PageRenderTime 258ms CodeModel.GetById 29ms RepoModel.GetById 1ms app.codeStats 1ms

/dokuwiki/html/inc/utf8.php

http://portablenginxdokuwik.codeplex.com
PHP | 1683 lines | 1013 code | 152 blank | 518 comment | 168 complexity | 965a4bb72bd4f2927804953e18c4cfe8 MD5 | raw file
Possible License(s): BSD-3-Clause, GPL-2.0
  1. <?php
  2. /**
  3. * UTF8 helper functions
  4. *
  5. * @license LGPL 2.1 (http://www.gnu.org/copyleft/lesser.html)
  6. * @author Andreas Gohr <andi@splitbrain.org>
  7. */
  8. /**
  9. * check for mb_string support
  10. */
  11. if(!defined('UTF8_MBSTRING')){
  12. if(function_exists('mb_substr') && !defined('UTF8_NOMBSTRING')){
  13. define('UTF8_MBSTRING',1);
  14. }else{
  15. define('UTF8_MBSTRING',0);
  16. }
  17. }
  18. if(UTF8_MBSTRING){ mb_internal_encoding('UTF-8'); }
  19. if(!function_exists('utf8_isASCII')){
  20. /**
  21. * Checks if a string contains 7bit ASCII only
  22. *
  23. * @author Andreas Haerter <andreas.haerter@dev.mail-node.com>
  24. */
  25. function utf8_isASCII($str){
  26. return (preg_match('/(?:[^\x00-\x7F])/', $str) !== 1);
  27. }
  28. }
  29. if(!function_exists('utf8_strip')){
  30. /**
  31. * Strips all highbyte chars
  32. *
  33. * Returns a pure ASCII7 string
  34. *
  35. * @author Andreas Gohr <andi@splitbrain.org>
  36. */
  37. function utf8_strip($str){
  38. $ascii = '';
  39. $len = strlen($str);
  40. for($i=0; $i<$len; $i++){
  41. if(ord($str{$i}) <128){
  42. $ascii .= $str{$i};
  43. }
  44. }
  45. return $ascii;
  46. }
  47. }
  48. if(!function_exists('utf8_check')){
  49. /**
  50. * Tries to detect if a string is in Unicode encoding
  51. *
  52. * @author <bmorel@ssi.fr>
  53. * @link http://www.php.net/manual/en/function.utf8-encode.php
  54. */
  55. function utf8_check($Str) {
  56. $len = strlen($Str);
  57. for ($i=0; $i<$len; $i++) {
  58. $b = ord($Str[$i]);
  59. if ($b < 0x80) continue; # 0bbbbbbb
  60. elseif (($b & 0xE0) == 0xC0) $n=1; # 110bbbbb
  61. elseif (($b & 0xF0) == 0xE0) $n=2; # 1110bbbb
  62. elseif (($b & 0xF8) == 0xF0) $n=3; # 11110bbb
  63. elseif (($b & 0xFC) == 0xF8) $n=4; # 111110bb
  64. elseif (($b & 0xFE) == 0xFC) $n=5; # 1111110b
  65. else return false; # Does not match any model
  66. for ($j=0; $j<$n; $j++) { # n bytes matching 10bbbbbb follow ?
  67. if ((++$i == $len) || ((ord($Str[$i]) & 0xC0) != 0x80))
  68. return false;
  69. }
  70. }
  71. return true;
  72. }
  73. }
  74. if(!function_exists('utf8_basename')){
  75. /**
  76. * A locale independent basename() implementation
  77. *
  78. * works around a bug in PHP's basename() implementation
  79. *
  80. * @see basename()
  81. * @link https://bugs.php.net/bug.php?id=37738
  82. * @param string $path A path
  83. * @param string $suffix If the name component ends in suffix this will also be cut off
  84. * @return string
  85. */
  86. function utf8_basename($path, $suffix=''){
  87. $path = trim($path,'\\/');
  88. $rpos = max(strrpos($path, '/'), strrpos($path, '\\'));
  89. if($rpos) $path = substr($path, $rpos+1);
  90. $suflen = strlen($suffix);
  91. if($suflen && (substr($path, -$suflen) == $suffix)){
  92. $path = substr($path, 0, -$suflen);
  93. }
  94. return $path;
  95. }
  96. }
  97. if(!function_exists('utf8_strlen')){
  98. /**
  99. * Unicode aware replacement for strlen()
  100. *
  101. * utf8_decode() converts characters that are not in ISO-8859-1
  102. * to '?', which, for the purpose of counting, is alright - It's
  103. * even faster than mb_strlen.
  104. *
  105. * @author <chernyshevsky at hotmail dot com>
  106. * @see strlen()
  107. * @see utf8_decode()
  108. */
  109. function utf8_strlen($string){
  110. return strlen(utf8_decode($string));
  111. }
  112. }
  113. if(!function_exists('utf8_substr')){
  114. /**
  115. * UTF-8 aware alternative to substr
  116. *
  117. * Return part of a string given character offset (and optionally length)
  118. *
  119. * @author Harry Fuecks <hfuecks@gmail.com>
  120. * @author Chris Smith <chris@jalakai.co.uk>
  121. * @param string $str
  122. * @param int $offset number of UTF-8 characters offset (from left)
  123. * @param int $length (optional) length in UTF-8 characters from offset
  124. * @return mixed string or false if failure
  125. */
  126. function utf8_substr($str, $offset, $length = null) {
  127. if(UTF8_MBSTRING){
  128. if( $length === null ){
  129. return mb_substr($str, $offset);
  130. }else{
  131. return mb_substr($str, $offset, $length);
  132. }
  133. }
  134. /*
  135. * Notes:
  136. *
  137. * no mb string support, so we'll use pcre regex's with 'u' flag
  138. * pcre only supports repetitions of less than 65536, in order to accept up to MAXINT values for
  139. * offset and length, we'll repeat a group of 65535 characters when needed (ok, up to MAXINT-65536)
  140. *
  141. * substr documentation states false can be returned in some cases (e.g. offset > string length)
  142. * mb_substr never returns false, it will return an empty string instead.
  143. *
  144. * calculating the number of characters in the string is a relatively expensive operation, so
  145. * we only carry it out when necessary. It isn't necessary for +ve offsets and no specified length
  146. */
  147. // cast parameters to appropriate types to avoid multiple notices/warnings
  148. $str = (string)$str; // generates E_NOTICE for PHP4 objects, but not PHP5 objects
  149. $offset = (int)$offset;
  150. if (!is_null($length)) $length = (int)$length;
  151. // handle trivial cases
  152. if ($length === 0) return '';
  153. if ($offset < 0 && $length < 0 && $length < $offset) return '';
  154. $offset_pattern = '';
  155. $length_pattern = '';
  156. // normalise -ve offsets (we could use a tail anchored pattern, but they are horribly slow!)
  157. if ($offset < 0) {
  158. $strlen = strlen(utf8_decode($str)); // see notes
  159. $offset = $strlen + $offset;
  160. if ($offset < 0) $offset = 0;
  161. }
  162. // establish a pattern for offset, a non-captured group equal in length to offset
  163. if ($offset > 0) {
  164. $Ox = (int)($offset/65535);
  165. $Oy = $offset%65535;
  166. if ($Ox) $offset_pattern = '(?:.{65535}){'.$Ox.'}';
  167. $offset_pattern = '^(?:'.$offset_pattern.'.{'.$Oy.'})';
  168. } else {
  169. $offset_pattern = '^'; // offset == 0; just anchor the pattern
  170. }
  171. // establish a pattern for length
  172. if (is_null($length)) {
  173. $length_pattern = '(.*)$'; // the rest of the string
  174. } else {
  175. if (!isset($strlen)) $strlen = strlen(utf8_decode($str)); // see notes
  176. if ($offset > $strlen) return ''; // another trivial case
  177. if ($length > 0) {
  178. $length = min($strlen-$offset, $length); // reduce any length that would go passed the end of the string
  179. $Lx = (int)($length/65535);
  180. $Ly = $length%65535;
  181. // +ve length requires ... a captured group of length characters
  182. if ($Lx) $length_pattern = '(?:.{65535}){'.$Lx.'}';
  183. $length_pattern = '('.$length_pattern.'.{'.$Ly.'})';
  184. } else if ($length < 0) {
  185. if ($length < ($offset - $strlen)) return '';
  186. $Lx = (int)((-$length)/65535);
  187. $Ly = (-$length)%65535;
  188. // -ve length requires ... capture everything except a group of -length characters
  189. // anchored at the tail-end of the string
  190. if ($Lx) $length_pattern = '(?:.{65535}){'.$Lx.'}';
  191. $length_pattern = '(.*)(?:'.$length_pattern.'.{'.$Ly.'})$';
  192. }
  193. }
  194. if (!preg_match('#'.$offset_pattern.$length_pattern.'#us',$str,$match)) return '';
  195. return $match[1];
  196. }
  197. }
  198. if(!function_exists('utf8_substr_replace')){
  199. /**
  200. * Unicode aware replacement for substr_replace()
  201. *
  202. * @author Andreas Gohr <andi@splitbrain.org>
  203. * @see substr_replace()
  204. */
  205. function utf8_substr_replace($string, $replacement, $start , $length=0 ){
  206. $ret = '';
  207. if($start>0) $ret .= utf8_substr($string, 0, $start);
  208. $ret .= $replacement;
  209. $ret .= utf8_substr($string, $start+$length);
  210. return $ret;
  211. }
  212. }
  213. if(!function_exists('utf8_ltrim')){
  214. /**
  215. * Unicode aware replacement for ltrim()
  216. *
  217. * @author Andreas Gohr <andi@splitbrain.org>
  218. * @see ltrim()
  219. * @param string $str
  220. * @param string $charlist
  221. * @return string
  222. */
  223. function utf8_ltrim($str,$charlist=''){
  224. if($charlist == '') return ltrim($str);
  225. //quote charlist for use in a characterclass
  226. $charlist = preg_replace('!([\\\\\\-\\]\\[/])!','\\\${1}',$charlist);
  227. return preg_replace('/^['.$charlist.']+/u','',$str);
  228. }
  229. }
  230. if(!function_exists('utf8_rtrim')){
  231. /**
  232. * Unicode aware replacement for rtrim()
  233. *
  234. * @author Andreas Gohr <andi@splitbrain.org>
  235. * @see rtrim()
  236. * @param string $str
  237. * @param string $charlist
  238. * @return string
  239. */
  240. function utf8_rtrim($str,$charlist=''){
  241. if($charlist == '') return rtrim($str);
  242. //quote charlist for use in a characterclass
  243. $charlist = preg_replace('!([\\\\\\-\\]\\[/])!','\\\${1}',$charlist);
  244. return preg_replace('/['.$charlist.']+$/u','',$str);
  245. }
  246. }
  247. if(!function_exists('utf8_trim')){
  248. /**
  249. * Unicode aware replacement for trim()
  250. *
  251. * @author Andreas Gohr <andi@splitbrain.org>
  252. * @see trim()
  253. * @param string $str
  254. * @param string $charlist
  255. * @return string
  256. */
  257. function utf8_trim($str,$charlist='') {
  258. if($charlist == '') return trim($str);
  259. return utf8_ltrim(utf8_rtrim($str,$charlist),$charlist);
  260. }
  261. }
  262. if(!function_exists('utf8_strtolower')){
  263. /**
  264. * This is a unicode aware replacement for strtolower()
  265. *
  266. * Uses mb_string extension if available
  267. *
  268. * @author Leo Feyer <leo@typolight.org>
  269. * @see strtolower()
  270. * @see utf8_strtoupper()
  271. */
  272. function utf8_strtolower($string){
  273. if(UTF8_MBSTRING) return mb_strtolower($string,'utf-8');
  274. global $UTF8_UPPER_TO_LOWER;
  275. return strtr($string,$UTF8_UPPER_TO_LOWER);
  276. }
  277. }
  278. if(!function_exists('utf8_strtoupper')){
  279. /**
  280. * This is a unicode aware replacement for strtoupper()
  281. *
  282. * Uses mb_string extension if available
  283. *
  284. * @author Leo Feyer <leo@typolight.org>
  285. * @see strtoupper()
  286. * @see utf8_strtoupper()
  287. */
  288. function utf8_strtoupper($string){
  289. if(UTF8_MBSTRING) return mb_strtoupper($string,'utf-8');
  290. global $UTF8_LOWER_TO_UPPER;
  291. return strtr($string,$UTF8_LOWER_TO_UPPER);
  292. }
  293. }
  294. if(!function_exists('utf8_ucfirst')){
  295. /**
  296. * UTF-8 aware alternative to ucfirst
  297. * Make a string's first character uppercase
  298. *
  299. * @author Harry Fuecks
  300. * @param string
  301. * @return string with first character as upper case (if applicable)
  302. */
  303. function utf8_ucfirst($str){
  304. switch ( utf8_strlen($str) ) {
  305. case 0:
  306. return '';
  307. case 1:
  308. return utf8_strtoupper($str);
  309. default:
  310. preg_match('/^(.{1})(.*)$/us', $str, $matches);
  311. return utf8_strtoupper($matches[1]).$matches[2];
  312. }
  313. }
  314. }
  315. if(!function_exists('utf8_ucwords')){
  316. /**
  317. * UTF-8 aware alternative to ucwords
  318. * Uppercase the first character of each word in a string
  319. *
  320. * @author Harry Fuecks
  321. * @param string
  322. * @return string with first char of each word uppercase
  323. * @see http://www.php.net/ucwords
  324. */
  325. function utf8_ucwords($str) {
  326. // Note: [\x0c\x09\x0b\x0a\x0d\x20] matches;
  327. // form feeds, horizontal tabs, vertical tabs, linefeeds and carriage returns
  328. // This corresponds to the definition of a "word" defined at http://www.php.net/ucwords
  329. $pattern = '/(^|([\x0c\x09\x0b\x0a\x0d\x20]+))([^\x0c\x09\x0b\x0a\x0d\x20]{1})[^\x0c\x09\x0b\x0a\x0d\x20]*/u';
  330. return preg_replace_callback($pattern, 'utf8_ucwords_callback',$str);
  331. }
  332. /**
  333. * Callback function for preg_replace_callback call in utf8_ucwords
  334. * You don't need to call this yourself
  335. *
  336. * @author Harry Fuecks
  337. * @param array $matches matches corresponding to a single word
  338. * @return string with first char of the word in uppercase
  339. * @see utf8_ucwords
  340. * @see utf8_strtoupper
  341. */
  342. function utf8_ucwords_callback($matches) {
  343. $leadingws = $matches[2];
  344. $ucfirst = utf8_strtoupper($matches[3]);
  345. $ucword = utf8_substr_replace(ltrim($matches[0]),$ucfirst,0,1);
  346. return $leadingws . $ucword;
  347. }
  348. }
  349. if(!function_exists('utf8_deaccent')){
  350. /**
  351. * Replace accented UTF-8 characters by unaccented ASCII-7 equivalents
  352. *
  353. * Use the optional parameter to just deaccent lower ($case = -1) or upper ($case = 1)
  354. * letters. Default is to deaccent both cases ($case = 0)
  355. *
  356. * @author Andreas Gohr <andi@splitbrain.org>
  357. */
  358. function utf8_deaccent($string,$case=0){
  359. if($case <= 0){
  360. global $UTF8_LOWER_ACCENTS;
  361. $string = strtr($string,$UTF8_LOWER_ACCENTS);
  362. }
  363. if($case >= 0){
  364. global $UTF8_UPPER_ACCENTS;
  365. $string = strtr($string,$UTF8_UPPER_ACCENTS);
  366. }
  367. return $string;
  368. }
  369. }
  370. if(!function_exists('utf8_romanize')){
  371. /**
  372. * Romanize a non-latin string
  373. *
  374. * @author Andreas Gohr <andi@splitbrain.org>
  375. */
  376. function utf8_romanize($string){
  377. if(utf8_isASCII($string)) return $string; //nothing to do
  378. global $UTF8_ROMANIZATION;
  379. return strtr($string,$UTF8_ROMANIZATION);
  380. }
  381. }
  382. if(!function_exists('utf8_stripspecials')){
  383. /**
  384. * Removes special characters (nonalphanumeric) from a UTF-8 string
  385. *
  386. * This function adds the controlchars 0x00 to 0x19 to the array of
  387. * stripped chars (they are not included in $UTF8_SPECIAL_CHARS)
  388. *
  389. * @author Andreas Gohr <andi@splitbrain.org>
  390. * @param string $string The UTF8 string to strip of special chars
  391. * @param string $repl Replace special with this string
  392. * @param string $additional Additional chars to strip (used in regexp char class)
  393. * @return string
  394. */
  395. function utf8_stripspecials($string,$repl='',$additional=''){
  396. global $UTF8_SPECIAL_CHARS2;
  397. static $specials = null;
  398. if(is_null($specials)){
  399. #$specials = preg_quote(unicode_to_utf8($UTF8_SPECIAL_CHARS), '/');
  400. $specials = preg_quote($UTF8_SPECIAL_CHARS2, '/');
  401. }
  402. return preg_replace('/['.$additional.'\x00-\x19'.$specials.']/u',$repl,$string);
  403. }
  404. }
  405. if(!function_exists('utf8_strpos')){
  406. /**
  407. * This is an Unicode aware replacement for strpos
  408. *
  409. * @author Leo Feyer <leo@typolight.org>
  410. * @see strpos()
  411. * @param string
  412. * @param string
  413. * @param integer
  414. * @return integer
  415. */
  416. function utf8_strpos($haystack, $needle, $offset=0){
  417. $comp = 0;
  418. $length = null;
  419. while (is_null($length) || $length < $offset) {
  420. $pos = strpos($haystack, $needle, $offset + $comp);
  421. if ($pos === false)
  422. return false;
  423. $length = utf8_strlen(substr($haystack, 0, $pos));
  424. if ($length < $offset)
  425. $comp = $pos - $length;
  426. }
  427. return $length;
  428. }
  429. }
  430. if(!function_exists('utf8_tohtml')){
  431. /**
  432. * Encodes UTF-8 characters to HTML entities
  433. *
  434. * @author Tom N Harris <tnharris@whoopdedo.org>
  435. * @author <vpribish at shopping dot com>
  436. * @link http://www.php.net/manual/en/function.utf8-decode.php
  437. */
  438. function utf8_tohtml ($str) {
  439. $ret = '';
  440. foreach (utf8_to_unicode($str) as $cp) {
  441. if ($cp < 0x80)
  442. $ret .= chr($cp);
  443. elseif ($cp < 0x100)
  444. $ret .= "&#$cp;";
  445. else
  446. $ret .= '&#x'.dechex($cp).';';
  447. }
  448. return $ret;
  449. }
  450. }
  451. if(!function_exists('utf8_unhtml')){
  452. /**
  453. * Decodes HTML entities to UTF-8 characters
  454. *
  455. * Convert any &#..; entity to a codepoint,
  456. * The entities flag defaults to only decoding numeric entities.
  457. * Pass HTML_ENTITIES and named entities, including &amp; &lt; etc.
  458. * are handled as well. Avoids the problem that would occur if you
  459. * had to decode "&amp;#38;&#38;amp;#38;"
  460. *
  461. * unhtmlspecialchars(utf8_unhtml($s)) -> "&#38;&#38;"
  462. * utf8_unhtml(unhtmlspecialchars($s)) -> "&&amp#38;"
  463. * what it should be -> "&#38;&amp#38;"
  464. *
  465. * @author Tom N Harris <tnharris@whoopdedo.org>
  466. * @param string $str UTF-8 encoded string
  467. * @param boolean $entities Flag controlling decoding of named entities.
  468. * @return string UTF-8 encoded string with numeric (and named) entities replaced.
  469. */
  470. function utf8_unhtml($str, $entities=null) {
  471. static $decoder = null;
  472. if (is_null($decoder))
  473. $decoder = new utf8_entity_decoder();
  474. if (is_null($entities))
  475. return preg_replace_callback('/(&#([Xx])?([0-9A-Za-z]+);)/m',
  476. 'utf8_decode_numeric', $str);
  477. else
  478. return preg_replace_callback('/&(#)?([Xx])?([0-9A-Za-z]+);/m',
  479. array(&$decoder, 'decode'), $str);
  480. }
  481. }
  482. if(!function_exists('utf8_decode_numeric')){
  483. /**
  484. * Decodes numeric HTML entities to their correct UTF-8 characters
  485. *
  486. * @param $ent string A numeric entity
  487. * @return string
  488. */
  489. function utf8_decode_numeric($ent) {
  490. switch ($ent[2]) {
  491. case 'X':
  492. case 'x':
  493. $cp = hexdec($ent[3]);
  494. break;
  495. default:
  496. $cp = intval($ent[3]);
  497. break;
  498. }
  499. return unicode_to_utf8(array($cp));
  500. }
  501. }
  502. if(!class_exists('utf8_entity_decoder')){
  503. /**
  504. * Encapsulate HTML entity decoding tables
  505. */
  506. class utf8_entity_decoder {
  507. var $table;
  508. /**
  509. * Initializes the decoding tables
  510. */
  511. function __construct() {
  512. $table = get_html_translation_table(HTML_ENTITIES);
  513. $table = array_flip($table);
  514. $this->table = array_map(array(&$this,'makeutf8'), $table);
  515. }
  516. /**
  517. * Wrapper aorund unicode_to_utf8()
  518. *
  519. * @param $c string
  520. * @return mixed
  521. */
  522. function makeutf8($c) {
  523. return unicode_to_utf8(array(ord($c)));
  524. }
  525. /**
  526. * Decodes any HTML entity to it's correct UTF-8 char equivalent
  527. *
  528. * @param $ent string An entity
  529. * @return string
  530. */
  531. function decode($ent) {
  532. if ($ent[1] == '#') {
  533. return utf8_decode_numeric($ent);
  534. } elseif (array_key_exists($ent[0],$this->table)) {
  535. return $this->table[$ent[0]];
  536. } else {
  537. return $ent[0];
  538. }
  539. }
  540. }
  541. }
  542. if(!function_exists('utf8_to_unicode')){
  543. /**
  544. * Takes an UTF-8 string and returns an array of ints representing the
  545. * Unicode characters. Astral planes are supported ie. the ints in the
  546. * output can be > 0xFFFF. Occurrances of the BOM are ignored. Surrogates
  547. * are not allowed.
  548. *
  549. * If $strict is set to true the function returns false if the input
  550. * string isn't a valid UTF-8 octet sequence and raises a PHP error at
  551. * level E_USER_WARNING
  552. *
  553. * Note: this function has been modified slightly in this library to
  554. * trigger errors on encountering bad bytes
  555. *
  556. * @author <hsivonen@iki.fi>
  557. * @author Harry Fuecks <hfuecks@gmail.com>
  558. * @param string $str UTF-8 encoded string
  559. * @param boolean $strict Check for invalid sequences?
  560. * @return mixed array of unicode code points or false if UTF-8 invalid
  561. * @see unicode_to_utf8
  562. * @link http://hsivonen.iki.fi/php-utf8/
  563. * @link http://sourceforge.net/projects/phputf8/
  564. */
  565. function utf8_to_unicode($str,$strict=false) {
  566. $mState = 0; // cached expected number of octets after the current octet
  567. // until the beginning of the next UTF8 character sequence
  568. $mUcs4 = 0; // cached Unicode character
  569. $mBytes = 1; // cached expected number of octets in the current sequence
  570. $out = array();
  571. $len = strlen($str);
  572. for($i = 0; $i < $len; $i++) {
  573. $in = ord($str{$i});
  574. if ( $mState == 0) {
  575. // When mState is zero we expect either a US-ASCII character or a
  576. // multi-octet sequence.
  577. if (0 == (0x80 & ($in))) {
  578. // US-ASCII, pass straight through.
  579. $out[] = $in;
  580. $mBytes = 1;
  581. } else if (0xC0 == (0xE0 & ($in))) {
  582. // First octet of 2 octet sequence
  583. $mUcs4 = ($in);
  584. $mUcs4 = ($mUcs4 & 0x1F) << 6;
  585. $mState = 1;
  586. $mBytes = 2;
  587. } else if (0xE0 == (0xF0 & ($in))) {
  588. // First octet of 3 octet sequence
  589. $mUcs4 = ($in);
  590. $mUcs4 = ($mUcs4 & 0x0F) << 12;
  591. $mState = 2;
  592. $mBytes = 3;
  593. } else if (0xF0 == (0xF8 & ($in))) {
  594. // First octet of 4 octet sequence
  595. $mUcs4 = ($in);
  596. $mUcs4 = ($mUcs4 & 0x07) << 18;
  597. $mState = 3;
  598. $mBytes = 4;
  599. } else if (0xF8 == (0xFC & ($in))) {
  600. /* First octet of 5 octet sequence.
