  'ß' => 'ss', 'ă' => 'a', 'ř' => 'r', 'ț' => 't', 'ň' => 'n', 'ā' => 'a', 'ķ' => 'k',
  'ŝ' => 's', 'ỳ' => 'y', 'ņ' => 'n', 'ĺ' => 'l', 'ħ' => 'h', 'ṗ' => 'p', 'ó' => 'o',
  'ú' => 'u', 'ě' => 'e', 'é' => 'e', 'ç' => 'c', 'ẁ' => 'w', 'ċ' => 'c', 'õ' => 'o',
  'ṡ' => 's', 'Þ' => 'o', 'Ä£' => 'g', 'ŧ' => 't', 'ș' => 's', 'ė' => 'e', 'ĉ' => 'c',
  'ś' => 's', 'î' => 'i', 'ű' => 'u', 'ć' => 'c', 'ę' => 'e', 'ŵ' => 'w', 'ṫ' => 't',
  'Å«' => 'u', 'č' => 'c', 'ö' => 'oe', 'Ú' => 'e', 'Å·' => 'y', 'ą
' => 'a', 'ł' => 'l',
  'ų' => 'u', 'ů' => 'u', 'ş' => 's', 'ğ' => 'g', 'ÄŒ' => 'l', 'ƒ' => 'f', 'ÅŸ' => 'z',
  'ẃ' => 'w', 'ឃ' => 'b', 'Ã¥' => 'a', 'ì' => 'i', 'ï' => 'i', 'ᾋ' => 'd', 'Å¥' => 't',
  'ŗ' => 'r', 'À' => 'ae', 'í' => 'i', 'ŕ' => 'r', 'ê' => 'e', 'ÃŒ' => 'ue', 'ò' => 'o',
  'ē' => 'e', 'ñ' => 'n', 'ń' => 'n', 'ĥ' => 'h', 'ĝ' => 'g', 'đ' => 'd', 'ĵ' => 'j',
  'ÿ' => 'y', 'Å©' => 'u', 'Å­' => 'u', 'Æ°' => 'u', 'Å£' => 't', 'Ãœ' => 'y', 'ő' => 'o',
  'â' => 'a', 'ÄŸ' => 'l', 'ẅ
' => 'w', 'Ō' => 'z', 'ī' => 'i', 'ã' => 'a', 'ġ' => 'g',
  'ṁ' => 'm', 'ō' => 'o', 'ĩ' => 'i', 'ù' => 'u', 'į' => 'i', 'ź' => 'z', 'á' => 'a',
  'û' => 'u', 'ß' => 'th', 'ð' => 'dh', 'Ê' => 'ae', 'µ' => 'u', 'ĕ' => 'e',
);

/**
 * UTF-8 lookup table for upper case accented letters
 *
 * This lookuptable defines replacements for accented characters from the ASCII-7
 * range. This are upper case letters only.
 *
 * @author Andreas Gohr <[email protected]>
 * @see    utf8_deaccent()
 */
global $UTF8_UPPER_ACCENTS;
if(empty($UTF8_UPPER_ACCENTS)) $UTF8_UPPER_ACCENTS = array(
  'À' => 'A', 'Ô' => 'O', 'Ď' => 'D', 'ᾞ' => 'F', 'Ë' => 'E', 'Å ' => 'S', 'Æ ' => 'O',
  'Ă' => 'A', 'Ř' => 'R', 'Ț' => 'T', 'Ň' => 'N', 'Ā' => 'A', 'Ķ' => 'K',
  'Ŝ' => 'S', 'Ỳ' => 'Y', 'Ņ
' => 'N', 'Ĺ' => 'L', 'ÄŠ' => 'H', 'Ṗ' => 'P', 'Ó' => 'O',
  'Ú' => 'U', 'Ě' => 'E', 'É' => 'E', 'Ç' => 'C', 'Ẁ' => 'W', 'Ċ' => 'C', 'Õ' => 'O',
  'á¹ ' => 'S', 'Ø' => 'O', 'Ä¢' => 'G', 'ÅŠ' => 'T', 'Ș' => 'S', 'Ė' => 'E', 'Ĉ' => 'C',
  'Ś' => 'S', 'Î' => 'I', 'Å°' => 'U', 'Ć' => 'C', 'Ę' => 'E', 'ÅŽ' => 'W', 'Ṫ' => 'T',
  'Ū' => 'U', 'Č' => 'C', 'Ö' => 'Oe', 'È' => 'E', 'Ŷ' => 'Y', 'Ą' => 'A', 'Ł' => 'L',
  'Ų' => 'U', 'Å®' => 'U', 'Ş' => 'S', 'Ğ' => 'G', 'Ä»' => 'L', 'Ƒ' => 'F', 'Åœ' => 'Z',
  'Ẃ' => 'W', 'ᾂ' => 'B', 'Å
' => 'A', 'Ì' => 'I', 'Ï' => 'I', 'ᾊ' => 'D', 'Å€' => 'T',
  'Ŗ' => 'R', 'Ä' => 'Ae', 'Í' => 'I', 'Ŕ' => 'R', 'Ê' => 'E', 'Ü' => 'Ue', 'Ò' => 'O',
  'Ē' => 'E', 'Ñ' => 'N', 'Ń' => 'N', 'Ä€' => 'H', 'Ĝ' => 'G', 'Đ' => 'D', 'ÄŽ' => 'J',
  'Ş' => 'Y', 'Ś' => 'U', 'Ŭ' => 'U', 'Ư' => 'U', 'Ţ' => 'T', 'Ý' => 'Y', 'Ő' => 'O',
  'Â' => 'A', 'Äœ' => 'L', 'Ẅ' => 'W', 'Å»' => 'Z', 'Ī' => 'I', 'Ã' => 'A', 'Ä ' => 'G',
  'Ṁ' => 'M', 'Ō' => 'O', 'Äš' => 'I', 'Ù' => 'U', 'Ä®' => 'I', 'Ź' => 'Z', 'Á' => 'A',
  'Û' => 'U', 'Þ' => 'Th', 'Ð' => 'Dh', 'Æ' => 'Ae', 'Ĕ' => 'E',
);

