/utf8.php
PHP | 1618 lines | 984 code | 149 blank | 485 comment | 168 complexity | 0c5597f8ecec2f4b3ada4d0743facfa0 MD5 | raw file
Possible License(s): GPL-3.0, BSD-2-Clause
- <?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[$i]) & 0xC0) != 0x80))
- return false;
- }
- }
- return true;
- }
- }
- if(!function_exists('utf8_strlen')){
- /**
- * Unicode aware replacement for strlen()
- *
- * utf8_decode() converts characters that are not in ISO-8859-1
- * to '?', which, for the purpose of counting, is alright - It's
- * even faster than mb_strlen.
- *
- * @author <chernyshevsky at hotmail dot com>
- * @see strlen()
- * @see utf8_decode()
- */
- function utf8_strlen($string){
- return strlen(utf8_decode($string));
- }
- }
- if(!function_exists('utf8_substr')){
- /**
- * UTF-8 aware alternative to substr
- *
- * Return part of a string given character offset (and optionally length)
- *
- * @author Harry Fuecks <hfuecks@gmail.com>
- * @author Chris Smith <chris@jalakai.co.uk>
- * @param string
- * @param integer number of UTF-8 characters offset (from left)
- * @param integer (optional) length in UTF-8 characters from offset
- * @return mixed string or false if failure
- */
- function utf8_substr($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 $match[1];
- }
- }
- if(!function_exists('utf8_substr_replace')){
- /**
- * Unicode aware replacement for substr_replace()
- *
- * @author Andreas Gohr <andi@splitbrain.org>
- * @see substr_replace()
- */
- function utf8_substr_replace($string, $replacement, $start , $length=0 ){
- $ret = '';
- if($start>0) $ret .= utf8_substr($string, 0, $start);
- $ret .= $replacement;
- $ret .= utf8_substr($string, $start+$length);
- return $ret;
- }
- }
- if(!function_exists('utf8_ltrim')){
- /**
- * Unicode aware replacement for ltrim()
- *
- * @author Andreas Gohr <andi@splitbrain.org>
- * @see ltrim()
- * @return string
- */
- function utf8_ltrim($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()
- * @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','',$str);
- }
- }
- if(!function_exists('utf8_trim')){
- /**
- * Unicode aware replacement for trim()
- *
- * @author Andreas Gohr <andi@splitbrain.org>
- * @see trim()
- * @return string
- */
- function utf8_trim($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',$str);
- }
- /**
- * Callback function for preg_replace_callback call in utf8_ucwords
- * You don't need to call this yourself
- *
- * @author Harry Fuecks
- * @param array of matches corresponding to a single word
- * @return string with first char of the word in uppercase
- * @see utf8_ucwords
- * @see utf8_strtoupper
- */
- function utf8_ucwords_callback($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 <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 $additional Additional chars to strip (used in regexp char class)
- */
- function utf8_stripspecials($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 <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 $entities Flag controlling decoding of named entities.
- * @return UTF-8 encoded string with numeric (and named) entities replaced.
- */
- function utf8_unhtml($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 $strict is set to true the function returns false if the input
- * string isn't a valid UTF-8 octet sequence and raises a PHP error at
- * level E_USER_WARNING
- *
- * Note: this function has been modified slightly in this library to
- * trigger errors on encountering bad bytes
- *
- * @author <hsivonen@iki.fi>
- * @author Harry Fuecks <hfuecks@gmail.com>
- * @param string UTF-8 encoded string
- * @param boolean Check for invalid sequences?
- * @return mixed array of unicode code points or false if UTF-8 invalid
- * @see unicode_to_utf8
- * @link http://hsivonen.iki.fi/php-utf8/
- * @link http://sourceforge.net/projects/phputf8/
- */
- function utf8_to_unicode($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 $strict is set to true the function returns false if the input
- * array contains ints that represent surrogates or are outside the
- * Unicode range and raises a PHP error at level E_USER_WARNING
- *
- * Note: this function has been modified slightly in this library to use
- * output buffering to concatenate the UTF-8 string (faster) as well as
- * reference the array by it's keys
- *
- * @param array of unicode code points representing a string
- * @param boolean Check for invalid sequences?
- * @return mixed UTF-8 string or false if array contains invalid code points
- * @author <hsivonen@iki.fi>
- * @author Harry Fuecks <hfuecks@gmail.com>
- * @see utf8_to_unicode
- * @link http://hsivonen.iki.fi/php-utf8/
- * @link http://sourceforge.net/projects/phputf8/
- */
- function unicode_to_utf8($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($uni);
- }
- }
- if(!function_exists('utf8_bad_replace')){
- /**
- * Replace bad bytes with an alternative character
- *
- * ASCII character is recommended for replacement char
- *
- * PCRE Pattern to locate bad bytes in a UTF-8 string
- * Comes from W3 FAQ: Multilingual Forms
- * Note: modified to include full ASCII range including control chars
- *
- * @author Harry Fuecks <hfuecks@gmail.com>
- * @see http://www.w3.org/International/questions/qa-forms-utf-8
- * @param string to search
- * @param string to replace bad bytes with (defaults to '?') - use ASCII
- * @return string
- */
- function utf8_bad_replace($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 $str now pointing to a utf8 character boundary
- *
