/dokuwiki/html/inc/utf8.php
PHP | 1683 lines | 1013 code | 152 blank | 518 comment | 168 complexity | 965a4bb72bd4f2927804953e18c4cfe8 MD5 | raw file
Possible License(s): BSD-3-Clause, GPL-2.0
- <?php
- /**
- * UTF8 helper functions
- *
- * @license LGPL 2.1 (http://www.gnu.org/copyleft/lesser.html)
- * @author Andreas Gohr <andi@splitbrain.org>
- */
- /**
- * 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 <andreas.haerter@dev.mail-node.com>
- */
- function utf8_isASCII($str){
- return (preg_match('/(?:[^\x00-\x7F])/', $str) !== 1);
- }
- }
- if(!function_exists('utf8_strip')){
- /**
- * Strips all highbyte chars
- *
- * Returns a pure ASCII7 string
- *
- * @author Andreas Gohr <andi@splitbrain.org>
- */
- function utf8_strip($str){
- $ascii = '';
- $len = strlen($str);
- for($i=0; $i<$len; $i++){
- if(ord($str{$i}) <128){
- $ascii .= $str{$i};
- }
- }
- return $ascii;
- }
- }
- if(!function_exists('utf8_check')){
- /**
- * Tries to detect if a string is in Unicode encoding
- *
- * @author <bmorel@ssi.fr>
- * @link http://www.php.net/manual/en/function.utf8-encode.php
- */
- function utf8_check($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_basename')){
- /**
- * A locale independent basename() implementation
- *
- * works around a bug in PHP's basename() implementation
- *
- * @see basename()
- * @link https://bugs.php.net/bug.php?id=37738
- * @param string $path A path
- * @param string $suffix If the name component ends in suffix this will also be cut off
- * @return string
- */
- function utf8_basename($path, $suffix=''){
- $path = trim($path,'\\/');
- $rpos = max(strrpos($path, '/'), strrpos($path, '\\'));
- if($rpos) $path = substr($path, $rpos+1);
- $suflen = strlen($suffix);
- if($suflen && (substr($path, -$suflen) == $suffix)){
- $path = substr($path, 0, -$suflen);
- }
- return $path;
- }
- }
- if(!function_exists('utf8_strlen')){
- /**
- * Unicode aware replacement for strlen()
- *
- * utf8_decode() converts characters that are not in ISO-8859-1
- * to '?', which, for the purpose of counting, is alright - It's
- * even faster than mb_strlen.
- *
- * @author <chernyshevsky at hotmail dot com>
- * @see strlen()
- * @see utf8_decode()
- */
- function utf8_strlen($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 <hfuecks@gmail.com>
- * @author Chris Smith <chris@jalakai.co.uk>
- * @param string $str
- * @param int $offset number of UTF-8 characters offset (from left)
- * @param int $length (optional) length in UTF-8 characters from offset
- * @return mixed string or false if failure
- */
- function utf8_substr($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 $match[1];
- }
- }
- if(!function_exists('utf8_substr_replace')){
- /**
- * Unicode aware replacement for substr_replace()
- *
- * @author Andreas Gohr <andi@splitbrain.org>
- * @see substr_replace()
- */
- function utf8_substr_replace($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 <andi@splitbrain.org>
- * @see ltrim()
- * @param string $str
- * @param string $charlist
- * @return string
- */
- function utf8_ltrim($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 <andi@splitbrain.org>
- * @see rtrim()
- * @param string $str
- * @param string $charlist
- * @return string
- */
- function utf8_rtrim($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 <andi@splitbrain.org>
- * @see trim()
- * @param string $str
- * @param string $charlist
- * @return string
- */
- function utf8_trim($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 <leo@typolight.org>
- * @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,$UTF8_UPPER_TO_LOWER);
- }
- }
- if(!function_exists('utf8_strtoupper')){
- /**
- * This is a unicode aware replacement for strtoupper()
- *
- * Uses mb_string extension if available
- *
- * @author Leo Feyer <leo@typolight.org>
- * @see strtoupper()
- * @see utf8_strtoupper()
- */
- function utf8_strtoupper($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 $matches matches corresponding to a single word
- * @return string with first char of the word in uppercase
- * @see utf8_ucwords
- * @see utf8_strtoupper
- */
- function utf8_ucwords_callback($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 <andi@splitbrain.org>
- */
- 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 $string;
- }
- }
- if(!function_exists('utf8_romanize')){
- /**
- * Romanize a non-latin string
- *
- * @author Andreas Gohr <andi@splitbrain.org>
- */
- function utf8_romanize($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 <andi@splitbrain.org>
- * @param string $string The UTF8 string to strip of special chars
- * @param string $repl Replace special with this string
- * @param string $additional Additional chars to strip (used in regexp char class)
- * @return string
- */
- function utf8_stripspecials($string,$repl='',$additional=''){
- 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 <leo@typolight.org>
- * @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 $length;
- }
- }
- if(!function_exists('utf8_tohtml')){
- /**
- * Encodes UTF-8 characters to HTML entities
- *
- * @author Tom N Harris <tnharris@whoopdedo.org>
- * @author <vpribish at shopping dot com>
- * @link http://www.php.net/manual/en/function.utf8-decode.php
- */
- function utf8_tohtml ($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 $ret;
- }
- }
- if(!function_exists('utf8_unhtml')){
- /**
- * Decodes HTML entities to UTF-8 characters
- *
- * Convert any &#..; entity to a codepoint,
- * The entities flag defaults to only decoding numeric entities.
- * Pass HTML_ENTITIES and named entities, including & < etc.
- * are handled as well. Avoids the problem that would occur if you
- * had to decode "&#38;&amp;#38;"
- *
- * unhtmlspecialchars(utf8_unhtml($s)) -> "&&"
- * utf8_unhtml(unhtmlspecialchars($s)) -> "&&#38;"
- * what it should be -> "&&#38;"
- *
- * @author Tom N Harris <tnharris@whoopdedo.org>
- * @param string $str UTF-8 encoded string
- * @param boolean $entities Flag controlling decoding of named entities.
- * @return string UTF-8 encoded string with numeric (and named) entities replaced.
- */
- function utf8_unhtml($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')){
- /**
- * Decodes numeric HTML entities to their correct UTF-8 characters
- *
- * @param $ent string A numeric entity
- * @return string
- */
- function utf8_decode_numeric($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')){
- /**
- * Encapsulate HTML entity decoding tables
- */
- class utf8_entity_decoder {
- var $table;
- /**
- * Initializes the decoding tables
- */
- function __construct() {
- $table = get_html_translation_table(HTML_ENTITIES);
- $table = array_flip($table);
- $this->table = array_map(array(&$this,'makeutf8'), $table);
- }
- /**
- * Wrapper aorund unicode_to_utf8()
- *
- * @param $c string
- * @return mixed
- */
- function makeutf8($c) {
- return unicode_to_utf8(array(ord($c)));
- }
- /**
- * Decodes any HTML entity to it's correct UTF-8 char equivalent
- *
- * @param $ent string An entity
- * @return string
- */
- function decode($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 <hsivonen@iki.fi>
- * @author Harry Fuecks <hfuecks@gmail.com>