/**
 * UTF-8 array of common special characters
 *
 * This array should contain all special characters (not a letter or digit)
 * defined in the various local charsets - it's not a complete list of non-alphanum
 * characters in UTF-8. It's not perfect but should match most cases of special
 * chars.
 *
 * The controlchars 0x00 to 0x19 are _not_ included in this array. The space 0x20 is!
 * These chars are _not_ in the array either:  _ (0x5f), : 0x3a, . 0x2e, - 0x2d, * 0x2a
 *
 * @author Andreas Gohr <[email protected]>
 * @see    utf8_stripspecials()
 */
global $UTF8_SPECIAL_CHARS;
if(empty($UTF8_SPECIAL_CHARS)) $UTF8_SPECIAL_CHARS = array(
  0x001a, 0x001b, 0x001c, 0x001d, 0x001e, 0x001f, 0x0020, 0x0021, 0x0022, 0x0023,
  0x0024, 0x0025, 0x0026, 0x0027, 0x0028, 0x0029,         0x002b, 0x002c,
          0x002f,         0x003b, 0x003c, 0x003d, 0x003e, 0x003f, 0x0040, 0x005b,
  0x005c, 0x005d, 0x005e,         0x0060, 0x007b, 0x007c, 0x007d, 0x007e,
  0x007f, 0x0080, 0x0081, 0x0082, 0x0083, 0x0084, 0x0085, 0x0086, 0x0087, 0x0088,
  0x0089, 0x008a, 0x008b, 0x008c, 0x008d, 0x008e, 0x008f, 0x0090, 0x0091, 0x0092,
  0x0093, 0x0094, 0x0095, 0x0096, 0x0097, 0x0098, 0x0099, 0x009a, 0x009b, 0x009c,
  0x009d, 0x009e, 0x009f, 0x00a0, 0x00a1, 0x00a2, 0x00a3, 0x00a4, 0x00a5, 0x00a6,
  0x00a7, 0x00a8, 0x00a9, 0x00aa, 0x00ab, 0x00ac, 0x00ad, 0x00ae, 0x00af, 0x00b0,
  0x00b1, 0x00b2, 0x00b3, 0x00b4, 0x00b5, 0x00b6, 0x00b7, 0x00b8, 0x00b9, 0x00ba,
  0x00bb, 0x00bc, 0x00bd, 0x00be, 0x00bf, 0x00d7, 0x00f7, 0x02c7, 0x02d8, 0x02d9,
  0x02da, 0x02db, 0x02dc, 0x02dd, 0x0300, 0x0301, 0x0303, 0x0309, 0x0323, 0x0384,
  0x0385, 0x0387, 0x03c6, 0x03d1, 0x03d2, 0x03d5, 0x03d6, 0x05b0, 0x05b1,
  0x05b2, 0x05b3, 0x05b4, 0x05b5, 0x05b6, 0x05b7, 0x05b8, 0x05b9, 0x05bb, 0x05bc,
  0x05bd, 0x05be, 0x05bf, 0x05c0, 0x05c1, 0x05c2, 0x05c3, 0x05f3, 0x05f4, 0x060c,
  0x061b, 0x061f, 0x0640, 0x064b, 0x064c, 0x064d, 0x064e, 0x064f, 0x0650, 0x0651,
  0x0652, 0x066a, 0x0e3f, 0x200c, 0x200d, 0x200e, 0x200f, 0x2013, 0x2014, 0x2015,
  0x2017, 0x2018, 0x2019, 0x201a, 0x201c, 0x201d, 0x201e, 0x2020, 0x2021, 0x2022,
  0x2026, 0x2030, 0x2032, 0x2033, 0x2039, 0x203a, 0x2044, 0x20a7, 0x20aa, 0x20ab,
  0x20ac, 0x2116, 0x2118, 0x2122, 0x2126, 0x2135, 0x2190, 0x2191, 0x2192, 0x2193,
  0x2194, 0x2195, 0x21b5, 0x21d0, 0x21d1, 0x21d2, 0x21d3, 0x21d4, 0x2200, 0x2202,
  0x2203, 0x2205, 0x2206, 0x2207, 0x2208, 0x2209, 0x220b, 0x220f, 0x2211, 0x2212,
  0x2215, 0x2217, 0x2219, 0x221a, 0x221d, 0x221e, 0x2220, 0x2227, 0x2228, 0x2229,
  0x222a, 0x222b, 0x2234, 0x223c, 0x2245, 0x2248, 0x2260, 0x2261, 0x2264, 0x2265,
  0x2282, 0x2283, 0x2284, 0x2286, 0x2287, 0x2295, 0x2297, 0x22a5, 0x22c5, 0x2310,
  0x2320, 0x2321, 0x2329, 0x232a, 0x2469, 0x2500, 0x2502, 0x250c, 0x2510, 0x2514,
  0x2518, 0x251c, 0x2524, 0x252c, 0x2534, 0x253c, 0x2550, 0x2551, 0x2552, 0x2553,
  0x2554, 0x2555, 0x2556, 0x2557, 0x2558, 0x2559, 0x255a, 0x255b, 0x255c, 0x255d,
  0x255e, 0x255f, 0x2560, 0x2561, 0x2562, 0x2563, 0x2564, 0x2565, 0x2566, 0x2567,
  0x2568, 0x2569, 0x256a, 0x256b, 0x256c, 0x2580, 0x2584, 0x2588, 0x258c, 0x2590,
  0x2591, 0x2592, 0x2593, 0x25a0, 0x25b2, 0x25bc, 0x25c6, 0x25ca, 0x25cf, 0x25d7,
  0x2605, 0x260e, 0x261b, 0x261e, 0x2660, 0x2663, 0x2665, 0x2666, 0x2701, 0x2702,
  0x2703, 0x2704, 0x2706, 0x2707, 0x2708, 0x2709, 0x270c, 0x270d, 0x270e, 0x270f,
  0x2710, 0x2711, 0x2712, 0x2713, 0x2714, 0x2715, 0x2716, 0x2717, 0x2718, 0x2719,
  0x271a, 0x271b, 0x271c, 0x271d, 0x271e, 0x271f, 0x2720, 0x2721, 0x2722, 0x2723,
  0x2724, 0x2725, 0x2726, 0x2727, 0x2729, 0x272a, 0x272b, 0x272c, 0x272d, 0x272e,
  0x272f, 0x2730, 0x2731, 0x2732, 0x2733, 0x2734, 0x2735, 0x2736, 0x2737, 0x2738,
  0x2739, 0x273a, 0x273b, 0x273c, 0x273d, 0x273e, 0x273f, 0x2740, 0x2741, 0x2742,
  0x2743, 0x2744, 0x2745, 0x2746, 0x2747, 0x2748, 0x2749, 0x274a, 0x274b, 0x274d,
  0x274f, 0x2750, 0x2751, 0x2752, 0x2756, 0x2758, 0x2759, 0x275a, 0x275b, 0x275c,
  0x275d, 0x275e, 0x2761, 0x2762, 0x2763, 0x2764, 0x2765, 0x2766, 0x2767, 0x277f,
  0x2789, 0x2793, 0x2794, 0x2798, 0x2799, 0x279a, 0x279b, 0x279c, 0x279d, 0x279e,
  0x279f, 0x27a0, 0x27a1, 0x27a2, 0x27a3, 0x27a4, 0x27a5, 0x27a6, 0x27a7, 0x27a8,
  0x27a9, 0x27aa, 0x27ab, 0x27ac, 0x27ad, 0x27ae, 0x27af, 0x27b1, 0x27b2, 0x27b3,
  0x27b4, 0x27b5, 0x27b6, 0x27b7, 0x27b8, 0x27b9, 0x27ba, 0x27bb, 0x27bc, 0x27bd,
  0x27be, 0x3000, 0x3001, 0x3002, 0x3003, 0x3008, 0x3009, 0x300a, 0x300b, 0x300c,
  0x300d, 0x300e, 0x300f, 0x3010, 0x3011, 0x3012, 0x3014, 0x3015, 0x3016, 0x3017,
  0x3018, 0x3019, 0x301a, 0x301b, 0x3036,
  0xf6d9, 0xf6da, 0xf6db, 0xf8d7, 0xf8d8, 0xf8d9, 0xf8da, 0xf8db, 0xf8dc,
  0xf8dd, 0xf8de, 0xf8df, 0xf8e0, 0xf8e1, 0xf8e2, 0xf8e3, 0xf8e4, 0xf8e5, 0xf8e6,
  0xf8e7, 0xf8e8, 0xf8e9, 0xf8ea, 0xf8eb, 0xf8ec, 0xf8ed, 0xf8ee, 0xf8ef, 0xf8f0,
  0xf8f1, 0xf8f2, 0xf8f3, 0xf8f4, 0xf8f5, 0xf8f6, 0xf8f7, 0xf8f8, 0xf8f9, 0xf8fa,
  0xf8fb, 0xf8fc, 0xf8fd, 0xf8fe, 0xfe7c, 0xfe7d,
          0xff01, 0xff02, 0xff03, 0xff04, 0xff05, 0xff06, 0xff07, 0xff08, 0xff09,
  0xff09, 0xff0a, 0xff0b, 0xff0c, 0xff0d, 0xff0e, 0xff0f, 0xff1a, 0xff1b, 0xff1c,
  0xff1d, 0xff1e, 0xff1f, 0xff20, 0xff3b, 0xff3c, 0xff3d, 0xff3e, 0xff40, 0xff5b,
  0xff5c, 0xff5d, 0xff5e, 0xff5f, 0xff60, 0xff61, 0xff62, 0xff63, 0xff64, 0xff65,
  0xffe0, 0xffe1, 0xffe2, 0xffe3, 0xffe4, 0xffe5, 0xffe6, 0xffe8, 0xffe9, 0xffea,
  0xffeb, 0xffec, 0xffed, 0xffee,
  0x01d6fc, 0x01d6fd, 0x01d6fe, 0x01d6ff, 0x01d700, 0x01d701, 0x01d702, 0x01d703,
  0x01d704, 0x01d705, 0x01d706, 0x01d707, 0x01d708, 0x01d709, 0x01d70a, 0x01d70b,
  0x01d70c, 0x01d70d, 0x01d70e, 0x01d70f, 0x01d710, 0x01d711, 0x01d712, 0x01d713,
  0x01d714, 0x01d715, 0x01d716, 0x01d717, 0x01d718, 0x01d719, 0x01d71a, 0x01d71b,
  0xc2a0, 0xe28087, 0xe280af, 0xe281a0, 0xefbbbf,
);

// utf8 version of above data
global $UTF8_SPECIAL_CHARS2;
if(empty($UTF8_SPECIAL_CHARS2)) $UTF8_SPECIAL_CHARS2 =
    "\x1A".'