- * @author chris smith <chris@jalakai.co.uk>
- */
- function utf8_correctIdx(&$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(
- "ď˝"=>"ďźş","ď˝"=>"ďźš","ď˝"=>"","ď˝"=>"","ď˝"=>"ďźś","ď˝"=>"ďźľ","ď˝"=>"ďź´","ď˝"=>"ďźł","ď˝"=>"","ď˝"=>"ďźą",
- "ď˝"=>"ďź°","ď˝"=>"","ď˝"=>"","ď˝"=>"ďź","ď˝"=>"","ď˝"=>"","ď˝"=>"","ď˝"=>"","ď˝"=>"","ď˝"=>"",
- "ď˝"=>"","ď˝
"=>"","ď˝"=>"","ď˝"=>"","ď˝"=>"","ď˝"=>"","áżł"=>"áżź","ῼ"=>"῏","ῥ"=>"Ὴ","áż"=>"áż",
- "áż"=>"áż","áż"=>"áż","ážž"=>"Î","ážł"=>"ážź","ážą"=>"ážš","áž°"=>"ី","ឧ"=>"ឯ","ឌ"=>"ណ","ូ"=>"áž","ឤ"=>"ត",
- "ឣ"=>"ឍ","អ"=>"ឪ","ឥ"=>"ដ","áž"=>"áž","áž"=>"áž","áž"=>"áž","áž"=>"áž","áž"=>"áž","áž"=>"áž","áž"=>"áž",
- "áž"=>"áž","áž"=>"áž","áž"=>"áž","áž
"=>"áž","áž"=>"áž","áž"=>"áž","áž"=>"áž","áž"=>"áž","áž"=>"áž","á˝˝"=>"áżť",
- "Ὗ"=>"áżş","Ὕ"=>"῍","ὺ"=>"Ὺ","὚"=>"áżš","ὸ"=>"Ὸ","ὡ"=>"áż","὜"=>"áż","὾"=>"áż","á˝´"=>"áż","έ"=>"áż",
- "ὲ"=>"áż","ό"=>"ážť","á˝°"=>"ážş","ὧ"=>"Ὧ","Ὄ"=>"὎","ὼ"=>"á˝","ὤ"=>"὏","ὣ"=>"Ὅ","ὢ"=>"Ὢ","ὥ"=>"Ὂ",
- "á˝"=>"á˝","á˝"=>"á˝","á˝"=>"á˝","á˝"=>"á˝","á˝
"=>"á˝","á˝"=>"á˝","á˝"=>"á˝","á˝"=>"á˝","á˝"=>"á˝","á˝"=>"á˝",
- "១"=>"៿","ៜ"=>"៞","៾"=>"៽","៴"=>"៟","៳"=>"៝","៲"=>"៺","៹"=>"៚","៰"=>"៸","៧"=>"៯","៌"=>"៎",
- "៼"=>"áź","៤"=>"៏","៣"=>"៍","២"=>"៪","៥"=>"៊","áź"=>"áź","áź"=>"áź","áź"=>"áź","áź"=>"áź","áź"=>"áź",
- "áź"=>"áź","áź"=>"áź","áź"=>"áź","áź
"=>"áź","áź"=>"áź","áź"=>"áź","áź"=>"áź","áź"=>"áź","áź"=>"áź","áťš"=>"᝸",
- "ᝡ"=>"áťś","áťľ"=>"áť´","áťł"=>"ᝲ","áťą"=>"áť°","ᝯ"=>"ᝎ","áť"=>"ᝏ","ᝍ"=>"ᝪ","ᝊ"=>"ᝨ","ᝧ"=>"ᝌ","᝼"=>"ᝤ",
- "ᝣ"=>"ᝢ","ᝥ"=>"áť ","áť"=>"áť","áť"=>"áť","áť"=>"áť","áť"=>"áť","áť"=>"áť","áť"=>"áť","áť"=>"áť","áť"=>"áť",
- "áť"=>"áť","áť"=>"áť","áť"=>"áť","áť"=>"áť","áť"=>"áť","áť
"=>"áť","áť"=>"áť","áť"=>"áť","áşż"=>"áşž","áş˝"=>"áşź",
- "áşť"=>"áşş","áşš"=>"Ẹ","ạ"=>"áşś","áşľ"=>"áş´","áşł"=>"Ẳ","áşą"=>"áş°","ắ"=>"Ẏ","áş"=>"ẏ","ẍ"=>"Ẫ","Ẋ"=>"Ẩ",
- "ầ"=>"Ẍ","Ẽ"=>"Ấ","ả"=>"Ả","ấ"=>"áş ","áş"=>"áš ","áş"=>"áş","áş"=>"áş","áş"=>"áş","áş"=>"áş","áş"=>"áş",
- "áş"=>"áş","áş"=>"áş","áş"=>"áş","áş
"=>"áş","áş"=>"áş","áş"=>"áş","ášż"=>"ášž","áš˝"=>"ášź","ášť"=>"ášş","ášš"=>"ᚸ",
- "ᚡ"=>"ášś","ášľ"=>"áš´","ášł"=>"ᚲ","ášą"=>"áš°","ᚯ"=>"ᚎ","áš"=>"ᚏ","ᚍ"=>"ᚪ","ᚊ"=>"ᚨ","ᚧ"=>"ᚌ","ᚼ"=>"ᚤ",
- "ᚣ"=>"ᚢ","ᚥ"=>"áš ","áš"=>"áš","áš"=>"áš","áš"=>"áš","áš"=>"áš","áš"=>"áš","áš"=>"áš","áš"=>"áš","áš"=>"áš",
- "áš"=>"áš","áš"=>"áš","áš"=>"áš","áš"=>"áš","áš"=>"áš","áš
"=>"áš","áš"=>"áš","áš"=>"áš","ḿ"=>"Ḟ","ḽ"=>"ḟ",
- "ḝ"=>"Ḻ","Ḛ"=>"Ḹ","ḡ"=>"Ḝ","Ḿ"=>"Ḵ","ḳ"=>"Ḳ","ḹ"=>"Ḱ","ḯ"=>"Ḏ","á¸"=>"ḏ","ḍ"=>"Ḫ","Ḋ"=>"Ḩ",
- "ḧ"=>"Ḍ","Ḽ"=>"Ḥ","ḣ"=>"Ḣ","ḥ"=>"Ḡ","á¸"=>"á¸","á¸"=>"á¸","á¸"=>"á¸","á¸"=>"á¸","á¸"=>"á¸","á¸"=>"á¸",
- "á¸"=>"á¸","á¸"=>"á¸","á¸"=>"á¸","á¸"=>"á¸","á¸"=>"á¸","á¸"=>"á¸","á¸"=>"á¸","á¸
"=>"á¸","á¸"=>"á¸","á¸"=>"á¸",
- "Ö"=>"Ő","Ö
"=>"Ő","Ö"=>"Ő","Ö"=>"Ő","Ö"=>"Ő","Ö"=>"Ő","Ö"=>"Ő","Őż"=>"Ő","Őž"=>"Ő","Ő˝"=>"Ő",
- "Őź"=>"Ő","Őť"=>"Ő","Őş"=>"Ő","Őš"=>"Ő","Ő¸"=>"Ő","Őˇ"=>"Ő","Őś"=>"Ő","Őľ"=>"Ő
","Ő´"=>"Ő","Őł"=>"Ő",
- "Ő˛"=>"Ő","Őą"=>"Ő","Ő°"=>"Ő","ŐŻ"=>"Ôż","ŐŽ"=>"Ôž","Ő"=>"Ô˝","ŐŹ"=>"Ôź","ŐŤ"=>"Ôť","ŐŞ"=>"Ôş","ŐŠ"=>"Ôš",
- "Ő¨"=>"Ô¸","Ő§"=>"Ôˇ","ŐŚ"=>"Ôś","ŐĽ"=>"Ôľ","Ő¤"=>"Ô´","ŐŁ"=>"Ôł","Ő˘"=>"Ô˛","ŐĄ"=>"Ôą","Ô"=>"Ô","Ô"=>"Ô",
- "Ô"=>"Ô","Ô"=>"Ô","Ô"=>"Ô","Ô
"=>"Ô","Ô"=>"Ô","Ô"=>"Ô","Óš"=>"Ó¸","Óľ"=>"Ó´","Ół"=>"Ó˛","Óą"=>"Ó°",
- "ÓŻ"=>"ÓŽ","Ó"=>"ÓŹ","ÓŤ"=>"ÓŞ","ÓŠ"=>"Ó¨","Ó§"=>"ÓŚ","ÓĽ"=>"Ó¤","ÓŁ"=>"Ó˘","ÓĄ"=>"Ó ","Ó"=>"Ó","Ó"=>"Ó",
- "Ó"=>"Ó","Ó"=>"Ó","Ó"=>"Ó","Ó"=>"Ó","Ó"=>"Ó","Ó"=>"Ó","Ó"=>"Ó","Ó"=>"Ó","Ó"=>"Ó","Ó"=>"Ó",
- "Ó"=>"Ó
","Ó"=>"Ó","Ó"=>"Ó","Ňż"=>"Ňž","Ň˝"=>"Ňź","Ňť"=>"Ňş","Ňš"=>"Ҹ","ҡ"=>"Ňś","Ňľ"=>"Ň´","Ňł"=>"Ҳ",
- "Ňą"=>"Ň°","ŇŻ"=>"ŇŽ","Ň"=>"ŇŹ","ŇŤ"=>"ŇŞ","ŇŠ"=>"Ҩ","ҧ"=>"ŇŚ","ŇĽ"=>"Ҥ","ŇŁ"=>"Ң","ŇĄ"=>"Ň ","Ň"=>"Ň",
- "Ň"=>"Ň","Ň"=>"Ň","Ň"=>"Ň","Ň"=>"Ň","Ň"=>"Ň","Ň"=>"Ň","Ň"=>"Ň","Ň"=>"Ň","Ň"=>"Ň","Ň"=>"Ň",
- "Ň"=>"Ň","Ńż"=>"Ńž","Ń˝"=>"Ńź","Ńť"=>"Ńş","Ńš"=>"Ѹ","ѡ"=>"Ńś","Ńľ"=>"Ń´","Ńł"=>"Ѳ","Ńą"=>"Ń°","ŃŻ"=>"ŃŽ",
- "Ń"=>"ŃŹ","ŃŤ"=>"ŃŞ","ŃŠ"=>"Ѩ","ѧ"=>"ŃŚ","ŃĽ"=>"Ѥ","ŃŁ"=>"Ѣ","ŃĄ"=>"Ń ","Ń"=>"Đ","Ń"=>"Đ","Ń"=>"Đ",
- "Ń"=>"Đ","Ń"=>"Đ","Ń"=>"Đ","Ń"=>"Đ","Ń"=>"Đ","Ń"=>"Đ","Ń"=>"Đ","Ń"=>"Đ
","Ń"=>"Đ","Ń"=>"Đ",
- "Ń"=>"Đ","Ń"=>"Đ","Ń"=>"Đ","Ń"=>"ĐŻ","Ń"=>"ĐŽ","Ń"=>"Đ","Ń"=>"ĐŹ","Ń"=>"ĐŤ","Ń"=>"ĐŞ","Ń"=>"ĐŠ",
- "Ń"=>"Ш","Ń"=>"Ч","Ń"=>"ĐŚ","Ń
"=>"ĐĽ","Ń"=>"Ф","Ń"=>"ĐŁ","Ń"=>"Т","Ń"=>"ĐĄ","Ń"=>"Đ ","Đż"=>"Đ",
- "Đž"=>"Đ","Đ˝"=>"Đ","Đź"=>"Đ","Đť"=>"Đ","Đş"=>"Đ","Đš"=>"Đ","и"=>"Đ","С"=>"Đ","Đś"=>"Đ","Đľ"=>"Đ",
- "Đ´"=>"Đ","Đł"=>"Đ","в"=>"Đ","Đą"=>"Đ","Đ°"=>"Đ","Ďľ"=>"Î","ϲ"=>"ÎŁ","Ďą"=>"ÎĄ","Ď°"=>"Î","ĎŻ"=>"ĎŽ",
- "Ď"=>"ĎŹ","ĎŤ"=>"ĎŞ","ĎŠ"=>"Ϩ","ϧ"=>"ĎŚ","ĎĽ"=>"Ϥ","ĎŁ"=>"Ϣ","ĎĄ"=>"Ď ","Ď"=>"Ď","Ď"=>"Ď","Ď"=>"Ď",
- "Ď"=>"Ď","Ď"=>"Î ","Ď"=>"ÎŚ","Ď"=>"Î","Ď"=>"Î","Ď"=>"Î","Ď"=>"Î","Ď"=>"Î","Ď"=>"ÎŤ","Ď"=>"ÎŞ",
- "Ď"=>"Ί","Ď"=>"Ψ","Ď"=>"Χ","Ď"=>"ÎŚ","Ď
"=>"ÎĽ","Ď"=>"Τ","Ď"=>"ÎŁ","Ď"=>"ÎŁ","Ď"=>"ÎĄ","Ď"=>"Î ",
- "Îż"=>"Î","Ξ"=>"Î","ν"=>"Î","Îź"=>"Î","Îť"=>"Î","Îş"=>"Î","Κ"=>"Î","θ"=>"Î","Ρ"=>"Î","Îś"=>"Î",
- "Îľ"=>"Î","δ"=>"Î","Îł"=>"Î","β"=>"Î","Îą"=>"Î","ÎŻ"=>"Î","ÎŽ"=>"Î","Î"=>"Î","ÎŹ"=>"Î","Ę"=>"ơ",
- "Ę"=>"Ʋ","Ę"=>"Ćą","Ę"=>"ĆŽ","Ę"=>"ĆŠ","Ę"=>"ĆŚ","Éľ"=>"Ć","ɲ"=>"Ć","ÉŻ"=>"Ć","ÉŠ"=>"Ć","ɨ"=>"Ć",
- "ÉŁ"=>"Ć","É"=>"Ć","É"=>"Ć","É"=>"Ć","É"=>"Ć","É"=>"Ć","É"=>"Ć","Čł"=>"Ȳ","Čą"=>"Č°","ČŻ"=>"ČŽ",
- "Č"=>"ČŹ","ČŤ"=>"ČŞ","ČŠ"=>"Ȩ","ȧ"=>"ČŚ","ČĽ"=>"Ȥ","ČŁ"=>"Ȣ","Č"=>"Č","Č"=>"Č","Č"=>"Č","Č"=>"Č",
- "Č"=>"Č","Č"=>"Č","Č"=>"Č","Č"=>"Č","Č"=>"Č","Č"=>"Č","Č"=>"Č","Č"=>"Č","Č"=>"Č","Č
"=>"Č",
- "Č"=>"Č","Č"=>"Č","Çż"=>"Çž","Ç˝"=>"Çź","Çť"=>"Çş","Çš"=>"Ǹ","Çľ"=>"Ç´","Çł"=>"Dz","ÇŻ"=>"ÇŽ","Ç"=>"ÇŹ",
- "ÇŤ"=>"ÇŞ","ÇŠ"=>"Ǩ","ǧ"=>"ÇŚ","ÇĽ"=>"Ǥ","ÇŁ"=>"Ǣ","ÇĄ"=>"Ç ","Ç"=>"Ç","Ç"=>"Ć","Ç"=>"Ç","Ç"=>"Ç",
