PageRenderTime 62ms CodeModel.GetById 24ms RepoModel.GetById 1ms app.codeStats 0ms

/contrib/wiki/inc/utf8.php

https://bitbucket.org/mariocesar/solmujeres
PHP | 1659 lines | 1001 code | 151 blank | 507 comment | 174 complexity | fcf58e088c765bde2f602c53f1dcbcc8 MD5 | raw file
Possible License(s): LGPL-2.1, GPL-2.0, BSD-3-Clause

Large files files are truncated, but you can click here to view the full file

  1. <?php
  2. /**
  3. * UTF8 helper functions
  4. *
  5. * @license LGPL (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_encodeFN')){
  20. /**
  21. * URL-Encode a filename to allow unicodecharacters
  22. *
  23. * Slashes are not encoded
  24. *
  25. * When the second parameter is true the string will
  26. * be encoded only if non ASCII characters are detected -
  27. * This makes it safe to run it multiple times on the
  28. * same string (default is true)
  29. *
  30. * @author Andreas Gohr <andi@splitbrain.org>
  31. * @see urlencode
  32. */
  33. function utf8_encodeFN($file,$safe=true){
  34. if($safe && preg_match('#^[a-zA-Z0-9/_\-.%]+$#',$file)){
  35. return $file;
  36. }
  37. $file = urlencode($file);
  38. $file = str_replace('%2F','/',$file);
  39. return $file;
  40. }
  41. }
  42. if(!function_exists('utf8_decodeFN')){
  43. /**
  44. * URL-Decode a filename
  45. *
  46. * This is just a wrapper around urldecode
  47. *
  48. * @author Andreas Gohr <andi@splitbrain.org>
  49. * @see urldecode
  50. */
  51. function utf8_decodeFN($file){
  52. $file = urldecode($file);
  53. return $file;
  54. }
  55. }
  56. if(!function_exists('utf8_isASCII')){
  57. /**
  58. * Checks if a string contains 7bit ASCII only
  59. *
  60. * @author Andreas Gohr <andi@splitbrain.org>
  61. */
  62. function utf8_isASCII($str){
  63. for($i=0; $i<strlen($str); $i++){
  64. if(ord($str{$i}) >127) return false;
  65. }
  66. return true;
  67. }
  68. }
  69. if(!function_exists('utf8_strip')){
  70. /**
  71. * Strips all highbyte chars
  72. *
  73. * Returns a pure ASCII7 string
  74. *
  75. * @author Andreas Gohr <andi@splitbrain.org>
  76. */
  77. function utf8_strip($str){
  78. $ascii = '';
  79. for($i=0; $i<strlen($str); $i++){
  80. if(ord($str{$i}) <128){
  81. $ascii .= $str{$i};
  82. }
  83. }
  84. return $ascii;
  85. }
  86. }
  87. if(!function_exists('utf8_check')){
  88. /**
  89. * Tries to detect if a string is in Unicode encoding
  90. *
  91. * @author <bmorel@ssi.fr>
  92. * @link http://www.php.net/manual/en/function.utf8-encode.php
  93. */
  94. function utf8_check($Str) {
  95. for ($i=0; $i<strlen($Str); $i++) {
  96. $b = ord($Str[$i]);
  97. if ($b < 0x80) continue; # 0bbbbbbb
  98. elseif (($b & 0xE0) == 0xC0) $n=1; # 110bbbbb
  99. elseif (($b & 0xF0) == 0xE0) $n=2; # 1110bbbb
  100. elseif (($b & 0xF8) == 0xF0) $n=3; # 11110bbb
  101. elseif (($b & 0xFC) == 0xF8) $n=4; # 111110bb
  102. elseif (($b & 0xFE) == 0xFC) $n=5; # 1111110b
  103. else return false; # Does not match any model
  104. for ($j=0; $j<$n; $j++) { # n bytes matching 10bbbbbb follow ?
  105. if ((++$i == strlen($Str)) || ((ord($Str[$i]) & 0xC0) != 0x80))
  106. return false;
  107. }
  108. }
  109. return true;
  110. }
  111. }
  112. if(!function_exists('utf8_strlen')){
  113. /**
  114. * Unicode aware replacement for strlen()
  115. *
  116. * utf8_decode() converts characters that are not in ISO-8859-1
  117. * to '?', which, for the purpose of counting, is alright - It's
  118. * even faster than mb_strlen.
  119. *
  120. * @author <chernyshevsky at hotmail dot com>
  121. * @see strlen()
  122. * @see utf8_decode()
  123. */
  124. function utf8_strlen($string){
  125. return strlen(utf8_decode($string));
  126. }
  127. }
  128. if(!function_exists('utf8_substr')){
  129. /**
  130. * UTF-8 aware alternative to substr
  131. *
  132. * Return part of a string given character offset (and optionally length)
  133. *
  134. * @author Harry Fuecks <hfuecks@gmail.com>
  135. * @author Chris Smith <chris@jalakai.co.uk>
  136. * @param string
  137. * @param integer number of UTF-8 characters offset (from left)
  138. * @param integer (optional) length in UTF-8 characters from offset
  139. * @return mixed string or false if failure
  140. */
  141. function utf8_substr($str, $offset, $length = null) {
  142. if(UTF8_MBSTRING){
  143. if( $length === null ){
  144. return mb_substr($str, $offset);
  145. }else{
  146. return mb_substr($str, $offset, $length);
  147. }
  148. }
  149. /*
  150. * Notes:
  151. *
  152. * no mb string support, so we'll use pcre regex's with 'u' flag
  153. * pcre only supports repetitions of less than 65536, in order to accept up to MAXINT values for
  154. * offset and length, we'll repeat a group of 65535 characters when needed (ok, up to MAXINT-65536)
  155. *
  156. * substr documentation states false can be returned in some cases (e.g. offset > string length)
  157. * mb_substr never returns false, it will return an empty string instead.
  158. *
  159. * calculating the number of characters in the string is a relatively expensive operation, so
  160. * we only carry it out when necessary. It isn't necessary for +ve offsets and no specified length
  161. */
  162. // cast parameters to appropriate types to avoid multiple notices/warnings
  163. $str = (string)$str; // generates E_NOTICE for PHP4 objects, but not PHP5 objects
  164. $offset = (int)$offset;
  165. if (!is_null($length)) $length = (int)$length;
  166. // handle trivial cases
  167. if ($length === 0) return '';
  168. if ($offset < 0 && $length < 0 && $length < $offset) return '';
  169. $offset_pattern = '';
  170. $length_pattern = '';
  171. // normalise -ve offsets (we could use a tail anchored pattern, but they are horribly slow!)