- * @param string $str UTF-8 encoded string
- * @param boolean $strict Check for invalid sequences?
- * @return mixed array of unicode code points or false if UTF-8 invalid
- * @see unicode_to_utf8
- * @link http://hsivonen.iki.fi/php-utf8/
- * @link http://sourceforge.net/projects/phputf8/
- */
- function utf8_to_unicode($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 $arr of unicode code points representing a string
- * @param boolean $strict Check for invalid sequences?
- * @return mixed UTF-8 string or false if array contains invalid code points
- * @author <hsivonen@iki.fi>
- * @author Harry Fuecks <hfuecks@gmail.com>
- * @see utf8_to_unicode
- * @link http://hsivonen.iki.fi/php-utf8/
- * @link http://sourceforge.net/projects/phputf8/
- */
- function unicode_to_utf8($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 <hfuecks@gmail.com>
- * @see http://www.w3.org/International/questions/qa-forms-utf-8
- * @param string $str to search
- * @param string $replace to replace bad bytes with (defaults to '?') - use ASCII
- * @return string
- */
- function utf8_bad_replace($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 $str now pointing to a utf8 character boundary
- *
- * @author chris smith <chris@jalakai.co.uk>
- */
- function utf8_correctIdx(&$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 <andi@splitbrain.org>
- */
- global $UTF8_LOWER_TO_UPPER;
- if(empty($UTF8_LOWER_TO_UPPER)) $UTF8_LOWER_TO_UPPER = array(
- "??š"=>"???","??™"=>"??š","??˜"=>"??¸","??—"=>"???","??–"=>"???","??•"=>"???","??”"=>"??´","??“"=>"???","??’"=>"???","??‘"=>"???",
- "???"=>"??°","???"=>"???","??Ž"=>"??Ž","???"=>"??","??Œ"=>"???","??‹"=>"???","??Š"=>"???","??‰"=>"??Š","??ˆ"=>"??¨","??‡"=>"??§",
- "??†"=>"???","??…"=>"???","??„"=>"??¤","??ƒ"=>"???","??‚"=>"???","?? "=>"???","á??"=>"á??","á??"=>"á??","á??"=>"á?Š","á?‘"=>"á?™",
- "á??"=>"á?˜","á?ƒ"=>"á?Œ","ážž"=>"Ι","áž?"=>"áž?","áž?"=>"ážš","áž°"=>"ី","ឧ"=>"áž?","áž?"=>"ណ","áž?"=>"áž","ឤ"=>"áž?",
- "áž?"=>"áž?","áž?"=>"áž?","áž?"=>"ដ","áž—"=>"áž&#x;","áž–"=>"ážž","áž•"=>"áž?","áž”"=>"ážœ","áž“"=>"áž›","áž’"=>"ážš","áž‘"=>"áž™",
- "áž?"=>"ម","ជ"=>"áž?","ឆ"=>"ណ","áž…"=>"áž?","áž„"=>"ឌ","ឃ"=>"áž‹","áž‚"=>"ដ","áž "=>"ញ","ក"=>"ឈ","á??"=>"á??",
- "á??"=>"á??","á??"=>"á??","á??"=>"á??","á?š"=>"á?š","á?¸"=>"á?¸","á??"=>"á?›","á??"=>"á?š","á??"=>"á?‹","á?´"=>"á?Š","á??"=>"á?‰",
- "á??"=>"á?ˆ","á??"=>"áž?","á?°"=>"áž?","á?§"=>"á??","á??"=>"á?Ž","á??"=>"á?","á?¤"=>"á??","á??"=>"á??","á??"=>"á??","á??"=>"á?Š",
- "á?—"=>"á?&#x;","á?•"=>"á??","á?“"=>"á?›","á?‘"=>"á?™","á?…"=>"á??","á?„"=>"á?Œ","á?ƒ"=>"á?‹","á?‚"=>"á?Š","á? "=>"á?‰","á?€"=>"á?ˆ",
- "á??"=>"á??","á??"=>"á?ž","á??"=>"á??","á?´"=>"á??","á??"=>"á??","á??"=>"á??","á??"=>"á?š","á?°"=>"á?¸","á?§"=>"á??","á??"=>"á?Ž",
- "á??"=>"á?","á?¤"=>"á??","á??"=>"á??","á??"=>"á??","á??"=>"á?Š","á?•"=>"á??","á?”"=>"á?œ","á?“"=>"á?›","á?’"=>"á?š","á?‘"=>"á?™",
- "á??"=>"á?˜","á?‡"=>"á??","á?†"=>"á?Ž","á?…"=>"á??","á?„"=>"á?Œ","á?ƒ"=>"á?‹","á?‚"=>"á?Š","á? "=>"á?‰","á?€"=>"á?ˆ","á?š"=>"á?¸",
- "á??"=>"á??","á??"=>"á?´","á??"=>"á??","á??"=>"á?°","á??"=>"á?Ž","á?"=>"á??","á??"=>"á??","á?Š"=>"á?¨","á?§"=>"á??","á??"=>"á?¤",
- "á??"=>"á??","á??"=>"á? ","á?&#x;"=>"á?ž","á??"=>"á?œ","á?›"=>"á?š","á?™"=>"á?˜","á?—"=>"á?–","á?•"=>"á?”","á?“"=>"á?’","á?‘"=>"á??",
- "á??"=>"á?Ž","á??"=>"á?Œ","á?‹"=>"á?Š","á?‰"=>"á?ˆ","á?‡"=>"á?†","á?…"=>"á?„","á?ƒ"=>"á?‚","á? "=>"á?€","á??"=>"á?ž","á??"=>"á??",
- "á??"=>"á??","á?š"=>"á?¸","á??"=>"á??","á??"=>"á?´","á??"=>"á??","á??"=>"á?°","á??"=>"á?Ž","á?"=>"á??","á??"=>"á??","á?Š"=>"á?¨",
- "á?§"=>"á??","á??"=>"á?¤","á??"=>"á??","á??"=>"á? ","á?›"=>"áš ","á?•"=>"á?”","á?“"=>"á?’","á?‘"=>"á??","á??"=>"á?Ž","á??"=>"á?Œ",
- "á?‹"=>"á?Š","á?‰"=>"á?ˆ","á?‡"=>"á?†","á?…"=>"á?„","á?ƒ"=>"á?‚","á? "=>"á?€","áš?"=>"ášž","áš?"=>"áš?","áš?"=>"áš?","ášš"=>"ᚸ",
- "áš?"=>"áš?","áš?"=>"áš´","áš?"=>"áš?","áš?"=>"áš°","áš?"=>"ᚎ","áš"=>"áš?","áš?"=>"áš?","ᚊ"=>"ᚨ","ᚧ"=>"áš?","áš?"=>"ᚤ",
- "áš?"=>"áš?","áš?"=>"áš ","áš&#x;"=>"ášž","áš?"=>"ášœ","áš›"=>"ášš","áš™"=>"ᚘ","áš—"=>"áš–","áš•"=>"áš”","áš“"=>"áš’","áš‘"=>"áš?",
- "�"=>"ᚎ","�"=>"ᚌ","ᚋ"=>"ᚊ","ᚉ"=>"ᚈ","ᚇ"=>"ᚆ","ᚅ"=>"ᚄ","ᚃ"=>"ᚂ","ᚠ"=>" ","�"=>"Ḟ","�"=>"�",
- "á¸?"=>"á¸?","Ḛ"=>"Ḹ","á¸?"=>"á¸?","á¸?"=>"Ḵ","á¸?"=>"á¸?","á¸?"=>"Ḱ","á¸?"=>"Ḏ","á¸"=>"á¸?","á¸?"=>"á¸?","Ḋ"=>"Ḩ",
- "ḧ"=>"á¸?","á¸?"=>"Ḥ","á¸?"=>"á¸?","á¸?"=>"Ḡ","á¸&#x;"=>"Ḟ","á¸?"=>"Ḝ","ḛ"=>"Ḛ","ḙ"=>"Ḙ","ḗ"=>"Ḗ","ḕ"=>"Ḕ",
- "ḓ"=>"Ḓ","ḑ"=>"�","�"=>"Ḏ","�"=>"Ḍ","ḋ"=>"Ḋ","ḉ"=>"Ḉ","ḇ"=>"Ḇ","ḅ"=>"Ḅ","ḃ"=>"Ḃ","Ḡ"=>"Ḁ",
- "Ö†"=>"?–","Ö…"=>"?•","Ö„"=>"?”","Öƒ"=>"?“","Ö‚"=>"?’","Ö "=>"?‘","Ö€"=>"??","??"=>"??","?ž"=>"?Ž","??"=>"??",
- "??"=>"?Œ","??"=>"?‹","??"=>"?Š","?š"=>"?‰","?¸"=>"?ˆ","??"=>"?‡","??"=>"?†","??"=>"?…","?´"=>"?„","??"=>"?ƒ",
- "??"=>"?‚","??"=>"? ","?°"=>"?€","??"=>"Ô?","?Ž"=>"Ôž","?"=>"Ô?","??"=>"Ô?","??"=>"Ô?","??"=>"Ô?","?Š"=>"Ôš",
- "?¨"=>"Ô¸","?§"=>"Ô?","??"=>"Ô?","??"=>"Ô?","?¤"=>"Ô´","??"=>"Ô?","??"=>"Ô?","??"=>"Ô?","Ô?"=>"ÔŽ","Ô?"=>"ÔŒ",
- "Ô‹"=>"ÔŠ","Ô‰"=>"Ôˆ","Ô‡"=>"Ô†","Ô…"=>"Ô„","Ôƒ"=>"Ô‚","Ô "=>"Ô€","Óš"=>"Ó¸","Ó?"=>"Ó´","Ó?"=>"Ó?","Ó?"=>"Ó°",
- "Ó?"=>"ÓŽ","Ó"=>"Ó?","Ó?"=>"Ó?","ÓŠ"=>"Ó¨","Ó§"=>"Ó?","Ó?"=>"Ó¤","Ó?"=>"Ó?","Ó?"=>"Ó ","Ó&#x;"=>"Óž","Ó?"=>"Óœ",
- "Ó›"=>"Óš","Ó™"=>"Ó˜","Ó—"=>"Ó–","Ó•"=>"Ó”","Ó“"=>"Ó’","Ó‘"=>"Ó?","ÓŽ"=>"Ó?","ÓŒ"=>"Ó‹","ÓŠ"=>"Ó‰","Óˆ"=>"Ó‡",
- "Ó†"=>"Ó…","Ó„"=>"Óƒ","Ó‚"=>"Ó ","??"=>"?ž","??"=>"??","??"=>"??","?š"=>"?¸","??"=>"??","??"=>"?´","??"=>"??",
- "??"=>"?°","??"=>"?Ž","?"=>"??","??"=>"??","?Š"=>"?¨","?§"=>"??","??"=>"?¤","??"=>"??","??"=>"? ","?&#x;"=>"?ž",
- "??"=>"?œ","?›"=>"?š","?™"=>"?˜","?—"=>"?–","?•"=>"?”","?“"=>"?’","?‘"=>"??","??"=>"?Ž","??"=>"?Œ","?‹"=>"?Š",
- "? "=>"?€","??"=>"?ž","??"=>"??","??"=>"??","?š"=>"?¸","??"=>"??","??"=>"?´","??"=>"??","??"=>"?°","??"=>"?Ž",
- "?"=>"??","??"=>"??","?Š"=>"?¨","?§"=>"??","??"=>"?¤","??"=>"??","??"=>"? ","?&#x;"=>"??","?ž"=>"?Ž","??"=>"??",
- "?œ"=>"?Œ","?›"=>"?‹","?š"=>"?Š","?™"=>"?‰","?˜"=>"?ˆ","?—"=>"?‡","?–"=>"?†","?•"=>"?…","?”"=>"?„","?“"=>"?ƒ",
- "?’"=>"?‚","?‘"=>"? ","??"=>"?€","??"=>"??","?Ž"=>"?Ž","??"=>"?","?Œ"=>"??","?‹"=>"??","?Š"=>"??","?‰"=>"?Š",
- "?ˆ"=>"?¨","?‡"=>"?§","?†"=>"??","?…"=>"??","?„"=>"?¤","?ƒ"=>"??","?‚"=>"??","? "=>"??","?€"=>"? ","??"=>"?&#x;",
- "?ž"=>"?ž","??"=>"??","??"=>"?œ","??"=>"?›","??"=>"?š","?š"=>"?™","?¸"=>"?˜","??"=>"?—","??"=>"?–","??"=>"?•",
- "?´"=>"?”","??"=>"?“","??"=>"?’","??"=>"?‘","?°"=>"??","??"=>"Ε","??"=>"Î?","??"=>"Î?","?°"=>"Κ","??"=>"?Ž",
- "?"=>"??","??"=>"??","?Š"=>"?¨","?§"=>"??","??"=>"?¤","??"=>"??","??"=>"? ","?&#x;"=>"?ž","??"=>"?œ","?›"=>"?š",
- "?™"=>"?˜","?–"=>"Î ","?•"=>"Î?","?‘"=>"Θ","??"=>"Î’","?Ž"=>"Î?","??"=>"ÎŽ","?Œ"=>"ÎŒ","?‹"=>"Î?","?Š"=>"Î?",
- "?‰"=>"Ί","?ˆ"=>"Ψ","?‡"=>"Χ","?†"=>"Î?","?…"=>"Î?","?„"=>"Τ","?ƒ"=>"Î?","?‚"=>"Î?","? "=>"Î?","?€"=>"Î ",
- "Î?"=>"Î&#x;","Ξ"=>"Ξ","Î?"=>"Î?","Î?"=>"Îœ","Î?"=>"Λ","Î?"=>"Κ","Κ"=>"Ι","θ"=>"Θ","Î?"=>"Η","Î?"=>"Ζ",
- "Î?"=>"Ε","δ"=>"Δ","Î?"=>"Γ","Î?"=>"Î’","Î?"=>"Α","Î?"=>"Ί","ÎŽ"=>"Ή","Î"=>"Έ","Î?"=>"Ά","?’"=>"??",
- "?‹"=>"??","?Š"=>"??","?ˆ"=>"?Ž","?ƒ"=>"?Š","?€"=>"??","É?"=>"?&#x;","É?"=>"??","É?"=>"?œ","ÉŠ"=>"?–","ɨ"=>"?—",
- "É?"=>"?”","É›"=>"??","É™"=>"??","É—"=>"?Š","É–"=>"?‰","É”"=>"?†","É“"=>"? ","??"=>"??","??"=>"?°","??"=>"?Ž",