- "Ç"=>"Ç","Ç"=>"Ç","Ç"=>"Ç","Ç"=>"Ç","Ç"=>"Ç","Ç"=>"Ç","Ç"=>"Ç","Ç"=>"Ç","Ç"=>"Ç
","ƿ"=>"ǡ",
- "Ć˝"=>"Ćź","Ćš"=>"Ƹ","Ćś"=>"Ćľ","Ć´"=>"Ćł","Ć°"=>"ĆŻ","Ć"=>"ĆŹ","ƨ"=>"Ƨ","ĆĽ"=>"Ƥ","ĆŁ"=>"Ƣ","ĆĄ"=>"Ć ",
- "Ć"=>"Č ","Ć"=>"Ć","Ć"=>"Çś","Ć"=>"Ć","Ć"=>"Ć","Ć"=>"Ć","Ć
"=>"Ć","Ć"=>"Ć","Ĺż"=>"S","Ĺž"=>"Ĺ˝",
- "Ĺź"=>"Ĺť","Ĺş"=>"Ĺš","š"=>"Ĺś","Ĺľ"=>"Ĺ´","Ĺł"=>"Ų","Ĺą"=>"Ĺ°","ĹŻ"=>"ĹŽ","Ĺ"=>"ĹŹ","ĹŤ"=>"ĹŞ","ĹŠ"=>"Ũ",
- "ŧ"=>"ĹŚ","ĹĽ"=>"Ť","ĹŁ"=>"Ţ","ĹĄ"=>"Ĺ ","Ĺ"=>"Ĺ","Ĺ"=>"Ĺ","Ĺ"=>"Ĺ","Ĺ"=>"Ĺ","Ĺ"=>"Ĺ","Ĺ"=>"Ĺ",
- "Ĺ"=>"Ĺ","Ĺ"=>"Ĺ","Ĺ"=>"Ĺ","Ĺ"=>"Ĺ","Ĺ"=>"Ĺ","Ĺ"=>"Ĺ","Ĺ"=>"Ĺ
","Ĺ"=>"Ĺ","Ĺ"=>"Ĺ","Ĺ"=>"Äż",
- "Äž"=>"Ä˝","Äź"=>"Äť","Äş"=>"Äš","ġ"=>"Äś","Äľ"=>"Ä´","Äł"=>"IJ","Äą"=>"I","ÄŻ"=>"ÄŽ","Ä"=>"ÄŹ","ÄŤ"=>"ÄŞ",
- "ÄŠ"=>"Ĩ","ħ"=>"ÄŚ","ÄĽ"=>"Ĥ","ÄŁ"=>"Ģ","ÄĄ"=>"Ä ","Ä"=>"Ä","Ä"=>"Ä","Ä"=>"Ä","Ä"=>"Ä","Ä"=>"Ä",
- "Ä"=>"Ä","Ä"=>"Ä","Ä"=>"Ä","Ä"=>"Ä","Ä"=>"Ä","Ä"=>"Ä","Ä"=>"Ä","Ä"=>"Ä","Ä
"=>"Ä","Ä"=>"Ä",
- "Ä"=>"Ä","Ăż"=>"Ÿ","Ăž"=>"Ă","Ă˝"=>"Ă","Ăź"=>"Ă","Ăť"=>"Ă","Ăş"=>"Ă","Ăš"=>"Ă","ø"=>"Ă","Ăś"=>"Ă",
- "Ăľ"=>"Ă","Ă´"=>"Ă","Ăł"=>"Ă","ò"=>"Ă","Ăą"=>"Ă","Ă°"=>"Ă","ĂŻ"=>"Ă","ĂŽ"=>"Ă","Ă"=>"Ă","ĂŹ"=>"Ă",
- "ĂŤ"=>"Ă","ĂŞ"=>"Ă","ĂŠ"=>"Ă","è"=>"Ă","ç"=>"Ă","ĂŚ"=>"Ă","ĂĽ"=>"Ă
","ä"=>"Ă","ĂŁ"=>"Ă","â"=>"Ă",
- "ĂĄ"=>"Ă","Ă "=>"Ă","Âľ"=>"Î","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 <andi@splitbrain.org>
- */
- global $UTF8_UPPER_TO_LOWER;
- if(empty($UTF8_UPPER_TO_LOWER)) $UTF8_UPPER_TO_LOWER = array (
- "ďźş"=>"ď˝","ďźš"=>"ď˝",""=>"ď˝",""=>"ď˝","ďźś"=>"ď˝","ďźľ"=>"ď˝","ďź´"=>"ď˝","ďźł"=>"ď˝",""=>"ď˝","ďźą"=>"ď˝",
- "ďź°"=>"ď˝",""=>"ď˝",""=>"ď˝","ďź"=>"ď˝",""=>"ď˝",""=>"ď˝",""=>"ď˝",""=>"ď˝",""=>"ď˝",""=>"ď˝",
- ""=>"ď˝",""=>"ď˝
",""=>"ď˝",""=>"ď˝",""=>"ď˝",""=>"ď˝","áżź"=>"áżł","῏"=>"ῼ","Ὴ"=>"ῥ","áż"=>"áż",
- "áż"=>"áż","áż"=>"áż","Î"=>"ážž","ážź"=>"ážł","ážš"=>"ážą","ី"=>"áž°","ឯ"=>"ឧ","ណ"=>"ឌ","áž"=>"ូ","ត"=>"ឤ",
- "ឍ"=>"ឣ","ឪ"=>"អ","ដ"=>"ឥ","áž"=>"áž","áž"=>"áž","áž"=>"áž","áž"=>"áž","áž"=>"áž","áž"=>"áž","áž"=>"áž",
- "áž"=>"áž","áž"=>"áž","áž"=>"áž","áž"=>"áž
","áž"=>"áž","áž"=>"áž","áž"=>"áž","áž"=>"áž","áž"=>"áž","áżť"=>"á˝˝",
- "áżş"=>"Ὗ","῍"=>"Ὕ","Ὺ"=>"ὺ","áżš"=>"὚","Ὸ"=>"ὸ","áż"=>"ὡ","áż"=>"὜","áż"=>"὾","áż"=>"á˝´","áż"=>"έ",
- "áż"=>"ὲ","ážť"=>"ό","ážş"=>"á˝°","Ὧ"=>"ὧ","὎"=>"Ὄ","á˝"=>"ὼ","὏"=>"ὤ","Ὅ"=>"ὣ","Ὢ"=>"ὢ","Ὂ"=>"ὥ",
- "á˝"=>"á˝","á˝"=>"á˝","á˝"=>"á˝","á˝"=>"á˝","á˝"=>"á˝
","á˝"=>"á˝","á˝"=>"á˝","á˝"=>"á˝","á˝"=>"á˝","á˝"=>"á˝",
- "៿"=>"១","៞"=>"ៜ","៽"=>"៾","៟"=>"៴","៝"=>"៳","៺"=>"៲","៚"=>"៹","៸"=>"៰","៯"=>"៧","៎"=>"៌",
- "áź"=>"៼","៏"=>"៤","៍"=>"៣","៪"=>"២","៊"=>"៥","áź"=>"áź","áź"=>"áź","áź"=>"áź","áź"=>"áź","áź"=>"áź",
- "áź"=>"áź","áź"=>"áź","áź"=>"áź","áź"=>"áź
","áź"=>"áź","áź"=>"áź","áź"=>"áź","áź"=>"áź","áź"=>"áź","᝸"=>"áťš",
- "áťś"=>"ᝡ","áť´"=>"áťľ","ᝲ"=>"áťł","áť°"=>"áťą","ᝎ"=>"ᝯ","ᝏ"=>"áť","ᝪ"=>"ᝍ","ᝨ"=>"ᝊ","ᝌ"=>"ᝧ","ᝤ"=>"᝼",
- "ᝢ"=>"ᝣ","áť "=>"ᝥ","áť"=>"áť","áť"=>"áť","áť"=>"áť","áť"=>"áť","áť"=>"áť","áť"=>"áť","áť"=>"áť","áť"=>"áť",
- "áť"=>"áť","áť"=>"áť","áť"=>"áť","áť"=>"áť","áť"=>"áť","áť"=>"áť
","áť"=>"áť","áť"=>"áť","áşž"=>"áşż","áşź"=>"áş˝",
- "áşş"=>"áşť","Ẹ"=>"áşš","áşś"=>"ạ","áş´"=>"áşľ","Ẳ"=>"áşł","áş°"=>"áşą","Ẏ"=>"ắ","ẏ"=>"áş","Ẫ"=>"ẍ","Ẩ"=>"Ẋ",
- "Ẍ"=>"ầ","Ấ"=>"Ẽ","Ả"=>"ả","áş "=>"ấ","áš "=>"áş","áş"=>"áş","áş"=>"áş","áş"=>"áş","áş"=>"áş","áş"=>"áş",
- "áş"=>"áş","áş"=>"áş","áş"=>"áş","áş"=>"áş
","áş"=>"áş","áş"=>"áş","ášž"=>"ášż","ášź"=>"áš˝","ášş"=>"ášť","ᚸ"=>"ášš",
- "ášś"=>"ᚡ","áš´"=>"ášľ","ᚲ"=>"ášł","áš°"=>"ášą","ᚎ"=>"ᚯ","ᚏ"=>"áš","ᚪ"=>"ᚍ","ᚨ"=>"ᚊ","ᚌ"=>"ᚧ","ᚤ"=>"ᚼ",
- "ᚢ"=>"ᚣ","áš "=>"ᚥ","áš"=>"áš","áš"=>"áš","áš"=>"áš","áš"=>"áš","áš"=>"áš","áš"=>"áš","áš"=>"áš","áš"=>"áš",
- "áš"=>"áš","áš"=>"áš","áš"=>"áš","áš"=>"áš","áš"=>"áš","áš"=>"áš
","áš"=>"áš","áš"=>"áš","Ḟ"=>"ḿ","ḟ"=>"ḽ",
- "Ḻ"=>"ḝ","Ḹ"=>"Ḛ","Ḝ"=>"ḡ","Ḵ"=>"Ḿ","Ḳ"=>"ḳ","Ḱ"=>"ḹ","Ḏ"=>"ḯ","ḏ"=>"á¸","Ḫ"=>"ḍ","Ḩ"=>"Ḋ",
- "Ḍ"=>"ḧ","Ḥ"=>"Ḽ","Ḣ"=>"ḣ","Ḡ"=>"ḥ","á¸"=>"á¸","á¸"=>"á¸","á¸"=>"á¸","á¸"=>"á¸","á¸"=>"á¸","á¸"=>"á¸",
- "á¸"=>"á¸","á¸"=>"á¸","á¸"=>"á¸","á¸"=>"á¸","á¸"=>"á¸","á¸"=>"á¸","á¸"=>"á¸","á¸"=>"á¸
","á¸"=>"á¸","á¸"=>"á¸",
- "Ő"=>"Ö","Ő"=>"Ö
","Ő"=>"Ö","Ő"=>"Ö","Ő"=>"Ö","Ő"=>"Ö","Ő"=>"Ö","Ő"=>"Őż","Ő"=>"Őž","Ő"=>"Ő˝",
- "Ő"=>"Őź","Ő"=>"Őť","Ő"=>"Őş","Ő"=>"Őš","Ő"=>"Ő¸","Ő"=>"Őˇ","Ő"=>"Őś","Ő
"=>"Őľ","Ő"=>"Ő´","Ő"=>"Őł",
- "Ő"=>"Ő˛","Ő"=>"Őą","Ő"=>"Ő°","Ôż"=>"ŐŻ","Ôž"=>"ŐŽ","Ô˝"=>"Ő","Ôź"=>"ŐŹ","Ôť"=>"ŐŤ","Ôş"=>"ŐŞ","Ôš"=>"ŐŠ",
- "Ô¸"=>"Ő¨","Ôˇ"=>"Ő§","Ôś"=>"ŐŚ","Ôľ"=>"ŐĽ","Ô´"=>"Ő¤","Ôł"=>"ŐŁ","Ô˛"=>"Ő˘","Ôą"=>"ŐĄ","Ô"=>"Ô","Ô"=>"Ô",
- "Ô"=>"Ô","Ô"=>"Ô","Ô"=>"Ô","Ô"=>"Ô
","Ô"=>"Ô","Ô"=>"Ô","Ó¸"=>"Óš","Ó´"=>"Óľ","Ó˛"=>"Ół","Ó°"=>"Óą",
- "ÓŽ"=>"ÓŻ","ÓŹ"=>"Ó","ÓŞ"=>"ÓŤ","Ó¨"=>"ÓŠ","ÓŚ"=>"Ó§","Ó¤"=>"ÓĽ","Ó˘"=>"ÓŁ","Ó "=>"ÓĄ","Ó"=>"Ó","Ó"=>"Ó",
- "Ó"=>"Ó","Ó"=>"Ó","Ó"=>"Ó","Ó"=>"Ó","Ó"=>"Ó","Ó"=>"Ó","Ó"=>"Ó","Ó"=>"Ó","Ó"=>"Ó","Ó"=>"Ó",
- "Ó
"=>"Ó","Ó"=>"Ó","Ó"=>"Ó","Ňž"=>"Ňż","Ňź"=>"Ň˝","Ňş"=>"Ňť","Ҹ"=>"Ňš","Ňś"=>"ҡ","Ň´"=>"Ňľ","Ҳ"=>"Ňł",
- "Ň°"=>"Ňą","ŇŽ"=>"ŇŻ","ŇŹ"=>"Ň","ŇŞ"=>"ŇŤ","Ҩ"=>"ŇŠ","ŇŚ"=>"ҧ","Ҥ"=>"ŇĽ","Ң"=>"ŇŁ","Ň "=>"ŇĄ","Ň"=>"Ň",
- "Ň"=>"Ň","Ň"=>"Ň","Ň"=>"Ň","Ň"=>"Ň","Ň"=>"Ň","Ň"=>"Ň","Ň"=>"Ň","Ň"=>"Ň","Ň"=>"Ň","Ň"=>"Ň",
- "Ň"=>"Ň","Ńž"=>"Ńż","Ńź"=>"Ń˝","Ńş"=>"Ńť","Ѹ"=>"Ńš","Ńś"=>"ѡ","Ń´"=>"Ńľ","Ѳ"=>"Ńł","Ń°"=>"Ńą","ŃŽ"=>"ŃŻ",
- "ŃŹ"=>"Ń","ŃŞ"=>"ŃŤ","Ѩ"=>"ŃŠ","ŃŚ"=>"ѧ","Ѥ"=>"ŃĽ","Ѣ"=>"ŃŁ","Ń "=>"ŃĄ","Đ"=>"Ń","Đ"=>"Ń","Đ"=>"Ń",
- "Đ"=>"Ń","Đ"=>"Ń","Đ"=>"Ń","Đ"=>"Ń","Đ"=>"Ń","Đ"=>"Ń","Đ"=>"Ń","Đ
"=>"Ń","Đ"=>"Ń","Đ"=>"Ń",
- "Đ"=>"Ń","Đ"=>"Ń","Đ"=>"Ń","ĐŻ"=>"Ń","ĐŽ"=>"Ń","Đ"=>"Ń","ĐŹ"=>"Ń","ĐŤ"=>"Ń","ĐŞ"=>"Ń","ĐŠ"=>"Ń",
- "Ш"=>"Ń","Ч"=>"Ń","ĐŚ"=>"Ń","ĐĽ"=>"Ń