  172. if ($offset < 0) {
  173. $strlen = strlen(utf8_decode($str)); // see notes
  174. $offset = $strlen + $offset;
  175. if ($offset < 0) $offset = 0;
  176. }
  177. // establish a pattern for offset, a non-captured group equal in length to offset
  178. if ($offset > 0) {
  179. $Ox = (int)($offset/65535);
  180. $Oy = $offset%65535;
  181. if ($Ox) $offset_pattern = '(?:.{65535}){'.$Ox.'}';
  182. $offset_pattern = '^(?:'.$offset_pattern.'.{'.$Oy.'})';
  183. } else {
  184. $offset_pattern = '^'; // offset == 0; just anchor the pattern
  185. }
  186. // establish a pattern for length
  187. if (is_null($length)) {
  188. $length_pattern = '(.*)$'; // the rest of the string
  189. } else {
  190. if (!isset($strlen)) $strlen = strlen(utf8_decode($str)); // see notes
  191. if ($offset > $strlen) return ''; // another trivial case
  192. if ($length > 0) {
  193. $length = min($strlen-$offset, $length); // reduce any length that would go passed the end of the string
  194. $Lx = (int)($length/65535);
  195. $Ly = $length%65535;
  196. // +ve length requires ... a captured group of length characters
  197. if ($Lx) $length_pattern = '(?:.{65535}){'.$Lx.'}';
  198. $length_pattern = '('.$length_pattern.'.{'.$Ly.'})';
  199. } else if ($length < 0) {
  200. if ($length < ($offset - $strlen)) return '';
  201. $Lx = (int)((-$length)/65535);
  202. $Ly = (-$length)%65535;
  203. // -ve length requires ... capture everything except a group of -length characters
  204. // anchored at the tail-end of the string
  205. if ($Lx) $length_pattern = '(?:.{65535}){'.$Lx.'}';
  206. $length_pattern = '(.*)(?:'.$length_pattern.'.{'.$Ly.'})$';
  207. }
  208. }
  209. if (!preg_match('#'.$offset_pattern.$length_pattern.'#us',$str,$match)) return '';
  210. return $match[1];
  211. }
  212. }
  213. if(!function_exists('utf8_substr_replace')){
  214. /**
  215. * Unicode aware replacement for substr_replace()
  216. *
  217. * @author Andreas Gohr <andi@splitbrain.org>
  218. * @see substr_replace()
  219. */
  220. function utf8_substr_replace($string, $replacement, $start , $length=0 ){
  221. $ret = '';
  222. if($start>0) $ret .= utf8_substr($string, 0, $start);
  223. $ret .= $replacement;
  224. $ret .= utf8_substr($string, $start+$length);
  225. return $ret;
  226. }
  227. }
  228. if(!function_exists('utf8_ltrim')){
  229. /**
  230. * Unicode aware replacement for ltrim()
  231. *
  232. * @author Andreas Gohr <andi@splitbrain.org>
  233. * @see ltrim()
  234. * @return string
  235. */
  236. function utf8_ltrim($str,$charlist=''){
  237. if($charlist == '') return ltrim($str);
  238. //quote charlist for use in a characterclass
  239. $charlist = preg_replace('!([\\\\\\-\\]\\[/])!','\\\${1}',$charlist);
  240. return preg_replace('/^['.$charlist.']+/u','',$str);
  241. }
  242. }
  243. if(!function_exists('utf8_rtrim')){
  244. /**
  245. * Unicode aware replacement for rtrim()
  246. *
  247. * @author Andreas Gohr <andi@splitbrain.org>
  248. * @see rtrim()
  249. * @return string
  250. */
  251. function utf8_rtrim($str,$charlist=''){
  252. if($charlist == '') return rtrim($str);
  253. //quote charlist for use in a characterclass
  254. $charlist = preg_replace('!([\\\\\\-\\]\\[/])!','\\\${1}',$charlist);
  255. return preg_replace('/['.$charlist.']+$/u','',$str);
  256. }
  257. }
  258. if(!function_exists('utf8_trim')){
  259. /**
  260. * Unicode aware replacement for trim()
  261. *
  262. * @author Andreas Gohr <andi@splitbrain.org>
  263. * @see trim()
  264. * @return string
  265. */
  266. function utf8_trim($str,$charlist='') {
  267. if($charlist == '') return trim($str);
  268. return utf8_ltrim(utf8_rtrim($str,$charlist),$charlist);
  269. }
  270. }
  271. if(!function_exists('utf8_strtolower')){
  272. /**
  273. * This is a unicode aware replacement for strtolower()
  274. *
  275. * Uses mb_string extension if available
  276. *
  277. * @author Leo Feyer <leo@typolight.org>
  278. * @see strtolower()
  279. * @see utf8_strtoupper()
  280. */
  281. function utf8_strtolower($string){
  282. if(UTF8_MBSTRING) return mb_strtolower($string,'utf-8');
  283. global $UTF8_UPPER_TO_LOWER;
  284. return strtr($string,$UTF8_UPPER_TO_LOWER);
  285. }
  286. }
  287. if(!function_exists('utf8_strtoupper')){
  288. /**
  289. * This is a unicode aware replacement for strtoupper()
  290. *
  291. * Uses mb_string extension if available
  292. *
  293. * @author Leo Feyer <leo@typolight.org>
  294. * @see strtoupper()
  295. * @see utf8_strtoupper()
  296. */
  297. function utf8_strtoupper($string){
  298. if(UTF8_MBSTRING) return mb_strtoupper($string,'utf-8');
  299. global $UTF8_LOWER_TO_UPPER;
  300. return strtr($string,$UTF8_LOWER_TO_UPPER);
  301. }
  302. }
  303. if(!function_exists('utf8_ucfirst')){
  304. /**
  305. * UTF-8 aware alternative to ucfirst
  306. * Make a string's first character uppercase
  307. *
  308. * @author Harry Fuecks
  309. * @param string
  310. * @return string with first character as upper case (if applicable)
  311. */
  312. function utf8_ucfirst($str){
  313. switch ( utf8_strlen($str) ) {
  314. case 0:
  315. return '';
  316. case 1:
  317. return utf8_strtoupper($str);
  318. default:
  319. preg_match('/^(.{1})(.*)$/us', $str, $matches);
  320. return utf8_strtoupper($matches[1]).$matches[2];
  321. }
  322. }
  323. }
  324. if(!function_exists('utf8_ucwords')){
  325. /**
  326. * UTF-8 aware alternative to ucwords
  327. * Uppercase the first character of each word in a string
  328. *
  329. * @author Harry Fuecks
  330. * @param string
  331. * @return string with first char of each word uppercase
  332. * @see http://www.php.net/ucwords
  333. */
  334. function utf8_ucwords($str) {
  335. // Note: [\x0c\x09\x0b\x0a\x0d\x20] matches;
  336. // form feeds, horizontal tabs, vertical tabs, linefeeds and carriage returns
  337. // This corresponds to the definition of a "word" defined at http://www.php.net/ucwords
  338. $pattern = '/(^|([\x0c\x09\x0b\x0a\x0d\x20]+))([^\x0c\x09\x0b\x0a\x0d\x20]{1})[^\x0c\x09\x0b\x0a\x0d\x20]*/u';
  339. return preg_replace_callback($pattern, 'utf8_ucwords_callback',$str);
  340. }
  341. /**
  342. * Callback function for preg_replace_callback call in utf8_ucwords
  343. * You don't need to call this yourself
  344. *
  345. * @author Harry Fuecks
  346. * @param array of matches corresponding to a single word