 !"#$%&\'()+,/;<=>?@[\]^`{|}~€‚ƒ„…
†‡ˆ‰Š‹ŒŽ‘’“”•ￜ'.
    'ￜ—˜™š›œžŸ ¡¢£€¥Š§š©ª«¬­®¯°±²³Žµ¶·ž¹º»Œœￜ'.
    'ￜ¿×÷ˇ˘˙˚˛˜˝̣̀́̃̉΄΅
·ϖְֱֲֳ֎ֵֶַֹֻ֞֌ֿ֜֟ￜ'.
    'ï¿œ××‚×ƒ×³×ŽØŒØ›ØŸÙ€Ù‹ÙŒÙÙŽÙÙÙ‘Ù’Ùªàž¿â€Œâ€â€Žâ€â€“â€”â€•â€—â€˜â€™â€šâ€œâ€ï¿œ'.
    'ￜￜ†‡• ‰′″‹›⁄₧₪₫€№℘™ℊℵ←↑→↓↔↕↵'.
    '⇐⇑⇒⇓⇔∀∂∃∅
∆∇∈∉∋∏∑−∕∗∙√∝∞∠∧√ￜ'.
    'ￜ∪∫∎∌≅
≈≠≡≀≥⊂⊃⊄⊆⊇⊕⊗⊥⋅
⌐⌠⌡〈〉⑩─ￜ'.
    'ￜￜ┌┐└┘├─┬┎┌═║╒╓╔╕╖╗╘╙╚╛╜╝╞╟╠'.
    '╡╢╣╀╥╊╧╚╩╪╫╬▀▄█▌▐░▒▓■▲▌◆◊●ￜ'.
    'ￜ★
☎☛☞♠♣♥♊✁✂✃✄✆✇✈✉✌✍✎✏✐✑✒✓✔✕ￜ'.
    'ￜￜ✗✘✙✚✛✜✝✞✟✠✡✢✣✀✥✊✧✩✪✫✬✭✮✯✰✱'.
    '✲✳✎✵✶✷✞✹✺✻✌✜✟✿❀❁❂❃❄❅
❆❇❈❉❊❋ￜ'.
    'ￜ❏❐❑❒❖❘❙❚❛❜❝❞❡❢❣❀❥❊❧❿➉➓➔➘➙➚ￜ'.
    'ￜￜ➜➝➞➟➠➡➢➣➀➥➊➧➚➩➪➫➬➭➮➯➱➲➳➎➵➶'.
    '➷➞➹➺➻➌➜➟'.
    '　、。〃〈〉《》「」『』【】〒〔〕〖〗〘〙〚〛〶'.
    'ï›™ï›šï››ï£—ï£˜ï£™ï£šï£›ï£œï£ï£žï£Ÿï£ ï£¡ï£¢ï££ï£€ï£¥ï¿œ'.
    'ￜ﹌﹜'.
    '
ïŒ†ïŒ‡ïŒˆïŒ‰ïŒŠïŒ‹ïŒŒïŒïŒŽïŒïŒšïŒ›ïŒœïŒïŒžïŒŸïŒ ïŒ»ïŒŒïŒœïŒŸïœ€ïœ›ïœœïœïœž'.
    'ïœŸïœ ïœ¡ïœ¢ïœ£ïœ€ïœ¥ï¿ ï¿¡ï¿¢ï¿£ï¿€ï¿¥ï¿Šï¿šï¿©ï¿ªï¿«ï¿¬ï¿­ï¿®'.
    '𝛌𝛜𝛟𝛿𝜀𝜁𝜂𝜃𝜄𝜅
𝜆𝜇𝜈𝜉𝜊𝜋𝜌𝜍𝜎𝜏𝜐𝜑𝜒𝜓𝜔𝜕𝜖𝜗𝜘𝜙𝜚𝜛'.
    '   ⁠';

/**
 * Romanization lookup table
 *
 * This lookup tables provides a way to transform strings written in a language
 * different from the ones based upon latin letters into plain ASCII.
 *
 * Please note: this is not a scientific transliteration table. It only works
 * oneway from nonlatin to ASCII and it works by simple character replacement
 * only. Specialities of each language are not supported.
 *
 * @author Andreas Gohr <[email protected]>
 * @author Vitaly Blokhin <[email protected]>
 * @link   http://www.uconv.com/translit.htm
 * @author Bisqwit <[email protected]>
 * @link   http://kanjidict.stc.cx/hiragana.php?src=2
 * @link   http://www.translatum.gr/converter/greek-transliteration.htm
 * @link   http://en.wikipedia.org/wiki/Royal_Thai_General_System_of_Transcription
 * @link   http://www.btranslations.com/resources/romanization/korean.asp
 * @author Arthit Suriyawongkul <[email protected]>
 * @author Denis Scheither <[email protected]>
 */
global $UTF8_ROMANIZATION;
if(empty($UTF8_ROMANIZATION)) $UTF8_ROMANIZATION = array(
  // scandinavian - differs from what we do in deaccent
  'å'=>'a','Å
'=>'A','À'=>'a','Ä'=>'A','ö'=>'o','Ö'=>'O',