- "?"=>"??","??"=>"??","?Š"=>"?¨","?§"=>"??","??"=>"?¤","??"=>"??","?&#x;"=>"?ž","??"=>"?œ","?›"=>"?š","?™"=>"?˜",
- "?—"=>"?–","?•"=>"?”","?“"=>"?’","?‘"=>"??","??"=>"?Ž","??"=>"?Œ","?‹"=>"?Š","?‰"=>"?ˆ","?‡"=>"?†","?…"=>"?„",
- "?ƒ"=>"?‚","? "=>"?€","Ç?"=>"Çž","Ç?"=>"Ç?","Ç?"=>"Ç?","Çš"=>"Ǹ","Ç?"=>"Ç´","Ç?"=>"Ç?","Ç?"=>"ÇŽ","Ç"=>"Ç?",
- "Ç?"=>"Ç?","ÇŠ"=>"Ǩ","ǧ"=>"Ç?","Ç?"=>"Ǥ","Ç?"=>"Ç?","Ç?"=>"Ç ","Ç&#x;"=>"Çž","Ç?"=>"?Ž","Çœ"=>"Ç›","Çš"=>"Ç™",
- "ǘ"=>"Ç—","Ç–"=>"Ç•","Ç”"=>"Ç“","Ç’"=>"Ç‘","Ç?"=>"Ç?","ÇŽ"=>"Ç?","ÇŒ"=>"Ç‹","lj"=>"Lj","dž"=>"Ç…","??"=>"Ç?",
- "??"=>"??","?š"=>"?¸","??"=>"??","?´"=>"??","?°"=>"??","?"=>"??","?¨"=>"?§","??"=>"?¤","??"=>"??","??"=>"? ",
- "?ž"=>"? ","?™"=>"?˜","?•"=>"Ç?","?’"=>"?‘","?Œ"=>"?‹","?ˆ"=>"?‡","?…"=>"?„","?ƒ"=>"?‚","??"=>"S","?ž"=>"??",
- "??"=>"??","??"=>"?š","??"=>"??","??"=>"?´","??"=>"??","??"=>"?°","??"=>"?Ž","?"=>"??","??"=>"??","?Š"=>"?¨",
- "?§"=>"??","??"=>"?¤","??"=>"??","??"=>"? ","?&#x;"=>"?ž","??"=>"?œ","?›"=>"?š","?™"=>"?˜","?—"=>"?–","?•"=>"?”",
- "?“"=>"?’","?‘"=>"??","??"=>"?Ž","??"=>"?Œ","?‹"=>"?Š","?ˆ"=>"?‡","?†"=>"?…","?„"=>"?ƒ","?‚"=>"? ","?€"=>"Ä?",
- "Äž"=>"Ä?","Ä?"=>"Ä?","Ä?"=>"Äš","Ä?"=>"Ä?","Ä?"=>"Ä´","Ä?"=>"Ä?","Ä?"=>"I","Ä?"=>"ÄŽ","Ä"=>"Ä?","Ä?"=>"Ä?",
- "ÄŠ"=>"Ĩ","ħ"=>"Ä?","Ä?"=>"Ĥ","Ä?"=>"Ä?","Ä?"=>"Ä ","Ä&#x;"=>"Äž","Ä?"=>"Äœ","Ä›"=>"Äš","Ä™"=>"Ę","Ä—"=>"Ä–",
- "Ä•"=>"Ä”","Ä“"=>"Ä’","Ä‘"=>"Ä?","Ä?"=>"ÄŽ","Ä?"=>"ÄŒ","Ä‹"=>"ÄŠ","ĉ"=>"Ĉ","ć"=>"Ć","Ä…"=>"Ä„","ă"=>"Ä‚",
- "Ä "=>"Ä€","??"=>"?¸","?ž"=>"?ž","??"=>"??","??"=>"?œ","??"=>"?›","??"=>"?š","?š"=>"?™","?¸"=>"?˜","??"=>"?–",
- "??"=>"?•","?´"=>"?”","??"=>"?“","??"=>"?’","??"=>"?‘","?°"=>"??","??"=>"??","?Ž"=>"?Ž","?"=>"??","??"=>"?Œ",
- "??"=>"?‹","??"=>"?Š","?Š"=>"?‰","?¨"=>"?ˆ","?§"=>"?‡","??"=>"?†","??"=>"?…","?¤"=>"?„","??"=>"?ƒ","??"=>"?‚",
- "??"=>"? ","? "=>"?€","Â?"=>"Îœ","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 corresponding
- * upper case letter in UTF-8
- *
- * @author Andreas Gohr <andi@splitbrain.org>
- */
- global $UTF8_UPPER_TO_LOWER;
- if(empty($UTF8_UPPER_TO_LOWER)) $UTF8_UPPER_TO_LOWER = array (
- "???"=>"??š","??š"=>"??™","??¸"=>"??˜","???"=>"??—","???"=>"??–","???"=>"??•","??´"=>"??”","???"=>"??“","???"=>"??’","???"=>"??‘",
- "??°"=>"???","???"=>"???","??Ž"=>"??Ž","??"=>"???","???"=>"??Œ","???"=>"??‹","???"=>"??Š","??Š"=>"??‰","??¨"=>"??ˆ","??§"=>"??‡",
- "???"=>"??†","???"=>"??…","??¤"=>"??„","???"=>"??ƒ","???"=>"??‚","???"=>"?? ","á??"=>"á??","á??"=>"á??","á?Š"=>"á??","á?™"=>"á?‘",
- "á?˜"=>"á??","á?Œ"=>"á?ƒ","Ι"=>"ážž","áž?"=>"áž?","ážš"=>"áž?","ី"=>"áž°","áž?"=>"ឧ","ណ"=>"áž?","áž"=>"áž?","áž?"=>"ឤ",
- "áž?"=>"áž?","áž?"=>"áž?","ដ"=>"áž?","áž&#x;"=>"áž—","ážž"=>"áž–","áž?"=>"áž•","ážœ"=>"áž”","áž›"=>"áž“","ážš"=>"áž’","áž™"=>"áž‘",
- "ម"=>"áž?","áž?"=>"ជ","ណ"=>"ឆ","áž?"=>"áž…","ឌ"=>"áž„","áž‹"=>"ឃ","ដ"=>"áž‚","ញ"=>"áž ","ឈ"=>"ក","á??"=>"á??",
- "á??"=>"á??","á??"=>"á??","á??"=>"á??","á?š"=>"á?š","á?¸"=>"á?¸","á?›"=>"á??","á?š"=>"á??","á?‹"=>"á??","á?Š"=>"á?´","á?‰"=>"á??",
- "á?ˆ"=>"á??","áž?"=>"á??","áž?"=>"á?°","á??"=>"á?§","á?Ž"=>"á??","á?"=>"á??","á??"=>"á?¤","á??"=>"á??","á??"=>"á??","á?Š"=>"á??",
- "á?&#x;"=>"á?—","á??"=>"á?•","á?›"=>"á?“","á?™"=>"á?‘","á??"=>"á?…","á?Œ"=>"á?„","á?‹"=>"á?ƒ","á?Š"=>"á?‚","á?‰"=>"á? ","á?ˆ"=>"á?€",
- "á??"=>"á??","á?ž"=>"á??","á??"=>"á??","á??"=>"á?´","á??"=>"á??","á??"=>"á??","á?š"=>"á??","á?¸"=>"á?°","á??"=>"á?§","á?Ž"=>"á??",
- "á?"=>"á??","á??"=>"á?¤","á??"=>"á??","á??"=>"á??","á?Š"=>"á??","á??"=>"á?•","á?œ"=>"á?”","á?›"=>"á?“","á?š"=>"á?’","á?™"=>"á?‘",
- "á?˜"=>"á??","á??"=>"á?‡","á?Ž"=>"á?†","á??"=>"á?…","á?Œ"=>"á?„","á?‹"=>"á?ƒ","á?Š"=>"á?‚","á?‰"=>"á? ","á?ˆ"=>"á?€","á?¸"=>"á?š",
- "á??"=>"á??","á?´"=>"á??","á??"=>"á??","á?°"=>"á??","á?Ž"=>"á??","á??"=>"á?","á??"=>"á??","á?¨"=>"á?Š","á??"=>"á?§","á?¤"=>"á??",
- "á??"=>"á??","á? "=>"á??","á?ž"=>"á?&#x;","á?œ"=>"á??","á?š"=>"á?›","á?˜"=>"á?™","á?–"=>"á?—","á?”"=>"á?•","á?’"=>"á?“","á??"=>"á?‘",
- "á?Ž"=>"á??","á?Œ"=>"á??","á?Š"=>"á?‹","á?ˆ"=>"á?‰","á?†"=>"á?‡","á?„"=>"á?…","á?‚"=>"á?ƒ","á?€"=>"á? ","á?ž"=>"á??","á??"=>"á??",
- "á??"=>"á??","á?¸"=>"á?š","á??"=>"á??","á?´"=>"á??","á??"=>"á??","á?°"=>"á??","á?Ž"=>"á??","á??"=>"á?","á??"=>"á??","á?¨"=>"á?Š",
- "á??"=>"á?§","á?¤"=>"á??","á??"=>"á??","á? "=>"á??","áš "=>"á?›","á?”"=>"á?•","á?’"=>"á?“","á??"=>"á?‘","á?Ž"=>"á??","á?Œ"=>"á??",
- "á?Š"=>"á?‹","á?ˆ"=>"á?‰","á?†"=>"á?‡","á?„"=>"á?…","á?‚"=>"á?ƒ","á?€"=>"á? ","ášž"=>"áš?","áš?"=>"áš?","áš?"=>"áš?","ᚸ"=>"ášš",
- "áš?"=>"áš?","áš´"=>"áš?","áš?"=>"áš?","áš°"=>"áš?","ᚎ"=>"áš?","áš?"=>"áš","áš?"=>"áš?","ᚨ"=>"ᚊ","áš?"=>"ᚧ","ᚤ"=>"áš?",
- "áš?"=>"áš?","áš "=>"áš?","ášž"=>"áš&#x;","ášœ"=>"áš?","ášš"=>"áš›","ᚘ"=>"áš™","áš–"=>"áš—","áš”"=>"áš•","áš’"=>"áš“","áš?"=>"áš‘",
- "ᚎ"=>"�","ᚌ"=>"�","ᚊ"=>"ᚋ","ᚈ"=>"ᚉ","ᚆ"=>"ᚇ","ᚄ"=>"ᚅ","ᚂ"=>"ᚃ"," "=>"ᚠ","Ḟ"=>"�","�"=>"�",
- "á¸?"=>"á¸?","Ḹ"=>"Ḛ","á¸?"=>"á¸?","Ḵ"=>"á¸?","á¸?"=>"á¸?","Ḱ"=>"á¸?","Ḏ"=>"á¸?","á¸?"=>"á¸","á¸?"=>"á¸?","Ḩ"=>"Ḋ",
- "á¸?"=>"ḧ","Ḥ"=>"á¸?","á¸?"=>"á¸?","Ḡ"=>"á¸?","Ḟ"=>"á¸&#x;","Ḝ"=>"á¸?","Ḛ"=>"ḛ","Ḙ"=>"ḙ","Ḗ"=>"ḗ","Ḕ"=>"ḕ",
- "Ḓ"=>"ḓ","�"=>"ḑ","Ḏ"=>"�","Ḍ"=>"�","Ḋ"=>"ḋ","Ḉ"=>"ḉ","Ḇ"=>"ḇ","Ḅ"=>"ḅ","Ḃ"=>"ḃ","Ḁ"=>"Ḡ",
- "?–"=>"Ö†","?•"=>"Ö…","?”"=>"Ö„","?“"=>"Öƒ","?’"=>"Ö‚","?‘"=>"Ö ","??"=>"Ö€","??"=>"??","?Ž"=>"?ž","??"=>"??",
- "?Œ"=>"??","?‹"=>"??","?Š"=>"??","?‰"=>"?š","?ˆ"=>"?¸","?‡"=>"??","?†"=>"??","?…"=>"??","?„"=>"?´","?ƒ"=>"??",
- "?‚"=>"??","? "=>"??","?€"=>"?°","Ô?"=>"??","Ôž"=>"?Ž","Ô?"=>"?","Ô?"=>"??","Ô?"=>"??","Ô?"=>"??","Ôš"=>"?Š",
- "Ô¸"=>"?¨","Ô?"=>"?§","Ô?"=>"??","Ô?"=>"??","Ô´"=>"?¤","Ô?"=>"??","Ô?"=>"??","Ô?"=>"??","ÔŽ"=>"Ô?","ÔŒ"=>"Ô?",
- "ÔŠ"=>"Ô‹","Ôˆ"=>"Ô‰","Ô†"=>"Ô‡","Ô„"=>"Ô…","Ô‚"=>"Ôƒ","Ô€"=>"Ô ","Ó¸"=>"Óš","Ó´"=>"Ó?","Ó?"=>"Ó?","Ó°"=>"Ó?",
- "ÓŽ"=>"Ó?","Ó?"=>"Ó","Ó?"=>"Ó?","Ó¨"=>"ÓŠ","Ó?"=>"Ó§","Ó¤"=>"Ó?","Ó?"=>"Ó?","Ó "=>"Ó?","Óž"=>"Ó&#x;","Óœ"=>"Ó?",
- "Óš"=>"Ó›","Ó˜"=>"Ó™","Ó–"=>"Ó—","Ó”"=>"Ó•","Ó’"=>"Ó“","Ó?"=>"Ó‘","Ó?"=>"ÓŽ","Ó‹"=>"ÓŒ","Ó‰"=>"ÓŠ","Ó‡"=>"Óˆ",
- "Ó…"=>"Ó†","Óƒ"=>"Ó„","Ó "=>"Ó‚","?ž"=>"??","??"=>"??","??"=>"??","?¸"=>"?š","??"=>"??","?´"=>"??","??"=>"??",
- "?°"=>"??","?Ž"=>"??","??"=>"?","??"=>"??","?¨"=>"?Š","??"=>"?§","?¤"=>"??","??"=>"??","? "=>"??","?ž"=>"?&#x;",
- "?œ"=>"??","?š"=>"?›","?˜"=>"?™","?–"=>"?—","?”"=>"?•","?’"=>"?“","??"=>"?‘","?Ž"=>"??","?Œ"=>"??","?Š"=>"?‹",
- "?€"=>"? ","?ž"=>"??","??"=>"??","??"=>"??","?¸"=>"?š","??"=>"??","?´"=>"??","??"=>"??","?°"=>"??","?Ž"=>"??",
- "??"=>"?","??"=>"??","?¨"=>"?Š","??"=>"?§","?¤"=>"??","??"=>"??","? "=>"??","??"=>"?&#x;","?Ž"=>"?ž","??"=>"??",
- "?Œ"=>"?œ","?‹"=>"?›","?Š"=>"?š","?‰"=>"?™","?ˆ"=>"?˜","?‡"=>"?—","?†"=>"?–","?…"=>"?•","?„"=>"?”","?ƒ"=>"?“",
- "?‚"=>"?’","? "=>"?‘","?€"=>"??","??"=>"??","?Ž"=>"?Ž","?"=>"??","??"=>"?Œ","??"=>"?‹","??"=>"?Š","?Š"=>"?‰",
- "?¨"=>"?ˆ","?§"=>"?‡","??"=>"?†","??"=>"?…","?¤"=>"?„","??"=>"?ƒ","??"=>"?‚","??"=>"? ","? "=>"?€","?&#x;"=>"??",
- "?ž"=>"?ž","??"=>"??","?œ"=>"??","?›"=>"??","?š"=>"??","?™"=>"?š","?˜"=>"?¸","?—"=>"??","?–"=>"??","?•"=>"??",
- "?”"=>"?´","?“"=>"??","?’"=>"??","?‘"=>"??","??"=>"?°","Ε"=>"??","Î?"=>"??","Î?"=>"??","Κ"=>"?°","?Ž"=>"??",
- "??"=>"?","??"=>"??","?¨"=>"?Š","??"=>"?§","?¤"=>"??","??"=>"??","? "=>"??","?ž"=>"?&#x;","?œ"=>"??","?š"=>"?›",