  347. * @return string with first char of the word in uppercase
  348. * @see utf8_ucwords
  349. * @see utf8_strtoupper
  350. */
  351. function utf8_ucwords_callback($matches) {
  352. $leadingws = $matches[2];
  353. $ucfirst = utf8_strtoupper($matches[3]);
  354. $ucword = utf8_substr_replace(ltrim($matches[0]),$ucfirst,0,1);
  355. return $leadingws . $ucword;
  356. }
  357. }
  358. if(!function_exists('utf8_deaccent')){
  359. /**
  360. * Replace accented UTF-8 characters by unaccented ASCII-7 equivalents
  361. *
  362. * Use the optional parameter to just deaccent lower ($case = -1) or upper ($case = 1)
  363. * letters. Default is to deaccent both cases ($case = 0)
  364. *
  365. * @author Andreas Gohr <andi@splitbrain.org>
  366. */
  367. function utf8_deaccent($string,$case=0){
  368. if($case <= 0){
  369. global $UTF8_LOWER_ACCENTS;
  370. $string = strtr($string,$UTF8_LOWER_ACCENTS);
  371. }
  372. if($case >= 0){
  373. global $UTF8_UPPER_ACCENTS;
  374. $string = strtr($string,$UTF8_UPPER_ACCENTS);
  375. }
  376. return $string;
  377. }
  378. }
  379. if(!function_exists('utf8_romanize')){
  380. /**
  381. * Romanize a non-latin string
  382. *
  383. * @author Andreas Gohr <andi@splitbrain.org>
  384. */
  385. function utf8_romanize($string){
  386. if(utf8_isASCII($string)) return $string; //nothing to do
  387. global $UTF8_ROMANIZATION;
  388. return strtr($string,$UTF8_ROMANIZATION);
  389. }
  390. }
  391. if(!function_exists('utf8_stripspecials')){
  392. /**
  393. * Removes special characters (nonalphanumeric) from a UTF-8 string
  394. *
  395. * This function adds the controlchars 0x00 to 0x19 to the array of
  396. * stripped chars (they are not included in $UTF8_SPECIAL_CHARS)
  397. *
  398. * @author Andreas Gohr <andi@splitbrain.org>
  399. * @param string $string The UTF8 string to strip of special chars
  400. * @param string $repl Replace special with this string
  401. * @param string $additional Additional chars to strip (used in regexp char class)
  402. */
  403. function utf8_stripspecials($string,$repl='',$additional=''){
  404. global $UTF8_SPECIAL_CHARS;
  405. global $UTF8_SPECIAL_CHARS2;
  406. static $specials = null;
  407. if(is_null($specials)){
  408. #$specials = preg_quote(unicode_to_utf8($UTF8_SPECIAL_CHARS), '/');
  409. $specials = preg_quote($UTF8_SPECIAL_CHARS2, '/');
  410. }
  411. return preg_replace('/['.$additional.'\x00-\x19'.$specials.']/u',$repl,$string);
  412. }
  413. }
  414. if(!function_exists('utf8_strpos')){
  415. /**
  416. * This is an Unicode aware replacement for strpos
  417. *
  418. * @author Leo Feyer <leo@typolight.org>
  419. * @see strpos()
  420. * @param string
  421. * @param string
  422. * @param integer
  423. * @return integer
  424. */
  425. function utf8_strpos($haystack, $needle, $offset=0){
  426. $comp = 0;
  427. $length = null;
  428. while (is_null($length) || $length < $offset) {
  429. $pos = strpos($haystack, $needle, $offset + $comp);
  430. if ($pos === false)
  431. return false;
  432. $length = utf8_strlen(substr($haystack, 0, $pos));
  433. if ($length < $offset)
  434. $comp = $pos - $length;
  435. }
  436. return $length;
  437. }
  438. }
  439. if(!function_exists('utf8_tohtml')){
  440. /**
  441. * Encodes UTF-8 characters to HTML entities
  442. *
  443. * @author Tom N Harris <tnharris@whoopdedo.org>
  444. * @author <vpribish at shopping dot com>
  445. * @link http://www.php.net/manual/en/function.utf8-decode.php
  446. */
  447. function utf8_tohtml ($str) {
  448. $ret = '';
  449. foreach (utf8_to_unicode($str) as $cp) {
  450. if ($cp < 0x80)
  451. $ret .= chr($cp);
  452. elseif ($cp < 0x100)
  453. $ret .= "&#$cp;";
  454. else
  455. $ret .= '&#x'.dechex($cp).';';
  456. }
  457. return $ret;
  458. }
  459. }
  460. if(!function_exists('utf8_unhtml')){
  461. /**
  462. * Decodes HTML entities to UTF-8 characters
  463. *
  464. * Convert any &#..; entity to a codepoint,
  465. * The entities flag defaults to only decoding numeric entities.
  466. * Pass HTML_ENTITIES and named entities, including &amp; &lt; etc.
  467. * are handled as well. Avoids the problem that would occur if you
  468. * had to decode "&amp;#38;&#38;amp;#38;"
  469. *
  470. * unhtmlspecialchars(utf8_unhtml($s)) -> "&#38;&#38;"
  471. * utf8_unhtml(unhtmlspecialchars($s)) -> "&&amp#38;"
  472. * what it should be -> "&#38;&amp#38;"
  473. *
  474. * @author Tom N Harris <tnharris@whoopdedo.org>
  475. * @param string $str UTF-8 encoded string
  476. * @param boolean $entities Flag controlling decoding of named entities.
  477. * @return UTF-8 encoded string with numeric (and named) entities replaced.
  478. */
  479. function utf8_unhtml($str, $entities=null) {
  480. static $decoder = null;
  481. if (is_null($decoder))
  482. $decoder = new utf8_entity_decoder();
  483. if (is_null($entities))
  484. return preg_replace_callback('/(&#([Xx])?([0-9A-Za-z]+);)/m',
  485. 'utf8_decode_numeric', $str);
  486. else
  487. return preg_replace_callback('/&(#)?([Xx])?([0-9A-Za-z]+);/m',
  488. array(&$decoder, 'decode'), $str);
  489. }
  490. }
  491. if(!function_exists('utf8_decode_numeric')){
  492. function utf8_decode_numeric($ent) {
  493. switch ($ent[2]) {
  494. case 'X':
  495. case 'x':
  496. $cp = hexdec($ent[3]);
  497. break;
  498. default:
  499. $cp = intval($ent[3]);
  500. break;
  501. }
  502. return unicode_to_utf8(array($cp));
  503. }
  504. }
  505. if(!class_exists('utf8_entity_decoder')){
  506. class utf8_entity_decoder {
  507. var $table;
  508. function utf8_entity_decoder() {
  509. $table = get_html_translation_table(HTML_ENTITIES);
  510. $table = array_flip($table);
  511. $this->table = array_map(array(&$this,'makeutf8'), $table);
  512. }
  513. function makeutf8($c) {
  514. return unicode_to_utf8(array(ord($c)));
  515. }
  516. function decode($ent) {
  517. if ($ent[1] == '#') {
  518. return utf8_decode_numeric($ent);
  519. } elseif (array_key_exists($ent[0],$this->table)) {
  520. return $this->table[$ent[0]];
  521. } else {
  522. return $ent[0];
  523. }
  524. }
  525. }
  526. }
  527. if(!function_exists('utf8_to_unicode')){
  528. /**
  529. * Takes an UTF-8 string and returns an array of ints representing the
  530. * Unicode characters. Astral planes are supported ie. the ints in the
  531. * output can be > 0xFFFF. Occurrances of the BOM are ignored. Surrogates
  532. * are not allowed.