  //russian cyrillic
  'а'=>'a','А'=>'A','б'=>'b','Б'=>'B','в'=>'v','В'=>'V','г'=>'g','Г'=>'G',
  'ÐŽ'=>'d','Д'=>'D','е'=>'e','Е'=>'E','ё'=>'jo','Ё'=>'Jo','ж'=>'zh','Ж'=>'Zh',
  'з'=>'z','З'=>'Z','О'=>'i','И'=>'I','й'=>'j','Й'=>'J','к'=>'k','К'=>'K',
  'л'=>'l','Л'=>'L','ÐŒ'=>'m','М'=>'M','Ðœ'=>'n','Н'=>'N','П'=>'o','О'=>'O',
  'п'=>'p','П'=>'P','р'=>'r','Р'=>'R','с'=>'s','С'=>'S','т'=>'t','Т'=>'T',
  'у'=>'u','У'=>'U','ф'=>'f','Ѐ'=>'F','х
'=>'x','Ð¥'=>'X','ц'=>'c','Њ'=>'C',
  'ч'=>'ch','Ч'=>'Ch','ш'=>'sh','К'=>'Sh','щ'=>'sch','Щ'=>'Sch','ъ'=>'',
  'Ъ'=>'','ы'=>'y','Ы'=>'Y','ь'=>'','Ь'=>'','э'=>'eh','Э'=>'Eh','ю'=>'ju',
  'Ю'=>'Ju','я'=>'ja','Я'=>'Ja',
  // Ukrainian cyrillic
  'Ґ'=>'Gh','ґ'=>'gh','Є'=>'Je','є'=>'je','І'=>'I','і'=>'i','Ї'=>'Ji','ї'=>'ji',
  // Georgian
  'ა'=>'a','ბ'=>'b','გ'=>'g','დ'=>'d','ე'=>'e','ვ'=>'v','ზ'=>'z','თ'=>'th',
  'ი'=>'i','კ'=>'p','ლ'=>'l','მ'=>'m','ნ'=>'n','ო'=>'o','პ'=>'p','ჟ'=>'zh',
  'რ'=>'r','ს'=>'s','ტ'=>'t','უ'=>'u','Ⴠ'=>'ph','ქ'=>'kh','჊'=>'gh','ყ'=>'q',
  'ლ'=>'sh','ჩ'=>'ch','ც'=>'c','ძ'=>'dh','წ'=>'w','ჭ'=>'j','ხ'=>'x','ჯ'=>'jh',
  'ჰ'=>'xh',
  //Sanskrit
  'à€…
'=>'a','à€†'=>'ah','à€‡'=>'i','à€ˆ'=>'ih','à€‰'=>'u','à€Š'=>'uh','à€‹'=>'ry',
  'ॠ'=>'ryh','à€Œ'=>'ly','ॡ'=>'lyh','à€'=>'e','à€'=>'ay','à€“'=>'o','à€”'=>'aw',
  'à€…
à€‚'=>'amh','à€…
à€ƒ'=>'aq','à€•'=>'k','à€–'=>'kh','à€—'=>'g','à€˜'=>'gh','à€™'=>'nh',
  'à€š'=>'c','à€›'=>'ch','à€œ'=>'j','à€'=>'jh','à€ž'=>'ny','à€Ÿ'=>'tq','à€ '=>'tqh',
  'à€¡'=>'dq','à€¢'=>'dqh','à€£'=>'nq','à€€'=>'t','à€¥'=>'th','à€Š'=>'d','à€§'=>'dh',
  'à€š'=>'n','à€ª'=>'p','à€«'=>'ph','à€¬'=>'b','à€­'=>'bh','à€®'=>'m','à€¯'=>'z','à€°'=>'r',
  'à€²'=>'l','à€µ'=>'v','à€¶'=>'sh','à€·'=>'sqh','à€ž'=>'s','à€¹'=>'x',
  //Hebrew
  'א'=>'a', 'ב'=>'b','ג'=>'g','ד'=>'d','ה'=>'h','ו'=>'v','ז'=>'z','ח'=>'kh','ט'=>'th',
  'י'=>'y','ך'=>'h','כ'=>'k','ל'=>'l','ם'=>'m','מ'=>'m','ן'=>'n','× '=>'n',
  'ס'=>'s','ע'=>'ah','ף'=>'f','׀'=>'p','ץ'=>'c','׊'=>'c','ק'=>'q','ך'=>'r',
  'ש'=>'sh','ת'=>'t',
  //Arabic
  'ا'=>'a','ؚ'=>'b','ت'=>'t','ث'=>'th','ج'=>'g','ح'=>'xh','خ'=>'x','د'=>'d',
  'ذ'=>'dh','ر'=>'r','ز'=>'z','س'=>'s','؎'=>'sh','ص'=>'s\'','ض'=>'d\'',
  'Ø·'=>'t\'','Øž'=>'z\'','ع'=>'y','غ'=>'gh','ف'=>'f','ق'=>'q','ك'=>'k',
  'ل'=>'l','م
'=>'m','ن'=>'n','ه'=>'x\'','و'=>'u','ي'=>'i',

  // Japanese characters  (last update: 2008-05-09)

  // Japanese hiragana

  // 3 character syllables, っ doubles the consonant after
  'っちゃ'=>'ccha','っちぇ'=>'cche','っちょ'=>'ccho','っちゅ
'=>'cchu',
  'っびゃ'=>'bbya','っびぇ'=>'bbye','っびぃ'=>'bbyi','っびょ'=>'bbyo','っびゅ
'=>'bbyu',
  'っぎゃ'=>'ppya','っぎぇ'=>'ppye','っぎぃ'=>'ppyi','っぎょ'=>'ppyo','っぎゅ
'=>'ppyu',
  'っちゃ'=>'ccha','っちぇ'=>'cche','っち'=>'cchi','っちょ'=>'ccho','っちゅ
'=>'cchu',
  // 'っひゃ'=>'hya','っひぇ'=>'hye','っひぃ'=>'hyi','っひょ'=>'hyo','っひゅ
'=>'hyu',
  'っきゃ'=>'kkya','っきぇ'=>'kkye','っきぃ'=>'kkyi','っきょ'=>'kkyo','っきゅ
'=>'kkyu',
  'っぎゃ'=>'ggya','っぎぇ'=>'ggye','っぎぃ'=>'ggyi','っぎょ'=>'ggyo','っぎゅ
'=>'ggyu',
  'っみゃ'=>'mmya','っみぇ'=>'mmye','っみぃ'=>'mmyi','っみょ'=>'mmyo','っみゅ
'=>'mmyu',
  'っにゃ'=>'nnya','っにぇ'=>'nnye','っにぃ'=>'nnyi','っにょ'=>'nnyo','っにゅ
'=>'nnyu',
  'っりゃ'=>'rrya','っりぇ'=>'rrye','っりぃ'=>'rryi','っりょ'=>'rryo','っりゅ
'=>'rryu',
  'っしゃ'=>'ssha','っしぇ'=>'sshe','っし'=>'sshi','っしょ'=>'ssho','っしゅ
'=>'sshu',

  // seperate hiragana 'n' ('n' + 'i' != 'ni', normally we would write "kon'nichi wa" but the apostrophe would be converted to _ anyway)
  'んあ'=>'n_a','んえ'=>'n_e','んい'=>'n_i','んお'=>'n_o','んう'=>'n_u',
  'んや'=>'n_ya','んよ'=>'n_yo','んゆ'=>'n_yu',

   // 2 character syllables - normal
  'ふぁ'=>'fa','ふぇ'=>'fe','ふぃ'=>'fi','ふぉ'=>'fo',
  'ちゃ'=>'cha','ちぇ'=>'che','ち'=>'chi','ちょ'=>'cho','ちゅ
'=>'chu',
  'ひゃ'=>'hya','ひぇ'=>'hye','ひぃ'=>'hyi','ひょ'=>'hyo','ひゅ
'=>'hyu',
  'びゃ'=>'bya','びぇ'=>'bye','びぃ'=>'byi','びょ'=>'byo','びゅ
'=>'byu',
  'ぎゃ'=>'pya','ぎぇ'=>'pye','ぎぃ'=>'pyi','ぎょ'=>'pyo','ぎゅ
'=>'pyu',
  'きゃ'=>'kya','きぇ'=>'kye','きぃ'=>'kyi','きょ'=>'kyo','きゅ
'=>'kyu',
  'ぎゃ'=>'gya','ぎぇ'=>'gye','ぎぃ'=>'gyi','ぎょ'=>'gyo','ぎゅ
'=>'gyu',
  'みゃ'=>'mya','みぇ'=>'mye','みぃ'=>'myi','みょ'=>'myo','みゅ
'=>'myu',
  'にゃ'=>'nya','にぇ'=>'nye','にぃ'=>'nyi','にょ'=>'nyo','にゅ
'=>'nyu',
  'りゃ'=>'rya','りぇ'=>'rye','りぃ'=>'ryi','りょ'=>'ryo','りゅ
'=>'ryu',
  'しゃ'=>'sha','しぇ'=>'she','し'=>'shi','しょ'=>'sho','しゅ
'=>'shu',
  'じゃ'=>'ja','じぇ'=>'je','じょ'=>'jo','じゅ
'=>'ju',
  'うぇ'=>'we','うぃ'=>'wi',
  'いぇ'=>'ye',

  // 2 character syllables, っ doubles the consonant after
  'っば'=>'bba','っべ'=>'bbe','っび'=>'bbi','っが'=>'bbo','っぶ'=>'bbu',
  'っぱ'=>'ppa','っぺ'=>'ppe','っぎ'=>'ppi','っぜ'=>'ppo','っぷ'=>'ppu',
  'った'=>'tta','っお'=>'tte','っち'=>'cchi','っず'=>'tto','っ぀'=>'ttsu',
  'っだ'=>'dda','っで'=>'dde','っぢ'=>'ddi','っど'=>'ddo','っづ'=>'ddu',
  'っが'=>'gga','っげ'=>'gge','っぎ'=>'ggi','っご'=>'ggo','っぐ'=>'ggu',
  'っか'=>'kka','っけ'=>'kke','っき'=>'kki','っこ'=>'kko','っく'=>'kku',
  'った'=>'mma','っめ'=>'mme','っみ'=>'mmi','っも'=>'mmo','っむ'=>'mmu',
  'っな'=>'nna','っね'=>'nne','っに'=>'nni','っの'=>'nno','っぬ'=>'nnu',
  'っら'=>'rra','っれ'=>'rre','っり'=>'rri','っろ'=>'rro','っる'=>'rru',
  'っさ'=>'ssa','っせ'=>'sse','っし'=>'sshi','っそ'=>'sso','っす'=>'ssu',
  'っざ'=>'zza','っぜ'=>'zze','っじ'=>'jji','っぞ'=>'zzo','っず'=>'zzu',