- "?˜"=>"?™","Î "=>"?–","Î?"=>"?•","Θ"=>"?‘","Î’"=>"??","Î?"=>"?Ž","ÎŽ"=>"??","ÎŒ"=>"?Œ","Î?"=>"?‹","Î?"=>"?Š",
- "Ί"=>"?‰","Ψ"=>"?ˆ","Χ"=>"?‡","Î?"=>"?†","Î?"=>"?…","Τ"=>"?„","Î?"=>"?ƒ","Î?"=>"?‚","Î?"=>"? ","Î "=>"?€",
- "Î&#x;"=>"Î?","Ξ"=>"Ξ","Î?"=>"Î?","Îœ"=>"Î?","Λ"=>"Î?","Κ"=>"Î?","Ι"=>"Κ","Θ"=>"θ","Η"=>"Î?","Ζ"=>"Î?",
- "Ε"=>"Î?","Δ"=>"δ","Γ"=>"Î?","Î’"=>"Î?","Α"=>"Î?","Ί"=>"Î?","Ή"=>"ÎŽ","Έ"=>"Î","Ά"=>"Î?","??"=>"?’",
- "??"=>"?‹","??"=>"?Š","?Ž"=>"?ˆ","?Š"=>"?ƒ","??"=>"?€","?&#x;"=>"É?","??"=>"É?","?œ"=>"É?","?–"=>"ÉŠ","?—"=>"ɨ",
- "?”"=>"É?","??"=>"É›","??"=>"É™","?Š"=>"É—","?‰"=>"É–","?†"=>"É”","? "=>"É“","??"=>"??","?°"=>"??","?Ž"=>"??",
- "??"=>"?","??"=>"??","?¨"=>"?Š","??"=>"?§","?¤"=>"??","??"=>"??","?ž"=>"?&#x;","?œ"=>"??","?š"=>"?›","?˜"=>"?™",
- "?–"=>"?—","?”"=>"?•","?’"=>"?“","??"=>"?‘","?Ž"=>"??","?Œ"=>"??","?Š"=>"?‹","?ˆ"=>"?‰","?†"=>"?‡","?„"=>"?…",
- "?‚"=>"?ƒ","?€"=>"? ","Çž"=>"Ç?","Ç?"=>"Ç?","Ç?"=>"Ç?","Ǹ"=>"Çš","Ç´"=>"Ç?","Ç?"=>"Ç?","ÇŽ"=>"Ç?","Ç?"=>"Ç",
- "Ç?"=>"Ç?","Ǩ"=>"ÇŠ","Ç?"=>"ǧ","Ǥ"=>"Ç?","Ç?"=>"Ç?","Ç "=>"Ç?","Çž"=>"Ç&#x;","?Ž"=>"Ç?","Ç›"=>"Çœ","Ç™"=>"Çš",
- "Ç—"=>"ǘ","Ç•"=>"Ç–","Ç“"=>"Ç”","Ç‘"=>"Ç’","Ç?"=>"Ç?","Ç?"=>"ÇŽ","Ç‹"=>"ÇŒ","Lj"=>"lj","Ç…"=>"dž","Ç?"=>"??",
- "??"=>"??","?¸"=>"?š","??"=>"??","??"=>"?´","??"=>"?°","??"=>"?","?§"=>"?¨","?¤"=>"??","??"=>"??","? "=>"??",
- "? "=>"?ž","?˜"=>"?™","Ç?"=>"?•","?‘"=>"?’","?‹"=>"?Œ","?‡"=>"?ˆ","?„"=>"?…","?‚"=>"?ƒ","S"=>"??","??"=>"?ž",
- "??"=>"??","?š"=>"??","??"=>"??","?´"=>"??","??"=>"??","?°"=>"??","?Ž"=>"??","??"=>"?","??"=>"??","?¨"=>"?Š",
- "??"=>"?§","?¤"=>"??","??"=>"??","? "=>"??","?ž"=>"?&#x;","?œ"=>"??","?š"=>"?›","?˜"=>"?™","?–"=>"?—","?”"=>"?•",
- "?’"=>"?“","??"=>"?‘","?Ž"=>"??","?Œ"=>"??","?Š"=>"?‹","?‡"=>"?ˆ","?…"=>"?†","?ƒ"=>"?„","? "=>"?‚","Ä?"=>"?€",
- "Ä?"=>"Äž","Ä?"=>"Ä?","Äš"=>"Ä?","Ä?"=>"Ä?","Ä´"=>"Ä?","Ä?"=>"Ä?","I"=>"Ä?","ÄŽ"=>"Ä?","Ä?"=>"Ä","Ä?"=>"Ä?",
- "Ĩ"=>"ÄŠ","Ä?"=>"ħ","Ĥ"=>"Ä?","Ä?"=>"Ä?","Ä "=>"Ä?","Äž"=>"Ä&#x;","Äœ"=>"Ä?","Äš"=>"Ä›","Ę"=>"Ä™","Ä–"=>"Ä—",
- "Ä”"=>"Ä•","Ä’"=>"Ä“","Ä?"=>"Ä‘","ÄŽ"=>"Ä?","ÄŒ"=>"Ä?","ÄŠ"=>"Ä‹","Ĉ"=>"ĉ","Ć"=>"ć","Ä„"=>"Ä…","Ä‚"=>"ă",
- "Ä€"=>"Ä ","?¸"=>"??","?ž"=>"?ž","??"=>"??","?œ"=>"??","?›"=>"??","?š"=>"??","?™"=>"?š","?˜"=>"?¸","?–"=>"??",
- "?•"=>"??","?”"=>"?´","?“"=>"??","?’"=>"??","?‘"=>"??","??"=>"?°","??"=>"??","?Ž"=>"?Ž","??"=>"?","?Œ"=>"??",
- "?‹"=>"??","?Š"=>"??","?‰"=>"?Š","?ˆ"=>"?¨","?‡"=>"?§","?†"=>"??","?…"=>"??","?„"=>"?¤","?ƒ"=>"??","?‚"=>"??",
- "? "=>"??","?€"=>"? ","Îœ"=>"Â?","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 <andi@splitbrain.org>
- * @see utf8_deaccent()
- */
- global $UTF8_LOWER_ACCENTS;
- if(empty($UTF8_LOWER_ACCENTS)) $UTF8_LOWER_ACCENTS = array(
- '? ' => 'a', '?´' => 'o', 'Ä?' => 'd', 'á¸&#x;' => 'f', '??' => 'e', '??' => 's', '??' => 'o',
- '?&#x;' => 'ss', 'ă' => 'a', '?™' => 'r', '?›' => 't', '?ˆ' => 'n', 'Ä ' => 'a', 'Ä?' => 'k',
- '??' => 's', 'á??' => 'y', '?†' => 'n', 'Ä?' => 'l', 'ħ' => 'h', 'áš—' => 'p', '??' => 'o',
- '??' => 'u', 'Ä›' => 'e', '?Š' => 'e', '?§' => 'c', 'á? ' => 'w', 'Ä‹' => 'c', '??' => 'o',
- 'áš?' => 's', '?¸' => 'o', 'Ä?' => 'g', '?§' => 't', '?™' => 's', 'Ä—' => 'e', 'ĉ' => 'c',
- '?›' => 's', '?Ž' => 'i', '??' => 'u', 'ć' => 'c', 'Ä™' => 'e', '??' => 'w', 'áš?' => 't',
- '??' => 'u', 'Ä?' => 'c', '??' => 'oe', '?¨' => 'e', '??' => 'y', 'Ä…' => 'a', '?‚' => 'l',
- '??' => 'u', '??' => 'u', '?&#x;' => 's', 'Ä&#x;' => 'g', 'Ä?' => 'l', '?’' => 'f', '?ž' => 'z',
- '�' => 'w', 'ḃ' => 'b', '??' => 'a', '??' => 'i', '??' => 'i', 'ḋ' => 'd', '??' => 't',
- '?—' => 'r', '?¤' => 'ae', '?' => 'i', '?•' => 'r', '??' => 'e', '??' => 'ue', '??' => 'o',
- 'Ä“' => 'e', '??' => 'n', '?„' => 'n', 'Ä?' => 'h', 'Ä?' => 'g', 'Ä‘' => 'd', 'Ä?' => 'j',
- '??' => 'y', '?Š' => 'u', '?' => 'u', '?°' => 'u', '??' => 't', '??' => 'y', '?‘' => 'o',
- '??' => 'a', 'Äž' => 'l', 'á?…' => 'w', '??' => 'z', 'Ä?' => 'i', '??' => 'a', 'Ä?' => 'g',
- 'áš ' => 'm', '??' => 'o', 'ÄŠ' => 'i', '?š' => 'u', 'Ä?' => 'i', '??' => 'z', '??' => 'a',
- '??' => 'u', '?ž' => 'th', '?°' => 'dh', '??' => 'ae', 'Â?' => 'u', 'Ä•' => '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 <andi@splitbrain.org>
- * @see utf8_deaccent()
- */
- global $UTF8_UPPER_ACCENTS;
- if(empty($UTF8_UPPER_ACCENTS)) $UTF8_UPPER_ACCENTS = array(
- '?€' => 'A', '?”' => 'O', 'ÄŽ' => 'D', 'Ḟ' => 'F', '?‹' => 'E', '? ' => 'S', '? ' => 'O',
- 'Ä‚' => 'A', '?˜' => 'R', '?š' => 'T', '?‡' => 'N', 'Ä€' => 'A', 'Ä?' => 'K',
- '?œ' => 'S', 'á??' => 'Y', '?…' => 'N', 'Äš' => 'L', 'Ä?' => 'H', 'áš–' => 'P', '?“' => 'O',
- '?š' => 'U', 'Äš' => 'E', '?‰' => 'E', '?‡' => 'C', 'á?€' => 'W', 'ÄŠ' => 'C', '?•' => 'O',
- 'áš ' => 'S', '?˜' => 'O', 'Ä?' => 'G', '??' => 'T', '?˜' => 'S', 'Ä–' => 'E', 'Ĉ' => 'C',
- '?š' => 'S', '?Ž' => 'I', '?°' => 'U', 'Ć' => 'C', 'Ę' => 'E', '?´' => 'W', 'áš?' => 'T',
- '??' => 'U', 'ÄŒ' => 'C', '?–' => 'Oe', '?ˆ' => 'E', '??' => 'Y', 'Ä„' => 'A', '? ' => 'L',
- '??' => 'U', '?Ž' => 'U', '?ž' => 'S', 'Äž' => 'G', 'Ä?' => 'L', '?‘' => 'F', '??' => 'Z',
- 'á?‚' => 'W', 'Ḃ' => 'B', '?…' => 'A', '?Œ' => 'I', '??' => 'I', 'Ḋ' => 'D', '?¤' => 'T',
- '?–' => 'R', '?„' => 'Ae', '??' => 'I', '?”' => 'R', '?Š' => 'E', '?œ' => 'Ue', '?’' => 'O',
- 'Ä’' => 'E', '?‘' => 'N', '?ƒ' => 'N', 'Ĥ' => 'H', 'Äœ' => 'G', 'Ä?' => 'D', 'Ä´' => 'J',
- '?¸' => 'Y', '?¨' => 'U', '??' => 'U', '??' => 'U', '??' => 'T', '??' => 'Y', '??' => 'O',
- '?‚' => 'A', 'Ä?' => 'L', 'á?„' => 'W', '??' => 'Z', 'Ä?' => 'I', '?ƒ' => 'A', 'Ä ' => 'G',
- ' ' => 'M', '?Œ' => 'O', 'Ĩ' => 'I', '?™' => 'U', 'ÄŽ' => 'I', '?š' => 'Z', '? ' => 'A',
- '?›' => 'U', '?ž' => 'Th', '??' => 'Dh', '?†' => 'Ae', 'Ä”' => '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 <andi@splitbrain.org>
- * @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��‘’“”•???'.
- '???—˜™š›œÂ?žÂ&#x; Â?Â?Â?¤Â?Â?§¨ŠÂ?Â?Â?ÂÂŽÂ?°Â?Â?Â?´Â?Â?Â?¸šÂ?Â?Â?Â????'.
- '???Â??—??ˇ˘˙˚˛˜Ë??€? ?ƒ?‰??΄΅·?–Ö°Ö?Ö?Ö?Ö´Ö?Ö?Ö?Ö¸ÖšÖ?Ö?Ö?ÖžÖ????'.
- '???× ×‚×ƒ×?×´?Œ?›?&#x;?€?‹?Œ???Ž?????‘?’???¸?‌â€?‎â€?–—―‗‘’‚“â€????'.
- '??????†���‰��‚�⠄₧���№℘����↑→↓↔↕�'.
- '�⇑⇒⇓⇔∀∂∃∅∆∇∈∉∋�∑−∕∗∙√�∞∠∧∨???'.
- '???��∴�≅≈≠�≤�⊂⊃⊄⊆⊇⊕⊗�⋅�⌠�⌊�⑊─???'.
- '??????┌â”?└┘├┤â”?â”´â”?â•?║╒╓╔╕╖╗╘╙╚╛╜â•?â•žâ•&#x;â• '.
- '���╤��╧╨╊���▀▄█▌�░▒▓■��◆◊�???'.
- '???★☎☛☞♠���✠✂✃✄✆✇✈✉✌�✎��✑✒✓✔✕???'.
- '??????✗✘✙✚✛✜âœ?✞âœ&#x;✠âœ?âœ?âœ?✤âœ?âœ?✧✊âœ?âœ?âœ?âœâœŽâœ?✰âœ?'.
- 'âœ?âœ?✴âœ?âœ?âœ?✸✚âœ?âœ?âœ?âœ?✞âœ?â?€â? â?‚â?ƒâ?„â?…â?†â?‡â?ˆâ?‰â?Šâ?‹???'.
- '???â??â??â?‘â?’â?–â?˜â?™â?šâ?›â?œâ??â?žâ??â??â??â?¤â??â??â?§â??➉➓➔➘➙➚???'.
- '??????âžœâž?âžžâž&#x;âž âž?âž?âž?➤âž?âž?➧➨➊âž?âž?âž?âžâžŽâž?âž?âž?âž?âž´âž?âž?'.
- '�➸➚����➞'.
- '?€€?€ ?€‚?€ƒ?€ˆ?€‰?€Š?€‹?€Œ?€??€Ž?€??€??€‘?€’?€”?€•?€–?€—?€˜?€™?€š?€›?€?'.
- '?›™?›š?››??—??˜??™??š??›??œ?????ž??&#x;?? ???????????¤??????'.
- '?????§??¨??Š?????????????Ž?????°???????????´???????????¸??š??????????????ž?š??š?'.
- '?? ??‚??ƒ??„??…??†??‡??ˆ??‰??Š??‹??Œ?????Ž?????š??›??œ?????ž??&#x;?? ???????????ž??€??›??œ?????ž'.
- '??&#x;?? ???????????¤????? ???????????¤????????¨??Š?????????????Ž'.
- '??›???›???›ž??›???œ€??œ ??œ‚??œƒ??œ„??œ…??œ†??œ‡??œˆ??œ‰??œŠ??œ‹??œŒ??œ???œŽ??œ???œ???œ‘??œ’??œ“??œ”??œ•??œ–??œ—??œ˜??œ™??œš??œ›'.