  533. *
  534. * If $strict is set to true the function returns false if the input
  535. * string isn't a valid UTF-8 octet sequence and raises a PHP error at
  536. * level E_USER_WARNING
  537. *
  538. * Note: this function has been modified slightly in this library to
  539. * trigger errors on encountering bad bytes
  540. *
  541. * @author <hsivonen@iki.fi>
  542. * @author Harry Fuecks <hfuecks@gmail.com>
  543. * @param string UTF-8 encoded string
  544. * @param boolean Check for invalid sequences?
  545. * @return mixed array of unicode code points or false if UTF-8 invalid
  546. * @see unicode_to_utf8
  547. * @link http://hsivonen.iki.fi/php-utf8/
  548. * @link http://sourceforge.net/projects/phputf8/
  549. */
  550. function utf8_to_unicode($str,$strict=false) {
  551. $mState = 0; // cached expected number of octets after the current octet
  552. // until the beginning of the next UTF8 character sequence
  553. $mUcs4 = 0; // cached Unicode character
  554. $mBytes = 1; // cached expected number of octets in the current sequence
  555. $out = array();
  556. $len = strlen($str);
  557. for($i = 0; $i < $len; $i++) {
  558. $in = ord($str{$i});
  559. if ( $mState == 0) {
  560. // When mState is zero we expect either a US-ASCII character or a
  561. // multi-octet sequence.
  562. if (0 == (0x80 & ($in))) {
  563. // US-ASCII, pass straight through.
  564. $out[] = $in;
  565. $mBytes = 1;
  566. } else if (0xC0 == (0xE0 & ($in))) {
  567. // First octet of 2 octet sequence
  568. $mUcs4 = ($in);
  569. $mUcs4 = ($mUcs4 & 0x1F) << 6;
  570. $mState = 1;
  571. $mBytes = 2;
  572. } else if (0xE0 == (0xF0 & ($in))) {
  573. // First octet of 3 octet sequence
  574. $mUcs4 = ($in);
  575. $mUcs4 = ($mUcs4 & 0x0F) << 12;
  576. $mState = 2;
  577. $mBytes = 3;
  578. } else if (0xF0 == (0xF8 & ($in))) {
  579. // First octet of 4 octet sequence
  580. $mUcs4 = ($in);
  581. $mUcs4 = ($mUcs4 & 0x07) << 18;
  582. $mState = 3;
  583. $mBytes = 4;
  584. } else if (0xF8 == (0xFC & ($in))) {
  585. /* First octet of 5 octet sequence.
  586. *
  587. * This is illegal because the encoded codepoint must be either
  588. * (a) not the shortest form or
  589. * (b) outside the Unicode range of 0-0x10FFFF.
  590. * Rather than trying to resynchronize, we will carry on until the end
  591. * of the sequence and let the later error handling code catch it.
  592. */
  593. $mUcs4 = ($in);
  594. $mUcs4 = ($mUcs4 & 0x03) << 24;
  595. $mState = 4;
  596. $mBytes = 5;
  597. } else if (0xFC == (0xFE & ($in))) {
  598. // First octet of 6 octet sequence, see comments for 5 octet sequence.
  599. $mUcs4 = ($in);
  600. $mUcs4 = ($mUcs4 & 1) << 30;
  601. $mState = 5;
  602. $mBytes = 6;
  603. } elseif($strict) {
  604. /* Current octet is neither in the US-ASCII range nor a legal first
  605. * octet of a multi-octet sequence.
  606. */
  607. trigger_error(
  608. 'utf8_to_unicode: Illegal sequence identifier '.
  609. 'in UTF-8 at byte '.$i,
  610. E_USER_WARNING
  611. );
  612. return false;
  613. }
  614. } else {
  615. // When mState is non-zero, we expect a continuation of the multi-octet
  616. // sequence
  617. if (0x80 == (0xC0 & ($in))) {
  618. // Legal continuation.
  619. $shift = ($mState - 1) * 6;
  620. $tmp = $in;
  621. $tmp = ($tmp & 0x0000003F) << $shift;
  622. $mUcs4 |= $tmp;
  623. /**
  624. * End of the multi-octet sequence. mUcs4 now contains the final
  625. * Unicode codepoint to be output
  626. */
  627. if (0 == --$mState) {
  628. /*
  629. * Check for illegal sequences and codepoints.
  630. */
  631. // From Unicode 3.1, non-shortest form is illegal
  632. if (((2 == $mBytes) && ($mUcs4 < 0x0080)) ||
  633. ((3 == $mBytes) && ($mUcs4 < 0x0800)) ||
  634. ((4 == $mBytes) && ($mUcs4 < 0x10000)) ||
  635. (4 < $mBytes) ||
  636. // From Unicode 3.2, surrogate characters are illegal
  637. (($mUcs4 & 0xFFFFF800) == 0xD800) ||
  638. // Codepoints outside the Unicode range are illegal
  639. ($mUcs4 > 0x10FFFF)) {
  640. if($strict){
  641. trigger_error(
  642. 'utf8_to_unicode: Illegal sequence or codepoint '.
  643. 'in UTF-8 at byte '.$i,
  644. E_USER_WARNING
  645. );
  646. return false;
  647. }
  648. }
  649. if (0xFEFF != $mUcs4) {
  650. // BOM is legal but we don't want to output it
  651. $out[] = $mUcs4;
  652. }
  653. //initialize UTF8 cache
  654. $mState = 0;
  655. $mUcs4 = 0;
  656. $mBytes = 1;
  657. }
  658. } elseif($strict) {
  659. /**
  660. *((0xC0 & (*in) != 0x80) && (mState != 0))
  661. * Incomplete multi-octet sequence.
  662. */
  663. trigger_error(
  664. 'utf8_to_unicode: Incomplete multi-octet '.
  665. ' sequence in UTF-8 at byte '.$i,
  666. E_USER_WARNING
  667. );
  668. return false;
  669. }
  670. }
  671. }
  672. return $out;
  673. }
  674. }
  675. if(!function_exists('unicode_to_utf8')){
  676. /**
  677. * Takes an array of ints representing the Unicode characters and returns
  678. * a UTF-8 string. Astral planes are supported ie. the ints in the
  679. * input can be > 0xFFFF. Occurrances of the BOM are ignored. Surrogates
  680. * are not allowed.