  601. *
  602. * This is illegal because the encoded codepoint must be either
  603. * (a) not the shortest form or
  604. * (b) outside the Unicode range of 0-0x10FFFF.
  605. * Rather than trying to resynchronize, we will carry on until the end
  606. * of the sequence and let the later error handling code catch it.
  607. */
  608. $mUcs4 = ($in);
  609. $mUcs4 = ($mUcs4 & 0x03) << 24;
  610. $mState = 4;
  611. $mBytes = 5;
  612. } else if (0xFC == (0xFE & ($in))) {
  613. // First octet of 6 octet sequence, see comments for 5 octet sequence.
  614. $mUcs4 = ($in);
  615. $mUcs4 = ($mUcs4 & 1) << 30;
  616. $mState = 5;
  617. $mBytes = 6;
  618. } elseif($strict) {
  619. /* Current octet is neither in the US-ASCII range nor a legal first
  620. * octet of a multi-octet sequence.
  621. */
  622. trigger_error(
  623. 'utf8_to_unicode: Illegal sequence identifier '.
  624. 'in UTF-8 at byte '.$i,
  625. E_USER_WARNING
  626. );
  627. return false;
  628. }
  629. } else {
  630. // When mState is non-zero, we expect a continuation of the multi-octet
  631. // sequence
  632. if (0x80 == (0xC0 & ($in))) {
  633. // Legal continuation.
  634. $shift = ($mState - 1) * 6;
  635. $tmp = $in;
  636. $tmp = ($tmp & 0x0000003F) << $shift;
  637. $mUcs4 |= $tmp;
  638. /**
  639. * End of the multi-octet sequence. mUcs4 now contains the final
  640. * Unicode codepoint to be output
  641. */
  642. if (0 == --$mState) {
  643. /*
  644. * Check for illegal sequences and codepoints.
  645. */
  646. // From Unicode 3.1, non-shortest form is illegal
  647. if (((2 == $mBytes) && ($mUcs4 < 0x0080)) ||
  648. ((3 == $mBytes) && ($mUcs4 < 0x0800)) ||
  649. ((4 == $mBytes) && ($mUcs4 < 0x10000)) ||
  650. (4 < $mBytes) ||
  651. // From Unicode 3.2, surrogate characters are illegal
  652. (($mUcs4 & 0xFFFFF800) == 0xD800) ||
  653. // Codepoints outside the Unicode range are illegal
  654. ($mUcs4 > 0x10FFFF)) {
  655. if($strict){
  656. trigger_error(
  657. 'utf8_to_unicode: Illegal sequence or codepoint '.
  658. 'in UTF-8 at byte '.$i,
  659. E_USER_WARNING
  660. );
  661. return false;
  662. }
  663. }
  664. if (0xFEFF != $mUcs4) {
  665. // BOM is legal but we don't want to output it
  666. $out[] = $mUcs4;
  667. }
  668. //initialize UTF8 cache
  669. $mState = 0;
  670. $mUcs4 = 0;
  671. $mBytes = 1;
  672. }
  673. } elseif($strict) {
  674. /**
  675. *((0xC0 & (*in) != 0x80) && (mState != 0))
  676. * Incomplete multi-octet sequence.
  677. */
  678. trigger_error(
  679. 'utf8_to_unicode: Incomplete multi-octet '.
  680. ' sequence in UTF-8 at byte '.$i,
  681. E_USER_WARNING
  682. );
  683. return false;
  684. }
  685. }
  686. }
  687. return $out;
  688. }
  689. }
  690. if(!function_exists('unicode_to_utf8')){
  691. /**
  692. * Takes an array of ints representing the Unicode characters and returns
  693. * a UTF-8 string. Astral planes are supported ie. the ints in the
  694. * input can be > 0xFFFF. Occurrances of the BOM are ignored. Surrogates
  695. * are not allowed.
  696. *
  697. * If $strict is set to true the function returns false if the input
  698. * array contains ints that represent surrogates or are outside the
  699. * Unicode range and raises a PHP error at level E_USER_WARNING
  700. *
  701. * Note: this function has been modified slightly in this library to use
  702. * output buffering to concatenate the UTF-8 string (faster) as well as
  703. * reference the array by it's keys
  704. *
  705. * @param array $arr of unicode code points representing a string
  706. * @param boolean $strict Check for invalid sequences?
  707. * @return mixed UTF-8 string or false if array contains invalid code points
  708. * @author <hsivonen@iki.fi>
  709. * @author Harry Fuecks <hfuecks@gmail.com>
  710. * @see utf8_to_unicode
  711. * @link http://hsivonen.iki.fi/php-utf8/
  712. * @link http://sourceforge.net/projects/phputf8/
  713. */
  714. function unicode_to_utf8($arr,$strict=false) {
  715. if (!is_array($arr)) return '';
  716. ob_start();
  717. foreach (array_keys($arr) as $k) {
  718. if ( ($arr[$k] >= 0) && ($arr[$k] <= 0x007f) ) {
  719. # ASCII range (including control chars)
  720. echo chr($arr[$k]);
  721. } else if ($arr[$k] <= 0x07ff) {
  722. # 2 byte sequence
  723. echo chr(0xc0 | ($arr[$k] >> 6));
  724. echo chr(0x80 | ($arr[$k] & 0x003f));
  725. } else if($arr[$k] == 0xFEFF) {
  726. # Byte order mark (skip)
  727. // nop -- zap the BOM
  728. } else if ($arr[$k] >= 0xD800 && $arr[$k] <= 0xDFFF) {
  729. # Test for illegal surrogates
  730. // found a surrogate
  731. if($strict){
  732. trigger_error(
  733. 'unicode_to_utf8: Illegal surrogate '.
  734. 'at index: '.$k.', value: '.$arr[$k],
  735. E_USER_WARNING
  736. );
  737. return false;
  738. }
  739. } else if ($arr[$k] <= 0xffff) {
  740. # 3 byte sequence
  741. echo chr(0xe0 | ($arr[$k] >> 12));
  742. echo chr(0x80 | (($arr[$k] >> 6) & 0x003f));
  743. echo chr(0x80 | ($arr[$k] & 0x003f));
  744. } else if ($arr[$k] <= 0x10ffff) {
  745. # 4 byte sequence
  746. echo chr(0xf0 | ($arr[$k] >> 18));
  747. echo chr(0x80 | (($arr[$k] >> 12) & 0x3f));
  748. echo chr(0x80 | (($arr[$k] >> 6) & 0x3f));
  749. echo chr(0x80 | ($arr[$k] & 0x3f));
  750. } elseif($strict) {
  751. trigger_error(
  752. 'unicode_to_utf8: Codepoint out of Unicode range '.
  753. 'at index: '.$k.', value: '.$arr[$k],
  754. E_USER_WARNING
  755. );
  756. // out of range
  757. return false;
  758. }
  759. }
  760. $result = ob_get_contents();
  761. ob_end_clean();
  762. return $result;
  763. }
  764. }
  765. if(!function_exists('utf8_to_utf16be')){
  766. /**
  767. * UTF-8 to UTF-16BE conversion.
  768. *
  769. * Maybe really UCS-2 without mb_string due to utf8_to_unicode limits
  770. */
  771. function utf8_to_utf16be(&$str, $bom = false) {
  772. $out = $bom ? "\xFE\xFF" : '';
  773. if(UTF8_MBSTRING) return $out.mb_convert_encoding($str,'UTF-16BE','UTF-8');
  774. $uni = utf8_to_unicode($str);
  775. foreach($uni as $cp){
  776. $out .= pack('n',$cp);
  777. }
  778. return $out;
  779. }
  780. }
  781. if(!function_exists('utf16be_to_utf8')){
  782. /**
  783. * UTF-8 to UTF-16BE conversion.
  784. *
  785. * Maybe really UCS-2 without mb_string due to utf8_to_unicode limits
  786. */
  787. function utf16be_to_utf8(&$str) {
  788. $uni = unpack('n*',$str);
  789. return unicode_to_utf8($uni);
  790. }
  791. }
  792. if(!function_exists('utf8_bad_replace')){
  793. /**
  794. * Replace bad bytes with an alternative character
  795. *
  796. * ASCII character is recommended for replacement char
  797. *
  798. * PCRE Pattern to locate bad bytes in a UTF-8 string
  799. * Comes from W3 FAQ: Multilingual Forms
  800. * Note: modified to include full ASCII range including control chars
  801. *
  802. * @author Harry Fuecks <hfuecks@gmail.com>
  803. * @see http://www.w3.org/International/questions/qa-forms-utf-8
  804. * @param string $str to search
  805. * @param string $replace to replace bad bytes with (defaults to '?') - use ASCII
  806. * @return string
  807. */
  808. function utf8_bad_replace($str, $replace = '') {
  809. $UTF8_BAD =
  810. '([\x00-\x7F]'. # ASCII (including control chars)
  811. '|[\xC2-\xDF][\x80-\xBF]'. # non-overlong 2-byte
  812. '|\xE0[\xA0-\xBF][\x80-\xBF]'. # excluding overlongs
  813. '|[\xE1-\xEC\xEE\xEF][\x80-\xBF]{2}'. # straight 3-byte
  814. '|\xED[\x80-\x9F][\x80-\xBF]'. # excluding surrogates
  815. '|\xF0[\x90-\xBF][\x80-\xBF]{2}'. # planes 1-3
  816. '|[\xF1-\xF3][\x80-\xBF]{3}'. # planes 4-15
  817. '|\xF4[\x80-\x8F][\x80-\xBF]{2}'. # plane 16
  818. '|(.{1}))'; # invalid byte
  819. ob_start();
  820. while (preg_match('/'.$UTF8_BAD.'/S', $str, $matches)) {
  821. if ( !isset($matches[2])) {
  822. echo $matches[0];
  823. } else {
  824. echo $replace;
  825. }
  826. $str = substr($str,strlen($matches[0]));
  827. }
  828. $result = ob_get_contents();
  829. ob_end_clean();
  830. return $result;
  831. }
  832. }
  833. if(!function_exists('utf8_correctIdx')){
  834. /**
  835. * adjust a byte index into a utf8 string to a utf8 character boundary
  836. *
  837. * @param $str string utf8 character string
  838. * @param $i int byte index into $str
  839. * @param $next bool direction to search for boundary,
  840. * false = up (current character)
  841. * true = down (next character)
  842. *
  843. * @return int byte index into $str now pointing to a utf8 character boundary
  844. *
  845. * @author chris smith <chris@jalakai.co.uk>
  846. */
  847. function utf8_correctIdx(&$str,$i,$next=false) {
  848. if ($i <= 0) return 0;
  849. $limit = strlen($str);
  850. if ($i>=$limit) return $limit;
  851. if ($next) {
  852. while (($i<$limit) && ((ord($str[$i]) & 0xC0) == 0x80)) $i++;
  853. } else {
  854. while ($i && ((ord($str[$i]) & 0xC0) == 0x80)) $i--;
  855. }
  856. return $i;
  857. }
  858. }
  859. // only needed if no mb_string available
  860. if(!UTF8_MBSTRING){
  861. /**
  862. * UTF-8 Case lookup table
  863. *
  864. * This lookuptable defines the upper case letters to their correspponding
  865. * lower case letter in UTF-8
  866. *
  867. * @author Andreas Gohr <andi@splitbrain.org>
  868. */
  869. global $UTF8_LOWER_TO_UPPER;
  870. if(empty($UTF8_LOWER_TO_UPPER)) $UTF8_LOWER_TO_UPPER = array(
  871. "??&#x161;"=>"???","??&#x2122;"=>"??š","??&#x2DC;"=>"??¸","??&#x2014;"=>"???","??&#x2013;"=>"???","??&#x2022;"=>"???","??&#x201D;"=>"??´","??&#x201C;"=>"???","??&#x2019;"=>"???","??&#x2018;"=>"???",
  872. "???"=>"??°","???"=>"???","??&#x17D;"=>"??Ž","???"=>"??­","??&#x152;"=>"???","??&#x2039;"=>"???","??&#x160;"=>"???","??&#x2030;"=>"??Š","??&#x2C6;"=>"??¨","??&#x2021;"=>"??§",
  873. "??&#x2020;"=>"???","??&#x2026;"=>"???","??&#x201E;"=>"??¤","??&#x192;"=>"???","??&#x201A;"=>"???","?? "=>"???","á??"=>"á??","á??"=>"á??","á??"=>"á?Š","á?&#x2018;"=>"á?&#x2122;",
  874. "á??"=>"á?&#x2DC;","á?&#x192;"=>"á?&#x152;","ážž"=>"Î&#x2122;","áž?"=>"áž?","áž?"=>"ážš","áž°"=>"ី","ឧ"=>"áž?","áž?"=>"ណ","áž?"=>"áž­","ឤ"=>"áž?",
  875. "áž?"=>"áž?","áž?"=>"áž?","áž?"=>"ដ","áž&#x2014;"=>"áž&#x;","áž&#x2013;"=>"áž&#x17E;","áž&#x2022;"=>"áž?","áž&#x201D;"=>"áž&#x153;","áž&#x201C;"=>"áž&#x203A;","áž&#x2019;"=>"áž&#x161;","áž&#x2018;"=>"áž&#x2122;",
  876. "áž?"=>"áž&#x2DC;","áž&#x2021;"=>"áž?","áž&#x2020;"=>"áž&#x17D;","áž&#x2026;"=>"áž?","áž&#x201E;"=>"áž&#x152;","áž&#x192;"=>"áž&#x2039;","áž&#x201A;"=>"áž&#x160;","áž "=>"áž&#x2030;","áž&#x20AC;"=>"áž&#x2C6;","á??"=>"á??",
  877. "á??"=>"á??","á??"=>"á??","á??"=>"á??","á?š"=>"á?š","á?¸"=>"á?¸","á??"=>"á?&#x203A;","á??"=>"á?&#x161;","á??"=>"á?&#x2039;","á?´"=>"á?&#x160;","á??"=>"á?&#x2030;",
  878. "á??"=>"á?&#x2C6;","á??"=>"áž?","á?°"=>"áž?","á?§"=>"á??","á??"=>"á?Ž","á??"=>"á?­","á?¤"=>"á??","á??"=>"á??","á??"=>"á??","á??"=>"á?Š",
  879. "á?&#x2014;"=>"á?&#x;","á?&#x2022;"=>"á??","á?&#x201C;"=>"á?&#x203A;","á?&#x2018;"=>"á?&#x2122;","á?&#x2026;"=>"á??","á?&#x201E;"=>"á?&#x152;","á?&#x192;"=>"á?&#x2039;","á?&#x201A;"=>"á?&#x160;","á? "=>"á?&#x2030;","á?&#x20AC;"=>"á?&#x2C6;",
  880. "á??"=>"á??","á??"=>"á?ž","á??"=>"á??","á?´"=>"á??","á??"=>"á??","á??"=>"á??","á??"=>"á?š","á?°"=>"á?¸","á?§"=>"á??","á??"=>"á?Ž",
  881. "á??"=>"á?­","á?¤"=>"á??","á??"=>"á??","á??"=>"á??","á??"=>"á?Š","á?&#x2022;"=>"á??","á?&#x201D;"=>"á?&#x153;","á?&#x201C;"=>"á?&#x203A;","á?&#x2019;"=>"á?&#x161;","á?&#x2018;"=>"á?&#x2122;",
  882. "á??"=>"á?&#x2DC;","á?&#x2021;"=>"á??","á?&#x2020;"=>"á?&#x17D;","á?&#x2026;"=>"á??","á?&#x201E;"=>"á?&#x152;","á?&#x192;"=>"á?&#x2039;","á?&#x201A;"=>"á?&#x160;","á? "=>"á?&#x2030;","á?&#x20AC;"=>"á?&#x2C6;","á?š"=>"á?¸",
  883. "á??"=>"á??","á??"=>"á?´","á??"=>"á??","á??"=>"á?°","á??"=>"á?Ž","á?­"=>"á??","á??"=>"á??","á?Š"=>"á?¨","á?§"=>"á??","á??"=>"á?¤",
  884. "á??"=>"á??","á??"=>"á? ","á?&#x;"=>"á?&#x17E;","á??"=>"á?&#x153;","á?&#x203A;"=>"á?&#x161;","á?&#x2122;"=>"á?&#x2DC;","á?&#x2014;"=>"á?&#x2013;","á?&#x2022;"=>"á?&#x201D;","á?&#x201C;"=>"á?&#x2019;","á?&#x2018;"=>"á??",
  885. "á??"=>"á?&#x17D;","á??"=>"á?&#x152;","á?&#x2039;"=>"á?&#x160;","á?&#x2030;"=>"á?&#x2C6;","á?&#x2021;"=>"á?&#x2020;","á?&#x2026;"=>"á?&#x201E;","á?&#x192;"=>"á?&#x201A;","á? "=>"á?&#x20AC;","á??"=>"á?ž","á??"=>"á??",
  886. "á??"=>"á??","á?š"=>"á?¸","á??"=>"á??","á??"=>"á?´","á??"=>"á??","á??"=>"á?°","á??"=>"á?Ž","á?­"=>"á??","á??"=>"á??","á?Š"=>"á?¨",
  887. "á?§"=>"á??","á??"=>"á?¤","á??"=>"á??","á??"=>"á? ","á?&#x203A;"=>"áš ","á?&#x2022;"=>"á?&#x201D;","á?&#x201C;"=>"á?&#x2019;","á?&#x2018;"=>"á??","á??"=>"á?&#x17D;","á??"=>"á?&#x152;",
  888. "á?&#x2039;"=>"á?&#x160;","á?&#x2030;"=>"á?&#x2C6;","á?&#x2021;"=>"á?&#x2020;","á?&#x2026;"=>"á?&#x201E;","á?&#x192;"=>"á?&#x201A;","á? "=>"á?&#x20AC;","áš?"=>"ášž","áš?"=>"áš?","áš?"=>"áš?","ášš"=>"ᚸ",
  889. "�"=>"�","�"=>"ᚴ","�"=>"�","�"=>"ᚰ","�"=>"ᚎ","ᚭ"=>"�","�"=>"�","ᚊ"=>"ᚨ","ᚧ"=>"�","�"=>"ᚤ",
  890. "áš?"=>"áš?","áš?"=>"áš ","áš&#x;"=>"áš&#x17E;","áš?"=>"áš&#x153;","áš&#x203A;"=>"áš&#x161;","áš&#x2122;"=>"áš&#x2DC;","áš&#x2014;"=>"áš&#x2013;","áš&#x2022;"=>"áš&#x201D;","áš&#x201C;"=>"áš&#x2019;","áš&#x2018;"=>"áš?",
  891. "áš?"=>"áš&#x17D;","áš?"=>"áš&#x152;","áš&#x2039;"=>"áš&#x160;","áš&#x2030;"=>"áš&#x2C6;","áš&#x2021;"=>"áš&#x2020;","áš&#x2026;"=>"áš&#x201E;","áš&#x192;"=>"áš&#x201A;","áš "=>"áš&#x20AC;","á¸?"=>"Ḟ","á¸?"=>"á¸?",
  892. "�"=>"�","Ḛ"=>"Ḹ","�"=>"�","�"=>"Ḵ","�"=>"�","�"=>"Ḱ","�"=>"Ḏ","ḭ"=>"�","�"=>"�","Ḋ"=>"Ḩ",
  893. "ḧ"=>"á¸?","á¸?"=>"Ḥ","á¸?"=>"á¸?","á¸?"=>"Ḡ","á¸&#x;"=>"á¸&#x17E;","á¸?"=>"á¸&#x153;","á¸&#x203A;"=>"á¸&#x161;","á¸&#x2122;"=>"á¸&#x2DC;","á¸&#x2014;"=>"á¸&#x2013;","á¸&#x2022;"=>"á¸&#x201D;",
  894. "á¸&#x201C;"=>"á¸&#x2019;","á¸&#x2018;"=>"á¸?","á¸?"=>"á¸&#x17D;","á¸?"=>"á¸&#x152;","á¸&#x2039;"=>"á¸&#x160;","á¸&#x2030;"=>"á¸&#x2C6;","á¸&#x2021;"=>"á¸&#x2020;","á¸&#x2026;"=>"á¸&#x201E;","á¸&#x192;"=>"á¸&#x201A;","Ḡ"=>"á¸&#x20AC;",
  895. "Ö&#x2020;"=>"?&#x2013;","Ö&#x2026;"=>"?&#x2022;","Ö&#x201E;"=>"?&#x201D;","Ö&#x192;"=>"?&#x201C;","Ö&#x201A;"=>"?&#x2019;","Ö "=>"?&#x2018;","Ö&#x20AC;"=>"??","??"=>"??","?ž"=>"?&#x17D;","??"=>"??",
  896. "??"=>"?&#x152;","??"=>"?&#x2039;","??"=>"?&#x160;","?š"=>"?&#x2030;","?¸"=>"?&#x2C6;","??"=>"?&#x2021;","??"=>"?&#x2020;","??"=>"?&#x2026;","?´"=>"?&#x201E;","??"=>"?&#x192;",
  897. "??"=>"?&#x201A;","??"=>"? ","?°"=>"?&#x20AC;","??"=>"Ô?","?Ž"=>"Ôž","?­"=>"Ô?","??"=>"Ô?","??"=>"Ô?","??"=>"Ô?","?Š"=>"Ôš",
  898. "?¨"=>"Ô¸","?§"=>"Ô?","??"=>"Ô?","??"=>"Ô?","?¤"=>"Ô´","??"=>"Ô?","??"=>"Ô?","??"=>"Ô?","Ô?"=>"Ô&#x17D;","Ô?"=>"Ô&#x152;",
  899. "Ô&#x2039;"=>"Ô&#x160;","Ô&#x2030;"=>"Ô&#x2C6;","Ô&#x2021;"=>"Ô&#x2020;","Ô&#x2026;"=>"Ô&#x201E;","Ô&#x192;"=>"Ô&#x201A;","Ô "=>"Ô&#x20AC;","Óš"=>"Ó¸","Ó?"=>"Ó´","Ó?"=>"Ó?","Ó?"=>"Ó°",