- '  â€?â ???';
- /**
- * 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 <andi@splitbrain.org>
- * @author Vitaly Blokhin <vitinfo@vitn.com>
- * @link http://www.uconv.com/translit.htm
- * @author Bisqwit <bisqwit@iki.fi>
- * @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 <arthit@gmail.com>
- * @author Denis Scheither <amorphis@uni-bremen.de>
- * @author Eivind Morland <eivind.morland@gmail.com>
- */
- global $UTF8_ROMANIZATION;
- if(empty($UTF8_ROMANIZATION)) $UTF8_ROMANIZATION = array(
- // scandinavian - differs from what we do in deaccent
- '??'=>'a','?…'=>'A','?¤'=>'a','?„'=>'A','??'=>'o','?–'=>'O',
- //russian cyrillic
- '?°'=>'a','??'=>'A','??'=>'b','?‘'=>'B','??'=>'v','?’'=>'V','??'=>'g','?“'=>'G',
- '?´'=>'d','?”'=>'D','??'=>'e','?•'=>'E','?‘'=>'jo','? '=>'Jo','??'=>'zh','?–'=>'Zh',
- '??'=>'z','?—'=>'Z','?¸'=>'i','?˜'=>'I','?š'=>'j','?™'=>'J','??'=>'k','?š'=>'K',
- '??'=>'l','?›'=>'L','??'=>'m','?œ'=>'M','??'=>'n','??'=>'N','?ž'=>'o','?ž'=>'O',
- '??'=>'p','?&#x;'=>'P','?€'=>'r','? '=>'R','? '=>'s','??'=>'S','?‚'=>'t','??'=>'T',
- '?ƒ'=>'u','??'=>'U','?„'=>'f','?¤'=>'F','?…'=>'x','??'=>'X','?†'=>'c','??'=>'C',
- '?‡'=>'ch','?§'=>'Ch','?ˆ'=>'sh','?¨'=>'Sh','?‰'=>'sch','?Š'=>'Sch','?Š'=>'',
- '??'=>'','?‹'=>'y','??'=>'Y','?Œ'=>'','??'=>'','??'=>'eh','?'=>'Eh','?Ž'=>'ju',
- '?Ž'=>'Ju','??'=>'ja','??'=>'Ja',
- // Ukrainian cyrillic
- '??'=>'Gh','?‘'=>'gh','?„'=>'Je','?”'=>'je','?†'=>'I','?–'=>'i','?‡'=>'Ji','?—'=>'ji',
- // Georgian
- '�'=>'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','áƒ?'=>'o','პ'=>'p','áƒ&#x;'=>'zh',
- 'რ'=>'r','�'=>'s','�'=>'t','�'=>'u','ფ'=>'ph','�'=>'kh','�'=>'gh','ყ'=>'q',
- 'შ'=>'sh','჊'=>'ch','áƒ?'=>'c','áƒ?'=>'dh','áƒ?'=>'w','áƒ'=>'j','჎'=>'x','áƒ?'=>'jh',
- 'ჰ'=>'xh',
- //Sanskrit
- '?¤…'=>'a','?¤†'=>'ah','?¤‡'=>'i','?¤ˆ'=>'ih','?¤‰'=>'u','?¤Š'=>'uh','?¤‹'=>'ry',
- '?? '=>'ryh','?¤Œ'=>'ly','???'=>'lyh','?¤?'=>'e','?¤?'=>'ay','?¤“'=>'o','?¤”'=>'aw',
- '?¤…?¤‚'=>'amh','?¤…?¤ƒ'=>'aq','?¤•'=>'k','?¤–'=>'kh','?¤—'=>'g','?¤˜'=>'gh','?¤™'=>'nh',
- '?¤š'=>'c','?¤›'=>'ch','?¤œ'=>'j','?¤?'=>'jh','?¤ž'=>'ny','?¤&#x;'=>'tq','?¤ '=>'tqh',
- '?¤?'=>'dq','?¤?'=>'dqh','?¤?'=>'nq','?¤¤'=>'t','?¤?'=>'th','?¤?'=>'d','?¤§'=>'dh',
- '?¤¨'=>'n','?¤?'=>'p','?¤?'=>'ph','?¤?'=>'b','?¤'=>'bh','?¤Ž'=>'m','?¤?'=>'z','?¤°'=>'r',
- '?¤?'=>'l','?¤?'=>'v','?¤?'=>'sh','?¤?'=>'sqh','?¤¸'=>'s','?¤š'=>'x',
- //Sanskrit diacritics
- 'Ä€'=>'A','Ä?'=>'I','??'=>'U','ášš'=>'R','ášœ'=>'R','áš„'=>'N','?‘'=>'N','áš?'=>'T',
- 'Ḍ'=>'D','ᚆ'=>'N','?š'=>'S','áš?'=>'S',' '=>'M','áš‚'=>'M','Ḥ'=>'H','á¸?'=>'L','Ḹ'=>'L',
- 'Ä '=>'a','Ä?'=>'i','??'=>'u','áš›'=>'r','áš?'=>'r','áš…'=>'n','??'=>'n','áš'=>'t',
- 'á¸?'=>'d','ᚇ'=>'n','?›'=>'s','áš?'=>'s','áš '=>'m','ᚃ'=>'m','á¸?'=>'h','á¸?'=>'l','Ḛ'=>'l',
- //Hebrew
- '×?'=>'a', 'ב'=>'b','×’'=>'g','ד'=>'d','×”'=>'h','ו'=>'v','×–'=>'z','×—'=>'kh','ט'=>'th',
- '×™'=>'y','ך'=>'h','×›'=>'k','ל'=>'l','×?'=>'m','מ'=>'m','×&#x;'=>'n','× '=>'n',
- '×?'=>'s','×?'=>'ah','×?'=>'f','פ'=>'p','×?'=>'c','×?'=>'c','ק'=>'q','ר'=>'r',
- '׊'=>'sh','×?'=>'t',
- //Arabic
- '?§'=>'a','?¨'=>'b','??'=>'t','??'=>'th','??'=>'g','?'=>'xh','?Ž'=>'x','??'=>'d',
- '?°'=>'dh','??'=>'r','??'=>'z','??'=>'s','?´'=>'sh','??'=>'s\'','??'=>'d\'',
- '??'=>'t\'','?¸'=>'z\'','?š'=>'y','??'=>'gh','? '=>'f','?‚'=>'q','?ƒ'=>'k',
- '?„'=>'l','?…'=>'m','?†'=>'n','?‡'=>'x\'','?ˆ'=>'u','?Š'=>'i',
- // Japanese characters (last update: 2008-05-09)
- // Japanese hiragana
- // 3 character syllables, ? ? doubles the consonant after
- '? ?? ??‚ƒ'=>'ccha','? ?? ?? ‡'=>'cche','? ?? ??‚‡'=>'ccho','? ?? ??‚…'=>'cchu',
- '? ?? ??‚ƒ'=>'bbya','? ?? ?? ‡'=>'bbye','? ?? ?? ƒ'=>'bbyi','? ?? ??‚‡'=>'bbyo','? ?? ??‚…'=>'bbyu',
- '? ?? ´?‚ƒ'=>'ppya','? ?? ´? ‡'=>'ppye','? ?? ´? ƒ'=>'ppyi','? ?? ´?‚‡'=>'ppyo','? ?? ´?‚…'=>'ppyu',
- '? ?? ??‚ƒ'=>'ccha','? ?? ?? ‡'=>'cche','? ?? ?'=>'cchi','? ?? ??‚‡'=>'ccho','? ?? ??‚…'=>'cchu',
- // '? ?? ??‚ƒ'=>'hya','? ?? ?? ‡'=>'hye','? ?? ?? ƒ'=>'hyi','? ?? ??‚‡'=>'hyo','? ?? ??‚…'=>'hyu',
- '? ?? ??‚ƒ'=>'kkya','? ?? ?? ‡'=>'kkye','? ?? ?? ƒ'=>'kkyi','? ?? ??‚‡'=>'kkyo','? ?? ??‚…'=>'kkyu',
- '? ?? Ž?‚ƒ'=>'ggya','? ?? Ž? ‡'=>'ggye','? ?? Ž? ƒ'=>'ggyi','? ?? Ž?‚‡'=>'ggyo','? ?? Ž?‚…'=>'ggyu',
- '? ?? ??‚ƒ'=>'mmya','? ?? ?? ‡'=>'mmye','? ?? ?? ƒ'=>'mmyi','? ?? ??‚‡'=>'mmyo','? ?? ??‚…'=>'mmyu',
- '? ?? ??‚ƒ'=>'nnya','? ?? ?? ‡'=>'nnye','? ?? ?? ƒ'=>'nnyi','? ?? ??‚‡'=>'nnyo','? ?? ??‚…'=>'nnyu',
- '? ??‚Š?‚ƒ'=>'rrya','? ??‚Š? ‡'=>'rrye','? ??‚Š? ƒ'=>'rryi','? ??‚Š?‚‡'=>'rryo','? ??‚Š?‚…'=>'rryu',
- '? ?? —?‚ƒ'=>'ssha','? ?? —? ‡'=>'sshe','? ?? —'=>'sshi','? ?? —?‚‡'=>'ssho','? ?? —?‚…'=>'sshu',
- // seperate hiragana 'n' ('n' + 'i' != 'ni', normally we would write "kon'nichi wa" but the apostrophe would be converted to _ anyway)
- '?‚“? ‚'=>'n_a','?‚“? ˆ'=>'n_e','?‚“? „'=>'n_i','?‚“? Š'=>'n_o','?‚“? †'=>'n_u',
- '?‚“?‚„'=>'n_ya','?‚“?‚ˆ'=>'n_yo','?‚“?‚†'=>'n_yu',
- // 2 character syllables - normal
- '? ?? '=>'fa','? ?? ‡'=>'fe','? ?? ƒ'=>'fi','? ?? ‰'=>'fo',
- '? ??‚ƒ'=>'cha','? ?? ‡'=>'che','? ?'=>'chi','? ??‚‡'=>'cho','? ??‚…'=>'chu',
- '? ??‚ƒ'=>'hya','? ?? ‡'=>'hye','? ?? ƒ'=>'hyi','? ??‚‡'=>'hyo','? ??‚…'=>'hyu',
- '? ??‚ƒ'=>'bya','? ?? ‡'=>'bye','? ?? ƒ'=>'byi','? ??‚‡'=>'byo','? ??‚…'=>'byu',
- '? ´?‚ƒ'=>'pya','? ´? ‡'=>'pye','? ´? ƒ'=>'pyi','? ´?‚‡'=>'pyo','? ´?‚…'=>'pyu',
- '? ??‚ƒ'=>'kya','? ?? ‡'=>'kye','? ?? ƒ'=>'kyi','? ??‚‡'=>'kyo','? ??‚…'=>'kyu',
- '? Ž?‚ƒ'=>'gya','? Ž? ‡'=>'gye','? Ž? ƒ'=>'gyi','? Ž?‚‡'=>'gyo','? Ž?‚…'=>'gyu',
- '? ??‚ƒ'=>'mya','? ?? ‡'=>'mye','? ?? ƒ'=>'myi','? ??‚‡'=>'myo','? ??‚…'=>'myu',
- '? ??‚ƒ'=>'nya','? ?? ‡'=>'nye','? ?? ƒ'=>'nyi','? ??‚‡'=>'nyo','? ??‚…'=>'nyu',
- '?‚Š?‚ƒ'=>'rya','?‚Š? ‡'=>'rye','?‚Š? ƒ'=>'ryi','?‚Š?‚‡'=>'ryo','?‚Š?‚…'=>'ryu',
- '? —?‚ƒ'=>'sha','? —? ‡'=>'she','? —'=>'shi','? —?‚‡'=>'sho','? —?‚…'=>'shu',
- '? ˜?‚ƒ'=>'ja','? ˜? ‡'=>'je','? ˜?‚‡'=>'jo','? ˜?‚…'=>'ju',
- '? †? ‡'=>'we','? †? ƒ'=>'wi',
- '? „? ‡'=>'ye',
- // 2 character syllables, ? ? doubles the consonant after
- '? ?? °'=>'bba','? ?? š'=>'bbe','? ?? ?'=>'bbi','? ?? ?'=>'bbo','? ?? ?'=>'bbu',
- '? ?? ?'=>'ppa','? ?? ?'=>'ppe','? ?? ´'=>'ppi','? ?? ?'=>'ppo','? ?? ?'=>'ppu',
- '? ?? &#x;'=>'tta','? ?? ?'=>'tte','? ?? ?'=>'cchi','? ?? ¨'=>'tto','? ?? ¤'=>'ttsu',