  681. *
  682. * If $strict is set to true the function returns false if the input
  683. * array contains ints that represent surrogates or are outside the
  684. * Unicode range and raises a PHP error at level E_USER_WARNING
  685. *
  686. * Note: this function has been modified slightly in this library to use
  687. * output buffering to concatenate the UTF-8 string (faster) as well as
  688. * reference the array by it's keys
  689. *
  690. * @param array of unicode code points representing a string
  691. * @param boolean Check for invalid sequences?
  692. * @return mixed UTF-8 string or false if array contains invalid code points
  693. * @author <hsivonen@iki.fi>
  694. * @author Harry Fuecks <hfuecks@gmail.com>
  695. * @see utf8_to_unicode
  696. * @link http://hsivonen.iki.fi/php-utf8/
  697. * @link http://sourceforge.net/projects/phputf8/
  698. */
  699. function unicode_to_utf8($arr,$strict=false) {
  700. if (!is_array($arr)) return '';
  701. ob_start();
  702. foreach (array_keys($arr) as $k) {
  703. # ASCII range (including control chars)
  704. if ( ($arr[$k] >= 0) && ($arr[$k] <= 0x007f) ) {
  705. echo chr($arr[$k]);
  706. # 2 byte sequence
  707. } else if ($arr[$k] <= 0x07ff) {
  708. echo chr(0xc0 | ($arr[$k] >> 6));
  709. echo chr(0x80 | ($arr[$k] & 0x003f));
  710. # Byte order mark (skip)
  711. } else if($arr[$k] == 0xFEFF) {
  712. // nop -- zap the BOM
  713. # Test for illegal surrogates
  714. } else if ($arr[$k] >= 0xD800 && $arr[$k] <= 0xDFFF) {
  715. // found a surrogate
  716. if($strict){
  717. trigger_error(
  718. 'unicode_to_utf8: Illegal surrogate '.
  719. 'at index: '.$k.', value: '.$arr[$k],
  720. E_USER_WARNING
  721. );
  722. return false;
  723. }
  724. # 3 byte sequence
  725. } else if ($arr[$k] <= 0xffff) {
  726. echo chr(0xe0 | ($arr[$k] >> 12));
  727. echo chr(0x80 | (($arr[$k] >> 6) & 0x003f));
  728. echo chr(0x80 | ($arr[$k] & 0x003f));
  729. # 4 byte sequence
  730. } else if ($arr[$k] <= 0x10ffff) {
  731. echo chr(0xf0 | ($arr[$k] >> 18));
  732. echo chr(0x80 | (($arr[$k] >> 12) & 0x3f));
  733. echo chr(0x80 | (($arr[$k] >> 6) & 0x3f));
  734. echo chr(0x80 | ($arr[$k] & 0x3f));
  735. } elseif($strict) {
  736. trigger_error(
  737. 'unicode_to_utf8: Codepoint out of Unicode range '.
  738. 'at index: '.$k.', value: '.$arr[$k],
  739. E_USER_WARNING
  740. );
  741. // out of range
  742. return false;
  743. }
  744. }
  745. $result = ob_get_contents();
  746. ob_end_clean();
  747. return $result;
  748. }
  749. }
  750. if(!function_exists('utf8_to_utf16be')){
  751. /**
  752. * UTF-8 to UTF-16BE conversion.
  753. *
  754. * Maybe really UCS-2 without mb_string due to utf8_to_unicode limits
  755. */
  756. function utf8_to_utf16be(&$str, $bom = false) {
  757. $out = $bom ? "\xFE\xFF" : '';
  758. if(UTF8_MBSTRING) return $out.mb_convert_encoding($str,'UTF-16BE','UTF-8');
  759. $uni = utf8_to_unicode($str);
  760. foreach($uni as $cp){
  761. $out .= pack('n',$cp);
  762. }
  763. return $out;
  764. }
  765. }
  766. if(!function_exists('utf16be_to_utf8')){
  767. /**
  768. * UTF-8 to UTF-16BE conversion.
  769. *
  770. * Maybe really UCS-2 without mb_string due to utf8_to_unicode limits
  771. */
  772. function utf16be_to_utf8(&$str) {
  773. $uni = unpack('n*',$str);
  774. return unicode_to_utf8($uni);
  775. }
  776. }
  777. if(!function_exists('utf8_bad_replace')){
  778. /**
  779. * Replace bad bytes with an alternative character
  780. *
  781. * ASCII character is recommended for replacement char
  782. *
  783. * PCRE Pattern to locate bad bytes in a UTF-8 string
  784. * Comes from W3 FAQ: Multilingual Forms
  785. * Note: modified to include full ASCII range including control chars
  786. *
  787. * @author Harry Fuecks <hfuecks@gmail.com>
  788. * @see http://www.w3.org/International/questions/qa-forms-utf-8
  789. * @param string to search
  790. * @param string to replace bad bytes with (defaults to '?') - use ASCII
  791. * @return string
  792. */
  793. function utf8_bad_replace($str, $replace = '') {
  794. $UTF8_BAD =
  795. '([\x00-\x7F]'. # ASCII (including control chars)
  796. '|[\xC2-\xDF][\x80-\xBF]'. # non-overlong 2-byte
  797. '|\xE0[\xA0-\xBF][\x80-\xBF]'. # excluding overlongs
  798. '|[\xE1-\xEC\xEE\xEF][\x80-\xBF]{2}'. # straight 3-byte
  799. '|\xED[\x80-\x9F][\x80-\xBF]'. # excluding surrogates
  800. '|\xF0[\x90-\xBF][\x80-\xBF]{2}'. # planes 1-3
  801. '|[\xF1-\xF3][\x80-\xBF]{3}'. # planes 4-15
  802. '|\xF4[\x80-\x8F][\x80-\xBF]{2}'. # plane 16
  803. '|(.{1}))'; # invalid byte
  804. ob_start();
  805. while (preg_match('/'.$UTF8_BAD.'/S', $str, $matches)) {