  // 1 character syllabels
  'あ'=>'a','え'=>'e','い'=>'i','お'=>'o','う'=>'u','ん'=>'n',
  'は'=>'ha','ぞ'=>'he','ひ'=>'hi','ほ'=>'ho','ふ'=>'fu',
  'ば'=>'ba','べ'=>'be','び'=>'bi','が'=>'bo','ぶ'=>'bu',
  'ぱ'=>'pa','ぺ'=>'pe','ぎ'=>'pi','ぜ'=>'po','ぷ'=>'pu',
  'た'=>'ta','お'=>'te','ち'=>'chi','ず'=>'to','぀'=>'tsu',
  'だ'=>'da','で'=>'de','ぢ'=>'di','ど'=>'do','づ'=>'du',
  'が'=>'ga','げ'=>'ge','ぎ'=>'gi','ご'=>'go','ぐ'=>'gu',
  'か'=>'ka','け'=>'ke','き'=>'ki','こ'=>'ko','く'=>'ku',
  'た'=>'ma','め'=>'me','み'=>'mi','も'=>'mo','む'=>'mu',
  'な'=>'na','ね'=>'ne','に'=>'ni','の'=>'no','ぬ'=>'nu',
  'ら'=>'ra','れ'=>'re','り'=>'ri','ろ'=>'ro','る'=>'ru',
  'さ'=>'sa','せ'=>'se','し'=>'shi','そ'=>'so','す'=>'su',
  'わ'=>'wa','を'=>'wo',
  'ざ'=>'za','ぜ'=>'ze','じ'=>'ji','ぞ'=>'zo','ず'=>'zu',
  'や'=>'ya','よ'=>'yo','ゆ'=>'yu',
  // old characters
  'ゑ'=>'we','ゐ'=>'wi',

  //  convert what's left (probably only kicks in when something's missing above)
  // 'ぁ'=>'a','ぇ'=>'e','ぃ'=>'i','ぉ'=>'o','ぅ
'=>'u',
  // 'ゃ'=>'ya','ょ'=>'yo','ゅ
'=>'yu',

  // never seen one of those (disabled for the moment)
  // 'ノぁ'=>'va','ノぇ'=>'ve','ノぃ'=>'vi','ノぉ'=>'vo','ノ'=>'vu',
  // 'でゃ'=>'dha','でぇ'=>'dhe','でぃ'=>'dhi','でょ'=>'dho','でゅ
'=>'dhu',
  // 'どぁ'=>'dwa','どぇ'=>'dwe','どぃ'=>'dwi','どぉ'=>'dwo','どぅ
'=>'dwu',
  // 'ぢゃ'=>'dya','ぢぇ'=>'dye','ぢぃ'=>'dyi','ぢょ'=>'dyo','ぢゅ
'=>'dyu',
  // 'ふぁ'=>'fwa','ふぇ'=>'fwe','ふぃ'=>'fwi','ふぉ'=>'fwo','ふぅ
'=>'fwu',
  // 'ふゃ'=>'fya','ふぇ'=>'fye','ふぃ'=>'fyi','ふょ'=>'fyo','ふゅ
'=>'fyu',
  // 'すぁ'=>'swa','すぇ'=>'swe','すぃ'=>'swi','すぉ'=>'swo','すぅ
'=>'swu',
  // 'おゃ'=>'tha','おぇ'=>'the','おぃ'=>'thi','おょ'=>'tho','おゅ
'=>'thu',
  // '぀ゃ'=>'tsa','぀ぇ'=>'tse','぀ぃ'=>'tsi','぀ょ'=>'tso','぀'=>'tsu',
  // 'ずぁ'=>'twa','ずぇ'=>'twe','ずぃ'=>'twi','ずぉ'=>'two','ずぅ
'=>'twu',
  // 'ノゃ'=>'vya','ノぇ'=>'vye','ノぃ'=>'vyi','ノょ'=>'vyo','ノゅ
'=>'vyu',
  // 'うぁ'=>'wha','うぇ'=>'whe','うぃ'=>'whi','うぉ'=>'who','うぅ
'=>'whu',
  // 'じゃ'=>'zha','じぇ'=>'zhe','じぃ'=>'zhi','じょ'=>'zho','じゅ
'=>'zhu',
  // 'じゃ'=>'zya','じぇ'=>'zye','じぃ'=>'zyi','じょ'=>'zyo','じゅ
'=>'zyu',

  // 'spare' characters from other romanization systems
  // 'だ'=>'da','で'=>'de','ぢ'=>'di','ど'=>'do','づ'=>'du',
  // 'ら'=>'la','れ'=>'le','り'=>'li','ろ'=>'lo','る'=>'lu',
  // 'さ'=>'sa','せ'=>'se','し'=>'si','そ'=>'so','す'=>'su',
  // 'ちゃ'=>'cya','ちぇ'=>'cye','ちぃ'=>'cyi','ちょ'=>'cyo','ちゅ
'=>'cyu',
  //'じゃ'=>'jya','じぇ'=>'jye','じぃ'=>'jyi','じょ'=>'jyo','じゅ
'=>'jyu',
  //'りゃ'=>'lya','りぇ'=>'lye','りぃ'=>'lyi','りょ'=>'lyo','りゅ
'=>'lyu',
  //'しゃ'=>'sya','しぇ'=>'sye','しぃ'=>'syi','しょ'=>'syo','しゅ
'=>'syu',
  //'ちゃ'=>'tya','ちぇ'=>'tye','ちぃ'=>'tyi','ちょ'=>'tyo','ちゅ
'=>'tyu',
  //'し'=>'ci',,い'=>'yi','ぢ'=>'dzi',
  //'っじゃ'=>'jja','っじぇ'=>'jje','っじ'=>'jji','っじょ'=>'jjo','っじゅ
'=>'jju',


  // Japanese katakana

  // 4 character syllables: ッ doubles the consonant after, ヌ doubles the vowel before (usualy written with macron, but we don't want that in our URLs)
  'ッビャヌ'=>'bbyaa','ッビェヌ'=>'bbyee','ッビィヌ'=>'bbyii','ッビョヌ'=>'bbyoo','ッビュヌ'=>'bbyuu',
  'ッピャヌ'=>'ppyaa','ッピェヌ'=>'ppyee','ッピィヌ'=>'ppyii','ッピョヌ'=>'ppyoo','ッピュヌ'=>'ppyuu',
  'ッキャヌ'=>'kkyaa','ッキェヌ'=>'kkyee','ッキィヌ'=>'kkyii','ッキョヌ'=>'kkyoo','ッキュヌ'=>'kkyuu',
  'ッギャヌ'=>'ggyaa','ッギェヌ'=>'ggyee','ッギィヌ'=>'ggyii','ッギョヌ'=>'ggyoo','ッギュヌ'=>'ggyuu',
  'ッミャヌ'=>'mmyaa','ッミェヌ'=>'mmyee','ッミィヌ'=>'mmyii','ッミョヌ'=>'mmyoo','ッミュヌ'=>'mmyuu',
  'ッニャヌ'=>'nnyaa','ッニェヌ'=>'nnyee','ッニィヌ'=>'nnyii','ッニョヌ'=>'nnyoo','ッニュヌ'=>'nnyuu',
  'ッリャヌ'=>'rryaa','ッリェヌ'=>'rryee','ッリィヌ'=>'rryii','ッリョヌ'=>'rryoo','ッリュヌ'=>'rryuu',
  'ッシャヌ'=>'sshaa','ッシェヌ'=>'sshee','ッシヌ'=>'sshii','ッショヌ'=>'sshoo','ッシュヌ'=>'sshuu',
  'ッチャヌ'=>'cchaa','ッチェヌ'=>'cchee','ッチヌ'=>'cchii','ッチョヌ'=>'cchoo','ッチュヌ'=>'cchuu',
  'ッティヌ'=>'ttii',
  'ッヂィヌ'=>'ddii',