  900. "Ó?"=>"ÓŽ","Ó­"=>"Ó?","Ó?"=>"Ó?","ÓŠ"=>"Ó¨","Ó§"=>"Ó?","Ó?"=>"Ó¤","Ó?"=>"Ó?","Ó?"=>"Ó ","Ó&#x;"=>"Ó&#x17E;","Ó?"=>"Ó&#x153;",
  901. "Ó&#x203A;"=>"Ó&#x161;","Ó&#x2122;"=>"Ó&#x2DC;","Ó&#x2014;"=>"Ó&#x2013;","Ó&#x2022;"=>"Ó&#x201D;","Ó&#x201C;"=>"Ó&#x2019;","Ó&#x2018;"=>"Ó?","Ó&#x17D;"=>"Ó?","Ó&#x152;"=>"Ó&#x2039;","Ó&#x160;"=>"Ó&#x2030;","Ó&#x2C6;"=>"Ó&#x2021;",
  902. "Ó&#x2020;"=>"Ó&#x2026;","Ó&#x201E;"=>"Ó&#x192;","Ó&#x201A;"=>"Ó ","??"=>"?ž","??"=>"??","??"=>"??","?š"=>"?¸","??"=>"??","??"=>"?´","??"=>"??",
  903. "??"=>"?°","??"=>"?Ž","?­"=>"??","??"=>"??","?Š"=>"?¨","?§"=>"??","??"=>"?¤","??"=>"??","??"=>"? ","?&#x;"=>"?&#x17E;",
  904. "??"=>"?&#x153;","?&#x203A;"=>"?&#x161;","?&#x2122;"=>"?&#x2DC;","?&#x2014;"=>"?&#x2013;","?&#x2022;"=>"?&#x201D;","?&#x201C;"=>"?&#x2019;","?&#x2018;"=>"??","??"=>"?&#x17D;","??"=>"?&#x152;","?&#x2039;"=>"?&#x160;",
  905. "? "=>"?&#x20AC;","??"=>"?ž","??"=>"??","??"=>"??","?š"=>"?¸","??"=>"??","??"=>"?´","??"=>"??","??"=>"?°","??"=>"?Ž",
  906. "?­"=>"??","??"=>"??","?Š"=>"?¨","?§"=>"??","??"=>"?¤","??"=>"??","??"=>"? ","?&#x;"=>"??","?&#x17E;"=>"?&#x17D;","??"=>"??",
  907. "?&#x153;"=>"?&#x152;","?&#x203A;"=>"?&#x2039;","?&#x161;"=>"?&#x160;","?&#x2122;"=>"?&#x2030;","?&#x2DC;"=>"?&#x2C6;","?&#x2014;"=>"?&#x2021;","?&#x2013;"=>"?&#x2020;","?&#x2022;"=>"?&#x2026;","?&#x201D;"=>"?&#x201E;","?&#x201C;"=>"?&#x192;",
  908. "?&#x2019;"=>"?&#x201A;","?&#x2018;"=>"? ","??"=>"?&#x20AC;","??"=>"??","?&#x17D;"=>"?Ž","??"=>"?­","?&#x152;"=>"??","?&#x2039;"=>"??","?&#x160;"=>"??","?&#x2030;"=>"?Š",
  909. "?&#x2C6;"=>"?¨","?&#x2021;"=>"?§","?&#x2020;"=>"??","?&#x2026;"=>"??","?&#x201E;"=>"?¤","?&#x192;"=>"??","?&#x201A;"=>"??","? "=>"??","?&#x20AC;"=>"? ","??"=>"?&#x;",
  910. "?ž"=>"?&#x17E;","??"=>"??","??"=>"?&#x153;","??"=>"?&#x203A;","??"=>"?&#x161;","?š"=>"?&#x2122;","?¸"=>"?&#x2DC;","??"=>"?&#x2014;","??"=>"?&#x2013;","??"=>"?&#x2022;",
  911. "?´"=>"?&#x201D;","??"=>"?&#x201C;","??"=>"?&#x2019;","??"=>"?&#x2018;","?°"=>"??","??"=>"Î&#x2022;","??"=>"Î?","??"=>"Î?","?°"=>"Î&#x161;","??"=>"?Ž",
  912. "?­"=>"??","??"=>"??","?Š"=>"?¨","?§"=>"??","??"=>"?¤","??"=>"??","??"=>"? ","?&#x;"=>"?&#x17E;","??"=>"?&#x153;","?&#x203A;"=>"?&#x161;",
  913. "?&#x2122;"=>"?&#x2DC;","?&#x2013;"=>"Π","?&#x2022;"=>"Î?","?&#x2018;"=>"Î&#x2DC;","??"=>"Î&#x2019;","?&#x17D;"=>"Î?","??"=>"Î&#x17D;","?&#x152;"=>"Î&#x152;","?&#x2039;"=>"Î?","?&#x160;"=>"Î?",
  914. "?&#x2030;"=>"Ί","?&#x2C6;"=>"Ψ","?&#x2021;"=>"Χ","?&#x2020;"=>"Î?","?&#x2026;"=>"Î?","?&#x201E;"=>"Τ","?&#x192;"=>"Î?","?&#x201A;"=>"Î?","? "=>"Î?","?&#x20AC;"=>"Π",
  915. "Î?"=>"Î&#x;","Ξ"=>"Î&#x17E;","Î?"=>"Î?","Î?"=>"Î&#x153;","Î?"=>"Î&#x203A;","Î?"=>"Î&#x161;","Κ"=>"Î&#x2122;","θ"=>"Î&#x2DC;","Î?"=>"Î&#x2014;","Î?"=>"Î&#x2013;",
  916. "Î?"=>"Î&#x2022;","δ"=>"Î&#x201D;","Î?"=>"Î&#x201C;","Î?"=>"Î&#x2019;","Î?"=>"Î&#x2018;","Î?"=>"Î&#x160;","ÎŽ"=>"Î&#x2030;","έ"=>"Î&#x2C6;","Î?"=>"Î&#x2020;","?&#x2019;"=>"??",
  917. "?&#x2039;"=>"??","?&#x160;"=>"??","?&#x2C6;"=>"?Ž","?&#x192;"=>"?Š","?&#x20AC;"=>"??","É?"=>"?&#x;","É?"=>"??","É?"=>"?&#x153;","ÉŠ"=>"?&#x2013;","ɨ"=>"?&#x2014;",
  918. "É?"=>"?&#x201D;","É&#x203A;"=>"??","É&#x2122;"=>"??","É&#x2014;"=>"?&#x160;","É&#x2013;"=>"?&#x2030;","É&#x201D;"=>"?&#x2020;","É&#x201C;"=>"? ","??"=>"??","??"=>"?°","??"=>"?Ž",
  919. "?­"=>"??","??"=>"??","?Š"=>"?¨","?§"=>"??","??"=>"?¤","??"=>"??","?&#x;"=>"?&#x17E;","??"=>"?&#x153;","?&#x203A;"=>"?&#x161;","?&#x2122;"=>"?&#x2DC;",
  920. "?&#x2014;"=>"?&#x2013;","?&#x2022;"=>"?&#x201D;","?&#x201C;"=>"?&#x2019;","?&#x2018;"=>"??","??"=>"?&#x17D;","??"=>"?&#x152;","?&#x2039;"=>"?&#x160;","?&#x2030;"=>"?&#x2C6;","?&#x2021;"=>"?&#x2020;","?&#x2026;"=>"?&#x201E;",
  921. "?&#x192;"=>"?&#x201A;","? "=>"?&#x20AC;","Ç?"=>"Çž","Ç?"=>"Ç?","Ç?"=>"Ç?","Çš"=>"Ǹ","Ç?"=>"Ç´","Ç?"=>"Ç?","Ç?"=>"ÇŽ","Ç­"=>"Ç?",
  922. "Ç?"=>"Ç?","ÇŠ"=>"Ǩ","ǧ"=>"Ç?","Ç?"=>"Ǥ","Ç?"=>"Ç?","Ç?"=>"Ç ","Ç&#x;"=>"Ç&#x17E;","Ç?"=>"?&#x17D;","Ç&#x153;"=>"Ç&#x203A;","Ç&#x161;"=>"Ç&#x2122;",
  923. "Ç&#x2DC;"=>"Ç&#x2014;","Ç&#x2013;"=>"Ç&#x2022;","Ç&#x201D;"=>"Ç&#x201C;","Ç&#x2019;"=>"Ç&#x2018;","Ç?"=>"Ç?","Ç&#x17D;"=>"Ç?","Ç&#x152;"=>"Ç&#x2039;","Ç&#x2030;"=>"Ç&#x2C6;","Ç&#x2020;"=>"Ç&#x2026;","??"=>"Ç?",
  924. "??"=>"??","?š"=>"?¸","??"=>"??","?´"=>"??","?°"=>"??","?­"=>"??","?¨"=>"?§","??"=>"?¤","??"=>"??","??"=>"? ",
  925. "?&#x17E;"=>"? ","?&#x2122;"=>"?&#x2DC;","?&#x2022;"=>"Ç?","?&#x2019;"=>"?&#x2018;","?&#x152;"=>"?&#x2039;","?&#x2C6;"=>"?&#x2021;","?&#x2026;"=>"?&#x201E;","?&#x192;"=>"?&#x201A;","??"=>"S","?ž"=>"??",
  926. "??"=>"??","??"=>"?š","??"=>"??","??"=>"?´","??"=>"??","??"=>"?°","??"=>"?Ž","?­"=>"??","??"=>"??","?Š"=>"?¨",
  927. "?§"=>"??","??"=>"?¤","??"=>"??","??"=>"? ","?&#x;"=>"?&#x17E;","??"=>"?&#x153;","?&#x203A;"=>"?&#x161;","?&#x2122;"=>"?&#x2DC;","?&#x2014;"=>"?&#x2013;","?&#x2022;"=>"?&#x201D;",
  928. "?&#x201C;"=>"?&#x2019;","?&#x2018;"=>"??","??"=>"?&#x17D;","??"=>"?&#x152;","?&#x2039;"=>"?&#x160;","?&#x2C6;"=>"?&#x2021;","?&#x2020;"=>"?&#x2026;","?&#x201E;"=>"?&#x192;","?&#x201A;"=>"? ","?&#x20AC;"=>"Ä?",
  929. "Äž"=>"Ä?","Ä?"=>"Ä?","Ä?"=>"Äš","Ä?"=>"Ä?","Ä?"=>"Ä´","Ä?"=>"Ä?","Ä?"=>"I","Ä?"=>"ÄŽ","Ä­"=>"Ä?","Ä?"=>"Ä?",
  930. "ÄŠ"=>"Ĩ","ħ"=>"Ä?","Ä?"=>"Ĥ","Ä?"=>"Ä?","Ä?"=>"Ä ","Ä&#x;"=>"Ä&#x17E;","Ä?"=>"Ä&#x153;","Ä&#x203A;"=>"Ä&#x161;","Ä&#x2122;"=>"Ä&#x2DC;","Ä&#x2014;"=>"Ä&#x2013;",
  931. "Ä&#x2022;"=>"Ä&#x201D;","Ä&#x201C;"=>"Ä&#x2019;","Ä&#x2018;"=>"Ä?","Ä?"=>"Ä&#x17D;","Ä?"=>"Ä&#x152;","Ä&#x2039;"=>"Ä&#x160;","Ä&#x2030;"=>"Ä&#x2C6;","Ä&#x2021;"=>"Ä&#x2020;","Ä&#x2026;"=>"Ä&#x201E;","Ä&#x192;"=>"Ä&#x201A;",
  932. "Ä "=>"Ä&#x20AC;","??"=>"?¸","?ž"=>"?&#x17E;","??"=>"??","??"=>"?&#x153;","??"=>"?&#x203A;","??"=>"?&#x161;","?š"=>"?&#x2122;","?¸"=>"?&#x2DC;","??"=>"?&#x2013;",
  933. "??"=>"?&#x2022;","?´"=>"?&#x201D;","??"=>"?&#x201C;","??"=>"?&#x2019;","??"=>"?&#x2018;","?°"=>"??","??"=>"??","?Ž"=>"?&#x17D;","?­"=>"??","??"=>"?&#x152;",
  934. "??"=>"?&#x2039;","??"=>"?&#x160;","?Š"=>"?&#x2030;","?¨"=>"?&#x2C6;","?§"=>"?&#x2021;","??"=>"?&#x2020;","??"=>"?&#x2026;","?¤"=>"?&#x201E;","??"=>"?&#x192;","??"=>"?&#x201A;",
  935. "??"=>"? ","? "=>"?&#x20AC;","Â?"=>"Î&#x153;","z"=>"Z","y"=>"Y","x"=>"X","w"=>"W","v"=>"V","u"=>"U","t"=>"T",
  936. "s"=>"S","r"=>"R","q"=>"Q","p"=>"P","o"=>"O","n"=>"N","m"=>"M","l"=>"L","k"=>"K","j"=>"J",
  937. "i"=>"I","h"=>"H","g"=>"G","f"=>"F","e"=>"E","d"=>"D","c"=>"C","b"=>"B","a"=>"A"
  938. );
  939. /**
  940. * UTF-8 Case lookup table
  941. *
  942. * This lookuptable defines the lower case letters to their corresponding
  943. * upper case letter in UTF-8
  944. *
  945. * @author Andreas Gohr <andi@splitbrain.org>
  946. */
  947. global $UTF8_UPPER_TO_LOWER;
  948. if(empty($UTF8_UPPER_TO_LOWER)) $UTF8_UPPER_TO_LOWER = array (
  949. "???"=>"??&#x161;","??š"=>"??&#x2122;","??¸"=>"??&#x2DC;","???"=>"??&#x2014;","???"=>"??&#x2013;","???"=>"??&#x2022;","??´"=>"??&#x201D;","???"=>"??&#x201C;","???"=>"??&#x2019;","???"=>"??&#x2018;",
  950. "??°"=>"???","???"=>"???","??Ž"=>"??&#x17D;","??­"=>"???","???"=>"??&#x152;","???"=>"??&#x2039;","???"=>"??&#x160;","??Š"=>"??&#x2030;","??¨"=>"??&#x2C6;","??§"=>"??&#x2021;",
  951. "???"=>"??&#x2020;","???"=>"??&#x2026;","??¤"=>"??&#x201E;","???"=>"??&#x192;","???"=>"??&#x201A;","???"=>"?? ","á??"=>"á??","á??"=>"á??","á?Š"=>"á??","á?&#x2122;"=>"á?&#x2018;",
  952. "á?&#x2DC;"=>"á??","á?&#x152;"=>"á?&#x192;","Î&#x2122;"=>"ážž","áž?"=>"áž?","ážš"=>"áž?","ី"=>"áž°","áž?"=>"ឧ","ណ"=>"áž?","áž­"=>"áž?","áž?"=>"ឤ",
  953. "áž?"=>"áž?","áž?"=>"áž?","ដ"=>"áž?","áž&#x;"=>"áž&#x2014;","áž&#x17E;"=>"áž&#x2013;","áž?"=>"áž&#x2022;","áž&#x153;"=>"áž&#x201D;","áž&#x203A;"=>"áž&#x201C;","áž&#x161;"=>"áž&#x2019;","áž&#x2122;"=>"áž&#x2018;",
  954. "áž&#x2DC;"=>"áž?","áž?"=>"áž&#x2021;","áž&#x17D;"=>"áž&#x2020;","áž?"=>"áž&#x2026;","áž&#x152;"=>"áž&#x201E;","áž&#x2039;"=>"áž&#x192;","áž&#x160;"=>"áž&#x201A;","áž&#x2030;"=>"áž ","áž&#x2C6;"=>"áž&#x20AC;","á??"=>"á??",
  955. "á??"=>"á??","á??"=>"á??","á??"=>"á??","á?š"=>"á?š","á?¸"=>"á?¸","á?&#x203A;"=>"á??","á?&#x161;"=>"á??","á?&#x2039;"=>"á??","á?&#x160;"=>"á?´","á?&#x2030;"=>"á??",
  956. "á?&#x2C6;"=>"á??","áž?"=>"á??","áž?"=>"á?°","á??"=>"á?§","á?Ž"=>"á??","á?­"=>"á??","á??"=>"á?¤","á??"=>"á??","á??"=>"á??","á?Š"=>"á??",
  957. "á?&#x;"=>"á?&#x2014;","á??"=>"á?&#x2022;","á?&#x203A;"=>"á?&#x201C;","á?&#x2122;"=>"á?&#x2018;","á??"=>"á?&#x2026;","á?&#x152;"=>"á?&#x201E;","á?&#x2039;"=>"á?&#x192;","á?&#x160;"=>"á?&#x201A;","á?&#x2030;"=>"á? ","á?&#x2C6;"=>"á?&#x20AC;",
  958. "á??"=>"á??","á?ž"=>"á??","á??"=>"á??","á??"=>"á?´","á??"=>"á??","á??"=>"á??","á?š"=>"á??","á?¸"=>"á?°","á??"=>"á?§","á?Ž"=>"á??",
  959. "á?­"=>"á??","á??"=>"á?¤","á??"=>"á??","á??"=>"á??","á?Š"=>"á??","á??"=>"á?&#x2022;","á?&#x153;"=>"á?&#x201D;","á?&#x203A;"=>"á?&#x201C;","á?&#x161;"=>"á?&#x2019;","á?&#x2122;"=>"á?&#x2018;",
  960. "á?&#x2DC;"=>"á??","á??"=>"á?&#x2021;","á?&#x17D;"=>"á?&#x2020;","á??"=>"á?&#x2026;","á?&#x152;"=>"á?&#x201E;","á?&#x2039;"=>"á?&#x192;","á?&#x160;"=>"á?&#x201A;","á?&#x2030;"=>"á? ","á?&#x2C6;"=>"á?&#x20AC;","á?¸"=>"á?š",
  961. "á??"=>"á??","á?´"=>"á??","á??"=>"á??","á?°"=>"á??","á?Ž"=>"á??","á??"=>"á?­","á??"=>"á??","á?¨"=>"á?Š","á??"=>"á?§","á?¤"=>"á??",
  962. "á??"=>"á??","á? "=>"á??","á?&#x17E;"=>"á?&#x;","á?&#x153;"=>"á??","á?&#x161;"=>"á?&#x203A;","á?&#x2DC;"=>"á?&#x2122;","á?&#x2013;"=>"á?&#x2014;","á?&#x201D;"=>"á?&#x2022;","á?&#x2019;"=>"á?&#x201C;","á??"=>"á?&#x2018;",
  963. "á?&#x17D;"=>"á??","á?&#x152;"=>"á??","á?&#x160;"=>"á?&#x2039;","á?&#x2C6;"=>"á?&#x2030;","á?&#x2020;"=>"á?&#x2021;","á?&#x201E;"=>"á?&#x2026;","á?&#x201A;"=>"á?&#x192;","á?&#x20AC;"=>"á? ","á?ž"=>"á??","á??"=>"á??",
  964. "á??"=>"á??","á?¸"=>"á?š","á??"=>"á??","á?´"=>"á??","á??"=>"á??","á?°"=>"á??","á?Ž"=>"á??","á??"=>"á?­","á??"=>"á??","á?¨"=>"á?Š",
  965. "á??"=>"á?§","á?¤"=>"á??","á??"=>"á??","á? "=>"á??","áš "=>"á?&#x203A;","á?&#x201D;"=>"á?&#x2022;","á?&#x2019;"=>"á?&#x201C;","á??"=>"á?&#x2018;","á?&#x17D;"=>"á??","á?&#x152;"=>"á??",
  966. "á?&#x160;"=>"á?&#x2039;","á?&#x2C6;"=>"á?&#x2030;","á?&#x2020;"=>"á?&#x2021;","á?&#x201E;"=>"á?&#x2026;","á?&#x201A;"=>"á?&#x192;","á?&#x20AC;"=>"á? ","ášž"=>"áš?","áš?"=>"áš?","áš?"=>"áš?","ᚸ"=>"ášš",
  967. "�"=>"�","ᚴ"=>"�","�"=>"�","ᚰ"=>"�","ᚎ"=>"�","�"=>"ᚭ","�"=>"�","ᚨ"=>"ᚊ","�"=>"ᚧ","ᚤ"=>"�",
  968. "áš?"=>"áš?","áš "=>"áš?","áš&#x17E;"=>"áš&#x;","áš&#x153;"=>"áš?","áš&#x161;"=>"áš&#x203A;","áš&#x2DC;"=>"áš&#x2122;","áš&#x2013;"=>"áš&#x2014;","áš&#x201D;"=>"áš&#x2022;","áš&#x2019;"=>"áš&#x201C;","áš?"=>"áš&#x2018;",
  969. "áš&#x17D;"=>"áš?","áš&#x152;"=>"áš?","áš&#x160;"=>"áš&#x2039;","áš&#x2C6;"=>"áš&#x2030;","áš&#x2020;"=>"áš&#x2021;","áš&#x201E;"=>"áš&#x2026;","áš&#x201A;"=>"áš&#x192;","áš&#x20AC;"=>"áš ","Ḟ"=>"á¸?","á¸?"=>"á¸?",
  970. "�"=>"�","Ḹ"=>"Ḛ","�"=>"�","Ḵ"=>"�","�"=>"�","Ḱ"=>"�","Ḏ"=>"�","�"=>"ḭ","�"=>"�","Ḩ"=>"Ḋ",
  971. "á¸?"=>"ḧ","Ḥ"=>"á¸?","á¸?"=>"á¸?","Ḡ"=>"á¸?","á¸&#x17E;"=>"á¸&#x;","á¸&#x153;"=>"á¸?","á¸&#x161;"=>"á¸&#x203A;","á¸&#x2DC;"=>"á¸&#x2122;","á¸&#x2013;"=>"á¸&#x2014;","á¸&#x201D;"=>"á¸&#x2022;",
  972. "á¸&#x2019;"=>"á¸&#x201C;","á¸?"=>"á¸&#x2018;","á¸&#x17D;"=>"á¸?","á¸&#x152;"=>"á¸?","á¸&#x160;"=>"á¸&#x2039;","á¸&#x2C6;"=>"á¸&#x2030;","á¸&#x2020;"=>"á¸&#x2021;","á¸&#x201E;"=>"á¸&#x2026;","á¸&#x201A;"=>"á¸&#x192;","á¸&#x20AC;"=>"Ḡ",
  973. "?&#x2013;"=>"Ö&#x2020;","?&#x2022;"=>"Ö&#x2026;","?&#x201D;"=>"Ö&#x201E;","?&#x201C;"=>"Ö&#x192;","?&#x2019;"=>"Ö&#x201A;","?&#x2018;"=>"Ö ","??"=>"Ö&#x20AC;","??"=>"??","?&#x17D;"=>"?ž","??"=>"??",
  974. "?&#x152;"=>"??","?&#x2039;"=>"??","?&#x160;"=>"??","?&#x2030;"=>"?š","?&#x2C6;"=>"?¸","?&#x2021;"=>"??","?&#x2020;"=>"??","?&#x2026;"=>"??","?&#x201E;"=>"?´","?&#x192;"=>"??",
  975. "?&#x201A;"=>"??","? "=>"??","?&#x20AC;"=>"?°","Ô?"=>"??","Ôž"=>"?Ž","Ô?"=>"?­","Ô?"=>"??","Ô?"=>"??","Ô?"=>"??","Ôš"=>"?Š",
  976. "Ô¸"=>"?¨","Ô?"=>"?§","Ô?"=>"??","Ô?"=>"??","Ô´"=>"?¤","Ô?"=>"??","Ô?"=>"??","Ô?"=>"??","Ô&#x17D;"=>"Ô?","Ô&#x152;"=>"Ô?",
  977. "Ô&#x160;"=>"Ô&#x2039;","Ô&#x2C6;"=>"Ô&#x2030;","Ô&#x2020;"=>"Ô&#x2021;","Ô&#x201E;"=>"Ô&#x2026;","Ô&#x201A;"=>"Ô&#x192;","Ô&#x20AC;"=>"Ô ","Ó¸"=>"Óš","Ó´"=>"Ó?","Ó?"=>"Ó?","Ó°"=>"Ó?",
  978. "ÓŽ"=>"Ó?","Ó?"=>"Ó­","Ó?"=>"Ó?","Ó¨"=>"ÓŠ","Ó?"=>"Ó§","Ó¤"=>"Ó?","Ó?"=>"Ó?","Ó "=>"Ó?","Ó&#x17E;"=>"Ó&#x;","Ó&#x153;"=>"Ó?",
  979. "Ó&#x161;"=>"Ó&#x203A;","Ó&#x2DC;"=>"Ó&#x2122;","Ó&#x2013;"=>"Ó&#x2014;","Ó&#x201D;"=>"Ó&#x2022;","Ó&#x2019;"=>"Ó&#x201C;","Ó?"=>"Ó&#x2018;","Ó?"=>"Ó&#x17D;","Ó&#x2039;"=>"Ó&#x152;","Ó&#x2030;"=>"Ó&#x160;","Ó&#x2021;"=>"Ó&#x2C6;",
  980. "Ó&#x2026;"=>"Ó&#x2020;","Ó&#x192;"=>"Ó&#x201E;","Ó "=>"Ó&#x201A;","?ž"=>"??","??"=>"??","??"=>"??","?¸"=>"?š","??"=>"??","?´"=>"??","??"=>"??",
  981. "?°"=>"??","?Ž"=>"??","??"=>"?­","??"=>"??","?¨"=>"?Š","??"=>"?§","?¤"=>"??","??"=>"??","? "=>"??","?&#x17E;"=>"?&#x;",
  982. "?&#x153;"=>"??","?&#x161;"=>"?&#x203A;","?&#x2DC;"=>"?&#x2122;","?&#x2013;"=>"?&#x2014;","?&#x201D;"=>"?&#x2022;","?&#x2019;"=>"?&#x201C;","??"=>"?&#x2018;","?&#x17D;"=>"??","?&#x152;"=>"??","?&#x160;"=>"?&#x2039;",
  983. "?&#x20AC;"=>"? ","?ž"=>"??","??"=>"??","??"=>"??","?¸"=>"?š","??"=>"??","?´"=>"??","??"=>"??","?°"=>"??","?Ž"=>"??",
  984. "??"=>"?­","??"=>"??","?¨"=>"?Š","??"=>"?§","?¤"=>"??","??"=>"??","? "=>"??","??"=>"?&#x;","?&#x17D;"=>"?&#x17E;","??"=>"??",
  985. "?&#x152;"=>"?&#x153;","?&#x2039;"=>"?&#x203A;","?&#x160;"=>"?&#x161;","?&#x2030;"=>"?&#x2122;","?&#x2C6;"=>"?&#x2DC;","?&#x2021;"=>"?&#x2014;","?&#x2020;"=>"?&#x2013;","?&#x2026;"=>"?&#x2022;","?&#x201E;"=>"?&#x201D;","?&#x192;"=>"?&#x201C;",
  986. "?&#x201A;"=>"?&#x2019;","? "=>"?&#x2018;","?&#x20AC;"=>"??","??"=>"??","?Ž"=>"?&#x17D;","?­"=>"??","??"=>"?&#x152;","??"=>"?&#x2039;","??"=>"?&#x160;","?Š"=>"?&#x2030;",
  987. "?¨"=>"?&#x2C6;","?§"=>"?&#x2021;","??"=>"?&#x2020;","??"=>"?&#x2026;","?¤"=>"?&#x201E;","??"=>"?&#x192;","??"=>"?&#x201A;","??"=>"? ","? "=>"?&#x20AC;","?&#x;"=>"??",
  988. "?&#x17E;"=>"?ž","??"=>"??","?&#x153;"=>"??","?&#x203A;"=>"??","?&#x161;"=>"??","?&#x2122;"=>"?š","?&#x2DC;"=>"?¸","?&#x2014;"=>"??","?&#x2013;"=>"??","?&#x2022;"=>"??",
  989. "?&#x201D;"=>"?´","?&#x201C;"=>"??","?&#x2019;"=>"??","?&#x2018;"=>"??","??"=>"?°","Î&#x2022;"=>"??","Î?"=>"??","Î?"=>"??","Î&#x161;"=>"?°","?Ž"=>"??",
  990. "??"=>"?­","??"=>"??","?¨"=>"?Š","??"=>"?§","?¤"=>"??","??"=>"??","? "=>"??","?&#x17E;"=>"?&#x;","?&#x153;"=>"??","?&#x161;"=>"?&#x203A;",
  991. "?&#x2DC;"=>"?&#x2122;","Π"=>"?&#x2013;","Î?"=>"?&#x2022;","Î&#x2DC;"=>"?&#x2018;","Î&#x2019;"=>"??","Î?"=>"?&#x17D;","Î&#x17D;"=>"??","Î&#x152;"=>"?&#x152;","Î?"=>"?&#x2039;","Î?"=>"?&#x160;",
  992. "Ί"=>"?&#x2030;","Ψ"=>"?&#x2C6;","Χ"=>"?&#x2021;","Î?"=>"?&#x2020;","Î?"=>"?&#x2026;","Τ"=>"?&#x201E;","Î?"=>"?&#x192;","Î?"=>"?&#x201A;","Î?"=>"? ","Π"=>"?&#x20AC;",
  993. "Î&#x;"=>"Î?","Î&#x17E;"=>"Ξ","Î?"=>"Î?","Î&#x153;"=>"Î?","Î&#x203A;"=>"Î?","Î&#x161;"=>"Î?","Î&#x2122;"=>"Κ","Î&#x2DC;"=>"θ","Î&#x2014;"=>"Î?","Î&#x2013;"=>"Î?",