","Ф"=>"Ń","ĐŁ"=>"Ń","Т"=>"Ń","ĐĄ"=>"Ń","Đ "=>"Ń","Đ"=>"Đż",
- "Đ"=>"Đž","Đ"=>"Đ˝","Đ"=>"Đź","Đ"=>"Đť","Đ"=>"Đş","Đ"=>"Đš","Đ"=>"и","Đ"=>"С","Đ"=>"Đś","Đ"=>"Đľ",
- "Đ"=>"Đ´","Đ"=>"Đł","Đ"=>"в","Đ"=>"Đą","Đ"=>"Đ°","Î"=>"Ďľ","ÎŁ"=>"ϲ","ÎĄ"=>"Ďą","Î"=>"Ď°","ĎŽ"=>"ĎŻ",
- "ĎŹ"=>"Ď","ĎŞ"=>"ĎŤ","Ϩ"=>"ĎŠ","ĎŚ"=>"ϧ","Ϥ"=>"ĎĽ","Ϣ"=>"ĎŁ","Ď "=>"ĎĄ","Ď"=>"Ď","Ď"=>"Ď","Ď"=>"Ď",
- "Ď"=>"Ď","Î "=>"Ď","ÎŚ"=>"Ď","Î"=>"Ď","Î"=>"Ď","Î"=>"Ď","Î"=>"Ď","Î"=>"Ď","ÎŤ"=>"Ď","ÎŞ"=>"Ď",
- "Ί"=>"Ď","Ψ"=>"Ď","Χ"=>"Ď","ÎŚ"=>"Ď","ÎĽ"=>"Ď
","Τ"=>"Ď","ÎŁ"=>"Ď","ÎŁ"=>"Ď","ÎĄ"=>"Ď","Î "=>"Ď",
- "Î"=>"Îż","Î"=>"Ξ","Î"=>"ν","Î"=>"Îź","Î"=>"Îť","Î"=>"Îş","Î"=>"Κ","Î"=>"θ","Î"=>"Ρ","Î"=>"Îś",
- "Î"=>"Îľ","Î"=>"δ","Î"=>"Îł","Î"=>"β","Î"=>"Îą","Î"=>"ÎŻ","Î"=>"ÎŽ","Î"=>"Î","Î"=>"ÎŹ","ơ"=>"Ę",
- "Ʋ"=>"Ę","Ćą"=>"Ę","ĆŽ"=>"Ę","ĆŠ"=>"Ę","ĆŚ"=>"Ę","Ć"=>"Éľ","Ć"=>"ɲ","Ć"=>"ÉŻ","Ć"=>"ÉŠ","Ć"=>"ɨ",
- "Ć"=>"ÉŁ","Ć"=>"É","Ć"=>"É","Ć"=>"É","Ć"=>"É","Ć"=>"É","Ć"=>"É","Ȳ"=>"Čł","Č°"=>"Čą","ČŽ"=>"ČŻ",
- "ČŹ"=>"Č","ČŞ"=>"ČŤ","Ȩ"=>"ČŠ","ČŚ"=>"ȧ","Ȥ"=>"ČĽ","Ȣ"=>"ČŁ","Č"=>"Č","Č"=>"Č","Č"=>"Č","Č"=>"Č",
- "Č"=>"Č","Č"=>"Č","Č"=>"Č","Č"=>"Č","Č"=>"Č","Č"=>"Č","Č"=>"Č","Č"=>"Č","Č"=>"Č","Č"=>"Č
",
- "Č"=>"Č","Č"=>"Č","Çž"=>"Çż","Çź"=>"Ç˝","Çş"=>"Çť","Ǹ"=>"Çš","Ç´"=>"Çľ","Dz"=>"Çł","ÇŽ"=>"ÇŻ","ÇŹ"=>"Ç",
- "ÇŞ"=>"ÇŤ","Ǩ"=>"ÇŠ","ÇŚ"=>"ǧ","Ǥ"=>"ÇĽ","Ǣ"=>"ÇŁ","Ç "=>"ÇĄ","Ç"=>"Ç","Ć"=>"Ç","Ç"=>"Ç","Ç"=>"Ç",
- "Ç"=>"Ç","Ç"=>"Ç","Ç"=>"Ç","Ç"=>"Ç","Ç"=>"Ç","Ç"=>"Ç","Ç"=>"Ç","Ç"=>"Ç","Ç
"=>"Ç","ǡ"=>"Ćż",
- "Ćź"=>"Ć˝","Ƹ"=>"Ćš","Ćľ"=>"Ćś","Ćł"=>"Ć´","ĆŻ"=>"Ć°","ĆŹ"=>"Ć","Ƨ"=>"ƨ","Ƥ"=>"ĆĽ","Ƣ"=>"ĆŁ","Ć "=>"ĆĄ",
- "Č "=>"Ć","Ć"=>"Ć","Çś"=>"Ć","Ć"=>"Ć","Ć"=>"Ć","Ć"=>"Ć","Ć"=>"Ć
","Ć"=>"Ć","S"=>"Ĺż","Ĺ˝"=>"Ĺž",
- "Ĺť"=>"Ĺź","Ĺš"=>"Ĺş","Ĺś"=>"š","Ĺ´"=>"Ĺľ","Ų"=>"Ĺł","Ĺ°"=>"Ĺą","ĹŽ"=>"ĹŻ","ĹŹ"=>"Ĺ","ĹŞ"=>"ĹŤ","Ũ"=>"ĹŠ",
- "ĹŚ"=>"ŧ","Ť"=>"ĹĽ","Ţ"=>"ĹŁ","Ĺ "=>"ĹĄ","Ĺ"=>"Ĺ","Ĺ"=>"Ĺ","Ĺ"=>"Ĺ","Ĺ"=>"Ĺ","Ĺ"=>"Ĺ","Ĺ"=>"Ĺ",
- "Ĺ"=>"Ĺ","Ĺ"=>"Ĺ","Ĺ"=>"Ĺ","Ĺ"=>"Ĺ","Ĺ"=>"Ĺ","Ĺ"=>"Ĺ","Ĺ
"=>"Ĺ","Ĺ"=>"Ĺ","Ĺ"=>"Ĺ","Äż"=>"Ĺ",
- "Ä˝"=>"Äž","Äť"=>"Äź","Äš"=>"Äş","Äś"=>"ġ","Ä´"=>"Äľ","IJ"=>"Äł","I"=>"Äą","ÄŽ"=>"ÄŻ","ÄŹ"=>"Ä","ÄŞ"=>"ÄŤ",
- "Ĩ"=>"ÄŠ","ÄŚ"=>"ħ","Ĥ"=>"ÄĽ","Ģ"=>"ÄŁ","Ä "=>"ÄĄ","Ä"=>"Ä","Ä"=>"Ä","Ä"=>"Ä","Ä"=>"Ä","Ä"=>"Ä",
- "Ä"=>"Ä","Ä"=>"Ä","Ä"=>"Ä","Ä"=>"Ä","Ä"=>"Ä","Ä"=>"Ä","Ä"=>"Ä","Ä"=>"Ä","Ä"=>"Ä
","Ä"=>"Ä",
- "Ä"=>"Ä","Ÿ"=>"Ăż","Ă"=>"Ăž","Ă"=>"Ă˝","Ă"=>"Ăź","Ă"=>"Ăť","Ă"=>"Ăş","Ă"=>"Ăš","Ă"=>"ø","Ă"=>"Ăś",
- "Ă"=>"Ăľ","Ă"=>"Ă´","Ă"=>"Ăł","Ă"=>"ò","Ă"=>"Ăą","Ă"=>"Ă°","Ă"=>"ĂŻ","Ă"=>"ĂŽ","Ă"=>"Ă","Ă"=>"ĂŹ",
- "Ă"=>"ĂŤ","Ă"=>"ĂŞ","Ă"=>"ĂŠ","Ă"=>"è","Ă"=>"ç","Ă"=>"ĂŚ","Ă
"=>"ĂĽ","Ă"=>"ä","Ă"=>"ĂŁ","Ă"=>"â",
- "Ă"=>"ĂĄ","Ă"=>"Ă ","Î"=>"Âľ","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(
- 'Ă ' => 'a', 'Ă´' => 'o', 'Ä' => 'd', 'á¸' => 'f', 'ĂŤ' => 'e', 'ĹĄ' => 's', 'ĆĄ' => 'o',
- 'Ă' => 'ss', 'Ä' => 'a', 'Ĺ' => 'r', 'Č' => 't', 'Ĺ' => 'n', 'Ä' => 'a', 'ġ' => 'k',
- 'Ĺ' => 's', 'áťł' => 'y', 'Ĺ' => 'n', 'Äş' => 'l', 'ħ' => 'h', 'áš' => 'p', 'Ăł' => 'o',
- 'Ăş' => 'u', 'Ä' => 'e', 'ĂŠ' => 'e', 'ç' => 'c', 'áş' => 'w', 'Ä' => 'c', 'Ăľ' => 'o',
- 'ᚥ' => 's', 'ø' => 'o', 'ÄŁ' => 'g', 'ŧ' => 't', 'Č' => 's', 'Ä' => 'e', 'Ä' => 'c',
- 'Ĺ' => 's', 'ĂŽ' => 'i', 'Ĺą' => 'u', 'Ä' => 'c', 'Ä' => 'e', 'Ĺľ' => 'w', 'ᚍ' => 't',
- 'ĹŤ' => 'u', 'Ä' => 'c', 'Ăś' => 'oe', 'è' => 'e', 'š' => 'y', 'Ä
' => 'a', 'Ĺ' => 'l',
- 'Ĺł' => 'u', 'ĹŻ' => 'u', 'Ĺ' => 's', 'Ä' => 'g', 'Äź' => 'l', 'Ć' => 'f', 'Ĺž' => 'z',
- 'áş' => 'w', 'á¸' => 'b', 'ĂĽ' => 'a', 'ĂŹ' => 'i', 'ĂŻ' => 'i', 'á¸' => 'd', 'ĹĽ' => 't',
- 'Ĺ' => 'r', 'ä' => 'ae', 'Ă' => 'i', 'Ĺ' => 'r', 'ĂŞ' => 'e', 'Ăź' => 'ue', 'ò' => 'o',
- 'Ä' => 'e', 'Ăą' => 'n', 'Ĺ' => 'n', 'ÄĽ' => 'h', 'Ä' => 'g', 'Ä' => 'd', 'Äľ' => 'j',
- 'Ăż' => 'y', 'ĹŠ' => 'u', 'Ĺ' => 'u', 'Ć°' => 'u', 'ĹŁ' => 't', 'Ă˝' => 'y', 'Ĺ' => 'o',
- 'â' => 'a', 'Äž' => 'l', 'áş
' => 'w', 'Ĺź' => 'z', 'ÄŤ' => 'i', 'ĂŁ' => 'a', 'ÄĄ' => 'g',
- 'áš' => 'm', 'Ĺ' => 'o', 'ÄŠ' => 'i', 'Ăš' => 'u', 'ÄŻ' => 'i', 'Ĺş' => 'z', 'ĂĄ' => 'a',
- 'Ăť' => 'u', 'Ăž' => 'th', 'Ă°' => 'dh', 'ĂŚ' => 'ae', 'Âľ' => '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(
- 'Ă' => 'A', 'Ă' => 'O', 'Ä' => 'D', 'á¸' => 'F', 'Ă' => 'E', 'Ĺ ' => 'S', 'Ć ' => 'O',
- 'Ä' => 'A', 'Ĺ' => 'R', 'Č' => 'T', 'Ĺ' => 'N', 'Ä' => 'A', 'Äś' => 'K',
- 'Ĺ' => 'S', 'ᝲ' => 'Y', 'Ĺ
' => 'N', 'Äš' => 'L', 'ÄŚ' => 'H', 'áš' => 'P', 'Ă' => 'O',
- 'Ă' => 'U', 'Ä' => 'E', 'Ă' => 'E', 'Ă' => 'C', 'áş' => 'W', 'Ä' => 'C', 'Ă' => 'O',
- 'áš ' => 'S', 'Ă' => 'O', 'Ģ' => 'G', 'ĹŚ' => 'T', 'Č' => 'S', 'Ä' => 'E', 'Ä' => 'C',
- 'Ĺ' => 'S', 'Ă' => 'I', 'Ĺ°' => 'U', 'Ä' => 'C', 'Ä' => 'E', 'Ĺ´' => 'W', 'ᚪ' => 'T',
- 'ĹŞ' => 'U', 'Ä' => 'C', 'Ă' => 'Oe', 'Ă' => 'E', 'Ĺś' => 'Y', 'Ä' => 'A', 'Ĺ' => 'L',
- 'Ų' => 'U', 'ĹŽ' => 'U', 'Ĺ' => 'S', 'Ä' => 'G', 'Äť' => 'L', 'Ć' => 'F', 'Ĺ˝' => 'Z',
- 'áş' => 'W', 'á¸' => 'B', 'Ă
' => 'A', 'Ă' => 'I', 'Ă' => 'I', 'á¸' => 'D', 'Ť' => 'T',
- 'Ĺ' => 'R', 'Ă' => 'Ae', 'Ă' => 'I', 'Ĺ' => 'R', 'Ă' => 'E', 'Ă' => 'Ue', 'Ă' => 'O',
- 'Ä' => 'E', 'Ă' => 'N', 'Ĺ' => 'N', 'Ĥ' => 'H', 'Ä' => 'G', 'Ä' => 'D', 'Ä´' => 'J',
- 'Ÿ' => 'Y', 'Ũ' => 'U', 'ĹŹ' => 'U', 'ĆŻ' => 'U', 'Ţ' => 'T', 'Ă' => 'Y', 'Ĺ' => 'O',
- 'Ă' => 'A', 'Ä˝' => 'L', 'áş' => 'W', 'Ĺť' => 'Z', 'ÄŞ' => 'I', 'Ă' => 'A', 'Ä ' => 'G',
- 'áš' => 'M', 'Ĺ' => 'O', 'Ĩ' => 'I', 'Ă' => 'U', 'ÄŽ' => 'I', 'Ĺš' => 'Z', 'Ă' => 'A',
- 'Ă' => 'U', 'Ă' => 'Th', 'Ă' => 'Dh', 'Ă' => '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)) $UTF8_SPECIAL_CHARS2 =
- "\x1A".' !"#$%&\'()+,/;<=>?@[\]^`{|}~ÂÂÂÂÂÂ
ÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂďż˝'.