  // 3 character syllables - doubled vowels
  'ファヌ'=>'faa','フェヌ'=>'fee','フィヌ'=>'fii','フォヌ'=>'foo',
  'フャヌ'=>'fyaa','フェヌ'=>'fyee','フィヌ'=>'fyii','フョヌ'=>'fyoo','フュヌ'=>'fyuu',
  'ヒャヌ'=>'hyaa','ヒェヌ'=>'hyee','ヒィヌ'=>'hyii','ヒョヌ'=>'hyoo','ヒュヌ'=>'hyuu',
  'ビャヌ'=>'byaa','ビェヌ'=>'byee','ビィヌ'=>'byii','ビョヌ'=>'byoo','ビュヌ'=>'byuu',
  'ピャヌ'=>'pyaa','ピェヌ'=>'pyee','ピィヌ'=>'pyii','ピョヌ'=>'pyoo','ピュヌ'=>'pyuu',
  'キャヌ'=>'kyaa','キェヌ'=>'kyee','キィヌ'=>'kyii','キョヌ'=>'kyoo','キュヌ'=>'kyuu',
  'ギャヌ'=>'gyaa','ギェヌ'=>'gyee','ギィヌ'=>'gyii','ギョヌ'=>'gyoo','ギュヌ'=>'gyuu',
  'ミャヌ'=>'myaa','ミェヌ'=>'myee','ミィヌ'=>'myii','ミョヌ'=>'myoo','ミュヌ'=>'myuu',
  'ニャヌ'=>'nyaa','ニェヌ'=>'nyee','ニィヌ'=>'nyii','ニョヌ'=>'nyoo','ニュヌ'=>'nyuu',
  'リャヌ'=>'ryaa','リェヌ'=>'ryee','リィヌ'=>'ryii','リョヌ'=>'ryoo','リュヌ'=>'ryuu',
  'シャヌ'=>'shaa','シェヌ'=>'shee','シヌ'=>'shii','ショヌ'=>'shoo','シュヌ'=>'shuu',
  'ゞャヌ'=>'jaa','ゞェヌ'=>'jee','ゞヌ'=>'jii','ゞョヌ'=>'joo','ゞュヌ'=>'juu',
  'スァヌ'=>'swaa','スェヌ'=>'swee','スィヌ'=>'swii','スォヌ'=>'swoo','スゥヌ'=>'swuu',
  'デァヌ'=>'daa','デェヌ'=>'dee','ディヌ'=>'dii','デォヌ'=>'doo','デゥヌ'=>'duu',
  'チャヌ'=>'chaa','チェヌ'=>'chee','チヌ'=>'chii','チョヌ'=>'choo','チュヌ'=>'chuu',
  'ヂャヌ'=>'dyaa','ヂェヌ'=>'dyee','ヂィヌ'=>'dyii','ヂョヌ'=>'dyoo','ヂュヌ'=>'dyuu',
  'ツャヌ'=>'tsaa','ツェヌ'=>'tsee','ツィヌ'=>'tsii','ツョヌ'=>'tsoo','ツヌ'=>'tsuu',
  'トァヌ'=>'twaa','トェヌ'=>'twee','トィヌ'=>'twii','トォヌ'=>'twoo','トゥヌ'=>'twuu',
  'ドァヌ'=>'dwaa','ドェヌ'=>'dwee','ドィヌ'=>'dwii','ドォヌ'=>'dwoo','ドゥヌ'=>'dwuu',
  'りァヌ'=>'whaa','りェヌ'=>'whee','りィヌ'=>'whii','りォヌ'=>'whoo','りゥヌ'=>'whuu',
  'ノャヌ'=>'vyaa','ノェヌ'=>'vyee','ノィヌ'=>'vyii','ノョヌ'=>'vyoo','ノュヌ'=>'vyuu',
  'ノァヌ'=>'vaa','ノェヌ'=>'vee','ノィヌ'=>'vii','ノォヌ'=>'voo','ノヌ'=>'vuu',
  'りェヌ'=>'wee','りィヌ'=>'wii',
  'むェヌ'=>'yee',
  'ティヌ'=>'tii',
  'ヂィヌ'=>'dii',

  // 3 character syllables - doubled consonants
  'ッビャ'=>'bbya','ッビェ'=>'bbye','ッビィ'=>'bbyi','ッビョ'=>'bbyo','ッビュ'=>'bbyu',
  'ッピャ'=>'ppya','ッピェ'=>'ppye','ッピィ'=>'ppyi','ッピョ'=>'ppyo','ッピュ'=>'ppyu',
  'ッキャ'=>'kkya','ッキェ'=>'kkye','ッキィ'=>'kkyi','ッキョ'=>'kkyo','ッキュ'=>'kkyu',
  'ッギャ'=>'ggya','ッギェ'=>'ggye','ッギィ'=>'ggyi','ッギョ'=>'ggyo','ッギュ'=>'ggyu',
  'ッミャ'=>'mmya','ッミェ'=>'mmye','ッミィ'=>'mmyi','ッミョ'=>'mmyo','ッミュ'=>'mmyu',
  'ッニャ'=>'nnya','ッニェ'=>'nnye','ッニィ'=>'nnyi','ッニョ'=>'nnyo','ッニュ'=>'nnyu',
  'ッリャ'=>'rrya','ッリェ'=>'rrye','ッリィ'=>'rryi','ッリョ'=>'rryo','ッリュ'=>'rryu',
  'ッシャ'=>'ssha','ッシェ'=>'sshe','ッシ'=>'sshi','ッショ'=>'ssho','ッシュ'=>'sshu',
  'ッチャ'=>'ccha','ッチェ'=>'cche','ッチ'=>'cchi','ッチョ'=>'ccho','ッチュ'=>'cchu',
  'ッティ'=>'tti',
  'ッヂィ'=>'ddi',

  // 3 character syllables - doubled vowel and consonants
  'ッバヌ'=>'bbaa','ッベヌ'=>'bbee','ッビヌ'=>'bbii','ッボヌ'=>'bboo','ッブヌ'=>'bbuu',
  'ッパヌ'=>'ppaa','ッペヌ'=>'ppee','ッピヌ'=>'ppii','ッポヌ'=>'ppoo','ップヌ'=>'ppuu',
  'ッケヌ'=>'kkee','ッキヌ'=>'kkii','ッコヌ'=>'kkoo','ックヌ'=>'kkuu','ッカヌ'=>'kkaa',
  'ッガヌ'=>'ggaa','ッゲヌ'=>'ggee','ッギヌ'=>'ggii','ッゎヌ'=>'ggoo','ッグヌ'=>'gguu',
  'ッマヌ'=>'maa','ッメヌ'=>'mee','ッミヌ'=>'mii','ッモヌ'=>'moo','ッムヌ'=>'muu',
  'ッナヌ'=>'nnaa','ッネヌ'=>'nnee','ッニヌ'=>'nnii','ッノヌ'=>'nnoo','ッヌヌ'=>'nnuu',
  'ッラヌ'=>'rraa','ッレヌ'=>'rree','ッリヌ'=>'rrii','ッロヌ'=>'rroo','ッルヌ'=>'rruu',
  'ッサヌ'=>'ssaa','ッセヌ'=>'ssee','ッシヌ'=>'sshii','ッ゜ヌ'=>'ssoo','ッスヌ'=>'ssuu',
  'ッザヌ'=>'zzaa','ッれヌ'=>'zzee','ッゞヌ'=>'jjii','ッゟヌ'=>'zzoo','ッズヌ'=>'zzuu',
  'ッタヌ'=>'ttaa','ッテヌ'=>'ttee','ッチヌ'=>'chii','ットヌ'=>'ttoo','ッツヌ'=>'ttsuu',
  'ッダヌ'=>'ddaa','ッデヌ'=>'ddee','ッヂヌ'=>'ddii','ッドヌ'=>'ddoo','ッヅ
ヌ'=>'dduu',