  994. "Î&#x2022;"=>"Î?","Î&#x201D;"=>"δ","Î&#x201C;"=>"Î?","Î&#x2019;"=>"Î?","Î&#x2018;"=>"Î?","Î&#x160;"=>"Î?","Î&#x2030;"=>"ÎŽ","Î&#x2C6;"=>"έ","Î&#x2020;"=>"Î?","??"=>"?&#x2019;",
  995. "??"=>"?&#x2039;","??"=>"?&#x160;","?Ž"=>"?&#x2C6;","?Š"=>"?&#x192;","??"=>"?&#x20AC;","?&#x;"=>"É?","??"=>"É?","?&#x153;"=>"É?","?&#x2013;"=>"ÉŠ","?&#x2014;"=>"ɨ",
  996. "?&#x201D;"=>"É?","??"=>"É&#x203A;","??"=>"É&#x2122;","?&#x160;"=>"É&#x2014;","?&#x2030;"=>"É&#x2013;","?&#x2020;"=>"É&#x201D;","? "=>"É&#x201C;","??"=>"??","?°"=>"??","?Ž"=>"??",
  997. "??"=>"?­","??"=>"??","?¨"=>"?Š","??"=>"?§","?¤"=>"??","??"=>"??","?&#x17E;"=>"?&#x;","?&#x153;"=>"??","?&#x161;"=>"?&#x203A;","?&#x2DC;"=>"?&#x2122;",
  998. "?&#x2013;"=>"?&#x2014;","?&#x201D;"=>"?&#x2022;","?&#x2019;"=>"?&#x201C;","??"=>"?&#x2018;","?&#x17D;"=>"??","?&#x152;"=>"??","?&#x160;"=>"?&#x2039;","?&#x2C6;"=>"?&#x2030;","?&#x2020;"=>"?&#x2021;","?&#x201E;"=>"?&#x2026;",
  999. "?&#x201A;"=>"?&#x192;","?&#x20AC;"=>"? ","Çž"=>"Ç?","Ç?"=>"Ç?","Ç?"=>"Ç?","Ǹ"=>"Çš","Ç´"=>"Ç?","Ç?"=>"Ç?","ÇŽ"=>"Ç?","Ç?"=>"Ç­",
  1000. "Ç?"=>"Ç?","Ǩ"=>"ÇŠ","Ç?"=>"ǧ","Ǥ"=>"Ç?","Ç?"=>"Ç?","Ç "=>"Ç?","Ç&#x17E;"=>"Ç&#x;","?&#x17D;"=>"Ç?","Ç&#x203A;"=>"Ç&#x153;","Ç&#x2122;"=>"Ç&#x161;",
  1001. "Ç&#x2014;"=>"Ç&#x2DC;","Ç&#x2022;"=>"Ç&#x2013;","Ç&#x201C;"=>"Ç&#x201D;","Ç&#x2018;"=>"Ç&#x2019;","Ç?"=>"Ç?","Ç?"=>"Ç&#x17D;","Ç&#x2039;"=>"Ç&#x152;","Ç&#x2C6;"=>"Ç&#x2030;","Ç&#x2026;"=>"Ç&#x2020;","Ç?"=>"??",
  1002. "??"=>"??","?¸"=>"?š","??"=>"??","??"=>"?´","??"=>"?°","??"=>"?­","?§"=>"?¨","?¤"=>"??","??"=>"??","? "=>"??",
  1003. "? "=>"?&#x17E;","?&#x2DC;"=>"?&#x2122;","Ç?"=>"?&#x2022;","?&#x2018;"=>"?&#x2019;","?&#x2039;"=>"?&#x152;","?&#x2021;"=>"?&#x2C6;","?&#x201E;"=>"?&#x2026;","?&#x201A;"=>"?&#x192;","S"=>"??","??"=>"?ž",
  1004. "??"=>"??","?š"=>"??","??"=>"??","?´"=>"??","??"=>"??","?°"=>"??","?Ž"=>"??","??"=>"?­","??"=>"??","?¨"=>"?Š",
  1005. "??"=>"?§","?¤"=>"??","??"=>"??","? "=>"??","?&#x17E;"=>"?&#x;","?&#x153;"=>"??","?&#x161;"=>"?&#x203A;","?&#x2DC;"=>"?&#x2122;","?&#x2013;"=>"?&#x2014;","?&#x201D;"=>"?&#x2022;",
  1006. "?&#x2019;"=>"?&#x201C;","??"=>"?&#x2018;","?&#x17D;"=>"??","?&#x152;"=>"??","?&#x160;"=>"?&#x2039;","?&#x2021;"=>"?&#x2C6;","?&#x2026;"=>"?&#x2020;","?&#x192;"=>"?&#x201E;","? "=>"?&#x201A;","Ä?"=>"?&#x20AC;",
  1007. "Ä?"=>"Äž","Ä?"=>"Ä?","Äš"=>"Ä?","Ä?"=>"Ä?","Ä´"=>"Ä?","Ä?"=>"Ä?","I"=>"Ä?","ÄŽ"=>"Ä?","Ä?"=>"Ä­","Ä?"=>"Ä?",
  1008. "Ĩ"=>"ÄŠ","Ä?"=>"ħ","Ĥ"=>"Ä?","Ä?"=>"Ä?","Ä "=>"Ä?","Ä&#x17E;"=>"Ä&#x;","Ä&#x153;"=>"Ä?","Ä&#x161;"=>"Ä&#x203A;","Ä&#x2DC;"=>"Ä&#x2122;","Ä&#x2013;"=>"Ä&#x2014;",
  1009. "Ä&#x201D;"=>"Ä&#x2022;","Ä&#x2019;"=>"Ä&#x201C;","Ä?"=>"Ä&#x2018;","Ä&#x17D;"=>"Ä?","Ä&#x152;"=>"Ä?","Ä&#x160;"=>"Ä&#x2039;","Ä&#x2C6;"=>"Ä&#x2030;","Ä&#x2020;"=>"Ä&#x2021;","Ä&#x201E;"=>"Ä&#x2026;","Ä&#x201A;"=>"Ä&#x192;",
  1010. "Ä&#x20AC;"=>"Ä ","?¸"=>"??","?&#x17E;"=>"?ž","??"=>"??","?&#x153;"=>"??","?&#x203A;"=>"??","?&#x161;"=>"??","?&#x2122;"=>"?š","?&#x2DC;"=>"?¸","?&#x2013;"=>"??",
  1011. "?&#x2022;"=>"??","?&#x201D;"=>"?´","?&#x201C;"=>"??","?&#x2019;"=>"??","?&#x2018;"=>"??","??"=>"?°","??"=>"??","?&#x17D;"=>"?Ž","??"=>"?­","?&#x152;"=>"??",
  1012. "?&#x2039;"=>"??","?&#x160;"=>"??","?&#x2030;"=>"?Š","?&#x2C6;"=>"?¨","?&#x2021;"=>"?§","?&#x2020;"=>"??","?&#x2026;"=>"??","?&#x201E;"=>"?¤","?&#x192;"=>"??","?&#x201A;"=>"??",
  1013. "? "=>"??","?&#x20AC;"=>"? ","Î&#x153;"=>"Â?","Z"=>"z","Y"=>"y","X"=>"x","W"=>"w","V"=>"v","U"=>"u","T"=>"t",
  1014. "S"=>"s","R"=>"r","Q"=>"q","P"=>"p","O"=>"o","N"=>"n","M"=>"m","L"=>"l","K"=>"k","J"=>"j",
  1015. "I"=>"i","H"=>"h","G"=>"g","F"=>"f","E"=>"e","D"=>"d","C"=>"c","B"=>"b","A"=>"a"
  1016. );
  1017. }; // end of case lookup tables
  1018. /**
  1019. * UTF-8 lookup table for lower case accented letters
  1020. *
  1021. * This lookuptable defines replacements for accented characters from the ASCII-7
  1022. * range. This are lower case letters only.
  1023. *
  1024. * @author Andreas Gohr <andi@splitbrain.org>
  1025. * @see utf8_deaccent()
  1026. */
  1027. global $UTF8_LOWER_ACCENTS;
  1028. if(empty($UTF8_LOWER_ACCENTS)) $UTF8_LOWER_ACCENTS = array(
  1029. '? ' => 'a', '?´' => 'o', 'Ä?' => 'd', 'á¸&#x;' => 'f', '??' => 'e', '??' => 's', '??' => 'o',
  1030. '?&#x;' => 'ss', 'Ä&#x192;' => 'a', '?&#x2122;' => 'r', '?&#x203A;' => 't', '?&#x2C6;' => 'n', 'Ä ' => 'a', 'Ä?' => 'k',
  1031. '??' => 's', 'á??' => 'y', '?&#x2020;' => 'n', 'Ä?' => 'l', 'ħ' => 'h', 'áš&#x2014;' => 'p', '??' => 'o',
  1032. '??' => 'u', 'Ä&#x203A;' => 'e', '?Š' => 'e', '?§' => 'c', 'á? ' => 'w', 'Ä&#x2039;' => 'c', '??' => 'o',
  1033. 'áš?' => 's', '?¸' => 'o', 'Ä?' => 'g', '?§' => 't', '?&#x2122;' => 's', 'Ä&#x2014;' => 'e', 'Ä&#x2030;' => 'c',
  1034. '?&#x203A;' => 's', '?Ž' => 'i', '??' => 'u', 'Ä&#x2021;' => 'c', 'Ä&#x2122;' => 'e', '??' => 'w', 'áš?' => 't',
  1035. '??' => 'u', 'Ä?' => 'c', '??' => 'oe', '?¨' => 'e', '??' => 'y', 'Ä&#x2026;' => 'a', '?&#x201A;' => 'l',
  1036. '??' => 'u', '??' => 'u', '?&#x;' => 's', 'Ä&#x;' => 'g', 'Ä?' => 'l', '?&#x2019;' => 'f', '?ž' => 'z',
  1037. 'á?&#x192;' => 'w', 'á¸&#x192;' => 'b', '??' => 'a', '??' => 'i', '??' => 'i', 'á¸&#x2039;' => 'd', '??' => 't',
  1038. '?&#x2014;' => 'r', '?¤' => 'ae', '?­' => 'i', '?&#x2022;' => 'r', '??' => 'e', '??' => 'ue', '??' => 'o',
  1039. 'Ä&#x201C;' => 'e', '??' => 'n', '?&#x201E;' => 'n', 'Ä?' => 'h', 'Ä?' => 'g', 'Ä&#x2018;' => 'd', 'Ä?' => 'j',
  1040. '??' => 'y', '?Š' => 'u', '?­' => 'u', '?°' => 'u', '??' => 't', '??' => 'y', '?&#x2018;' => 'o',
  1041. '??' => 'a', 'Äž' => 'l', 'á?&#x2026;' => 'w', '??' => 'z', 'Ä?' => 'i', '??' => 'a', 'Ä?' => 'g',
  1042. 'áš ' => 'm', '??' => 'o', 'ÄŠ' => 'i', '?š' => 'u', 'Ä?' => 'i', '??' => 'z', '??' => 'a',
  1043. '??' => 'u', '?ž' => 'th', '?°' => 'dh', '??' => 'ae', 'Â?' => 'u', 'Ä&#x2022;' => 'e',
  1044. );
  1045. /**
  1046. * UTF-8 lookup table for upper case accented letters
  1047. *
  1048. * This lookuptable defines replacements for accented characters from the ASCII-7
  1049. * range. This are upper case letters only.
  1050. *
  1051. * @author Andreas Gohr <andi@splitbrain.org>
  1052. * @see utf8_deaccent()
  1053. */
  1054. global $UTF8_UPPER_ACCENTS;
  1055. if(empty($UTF8_UPPER_ACCENTS)) $UTF8_UPPER_ACCENTS = array(
  1056. '?&#x20AC;' => 'A', '?&#x201D;' => 'O', 'Ä&#x17D;' => 'D', 'á¸&#x17E;' => 'F', '?&#x2039;' => 'E', '? ' => 'S', '? ' => 'O',
  1057. 'Ä&#x201A;' => 'A', '?&#x2DC;' => 'R', '?&#x161;' => 'T', '?&#x2021;' => 'N', 'Ä&#x20AC;' => 'A', 'Ä?' => 'K',
  1058. '?&#x153;' => 'S', 'á??' => 'Y', '?&#x2026;' => 'N', 'Äš' => 'L', 'Ä?' => 'H', 'áš&#x2013;' => 'P', '?&#x201C;' => 'O',
  1059. '?&#x161;' => 'U', 'Ä&#x161;' => 'E', '?&#x2030;' => 'E', '?&#x2021;' => 'C', 'á?&#x20AC;' => 'W', 'Ä&#x160;' => 'C', '?&#x2022;' => 'O',
  1060. 'áš ' => 'S', '?&#x2DC;' => 'O', 'Ä?' => 'G', '??' => 'T', '?&#x2DC;' => 'S', 'Ä&#x2013;' => 'E', 'Ä&#x2C6;' => 'C',
  1061. '?&#x161;' => 'S', '?&#x17D;' => 'I', '?°' => 'U', 'Ä&#x2020;' => 'C', 'Ä&#x2DC;' => 'E', '?´' => 'W', 'áš?' => 'T',
  1062. '??' => 'U', 'Ä&#x152;' => 'C', '?&#x2013;' => 'Oe', '?&#x2C6;' => 'E', '??' => 'Y', 'Ä&#x201E;' => 'A', '? ' => 'L',
  1063. '??' => 'U', '?Ž' => 'U', '?&#x17E;' => 'S', 'Ä&#x17E;' => 'G', 'Ä?' => 'L', '?&#x2018;' => 'F', '??' => 'Z',
  1064. 'á?&#x201A;' => 'W', 'á¸&#x201A;' => 'B', '?&#x2026;' => 'A', '?&#x152;' => 'I', '??' => 'I', 'á¸&#x160;' => 'D', '?¤' => 'T',
  1065. '?&#x2013;' => 'R', '?&#x201E;' => 'Ae', '??' => 'I', '?&#x201D;' => 'R', '?&#x160;' => 'E', '?&#x153;' => 'Ue', '?&#x2019;' => 'O',
  1066. 'Ä&#x2019;' => 'E', '?&#x2018;' => 'N', '?&#x192;' => 'N', 'Ĥ' => 'H', 'Ä&#x153;' => 'G', 'Ä?' => 'D', 'Ä´' => 'J',
  1067. '?¸' => 'Y', '?¨' => 'U', '??' => 'U', '??' => 'U', '??' => 'T', '??' => 'Y', '??' => 'O',
  1068. '?&#x201A;' => 'A', 'Ä?' => 'L', 'á?&#x201E;' => 'W', '??' => 'Z', 'Ä?' => 'I', '?&#x192;' => 'A', 'Ä ' => 'G',
  1069. 'áš&#x20AC;' => 'M', '?&#x152;' => 'O', 'Ĩ' => 'I', '?&#x2122;' => 'U', 'ÄŽ' => 'I', '?š' => 'Z', '? ' => 'A',
  1070. '?&#x203A;' => 'U', '?&#x17E;' => 'Th', '??' => 'Dh', '?&#x2020;' => 'Ae', 'Ä&#x201D;' => 'E',
  1071. );
  1072. /**
  1073. * UTF-8 array of common special characters
  1074. *
  1075. * This array should contain all special characters (not a letter or digit)
  1076. * defined in the various local charsets - it's not a complete list of non-alphanum
  1077. * characters in UTF-8. It's not perfect but should match most cases of special
  1078. * chars.
  1079. *
  1080. * The controlchars 0x00 to 0x19 are _not_ included in this array. The space 0x20 is!
  1081. * These chars are _not_ in the array either: _ (0x5f), : 0x3a, . 0x2e, - 0x2d, * 0x2a
  1082. *
  1083. * @author Andreas Gohr <andi@splitbrain.org>
  1084. * @see utf8_stripspecials()
  1085. */
  1086. global $UTF8_SPECIAL_CHARS;
  1087. if(empty($UTF8_SPECIAL_CHARS)) $UTF8_SPECIAL_CHARS = array(
  1088. 0x001a, 0x001b, 0x001c, 0x001d, 0x001e, 0x001f, 0x0020, 0x0021, 0x0022, 0x0023,
  1089. 0x0024, 0x0025, 0x0026, 0x0027, 0x0028, 0x0029, 0x002b, 0x002c,
  1090. 0x002f, 0x003b, 0x003c, 0x003d, 0x003e, 0x003f, 0x0040, 0x005b,
  1091. 0x005c, 0x005d, 0x005e, 0x0060, 0x007b, 0x007c, 0x007d, 0x007e,
  1092. 0x007f, 0x0080, 0x0081, 0x0082, 0x0083, 0x0084, 0x0085, 0x0086, 0x0087, 0x0088,
  1093. 0x0089, 0x008a, 0x008b, 0x008c, 0x008d, 0x008e, 0x008f, 0x0090, 0x0091, 0x0092,
  1094. 0x0093, 0x0094, 0x0095, 0x0096, 0x0097, 0x0098, 0x0099, 0x009a, 0x009b, 0x009c,
  1095. 0x009d, 0x009e, 0x009f, 0x00a0, 0x00a1, 0x00a2, 0x00a3, 0x00a4, 0x00a5, 0x00a6,
  1096. 0x00a7, 0x00a8, 0x00a9, 0x00aa, 0x00ab, 0x00ac, 0x00ad, 0x00ae, 0x00af, 0x00b0,
  1097. 0x00b1, 0x00b2, 0x00b3, 0x00b4, 0x00b5, 0x00b6, 0x00b7, 0x00b8, 0x00b9, 0x00ba,
  1098. 0x00bb, 0x00bc, 0x00bd, 0x00be, 0x00bf, 0x00d7, 0x00f7, 0x02c7, 0x02d8, 0x02d9,
  1099. 0x02da, 0x02db, 0x02dc, 0x02dd, 0x0300, 0x0301, 0x0303, 0x0309, 0x0323, 0x0384,
  1100. 0x0385, 0x0387, 0x03c6, 0x03d1, 0x03d2, 0x03d5, 0x03d6, 0x05b0, 0x05b1,
  1101. 0x05b2, 0x05b3, 0x05b4, 0x05b5, 0x05b6, 0x05b7, 0x05b8, 0x05b9, 0x05bb, 0x05bc,
  1102. 0x05bd, 0x05be, 0x05bf, 0x05c0, 0x05c1, 0x05c2, 0x05c3, 0x05f3, 0x05f4, 0x060c,
  1103. 0x061b, 0x061f, 0x0640, 0x064b, 0x064c, 0x064d, 0x064e, 0x064f, 0x0650, 0x0651,
  1104. 0x0652, 0x066a, 0x0e3f, 0x200c, 0x200d, 0x200e, 0x200f, 0x2013, 0x2014, 0x2015,
  1105. 0x2017, 0x2018, 0x2019, 0x201a, 0x201c, 0x201d, 0x201e, 0x2020, 0x2021, 0x2022,
  1106. 0x2026, 0x2030, 0x2032, 0x2033, 0x2039, 0x203a, 0x2044, 0x20a7, 0x20aa, 0x20ab,
  1107. 0x20ac, 0x2116, 0x2118, 0x2122, 0x2126, 0x2135, 0x2190, 0x2191, 0x2192, 0x2193,
  1108. 0x2194, 0x2195, 0x21b5, 0x21d0, 0x21d1, 0x21d2, 0x21d3, 0x21d4, 0x2200, 0x2202,
  1109. 0x2203, 0x2205, 0x2206, 0x2207, 0x2208, 0x2209, 0x220b, 0x220f, 0x2211, 0x2212,
  1110. 0x2215, 0x2217, 0x2219, 0x221a, 0x221d, 0x221e, 0x2220, 0x2227, 0x2228, 0x2229,
  1111. 0x222a, 0x222b, 0x2234, 0x223c, 0x2245, 0x2248, 0x2260, 0x2261, 0x2264, 0x2265,
  1112. 0x2282, 0x2283, 0x2284, 0x2286, 0x2287, 0x2295, 0x2297, 0x22a5, 0x22c5, 0x2310,
  1113. 0x2320, 0x2321, 0x2329, 0x232a, 0x2469, 0x2500, 0x2502, 0x250c, 0x2510, 0x2514,
  1114. 0x2518, 0x251c, 0x2524, 0x252c, 0x2534, 0x253c, 0x2550, 0x2551, 0x2552, 0x2553,
  1115. 0x2554, 0x2555, 0x2556, 0x2557, 0x2558, 0x2559, 0x255a, 0x255b, 0x255c, 0x255d,
  1116. 0x255e, 0x255f, 0x2560, 0x2561, 0x2562, 0x2563, 0x2564, 0x2565, 0x2566, 0x2567,
  1117. 0x2568, 0x2569, 0x256a, 0x256b, 0x256c, 0x2580, 0x2584, 0x2588, 0x258c, 0x2590,
  1118. 0x2591, 0x2592, 0x2593, 0x25a0, 0x25b2, 0x25bc, 0x25c6, 0x25ca, 0x25cf, 0x25d7,
  1119. 0x2605, 0x260e, 0x261b, 0x261e, 0x2660, 0x2663, 0x2665, 0x2666, 0x2701, 0x2702,
  1120. 0x2703, 0x2704, 0x2706, 0x2707, 0x2708, 0x2709, 0x270c, 0x270d, 0x270e, 0x270f,
  1121. 0x2710, 0x2711, 0x2712, 0x2713, 0x2714, 0x2715, 0x2716, 0x2717, 0x2718, 0x2719,
  1122. 0x271a, 0x271b, 0x271c, 0x271d, 0x271e, 0x271f, 0x2720, 0x2721, 0x2722, 0x2723,
  1123. 0x2724, 0x2725, 0x2726, 0x2727, 0x2729, 0x272a, 0x272b, 0x272c, 0x272d, 0x272e,
  1124. 0x272f, 0x2730, 0x2731, 0x2732, 0x2733, 0x2734, 0x2735, 0x2736, 0x2737, 0x2738,
  1125. 0x2739, 0x273a, 0x273b, 0x273c, 0x273d, 0x273e, 0x273f, 0x2740, 0x2741, 0x2742,
  1126. 0x2743, 0x2744, 0x2745, 0x2746, 0x2747, 0x2748, 0x2749, 0x274a, 0x274b, 0x274d,
  1127. 0x274f, 0x2750, 0x2751, 0x2752, 0x2756, 0x2758, 0x2759, 0x275a, 0x275b, 0x275c,
  1128. 0x275d, 0x275e, 0x2761, 0x2762, 0x2763, 0x2764, 0x2765, 0x2766, 0x2767, 0x277f,
  1129. 0x2789, 0x2793, 0x2794, 0x2798, 0x2799, 0x279a, 0x279b, 0x279c, 0x279d, 0x279e,
  1130. 0x279f, 0x27a0, 0x27a1, 0x27a2, 0x27a3, 0x27a4, 0x27a5, 0x27a6, 0x27a7, 0x27a8,
  1131. 0x27a9, 0x27aa, 0x27ab, 0x27ac, 0x27ad, 0x27ae, 0x27af, 0x27b1, 0x27b2, 0x27b3,
  1132. 0x27b4, 0x27b5, 0x27b6, 0x27b7, 0x27b8, 0x27b9, 0x27ba, 0x27bb, 0x27bc, 0x27bd,
  1133. 0x27be, 0x3000, 0x3001, 0x3002, 0x3003, 0x3008, 0x3009, 0x300a, 0x300b, 0x300c,
  1134. 0x300d, 0x300e, 0x300f, 0x3010, 0x3011, 0x3012, 0x3014, 0x3015, 0x3016, 0x3017,
  1135. 0x3018, 0x3019, 0x301a, 0x301b, 0x3036,
  1136. 0xf6d9, 0xf6da, 0xf6db, 0xf8d7, 0xf8d8, 0xf8d9, 0xf8da, 0xf8db, 0xf8dc,
  1137. 0xf8dd, 0xf8de, 0xf8df, 0xf8e0, 0xf8e1, 0xf8e2, 0xf8e3, 0xf8e4, 0xf8e5, 0xf8e6,
  1138. 0xf8e7, 0xf8e8, 0xf8e9, 0xf8ea, 0xf8eb, 0xf8ec, 0xf8ed, 0xf8ee, 0xf8ef, 0xf8f0,
  1139. 0xf8f1, 0xf8f2, 0xf8f3, 0xf8f4, 0xf8f5, 0xf8f6, 0xf8f7, 0xf8f8, 0xf8f9, 0xf8fa,
  1140. 0xf8fb, 0xf8fc, 0xf8fd, 0xf8fe, 0xfe7c, 0xfe7d,
  1141. 0xff01, 0xff02, 0xff03, 0xff04, 0xff05, 0xff06, 0xff07, 0xff08, 0xff09,
  1142. 0xff09, 0xff0a, 0xff0b, 0xff0c, 0xff0d, 0xff0e, 0xff0f, 0xff1a, 0xff1b, 0xff1c,
  1143. 0xff1d, 0xff1e, 0xff1f, 0xff20, 0xff3b, 0xff3c, 0xff3d, 0xff3e, 0xff40, 0xff5b,
  1144. 0xff5c, 0xff5d, 0xff5e, 0xff5f, 0xff60, 0xff61, 0xff62, 0xff63, 0xff64, 0xff65,
  1145. 0xffe0, 0xffe1, 0xffe2, 0xffe3, 0xffe4, 0xffe5, 0xffe6, 0xffe8, 0xffe9, 0xffea,
  1146. 0xffeb, 0xffec, 0xffed, 0xffee,
  1147. 0x01d6fc, 0x01d6fd, 0x01d6fe, 0x01d6ff, 0x01d700, 0x01d701, 0x01d702, 0x01d703,
  1148. 0x01d704, 0x01d705, 0x01d706, 0x01d707, 0x01d708, 0x01d709, 0x01d70a, 0x01d70b,
  1149. 0x01d70c, 0x01d70d, 0x01d70e, 0x01d70f, 0x01d710, 0x01d711, 0x01d712, 0x01d713,
  1150. 0x01d714, 0x01d715, 0x01d716, 0x01d717, 0x01d718, 0x01d719, 0x01d71a, 0x01d71b,
  1151. 0xc2a0, 0xe28087, 0xe280af, 0xe281a0, 0xefbbbf,
  1152. );
  1153. // utf8 version of above data
  1154. global $UTF8_SPECIAL_CHARS2;
  1155. if(empty($UTF8_SPECIAL_CHARS2)) $UTF8_SPECIAL_CHARS2 =
  1156. "\x1A".' !"#$%&\'()+,/;<=>?@[\]^`{|}~Â&#x20AC;Â Â&#x201A;Â&#x192;Â&#x201E;Â&#x2026;Â&#x2020;Â&#x2021;Â&#x2C6;Â&#x2030;Â&#x160;Â&#x2039;Â&#x152;Â?Â&#x17D;Â?Â?Â&#x2018;Â&#x2019;Â&#x201C;Â&#x201D;Â&#x2022;???'.