- '� ¥¢£¤¼Œ§¨ŠªÂŽ¯°¹²³´¾œ¡¸šºŸ½�'.
- '�¿ĂáËËËËËËËĚĚĚĚĚŁÎÎ
ÎĎÖ°ÖąÖ˛ÖłÖ´ÖľÖśÖˇÖ¸ÖšÖťÖźÖ˝ÖžÖżďż˝'.
- 'ďż˝×××׳״ŘŘŘŮŮŮŮŮŮŮŮŮ٪฿âââââââââââââďż˝'.
- '��â âĄâ˘âŚâ°â˛âłâšâşââ§âŞâŤâŹâââ˘âŚâľâââââââľ'.
- 'âââââââââ
âââââââââââââââ â§â¨ďż˝'.
- 'ďż˝âŞâŤâ´âźâ
ââ âĄâ¤âĽââââââââĽâ
ââ âĄâŠâŞâŠâďż˝'.
- '��ââââââ¤âŹâ´âźâââââââââââââââââ '.
- 'âĄâ˘âŁâ¤âĽâŚâ§â¨âŠâŞâŤâŹâââââââââ â˛âźâââďż˝'.
- 'ďż˝â
ââââ âŁâĽâŚââââââââââââââââââďż˝'.
- '��ââââââââââ âĄâ˘âŁâ¤âĽâŚâ§âŠâŞâŤâŹââŽâŻâ°âą'.
- 'â˛âłâ´âľâśâˇâ¸âšâşâťâźâ˝âžâżââââââ
ââââââďż˝'.
- 'ďż˝âââââââââââââĄâ˘âŁâ¤âĽâŚâ§âżââââââďż˝'.
- '��âââââ âĄâ˘âŁâ¤âĽâŚâ§â¨âŠâŞâŤâŹââŽâŻâąâ˛âłâ´âľâś'.
- 'âˇâ¸âšâşâťâźâ˝âž'.
- 'ăăăăăăăăăăăăăăăăăăăăăăăăś'.
- 'ďďďďŁďŁďŁďŁďŁďŁďŁďŁďŁďŁ �'.
- '�ďŁďŁŽďŁŻďŁ°ďŁąďŁ˛ďŁłďŁ´ďŁľďŁśďŁˇďŁ¸ďŁšďŁşďŁťďŁźďŁ˝ďŁžďšźďš˝'.
- 'ďźďźďźďźďź
ďźďźďźďźďźďźďźďźďźďźďźďźďźďźďźďźďź ď˝ď˝ď˝ď˝ď˝'.
- 'ď˝ď˝ ď˝Ąď˝˘ď˝Łď˝¤ď˝Ľďż ďżĄďż˘ďżŁďż¤ďżĽďżŚďż¨ďżŠďżŞďżŤďżŹďżďżŽ'.
- 'đźđ˝đžđżđđđđđđ
đđđđđđđđđđđđđđđđđđđđđđ'.
- ' ââŻâ ďťż';
- /**
- * 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>
- */
- global $UTF8_ROMANIZATION;
- if(empty($UTF8_ROMANIZATION)) $UTF8_ROMANIZATION = array(
- // scandinavian - differs from what we do in deaccent
- 'ĂĽ'=>'a','Ă
'=>'A','ä'=>'a','Ă'=>'A','Ăś'=>'o','Ă'=>'O',
- //russian cyrillic
- 'Đ°'=>'a','Đ'=>'A','Đą'=>'b','Đ'=>'B','в'=>'v','Đ'=>'V','Đł'=>'g','Đ'=>'G',
- 'Đ´'=>'d','Đ'=>'D','Đľ'=>'e','Đ'=>'E','Ń'=>'jo','Đ'=>'Jo','Đś'=>'zh','Đ'=>'Zh',
- 'С'=>'z','Đ'=>'Z','и'=>'i','Đ'=>'I','Đš'=>'j','Đ'=>'J','Đş'=>'k','Đ'=>'K',
- 'Đť'=>'l','Đ'=>'L','Đź'=>'m','Đ'=>'M','Đ˝'=>'n','Đ'=>'N','Đž'=>'o','Đ'=>'O',
- 'Đż'=>'p','Đ'=>'P','Ń'=>'r','Đ '=>'R','Ń'=>'s','ĐĄ'=>'S','Ń'=>'t','Т'=>'T',
- 'Ń'=>'u','ĐŁ'=>'U','Ń'=>'f','Ф'=>'F','Ń
'=>'x','ĐĽ'=>'X','Ń'=>'c','ĐŚ'=>'C',
- 'Ń'=>'ch','Ч'=>'Ch','Ń'=>'sh','Ш'=>'Sh','Ń'=>'sch','ĐŠ'=>'Sch','Ń'=>'',
- 'ĐŞ'=>'','Ń'=>'y','ĐŤ'=>'Y','Ń'=>'','ĐŹ'=>'','Ń'=>'eh','Đ'=>'Eh','Ń'=>'ju',
- 'ĐŽ'=>'Ju','Ń'=>'ja','ĐŻ'=>'Ja',
- // Ukrainian cyrillic
- 'Ň'=>'Gh','Ň'=>'gh','Đ'=>'Je','Ń'=>'je','Đ'=>'I','Ń'=>'i','Đ'=>'Ji','Ń'=>'ji',
- // Georgian
- 'á'=>'a','á'=>'b','á'=>'g','á'=>'d','á'=>'e','á'=>'v','á'=>'z','á'=>'th',
- 'á'=>'i','á'=>'p','á'=>'l','á'=>'m','á'=>'n','á'=>'o','á'=>'p','á'=>'zh',
- 'á '=>'r','áĄ'=>'s','á˘'=>'t','áŁ'=>'u','á¤'=>'ph','áĽ'=>'kh','áŚ'=>'gh','á§'=>'q',
- 'á¨'=>'sh','áŠ'=>'ch','áŞ'=>'c','áŤ'=>'dh','áŹ'=>'w','á'=>'j','áŽ'=>'x','áŻ'=>'jh',
- 'á°'=>'xh',
- //Sanskrit
- 'ŕ¤
'=>'a','ŕ¤'=>'ah','ŕ¤'=>'i','ŕ¤'=>'ih','ŕ¤'=>'u','ŕ¤'=>'uh','ŕ¤'=>'ry',
- '༠'=>'ryh','ŕ¤'=>'ly','༥'=>'lyh','ŕ¤'=>'e','ŕ¤'=>'ay','ŕ¤'=>'o','ŕ¤'=>'aw',
- 'ŕ¤
ŕ¤'=>'amh','ŕ¤
ŕ¤'=>'aq','ŕ¤'=>'k','ŕ¤'=>'kh','ŕ¤'=>'g','ŕ¤'=>'gh','ŕ¤'=>'nh',
- 'ŕ¤'=>'c','ŕ¤'=>'ch','ŕ¤'=>'j','ŕ¤'=>'jh','ŕ¤'=>'ny','ŕ¤'=>'tq','ठ'=>'tqh',
- 'थ'=>'dq','ढ'=>'dqh','ण'=>'nq','त'=>'t','़'=>'th','ऌ'=>'d','ध'=>'dh',
- 'न'=>'n','प'=>'p','ऍ'=>'ph','ए'=>'b','ŕ¤'=>'bh','ऎ'=>'m','य'=>'z','र'=>'r',
- 'ल'=>'l','ा'=>'v','ज'=>'sh','ड'=>'sqh','स'=>'s','च'=>'x',
- //Hebrew
- '×'=>'a', '×'=>'b','×'=>'g','×'=>'d','×'=>'h','×'=>'v','×'=>'z','×'=>'kh','×'=>'th',
- '×'=>'y','×'=>'h','×'=>'k','×'=>'l','×'=>'m','×'=>'m','×'=>'n','× '=>'n',
- 'ץ'=>'s','ע'=>'ah','ף'=>'f','פ'=>'p','׼'=>'c','׌'=>'c','ק'=>'q','ר'=>'r',
- '׊'=>'sh','ת'=>'t',
- //Arabic
- 'ا'=>'a','ب'=>'b','ŘŞ'=>'t','ŘŤ'=>'th','ŘŹ'=>'g','Ř'=>'xh','ŘŽ'=>'x','ŘŻ'=>'d',
- 'ذ'=>'dh','ع'=>'r','ز'=>'z','س'=>'s','ش'=>'sh','ؾ'=>'s\'','؜'=>'d\'',
- 'ء'=>'t\'','ظ'=>'z\'','Řš'=>'y','Řş'=>'gh','Ů'=>'f','Ů'=>'q','Ů'=>'k',
- 'Ů'=>'l','Ů
'=>'m','Ů'=>'n','Ů'=>'x\'','Ů'=>'u','Ů'=>'i',
- // Japanese characters (last update: 2008-05-09)
- // Japanese hiragana
- // 3 character syllables, 㣠doubles the consonant after
- 'ăŁăĄă'=>'ccha','ăŁăĄă'=>'cche','ăŁăĄă'=>'ccho','ăŁăĄă
'=>'cchu',
- 'ăŁăłă'=>'bbya','ăŁăłă'=>'bbye','ăŁăłă'=>'bbyi','ăŁăłă'=>'bbyo','ăŁăłă
'=>'bbyu',
- 'ăŁă´ă'=>'ppya','ăŁă´ă'=>'ppye','ăŁă´ă'=>'ppyi','ăŁă´ă'=>'ppyo','ăŁă´ă
'=>'ppyu',
- 'ăŁăĄă'=>'ccha','ăŁăĄă'=>'cche','ăŁăĄ'=>'cchi','ăŁăĄă'=>'ccho','ăŁăĄă
'=>'cchu',
- // 'ăŁă˛ă'=>'hya','ăŁă˛ă'=>'hye','ăŁă˛ă'=>'hyi','ăŁă˛ă'=>'hyo','ăŁă˛ă
'=>'hyu',
- 'ăŁăă'=>'kkya','ăŁăă'=>'kkye','ăŁăă'=>'kkyi','ăŁăă'=>'kkyo','ăŁăă
'=>'kkyu',
- 'ăŁăă'=>'ggya','ăŁăă'=>'ggye','ăŁăă'=>'ggyi','ăŁăă'=>'ggyo','ăŁăă
'=>'ggyu',
- 'ăŁăżă'=>'mmya','ăŁăżă'=>'mmye','ăŁăżă'=>'mmyi','ăŁăżă'=>'mmyo','ăŁăżă
'=>'mmyu',
- 'ăŁăŤă'=>'nnya','ăŁăŤă'=>'nnye','ăŁăŤă'=>'nnyi','ăŁăŤă'=>'nnyo','ăŁăŤă
'=>'nnyu',
- 'ăŁăă'=>'rrya','ăŁăă'=>'rrye','ăŁăă'=>'rryi','ăŁăă'=>'rryo','ăŁăă
'=>'rryu',
- 'ăŁăă'=>'ssha','ăŁăă'=>'sshe','ăŁă'=>'sshi','ăŁăă'=>'ssho','ăŁăă
'=>'sshu',
- // seperate hiragana 'n' ('n' + 'i' != 'ni', normally we would write "kon'nichi wa" but the apostrophe would be converted to _ anyway)
- 'ăă'=>'n_a','ăă'=>'n_e','ăă'=>'n_i','ăă'=>'n_o','ăă'=>'n_u',
- 'ăă'=>'n_ya','ăă'=>'n_yo','ăă'=>'n_yu',
- // 2 character syllables - normal
- 'ăľă'=>'fa','ăľă'=>'fe','ăľă'=>'fi','ăľă'=>'fo',
- 'ăĄă'=>'cha','ăĄă'=>'che','ăĄ'=>'chi','ăĄă'=>'cho','ăĄă
'=>'chu',
- 'ă˛ă'=>'hya','ă˛ă'=>'hye','ă˛ă'=>'hyi','ă˛ă'=>'hyo','ă˛ă
'=>'hyu',
- 'ăłă'=>'bya','ăłă'=>'bye','ăłă'=>'byi','ăłă'=>'byo','ăłă
'=>'byu',
- 'ă´ă'=>'pya','ă´ă'=>'pye','ă´ă'=>'pyi','ă´ă'=>'pyo','ă´ă
'=>'pyu',
- 'ăă'=>'kya','ăă'=>'kye','ăă'=>'kyi','ăă'=>'kyo','ăă
'=>'kyu',
- 'ăă'=>'gya','ăă'=>'gye','ăă'=>'gyi','ăă'=>'gyo','ăă
'=>'gyu',
- 'ăżă'=>'mya','ăżă'=>'mye','ăżă'=>'myi','ăżă'=>'myo','ăżă
'=>'myu',
- 'ăŤă'=>'nya','ăŤă'=>'nye','ăŤă'=>'nyi','ăŤă'=>'nyo','ăŤă
'=>'nyu',