  806. if ( !isset($matches[2])) {
  807. echo $matches[0];
  808. } else {
  809. echo $replace;
  810. }
  811. $str = substr($str,strlen($matches[0]));
  812. }
  813. $result = ob_get_contents();
  814. ob_end_clean();
  815. return $result;
  816. }
  817. }
  818. if(!function_exists('utf8_correctIdx')){
  819. /**
  820. * adjust a byte index into a utf8 string to a utf8 character boundary
  821. *
  822. * @param $str string utf8 character string
  823. * @param $i int byte index into $str
  824. * @param $next bool direction to search for boundary,
  825. * false = up (current character)
  826. * true = down (next character)
  827. *
  828. * @return int byte index into $str now pointing to a utf8 character boundary
  829. *
  830. * @author chris smith <chris@jalakai.co.uk>
  831. */
  832. function utf8_correctIdx(&$str,$i,$next=false) {
  833. if ($i <= 0) return 0;
  834. $limit = strlen($str);
  835. if ($i>=$limit) return $limit;
  836. if ($next) {
  837. while (($i<$limit) && ((ord($str[$i]) & 0xC0) == 0x80)) $i++;
  838. } else {
  839. while ($i && ((ord($str[$i]) & 0xC0) == 0x80)) $i--;
  840. }
  841. return $i;
  842. }
  843. }
  844. // only needed if no mb_string available
  845. if(!UTF8_MBSTRING){
  846. /**
  847. * UTF-8 Case lookup table
  848. *
  849. * This lookuptable defines the upper case letters to their correspponding
  850. * lower case letter in UTF-8
  851. *
  852. * @author Andreas Gohr <andi@splitbrain.org>
  853. */
  854. global $UTF8_LOWER_TO_UPPER;
  855. if(empty($UTF8_LOWER_TO_UPPER)) $UTF8_LOWER_TO_UPPER = array(
  856. "??&#x161;"=>"???","??&#x2122;"=>"??š","??&#x2DC;"=>"??¸","??&#x2014;"=>"???","??&#x2013;"=>"???","??&#x2022;"=>"???","??&#x201D;"=>"??´","??&#x201C;"=>"???","??&#x2019;"=>"???","??&#x2018;"=>"???",
  857. "???"=>"??°","???"=>"???","??&#x17D;"=>"??Ž","???"=>"??­","??&#x152;"=>"???","??&#x2039;"=>"???","??&#x160;"=>"???","??&#x2030;"=>"??Š","??&#x2C6;"=>"??¨","??&#x2021;"=>"??§",
  858. "??&#x2020;"=>"???","??&#x2026;"=>"???","??&#x201E;"=>"??¤","??&#x192;"=>"???","??&#x201A;"=>"???","?? "=>"???","á??"=>"á??","á??"=>"á??","á??"=>"á?Š","á?&#x2018;"=>"á?&#x2122;",
  859. "á??"=>"á?&#x2DC;","á?&#x192;"=>"á?&#x152;","ážž"=>"Î&#x2122;","áž?"=>"áž?","áž?"=>"ážš","áž°"=>"ី","ឧ"=>"áž?","áž?"=>"ណ","áž?"=>"áž­","ឤ"=>"áž?",
  860. "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;",
  861. "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??",
  862. "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;",
  863. "á??"=>"á?&#x2C6;","á??"=>"áž?","á?°"=>"áž?","á?§"=>"á??","á??"=>"á?Ž","á??"=>"á?­","á?¤"=>"á??","á??"=>"á??","á??"=>"á??","á??"=>"á?Š",
  864. "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;",
  865. "á??"=>"á??","á??"=>"á?ž","á??"=>"á??","á?´"=>"á??","á??"=>"á??","á??"=>"á??","á??"=>"á?š","á?°"=>"á?¸","á?§"=>"á??","á??"=>"á?Ž",
  866. "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;",
  867. "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?¸",
  868. "á??"=>"á??","á??"=>"á?´","á??"=>"á??","á??"=>"á?°","á??"=>"á?Ž","á?­"=>"á??","á??"=>"á??","á?Š"=>"á?¨","á?§"=>"á??","á??"=>"á?¤",
  869. "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??",
  870. "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??",
  871. "á??"=>"á??","á?š"=>"á?¸","á??"=>"á??","á??"=>"á?´","á??"=>"á??","á??"=>"á?°","á??"=>"á?Ž","á?­"=>"á??","á??"=>"á??","á?Š"=>"á?¨",
  872. "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;",
  873. "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",
  874. "�"=>"�","�"=>"ᚴ","�"=>"�","�"=>"ᚰ","�"=>"ᚎ","ᚭ"=>"�","�"=>"�","ᚊ"=>"ᚨ","ᚧ"=>"�","�"=>"ᚤ",
  875. "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?",
  876. "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¸?",
  877. "�"=>"�","Ḛ"=>"Ḹ","�"=>"�","�"=>"Ḵ","�"=>"�","�"=>"Ḱ","�"=>"Ḏ","ḭ"=>"�","�"=>"�","Ḋ"=>"Ḩ",
  878. "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;",
  879. "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;",
  880. "Ö&#x2020;"=>"?&#x2013;","Ö&#x2026;"=>"?&#x2022;","Ö&#x201E;"=>"?&#x201D;","Ö&#x192;"=>"?&#x201C;","Ö&#x201A;"=>"?&#x2019;","Ö "=>"?&#x2018;","Ö&#x20AC;"=>"??","??"=>"??","?ž"=>"?&#x17D;","??"=>"??",
  881. "??"=>"?&#x152;","??"=>"?&#x2039;","??"=>"?&#x160;","?š"=>"?&#x2030;","?¸"=>"?&#x2C6;","??"=>"?&#x2021;","??"=>"?&#x2020;","??"=>"?&#x2026;","?´"=>"?&#x201E;","??"=>"?&#x192;",
  882. "??"=>"?&#x201A;","??"=>"? ","?°"=>"?&#x20AC;","??"=>"Ô?","?Ž"=>"Ôž","?­"=>"Ô?","??"=>"Ô?","??"=>"Ô?","??"=>"Ô?","?Š"=>"Ôš",
  883. "?¨"=>"Ô¸","?§"=>"Ô?","??"=>"Ô?","??"=>"Ô?","?¤"=>"Ô´","??"=>"Ô?","??"=>"Ô?","??"=>"Ô?","Ô?"=>"Ô&#x17D;","Ô?"=>"Ô&#x152;",
  884. "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°",