  // 2 character syllables - normal
  'ファ'=>'fa','フェ'=>'fe','フィ'=>'fi','フォ'=>'fo','フゥ'=>'fu',
  // 'フャ'=>'fya','フェ'=>'fye','フィ'=>'fyi','フョ'=>'fyo','フュ'=>'fyu',
  'フャ'=>'fa','フェ'=>'fe','フィ'=>'fi','フョ'=>'fo','フュ'=>'fu',
  'ヒャ'=>'hya','ヒェ'=>'hye','ヒィ'=>'hyi','ヒョ'=>'hyo','ヒュ'=>'hyu',
  'ビャ'=>'bya','ビェ'=>'bye','ビィ'=>'byi','ビョ'=>'byo','ビュ'=>'byu',
  'ピャ'=>'pya','ピェ'=>'pye','ピィ'=>'pyi','ピョ'=>'pyo','ピュ'=>'pyu',
  'キャ'=>'kya','キェ'=>'kye','キィ'=>'kyi','キョ'=>'kyo','キュ'=>'kyu',
  'ギャ'=>'gya','ギェ'=>'gye','ギィ'=>'gyi','ギョ'=>'gyo','ギュ'=>'gyu',
  'ミャ'=>'mya','ミェ'=>'mye','ミィ'=>'myi','ミョ'=>'myo','ミュ'=>'myu',
  'ニャ'=>'nya','ニェ'=>'nye','ニィ'=>'nyi','ニョ'=>'nyo','ニュ'=>'nyu',
  'リャ'=>'rya','リェ'=>'rye','リィ'=>'ryi','リョ'=>'ryo','リュ'=>'ryu',
  'シャ'=>'sha','シェ'=>'she','ショ'=>'sho','シュ'=>'shu',
  'ゞャ'=>'ja','ゞェ'=>'je','ゞョ'=>'jo','ゞュ'=>'ju',
  'スァ'=>'swa','スェ'=>'swe','スィ'=>'swi','スォ'=>'swo','スゥ'=>'swu',
  'デァ'=>'da','デェ'=>'de','ディ'=>'di','デォ'=>'do','デゥ'=>'du',
  'チャ'=>'cha','チェ'=>'che','チ'=>'chi','チョ'=>'cho','チュ'=>'chu',
  // 'ヂャ'=>'dya','ヂェ'=>'dye','ヂィ'=>'dyi','ヂョ'=>'dyo','ヂュ'=>'dyu',
  'ツャ'=>'tsa','ツェ'=>'tse','ツィ'=>'tsi','ツョ'=>'tso','ツ'=>'tsu',
  'トァ'=>'twa','トェ'=>'twe','トィ'=>'twi','トォ'=>'two','トゥ'=>'twu',
  'ドァ'=>'dwa','ドェ'=>'dwe','ドィ'=>'dwi','ドォ'=>'dwo','ドゥ'=>'dwu',
  'ã‚Šã‚¡'=>'wha','りェ'=>'whe','ã‚Šã‚£'=>'whi','ã‚Šã‚©'=>'who','ã‚Šã‚¥'=>'whu',
  'ノャ'=>'vya','ノェ'=>'vye','ノィ'=>'vyi','ノョ'=>'vyo','ノュ'=>'vyu',
  'ノァ'=>'va','ノェ'=>'ve','ノィ'=>'vi','ノォ'=>'vo','ノ'=>'vu',
  'りェ'=>'we','ã‚Šã‚£'=>'wi',
  'むェ'=>'ye',
  'ティ'=>'ti',
  'ヂィ'=>'di',

  // 2 character syllables - doubled vocal
  'アヌ'=>'aa','゚ヌ'=>'ee','むヌ'=>'ii','オヌ'=>'oo','りヌ'=>'uu',
  'ダヌ'=>'daa','デヌ'=>'dee','ヂヌ'=>'dii','ドヌ'=>'doo','ヅ
ヌ'=>'duu',
  'ハヌ'=>'haa','ヘヌ'=>'hee','ヒヌ'=>'hii','ホヌ'=>'hoo','フヌ'=>'fuu',
  'バヌ'=>'baa','ベヌ'=>'bee','ビヌ'=>'bii','ボヌ'=>'boo','ブヌ'=>'buu',
  'パヌ'=>'paa','ペヌ'=>'pee','ピヌ'=>'pii','ポヌ'=>'poo','プヌ'=>'puu',
  'ケヌ'=>'kee','キヌ'=>'kii','コヌ'=>'koo','クヌ'=>'kuu','カヌ'=>'kaa',
  'ガヌ'=>'gaa','ゲヌ'=>'gee','ギヌ'=>'gii','ゎヌ'=>'goo','グヌ'=>'guu',
  'マヌ'=>'maa','メヌ'=>'mee','ミヌ'=>'mii','モヌ'=>'moo','ムヌ'=>'muu',
  'ナヌ'=>'naa','ネヌ'=>'nee','ニヌ'=>'nii','ノヌ'=>'noo','ヌヌ'=>'nuu',
  'ラヌ'=>'raa','レヌ'=>'ree','リヌ'=>'rii','ロヌ'=>'roo','ルヌ'=>'ruu',
  'サヌ'=>'saa','セヌ'=>'see','シヌ'=>'shii','゜ヌ'=>'soo','スヌ'=>'suu',
  'ザヌ'=>'zaa','れヌ'=>'zee','ゞヌ'=>'jii','ゟヌ'=>'zoo','ズヌ'=>'zuu',
  'タヌ'=>'taa','テヌ'=>'tee','チヌ'=>'chii','トヌ'=>'too','ツヌ'=>'tsuu',
  'ワヌ'=>'waa','ヲヌ'=>'woo',
  'ダヌ'=>'yaa','ペヌ'=>'yoo','ナヌ'=>'yuu',
  'ヵヌ'=>'kaa','ヶヌ'=>'kee',
  // old characters
  'ヱヌ'=>'wee','ヰヌ'=>'wii',

  // seperate katakana 'n'
  'ンア'=>'n_a','ン゚'=>'n_e','ンむ'=>'n_i','ンオ'=>'n_o','ンり'=>'n_u',
  'ンダ'=>'n_ya','ンペ'=>'n_yo','ンナ'=>'n_yu',

  // 2 character syllables - doubled consonants
  'ッバ'=>'bba','ッベ'=>'bbe','ッビ'=>'bbi','ッボ'=>'bbo','ッブ'=>'bbu',
  'ッパ'=>'ppa','ッペ'=>'ppe','ッピ'=>'ppi','ッポ'=>'ppo','ップ'=>'ppu',
  'ッケ'=>'kke','ッキ'=>'kki','ッコ'=>'kko','ック'=>'kku','ッカ'=>'kka',
  'ッガ'=>'gga','ッゲ'=>'gge','ッギ'=>'ggi','ッゎ'=>'ggo','ッグ'=>'ggu',
  'ッマ'=>'ma','ッメ'=>'me','ッミ'=>'mi','ッモ'=>'mo','ッム'=>'mu',
  'ッナ'=>'nna','ッネ'=>'nne','ッニ'=>'nni','ッノ'=>'nno','ッヌ'=>'nnu',
  'ッラ'=>'rra','ッレ'=>'rre','ッリ'=>'rri','ッロ'=>'rro','ッル'=>'rru',
  'ッサ'=>'ssa','ッセ'=>'sse','ッシ'=>'sshi','ッ゜'=>'sso','ッス'=>'ssu',
  'ッザ'=>'zza','ッれ'=>'zze','ッゞ'=>'jji','ッゟ'=>'zzo','ッズ'=>'zzu',
  'ッタ'=>'tta','ッテ'=>'tte','ッチ'=>'cchi','ット'=>'tto','ッツ'=>'ttsu',
  'ッダ'=>'dda','ッデ'=>'dde','ッヂ'=>'ddi','ッド'=>'ddo','ッヅ
'=>'ddu',