- 'ăă'=>'rya','ăă'=>'rye','ăă'=>'ryi','ăă'=>'ryo','ăă
'=>'ryu',
- 'ăă'=>'sha','ăă'=>'she','ă'=>'shi','ăă'=>'sho','ăă
'=>'shu',
- 'ăă'=>'ja','ăă'=>'je','ăă'=>'jo','ăă
'=>'ju',
- 'ăă'=>'we','ăă'=>'wi',
- 'ăă'=>'ye',
- // 2 character syllables, 㣠doubles the consonant after
- 'ăŁă°'=>'bba','ăŁăš'=>'bbe','ăŁăł'=>'bbi','ăŁăź'=>'bbo','ăŁăś'=>'bbu',
- 'ăŁăą'=>'ppa','ăŁăş'=>'ppe','ăŁă´'=>'ppi','ăŁă˝'=>'ppo','ăŁăˇ'=>'ppu',
- 'ăŁă'=>'tta','ăŁăŚ'=>'tte','ăŁăĄ'=>'cchi','ăŁă¨'=>'tto','ăŁă¤'=>'ttsu',
- 'ăŁă '=>'dda','ăŁă§'=>'dde','ăŁă˘'=>'ddi','ăŁăŠ'=>'ddo','ăŁăĽ'=>'ddu',
- 'ăŁă'=>'gga','ăŁă'=>'gge','ăŁă'=>'ggi','ăŁă'=>'ggo','ăŁă'=>'ggu',
- 'ăŁă'=>'kka','ăŁă'=>'kke','ăŁă'=>'kki','ăŁă'=>'kko','ăŁă'=>'kku',
- 'ăŁăž'=>'mma','ăŁă'=>'mme','ăŁăż'=>'mmi','ăŁă'=>'mmo','ăŁă'=>'mmu',
- 'ăŁăŞ'=>'nna','ăŁă'=>'nne','ăŁăŤ'=>'nni','ăŁăŽ'=>'nno','ăŁăŹ'=>'nnu',
- 'ăŁă'=>'rra','ăŁă'=>'rre','ăŁă'=>'rri','ăŁă'=>'rro','ăŁă'=>'rru',
- 'ăŁă'=>'ssa','ăŁă'=>'sse','ăŁă'=>'sshi','ăŁă'=>'sso','ăŁă'=>'ssu',
- 'ăŁă'=>'zza','ăŁă'=>'zze','ăŁă'=>'jji','ăŁă'=>'zzo','ăŁă'=>'zzu',
- // 1 character syllabels
- 'ă'=>'a','ă'=>'e','ă'=>'i','ă'=>'o','ă'=>'u','ă'=>'n',
- 'ăŻ'=>'ha','ă¸'=>'he','ă˛'=>'hi','ăť'=>'ho','ăľ'=>'fu',
- 'ă°'=>'ba','ăš'=>'be','ăł'=>'bi','ăź'=>'bo','ăś'=>'bu',
- 'ăą'=>'pa','ăş'=>'pe','ă´'=>'pi','ă˝'=>'po','ăˇ'=>'pu',
- 'ă'=>'ta','ăŚ'=>'te','ăĄ'=>'chi','ă¨'=>'to','ă¤'=>'tsu',
- 'ă '=>'da','ă§'=>'de','ă˘'=>'di','ăŠ'=>'do','ăĽ'=>'du',
- 'ă'=>'ga','ă'=>'ge','ă'=>'gi','ă'=>'go','ă'=>'gu',
- 'ă'=>'ka','ă'=>'ke','ă'=>'ki','ă'=>'ko','ă'=>'ku',
- 'ăž'=>'ma','ă'=>'me','ăż'=>'mi','ă'=>'mo','ă'=>'mu',
- 'ăŞ'=>'na','ă'=>'ne','ăŤ'=>'ni','ăŽ'=>'no','ăŹ'=>'nu',
- 'ă'=>'ra','ă'=>'re','ă'=>'ri','ă'=>'ro','ă'=>'ru',
- 'ă'=>'sa','ă'=>'se','ă'=>'shi','ă'=>'so','ă'=>'su',
- 'ă'=>'wa','ă'=>'wo',
- 'ă'=>'za','ă'=>'ze','ă'=>'ji','ă'=>'zo','ă'=>'zu',
- 'ă'=>'ya','ă'=>'yo','ă'=>'yu',
- // old characters
- 'ă'=>'we','ă'=>'wi',
- // convert what's left (probably only kicks in when something's missing above)
- // 'ă'=>'a','ă'=>'e','ă'=>'i','ă'=>'o','ă
'=>'u',
- // 'ă'=>'ya','ă'=>'yo','ă
'=>'yu',
- // never seen one of those (disabled for the moment)
- // 'ă´ă'=>'va','ă´ă'=>'ve','ă´ă'=>'vi','ă´ă'=>'vo','ă´'=>'vu',
- // 'ă§ă'=>'dha','ă§ă'=>'dhe','ă§ă'=>'dhi','ă§ă'=>'dho','ă§ă
'=>'dhu',
- // 'ăŠă'=>'dwa','ăŠă'=>'dwe','ăŠă'=>'dwi','ăŠă'=>'dwo','ăŠă
'=>'dwu',
- // 'ă˘ă'=>'dya','ă˘ă'=>'dye','ă˘ă'=>'dyi','ă˘ă'=>'dyo','ă˘ă
'=>'dyu',
- // 'ăľă'=>'fwa','ăľă'=>'fwe','ăľă'=>'fwi','ăľă'=>'fwo','ăľă
'=>'fwu',
- // 'ăľă'=>'fya','ăľă'=>'fye','ăľă'=>'fyi','ăľă'=>'fyo','ăľă
'=>'fyu',
- // 'ăă'=>'swa','ăă'=>'swe','ăă'=>'swi','ăă'=>'swo','ăă
'=>'swu',
- // 'ăŚă'=>'tha','ăŚă'=>'the','ăŚă'=>'thi','ăŚă'=>'tho','ăŚă
'=>'thu',
- // 'ă¤ă'=>'tsa','ă¤ă'=>'tse','ă¤ă'=>'tsi','ă¤ă'=>'tso','ă¤'=>'tsu',
- // 'ă¨ă'=>'twa','ă¨ă'=>'twe','ă¨ă'=>'twi','ă¨ă'=>'two','ă¨ă
'=>'twu',
- // 'ă´ă'=>'vya','ă´ă'=>'vye','ă´ă'=>'vyi','ă´ă'=>'vyo','ă´ă
'=>'vyu',
- // 'ăă'=>'wha','ăă'=>'whe','ăă'=>'whi','ăă'=>'who','ăă
'=>'whu',
- // 'ăă'=>'zha','ăă'=>'zhe','ăă'=>'zhi','ăă'=>'zho','ăă
'=>'zhu',
- // 'ăă'=>'zya','ăă'=>'zye','ăă'=>'zyi','ăă'=>'zyo','ăă
'=>'zyu',
- // 'spare' characters from other romanization systems
- // 'ă '=>'da','ă§'=>'de','ă˘'=>'di','ăŠ'=>'do','ăĽ'=>'du',
- // 'ă'=>'la','ă'=>'le','ă'=>'li','ă'=>'lo','ă'=>'lu',
- // 'ă'=>'sa','ă'=>'se','ă'=>'si','ă'=>'so','ă'=>'su',
- // 'ăĄă'=>'cya','ăĄă'=>'cye','ăĄă'=>'cyi','ăĄă'=>'cyo','ăĄă
'=>'cyu',
- //'ăă'=>'jya','ăă'=>'jye','ăă'=>'jyi','ăă'=>'jyo','ăă
'=>'jyu',
- //'ăă'=>'lya','ăă'=>'lye','ăă'=>'lyi','ăă'=>'lyo','ăă
'=>'lyu',
- //'ăă'=>'sya','ăă'=>'sye','ăă'=>'syi','ăă'=>'syo','ăă
'=>'syu',
- //'ăĄă'=>'tya','ăĄă'=>'tye','ăĄă'=>'tyi','ăĄă'=>'tyo','ăĄă
'=>'tyu',
- //'ă'=>'ci',,ă'=>'yi','ă˘'=>'dzi',
- //'ăŁăă'=>'jja','ăŁăă'=>'jje','ăŁă'=>'jji','ăŁăă'=>'jjo','ăŁăă
'=>'jju',
- // Japanese katakana
- // 4 character syllables: ă doubles the consonant after, ăź doubles the vowel before (usualy written with macron, but we don't want that in our URLs)
- 'ăăăŁăź'=>'bbyaa','ăăă§ăź'=>'bbyee','ăăăŁăź'=>'bbyii','ăăă§ăź'=>'bbyoo','ăăăĽăź'=>'bbyuu',
- 'ăăăŁăź'=>'ppyaa','ăăă§ăź'=>'ppyee','ăăăŁăź'=>'ppyii','ăăă§ăź'=>'ppyoo','ăăăĽăź'=>'ppyuu',
- 'ăăăŁăź'=>'kkyaa','ăăă§ăź'=>'kkyee','ăăăŁăź'=>'kkyii','ăăă§ăź'=>'kkyoo','ăăăĽăź'=>'kkyuu',
- 'ăăŽăŁăź'=>'ggyaa','ăăŽă§ăź'=>'ggyee','ăăŽăŁăź'=>'ggyii','ăăŽă§ăź'=>'ggyoo','ăăŽăĽăź'=>'ggyuu',
- 'ăăăŁăź'=>'mmyaa','ăăă§ăź'=>'mmyee','ăăăŁăź'=>'mmyii','ăăă§ăź'=>'mmyoo','ăăăĽăź'=>'mmyuu',
- 'ăăăŁăź'=>'nnyaa','ăăă§ăź'=>'nnyee','ăăăŁăź'=>'nnyii','ăăă§ăź'=>'nnyoo','ăăăĽăź'=>'nnyuu',
- 'ăăŞăŁăź'=>'rryaa','ăăŞă§ăź'=>'rryee','ăăŞăŁăź'=>'rryii','ăăŞă§ăź'=>'rryoo','ăăŞăĽăź'=>'rryuu',
- 'ăăˇăŁăź'=>'sshaa','ăăˇă§ăź'=>'sshee','ăăˇăź'=>'sshii','ăăˇă§ăź'=>'sshoo','ăăˇăĽăź'=>'sshuu',
- 'ăăăŁăź'=>'cchaa','ăăă§ăź'=>'cchee','ăăăź'=>'cchii','ăăă§ăź'=>'cchoo','ăăăĽăź'=>'cchuu',
- 'ăăăŁăź'=>'ttii',
- 'ăăăŁăź'=>'ddii',
- // 3 character syllables - doubled vowels
- 'ăăĄăź'=>'faa','ăă§ăź'=>'fee','ăăŁăź'=>'fii','ăăŠăź'=>'foo',
- 'ăăŁăź'=>'fyaa','ăă§ăź'=>'fyee','ăăŁăź'=>'fyii','ăă§ăź'=>'fyoo','ăăĽăź'=>'fyuu',
- 'ăăŁăź'=>'hyaa','ăă§ăź'=>'hyee','ăăŁăź'=>'hyii','ăă§ăź'=>'hyoo','ăăĽăź'=>'hyuu',
- 'ăăŁăź'=>'byaa','ăă§ăź'=>'byee','ăăŁăź'=>'byii','ăă§ăź'=>'byoo','ăăĽăź'=>'byuu',
- 'ăăŁăź'=>'pyaa','ăă§ăź'=>'pyee','ăăŁăź'=>'pyii','ăă§ăź'=>'pyoo','ăăĽăź'=>'pyuu',
- 'ăăŁăź'=>'kyaa','ăă§ăź'=>'kyee','ăăŁăź'=>'kyii','ăă§ăź'=>'kyoo','ăăĽăź'=>'kyuu',