  885. "Ó?"=>"ÓŽ","Ó­"=>"Ó?","Ó?"=>"Ó?","ÓŠ"=>"Ó¨","Ó§"=>"Ó?","Ó?"=>"Ó¤","Ó?"=>"Ó?","Ó?"=>"Ó ","Ó&#x;"=>"Ó&#x17E;","Ó?"=>"Ó&#x153;",
  886. "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;",
  887. "Ó&#x2020;"=>"Ó&#x2026;","Ó&#x201E;"=>"Ó&#x192;","Ó&#x201A;"=>"Ó ","??"=>"?ž","??"=>"??","??"=>"??","?š"=>"?¸","??"=>"??","??"=>"?´","??"=>"??",
  888. "??"=>"?°","??"=>"?Ž","?­"=>"??","??"=>"??","?Š"=>"?¨","?§"=>"??","??"=>"?¤","??"=>"??","??"=>"? ","?&#x;"=>"?&#x17E;",
  889. "??"=>"?&#x153;","?&#x203A;"=>"?&#x161;","?&#x2122;"=>"?&#x2DC;","?&#x2014;"=>"?&#x2013;","?&#x2022;"=>"?&#x201D;","?&#x201C;"=>"?&#x2019;","?&#x2018;"=>"??","??"=>"?&#x17D;","??"=>"?&#x152;","?&#x2039;"=>"?&#x160;",
  890. "? "=>"?&#x20AC;","??"=>"?ž","??"=>"??","??"=>"??","?š"=>"?¸","??"=>"??","??"=>"?´","??"=>"??","??"=>"?°","??"=>"?Ž",
  891. "?­"=>"??","??"=>"??","?Š"=>"?¨","?§"=>"??","??"=>"?¤","??"=>"??","??"=>"? ","?&#x;"=>"??","?&#x17E;"=>"?&#x17D;","??"=>"??",
  892. "?&#x153;"=>"?&#x152;","?&#x203A;"=>"?&#x2039;","?&#x161;"=>"?&#x160;","?&#x2122;"=>"?&#x2030;","?&#x2DC;"=>"?&#x2C6;","?&#x2014;"=>"?&#x2021;","?&#x2013;"=>"?&#x2020;","?&#x2022;"=>"?&#x2026;","?&#x201D;"=>"?&#x201E;","?&#x201C;"=>"?&#x192;",
  893. "?&#x2019;"=>"?&#x201A;","?&#x2018;"=>"? ","??"=>"?&#x20AC;","??"=>"??","?&#x17D;"=>"?Ž","??"=>"?­","?&#x152;"=>"??","?&#x2039;"=>"??","?&#x160;"=>"??","?&#x2030;"=>"?Š",
  894. "?&#x2C6;"=>"?¨","?&#x2021;"=>"?§","?&#x2020;"=>"??","?&#x2026;"=>"??","?&#x201E;"=>"?¤","?&#x192;"=>"??","?&#x201A;"=>"??","? "=>"??","?&#x20AC;"=>"? ","??"=>"?&#x;",
  895. "?ž"=>"?&#x17E;","??"=>"??","??"=>"?&#x153;","??"=>"?&#x203A;","??"=>"?&#x161;","?š"=>"?&#x2122;","?¸"=>"?&#x2DC;","??"=>"?&#x2014;","??"=>"?&#x2013;","??"=>"?&#x2022;",
  896. "?´"=>"?&#x201D;","??"=>"?&#x201C;","??"=>"?&#x2019;","??"=>"?&#x2018;","?°"=>"??","??"=>"Î&#x2022;","??"=>"Î?","??"=>"Î?","?°"=>"Î&#x161;","??"=>"?Ž",
  897. "?­"=>"??","??"=>"??","?Š"=>"?¨","?§"=>"??","??"=>"?¤","??"=>"??","??"=>"? ","?&#x;"=>"?&#x17E;","??"=>"?&#x153;","?&#x203A;"=>"?&#x161;",
  898. "?&#x2122;"=>"?&#x2DC;","?&#x2013;"=>"Π","?&#x2022;"=>"Î?","?&#x2018;"=>"Î&#x2DC;","??"=>"Î&#x2019;","?&#x17D;"=>"Î?","??"=>"Î&#x17D;","?&#x152;"=>"Î&#x152;","?&#x2039;"=>"Î?","?&#x160;"=>"Î?",
  899. "?&#x2030;"=>"Ί","?&#x2C6;"=>"Ψ","?&#x2021;"=>"Χ","?&#x2020;"=>"Î?","?&#x2026;"=>"Î?","?&#x201E;"=>"Τ","?&#x192;"=>"Î?","?&#x201A;"=>"Î?","? "=>"Î?","?&#x20AC;"=>"Π",
  900. "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;",
  901. "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;"=>"??",
  902. "?&#x2039;"=>"??","?&#x160;"=>"??","?&#x2C6;"=>"?Ž","?&#x192;"=>"?Š","?&#x20AC;"=>"??","É?"=>"?&#x;","É?"=>"??","É?"=>"?&#x153;","ÉŠ"=>"?&#x2013;","ɨ"=>"?&#x2014;",
  903. "É?"=>"?&#x201D;","É&#x203A;"=>"??","É&#x2122;"=>"??","É&#x2014;"=>"?&#x160;","É&#x2013;"=>"?&#x2030;","É&#x201D;"=>"?&#x2020;","É&#x201C;"=>"? ","??"=>"??","??"=>"?°","??"=>"?Ž",
  904. "?­"=>"??","??"=>"??","?Š"=>"?¨","?§"=>"??","??"=>"?¤","??"=>"??","?&#x;"=>"?&#x17E;","??"=>"?&#x153;","?&#x203A;"=>"?&#x161;","?&#x2122;"=>"?&#x2DC;",
  905. "?&#x2014;"=>"?&#x2013;","?&#x2022;"=>"?&#x201D;","?&#x201C;"=>"?&#x2019;","?&#x2018;"=>"??","??"=>"?&#x17D;","??"=>"?&#x152;","?&#x2039;"=>"?&#x160;","?&#x2030;"=>"?&#x2C6;","?&#x2021;"=>"?&#x2020;","?&#x2026;"=>"?&#x201E;",
  906. "?&#x192;"=>"?&#x201A;","? "=>"?&#x20AC;","Ç?"=>"Çž","Ç?"=>"Ç?","Ç?"=>"Ç?","Çš"=>"Ǹ","Ç?"=>"Ç´","Ç?"=>"Ç?","Ç?"=>"ÇŽ","Ç­"=>"Ç?",
  907. "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;",
  908. "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?",
  909. "??"=>"??","?š"=>"?¸","??"=>"??","?´"=>"??","?°"=>"??","?­"=>"??","?¨"=>"?§","??"=>"?¤","??"=>"??","??"=>"? ",
  910. "?&#x17E;"=>"? ","?&#x2122;"=>"?&#x2DC;","?&#x2022;"=>"Ç?","?&#x2019;"=>"?&#x2018;","?&#x152;"=>"?&#x2039;","?&#x2C6;"=>"?&#x2021;","?&#x2026;"=>"?&#x201E;","?&#x192;"=>"?&#x201A;","??"=>"S","?ž"=>"??",
  911. "??"=>"??","??"=>"?š","??"=>"??","??"=>"?´","??"=>"??","??"=>"?°","??"=>"?Ž","?­"=>"??","??"=>"??","?Š"=>"?¨",
  912. "?§"=>"??","??"=>"?¤","??"=>"??","??"=>"? ","?&#x;"=>"?&#x17E;","??"=>"?&#x153;","?&#x203A;"=>"?&#x161;","?&#x2122;"=>"?&#x2DC;","?&#x2014;"=>"?&#x2013;","?&#x2022;"=>"?&#x201D;",
  913. "?&#x201C;"=>"?&#x2019;","?&#x2018;"=>"??","??"=>"?&#x17D;","??"=>"?&#x152;","?&#x2039;"=>"?&#x160;","?&#x2C6;"=>"?&#x2021;","?&#x2020;"=>"?&#x2026;","?&#x201E;"=>"?&#x192;","?&#x201A;"=>"? ","?&#x20AC;"=>"Ä?",
  914. "Äž"=>"Ä?","Ä?"=>"Ä?","Ä?"=>"Äš","Ä?"=>"Ä?","Ä?"=>"Ä´","Ä?"=>"Ä?","Ä?"=>"I","Ä?"=>"ÄŽ","Ä­"=>"Ä?","Ä?"=>"Ä?",
  915. "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;",
  916. "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;",