  1157. '???Â&#x2014;Â&#x2DC;Â&#x2122;Â&#x161;Â&#x203A;Â&#x153;Â?Â&#x17E;Â&#x; Â?Â?Â?¤Â?Â?§¨ŠÂ?Â?Â?­ŽÂ?°Â?Â?Â?´Â?Â?Â?¸šÂ?Â?Â?Â????'.
  1158. '???Â??&#x2014;??Ë&#x2021;Ë&#x2DC;Ë&#x2122;Ë&#x161;Ë&#x203A;Ë&#x153;Ë??&#x20AC;? ?&#x192;?&#x2030;??Î&#x201E;Î&#x2026;Î&#x2021;?&#x2013;Ö°Ö?Ö?Ö?Ö´Ö?Ö?Ö?Ö¸ÖšÖ?Ö?Ö?ÖžÖ????'.
  1159. '???× ×&#x201A;×&#x192;×?×´?&#x152;?&#x203A;?&#x;?&#x20AC;?&#x2039;?&#x152;???&#x17D;?????&#x2018;?&#x2019;???¸?â&#x20AC;&#x152;â&#x20AC;?â&#x20AC;&#x17D;â&#x20AC;?â&#x20AC;&#x201C;â&#x20AC;&#x201D;â&#x20AC;&#x2022;â&#x20AC;&#x2014;â&#x20AC;&#x2DC;â&#x20AC;&#x2122;â&#x20AC;&#x161;â&#x20AC;&#x153;â&#x20AC;????'.
  1160. '??????â&#x20AC; â&#x20AC;?â&#x20AC;?â&#x20AC;?â&#x20AC;°â&#x20AC;?â&#x20AC;?â&#x20AC;šâ&#x20AC;?â &#x201E;â&#x201A;§â&#x201A;?â&#x201A;?â&#x201A;?â&#x201E;&#x2013;â&#x201E;&#x2DC;â&#x201E;?â&#x201E;?â&#x201E;?â&#x2020;?â&#x2020;&#x2018;â&#x2020;&#x2019;â&#x2020;&#x201C;â&#x2020;&#x201D;â&#x2020;&#x2022;â&#x2020;?'.
  1161. 'â&#x2021;?â&#x2021;&#x2018;â&#x2021;&#x2019;â&#x2021;&#x201C;â&#x2021;&#x201D;â&#x2C6;&#x20AC;â&#x2C6;&#x201A;â&#x2C6;&#x192;â&#x2C6;&#x2026;â&#x2C6;&#x2020;â&#x2C6;&#x2021;â&#x2C6;&#x2C6;â&#x2C6;&#x2030;â&#x2C6;&#x2039;â&#x2C6;?â&#x2C6;&#x2018;â&#x2C6;&#x2019;â&#x2C6;&#x2022;â&#x2C6;&#x2014;â&#x2C6;&#x2122;â&#x2C6;&#x161;â&#x2C6;?â&#x2C6;&#x17E;â&#x2C6; â&#x2C6;§â&#x2C6;¨???'.
  1162. '???â&#x2C6;?â&#x2C6;?â&#x2C6;´â&#x2C6;?â&#x2030;&#x2026;â&#x2030;&#x2C6;â&#x2030; â&#x2030;?â&#x2030;¤â&#x2030;?â&#x160;&#x201A;â&#x160;&#x192;â&#x160;&#x201E;â&#x160;&#x2020;â&#x160;&#x2021;â&#x160;&#x2022;â&#x160;&#x2014;â&#x160;?â&#x2039;&#x2026;â&#x152;?â&#x152; â&#x152;?â&#x152;Šâ&#x152;?â&#x2018;Šâ&#x201D;&#x20AC;???'.
  1163. '??????â&#x201D;&#x152;â&#x201D;?â&#x201D;&#x201D;â&#x201D;&#x2DC;â&#x201D;&#x153;â&#x201D;¤â&#x201D;?â&#x201D;´â&#x201D;?â&#x2022;?â&#x2022;&#x2018;â&#x2022;&#x2019;â&#x2022;&#x201C;â&#x2022;&#x201D;â&#x2022;&#x2022;â&#x2022;&#x2013;â&#x2022;&#x2014;â&#x2022;&#x2DC;â&#x2022;&#x2122;â&#x2022;&#x161;â&#x2022;&#x203A;â&#x2022;&#x153;â&#x2022;?â&#x2022;&#x17E;â&#x2022;&#x;â&#x2022; '.
  1164. 'â&#x2022;?â&#x2022;?â&#x2022;?â&#x2022;¤â&#x2022;?â&#x2022;?â&#x2022;§â&#x2022;¨â&#x2022;Šâ&#x2022;?â&#x2022;?â&#x2022;?â&#x2013;&#x20AC;â&#x2013;&#x201E;â&#x2013;&#x2C6;â&#x2013;&#x152;â&#x2013;?â&#x2013;&#x2018;â&#x2013;&#x2019;â&#x2013;&#x201C;â&#x2013; â&#x2013;?â&#x2013;?â&#x2014;&#x2020;â&#x2014;&#x160;â&#x2014;????'.
  1165. '???â&#x2DC;&#x2026;â&#x2DC;&#x17D;â&#x2DC;&#x203A;â&#x2DC;&#x17E;â&#x2122; â&#x2122;?â&#x2122;?â&#x2122;?â&#x153; â&#x153;&#x201A;â&#x153;&#x192;â&#x153;&#x201E;â&#x153;&#x2020;â&#x153;&#x2021;â&#x153;&#x2C6;â&#x153;&#x2030;â&#x153;&#x152;â&#x153;?â&#x153;&#x17D;â&#x153;?â&#x153;?â&#x153;&#x2018;â&#x153;&#x2019;â&#x153;&#x201C;â&#x153;&#x201D;â&#x153;&#x2022;???'.
  1166. '??????â&#x153;&#x2014;â&#x153;&#x2DC;â&#x153;&#x2122;â&#x153;&#x161;â&#x153;&#x203A;â&#x153;&#x153;â&#x153;?â&#x153;&#x17E;â&#x153;&#x;â&#x153; â&#x153;?â&#x153;?â&#x153;?â&#x153;¤â&#x153;?â&#x153;?â&#x153;§â&#x153;Šâ&#x153;?â&#x153;?â&#x153;?â&#x153;­â&#x153;Žâ&#x153;?â&#x153;°â&#x153;?'.
  1167. 'â&#x153;?â&#x153;?â&#x153;´â&#x153;?â&#x153;?â&#x153;?â&#x153;¸â&#x153;šâ&#x153;?â&#x153;?â&#x153;?â&#x153;?â&#x153;žâ&#x153;?â?&#x20AC;â? â?&#x201A;â?&#x192;â?&#x201E;â?&#x2026;â?&#x2020;â?&#x2021;â?&#x2C6;â?&#x2030;â?&#x160;â?&#x2039;???'.
  1168. '???â??â??â?&#x2018;â?&#x2019;â?&#x2013;â?&#x2DC;â?&#x2122;â?&#x161;â?&#x203A;â?&#x153;â??â?&#x17E;â??â??â??â?¤â??â??â?§â??â&#x17E;&#x2030;â&#x17E;&#x201C;â&#x17E;&#x201D;â&#x17E;&#x2DC;â&#x17E;&#x2122;â&#x17E;&#x161;???'.
  1169. '??????â&#x17E;&#x153;â&#x17E;?â&#x17E;&#x17E;â&#x17E;&#x;â&#x17E; â&#x17E;?â&#x17E;?â&#x17E;?â&#x17E;¤â&#x17E;?â&#x17E;?â&#x17E;§â&#x17E;¨â&#x17E;Šâ&#x17E;?â&#x17E;?â&#x17E;?â&#x17E;­â&#x17E;Žâ&#x17E;?â&#x17E;?â&#x17E;?â&#x17E;?â&#x17E;´â&#x17E;?â&#x17E;?'.
  1170. 'â&#x17E;?â&#x17E;¸â&#x17E;šâ&#x17E;?â&#x17E;?â&#x17E;?â&#x17E;?â&#x17E;ž'.
  1171. '?&#x20AC;&#x20AC;?&#x20AC; ?&#x20AC;&#x201A;?&#x20AC;&#x192;?&#x20AC;&#x2C6;?&#x20AC;&#x2030;?&#x20AC;&#x160;?&#x20AC;&#x2039;?&#x20AC;&#x152;?&#x20AC;??&#x20AC;&#x17D;?&#x20AC;??&#x20AC;??&#x20AC;&#x2018;?&#x20AC;&#x2019;?&#x20AC;&#x201D;?&#x20AC;&#x2022;?&#x20AC;&#x2013;?&#x20AC;&#x2014;?&#x20AC;&#x2DC;?&#x20AC;&#x2122;?&#x20AC;&#x161;?&#x20AC;&#x203A;?&#x20AC;?'.
  1172. '?&#x203A;&#x2122;?&#x203A;&#x161;?&#x203A;&#x203A;??&#x2014;??&#x2DC;??&#x2122;??&#x161;??&#x203A;??&#x153;?????&#x17E;??&#x;?? ???????????¤??????'.
  1173. '?????§??¨??Š???????????­??Ž?????°???????????´???????????¸??š??????????????ž?š??š?'.
  1174. '?? ??&#x201A;??&#x192;??&#x201E;??&#x2026;??&#x2020;??&#x2021;??&#x2C6;??&#x2030;??&#x160;??&#x2039;??&#x152;?????&#x17D;?????&#x161;??&#x203A;??&#x153;?????&#x17E;??&#x;?? ???????????ž??&#x20AC;??&#x203A;??&#x153;?????&#x17E;'.
  1175. '??&#x;?? ???????????¤????? ???????????¤????????¨??Š???????????­??Ž'.
  1176. '??&#x203A;???&#x203A;???&#x203A;ž??&#x203A;???&#x153;&#x20AC;??&#x153; ??&#x153;&#x201A;??&#x153;&#x192;??&#x153;&#x201E;??&#x153;&#x2026;??&#x153;&#x2020;??&#x153;&#x2021;??&#x153;&#x2C6;??&#x153;&#x2030;??&#x153;&#x160;??&#x153;&#x2039;??&#x153;&#x152;??&#x153;???&#x153;&#x17D;??&#x153;???&#x153;???&#x153;&#x2018;??&#x153;&#x2019;??&#x153;&#x201C;??&#x153;&#x201D;??&#x153;&#x2022;??&#x153;&#x2013;??&#x153;&#x2014;??&#x153;&#x2DC;??&#x153;&#x2122;??&#x153;&#x161;??&#x153;&#x203A;'.
  1177. ' â&#x20AC;&#x2021;â&#x20AC;?â  ???';
  1178. /**
  1179. * Romanization lookup table
  1180. *
  1181. * This lookup tables provides a way to transform strings written in a language
  1182. * different from the ones based upon latin letters into plain ASCII.
  1183. *
  1184. * Please note: this is not a scientific transliteration table. It only works
  1185. * oneway from nonlatin to ASCII and it works by simple character replacement
  1186. * only. Specialities of each language are not supported.
  1187. *
  1188. * @author Andreas Gohr <andi@splitbrain.org>
  1189. * @author Vitaly Blokhin <vitinfo@vitn.com>
  1190. * @link http://www.uconv.com/translit.htm
  1191. * @author Bisqwit <bisqwit@iki.fi>
  1192. * @link http://kanjidict.stc.cx/hiragana.php?src=2
  1193. * @link http://www.translatum.gr/converter/greek-transliteration.htm
  1194. * @link http://en.wikipedia.org/wiki/Royal_Thai_General_System_of_Transcription
  1195. * @link http://www.btranslations.com/resources/romanization/korean.asp
  1196. * @author Arthit Suriyawongkul <arthit@gmail.com>
  1197. * @author Denis Scheither <amorphis@uni-bremen.de>
  1198. * @author Eivind Morland <eivind.morland@gmail.com>
  1199. */
  1200. global $UTF8_ROMANIZATION;
  1201. if(empty($UTF8_ROMANIZATION)) $UTF8_ROMANIZATION = array(
  1202. // scandinavian - differs from what we do in deaccent
  1203. '??'=>'a','?&#x2026;'=>'A','?¤'=>'a','?&#x201E;'=>'A','??'=>'o','?&#x2013;'=>'O',
  1204. //russian cyrillic
  1205. '?°'=>'a','??'=>'A','??'=>'b','?&#x2018;'=>'B','??'=>'v','?&#x2019;'=>'V','??'=>'g','?&#x201C;'=>'G',
  1206. '?´'=>'d','?&#x201D;'=>'D','??'=>'e','?&#x2022;'=>'E','?&#x2018;'=>'jo','? '=>'Jo','??'=>'zh','?&#x2013;'=>'Zh',
  1207. '??'=>'z','?&#x2014;'=>'Z','?¸'=>'i','?&#x2DC;'=>'I','?š'=>'j','?&#x2122;'=>'J','??'=>'k','?&#x161;'=>'K',
  1208. '??'=>'l','?&#x203A;'=>'L','??'=>'m','?&#x153;'=>'M','??'=>'n','??'=>'N','?ž'=>'o','?&#x17E;'=>'O',
  1209. '??'=>'p','?&#x;'=>'P','?&#x20AC;'=>'r','? '=>'R','? '=>'s','??'=>'S','?&#x201A;'=>'t','??'=>'T',
  1210. '?&#x192;'=>'u','??'=>'U','?&#x201E;'=>'f','?¤'=>'F','?&#x2026;'=>'x','??'=>'X','?&#x2020;'=>'c','??'=>'C',
  1211. '?&#x2021;'=>'ch','?§'=>'Ch','?&#x2C6;'=>'sh','?¨'=>'Sh','?&#x2030;'=>'sch','?Š'=>'Sch','?&#x160;'=>'',
  1212. '??'=>'','?&#x2039;'=>'y','??'=>'Y','?&#x152;'=>'','??'=>'','??'=>'eh','?­'=>'Eh','?&#x17D;'=>'ju',
  1213. '?Ž'=>'Ju','??'=>'ja','??'=>'Ja',
  1214. // Ukrainian cyrillic
  1215. '??'=>'Gh','?&#x2018;'=>'gh','?&#x201E;'=>'Je','?&#x201D;'=>'je','?&#x2020;'=>'I','?&#x2013;'=>'i','?&#x2021;'=>'Ji','?&#x2014;'=>'ji',
  1216. // Georgian
  1217. 'á&#x192;?'=>'a','á&#x192;&#x2018;'=>'b','á&#x192;&#x2019;'=>'g','á&#x192;&#x201C;'=>'d','á&#x192;&#x201D;'=>'e','á&#x192;&#x2022;'=>'v','á&#x192;&#x2013;'=>'z','á&#x192;&#x2014;'=>'th',
  1218. 'á&#x192;&#x2DC;'=>'i','á&#x192;&#x2122;'=>'p','á&#x192;&#x161;'=>'l','á&#x192;&#x203A;'=>'m','á&#x192;&#x153;'=>'n','á&#x192;?'=>'o','á&#x192;&#x17E;'=>'p','á&#x192;&#x;'=>'zh',
  1219. 'á&#x192; '=>'r','á&#x192;?'=>'s','á&#x192;?'=>'t','á&#x192;?'=>'u','á&#x192;¤'=>'ph','á&#x192;?'=>'kh','á&#x192;?'=>'gh','á&#x192;§'=>'q',
  1220. 'á&#x192;¨'=>'sh','á&#x192;Š'=>'ch','á&#x192;?'=>'c','á&#x192;?'=>'dh','á&#x192;?'=>'w','á&#x192;­'=>'j','á&#x192;Ž'=>'x','á&#x192;?'=>'jh',
  1221. 'á&#x192;°'=>'xh',
  1222. //Sanskrit
  1223. '?¤&#x2026;'=>'a','?¤&#x2020;'=>'ah','?¤&#x2021;'=>'i','?¤&#x2C6;'=>'ih','?¤&#x2030;'=>'u','?¤&#x160;'=>'uh','?¤&#x2039;'=>'ry',
  1224. '?? '=>'ryh','?¤&#x152;'=>'ly','???'=>'lyh','?¤?'=>'e','?¤?'=>'ay','?¤&#x201C;'=>'o','?¤&#x201D;'=>'aw',
  1225. '?¤&#x2026;?¤&#x201A;'=>'amh','?¤&#x2026;?¤&#x192;'=>'aq','?¤&#x2022;'=>'k','?¤&#x2013;'=>'kh','?¤&#x2014;'=>'g','?¤&#x2DC;'=>'gh','?¤&#x2122;'=>'nh',
  1226. '?¤&#x161;'=>'c','?¤&#x203A;'=>'ch','?¤&#x153;'=>'j','?¤?'=>'jh','?¤&#x17E;'=>'ny','?¤&#x;'=>'tq','?¤ '=>'tqh',
  1227. '?¤?'=>'dq','?¤?'=>'dqh','?¤?'=>'nq','?¤¤'=>'t','?¤?'=>'th','?¤?'=>'d','?¤§'=>'dh',
  1228. '?¤¨'=>'n','?¤?'=>'p','?¤?'=>'ph','?¤?'=>'b','?¤­'=>'bh','?¤Ž'=>'m','?¤?'=>'z','?¤°'=>'r',
  1229. '?¤?'=>'l','?¤?'=>'v','?¤?'=>'sh','?¤?'=>'sqh','?¤¸'=>'s','?¤š'=>'x',
  1230. //Sanskrit diacritics
  1231. 'Ä&#x20AC;'=>'A','Ä?'=>'I','??'=>'U','áš&#x161;'=>'R','áš&#x153;'=>'R','áš&#x201E;'=>'N','?&#x2018;'=>'N','áš?'=>'T',
  1232. 'á¸&#x152;'=>'D','áš&#x2020;'=>'N','?&#x161;'=>'S','áš?'=>'S','áš&#x20AC;'=>'M','áš&#x201A;'=>'M','Ḥ'=>'H','á¸?'=>'L','Ḹ'=>'L',
  1233. 'Ä '=>'a','Ä?'=>'i','??'=>'u','áš&#x203A;'=>'r','áš?'=>'r','áš&#x2026;'=>'n','??'=>'n','áš­'=>'t',
  1234. 'á¸?'=>'d','áš&#x2021;'=>'n','?&#x203A;'=>'s','áš?'=>'s','áš '=>'m','áš&#x192;'=>'m','á¸?'=>'h','á¸?'=>'l','Ḛ'=>'l',
  1235. //Hebrew
  1236. '×?'=>'a', '×&#x2018;'=>'b','×&#x2019;'=>'g','×&#x201C;'=>'d','×&#x201D;'=>'h','×&#x2022;'=>'v','×&#x2013;'=>'z','×&#x2014;'=>'kh','×&#x2DC;'=>'th',
  1237. '×&#x2122;'=>'y','×&#x161;'=>'h','×&#x203A;'=>'k','×&#x153;'=>'l','×?'=>'m','×&#x17E;'=>'m','×&#x;'=>'n','× '=>'n',
  1238. '×?'=>'s','×?'=>'ah','×?'=>'f','פ'=>'p','×?'=>'c','×?'=>'c','ק'=>'q','ר'=>'r',
  1239. '׊'=>'sh','×?'=>'t',
  1240. //Arabic
  1241. '?§'=>'a','?¨'=>'b','??'=>'t','??'=>'th','??'=>'g','?­'=>'xh','?Ž'=>'x','??'=>'d',
  1242. '?°'=>'dh','??'=>'r','??'=>'z','??'=>'s','?´'=>'sh','??'=>'s\'','??'=>'d\'',
  1243. '??'=>'t\'','?¸'=>'z\'','?š'=>'y','??'=>'gh','? '=>'f','?&#x201A;'=>'q','?&#x192;'=>'k',
  1244. '?&#x201E;'=>'l','?&#x2026;'=>'m','?&#x2020;'=>'n','?&#x2021;'=>'x\'','?&#x2C6;'=>'u','?&#x160;'=>'i',
  1245. // Japanese characters (last update: 2008-05-09)
  1246. // Japanese hiragana
  1247. // 3 character syllables, ? ? doubles the consonant after
  1248. '? ?? ??&#x201A;&#x192;'=>'ccha','? ?? ?? &#x2021;'=>'cche','? ?? ??&#x201A;&#x2021;'=>'ccho','? ?? ??&#x201A;&#x2026;'=>'cchu',
  1249. '? ?? ??&#x201A;&#x192;'=>'bbya','? ?? ?? &#x2021;'=>'bbye','? ?? ?? &#x192;'=>'bbyi','? ?? ??&#x201A;&#x2021;'=>'bbyo','? ?? ??&#x201A;&#x2026;'=>'bbyu',
  1250. '? ?? ´?&#x201A;&#x192;'=>'ppya','? ?? ´? &#x2021;'=>'ppye','? ?? ´? &#x192;'=>'ppyi','? ?? ´?&#x201A;&#x2021;'=>'ppyo','? ?? ´?&#x201A;&#x2026;'=>'ppyu',
  1251. '? ?? ??&#x201A;&#x192;'=>'ccha','? ?? ?? &#x2021;'=>'cche','? ?? ?'=>'cchi','? ?? ??&#x201A;&#x2021;'=>'ccho','? ?? ??&#x201A;&#x2026;'=>'cchu',
  1252. // '? ?? ??&#x201A;&#x192;'=>'hya','? ?? ?? &#x2021;'=>'hye','? ?? ?? &#x192;'=>'hyi','? ?? ??&#x201A;&#x2021;'=>'hyo','? ?? ??&#x201A;&#x2026;'=>'hyu',
  1253. '? ?? ??&#x201A;&#x192;'=>'kkya','? ?? ?? &#x2021;'=>'kkye','? ?? ?? &#x192;'=>'kkyi','? ?? ??&#x201A;&#x2021;'=>'kkyo','? ?? ??&#x201A;&#x2026;'=>'kkyu',
  1254. '? ?? &#x17D;?&#x201A;&#x192;'=>'ggya','? ?? &#x17D;? &#x2021;'=>'ggye','? ?? &#x17D;? &#x192;'=>'ggyi','? ?? &#x17D;?&#x201A;&#x2021;'=>'ggyo','? ?? &#x17D;?&#x201A;&#x2026;'=>'ggyu',
  1255. '? ?? ??&#x201A;&#x192;'=>'mmya','? ?? ?? &#x2021;'=>'mmye','? ?? ?? &#x192;'=>'mmyi','? ?? ??&#x201A;&#x2021;'=>'mmyo','? ?? ??&#x201A;&#x2026;'=>'mmyu',
  1256. '? ?? ??&#x201A;&#x192;'=>'nnya','? ?? ?? &#x2021;'=>'nnye','? ?? ?? &#x192;'=>'nnyi','? ?? ??&#x201A;&#x2021;'=>'nnyo','? ?? ??&#x201A;&#x2026;'=>'nnyu',
  1257. '? ??&#x201A;&#x160;?&#x201A;&#x192;'=>'rrya','? ??&#x201A;&#x160;? &#x2021;'=>'rrye','? ??&#x201A;&#x160;? &#x192;'=>'rryi','? ??&#x201A;&#x160;?&#x201A;&#x2021;'=>'rryo','? ??&#x201A;&#x160;?&#x201A;&#x2026;'=>'rryu',
  1258. '? ?? &#x2014;?&#x201A;&#x192;'=>'ssha','? ?? &#x2014;? &#x2021;'=>'sshe','? ?? &#x2014;'=>'sshi','? ?? &#x2014;?&#x201A;&#x2021;'=>'ssho','? ?? &#x2014;?&#x201A;&#x2026;'=>'sshu',