- 'ăŽăŁăź'=>'gyaa','ăŽă§ăź'=>'gyee','ăŽăŁăź'=>'gyii','ăŽă§ăź'=>'gyoo','ăŽăĽăź'=>'gyuu',
- 'ăăŁăź'=>'myaa','ăă§ăź'=>'myee','ăăŁăź'=>'myii','ăă§ăź'=>'myoo','ăăĽăź'=>'myuu',
- 'ăăŁăź'=>'nyaa','ăă§ăź'=>'nyee','ăăŁăź'=>'nyii','ăă§ăź'=>'nyoo','ăăĽăź'=>'nyuu',
- 'ăŞăŁăź'=>'ryaa','ăŞă§ăź'=>'ryee','ăŞăŁăź'=>'ryii','ăŞă§ăź'=>'ryoo','ăŞăĽăź'=>'ryuu',
- 'ăˇăŁăź'=>'shaa','ăˇă§ăź'=>'shee','ăˇăź'=>'shii','ăˇă§ăź'=>'shoo','ăˇăĽăź'=>'shuu',
- 'ă¸ăŁăź'=>'jaa','ă¸ă§ăź'=>'jee','ă¸ăź'=>'jii','ă¸ă§ăź'=>'joo','ă¸ăĽăź'=>'juu',
- 'ăšăĄăź'=>'swaa','ăšă§ăź'=>'swee','ăšăŁăź'=>'swii','ăšăŠăź'=>'swoo','ăšăĽăź'=>'swuu',
- 'ăăĄăź'=>'daa','ăă§ăź'=>'dee','ăăŁăź'=>'dii','ăăŠăź'=>'doo','ăăĽăź'=>'duu',
- 'ăăŁăź'=>'chaa','ăă§ăź'=>'chee','ăăź'=>'chii','ăă§ăź'=>'choo','ăăĽăź'=>'chuu',
- 'ăăŁăź'=>'dyaa','ăă§ăź'=>'dyee','ăăŁăź'=>'dyii','ăă§ăź'=>'dyoo','ăăĽăź'=>'dyuu',
- 'ăăŁăź'=>'tsaa','ăă§ăź'=>'tsee','ăăŁăź'=>'tsii','ăă§ăź'=>'tsoo','ăăź'=>'tsuu',
- 'ăăĄăź'=>'twaa','ăă§ăź'=>'twee','ăăŁăź'=>'twii','ăăŠăź'=>'twoo','ăăĽăź'=>'twuu',
- 'ăăĄăź'=>'dwaa','ăă§ăź'=>'dwee','ăăŁăź'=>'dwii','ăăŠăź'=>'dwoo','ăăĽăź'=>'dwuu',
- 'ăŚăĄăź'=>'whaa','ăŚă§ăź'=>'whee','ăŚăŁăź'=>'whii','ăŚăŠăź'=>'whoo','ăŚăĽăź'=>'whuu',
- 'ă´ăŁăź'=>'vyaa','ă´ă§ăź'=>'vyee','ă´ăŁăź'=>'vyii','ă´ă§ăź'=>'vyoo','ă´ăĽăź'=>'vyuu',
- 'ă´ăĄăź'=>'vaa','ă´ă§ăź'=>'vee','ă´ăŁăź'=>'vii','ă´ăŠăź'=>'voo','ă´ăź'=>'vuu',
- 'ăŚă§ăź'=>'wee','ăŚăŁăź'=>'wii',
- 'ă¤ă§ăź'=>'yee',
- 'ăăŁăź'=>'tii',
- 'ăăŁăź'=>'dii',
- // 3 character syllables - doubled consonants
- 'ăăăŁ'=>'bbya','ăăă§'=>'bbye','ăăăŁ'=>'bbyi','ăăă§'=>'bbyo','ăăăĽ'=>'bbyu',
- 'ăăăŁ'=>'ppya','ăăă§'=>'ppye','ăăăŁ'=>'ppyi','ăăă§'=>'ppyo','ăăăĽ'=>'ppyu',
- 'ăăăŁ'=>'kkya','ăăă§'=>'kkye','ăăăŁ'=>'kkyi','ăăă§'=>'kkyo','ăăăĽ'=>'kkyu',
- 'ăăŽăŁ'=>'ggya','ăăŽă§'=>'ggye','ăăŽăŁ'=>'ggyi','ăăŽă§'=>'ggyo','ăăŽăĽ'=>'ggyu',
- 'ăăăŁ'=>'mmya','ăăă§'=>'mmye','ăăăŁ'=>'mmyi','ăăă§'=>'mmyo','ăăăĽ'=>'mmyu',
- 'ăăăŁ'=>'nnya','ăăă§'=>'nnye','ăăăŁ'=>'nnyi','ăăă§'=>'nnyo','ăăăĽ'=>'nnyu',
- 'ăăŞăŁ'=>'rrya','ăăŞă§'=>'rrye','ăăŞăŁ'=>'rryi','ăăŞă§'=>'rryo','ăăŞăĽ'=>'rryu',
- 'ăăˇăŁ'=>'ssha','ăăˇă§'=>'sshe','ăăˇ'=>'sshi','ăăˇă§'=>'ssho','ăăˇăĽ'=>'sshu',
- 'ăăăŁ'=>'ccha','ăăă§'=>'cche','ăă'=>'cchi','ăăă§'=>'ccho','ăăăĽ'=>'cchu',
- 'ăăăŁ'=>'tti',
- 'ăăăŁ'=>'ddi',
- // 3 character syllables - doubled vowel and consonants
- 'ăăăź'=>'bbaa','ăăăź'=>'bbee','ăăăź'=>'bbii','ăăăź'=>'bboo','ăăăź'=>'bbuu',
- 'ăăăź'=>'ppaa','ăăăź'=>'ppee','ăăăź'=>'ppii','ăăăź'=>'ppoo','ăăăź'=>'ppuu',
- 'ăăąăź'=>'kkee','ăăăź'=>'kkii','ăăłăź'=>'kkoo','ăăŻăź'=>'kkuu','ăăŤăź'=>'kkaa',
- 'ăăŹăź'=>'ggaa','ăă˛ăź'=>'ggee','ăăŽăź'=>'ggii','ăă´ăź'=>'ggoo','ăă°ăź'=>'gguu',
- 'ăăăź'=>'maa','ăăĄăź'=>'mee','ăăăź'=>'mii','ăă˘ăź'=>'moo','ăă ăź'=>'muu',
- 'ăăăź'=>'nnaa','ăăăź'=>'nnee','ăăăź'=>'nnii','ăăăź'=>'nnoo','ăăăź'=>'nnuu',
- 'ăăŠăź'=>'rraa','ăăŹăź'=>'rree','ăăŞăź'=>'rrii','ăăăź'=>'rroo','ăăŤăź'=>'rruu',
- 'ăăľăź'=>'ssaa','ăăťăź'=>'ssee','ăăˇăź'=>'sshii','ăă˝ăź'=>'ssoo','ăăšăź'=>'ssuu',
- 'ăăśăź'=>'zzaa','ăăźăź'=>'zzee','ăă¸ăź'=>'jjii','ăăžăź'=>'zzoo','ăăşăź'=>'zzuu',
- 'ăăżăź'=>'ttaa','ăăăź'=>'ttee','ăăăź'=>'chii','ăăăź'=>'ttoo','ăăăź'=>'ttsuu',
- 'ăăăź'=>'ddaa','ăăăź'=>'ddee','ăăăź'=>'ddii','ăăăź'=>'ddoo','ăă
ăź'=>'dduu',
- // 2 character syllables - normal
- 'ăăĄ'=>'fa','ăă§'=>'fe','ăăŁ'=>'fi','ăăŠ'=>'fo','ăăĽ'=>'fu',
- // 'ăăŁ'=>'fya','ăă§'=>'fye','ăăŁ'=>'fyi','ăă§'=>'fyo','ăăĽ'=>'fyu',
- 'ăăŁ'=>'fa','ăă§'=>'fe','ăăŁ'=>'fi','ăă§'=>'fo','ăăĽ'=>'fu',
- 'ăăŁ'=>'hya','ăă§'=>'hye','ăăŁ'=>'hyi','ăă§'=>'hyo','ăăĽ'=>'hyu',
- 'ăăŁ'=>'bya','ăă§'=>'bye','ăăŁ'=>'byi','ăă§'=>'byo','ăăĽ'=>'byu',
- 'ăăŁ'=>'pya','ăă§'=>'pye','ăăŁ'=>'pyi','ăă§'=>'pyo','ăăĽ'=>'pyu',
- 'ăăŁ'=>'kya','ăă§'=>'kye','ăăŁ'=>'kyi','ăă§'=>'kyo','ăăĽ'=>'kyu',
- 'ăŽăŁ'=>'gya','ăŽă§'=>'gye','ăŽăŁ'=>'gyi','ăŽă§'=>'gyo','ăŽăĽ'=>'gyu',
- 'ăăŁ'=>'mya','ăă§'=>'mye','ăăŁ'=>'myi','ăă§'=>'myo','ăăĽ'=>'myu',
- 'ăăŁ'=>'nya','ăă§'=>'nye','ăăŁ'=>'nyi','ăă§'=>'nyo','ăăĽ'=>'nyu',
- 'ăŞăŁ'=>'rya','ăŞă§'=>'rye','ăŞăŁ'=>'ryi','ăŞă§'=>'ryo','ăŞăĽ'=>'ryu',
- 'ăˇăŁ'=>'sha','ăˇă§'=>'she','ăˇă§'=>'sho','ăˇăĽ'=>'shu',
- 'ă¸ăŁ'=>'ja','ă¸ă§'=>'je','ă¸ă§'=>'jo','ă¸ăĽ'=>'ju',
- 'ăšăĄ'=>'swa','ăšă§'=>'swe','ăšăŁ'=>'swi','ăšăŠ'=>'swo','ăšăĽ'=>'swu',
- 'ăăĄ'=>'da','ăă§'=>'de','ăăŁ'=>'di','ăăŠ'=>'do','ăăĽ'=>'du',
- 'ăăŁ'=>'cha','ăă§'=>'che','ă'=>'chi','ăă§'=>'cho','ăăĽ'=>'chu',
- // 'ăăŁ'=>'dya','ăă§'=>'dye','ăăŁ'=>'dyi','ăă§'=>'dyo','ăăĽ'=>'dyu',
- 'ăăŁ'=>'tsa','ăă§'=>'tse','ăăŁ'=>'tsi','ăă§'=>'tso','ă'=>'tsu',
- 'ăăĄ'=>'twa','ăă§'=>'twe','ăăŁ'=>'twi','ăăŠ'=>'two','ăăĽ'=>'twu',
- 'ăăĄ'=>'dwa','ăă§'=>'dwe','ăăŁ'=>'dwi','ăăŠ'=>'dwo','ăăĽ'=>'dwu',
- 'ăŚăĄ'=>'wha','ăŚă§'=>'whe','ăŚăŁ'=>'whi','ăŚăŠ'=>'who','ăŚăĽ'=>'whu',
- 'ă´ăŁ'=>'vya','ă´ă§'=>'vye','ă´ăŁ'=>'vyi','ă´ă§'=>'vyo','ă´ăĽ'=>'vyu',
- 'ă´ăĄ'=>'va','ă´ă§'=>'ve','ă´ăŁ'=>'vi','ă´ăŠ'=>'vo','ă´'=>'vu',
- 'ăŚă§'=>'we','ăŚăŁ'=>'wi',
- 'ă¤ă§'=>'ye',
- 'ăăŁ'=>'ti',
- 'ăăŁ'=>'di',
- // 2 character syllables - doubled vocal
- 'ă˘ăź'=>'aa','ă¨ăź'=>'ee','ă¤ăź'=>'ii','ăŞăź'=>'oo','ăŚăź'=>'uu',
- 'ăăź'=>'daa','ăăź'=>'dee','ăăź'=>'dii','ăăź'=>'doo','ă
ăź'=>'duu',
- 'ăăź'=>'haa','ăăź'=>'hee','ăăź'=>'hii','ăăź'=>'hoo','ăăź'=>'fuu',
- 'ăăź'=>'baa','ăăź'=>'bee','ăăź'=>'bii','ăăź'=>'boo','ăăź'=>'buu',
- 'ăăź'=>'paa','ăăź'=>'pee','ăăź'=>'pii','ăăź'=>'poo','ăăź'=>'puu',
- 'ăąăź'=>'kee','ăăź'=>'kii','ăłăź'=>'koo','ăŻăź'=>'kuu','ăŤăź'=>'kaa',
- 'ăŹăź'=>'gaa','ă˛ăź'=>'gee','ăŽăź'=>'gii','ă´ăź'=>'goo','ă°ăź'=>'guu',