- '? ?? '=>'dda','? ?? §'=>'dde','? ?? ?'=>'ddi','? ?? Š'=>'ddo','? ?? ?'=>'ddu',
- '? ?? Œ'=>'gga','? ?? ’'=>'gge','? ?? Ž'=>'ggi','? ?? ”'=>'ggo','? ?? ?'=>'ggu',
- '? ?? ‹'=>'kka','? ?? ‘'=>'kke','? ?? ?'=>'kki','? ?? “'=>'kko','? ?? ?'=>'kku',
- '? ?? ž'=>'mma','? ??‚ '=>'mme','? ?? ?'=>'mmi','? ??‚‚'=>'mmo','? ??‚€'=>'mmu',
- '? ?? ?'=>'nna','? ?? '=>'nne','? ?? ?'=>'nni','? ?? Ž'=>'nno','? ?? ?'=>'nnu',
- '? ??‚‰'=>'rra','? ??‚Œ'=>'rre','? ??‚Š'=>'rri','? ??‚?'=>'rro','? ??‚‹'=>'rru',
- '? ?? •'=>'ssa','? ?? ›'=>'sse','? ?? —'=>'sshi','? ?? ?'=>'sso','? ?? ™'=>'ssu',
- '? ?? –'=>'zza','? ?? œ'=>'zze','? ?? ˜'=>'jji','? ?? ž'=>'zzo','? ?? š'=>'zzu',
- // 1 character syllabels
- '? ‚'=>'a','? ˆ'=>'e','? „'=>'i','? Š'=>'o','? †'=>'u','?‚“'=>'n',
- '? ?'=>'ha','? ¸'=>'he','? ?'=>'hi','? ?'=>'ho','? ?'=>'fu',
- '? °'=>'ba','? š'=>'be','? ?'=>'bi','? ?'=>'bo','? ?'=>'bu',
- '? ?'=>'pa','? ?'=>'pe','? ´'=>'pi','? ?'=>'po','? ?'=>'pu',
- '? &#x;'=>'ta','? ?'=>'te','? ?'=>'chi','? ¨'=>'to','? ¤'=>'tsu',
- '? '=>'da','? §'=>'de','? ?'=>'di','? Š'=>'do','? ?'=>'du',
- '? Œ'=>'ga','? ’'=>'ge','? Ž'=>'gi','? ”'=>'go','? ?'=>'gu',
- '? ‹'=>'ka','? ‘'=>'ke','? ?'=>'ki','? “'=>'ko','? ?'=>'ku',
- '? ž'=>'ma','?‚ '=>'me','? ?'=>'mi','?‚‚'=>'mo','?‚€'=>'mu',
- '? ?'=>'na','? '=>'ne','? ?'=>'ni','? Ž'=>'no','? ?'=>'nu',
- '?‚‰'=>'ra','?‚Œ'=>'re','?‚Š'=>'ri','?‚?'=>'ro','?‚‹'=>'ru',
- '? •'=>'sa','? ›'=>'se','? —'=>'shi','? ?'=>'so','? ™'=>'su',
- '?‚?'=>'wa','?‚’'=>'wo',
- '? –'=>'za','? œ'=>'ze','? ˜'=>'ji','? ž'=>'zo','? š'=>'zu',
- '?‚„'=>'ya','?‚ˆ'=>'yo','?‚†'=>'yu',
- // old characters
- '?‚‘'=>'we','?‚?'=>'wi',
- // convert what's left (probably only kicks in when something's missing above)
- // '? '=>'a','? ‡'=>'e','? ƒ'=>'i','? ‰'=>'o','? …'=>'u',
- // '?‚ƒ'=>'ya','?‚‡'=>'yo','?‚…'=>'yu',
- // never seen one of those (disabled for the moment)
- // '?ƒ´? '=>'va','?ƒ´? ‡'=>'ve','?ƒ´? ƒ'=>'vi','?ƒ´? ‰'=>'vo','?ƒ´'=>'vu',
- // '? §?‚ƒ'=>'dha','? §? ‡'=>'dhe','? §? ƒ'=>'dhi','? §?‚‡'=>'dho','? §?‚…'=>'dhu',
- // '? Š? '=>'dwa','? Š? ‡'=>'dwe','? Š? ƒ'=>'dwi','? Š? ‰'=>'dwo','? Š? …'=>'dwu',
- // '? ??‚ƒ'=>'dya','? ?? ‡'=>'dye','? ?? ƒ'=>'dyi','? ??‚‡'=>'dyo','? ??‚…'=>'dyu',
- // '? ?? '=>'fwa','? ?? ‡'=>'fwe','? ?? ƒ'=>'fwi','? ?? ‰'=>'fwo','? ?? …'=>'fwu',
- // '? ??‚ƒ'=>'fya','? ?? ‡'=>'fye','? ?? ƒ'=>'fyi','? ??‚‡'=>'fyo','? ??‚…'=>'fyu',
- // '? ™? '=>'swa','? ™? ‡'=>'swe','? ™? ƒ'=>'swi','? ™? ‰'=>'swo','? ™? …'=>'swu',
- // '? ??‚ƒ'=>'tha','? ?? ‡'=>'the','? ?? ƒ'=>'thi','? ??‚‡'=>'tho','? ??‚…'=>'thu',
- // '? ¤?‚ƒ'=>'tsa','? ¤? ‡'=>'tse','? ¤? ƒ'=>'tsi','? ¤?‚‡'=>'tso','? ¤'=>'tsu',
- // '? ¨? '=>'twa','? ¨? ‡'=>'twe','? ¨? ƒ'=>'twi','? ¨? ‰'=>'two','? ¨? …'=>'twu',
- // '?ƒ´?‚ƒ'=>'vya','?ƒ´? ‡'=>'vye','?ƒ´? ƒ'=>'vyi','?ƒ´?‚‡'=>'vyo','?ƒ´?‚…'=>'vyu',
- // '? †? '=>'wha','? †? ‡'=>'whe','? †? ƒ'=>'whi','? †? ‰'=>'who','? †? …'=>'whu',
- // '? ˜?‚ƒ'=>'zha','? ˜? ‡'=>'zhe','? ˜? ƒ'=>'zhi','? ˜?‚‡'=>'zho','? ˜?‚…'=>'zhu',
- // '? ˜?‚ƒ'=>'zya','? ˜? ‡'=>'zye','? ˜? ƒ'=>'zyi','? ˜?‚‡'=>'zyo','? ˜?‚…'=>'zyu',
- // 'spare' characters from other romanization systems
- // '? '=>'da','? §'=>'de','? ?'=>'di','? Š'=>'do','? ?'=>'du',
- // '?‚‰'=>'la','?‚Œ'=>'le','?‚Š'=>'li','?‚?'=>'lo','?‚‹'=>'lu',
- // '? •'=>'sa','? ›'=>'se','? —'=>'si','? ?'=>'so','? ™'=>'su',
- // '? ??‚ƒ'=>'cya','? ?? ‡'=>'cye','? ?? ƒ'=>'cyi','? ??‚‡'=>'cyo','? ??‚…'=>'cyu',
- //'? ˜?‚ƒ'=>'jya','? ˜? ‡'=>'jye','? ˜? ƒ'=>'jyi','? ˜?‚‡'=>'jyo','? ˜?‚…'=>'jyu',
- //'?‚Š?‚ƒ'=>'lya','?‚Š? ‡'=>'lye','?‚Š? ƒ'=>'lyi','?‚Š?‚‡'=>'lyo','?‚Š?‚…'=>'lyu',
- //'? —?‚ƒ'=>'sya','? —? ‡'=>'sye','? —? ƒ'=>'syi','? —?‚‡'=>'syo','? —?‚…'=>'syu',
- //'? ??‚ƒ'=>'tya','? ?? ‡'=>'tye','? ?? ƒ'=>'tyi','? ??‚‡'=>'tyo','? ??‚…'=>'tyu',
- //'? —'=>'ci',,? „'=>'yi','? ?'=>'dzi',
- //'? ?? ˜?‚ƒ'=>'jja','? ?? ˜? ‡'=>'jje','? ?? ˜'=>'jji','? ?? ˜?‚‡'=>'jjo','? ?? ˜?‚…'=>'jju',
- // Japanese katakana
- // 4 character syllables: ?ƒƒ doubles the consonant after, ?ƒ? doubles the vowel before (usualy written with macron, but we don't want that in our URLs)
- '?ƒƒ?ƒ“?ƒ??ƒ?'=>'bbyaa','?ƒƒ?ƒ“?‚§?ƒ?'=>'bbyee','?ƒƒ?ƒ“?‚??ƒ?'=>'bbyii','?ƒƒ?ƒ“?ƒ§?ƒ?'=>'bbyoo','?ƒƒ?ƒ“?ƒ??ƒ?'=>'bbyuu',
- '?ƒƒ?ƒ”?ƒ??ƒ?'=>'ppyaa','?ƒƒ?ƒ”?‚§?ƒ?'=>'ppyee','?ƒƒ?ƒ”?‚??ƒ?'=>'ppyii','?ƒƒ?ƒ”?ƒ§?ƒ?'=>'ppyoo','?ƒƒ?ƒ”?ƒ??ƒ?'=>'ppyuu',
- '?ƒƒ?‚?ƒ??ƒ?'=>'kkyaa','?ƒƒ?‚?‚§?ƒ?'=>'kkyee','?ƒƒ?‚?‚??ƒ?'=>'kkyii','?ƒƒ?‚?ƒ§?ƒ?'=>'kkyoo','?ƒƒ?‚?ƒ??ƒ?'=>'kkyuu',
- '?ƒƒ?‚Ž?ƒ??ƒ?'=>'ggyaa','?ƒƒ?‚Ž?‚§?ƒ?'=>'ggyee','?ƒƒ?‚Ž?‚??ƒ?'=>'ggyii','?ƒƒ?‚Ž?ƒ§?ƒ?'=>'ggyoo','?ƒƒ?‚Ž?ƒ??ƒ?'=>'ggyuu',
- '?ƒƒ?ƒ&#x;?ƒ??ƒ?'=>'mmyaa','?ƒƒ?ƒ&#x;?‚§?ƒ?'=>'mmyee','?ƒƒ?ƒ&#x;?‚??ƒ?'=>'mmyii','?ƒƒ?ƒ&#x;?ƒ§?ƒ?'=>'mmyoo','?ƒƒ?ƒ&#x;?ƒ??ƒ?'=>'mmyuu',
- '?ƒƒ?ƒ‹?ƒ??ƒ?'=>'nnyaa','?ƒƒ?ƒ‹?‚§?ƒ?'=>'nnyee','?ƒƒ?ƒ‹?‚??ƒ?'=>'nnyii','?ƒƒ?ƒ‹?ƒ§?ƒ?'=>'nnyoo','?ƒƒ?ƒ‹?ƒ??ƒ?'=>'nnyuu',
- '?ƒƒ?ƒ??ƒ??ƒ?'=>'rryaa','?ƒƒ?ƒ??‚§?ƒ?'=>'rryee','?ƒƒ?ƒ??‚??ƒ?'=>'rryii','?ƒƒ?ƒ??ƒ§?ƒ?'=>'rryoo','?ƒƒ?ƒ??ƒ??ƒ?'=>'rryuu',
- '?ƒƒ?‚??ƒ??ƒ?'=>'sshaa','?ƒƒ?‚??‚§?ƒ?'=>'sshee','?ƒƒ?‚??ƒ?'=>'sshii','?ƒƒ?‚??ƒ§?ƒ?'=>'sshoo','?ƒƒ?‚??ƒ??ƒ?'=>'sshuu',
- '?ƒƒ?ƒ ?ƒ??ƒ?'=>'cchaa','?ƒƒ?ƒ ?‚§?ƒ?'=>'cchee','?ƒƒ?ƒ ?ƒ?'=>'cchii','?ƒƒ?ƒ ?ƒ§?ƒ?'=>'cchoo','?ƒƒ?ƒ ?ƒ??ƒ?'=>'cchuu',
- '?ƒƒ?ƒ†?‚??ƒ?'=>'ttii',
- '?ƒƒ?ƒ‚?‚??ƒ?'=>'ddii',
- // 3 character syllables - doubled vowels
- '?ƒ•?‚??ƒ?'=>'faa','?ƒ•?‚§?ƒ?'=>'fee','?ƒ•?‚??ƒ?'=>'fii','?ƒ•?‚Š?ƒ?'=>'foo',
- '?ƒ•?ƒ??ƒ?'=>'fyaa','?ƒ•?‚§?ƒ?'=>'fyee','?ƒ•?‚??ƒ?'=>'fyii','?ƒ•?ƒ§?ƒ?'=>'fyoo','?ƒ•?ƒ??ƒ?'=>'fyuu',
- '?ƒ’?ƒ??ƒ?'=>'hyaa','?ƒ’?‚§?ƒ?'=>'hyee','?ƒ’?‚??ƒ?'=>'hyii','?ƒ’?ƒ§?ƒ?'=>'hyoo','?ƒ’?ƒ??ƒ?'=>'hyuu',
- '?ƒ“?ƒ??ƒ?'=>'byaa','?ƒ“?‚§?ƒ?'=>'byee','?ƒ“?‚??ƒ?'=>'byii','?ƒ“?ƒ§?ƒ?'=>'byoo','?ƒ“?ƒ??ƒ?'=>'byuu',
- '?ƒ”?ƒ??ƒ?'=>'pyaa','?ƒ”?‚§?ƒ?'=>'pyee','?ƒ”?‚??ƒ?'=>'pyii','?ƒ”?ƒ§?ƒ?'=>'pyoo','?ƒ”?ƒ??ƒ?'=>'pyuu',
- '?‚?ƒ??ƒ?'=>'kyaa','?‚?‚§?ƒ?'=>'kyee','?‚?‚??ƒ?'=>'kyii','?‚?ƒ§?ƒ?'=>'kyoo','?‚?ƒ??ƒ?'=>'kyuu',
- '?‚Ž?ƒ??ƒ?'=>'gyaa','?‚Ž?‚§?ƒ?'=>'gyee','?‚Ž?‚??ƒ?'=>'gyii','?‚Ž?ƒ§?ƒ?'=>'gyoo','?‚Ž?ƒ??ƒ?'=>'gyuu',
- '?ƒ&#x;?ƒ??ƒ?'=>'myaa','?ƒ&#x;?‚§?ƒ?'=>'myee','?ƒ&#x;?‚??ƒ?'=>'myii','?ƒ&#x;?ƒ§?ƒ?'=>'myoo','?ƒ&#x;?ƒ??ƒ?'=>'myuu',
- '?ƒ‹?ƒ??ƒ?'=>'nyaa','?ƒ‹?‚§?ƒ?'=>'nyee','?ƒ‹?‚??ƒ?'=>'nyii','?ƒ‹?ƒ§?ƒ?'=>'nyoo','?ƒ‹?ƒ??ƒ?'=>'nyuu',