  1259. // seperate hiragana 'n' ('n' + 'i' != 'ni', normally we would write "kon'nichi wa" but the apostrophe would be converted to _ anyway)
  1260. '?&#x201A;&#x201C;? &#x201A;'=>'n_a','?&#x201A;&#x201C;? &#x2C6;'=>'n_e','?&#x201A;&#x201C;? &#x201E;'=>'n_i','?&#x201A;&#x201C;? &#x160;'=>'n_o','?&#x201A;&#x201C;? &#x2020;'=>'n_u',
  1261. '?&#x201A;&#x201C;?&#x201A;&#x201E;'=>'n_ya','?&#x201A;&#x201C;?&#x201A;&#x2C6;'=>'n_yo','?&#x201A;&#x201C;?&#x201A;&#x2020;'=>'n_yu',
  1262. // 2 character syllables - normal
  1263. '? ?? '=>'fa','? ?? &#x2021;'=>'fe','? ?? &#x192;'=>'fi','? ?? &#x2030;'=>'fo',
  1264. '? ??&#x201A;&#x192;'=>'cha','? ?? &#x2021;'=>'che','? ?'=>'chi','? ??&#x201A;&#x2021;'=>'cho','? ??&#x201A;&#x2026;'=>'chu',
  1265. '? ??&#x201A;&#x192;'=>'hya','? ?? &#x2021;'=>'hye','? ?? &#x192;'=>'hyi','? ??&#x201A;&#x2021;'=>'hyo','? ??&#x201A;&#x2026;'=>'hyu',
  1266. '? ??&#x201A;&#x192;'=>'bya','? ?? &#x2021;'=>'bye','? ?? &#x192;'=>'byi','? ??&#x201A;&#x2021;'=>'byo','? ??&#x201A;&#x2026;'=>'byu',
  1267. '? ´?&#x201A;&#x192;'=>'pya','? ´? &#x2021;'=>'pye','? ´? &#x192;'=>'pyi','? ´?&#x201A;&#x2021;'=>'pyo','? ´?&#x201A;&#x2026;'=>'pyu',
  1268. '? ??&#x201A;&#x192;'=>'kya','? ?? &#x2021;'=>'kye','? ?? &#x192;'=>'kyi','? ??&#x201A;&#x2021;'=>'kyo','? ??&#x201A;&#x2026;'=>'kyu',
  1269. '? &#x17D;?&#x201A;&#x192;'=>'gya','? &#x17D;? &#x2021;'=>'gye','? &#x17D;? &#x192;'=>'gyi','? &#x17D;?&#x201A;&#x2021;'=>'gyo','? &#x17D;?&#x201A;&#x2026;'=>'gyu',
  1270. '? ??&#x201A;&#x192;'=>'mya','? ?? &#x2021;'=>'mye','? ?? &#x192;'=>'myi','? ??&#x201A;&#x2021;'=>'myo','? ??&#x201A;&#x2026;'=>'myu',
  1271. '? ??&#x201A;&#x192;'=>'nya','? ?? &#x2021;'=>'nye','? ?? &#x192;'=>'nyi','? ??&#x201A;&#x2021;'=>'nyo','? ??&#x201A;&#x2026;'=>'nyu',
  1272. '?&#x201A;&#x160;?&#x201A;&#x192;'=>'rya','?&#x201A;&#x160;? &#x2021;'=>'rye','?&#x201A;&#x160;? &#x192;'=>'ryi','?&#x201A;&#x160;?&#x201A;&#x2021;'=>'ryo','?&#x201A;&#x160;?&#x201A;&#x2026;'=>'ryu',
  1273. '? &#x2014;?&#x201A;&#x192;'=>'sha','? &#x2014;? &#x2021;'=>'she','? &#x2014;'=>'shi','? &#x2014;?&#x201A;&#x2021;'=>'sho','? &#x2014;?&#x201A;&#x2026;'=>'shu',
  1274. '? &#x2DC;?&#x201A;&#x192;'=>'ja','? &#x2DC;? &#x2021;'=>'je','? &#x2DC;?&#x201A;&#x2021;'=>'jo','? &#x2DC;?&#x201A;&#x2026;'=>'ju',
  1275. '? &#x2020;? &#x2021;'=>'we','? &#x2020;? &#x192;'=>'wi',
  1276. '? &#x201E;? &#x2021;'=>'ye',
  1277. // 2 character syllables, ? ? doubles the consonant after
  1278. '? ?? °'=>'bba','? ?? š'=>'bbe','? ?? ?'=>'bbi','? ?? ?'=>'bbo','? ?? ?'=>'bbu',
  1279. '? ?? ?'=>'ppa','? ?? ?'=>'ppe','? ?? ´'=>'ppi','? ?? ?'=>'ppo','? ?? ?'=>'ppu',
  1280. '? ?? &#x;'=>'tta','? ?? ?'=>'tte','? ?? ?'=>'cchi','? ?? ¨'=>'tto','? ?? ¤'=>'ttsu',
  1281. '? ??  '=>'dda','? ?? §'=>'dde','? ?? ?'=>'ddi','? ?? Š'=>'ddo','? ?? ?'=>'ddu',
  1282. '? ?? &#x152;'=>'gga','? ?? &#x2019;'=>'gge','? ?? &#x17D;'=>'ggi','? ?? &#x201D;'=>'ggo','? ?? ?'=>'ggu',
  1283. '? ?? &#x2039;'=>'kka','? ?? &#x2018;'=>'kke','? ?? ?'=>'kki','? ?? &#x201C;'=>'kko','? ?? ?'=>'kku',
  1284. '? ?? ž'=>'mma','? ??&#x201A; '=>'mme','? ?? ?'=>'mmi','? ??&#x201A;&#x201A;'=>'mmo','? ??&#x201A;&#x20AC;'=>'mmu',
  1285. '? ?? ?'=>'nna','? ?? ­'=>'nne','? ?? ?'=>'nni','? ?? Ž'=>'nno','? ?? ?'=>'nnu',
  1286. '? ??&#x201A;&#x2030;'=>'rra','? ??&#x201A;&#x152;'=>'rre','? ??&#x201A;&#x160;'=>'rri','? ??&#x201A;?'=>'rro','? ??&#x201A;&#x2039;'=>'rru',
  1287. '? ?? &#x2022;'=>'ssa','? ?? &#x203A;'=>'sse','? ?? &#x2014;'=>'sshi','? ?? ?'=>'sso','? ?? &#x2122;'=>'ssu',
  1288. '? ?? &#x2013;'=>'zza','? ?? &#x153;'=>'zze','? ?? &#x2DC;'=>'jji','? ?? &#x17E;'=>'zzo','? ?? &#x161;'=>'zzu',
  1289. // 1 character syllabels
  1290. '? &#x201A;'=>'a','? &#x2C6;'=>'e','? &#x201E;'=>'i','? &#x160;'=>'o','? &#x2020;'=>'u','?&#x201A;&#x201C;'=>'n',
  1291. '? ?'=>'ha','? ¸'=>'he','? ?'=>'hi','? ?'=>'ho','? ?'=>'fu',
  1292. '? °'=>'ba','? š'=>'be','? ?'=>'bi','? ?'=>'bo','? ?'=>'bu',
  1293. '? ?'=>'pa','? ?'=>'pe','? ´'=>'pi','? ?'=>'po','? ?'=>'pu',
  1294. '? &#x;'=>'ta','? ?'=>'te','? ?'=>'chi','? ¨'=>'to','? ¤'=>'tsu',
  1295. '?  '=>'da','? §'=>'de','? ?'=>'di','? Š'=>'do','? ?'=>'du',
  1296. '? &#x152;'=>'ga','? &#x2019;'=>'ge','? &#x17D;'=>'gi','? &#x201D;'=>'go','? ?'=>'gu',
  1297. '? &#x2039;'=>'ka','? &#x2018;'=>'ke','? ?'=>'ki','? &#x201C;'=>'ko','? ?'=>'ku',
  1298. '? ž'=>'ma','?&#x201A; '=>'me','? ?'=>'mi','?&#x201A;&#x201A;'=>'mo','?&#x201A;&#x20AC;'=>'mu',
  1299. '? ?'=>'na','? ­'=>'ne','? ?'=>'ni','? Ž'=>'no','? ?'=>'nu',
  1300. '?&#x201A;&#x2030;'=>'ra','?&#x201A;&#x152;'=>'re','?&#x201A;&#x160;'=>'ri','?&#x201A;?'=>'ro','?&#x201A;&#x2039;'=>'ru',
  1301. '? &#x2022;'=>'sa','? &#x203A;'=>'se','? &#x2014;'=>'shi','? ?'=>'so','? &#x2122;'=>'su',
  1302. '?&#x201A;?'=>'wa','?&#x201A;&#x2019;'=>'wo',
  1303. '? &#x2013;'=>'za','? &#x153;'=>'ze','? &#x2DC;'=>'ji','? &#x17E;'=>'zo','? &#x161;'=>'zu',
  1304. '?&#x201A;&#x201E;'=>'ya','?&#x201A;&#x2C6;'=>'yo','?&#x201A;&#x2020;'=>'yu',
  1305. // old characters
  1306. '?&#x201A;&#x2018;'=>'we','?&#x201A;?'=>'wi',
  1307. // convert what's left (probably only kicks in when something's missing above)
  1308. // '? '=>'a','? &#x2021;'=>'e','? &#x192;'=>'i','? &#x2030;'=>'o','? &#x2026;'=>'u',
  1309. // '?&#x201A;&#x192;'=>'ya','?&#x201A;&#x2021;'=>'yo','?&#x201A;&#x2026;'=>'yu',
  1310. // never seen one of those (disabled for the moment)
  1311. // '?&#x192;´? '=>'va','?&#x192;´? &#x2021;'=>'ve','?&#x192;´? &#x192;'=>'vi','?&#x192;´? &#x2030;'=>'vo','?&#x192;´'=>'vu',
  1312. // '? §?&#x201A;&#x192;'=>'dha','? §? &#x2021;'=>'dhe','? §? &#x192;'=>'dhi','? §?&#x201A;&#x2021;'=>'dho','? §?&#x201A;&#x2026;'=>'dhu',
  1313. // '? Š? '=>'dwa','? Š? &#x2021;'=>'dwe','? Š? &#x192;'=>'dwi','? Š? &#x2030;'=>'dwo','? Š? &#x2026;'=>'dwu',
  1314. // '? ??&#x201A;&#x192;'=>'dya','? ?? &#x2021;'=>'dye','? ?? &#x192;'=>'dyi','? ??&#x201A;&#x2021;'=>'dyo','? ??&#x201A;&#x2026;'=>'dyu',
  1315. // '? ?? '=>'fwa','? ?? &#x2021;'=>'fwe','? ?? &#x192;'=>'fwi','? ?? &#x2030;'=>'fwo','? ?? &#x2026;'=>'fwu',
  1316. // '? ??&#x201A;&#x192;'=>'fya','? ?? &#x2021;'=>'fye','? ?? &#x192;'=>'fyi','? ??&#x201A;&#x2021;'=>'fyo','? ??&#x201A;&#x2026;'=>'fyu',
  1317. // '? &#x2122;? '=>'swa','? &#x2122;? &#x2021;'=>'swe','? &#x2122;? &#x192;'=>'swi','? &#x2122;? &#x2030;'=>'swo','? &#x2122;? &#x2026;'=>'swu',
  1318. // '? ??&#x201A;&#x192;'=>'tha','? ?? &#x2021;'=>'the','? ?? &#x192;'=>'thi','? ??&#x201A;&#x2021;'=>'tho','? ??&#x201A;&#x2026;'=>'thu',
  1319. // '? ¤?&#x201A;&#x192;'=>'tsa','? ¤? &#x2021;'=>'tse','? ¤? &#x192;'=>'tsi','? ¤?&#x201A;&#x2021;'=>'tso','? ¤'=>'tsu',
  1320. // '? ¨? '=>'twa','? ¨? &#x2021;'=>'twe','? ¨? &#x192;'=>'twi','? ¨? &#x2030;'=>'two','? ¨? &#x2026;'=>'twu',
  1321. // '?&#x192;´?&#x201A;&#x192;'=>'vya','?&#x192;´? &#x2021;'=>'vye','?&#x192;´? &#x192;'=>'vyi','?&#x192;´?&#x201A;&#x2021;'=>'vyo','?&#x192;´?&#x201A;&#x2026;'=>'vyu',
  1322. // '? &#x2020;? '=>'wha','? &#x2020;? &#x2021;'=>'whe','? &#x2020;? &#x192;'=>'whi','? &#x2020;? &#x2030;'=>'who','? &#x2020;? &#x2026;'=>'whu',
  1323. // '? &#x2DC;?&#x201A;&#x192;'=>'zha','? &#x2DC;? &#x2021;'=>'zhe','? &#x2DC;? &#x192;'=>'zhi','? &#x2DC;?&#x201A;&#x2021;'=>'zho','? &#x2DC;?&#x201A;&#x2026;'=>'zhu',
  1324. // '? &#x2DC;?&#x201A;&#x192;'=>'zya','? &#x2DC;? &#x2021;'=>'zye','? &#x2DC;? &#x192;'=>'zyi','? &#x2DC;?&#x201A;&#x2021;'=>'zyo','? &#x2DC;?&#x201A;&#x2026;'=>'zyu',
  1325. // 'spare' characters from other romanization systems
  1326. // '?  '=>'da','? §'=>'de','? ?'=>'di','? Š'=>'do','? ?'=>'du',
  1327. // '?&#x201A;&#x2030;'=>'la','?&#x201A;&#x152;'=>'le','?&#x201A;&#x160;'=>'li','?&#x201A;?'=>'lo','?&#x201A;&#x2039;'=>'lu',
  1328. // '? &#x2022;'=>'sa','? &#x203A;'=>'se','? &#x2014;'=>'si','? ?'=>'so','? &#x2122;'=>'su',
  1329. // '? ??&#x201A;&#x192;'=>'cya','? ?? &#x2021;'=>'cye','? ?? &#x192;'=>'cyi','? ??&#x201A;&#x2021;'=>'cyo','? ??&#x201A;&#x2026;'=>'cyu',
  1330. //'? &#x2DC;?&#x201A;&#x192;'=>'jya','? &#x2DC;? &#x2021;'=>'jye','? &#x2DC;? &#x192;'=>'jyi','? &#x2DC;?&#x201A;&#x2021;'=>'jyo','? &#x2DC;?&#x201A;&#x2026;'=>'jyu',
  1331. //'?&#x201A;&#x160;?&#x201A;&#x192;'=>'lya','?&#x201A;&#x160;? &#x2021;'=>'lye','?&#x201A;&#x160;? &#x192;'=>'lyi','?&#x201A;&#x160;?&#x201A;&#x2021;'=>'lyo','?&#x201A;&#x160;?&#x201A;&#x2026;'=>'lyu',
  1332. //'? &#x2014;?&#x201A;&#x192;'=>'sya','? &#x2014;? &#x2021;'=>'sye','? &#x2014;? &#x192;'=>'syi','? &#x2014;?&#x201A;&#x2021;'=>'syo','? &#x2014;?&#x201A;&#x2026;'=>'syu',
  1333. //'? ??&#x201A;&#x192;'=>'tya','? ?? &#x2021;'=>'tye','? ?? &#x192;'=>'tyi','? ??&#x201A;&#x2021;'=>'tyo','? ??&#x201A;&#x2026;'=>'tyu',
  1334. //'? &#x2014;'=>'ci',,? &#x201E;'=>'yi','? ?'=>'dzi',
  1335. //'? ?? &#x2DC;?&#x201A;&#x192;'=>'jja','? ?? &#x2DC;? &#x2021;'=>'jje','? ?? &#x2DC;'=>'jji','? ?? &#x2DC;?&#x201A;&#x2021;'=>'jjo','? ?? &#x2DC;?&#x201A;&#x2026;'=>'jju',
  1336. // Japanese katakana
  1337. // 4 character syllables: ?&#x192;&#x192; doubles the consonant after, ?&#x192;? doubles the vowel before (usualy written with macron, but we don't want that in our URLs)
  1338. '?&#x192;&#x192;?&#x192;&#x201C;?&#x192;??&#x192;?'=>'bbyaa','?&#x192;&#x192;?&#x192;&#x201C;?&#x201A;§?&#x192;?'=>'bbyee','?&#x192;&#x192;?&#x192;&#x201C;?&#x201A;??&#x192;?'=>'bbyii','?&#x192;&#x192;?&#x192;&#x201C;?&#x192;§?&#x192;?'=>'bbyoo','?&#x192;&#x192;?&#x192;&#x201C;?&#x192;??&#x192;?'=>'bbyuu',
  1339. '?&#x192;&#x192;?&#x192;&#x201D;?&#x192;??&#x192;?'=>'ppyaa','?&#x192;&#x192;?&#x192;&#x201D;?&#x201A;§?&#x192;?'=>'ppyee','?&#x192;&#x192;?&#x192;&#x201D;?&#x201A;??&#x192;?'=>'ppyii','?&#x192;&#x192;?&#x192;&#x201D;?&#x192;§?&#x192;?'=>'ppyoo','?&#x192;&#x192;?&#x192;&#x201D;?&#x192;??&#x192;?'=>'ppyuu',
  1340. '?&#x192;&#x192;?&#x201A;­?&#x192;??&#x192;?'=>'kkyaa','?&#x192;&#x192;?&#x201A;­?&#x201A;§?&#x192;?'=>'kkyee','?&#x192;&#x192;?&#x201A;­?&#x201A;??&#x192;?'=>'kkyii','?&#x192;&#x192;?&#x201A;­?&#x192;§?&#x192;?'=>'kkyoo','?&#x192;&#x192;?&#x201A;­?&#x192;??&#x192;?'=>'kkyuu',
  1341. '?&#x192;&#x192;?&#x201A;Ž?&#x192;??&#x192;?'=>'ggyaa','?&#x192;&#x192;?&#x201A;Ž?&#x201A;§?&#x192;?'=>'ggyee','?&#x192;&#x192;?&#x201A;Ž?&#x201A;??&#x192;?'=>'ggyii','?&#x192;&#x192;?&#x201A;Ž?&#x192;§?&#x192;?'=>'ggyoo','?&#x192;&#x192;?&#x201A;Ž?&#x192;??&#x192;?'=>'ggyuu',
  1342. '?&#x192;&#x192;?&#x192;&#x;?&#x192;??&#x192;?'=>'mmyaa','?&#x192;&#x192;?&#x192;&#x;?&#x201A;§?&#x192;?'=>'mmyee','?&#x192;&#x192;?&#x192;&#x;?&#x201A;??&#x192;?'=>'mmyii','?&#x192;&#x192;?&#x192;&#x;?&#x192;§?&#x192;?'=>'mmyoo','?&#x192;&#x192;?&#x192;&#x;?&#x192;??&#x192;?'=>'mmyuu',
  1343. '?&#x192;&#x192;?&#x192;&#x2039;?&#x192;??&#x192;?'=>'nnyaa','?&#x192;&#x192;?&#x192;&#x2039;?&#x201A;§?&#x192;?'=>'nnyee','?&#x192;&#x192;?&#x192;&#x2039;?&#x201A;??&#x192;?'=>'nnyii','?&#x192;&#x192;?&#x192;&#x2039;?&#x192;§?&#x192;?'=>'nnyoo','?&#x192;&#x192;?&#x192;&#x2039;?&#x192;??&#x192;?'=>'nnyuu',
  1344. '?&#x192;&#x192;?&#x192;??&#x192;??&#x192;?'=>'rryaa','?&#x192;&#x192;?&#x192;??&#x201A;§?&#x192;?'=>'rryee','?&#x192;&#x192;?&#x192;??&#x201A;??&#x192;?'=>'rryii','?&#x192;&#x192;?&#x192;??&#x192;§?&#x192;?'=>'rryoo','?&#x192;&#x192;?&#x192;??&#x192;??&#x192;?'=>'rryuu',
  1345. '?&#x192;&#x192;?&#x201A;??&#x192;??&#x192;?'=>'sshaa','?&#x192;&#x192;?&#x201A;??&#x201A;§?&#x192;?'=>'sshee','?&#x192;&#x192;?&#x201A;??&#x192;?'=>'sshii','?&#x192;&#x192;?&#x201A;??&#x192;§?&#x192;?'=>'sshoo','?&#x192;&#x192;?&#x201A;??&#x192;??&#x192;?'=>'sshuu',
  1346. '?&#x192;&#x192;?&#x192; ?&#x192;??&#x192;?'=>'cchaa','?&#x192;&#x192;?&#x192; ?&#x201A;§?&#x192;?'=>'cchee','?&#x192;&#x192;?&#x192; ?&#x192;?'=>'cchii','?&#x192;&#x192;?&#x192; ?&#x192;§?&#x192;?'=>'cchoo','?&#x192;&#x192;?&#x192; ?&#x192;??&#x192;?'=>'cchuu',
  1347. '?&#x192;&#x192;?&#x192;&#x2020;?&#x201A;??&#x192;?'=>'ttii',
  1348. '?&#x192;&#x192;?&#x192;&#x201A;?&#x201A;??&#x192;?'=>'ddii',
  1349. // 3 character syllables - doubled vowels
  1350. '?&#x192;&#x2022;?&#x201A;??&#x192;?'=>'faa','?&#x192;&#x2022;?&#x201A;§?&#x192;?'=>'fee','?&#x192;&#x2022;?&#x201A;??&#x192;?'=>'fii','?&#x192;&#x2022;?&#x201A;Š?&#x192;?'=>'foo',
  1351. '?&#x192;&#x2022;?&#x192;??&#x192;?'=>'fyaa','?&#x192;&#x2022;?&#x201A;§?&#x192;?'=>'fyee','?&#x192;&#x2022;?&#x201A;??&#x192;?'=>'fyii','?&#x192;&#x2022;?&#x192;§?&#x192;?'=>'fyoo','?&#x192;&#x2022;?&#x192;??&#x192;?'=>'fyuu',
  1352. '?&#x192;&#x2019;?&#x192;??&#x192;?'=>'hyaa','?&#x192;&#x2019;?&#x201A;§?&#x192;?'=>'hyee','?&#x192;&#x2019;?&#x201A;??&#x192;?'=>'hyii','?&#x192;&#x2019;?&#x192;§?&#x192;?'=>'hyoo','?&#x192;&#x2019;?&#x192;??&#x192;?'=>'hyuu',