  // 1 character syllables
  'ア'=>'a','ã‚š'=>'e','ã‚€'=>'i','オ'=>'o','ã‚Š'=>'u','ン'=>'n',
  'ハ'=>'ha','ヘ'=>'he','ヒ'=>'hi','ホ'=>'ho','フ'=>'fu',
  'バ'=>'ba','ベ'=>'be','ビ'=>'bi','ボ'=>'bo','ブ'=>'bu',
  'パ'=>'pa','ペ'=>'pe','ピ'=>'pi','ポ'=>'po','プ'=>'pu',
  'ケ'=>'ke','キ'=>'ki','コ'=>'ko','ク'=>'ku','カ'=>'ka',
  'ガ'=>'ga','ゲ'=>'ge','ギ'=>'gi','ã‚Ž'=>'go','グ'=>'gu',
  'マ'=>'ma','メ'=>'me','ミ'=>'mi','モ'=>'mo','ム'=>'mu',
  'ナ'=>'na','ネ'=>'ne','ニ'=>'ni','ノ'=>'no','ヌ'=>'nu',
  'ラ'=>'ra','レ'=>'re','リ'=>'ri','ロ'=>'ro','ル'=>'ru',
  'サ'=>'sa','セ'=>'se','シ'=>'shi','ã‚œ'=>'so','ス'=>'su',
  'ザ'=>'za','ã‚Œ'=>'ze','ã‚ž'=>'ji','ã‚Ÿ'=>'zo','ズ'=>'zu',
  'タ'=>'ta','テ'=>'te','チ'=>'chi','ト'=>'to','ツ'=>'tsu',
  'ダ'=>'da','デ'=>'de','ヂ'=>'di','ド'=>'do','ヅ
'=>'du',
  'ワ'=>'wa','ヲ'=>'wo',
  'ダ'=>'ya','ペ'=>'yo','ナ'=>'yu',
  'ヵ'=>'ka','ヶ'=>'ke',
  // old characters
  'ヱ'=>'we','ヰ'=>'wi',

  //  convert what's left (probably only kicks in when something's missing above)
  'ァ'=>'a','ェ'=>'e','ィ'=>'i','ォ'=>'o','ゥ'=>'u',
  'ャ'=>'ya','ョ'=>'yo','ュ'=>'yu',

  // special characters
  '・'=>'_','、'=>'_',
  'ヌ'=>'_', // when used with hiragana (seldom), this character would not be converted otherwise

  // 'ラ'=>'la','レ'=>'le','リ'=>'li','ロ'=>'lo','ル'=>'lu',
  // 'チャ'=>'cya','チェ'=>'cye','チィ'=>'cyi','チョ'=>'cyo','チュ'=>'cyu',
  //'デャ'=>'dha','デェ'=>'dhe','ディ'=>'dhi','デョ'=>'dho','デュ'=>'dhu',
  // 'リャ'=>'lya','リェ'=>'lye','リィ'=>'lyi','リョ'=>'lyo','リュ'=>'lyu',
  // 'テャ'=>'tha','テェ'=>'the','ティ'=>'thi','テョ'=>'tho','テュ'=>'thu',
  //'ファ'=>'fwa','フェ'=>'fwe','フィ'=>'fwi','フォ'=>'fwo','フゥ'=>'fwu',
  //'チャ'=>'tya','チェ'=>'tye','チィ'=>'tyi','チョ'=>'tyo','チュ'=>'tyu',
  // 'ゞャ'=>'jya','ゞェ'=>'jye','ã‚žã‚£'=>'jyi','ゞョ'=>'jyo','ゞュ'=>'jyu',
  // 'ゞャ'=>'zha','ゞェ'=>'zhe','ã‚žã‚£'=>'zhi','ゞョ'=>'zho','ゞュ'=>'zhu',
  //'ゞャ'=>'zya','ゞェ'=>'zye','ã‚žã‚£'=>'zyi','ゞョ'=>'zyo','ゞュ'=>'zyu',
  //'シャ'=>'sya','シェ'=>'sye','シィ'=>'syi','ショ'=>'syo','シュ'=>'syu',
  //'シ'=>'ci','フ'=>'hu',シ'=>'si','チ'=>'ti','ツ'=>'tu','ã‚€'=>'yi','ヂ'=>'dzi',

  // "Greeklish"
  'Γ'=>'G','Δ'=>'E','Θ'=>'Th','Λ'=>'L','Ξ'=>'X','Î '=>'P','Σ'=>'S','Ί'=>'F','Κ'=>'Ps',
  'γ'=>'g','ÎŽ'=>'e','Ξ'=>'th','λ'=>'l','Ο'=>'x','π'=>'p','σ'=>'s','φ'=>'f','ψ'=>'ps',

  // Thai
  'àž'=>'k','àž‚'=>'kh','àžƒ'=>'kh','àž„'=>'kh','àž…
'=>'kh','àž†'=>'kh','àž‡'=>'ng','àžˆ'=>'ch',
  'àž‰'=>'ch','àžŠ'=>'ch','àž‹'=>'s','àžŒ'=>'ch','àž'=>'y','àžŽ'=>'d','àž'=>'t','àž'=>'th',
  'àž‘'=>'d','àž’'=>'th','àž“'=>'n','àž”'=>'d','àž•'=>'t','àž–'=>'th','àž—'=>'th','àž˜'=>'th',
  'àž™'=>'n','àžš'=>'b','àž›'=>'p','àžœ'=>'ph','àž'=>'f','àžž'=>'ph','àžŸ'=>'f','àž '=>'ph',
  'àž¡'=>'m','àž¢'=>'y','àž£'=>'r','àž€'=>'rue','àž€à¹…
'=>'rue','àž¥'=>'l','àžŠ'=>'lue',
  'àžŠà¹…
'=>'lue','àž§'=>'w','àžš'=>'s','àž©'=>'s','àžª'=>'s','àž«'=>'h','àž¬'=>'l','àž®'=>'h',
  'àž°'=>'a','àž±'=>'a','àž£àž£'=>'a','àž²'=>'a','ๅ
'=>'a','àž³'=>'am','à¹àž²'=>'am',
  'àžŽ'=>'i','àžµ'=>'i','àž¶'=>'ue','àžµ'=>'ue','àžž'=>'u','àž¹'=>'u',
  'เ'=>'e','แ'=>'ae','โ'=>'o','àž­'=>'o',
  'àžµàž¢àž°'=>'ia','àžµàž¢'=>'ia','àž·àž­àž°'=>'uea','àž·àž­'=>'uea','àž±àž§àž°'=>'ua','àž±àž§'=>'ua',
  'ใ'=>'ai','ไ'=>'ai','àž±àž¢'=>'ai','àž²àž¢'=>'ai','àž²àž§'=>'ao',
  'àžžàž¢'=>'ui','àž­àž¢'=>'oi','àž·àž­àž¢'=>'ueai','àž§àž¢'=>'uai',
  'àžŽàž§'=>'io','à¹‡àž§'=>'eo','àžµàž¢àž§'=>'iao',
  '่'=>'','้'=>'','๊'=>'','๋'=>'','็'=>'',
  '์'=>'','๎'=>'','ํ'=>'','àžº'=>'',
  'ๆ'=>'2','๏'=>'o','àž¯'=>'-','๚'=>'-','๛'=>'-',
  '๐'=>'0','๑'=>'1','๒'=>'2','๓'=>'3','๔'=>'4',
  '๕'=>'5','๖'=>'6','๗'=>'7','๘'=>'8','๙'=>'9',

  // Korean
  'ㄱ'=>'k','ã…
‹'=>'kh','ㄲ'=>'kk','ㄷ'=>'t','ã…
Œ'=>'th','ã„ž'=>'tt','ã…
‚'=>'p',
  'ã…
'=>'ph','ã…
ƒ'=>'pp','ã…
ˆ'=>'c','ã…
Š'=>'ch','ã…
‰'=>'cc','ã…
…
'=>'s','ã…
†'=>'ss',
  'ã…
Ž'=>'h','ã…
‡'=>'ng','ã„Ž'=>'n','ㄹ'=>'l','ã…
'=>'m', 'ã…
'=>'a','ã…
“'=>'e','ã…
—'=>'o',
  'ã…
œ'=>'wu','ã…
¡'=>'u','ã…
£'=>'i','ã…
'=>'ay','ã…
”'=>'ey','ã…
š'=>'oy','ã…
˜'=>'wa','ã…
'=>'we',
  'ã…
Ÿ'=>'wi','ã…
™'=>'way','ã…
ž'=>'wey','ã…
¢'=>'uy','ã…
‘'=>'ya','ã…
•'=>'ye','ã…
›'=>'oy',
  'ã…
 '=>'yu','ã…
’'=>'yay','ã…
–'=>'yey',
);