- '?ƒ??ƒ??ƒ?'=>'ryaa','?ƒ??‚§?ƒ?'=>'ryee','?ƒ??‚??ƒ?'=>'ryii','?ƒ??ƒ§?ƒ?'=>'ryoo','?ƒ??ƒ??ƒ?'=>'ryuu',
- '?‚??ƒ??ƒ?'=>'shaa','?‚??‚§?ƒ?'=>'shee','?‚??ƒ?'=>'shii','?‚??ƒ§?ƒ?'=>'shoo','?‚??ƒ??ƒ?'=>'shuu',
- '?‚¸?ƒ??ƒ?'=>'jaa','?‚¸?‚§?ƒ?'=>'jee','?‚¸?ƒ?'=>'jii','?‚¸?ƒ§?ƒ?'=>'joo','?‚¸?ƒ??ƒ?'=>'juu',
- '?‚š?‚??ƒ?'=>'swaa','?‚š?‚§?ƒ?'=>'swee','?‚š?‚??ƒ?'=>'swii','?‚š?‚Š?ƒ?'=>'swoo','?‚š?‚??ƒ?'=>'swuu',
- '?ƒ‡?‚??ƒ?'=>'daa','?ƒ‡?‚§?ƒ?'=>'dee','?ƒ‡?‚??ƒ?'=>'dii','?ƒ‡?‚Š?ƒ?'=>'doo','?ƒ‡?‚??ƒ?'=>'duu',
- '?ƒ ?ƒ??ƒ?'=>'chaa','?ƒ ?‚§?ƒ?'=>'chee','?ƒ ?ƒ?'=>'chii','?ƒ ?ƒ§?ƒ?'=>'choo','?ƒ ?ƒ??ƒ?'=>'chuu',
- '?ƒ‚?ƒ??ƒ?'=>'dyaa','?ƒ‚?‚§?ƒ?'=>'dyee','?ƒ‚?‚??ƒ?'=>'dyii','?ƒ‚?ƒ§?ƒ?'=>'dyoo','?ƒ‚?ƒ??ƒ?'=>'dyuu',
- '?ƒ„?ƒ??ƒ?'=>'tsaa','?ƒ„?‚§?ƒ?'=>'tsee','?ƒ„?‚??ƒ?'=>'tsii','?ƒ„?ƒ§?ƒ?'=>'tsoo','?ƒ„?ƒ?'=>'tsuu',
- '?ƒˆ?‚??ƒ?'=>'twaa','?ƒˆ?‚§?ƒ?'=>'twee','?ƒˆ?‚??ƒ?'=>'twii','?ƒˆ?‚Š?ƒ?'=>'twoo','?ƒˆ?‚??ƒ?'=>'twuu',
- '?ƒ‰?‚??ƒ?'=>'dwaa','?ƒ‰?‚§?ƒ?'=>'dwee','?ƒ‰?‚??ƒ?'=>'dwii','?ƒ‰?‚Š?ƒ?'=>'dwoo','?ƒ‰?‚??ƒ?'=>'dwuu',
- '?‚??‚??ƒ?'=>'whaa','?‚??‚§?ƒ?'=>'whee','?‚??‚??ƒ?'=>'whii','?‚??‚Š?ƒ?'=>'whoo','?‚??‚??ƒ?'=>'whuu',
- '?ƒ´?ƒ??ƒ?'=>'vyaa','?ƒ´?‚§?ƒ?'=>'vyee','?ƒ´?‚??ƒ?'=>'vyii','?ƒ´?ƒ§?ƒ?'=>'vyoo','?ƒ´?ƒ??ƒ?'=>'vyuu',
- '?ƒ´?‚??ƒ?'=>'vaa','?ƒ´?‚§?ƒ?'=>'vee','?ƒ´?‚??ƒ?'=>'vii','?ƒ´?‚Š?ƒ?'=>'voo','?ƒ´?ƒ?'=>'vuu',
- '?‚??‚§?ƒ?'=>'wee','?‚??‚??ƒ?'=>'wii',
- '?‚¤?‚§?ƒ?'=>'yee',
- '?ƒ†?‚??ƒ?'=>'tii',
- '?ƒ‚?‚??ƒ?'=>'dii',
- // 3 character syllables - doubled consonants
- '?ƒƒ?ƒ“?ƒ?'=>'bbya','?ƒƒ?ƒ“?‚§'=>'bbye','?ƒƒ?ƒ“?‚?'=>'bbyi','?ƒƒ?ƒ“?ƒ§'=>'bbyo','?ƒƒ?ƒ“?ƒ?'=>'bbyu',
- '?ƒƒ?ƒ”?ƒ?'=>'ppya','?ƒƒ?ƒ”?‚§'=>'ppye','?ƒƒ?ƒ”?‚?'=>'ppyi','?ƒƒ?ƒ”?ƒ§'=>'ppyo','?ƒƒ?ƒ”?ƒ?'=>'ppyu',
- '?ƒƒ?‚?ƒ?'=>'kkya','?ƒƒ?‚?‚§'=>'kkye','?ƒƒ?‚?‚?'=>'kkyi','?ƒƒ?‚?ƒ§'=>'kkyo','?ƒƒ?‚?ƒ?'=>'kkyu',
- '?ƒƒ?‚Ž?ƒ?'=>'ggya','?ƒƒ?‚Ž?‚§'=>'ggye','?ƒƒ?‚Ž?‚?'=>'ggyi','?ƒƒ?‚Ž?ƒ§'=>'ggyo','?ƒƒ?‚Ž?ƒ?'=>'ggyu',
- '?ƒƒ?ƒ&#x;?ƒ?'=>'mmya','?ƒƒ?ƒ&#x;?‚§'=>'mmye','?ƒƒ?ƒ&#x;?‚?'=>'mmyi','?ƒƒ?ƒ&#x;?ƒ§'=>'mmyo','?ƒƒ?ƒ&#x;?ƒ?'=>'mmyu',
- '?ƒƒ?ƒ‹?ƒ?'=>'nnya','?ƒƒ?ƒ‹?‚§'=>'nnye','?ƒƒ?ƒ‹?‚?'=>'nnyi','?ƒƒ?ƒ‹?ƒ§'=>'nnyo','?ƒƒ?ƒ‹?ƒ?'=>'nnyu',
- '?ƒƒ?ƒ??ƒ?'=>'rrya','?ƒƒ?ƒ??‚§'=>'rrye','?ƒƒ?ƒ??‚?'=>'rryi','?ƒƒ?ƒ??ƒ§'=>'rryo','?ƒƒ?ƒ??ƒ?'=>'rryu',
- '?ƒƒ?‚??ƒ?'=>'ssha','?ƒƒ?‚??‚§'=>'sshe','?ƒƒ?‚?'=>'sshi','?ƒƒ?‚??ƒ§'=>'ssho','?ƒƒ?‚??ƒ?'=>'sshu',
- '?ƒƒ?ƒ ?ƒ?'=>'ccha','?ƒƒ?ƒ ?‚§'=>'cche','?ƒƒ?ƒ '=>'cchi','?ƒƒ?ƒ ?ƒ§'=>'ccho','?ƒƒ?ƒ ?ƒ?'=>'cchu',
- '?ƒƒ?ƒ†?‚?'=>'tti',
- '?ƒƒ?ƒ‚?‚?'=>'ddi',
- // 3 character syllables - doubled vowel and consonants
- '?ƒƒ?ƒ??ƒ?'=>'bbaa','?ƒƒ?ƒ™?ƒ?'=>'bbee','?ƒƒ?ƒ“?ƒ?'=>'bbii','?ƒƒ?ƒœ?ƒ?'=>'bboo','?ƒƒ?ƒ–?ƒ?'=>'bbuu',
- '?ƒƒ?ƒ‘?ƒ?'=>'ppaa','?ƒƒ?ƒš?ƒ?'=>'ppee','?ƒƒ?ƒ”?ƒ?'=>'ppii','?ƒƒ?ƒ??ƒ?'=>'ppoo','?ƒƒ?ƒ—?ƒ?'=>'ppuu',
- '?ƒƒ?‚??ƒ?'=>'kkee','?ƒƒ?‚?ƒ?'=>'kkii','?ƒƒ?‚??ƒ?'=>'kkoo','?ƒƒ?‚??ƒ?'=>'kkuu','?ƒƒ?‚??ƒ?'=>'kkaa',
- '?ƒƒ?‚??ƒ?'=>'ggaa','?ƒƒ?‚??ƒ?'=>'ggee','?ƒƒ?‚Ž?ƒ?'=>'ggii','?ƒƒ?‚´?ƒ?'=>'ggoo','?ƒƒ?‚°?ƒ?'=>'gguu',
- '?ƒƒ?ƒž?ƒ?'=>'maa','?ƒƒ?ƒ??ƒ?'=>'mee','?ƒƒ?ƒ&#x;?ƒ?'=>'mii','?ƒƒ?ƒ??ƒ?'=>'moo','?ƒƒ?ƒ ?ƒ?'=>'muu',
- '?ƒƒ?ƒŠ?ƒ?'=>'nnaa','?ƒƒ?ƒ??ƒ?'=>'nnee','?ƒƒ?ƒ‹?ƒ?'=>'nnii','?ƒƒ?ƒŽ?ƒ?'=>'nnoo','?ƒƒ?ƒŒ?ƒ?'=>'nnuu',
- '?ƒƒ?ƒŠ?ƒ?'=>'rraa','?ƒƒ?ƒ??ƒ?'=>'rree','?ƒƒ?ƒ??ƒ?'=>'rrii','?ƒƒ?ƒ?ƒ?'=>'rroo','?ƒƒ?ƒ??ƒ?'=>'rruu',
- '?ƒƒ?‚??ƒ?'=>'ssaa','?ƒƒ?‚??ƒ?'=>'ssee','?ƒƒ?‚??ƒ?'=>'sshii','?ƒƒ?‚??ƒ?'=>'ssoo','?ƒƒ?‚š?ƒ?'=>'ssuu',
- '?ƒƒ?‚??ƒ?'=>'zzaa','?ƒƒ?‚??ƒ?'=>'zzee','?ƒƒ?‚¸?ƒ?'=>'jjii','?ƒƒ?‚ž?ƒ?'=>'zzoo','?ƒƒ?‚??ƒ?'=>'zzuu',
- '?ƒƒ?‚??ƒ?'=>'ttaa','?ƒƒ?ƒ†?ƒ?'=>'ttee','?ƒƒ?ƒ ?ƒ?'=>'chii','?ƒƒ?ƒˆ?ƒ?'=>'ttoo','?ƒƒ?ƒ„?ƒ?'=>'ttsuu',
- '?ƒƒ?ƒ€?ƒ?'=>'ddaa','?ƒƒ?ƒ‡?ƒ?'=>'ddee','?ƒƒ?ƒ‚?ƒ?'=>'ddii','?ƒƒ?ƒ‰?ƒ?'=>'ddoo','?ƒƒ?ƒ…?ƒ?'=>'dduu',
- // 2 character syllables - normal
- '?ƒ•?‚?'=>'fa','?ƒ•?‚§'=>'fe','?ƒ•?‚?'=>'fi','?ƒ•?‚Š'=>'fo','?ƒ•?‚?'=>'fu',
- // '?ƒ•?ƒ?'=>'fya','?ƒ•?‚§'=>'fye','?ƒ•?‚?'=>'fyi','?ƒ•?ƒ§'=>'fyo','?ƒ•?ƒ?'=>'fyu',
- '?ƒ•?ƒ?'=>'fa','?ƒ•?‚§'=>'fe','?ƒ•?‚?'=>'fi','?ƒ•?ƒ§'=>'fo','?ƒ•?ƒ?'=>'fu',
- '?ƒ’?ƒ?'=>'hya','?ƒ’?‚§'=>'hye','?ƒ’?‚?'=>'hyi','?ƒ’?ƒ§'=>'hyo','?ƒ’?ƒ?'=>'hyu',
- '?ƒ“?ƒ?'=>'bya','?ƒ“?‚§'=>'bye','?ƒ“?‚?'=>'byi','?ƒ“?ƒ§'=>'byo','?ƒ“?ƒ?'=>'byu',
- '?ƒ”?ƒ?'=>'pya','?ƒ”?‚§'=>'pye','?ƒ”?‚?'=>'pyi','?ƒ”?ƒ§'=>'pyo','?ƒ”?ƒ?'=>'pyu',
- '?‚?ƒ?'=>'kya','?‚?‚§'=>'kye','?‚?‚?'=>'kyi','?‚?ƒ§'=>'kyo','?‚?ƒ?'=>'kyu',
- '?‚Ž?ƒ?'=>'gya','?‚Ž?‚§'=>'gye','?‚Ž?‚?'=>'gyi','?‚Ž?ƒ§'=>'gyo','?‚Ž?ƒ?'=>'gyu',
- '?ƒ&#x;?ƒ?'=>'mya','?ƒ&#x;?‚§'=>'mye','?ƒ&#x;?‚?'=>'myi','?ƒ&#x;?ƒ§'=>'myo','?ƒ&#x;?ƒ?'=>'myu',
- '?ƒ‹?ƒ?'=>'nya','?ƒ‹?‚§'=>'nye','?ƒ‹?‚?'=>'nyi','?ƒ‹?ƒ§'=>'nyo','?ƒ‹?ƒ?'=>'nyu',
- '?ƒ??ƒ?'=>'rya','?ƒ??‚§'=>'rye','?ƒ??‚?'=>'ryi','?ƒ??ƒ§'=>'ryo','?ƒ??ƒ?'=>'ryu',
- '?‚??ƒ?'=>'sha','?‚??‚§'=>'she','?‚??ƒ§'=>'sho','?‚??ƒ?'=>'shu',
- '?‚¸?ƒ?'=>'ja','?‚¸?‚§'=>'je','?‚¸?ƒ§'=>'jo','?‚¸?ƒ?'=>'ju',
- '?‚š?‚?'=>'swa','?‚š?‚§'=>'swe','?‚š?‚?'=>'swi','?‚š?‚Š'=>'swo','?‚š?‚?'=>'swu',
- '?ƒ‡?‚?'=>'da','?ƒ‡?‚§'=>'de','?ƒ‡?‚?'=>'di','?ƒ‡?‚Š'=>'do','?ƒ‡?‚?'=>'du',
- '?ƒ ?ƒ?'=>'cha','?ƒ ?‚§'=>'che','?ƒ '=>'chi','?ƒ ?ƒ§'=>'cho','?ƒ ?ƒ?'=>'chu',
- // '?ƒ‚?ƒ?'=>'dya','?ƒ‚?‚§'=>'dye','?ƒ‚?‚?'=>'dyi','?ƒ‚?ƒ§'=>'dyo','?ƒ‚?ƒ?'=>'dyu',
- '?ƒ„?ƒ?'=>'tsa','?ƒ„?‚§'=>'tse','?ƒ„?‚?'=>'tsi','?ƒ„?ƒ§'=>'tso','?ƒ„'=>'tsu',
- '?ƒˆ?‚?'=>'twa','?ƒˆ?‚§'=>'twe','?ƒˆ?‚?'=>'twi','?ƒˆ?‚Š'=>'two','?ƒˆ?‚?'=>'twu',
- '?ƒ‰?‚?'=>'dwa','?ƒ‰?‚§'=>'dwe','?ƒ‰?‚?'=>'dwi','?ƒ‰?‚Š'=>'dwo','?ƒ‰?‚?'=>'dwu',
- '?‚??‚?'=>'wha','?‚??‚§'=>'whe','?‚??‚?'=>'whi','?‚??‚Š'=>'who','?‚??‚?'=>'whu',
- '?ƒ´?ƒ?'=>'vya','?ƒ´?‚§'=>'vye','?ƒ´?‚?'=>'vyi','?ƒ´?ƒ§'=>'vyo','?ƒ´?ƒ?'=>'vyu',
- '?ƒ´?‚?'=>'va','?ƒ´?‚§'=>'ve','?ƒ´?‚?'=>'vi','?ƒ´?‚Š'=>'vo','?ƒ´'=>'vu',
- '?‚??‚§'=>'we','?‚??‚?'=>'wi',
- '?‚¤?‚§'=>'ye',
- '?ƒ†?‚?'=>'ti',
- '?ƒ‚?‚?'=>'di',
- // 2 character syllables - doubled vocal
- '?‚??ƒ?'=>'aa','?‚¨?ƒ?'=>'ee','?‚¤?ƒ?'=>'ii','?‚??ƒ?'=>'oo','?‚??ƒ?'=>'uu',
- '?ƒ€?ƒ?'=>'daa','?ƒ‡?ƒ?'=>'dee','?ƒ‚?ƒ?'=>'dii','?ƒ‰?ƒ?'=>'doo','?ƒ…?ƒ?'=>'duu',
- '?ƒ??ƒ?'=>'haa','?ƒ˜?ƒ?'=>'hee','?ƒ’?ƒ?'=>'hii','?ƒ›?ƒ?'=>'hoo','?ƒ•?ƒ?'=>'fuu',
- '?ƒ??ƒ?'=>'baa','?ƒ™?ƒ?'=>'bee','?ƒ“?ƒ?'=>'bii','?ƒœ?ƒ?'=>'boo','?ƒ–?ƒ?'=>'buu',
- '?ƒ‘?ƒ?'=>'paa','?ƒš?ƒ?'=>'pee','?ƒ”?ƒ?'=>'pii','?ƒ??ƒ?'=>'poo','?ƒ—?ƒ?'=>'puu',
- '?‚??ƒ?'=>'kee','?‚?ƒ?'=>'kii','?‚??ƒ?'=>'koo','?‚??ƒ?'=>'kuu','?‚??ƒ?'=>'kaa',
- '?‚??ƒ?'=>'gaa','?‚??ƒ?'=>'gee','?‚Ž?ƒ?'=>'gii','?‚´?ƒ?'=>'goo','?‚°?ƒ?'=>'guu',