  1353. '?&#x192;&#x201C;?&#x192;??&#x192;?'=>'byaa','?&#x192;&#x201C;?&#x201A;§?&#x192;?'=>'byee','?&#x192;&#x201C;?&#x201A;??&#x192;?'=>'byii','?&#x192;&#x201C;?&#x192;§?&#x192;?'=>'byoo','?&#x192;&#x201C;?&#x192;??&#x192;?'=>'byuu',
  1354. '?&#x192;&#x201D;?&#x192;??&#x192;?'=>'pyaa','?&#x192;&#x201D;?&#x201A;§?&#x192;?'=>'pyee','?&#x192;&#x201D;?&#x201A;??&#x192;?'=>'pyii','?&#x192;&#x201D;?&#x192;§?&#x192;?'=>'pyoo','?&#x192;&#x201D;?&#x192;??&#x192;?'=>'pyuu',
  1355. '?&#x201A;­?&#x192;??&#x192;?'=>'kyaa','?&#x201A;­?&#x201A;§?&#x192;?'=>'kyee','?&#x201A;­?&#x201A;??&#x192;?'=>'kyii','?&#x201A;­?&#x192;§?&#x192;?'=>'kyoo','?&#x201A;­?&#x192;??&#x192;?'=>'kyuu',
  1356. '?&#x201A;Ž?&#x192;??&#x192;?'=>'gyaa','?&#x201A;Ž?&#x201A;§?&#x192;?'=>'gyee','?&#x201A;Ž?&#x201A;??&#x192;?'=>'gyii','?&#x201A;Ž?&#x192;§?&#x192;?'=>'gyoo','?&#x201A;Ž?&#x192;??&#x192;?'=>'gyuu',
  1357. '?&#x192;&#x;?&#x192;??&#x192;?'=>'myaa','?&#x192;&#x;?&#x201A;§?&#x192;?'=>'myee','?&#x192;&#x;?&#x201A;??&#x192;?'=>'myii','?&#x192;&#x;?&#x192;§?&#x192;?'=>'myoo','?&#x192;&#x;?&#x192;??&#x192;?'=>'myuu',
  1358. '?&#x192;&#x2039;?&#x192;??&#x192;?'=>'nyaa','?&#x192;&#x2039;?&#x201A;§?&#x192;?'=>'nyee','?&#x192;&#x2039;?&#x201A;??&#x192;?'=>'nyii','?&#x192;&#x2039;?&#x192;§?&#x192;?'=>'nyoo','?&#x192;&#x2039;?&#x192;??&#x192;?'=>'nyuu',
  1359. '?&#x192;??&#x192;??&#x192;?'=>'ryaa','?&#x192;??&#x201A;§?&#x192;?'=>'ryee','?&#x192;??&#x201A;??&#x192;?'=>'ryii','?&#x192;??&#x192;§?&#x192;?'=>'ryoo','?&#x192;??&#x192;??&#x192;?'=>'ryuu',
  1360. '?&#x201A;??&#x192;??&#x192;?'=>'shaa','?&#x201A;??&#x201A;§?&#x192;?'=>'shee','?&#x201A;??&#x192;?'=>'shii','?&#x201A;??&#x192;§?&#x192;?'=>'shoo','?&#x201A;??&#x192;??&#x192;?'=>'shuu',
  1361. '?&#x201A;¸?&#x192;??&#x192;?'=>'jaa','?&#x201A;¸?&#x201A;§?&#x192;?'=>'jee','?&#x201A;¸?&#x192;?'=>'jii','?&#x201A;¸?&#x192;§?&#x192;?'=>'joo','?&#x201A;¸?&#x192;??&#x192;?'=>'juu',
  1362. '?&#x201A;š?&#x201A;??&#x192;?'=>'swaa','?&#x201A;š?&#x201A;§?&#x192;?'=>'swee','?&#x201A;š?&#x201A;??&#x192;?'=>'swii','?&#x201A;š?&#x201A;Š?&#x192;?'=>'swoo','?&#x201A;š?&#x201A;??&#x192;?'=>'swuu',
  1363. '?&#x192;&#x2021;?&#x201A;??&#x192;?'=>'daa','?&#x192;&#x2021;?&#x201A;§?&#x192;?'=>'dee','?&#x192;&#x2021;?&#x201A;??&#x192;?'=>'dii','?&#x192;&#x2021;?&#x201A;Š?&#x192;?'=>'doo','?&#x192;&#x2021;?&#x201A;??&#x192;?'=>'duu',
  1364. '?&#x192; ?&#x192;??&#x192;?'=>'chaa','?&#x192; ?&#x201A;§?&#x192;?'=>'chee','?&#x192; ?&#x192;?'=>'chii','?&#x192; ?&#x192;§?&#x192;?'=>'choo','?&#x192; ?&#x192;??&#x192;?'=>'chuu',
  1365. '?&#x192;&#x201A;?&#x192;??&#x192;?'=>'dyaa','?&#x192;&#x201A;?&#x201A;§?&#x192;?'=>'dyee','?&#x192;&#x201A;?&#x201A;??&#x192;?'=>'dyii','?&#x192;&#x201A;?&#x192;§?&#x192;?'=>'dyoo','?&#x192;&#x201A;?&#x192;??&#x192;?'=>'dyuu',
  1366. '?&#x192;&#x201E;?&#x192;??&#x192;?'=>'tsaa','?&#x192;&#x201E;?&#x201A;§?&#x192;?'=>'tsee','?&#x192;&#x201E;?&#x201A;??&#x192;?'=>'tsii','?&#x192;&#x201E;?&#x192;§?&#x192;?'=>'tsoo','?&#x192;&#x201E;?&#x192;?'=>'tsuu',
  1367. '?&#x192;&#x2C6;?&#x201A;??&#x192;?'=>'twaa','?&#x192;&#x2C6;?&#x201A;§?&#x192;?'=>'twee','?&#x192;&#x2C6;?&#x201A;??&#x192;?'=>'twii','?&#x192;&#x2C6;?&#x201A;Š?&#x192;?'=>'twoo','?&#x192;&#x2C6;?&#x201A;??&#x192;?'=>'twuu',
  1368. '?&#x192;&#x2030;?&#x201A;??&#x192;?'=>'dwaa','?&#x192;&#x2030;?&#x201A;§?&#x192;?'=>'dwee','?&#x192;&#x2030;?&#x201A;??&#x192;?'=>'dwii','?&#x192;&#x2030;?&#x201A;Š?&#x192;?'=>'dwoo','?&#x192;&#x2030;?&#x201A;??&#x192;?'=>'dwuu',
  1369. '?&#x201A;??&#x201A;??&#x192;?'=>'whaa','?&#x201A;??&#x201A;§?&#x192;?'=>'whee','?&#x201A;??&#x201A;??&#x192;?'=>'whii','?&#x201A;??&#x201A;Š?&#x192;?'=>'whoo','?&#x201A;??&#x201A;??&#x192;?'=>'whuu',
  1370. '?&#x192;´?&#x192;??&#x192;?'=>'vyaa','?&#x192;´?&#x201A;§?&#x192;?'=>'vyee','?&#x192;´?&#x201A;??&#x192;?'=>'vyii','?&#x192;´?&#x192;§?&#x192;?'=>'vyoo','?&#x192;´?&#x192;??&#x192;?'=>'vyuu',
  1371. '?&#x192;´?&#x201A;??&#x192;?'=>'vaa','?&#x192;´?&#x201A;§?&#x192;?'=>'vee','?&#x192;´?&#x201A;??&#x192;?'=>'vii','?&#x192;´?&#x201A;Š?&#x192;?'=>'voo','?&#x192;´?&#x192;?'=>'vuu',
  1372. '?&#x201A;??&#x201A;§?&#x192;?'=>'wee','?&#x201A;??&#x201A;??&#x192;?'=>'wii',
  1373. '?&#x201A;¤?&#x201A;§?&#x192;?'=>'yee',
  1374. '?&#x192;&#x2020;?&#x201A;??&#x192;?'=>'tii',
  1375. '?&#x192;&#x201A;?&#x201A;??&#x192;?'=>'dii',
  1376. // 3 character syllables - doubled consonants
  1377. '?&#x192;&#x192;?&#x192;&#x201C;?&#x192;?'=>'bbya','?&#x192;&#x192;?&#x192;&#x201C;?&#x201A;§'=>'bbye','?&#x192;&#x192;?&#x192;&#x201C;?&#x201A;?'=>'bbyi','?&#x192;&#x192;?&#x192;&#x201C;?&#x192;§'=>'bbyo','?&#x192;&#x192;?&#x192;&#x201C;?&#x192;?'=>'bbyu',
  1378. '?&#x192;&#x192;?&#x192;&#x201D;?&#x192;?'=>'ppya','?&#x192;&#x192;?&#x192;&#x201D;?&#x201A;§'=>'ppye','?&#x192;&#x192;?&#x192;&#x201D;?&#x201A;?'=>'ppyi','?&#x192;&#x192;?&#x192;&#x201D;?&#x192;§'=>'ppyo','?&#x192;&#x192;?&#x192;&#x201D;?&#x192;?'=>'ppyu',
  1379. '?&#x192;&#x192;?&#x201A;­?&#x192;?'=>'kkya','?&#x192;&#x192;?&#x201A;­?&#x201A;§'=>'kkye','?&#x192;&#x192;?&#x201A;­?&#x201A;?'=>'kkyi','?&#x192;&#x192;?&#x201A;­?&#x192;§'=>'kkyo','?&#x192;&#x192;?&#x201A;­?&#x192;?'=>'kkyu',
  1380. '?&#x192;&#x192;?&#x201A;Ž?&#x192;?'=>'ggya','?&#x192;&#x192;?&#x201A;Ž?&#x201A;§'=>'ggye','?&#x192;&#x192;?&#x201A;Ž?&#x201A;?'=>'ggyi','?&#x192;&#x192;?&#x201A;Ž?&#x192;§'=>'ggyo','?&#x192;&#x192;?&#x201A;Ž?&#x192;?'=>'ggyu',
  1381. '?&#x192;&#x192;?&#x192;&#x;?&#x192;?'=>'mmya','?&#x192;&#x192;?&#x192;&#x;?&#x201A;§'=>'mmye','?&#x192;&#x192;?&#x192;&#x;?&#x201A;?'=>'mmyi','?&#x192;&#x192;?&#x192;&#x;?&#x192;§'=>'mmyo','?&#x192;&#x192;?&#x192;&#x;?&#x192;?'=>'mmyu',
  1382. '?&#x192;&#x192;?&#x192;&#x2039;?&#x192;?'=>'nnya','?&#x192;&#x192;?&#x192;&#x2039;?&#x201A;§'=>'nnye','?&#x192;&#x192;?&#x192;&#x2039;?&#x201A;?'=>'nnyi','?&#x192;&#x192;?&#x192;&#x2039;?&#x192;§'=>'nnyo','?&#x192;&#x192;?&#x192;&#x2039;?&#x192;?'=>'nnyu',
  1383. '?&#x192;&#x192;?&#x192;??&#x192;?'=>'rrya','?&#x192;&#x192;?&#x192;??&#x201A;§'=>'rrye','?&#x192;&#x192;?&#x192;??&#x201A;?'=>'rryi','?&#x192;&#x192;?&#x192;??&#x192;§'=>'rryo','?&#x192;&#x192;?&#x192;??&#x192;?'=>'rryu',
  1384. '?&#x192;&#x192;?&#x201A;??&#x192;?'=>'ssha','?&#x192;&#x192;?&#x201A;??&#x201A;§'=>'sshe','?&#x192;&#x192;?&#x201A;?'=>'sshi','?&#x192;&#x192;?&#x201A;??&#x192;§'=>'ssho','?&#x192;&#x192;?&#x201A;??&#x192;?'=>'sshu',
  1385. '?&#x192;&#x192;?&#x192; ?&#x192;?'=>'ccha','?&#x192;&#x192;?&#x192; ?&#x201A;§'=>'cche','?&#x192;&#x192;?&#x192; '=>'cchi','?&#x192;&#x192;?&#x192; ?&#x192;§'=>'ccho','?&#x192;&#x192;?&#x192; ?&#x192;?'=>'cchu',
  1386. '?&#x192;&#x192;?&#x192;&#x2020;?&#x201A;?'=>'tti',
  1387. '?&#x192;&#x192;?&#x192;&#x201A;?&#x201A;?'=>'ddi',
  1388. // 3 character syllables - doubled vowel and consonants
  1389. '?&#x192;&#x192;?&#x192;??&#x192;?'=>'bbaa','?&#x192;&#x192;?&#x192;&#x2122;?&#x192;?'=>'bbee','?&#x192;&#x192;?&#x192;&#x201C;?&#x192;?'=>'bbii','?&#x192;&#x192;?&#x192;&#x153;?&#x192;?'=>'bboo','?&#x192;&#x192;?&#x192;&#x2013;?&#x192;?'=>'bbuu',
  1390. '?&#x192;&#x192;?&#x192;&#x2018;?&#x192;?'=>'ppaa','?&#x192;&#x192;?&#x192;&#x161;?&#x192;?'=>'ppee','?&#x192;&#x192;?&#x192;&#x201D;?&#x192;?'=>'ppii','?&#x192;&#x192;?&#x192;??&#x192;?'=>'ppoo','?&#x192;&#x192;?&#x192;&#x2014;?&#x192;?'=>'ppuu',
  1391. '?&#x192;&#x192;?&#x201A;??&#x192;?'=>'kkee','?&#x192;&#x192;?&#x201A;­?&#x192;?'=>'kkii','?&#x192;&#x192;?&#x201A;??&#x192;?'=>'kkoo','?&#x192;&#x192;?&#x201A;??&#x192;?'=>'kkuu','?&#x192;&#x192;?&#x201A;??&#x192;?'=>'kkaa',
  1392. '?&#x192;&#x192;?&#x201A;??&#x192;?'=>'ggaa','?&#x192;&#x192;?&#x201A;??&#x192;?'=>'ggee','?&#x192;&#x192;?&#x201A;Ž?&#x192;?'=>'ggii','?&#x192;&#x192;?&#x201A;´?&#x192;?'=>'ggoo','?&#x192;&#x192;?&#x201A;°?&#x192;?'=>'gguu',
  1393. '?&#x192;&#x192;?&#x192;&#x17E;?&#x192;?'=>'maa','?&#x192;&#x192;?&#x192;??&#x192;?'=>'mee','?&#x192;&#x192;?&#x192;&#x;?&#x192;?'=>'mii','?&#x192;&#x192;?&#x192;??&#x192;?'=>'moo','?&#x192;&#x192;?&#x192; ?&#x192;?'=>'muu',
  1394. '?&#x192;&#x192;?&#x192;&#x160;?&#x192;?'=>'nnaa','?&#x192;&#x192;?&#x192;??&#x192;?'=>'nnee','?&#x192;&#x192;?&#x192;&#x2039;?&#x192;?'=>'nnii','?&#x192;&#x192;?&#x192;&#x17D;?&#x192;?'=>'nnoo','?&#x192;&#x192;?&#x192;&#x152;?&#x192;?'=>'nnuu',
  1395. '?&#x192;&#x192;?&#x192;Š?&#x192;?'=>'rraa','?&#x192;&#x192;?&#x192;??&#x192;?'=>'rree','?&#x192;&#x192;?&#x192;??&#x192;?'=>'rrii','?&#x192;&#x192;?&#x192;­?&#x192;?'=>'rroo','?&#x192;&#x192;?&#x192;??&#x192;?'=>'rruu',
  1396. '?&#x192;&#x192;?&#x201A;??&#x192;?'=>'ssaa','?&#x192;&#x192;?&#x201A;??&#x192;?'=>'ssee','?&#x192;&#x192;?&#x201A;??&#x192;?'=>'sshii','?&#x192;&#x192;?&#x201A;??&#x192;?'=>'ssoo','?&#x192;&#x192;?&#x201A;š?&#x192;?'=>'ssuu',
  1397. '?&#x192;&#x192;?&#x201A;??&#x192;?'=>'zzaa','?&#x192;&#x192;?&#x201A;??&#x192;?'=>'zzee','?&#x192;&#x192;?&#x201A;¸?&#x192;?'=>'jjii','?&#x192;&#x192;?&#x201A;ž?&#x192;?'=>'zzoo','?&#x192;&#x192;?&#x201A;??&#x192;?'=>'zzuu',
  1398. '?&#x192;&#x192;?&#x201A;??&#x192;?'=>'ttaa','?&#x192;&#x192;?&#x192;&#x2020;?&#x192;?'=>'ttee','?&#x192;&#x192;?&#x192; ?&#x192;?'=>'chii','?&#x192;&#x192;?&#x192;&#x2C6;?&#x192;?'=>'ttoo','?&#x192;&#x192;?&#x192;&#x201E;?&#x192;?'=>'ttsuu',
  1399. '?&#x192;&#x192;?&#x192;&#x20AC;?&#x192;?'=>'ddaa','?&#x192;&#x192;?&#x192;&#x2021;?&#x192;?'=>'ddee','?&#x192;&#x192;?&#x192;&#x201A;?&#x192;?'=>'ddii','?&#x192;&#x192;?&#x192;&#x2030;?&#x192;?'=>'ddoo','?&#x192;&#x192;?&#x192;&#x2026;?&#x192;?'=>'dduu',
  1400. // 2 character syllables - normal
  1401. '?&#x192;&#x2022;?&#x201A;?'=>'fa','?&#x192;&#x2022;?&#x201A;§'=>'fe','?&#x192;&#x2022;?&#x201A;?'=>'fi','?&#x192;&#x2022;?&#x201A;Š'=>'fo','?&#x192;&#x2022;?&#x201A;?'=>'fu',
  1402. // '?&#x192;&#x2022;?&#x192;?'=>'fya','?&#x192;&#x2022;?&#x201A;§'=>'fye','?&#x192;&#x2022;?&#x201A;?'=>'fyi','?&#x192;&#x2022;?&#x192;§'=>'fyo','?&#x192;&#x2022;?&#x192;?'=>'fyu',
  1403. '?&#x192;&#x2022;?&#x192;?'=>'fa','?&#x192;&#x2022;?&#x201A;§'=>'fe','?&#x192;&#x2022;?&#x201A;?'=>'fi','?&#x192;&#x2022;?&#x192;§'=>'fo','?&#x192;&#x2022;?&#x192;?'=>'fu',
  1404. '?&#x192;&#x2019;?&#x192;?'=>'hya','?&#x192;&#x2019;?&#x201A;§'=>'hye','?&#x192;&#x2019;?&#x201A;?'=>'hyi','?&#x192;&#x2019;?&#x192;§'=>'hyo','?&#x192;&#x2019;?&#x192;?'=>'hyu',
  1405. '?&#x192;&#x201C;?&#x192;?'=>'bya','?&#x192;&#x201C;?&#x201A;§'=>'bye','?&#x192;&#x201C;?&#x201A;?'=>'byi','?&#x192;&#x201C;?&#x192;§'=>'byo','?&#x192;&#x201C;?&#x192;?'=>'byu',
  1406. '?&#x192;&#x201D;?&#x192;?'=>'pya','?&#x192;&#x201D;?&#x201A;§'=>'pye','?&#x192;&#x201D;?&#x201A;?'=>'pyi','?&#x192;&#x201D;?&#x192;§'=>'pyo','?&#x192;&#x201D;?&#x192;?'=>'pyu',
  1407. '?&#x201A;­?&#x192;?'=>'kya','?&#x201A;­?&#x201A;§'=>'kye','?&#x201A;­?&#x201A;?'=>'kyi','?&#x201A;­?&#x192;§'=>'kyo','?&#x201A;­?&#x192;?'=>'kyu',
  1408. '?&#x201A;Ž?&#x192;?'=>'gya','?&#x201A;Ž?&#x201A;§'=>'gye','?&#x201A;Ž?&#x201A;?'=>'gyi','?&#x201A;Ž?&#x192;§'=>'gyo','?&#x201A;Ž?&#x192;?'=>'gyu',
  1409. '?&#x192;&#x;?&#x192;?'=>'mya','?&#x192;&#x;?&#x201A;§'=>'mye','?&#x192;&#x;?&#x201A;?'=>'myi','?&#x192;&#x;?&#x192;§'=>'myo','?&#x192;&#x;?&#x192;?'=>'myu',
  1410. '?&#x192;&#x2039;?&#x192;?'=>'nya','?&#x192;&#x2039;?&#x201A;§'=>'nye','?&#x192;&#x2039;?&#x201A;?'=>'nyi','?&#x192;&#x2039;?&#x192;§'=>'nyo','?&#x192;&#x2039;?&#x192;?'=>'nyu',
  1411. '?&#x192;??&#x192;?'=>'rya','?&#x192;??&#x201A;§'=>'rye','?&#x192;??&#x201A;?'=>'ryi','?&#x192;??&#x192;§'=>'ryo','?&#x192;??&#x192;?'=>'ryu',
  1412. '?&#x201A;??&#x192;?'=>'sha','?&#x201A;??&#x201A;§'=>'she','?&#x201A;??&#x192;§'=>'sho','?&#x201A;??&#x192;?'=>'shu',
  1413. '?&#x201A;¸?&#x192;?'=>'ja','?&#x201A;¸?&#x201A;§'=>'je','?&#x201A;¸?&#x192;§'=>'jo','?&#x201A;¸?&#x192;?'=>'ju',
  1414. '?&#x201A;š?&#x201A;?'=>'swa','?&#x201A;š?&#x201A;§'=>'swe','?&#x201A;š?&#x201A;?'=>'swi','?&#x201A;š?&#x201A;Š'=>'swo','?&#x201A;š?&#x201A;?'=>'swu',
  1415. '?&#x192;&#x2021;?&#x201A;?'=>'da','?&#x192;&#x2021;?&#x201A;§'=>'de','?&#x192;&#x2021;?&#x201A;?'=>'di','?&#x192;&#x2021;?&#x201A;Š'=>'do','?&#x192;&#x2021;?&#x201A;?'=>'du',
  1416. '?&#x192; ?&#x192;?'=>'cha','?&#x192; ?&#x201A;§'=>'che','?&#x192; '=>'chi','?&#x192; ?&#x192;§'=>'cho','?&#x192; ?&#x192;?'=>'chu',
  1417. // '?&#x192;&#x201A;?&#x192;?'=>'dya','?&#x192;&#x201A;?&#x201A;§'=>'dye','?&#x192;&#x201A;?&#x201A;?'=>'dyi','?&#x192;&#x201A;?&#x192;§'=>'dyo','?&#x192;&#x201A;?&#x192;?'=>'dyu',
  1418. '?&#x192;&#x201E;?&#x192;?'=>'tsa','?&#x192;&#x201E;?&#x201A;§'=>'tse','?&#x192;&#x201E;?&#x201A;?'=>'tsi','?&#x192;&#x201E;?&#x192;§'=>'tso','?&#x192;&#x201E;'=>'tsu',
  1419. '?&#x192;&#x2C6;?&#x201A;?'=>'twa','?&#x192;&#x2C6;?&#x201A;§'=>'twe','?&#x192;&#x2C6;?&#x201A;?'=>'twi','?&#x192;&#x2C6;?&#x201A;Š'=>'two','?&#x192;&#x2C6;?&#x201A;?'=>'twu',
  1420. '?&#x192;&#x2030;?&#x201A;?'=>'dwa','?&#x192;&#x2030;?&#x201A;§'=>'dwe','?&#x192;&#x2030;?&#x201A;?'=>'dwi','?&#x192;&#x2030;?&#x201A;Š'=>'dwo','?&#x192;&#x2030;?&#x201A;?'=>'dwu',