- 'ăăź'=>'maa','ăĄăź'=>'mee','ăăź'=>'mii','ă˘ăź'=>'moo','ă ăź'=>'muu',
- 'ăăź'=>'naa','ăăź'=>'nee','ăăź'=>'nii','ăăź'=>'noo','ăăź'=>'nuu',
- 'ăŠăź'=>'raa','ăŹăź'=>'ree','ăŞăź'=>'rii','ăăź'=>'roo','ăŤăź'=>'ruu',
- 'ăľăź'=>'saa','ăťăź'=>'see','ăˇăź'=>'shii','ă˝ăź'=>'soo','ăšăź'=>'suu',
- 'ăśăź'=>'zaa','ăźăź'=>'zee','ă¸ăź'=>'jii','ăžăź'=>'zoo','ăşăź'=>'zuu',
- 'ăżăź'=>'taa','ăăź'=>'tee','ăăź'=>'chii','ăăź'=>'too','ăăź'=>'tsuu',
- 'ăŻăź'=>'waa','ă˛ăź'=>'woo',
- 'ă¤ăź'=>'yaa','ă¨ăź'=>'yoo','ăŚăź'=>'yuu',
- 'ăľăź'=>'kaa','ăśăź'=>'kee',
- // old characters
- 'ăąăź'=>'wee','ă°ăź'=>'wii',
- // seperate katakana 'n'
- 'ăłă˘'=>'n_a','ăłă¨'=>'n_e','ăłă¤'=>'n_i','ăłăŞ'=>'n_o','ăłăŚ'=>'n_u',
- 'ăłă¤'=>'n_ya','ăłă¨'=>'n_yo','ăłăŚ'=>'n_yu',
- // 2 character syllables - doubled consonants
- 'ăă'=>'bba','ăă'=>'bbe','ăă'=>'bbi','ăă'=>'bbo','ăă'=>'bbu',
- 'ăă'=>'ppa','ăă'=>'ppe','ăă'=>'ppi','ăă'=>'ppo','ăă'=>'ppu',
- 'ăăą'=>'kke','ăă'=>'kki','ăăł'=>'kko','ăăŻ'=>'kku','ăăŤ'=>'kka',
- 'ăăŹ'=>'gga','ăă˛'=>'gge','ăăŽ'=>'ggi','ăă´'=>'ggo','ăă°'=>'ggu',
- 'ăă'=>'ma','ăăĄ'=>'me','ăă'=>'mi','ăă˘'=>'mo','ăă '=>'mu',
- 'ăă'=>'nna','ăă'=>'nne','ăă'=>'nni','ăă'=>'nno','ăă'=>'nnu',
- 'ăăŠ'=>'rra','ăăŹ'=>'rre','ăăŞ'=>'rri','ăă'=>'rro','ăăŤ'=>'rru',
- 'ăăľ'=>'ssa','ăăť'=>'sse','ăăˇ'=>'sshi','ăă˝'=>'sso','ăăš'=>'ssu',
- 'ăăś'=>'zza','ăăź'=>'zze','ăă¸'=>'jji','ăăž'=>'zzo','ăăş'=>'zzu',
- 'ăăż'=>'tta','ăă'=>'tte','ăă'=>'cchi','ăă'=>'tto','ăă'=>'ttsu',
- 'ăă'=>'dda','ăă'=>'dde','ăă'=>'ddi','ăă'=>'ddo','ăă
'=>'ddu',
- // 1 character syllables
- 'ă˘'=>'a','ă¨'=>'e','ă¤'=>'i','ăŞ'=>'o','ăŚ'=>'u','ăł'=>'n',
- 'ă'=>'ha','ă'=>'he','ă'=>'hi','ă'=>'ho','ă'=>'fu',
- 'ă'=>'ba','ă'=>'be','ă'=>'bi','ă'=>'bo','ă'=>'bu',
- 'ă'=>'pa','ă'=>'pe','ă'=>'pi','ă'=>'po','ă'=>'pu',
- 'ăą'=>'ke','ă'=>'ki','ăł'=>'ko','ăŻ'=>'ku','ăŤ'=>'ka',
- 'ăŹ'=>'ga','ă˛'=>'ge','ăŽ'=>'gi','ă´'=>'go','ă°'=>'gu',
- 'ă'=>'ma','ăĄ'=>'me','ă'=>'mi','ă˘'=>'mo','ă '=>'mu',
- 'ă'=>'na','ă'=>'ne','ă'=>'ni','ă'=>'no','ă'=>'nu',
- 'ăŠ'=>'ra','ăŹ'=>'re','ăŞ'=>'ri','ă'=>'ro','ăŤ'=>'ru',
- 'ăľ'=>'sa','ăť'=>'se','ăˇ'=>'shi','ă˝'=>'so','ăš'=>'su',
- 'ăś'=>'za','ăź'=>'ze','ă¸'=>'ji','ăž'=>'zo','ăş'=>'zu',
- 'ăż'=>'ta','ă'=>'te','ă'=>'chi','ă'=>'to','ă'=>'tsu',
- 'ă'=>'da','ă'=>'de','ă'=>'di','ă'=>'do','ă
'=>'du',
- 'ăŻ'=>'wa','ă˛'=>'wo',
- 'ă¤'=>'ya','ă¨'=>'yo','ăŚ'=>'yu',
- 'ăľ'=>'ka','ăś'=>'ke',
- // old characters
- 'ăą'=>'we','ă°'=>'wi',
- // convert what's left (probably only kicks in when something's missing above)
- 'ăĄ'=>'a','ă§'=>'e','ăŁ'=>'i','ăŠ'=>'o','ăĽ'=>'u',
- 'ăŁ'=>'ya','ă§'=>'yo','ăĽ'=>'yu',
- // special characters
- 'ăť'=>'_','ă'=>'_',
- 'ăź'=>'_', // when used with hiragana (seldom), this character would not be converted otherwise
- // 'ăŠ'=>'la','ăŹ'=>'le','ăŞ'=>'li','ă'=>'lo','ăŤ'=>'lu',
- // 'ăăŁ'=>'cya','ăă§'=>'cye','ăăŁ'=>'cyi','ăă§'=>'cyo','ăăĽ'=>'cyu',
- //'ăăŁ'=>'dha','ăă§'=>'dhe','ăăŁ'=>'dhi','ăă§'=>'dho','ăăĽ'=>'dhu',
- // 'ăŞăŁ'=>'lya','ăŞă§'=>'lye','ăŞăŁ'=>'lyi','ăŞă§'=>'lyo','ăŞăĽ'=>'lyu',
- // 'ăăŁ'=>'tha','ăă§'=>'the','ăăŁ'=>'thi','ăă§'=>'tho','ăăĽ'=>'thu',
- //'ăăĄ'=>'fwa','ăă§'=>'fwe','ăăŁ'=>'fwi','ăăŠ'=>'fwo','ăăĽ'=>'fwu',
- //'ăăŁ'=>'tya','ăă§'=>'tye','ăăŁ'=>'tyi','ăă§'=>'tyo','ăăĽ'=>'tyu',
- // 'ă¸ăŁ'=>'jya','ă¸ă§'=>'jye','ă¸ăŁ'=>'jyi','ă¸ă§'=>'jyo','ă¸ăĽ'=>'jyu',
- // 'ă¸ăŁ'=>'zha','ă¸ă§'=>'zhe','ă¸ăŁ'=>'zhi','ă¸ă§'=>'zho','ă¸ăĽ'=>'zhu',
- //'ă¸ăŁ'=>'zya','ă¸ă§'=>'zye','ă¸ăŁ'=>'zyi','ă¸ă§'=>'zyo','ă¸ăĽ'=>'zyu',
- //'ăˇăŁ'=>'sya','ăˇă§'=>'sye','ăˇăŁ'=>'syi','ăˇă§'=>'syo','ăˇăĽ'=>'syu',
- //'ăˇ'=>'ci','ă'=>'hu',ăˇ'=>'si','ă'=>'ti','ă'=>'tu','ă¤'=>'yi','ă'=>'dzi',
- // "Greeklish"
- 'Î'=>'G','Î'=>'E','Î'=>'Th','Î'=>'L','Î'=>'X','Î '=>'P','ÎŁ'=>'S','ÎŚ'=>'F','Ψ'=>'Ps',
- 'Îł'=>'g','δ'=>'e','θ'=>'th','Îť'=>'l','Ξ'=>'x','Ď'=>'p','Ď'=>'s','Ď'=>'f','Ď'=>'ps',
- // Thai
- 'ŕ¸'=>'k','ŕ¸'=>'kh','ŕ¸'=>'kh','ŕ¸'=>'kh','ŕ¸
'=>'kh','ŕ¸'=>'kh','ŕ¸'=>'ng','ŕ¸'=>'ch',
- 'ŕ¸'=>'ch','ŕ¸'=>'ch','ŕ¸'=>'s','ŕ¸'=>'ch','ŕ¸'=>'y','ŕ¸'=>'d','ŕ¸'=>'t','ŕ¸'=>'th',
- 'ŕ¸'=>'d','ŕ¸'=>'th','ŕ¸'=>'n','ŕ¸'=>'d','ŕ¸'=>'t','ŕ¸'=>'th','ŕ¸'=>'th','ŕ¸'=>'th',
- 'ŕ¸'=>'n','ŕ¸'=>'b','ŕ¸'=>'p','ŕ¸'=>'ph','ŕ¸'=>'f','ŕ¸'=>'ph','ŕ¸'=>'f','ภ'=>'ph',
- 'ล'=>'m','ย'=>'y','ร'=>'r','ฤ'=>'rue','ฤŕš
'=>'rue','฼'=>'l','ฌ'=>'lue',
- 'ฌŕš
'=>'lue','ว'=>'w','ศ'=>'s','ช'=>'s','ส'=>'s','ญ'=>'h','ฏ'=>'l','ฎ'=>'h',
- 'ะ'=>'a','ู'=>'a','รร'=>'a','า'=>'a','ŕš
'=>'a','ำ'=>'am','ŕšŕ¸˛'=>'am',
- 'ิ'=>'i','฾'=>'i','ผ'=>'ue','฾'=>'ue','ุ'=>'u','บ'=>'u',
- 'ŕš'=>'e','ŕš'=>'ae','ŕš'=>'o','ŕ¸'=>'o',
- '฾ยะ'=>'ia','฾ย'=>'ia','มŕ¸ŕ¸°'=>'uea','มŕ¸'=>'uea','ูวะ'=>'ua','ูว'=>'ua',
- 'ŕš'=>'ai','ŕš'=>'ai','ูย'=>'ai','าย'=>'ai','าว'=>'ao',
- 'ุย'=>'ui','ŕ¸ŕ¸˘'=>'oi','มŕ¸ŕ¸˘'=>'ueai','วย'=>'uai',
- 'ิว'=>'io','ŕšŕ¸§'=>'eo','฾ยว'=>'iao',
- 'ŕš'=>'','ŕš'=>'','ŕš'=>'','ŕš'=>'','ŕš'=>'',
- 'ŕš'=>'','ŕš'=>'','ŕš'=>'','ฺ'=>'',
- 'ŕš'=>'2','ŕš'=>'o','ฯ'=>'-','ŕš'=>'-','ŕš'=>'-',
- 'ŕš'=>'0','ŕš'=>'1','ŕš'=>'2','ŕš'=>'3','ŕš'=>'4',
- 'ŕš'=>'5','ŕš'=>'6','ŕš'=>'7','ŕš'=>'8','ŕš'=>'9',
- // Korean
- 'ăą'=>'k','ă
'=>'kh','ă˛'=>'kk','ăˇ'=>'t','ă
'=>'th','ă¸'=>'tt','ă
'=>'p',
- 'ă
'=>'ph','ă
'=>'pp','ă
'=>'c','ă
'=>'ch','ă
'=>'cc','ă
'=>'s','ă
'=>'ss',
- 'ă
'=>'h','ă
'=>'ng','ă´'=>'n','ăš'=>'l','ă
'=>'m', 'ă
'=>'a','ă
'=>'e','ă
'=>'o',
- 'ă
'=>'wu','ă
Ą'=>'u','ă
Ł'=>'i','ă
'=>'ay','ă
'=>'ey','ă
'=>'oy','ă
'=>'wa','ă
'=>'we',
- 'ă
'=>'wi','ă
'=>'way','ă
'=>'wey','ă
˘'=>'uy','ă
'=>'ya','ă
'=>'ye','ă
'=>'oy',
- 'ă
'=>'yu','ă
'=>'yay','ă
'=>'yey',
- );