- '?ƒž?ƒ?'=>'maa','?ƒ??ƒ?'=>'mee','?ƒ&#x;?ƒ?'=>'mii','?ƒ??ƒ?'=>'moo','?ƒ ?ƒ?'=>'muu',
- '?ƒŠ?ƒ?'=>'naa','?ƒ??ƒ?'=>'nee','?ƒ‹?ƒ?'=>'nii','?ƒŽ?ƒ?'=>'noo','?ƒŒ?ƒ?'=>'nuu',
- '?ƒŠ?ƒ?'=>'raa','?ƒ??ƒ?'=>'ree','?ƒ??ƒ?'=>'rii','?ƒ?ƒ?'=>'roo','?ƒ??ƒ?'=>'ruu',
- '?‚??ƒ?'=>'saa','?‚??ƒ?'=>'see','?‚??ƒ?'=>'shii','?‚??ƒ?'=>'soo','?‚š?ƒ?'=>'suu',
- '?‚??ƒ?'=>'zaa','?‚??ƒ?'=>'zee','?‚¸?ƒ?'=>'jii','?‚ž?ƒ?'=>'zoo','?‚??ƒ?'=>'zuu',
- '?‚??ƒ?'=>'taa','?ƒ†?ƒ?'=>'tee','?ƒ ?ƒ?'=>'chii','?ƒˆ?ƒ?'=>'too','?ƒ„?ƒ?'=>'tsuu',
- '?ƒ??ƒ?'=>'waa','?ƒ??ƒ?'=>'woo',
- '?ƒ¤?ƒ?'=>'yaa','?ƒ¨?ƒ?'=>'yoo','?ƒ??ƒ?'=>'yuu',
- '?ƒ??ƒ?'=>'kaa','?ƒ??ƒ?'=>'kee',
- // old characters
- '?ƒ??ƒ?'=>'wee','?ƒ°?ƒ?'=>'wii',
- // seperate katakana 'n'
- '?ƒ??‚?'=>'n_a','?ƒ??‚¨'=>'n_e','?ƒ??‚¤'=>'n_i','?ƒ??‚?'=>'n_o','?ƒ??‚?'=>'n_u',
- '?ƒ??ƒ¤'=>'n_ya','?ƒ??ƒ¨'=>'n_yo','?ƒ??ƒ?'=>'n_yu',
- // 2 character syllables - doubled consonants
- '?ƒƒ?ƒ?'=>'bba','?ƒƒ?ƒ™'=>'bbe','?ƒƒ?ƒ“'=>'bbi','?ƒƒ?ƒœ'=>'bbo','?ƒƒ?ƒ–'=>'bbu',
- '?ƒƒ?ƒ‘'=>'ppa','?ƒƒ?ƒš'=>'ppe','?ƒƒ?ƒ”'=>'ppi','?ƒƒ?ƒ?'=>'ppo','?ƒƒ?ƒ—'=>'ppu',
- '?ƒƒ?‚?'=>'kke','?ƒƒ?‚'=>'kki','?ƒƒ?‚?'=>'kko','?ƒƒ?‚?'=>'kku','?ƒƒ?‚?'=>'kka',
- '?ƒƒ?‚?'=>'gga','?ƒƒ?‚?'=>'gge','?ƒƒ?‚Ž'=>'ggi','?ƒƒ?‚´'=>'ggo','?ƒƒ?‚°'=>'ggu',
- '?ƒƒ?ƒž'=>'ma','?ƒƒ?ƒ?'=>'me','?ƒƒ?ƒ&#x;'=>'mi','?ƒƒ?ƒ?'=>'mo','?ƒƒ?ƒ '=>'mu',
- '?ƒƒ?ƒŠ'=>'nna','?ƒƒ?ƒ?'=>'nne','?ƒƒ?ƒ‹'=>'nni','?ƒƒ?ƒŽ'=>'nno','?ƒƒ?ƒŒ'=>'nnu',
- '?ƒƒ?ƒŠ'=>'rra','?ƒƒ?ƒ?'=>'rre','?ƒƒ?ƒ?'=>'rri','?ƒƒ?ƒ'=>'rro','?ƒƒ?ƒ?'=>'rru',
- '?ƒƒ?‚?'=>'ssa','?ƒƒ?‚?'=>'sse','?ƒƒ?‚?'=>'sshi','?ƒƒ?‚?'=>'sso','?ƒƒ?‚š'=>'ssu',
- '?ƒƒ?‚?'=>'zza','?ƒƒ?‚?'=>'zze','?ƒƒ?‚¸'=>'jji','?ƒƒ?‚ž'=>'zzo','?ƒƒ?‚?'=>'zzu',
- '?ƒƒ?‚?'=>'tta','?ƒƒ?ƒ†'=>'tte','?ƒƒ?ƒ '=>'cchi','?ƒƒ?ƒˆ'=>'tto','?ƒƒ?ƒ„'=>'ttsu',
- '?ƒƒ?ƒ€'=>'dda','?ƒƒ?ƒ‡'=>'dde','?ƒƒ?ƒ‚'=>'ddi','?ƒƒ?ƒ‰'=>'ddo','?ƒƒ?ƒ…'=>'ddu',
- // 1 character syllables
- '?‚?'=>'a','?‚¨'=>'e','?‚¤'=>'i','?‚?'=>'o','?‚?'=>'u','?ƒ?'=>'n',
- '?ƒ?'=>'ha','?ƒ˜'=>'he','?ƒ’'=>'hi','?ƒ›'=>'ho','?ƒ•'=>'fu',
- '?ƒ?'=>'ba','?ƒ™'=>'be','?ƒ“'=>'bi','?ƒœ'=>'bo','?ƒ–'=>'bu',
- '?ƒ‘'=>'pa','?ƒš'=>'pe','?ƒ”'=>'pi','?ƒ?'=>'po','?ƒ—'=>'pu',
- '?‚?'=>'ke','?‚'=>'ki','?‚?'=>'ko','?‚?'=>'ku','?‚?'=>'ka',
- '?‚?'=>'ga','?‚?'=>'ge','?‚Ž'=>'gi','?‚´'=>'go','?‚°'=>'gu',
- '?ƒž'=>'ma','?ƒ?'=>'me','?ƒ&#x;'=>'mi','?ƒ?'=>'mo','?ƒ '=>'mu',
- '?ƒŠ'=>'na','?ƒ?'=>'ne','?ƒ‹'=>'ni','?ƒŽ'=>'no','?ƒŒ'=>'nu',
- '?ƒŠ'=>'ra','?ƒ?'=>'re','?ƒ?'=>'ri','?ƒ'=>'ro','?ƒ?'=>'ru',
- '?‚?'=>'sa','?‚?'=>'se','?‚?'=>'shi','?‚?'=>'so','?‚š'=>'su',
- '?‚?'=>'za','?‚?'=>'ze','?‚¸'=>'ji','?‚ž'=>'zo','?‚?'=>'zu',
- '?‚?'=>'ta','?ƒ†'=>'te','?ƒ '=>'chi','?ƒˆ'=>'to','?ƒ„'=>'tsu',
- '?ƒ€'=>'da','?ƒ‡'=>'de','?ƒ‚'=>'di','?ƒ‰'=>'do','?ƒ…'=>'du',
- '?ƒ?'=>'wa','?ƒ?'=>'wo',
- '?ƒ¤'=>'ya','?ƒ¨'=>'yo','?ƒ?'=>'yu',
- '?ƒ?'=>'ka','?ƒ?'=>'ke',
- // old characters
- '?ƒ?'=>'we','?ƒ°'=>'wi',
- // convert what's left (probably only kicks in when something's missing above)
- '?‚?'=>'a','?‚§'=>'e','?‚?'=>'i','?‚Š'=>'o','?‚?'=>'u',
- '?ƒ?'=>'ya','?ƒ§'=>'yo','?ƒ?'=>'yu',
- // special characters
- '?ƒ?'=>'_','?€ '=>'_',
- '?ƒ?'=>'_', // when used with hiragana (seldom), this character would not be converted otherwise
- // '?ƒŠ'=>'la','?ƒ?'=>'le','?ƒ?'=>'li','?ƒ'=>'lo','?ƒ?'=>'lu',
- // '?ƒ ?ƒ?'=>'cya','?ƒ ?‚§'=>'cye','?ƒ ?‚?'=>'cyi','?ƒ ?ƒ§'=>'cyo','?ƒ ?ƒ?'=>'cyu',
- //'?ƒ‡?ƒ?'=>'dha','?ƒ‡?‚§'=>'dhe','?ƒ‡?‚?'=>'dhi','?ƒ‡?ƒ§'=>'dho','?ƒ‡?ƒ?'=>'dhu',
- // '?ƒ??ƒ?'=>'lya','?ƒ??‚§'=>'lye','?ƒ??‚?'=>'lyi','?ƒ??ƒ§'=>'lyo','?ƒ??ƒ?'=>'lyu',
- // '?ƒ†?ƒ?'=>'tha','?ƒ†?‚§'=>'the','?ƒ†?‚?'=>'thi','?ƒ†?ƒ§'=>'tho','?ƒ†?ƒ?'=>'thu',
- //'?ƒ•?‚?'=>'fwa','?ƒ•?‚§'=>'fwe','?ƒ•?‚?'=>'fwi','?ƒ•?‚Š'=>'fwo','?ƒ•?‚?'=>'fwu',
- //'?ƒ ?ƒ?'=>'tya','?ƒ ?‚§'=>'tye','?ƒ ?‚?'=>'tyi','?ƒ ?ƒ§'=>'tyo','?ƒ ?ƒ?'=>'tyu',
- // '?‚¸?ƒ?'=>'jya','?‚¸?‚§'=>'jye','?‚¸?‚?'=>'jyi','?‚¸?ƒ§'=>'jyo','?‚¸?ƒ?'=>'jyu',
- // '?‚¸?ƒ?'=>'zha','?‚¸?‚§'=>'zhe','?‚¸?‚?'=>'zhi','?‚¸?ƒ§'=>'zho','?‚¸?ƒ?'=>'zhu',
- //'?‚¸?ƒ?'=>'zya','?‚¸?‚§'=>'zye','?‚¸?‚?'=>'zyi','?‚¸?ƒ§'=>'zyo','?‚¸?ƒ?'=>'zyu',
- //'?‚??ƒ?'=>'sya','?‚??‚§'=>'sye','?‚??‚?'=>'syi','?‚??ƒ§'=>'syo','?‚??ƒ?'=>'syu',
- //'?‚?'=>'ci','?ƒ•'=>'hu',?‚?'=>'si','?ƒ '=>'ti','?ƒ„'=>'tu','?‚¤'=>'yi','?ƒ‚'=>'dzi',
- // "Greeklish"
- 'Γ'=>'G','Δ'=>'E','Θ'=>'Th','Λ'=>'L','Ξ'=>'X','Î '=>'P','Î?'=>'S','Î?'=>'F','Ψ'=>'Ps',
- 'Î?'=>'g','δ'=>'e','θ'=>'th','Î?'=>'l','Ξ'=>'x','?€'=>'p','?ƒ'=>'s','?†'=>'f','?ˆ'=>'ps',
- // Thai
- '?¸ '=>'k','?¸‚'=>'kh','?¸ƒ'=>'kh','?¸„'=>'kh','?¸…'=>'kh','?¸†'=>'kh','?¸‡'=>'ng','?¸ˆ'=>'ch',
- '?¸‰'=>'ch','?¸Š'=>'ch','?¸‹'=>'s','?¸Œ'=>'ch','?¸?'=>'y','?¸Ž'=>'d','?¸?'=>'t','?¸?'=>'th',
- '?¸‘'=>'d','?¸’'=>'th','?¸“'=>'n','?¸”'=>'d','?¸•'=>'t','?¸–'=>'th','?¸—'=>'th','?¸˜'=>'th',
- '?¸™'=>'n','?¸š'=>'b','?¸›'=>'p','?¸œ'=>'ph','?¸?'=>'f','?¸ž'=>'ph','?¸&#x;'=>'f','?¸ '=>'ph',
- '?¸?'=>'m','?¸?'=>'y','?¸?'=>'r','?¸¤'=>'rue','?¸¤?š…'=>'rue','?¸?'=>'l','?¸?'=>'lue',
- '?¸??š…'=>'lue','?¸§'=>'w','?¸¨'=>'s','?¸Š'=>'s','?¸?'=>'s','?¸?'=>'h','?¸?'=>'l','?¸Ž'=>'h',
- '?¸°'=>'a','?¸?'=>'a','?¸??¸?'=>'a','?¸?'=>'a','?š…'=>'a','?¸?'=>'am','?š??¸?'=>'am',
- '?¸´'=>'i','?¸?'=>'i','?¸?'=>'ue','?¸?'=>'ue','?¸¸'=>'u','?¸š'=>'u',
- '?š€'=>'e','?š '=>'ae','?š‚'=>'o','?¸'=>'o',
- '?¸??¸??¸°'=>'ia','?¸??¸?'=>'ia','?¸??¸?¸°'=>'uea','?¸??¸'=>'uea','?¸??¸§?¸°'=>'ua','?¸??¸§'=>'ua',
- '?šƒ'=>'ai','?š„'=>'ai','?¸??¸?'=>'ai','?¸??¸?'=>'ai','?¸??¸§'=>'ao',
- '?¸¸?¸?'=>'ui','?¸?¸?'=>'oi','?¸??¸?¸?'=>'ueai','?¸§?¸?'=>'uai',
- '?¸´?¸§'=>'io','?š‡?¸§'=>'eo','?¸??¸??¸§'=>'iao',
- '?šˆ'=>'','?š‰'=>'','?šŠ'=>'','?š‹'=>'','?š‡'=>'',
- '?šŒ'=>'','?šŽ'=>'','?š?'=>'','?¸?'=>'',
- '?š†'=>'2','?š?'=>'o','?¸?'=>'-','?šš'=>'-','?š›'=>'-',
- '?š?'=>'0','?š‘'=>'1','?š’'=>'2','?š“'=>'3','?š”'=>'4',
- '?š•'=>'5','?š–'=>'6','?š—'=>'7','?š˜'=>'8','?š™'=>'9',
- // Korean
- '?„?'=>'k','?…‹'=>'kh','?„?'=>'kk','?„?'=>'t','?…Œ'=>'th','?„¸'=>'tt','?…‚'=>'p',
- '?…?'=>'ph','?…ƒ'=>'pp','?…ˆ'=>'c','?…Š'=>'ch','?…‰'=>'cc','?……'=>'s','?…†'=>'ss',
- '?…Ž'=>'h','?…‡'=>'ng','?„´'=>'n','?„š'=>'l','?… '=>'m', '?…?'=>'a','?…“'=>'e','?…—'=>'o',
- '?…œ'=>'wu','?…?'=>'u','?…?'=>'i','?…?'=>'ay','?…”'=>'ey','?…š'=>'oy','?…˜'=>'wa','?…?'=>'we',
- '?…&#x;'=>'wi','?…™'=>'way','?…ž'=>'wey','?…?'=>'uy','?…‘'=>'ya','?…•'=>'ye','?…›'=>'oy',
- '?… '=>'yu','?…’'=>'yay','?…–'=>'yey',
- );