  917. "Ä "=>"Ä&#x20AC;","??"=>"?¸","?ž"=>"?&#x17E;","??"=>"??","??"=>"?&#x153;","??"=>"?&#x203A;","??"=>"?&#x161;","?š"=>"?&#x2122;","?¸"=>"?&#x2DC;","??"=>"?&#x2013;",
  918. "??"=>"?&#x2022;","?´"=>"?&#x201D;","??"=>"?&#x201C;","??"=>"?&#x2019;","??"=>"?&#x2018;","?°"=>"??","??"=>"??","?Ž"=>"?&#x17D;","?­"=>"??","??"=>"?&#x152;",
  919. "??"=>"?&#x2039;","??"=>"?&#x160;","?Š"=>"?&#x2030;","?¨"=>"?&#x2C6;","?§"=>"?&#x2021;","??"=>"?&#x2020;","??"=>"?&#x2026;","?¤"=>"?&#x201E;","??"=>"?&#x192;","??"=>"?&#x201A;",
  920. "??"=>"? ","? "=>"?&#x20AC;","Â?"=>"Î&#x153;","z"=>"Z","y"=>"Y","x"=>"X","w"=>"W","v"=>"V","u"=>"U","t"=>"T",
  921. "s"=>"S","r"=>"R","q"=>"Q","p"=>"P","o"=>"O","n"=>"N","m"=>"M","l"=>"L","k"=>"K","j"=>"J",
  922. "i"=>"I","h"=>"H","g"=>"G","f"=>"F","e"=>"E","d"=>"D","c"=>"C","b"=>"B","a"=>"A"
  923. );
  924. /**
  925. * UTF-8 Case lookup table
  926. *
  927. * This lookuptable defines the lower case letters to their correspponding
  928. * upper case letter in UTF-8
  929. *
  930. * @author Andreas Gohr <andi@splitbrain.org>
  931. */
  932. global $UTF8_UPPER_TO_LOWER;
  933. if(empty($UTF8_UPPER_TO_LOWER)) $UTF8_UPPER_TO_LOWER = array (
  934. "???"=>"??&#x161;","??š"=>"??&#x2122;","??¸"=>"??&#x2DC;","???"=>"??&#x2014;","???"=>"??&#x2013;","???"=>"??&#x2022;","??´"=>"??&#x201D;","???"=>"??&#x201C;","???"=>"??&#x2019;","???"=>"??&#x2018;",
  935. "??°"=>"???","???"=>"???","??Ž"=>"??&#x17D;","??­"=>"???","???"=>"??&#x152;","???"=>"??&#x2039;","???"=>"??&#x160;","??Š"=>"??&#x2030;","??¨"=>"??&#x2C6;","??§"=>"??&#x2021;",
  936. "???"=>"??&#x2020;","???"=>"??&#x2026;","??¤"=>"??&#x201E;","???"=>"??&#x192;","???"=>"??&#x201A;","???"=>"?? ","á??"=>"á??","á??"=>"á??","á?Š"=>"á??","á?&#x2122;"=>"á?&#x2018;",
  937. "á?&#x2DC;"=>"á??","á?&#x152;"=>"á?&#x192;","Î&#x2122;"=>"ážž","áž?"=>"áž?","ážš"=>"áž?","ី"=>"áž°","áž?"=>"ឧ","ណ"=>"áž?","áž­"=>"áž?","áž?"=>"ឤ",
  938. "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;",
  939. "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??",
  940. "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??",
  941. "á?&#x2C6;"=>"á??","áž?"=>"á??","áž?"=>"á?°","á??"=>"á?§","á?Ž"=>"á??","á?­"=>"á??","á??"=>"á?¤","á??"=>"á??","á??"=>"á??","á?Š"=>"á??",
  942. "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;",
  943. "á??"=>"á??","á?ž"=>"á??","á??"=>"á??","á??"=>"á?´","á??"=>"á??","á??"=>"á??","á?š"=>"á??","á?¸"=>"á?°","á??"=>"á?§","á?Ž"=>"á??",
  944. "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;",
  945. "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",
  946. "á??"=>"á??","á?´"=>"á??","á??"=>"á??","á?°"=>"á??","á?Ž"=>"á??","á??"=>"á?­","á??"=>"á??","á?¨"=>"á?Š","á??"=>"á?§","á?¤"=>"á??",
  947. "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;",
  948. "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??",
  949. "á??"=>"á??","á?¸"=>"á?š","á??"=>"á??","á?´"=>"á??","á??"=>"á??","á?°"=>"á??","á?Ž"=>"á??","á??"=>"á?­","á??"=>"á??","á?¨"=>"á?Š",
  950. "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??",
  951. "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",
  952. "�"=>"�","ᚴ"=>"�","�"=>"�","ᚰ"=>"�","ᚎ"=>"�","�"=>"ᚭ","�"=>"�","ᚨ"=>"ᚊ","�"=>"ᚧ","ᚤ"=>"�",
  953. "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;",
  954. "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¸?",
  955. "�"=>"�","Ḹ"=>"Ḛ","�"=>"�","Ḵ"=>"�","�"=>"�","Ḱ"=>"�","Ḏ"=>"�","�"=>"ḭ","�"=>"�","Ḩ"=>"Ḋ",
  956. "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;",
  957. "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",
  958. "?&#x2013;"=>"Ö&#x2020;","?&#x2022;"=>"Ö&#x2026;","?&#x201D;"=>"Ö&#x201E;","?&#x201C;"=>"Ö&#x192;","?&#x2019;"=>"Ö&#x201A;","?&#x2018;"=>"Ö ","??"=>"Ö&#x20AC;","??"=>"??","?&#x17D;"=>"?ž","??"=>"??",
  959. "?&#x152;"=>"??","?&#x2039;"=>"??","?&#x160;"=>"??","?&#x2030;"=>"?š","?&#x2C6;"=>"?¸","?&#x2021;"=>"??","?&#x2020;"=>"??","?&#x2026;"=>"??","?&#x201E;"=>"?´","?&#x192;"=>"??",
  960. "?&#x201A;"=>"??","? "=>"??","?&#x20AC;"=>"?°","Ô?"=>"??","Ôž"=>"?Ž","Ô?"=>"?­","Ô?"=>"??","Ô?"=>"??","Ô?"=>"??","Ôš"=>"?Š",
  961. "Ô¸"=>"?¨","Ô?"=>"?§","Ô?"=>"??","Ô?"=>"??","Ô´"=>"?¤","Ô?"=>"??","Ô?"=>"??","Ô?"=>"??","Ô&#x17D;"=>"Ô?","Ô&#x152;"=>"Ô?",
  962. "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?",
  963. "ÓŽ"=>"Ó?","Ó?"=>"Ó­","Ó?"=>"Ó?","Ó¨"=>"ÓŠ","Ó?"=>"Ó§","Ó¤"=>"Ó?","Ó?"=>"Ó?","Ó "=>"Ó?","Ó&#x17E;"=>"Ó&#x;","Ó&#x153;"=>"Ó?",
  964. "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;",
  965. "Ó&#x2026;"=>"Ó&#x2020;","Ó&#x192;"=>"Ó&#x201E;","Ó "=>"Ó&#x201A;","?ž"=>"…

Large files files are truncated, but you can click here to view the full file