  1421. '?&#x201A;??&#x201A;?'=>'wha','?&#x201A;??&#x201A;§'=>'whe','?&#x201A;??&#x201A;?'=>'whi','?&#x201A;??&#x201A;Š'=>'who','?&#x201A;??&#x201A;?'=>'whu',
  1422. '?&#x192;´?&#x192;?'=>'vya','?&#x192;´?&#x201A;§'=>'vye','?&#x192;´?&#x201A;?'=>'vyi','?&#x192;´?&#x192;§'=>'vyo','?&#x192;´?&#x192;?'=>'vyu',
  1423. '?&#x192;´?&#x201A;?'=>'va','?&#x192;´?&#x201A;§'=>'ve','?&#x192;´?&#x201A;?'=>'vi','?&#x192;´?&#x201A;Š'=>'vo','?&#x192;´'=>'vu',
  1424. '?&#x201A;??&#x201A;§'=>'we','?&#x201A;??&#x201A;?'=>'wi',
  1425. '?&#x201A;¤?&#x201A;§'=>'ye',
  1426. '?&#x192;&#x2020;?&#x201A;?'=>'ti',
  1427. '?&#x192;&#x201A;?&#x201A;?'=>'di',
  1428. // 2 character syllables - doubled vocal
  1429. '?&#x201A;??&#x192;?'=>'aa','?&#x201A;¨?&#x192;?'=>'ee','?&#x201A;¤?&#x192;?'=>'ii','?&#x201A;??&#x192;?'=>'oo','?&#x201A;??&#x192;?'=>'uu',
  1430. '?&#x192;&#x20AC;?&#x192;?'=>'daa','?&#x192;&#x2021;?&#x192;?'=>'dee','?&#x192;&#x201A;?&#x192;?'=>'dii','?&#x192;&#x2030;?&#x192;?'=>'doo','?&#x192;&#x2026;?&#x192;?'=>'duu',
  1431. '?&#x192;??&#x192;?'=>'haa','?&#x192;&#x2DC;?&#x192;?'=>'hee','?&#x192;&#x2019;?&#x192;?'=>'hii','?&#x192;&#x203A;?&#x192;?'=>'hoo','?&#x192;&#x2022;?&#x192;?'=>'fuu',
  1432. '?&#x192;??&#x192;?'=>'baa','?&#x192;&#x2122;?&#x192;?'=>'bee','?&#x192;&#x201C;?&#x192;?'=>'bii','?&#x192;&#x153;?&#x192;?'=>'boo','?&#x192;&#x2013;?&#x192;?'=>'buu',
  1433. '?&#x192;&#x2018;?&#x192;?'=>'paa','?&#x192;&#x161;?&#x192;?'=>'pee','?&#x192;&#x201D;?&#x192;?'=>'pii','?&#x192;??&#x192;?'=>'poo','?&#x192;&#x2014;?&#x192;?'=>'puu',
  1434. '?&#x201A;??&#x192;?'=>'kee','?&#x201A;­?&#x192;?'=>'kii','?&#x201A;??&#x192;?'=>'koo','?&#x201A;??&#x192;?'=>'kuu','?&#x201A;??&#x192;?'=>'kaa',
  1435. '?&#x201A;??&#x192;?'=>'gaa','?&#x201A;??&#x192;?'=>'gee','?&#x201A;Ž?&#x192;?'=>'gii','?&#x201A;´?&#x192;?'=>'goo','?&#x201A;°?&#x192;?'=>'guu',
  1436. '?&#x192;&#x17E;?&#x192;?'=>'maa','?&#x192;??&#x192;?'=>'mee','?&#x192;&#x;?&#x192;?'=>'mii','?&#x192;??&#x192;?'=>'moo','?&#x192; ?&#x192;?'=>'muu',
  1437. '?&#x192;&#x160;?&#x192;?'=>'naa','?&#x192;??&#x192;?'=>'nee','?&#x192;&#x2039;?&#x192;?'=>'nii','?&#x192;&#x17D;?&#x192;?'=>'noo','?&#x192;&#x152;?&#x192;?'=>'nuu',
  1438. '?&#x192;Š?&#x192;?'=>'raa','?&#x192;??&#x192;?'=>'ree','?&#x192;??&#x192;?'=>'rii','?&#x192;­?&#x192;?'=>'roo','?&#x192;??&#x192;?'=>'ruu',
  1439. '?&#x201A;??&#x192;?'=>'saa','?&#x201A;??&#x192;?'=>'see','?&#x201A;??&#x192;?'=>'shii','?&#x201A;??&#x192;?'=>'soo','?&#x201A;š?&#x192;?'=>'suu',
  1440. '?&#x201A;??&#x192;?'=>'zaa','?&#x201A;??&#x192;?'=>'zee','?&#x201A;¸?&#x192;?'=>'jii','?&#x201A;ž?&#x192;?'=>'zoo','?&#x201A;??&#x192;?'=>'zuu',
  1441. '?&#x201A;??&#x192;?'=>'taa','?&#x192;&#x2020;?&#x192;?'=>'tee','?&#x192; ?&#x192;?'=>'chii','?&#x192;&#x2C6;?&#x192;?'=>'too','?&#x192;&#x201E;?&#x192;?'=>'tsuu',
  1442. '?&#x192;??&#x192;?'=>'waa','?&#x192;??&#x192;?'=>'woo',
  1443. '?&#x192;¤?&#x192;?'=>'yaa','?&#x192;¨?&#x192;?'=>'yoo','?&#x192;??&#x192;?'=>'yuu',
  1444. '?&#x192;??&#x192;?'=>'kaa','?&#x192;??&#x192;?'=>'kee',
  1445. // old characters
  1446. '?&#x192;??&#x192;?'=>'wee','?&#x192;°?&#x192;?'=>'wii',
  1447. // seperate katakana 'n'
  1448. '?&#x192;??&#x201A;?'=>'n_a','?&#x192;??&#x201A;¨'=>'n_e','?&#x192;??&#x201A;¤'=>'n_i','?&#x192;??&#x201A;?'=>'n_o','?&#x192;??&#x201A;?'=>'n_u',
  1449. '?&#x192;??&#x192;¤'=>'n_ya','?&#x192;??&#x192;¨'=>'n_yo','?&#x192;??&#x192;?'=>'n_yu',
  1450. // 2 character syllables - doubled consonants
  1451. '?&#x192;&#x192;?&#x192;?'=>'bba','?&#x192;&#x192;?&#x192;&#x2122;'=>'bbe','?&#x192;&#x192;?&#x192;&#x201C;'=>'bbi','?&#x192;&#x192;?&#x192;&#x153;'=>'bbo','?&#x192;&#x192;?&#x192;&#x2013;'=>'bbu',
  1452. '?&#x192;&#x192;?&#x192;&#x2018;'=>'ppa','?&#x192;&#x192;?&#x192;&#x161;'=>'ppe','?&#x192;&#x192;?&#x192;&#x201D;'=>'ppi','?&#x192;&#x192;?&#x192;?'=>'ppo','?&#x192;&#x192;?&#x192;&#x2014;'=>'ppu',
  1453. '?&#x192;&#x192;?&#x201A;?'=>'kke','?&#x192;&#x192;?&#x201A;­'=>'kki','?&#x192;&#x192;?&#x201A;?'=>'kko','?&#x192;&#x192;?&#x201A;?'=>'kku','?&#x192;&#x192;?&#x201A;?'=>'kka',
  1454. '?&#x192;&#x192;?&#x201A;?'=>'gga','?&#x192;&#x192;?&#x201A;?'=>'gge','?&#x192;&#x192;?&#x201A;Ž'=>'ggi','?&#x192;&#x192;?&#x201A;´'=>'ggo','?&#x192;&#x192;?&#x201A;°'=>'ggu',
  1455. '?&#x192;&#x192;?&#x192;&#x17E;'=>'ma','?&#x192;&#x192;?&#x192;?'=>'me','?&#x192;&#x192;?&#x192;&#x;'=>'mi','?&#x192;&#x192;?&#x192;?'=>'mo','?&#x192;&#x192;?&#x192; '=>'mu',
  1456. '?&#x192;&#x192;?&#x192;&#x160;'=>'nna','?&#x192;&#x192;?&#x192;?'=>'nne','?&#x192;&#x192;?&#x192;&#x2039;'=>'nni','?&#x192;&#x192;?&#x192;&#x17D;'=>'nno','?&#x192;&#x192;?&#x192;&#x152;'=>'nnu',
  1457. '?&#x192;&#x192;?&#x192;Š'=>'rra','?&#x192;&#x192;?&#x192;?'=>'rre','?&#x192;&#x192;?&#x192;?'=>'rri','?&#x192;&#x192;?&#x192;­'=>'rro','?&#x192;&#x192;?&#x192;?'=>'rru',
  1458. '?&#x192;&#x192;?&#x201A;?'=>'ssa','?&#x192;&#x192;?&#x201A;?'=>'sse','?&#x192;&#x192;?&#x201A;?'=>'sshi','?&#x192;&#x192;?&#x201A;?'=>'sso','?&#x192;&#x192;?&#x201A;š'=>'ssu',
  1459. '?&#x192;&#x192;?&#x201A;?'=>'zza','?&#x192;&#x192;?&#x201A;?'=>'zze','?&#x192;&#x192;?&#x201A;¸'=>'jji','?&#x192;&#x192;?&#x201A;ž'=>'zzo','?&#x192;&#x192;?&#x201A;?'=>'zzu',
  1460. '?&#x192;&#x192;?&#x201A;?'=>'tta','?&#x192;&#x192;?&#x192;&#x2020;'=>'tte','?&#x192;&#x192;?&#x192; '=>'cchi','?&#x192;&#x192;?&#x192;&#x2C6;'=>'tto','?&#x192;&#x192;?&#x192;&#x201E;'=>'ttsu',
  1461. '?&#x192;&#x192;?&#x192;&#x20AC;'=>'dda','?&#x192;&#x192;?&#x192;&#x2021;'=>'dde','?&#x192;&#x192;?&#x192;&#x201A;'=>'ddi','?&#x192;&#x192;?&#x192;&#x2030;'=>'ddo','?&#x192;&#x192;?&#x192;&#x2026;'=>'ddu',
  1462. // 1 character syllables
  1463. '?&#x201A;?'=>'a','?&#x201A;¨'=>'e','?&#x201A;¤'=>'i','?&#x201A;?'=>'o','?&#x201A;?'=>'u','?&#x192;?'=>'n',
  1464. '?&#x192;?'=>'ha','?&#x192;&#x2DC;'=>'he','?&#x192;&#x2019;'=>'hi','?&#x192;&#x203A;'=>'ho','?&#x192;&#x2022;'=>'fu',
  1465. '?&#x192;?'=>'ba','?&#x192;&#x2122;'=>'be','?&#x192;&#x201C;'=>'bi','?&#x192;&#x153;'=>'bo','?&#x192;&#x2013;'=>'bu',
  1466. '?&#x192;&#x2018;'=>'pa','?&#x192;&#x161;'=>'pe','?&#x192;&#x201D;'=>'pi','?&#x192;?'=>'po','?&#x192;&#x2014;'=>'pu',
  1467. '?&#x201A;?'=>'ke','?&#x201A;­'=>'ki','?&#x201A;?'=>'ko','?&#x201A;?'=>'ku','?&#x201A;?'=>'ka',
  1468. '?&#x201A;?'=>'ga','?&#x201A;?'=>'ge','?&#x201A;Ž'=>'gi','?&#x201A;´'=>'go','?&#x201A;°'=>'gu',
  1469. '?&#x192;&#x17E;'=>'ma','?&#x192;?'=>'me','?&#x192;&#x;'=>'mi','?&#x192;?'=>'mo','?&#x192; '=>'mu',
  1470. '?&#x192;&#x160;'=>'na','?&#x192;?'=>'ne','?&#x192;&#x2039;'=>'ni','?&#x192;&#x17D;'=>'no','?&#x192;&#x152;'=>'nu',
  1471. '?&#x192;Š'=>'ra','?&#x192;?'=>'re','?&#x192;?'=>'ri','?&#x192;­'=>'ro','?&#x192;?'=>'ru',
  1472. '?&#x201A;?'=>'sa','?&#x201A;?'=>'se','?&#x201A;?'=>'shi','?&#x201A;?'=>'so','?&#x201A;š'=>'su',
  1473. '?&#x201A;?'=>'za','?&#x201A;?'=>'ze','?&#x201A;¸'=>'ji','?&#x201A;ž'=>'zo','?&#x201A;?'=>'zu',
  1474. '?&#x201A;?'=>'ta','?&#x192;&#x2020;'=>'te','?&#x192; '=>'chi','?&#x192;&#x2C6;'=>'to','?&#x192;&#x201E;'=>'tsu',
  1475. '?&#x192;&#x20AC;'=>'da','?&#x192;&#x2021;'=>'de','?&#x192;&#x201A;'=>'di','?&#x192;&#x2030;'=>'do','?&#x192;&#x2026;'=>'du',
  1476. '?&#x192;?'=>'wa','?&#x192;?'=>'wo',
  1477. '?&#x192;¤'=>'ya','?&#x192;¨'=>'yo','?&#x192;?'=>'yu',
  1478. '?&#x192;?'=>'ka','?&#x192;?'=>'ke',
  1479. // old characters
  1480. '?&#x192;?'=>'we','?&#x192;°'=>'wi',
  1481. // convert what's left (probably only kicks in when something's missing above)
  1482. '?&#x201A;?'=>'a','?&#x201A;§'=>'e','?&#x201A;?'=>'i','?&#x201A;Š'=>'o','?&#x201A;?'=>'u',
  1483. '?&#x192;?'=>'ya','?&#x192;§'=>'yo','?&#x192;?'=>'yu',
  1484. // special characters
  1485. '?&#x192;?'=>'_','?&#x20AC; '=>'_',
  1486. '?&#x192;?'=>'_', // when used with hiragana (seldom), this character would not be converted otherwise
  1487. // '?&#x192;Š'=>'la','?&#x192;?'=>'le','?&#x192;?'=>'li','?&#x192;­'=>'lo','?&#x192;?'=>'lu',
  1488. // '?&#x192; ?&#x192;?'=>'cya','?&#x192; ?&#x201A;§'=>'cye','?&#x192; ?&#x201A;?'=>'cyi','?&#x192; ?&#x192;§'=>'cyo','?&#x192; ?&#x192;?'=>'cyu',
  1489. //'?&#x192;&#x2021;?&#x192;?'=>'dha','?&#x192;&#x2021;?&#x201A;§'=>'dhe','?&#x192;&#x2021;?&#x201A;?'=>'dhi','?&#x192;&#x2021;?&#x192;§'=>'dho','?&#x192;&#x2021;?&#x192;?'=>'dhu',
  1490. // '?&#x192;??&#x192;?'=>'lya','?&#x192;??&#x201A;§'=>'lye','?&#x192;??&#x201A;?'=>'lyi','?&#x192;??&#x192;§'=>'lyo','?&#x192;??&#x192;?'=>'lyu',
  1491. // '?&#x192;&#x2020;?&#x192;?'=>'tha','?&#x192;&#x2020;?&#x201A;§'=>'the','?&#x192;&#x2020;?&#x201A;?'=>'thi','?&#x192;&#x2020;?&#x192;§'=>'tho','?&#x192;&#x2020;?&#x192;?'=>'thu',
  1492. //'?&#x192;&#x2022;?&#x201A;?'=>'fwa','?&#x192;&#x2022;?&#x201A;§'=>'fwe','?&#x192;&#x2022;?&#x201A;?'=>'fwi','?&#x192;&#x2022;?&#x201A;Š'=>'fwo','?&#x192;&#x2022;?&#x201A;?'=>'fwu',
  1493. //'?&#x192; ?&#x192;?'=>'tya','?&#x192; ?&#x201A;§'=>'tye','?&#x192; ?&#x201A;?'=>'tyi','?&#x192; ?&#x192;§'=>'tyo','?&#x192; ?&#x192;?'=>'tyu',
  1494. // '?&#x201A;¸?&#x192;?'=>'jya','?&#x201A;¸?&#x201A;§'=>'jye','?&#x201A;¸?&#x201A;?'=>'jyi','?&#x201A;¸?&#x192;§'=>'jyo','?&#x201A;¸?&#x192;?'=>'jyu',
  1495. // '?&#x201A;¸?&#x192;?'=>'zha','?&#x201A;¸?&#x201A;§'=>'zhe','?&#x201A;¸?&#x201A;?'=>'zhi','?&#x201A;¸?&#x192;§'=>'zho','?&#x201A;¸?&#x192;?'=>'zhu',
  1496. //'?&#x201A;¸?&#x192;?'=>'zya','?&#x201A;¸?&#x201A;§'=>'zye','?&#x201A;¸?&#x201A;?'=>'zyi','?&#x201A;¸?&#x192;§'=>'zyo','?&#x201A;¸?&#x192;?'=>'zyu',
  1497. //'?&#x201A;??&#x192;?'=>'sya','?&#x201A;??&#x201A;§'=>'sye','?&#x201A;??&#x201A;?'=>'syi','?&#x201A;??&#x192;§'=>'syo','?&#x201A;??&#x192;?'=>'syu',
  1498. //'?&#x201A;?'=>'ci','?&#x192;&#x2022;'=>'hu',?&#x201A;?'=>'si','?&#x192; '=>'ti','?&#x192;&#x201E;'=>'tu','?&#x201A;¤'=>'yi','?&#x192;&#x201A;'=>'dzi',
  1499. // "Greeklish"
  1500. 'Î&#x201C;'=>'G','Î&#x201D;'=>'E','Î&#x2DC;'=>'Th','Î&#x203A;'=>'L','Î&#x17E;'=>'X','Π'=>'P','Î?'=>'S','Î?'=>'F','Ψ'=>'Ps',
  1501. 'Î?'=>'g','δ'=>'e','θ'=>'th','Î?'=>'l','Ξ'=>'x','?&#x20AC;'=>'p','?&#x192;'=>'s','?&#x2020;'=>'f','?&#x2C6;'=>'ps',
  1502. // Thai
  1503. '?¸ '=>'k','?¸&#x201A;'=>'kh','?¸&#x192;'=>'kh','?¸&#x201E;'=>'kh','?¸&#x2026;'=>'kh','?¸&#x2020;'=>'kh','?¸&#x2021;'=>'ng','?¸&#x2C6;'=>'ch',
  1504. '?¸&#x2030;'=>'ch','?¸&#x160;'=>'ch','?¸&#x2039;'=>'s','?¸&#x152;'=>'ch','?¸?'=>'y','?¸&#x17D;'=>'d','?¸?'=>'t','?¸?'=>'th',
  1505. '?¸&#x2018;'=>'d','?¸&#x2019;'=>'th','?¸&#x201C;'=>'n','?¸&#x201D;'=>'d','?¸&#x2022;'=>'t','?¸&#x2013;'=>'th','?¸&#x2014;'=>'th','?¸&#x2DC;'=>'th',
  1506. '?¸&#x2122;'=>'n','?¸&#x161;'=>'b','?¸&#x203A;'=>'p','?¸&#x153;'=>'ph','?¸?'=>'f','?¸&#x17E;'=>'ph','?¸&#x;'=>'f','?¸ '=>'ph',
  1507. '?¸?'=>'m','?¸?'=>'y','?¸?'=>'r','?¸¤'=>'rue','?¸¤?š&#x2026;'=>'rue','?¸?'=>'l','?¸?'=>'lue',
  1508. '?¸??š&#x2026;'=>'lue','?¸§'=>'w','?¸¨'=>'s','?¸Š'=>'s','?¸?'=>'s','?¸?'=>'h','?¸?'=>'l','?¸Ž'=>'h',
  1509. '?¸°'=>'a','?¸?'=>'a','?¸??¸?'=>'a','?¸?'=>'a','?š&#x2026;'=>'a','?¸?'=>'am','?š??¸?'=>'am',
  1510. '?¸´'=>'i','?¸?'=>'i','?¸?'=>'ue','?¸?'=>'ue','?¸¸'=>'u','?¸š'=>'u',
  1511. '?š&#x20AC;'=>'e','?š '=>'ae','?š&#x201A;'=>'o','?¸­'=>'o',
  1512. '?¸??¸??¸°'=>'ia','?¸??¸?'=>'ia','?¸??¸­?¸°'=>'uea','?¸??¸­'=>'uea','?¸??¸§?¸°'=>'ua','?¸??¸§'=>'ua',
  1513. '?š&#x192;'=>'ai','?š&#x201E;'=>'ai','?¸??¸?'=>'ai','?¸??¸?'=>'ai','?¸??¸§'=>'ao',
  1514. '?¸¸?¸?'=>'ui','?¸­?¸?'=>'oi','?¸??¸­?¸?'=>'ueai','?¸§?¸?'=>'uai',
  1515. '?¸´?¸§'=>'io','?š&#x2021;?¸§'=>'eo','?¸??¸??¸§'=>'iao',
  1516. '?š&#x2C6;'=>'','?š&#x2030;'=>'','?š&#x160;'=>'','?š&#x2039;'=>'','?š&#x2021;'=>'',
  1517. '?š&#x152;'=>'','?š&#x17D;'=>'','?š?'=>'','?¸?'=>'',
  1518. '?š&#x2020;'=>'2','?š?'=>'o','?¸?'=>'-','?š&#x161;'=>'-','?š&#x203A;'=>'-',
  1519. '?š?'=>'0','?š&#x2018;'=>'1','?š&#x2019;'=>'2','?š&#x201C;'=>'3','?š&#x201D;'=>'4',
  1520. '?š&#x2022;'=>'5','?š&#x2013;'=>'6','?š&#x2014;'=>'7','?š&#x2DC;'=>'8','?š&#x2122;'=>'9',
  1521. // Korean
  1522. '?&#x201E;?'=>'k','?&#x2026;&#x2039;'=>'kh','?&#x201E;?'=>'kk','?&#x201E;?'=>'t','?&#x2026;&#x152;'=>'th','?&#x201E;¸'=>'tt','?&#x2026;&#x201A;'=>'p',
  1523. '?&#x2026;?'=>'ph','?&#x2026;&#x192;'=>'pp','?&#x2026;&#x2C6;'=>'c','?&#x2026;&#x160;'=>'ch','?&#x2026;&#x2030;'=>'cc','?&#x2026;&#x2026;'=>'s','?&#x2026;&#x2020;'=>'ss',
  1524. '?&#x2026;&#x17D;'=>'h','?&#x2026;&#x2021;'=>'ng','?&#x201E;´'=>'n','?&#x201E;š'=>'l','?&#x2026; '=>'m', '?&#x2026;?'=>'a','?&#x2026;&#x201C;'=>'e','?&#x2026;&#x2014;'=>'o',
  1525. '?&#x2026;&#x153;'=>'wu','?&#x2026;?'=>'u','?&#x2026;?'=>'i','?&#x2026;?'=>'ay','?&#x2026;&#x201D;'=>'ey','?&#x2026;&#x161;'=>'oy','?&#x2026;&#x2DC;'=>'wa','?&#x2026;?'=>'we',
  1526. '?&#x2026;&#x;'=>'wi','?&#x2026;&#x2122;'=>'way','?&#x2026;&#x17E;'=>'wey','?&#x2026;?'=>'uy','?&#x2026;&#x2018;'=>'ya','?&#x2026;&#x2022;'=>'ye','?&#x2026;&#x203A;'=>'oy',
  1527. '?&#x2026; '=>'yu','?&#x2026;&#x2019;'=>'yay','?&#x2026;&#x2013;'=>'yey',
  1528. );