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/** 10 * check for mb_string support 11 */ 12if(!defined('UTF8_MBSTRING')){ 13 if(function_exists('mb_substr') && !defined('UTF8_NOMBSTRING')){ 14 define('UTF8_MBSTRING',1); 15 }else{ 16 define('UTF8_MBSTRING',0); 17 } 18} 19 20if(UTF8_MBSTRING){ mb_internal_encoding('UTF-8'); } 21 22 23/** 24 * URL-Encode a filename to allow unicodecharacters 25 * 26 * Slashes are not encoded 27 * 28 * When the second parameter is true the string will 29 * be encoded only if non ASCII characters are detected - 30 * This makes it safe to run it multiple times on the 31 * same string (default is true) 32 * 33 * @author Andreas Gohr <andi@splitbrain.org> 34 * @see urlencode 35 */ 36function utf8_encodeFN($file,$safe=true){ 37 if($safe && preg_match('#^[a-zA-Z0-9/_\-.%]+$#',$file)){ 38 return $file; 39 } 40 $file = urlencode($file); 41 $file = str_replace('%2F','/',$file); 42 return $file; 43} 44 45/** 46 * URL-Decode a filename 47 * 48 * This is just a wrapper around urldecode 49 * 50 * @author Andreas Gohr <andi@splitbrain.org> 51 * @see urldecode 52 */ 53function utf8_decodeFN($file){ 54 $file = urldecode($file); 55 return $file; 56} 57 58/** 59 * Checks if a string contains 7bit ASCII only 60 * 61 * @author Andreas Gohr <andi@splitbrain.org> 62 */ 63function utf8_isASCII($str){ 64 for($i=0; $i<strlen($str); $i++){ 65 if(ord($str{$i}) >127) return false; 66 } 67 return true; 68} 69 70/** 71 * Strips all highbyte chars 72 * 73 * Returns a pure ASCII7 string 74 * 75 * @author Andreas Gohr <andi@splitbrain.org> 76 */ 77function utf8_strip($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 $ascii; 85} 86 87/** 88 * Tries to detect if a string is in Unicode encoding 89 * 90 * @author <bmorel@ssi.fr> 91 * @link http://www.php.net/manual/en/function.utf8-encode.php 92 */ 93function utf8_check($Str) { 94 for ($i=0; $i<strlen($Str); $i++) { 95 $b = ord($Str[$i]); 96 if ($b < 0x80) continue; # 0bbbbbbb 97 elseif (($b & 0xE0) == 0xC0) $n=1; # 110bbbbb 98 elseif (($b & 0xF0) == 0xE0) $n=2; # 1110bbbb 99 elseif (($b & 0xF8) == 0xF0) $n=3; # 11110bbb 100 elseif (($b & 0xFC) == 0xF8) $n=4; # 111110bb 101 elseif (($b & 0xFE) == 0xFC) $n=5; # 1111110b 102 else return false; # Does not match any model 103 for ($j=0; $j<$n; $j++) { # n bytes matching 10bbbbbb follow ? 104 if ((++$i == strlen($Str)) || ((ord($Str[$i]) & 0xC0) != 0x80)) 105 return false; 106 } 107 } 108 return true; 109} 110 111/** 112 * Unicode aware replacement for strlen() 113 * 114 * utf8_decode() converts characters that are not in ISO-8859-1 115 * to '?', which, for the purpose of counting, is alright - It's 116 * even faster than mb_strlen. 117 * 118 * @author <chernyshevsky at hotmail dot com> 119 * @see strlen() 120 * @see utf8_decode() 121 */ 122function utf8_strlen($string){ 123 return strlen(utf8_decode($string)); 124} 125 126/** 127 * UTF-8 aware alternative to substr 128 * 129 * Return part of a string given character offset (and optionally length) 130 * 131 * @author Harry Fuecks <hfuecks@gmail.com> 132 * @author Chris Smith <chris@jalakai.co.uk> 133 * @param string 134 * @param integer number of UTF-8 characters offset (from left) 135 * @param integer (optional) length in UTF-8 characters from offset 136 * @return mixed string or false if failure 137 */ 138function utf8_substr($str, $offset, $length = null) { 139 if(UTF8_MBSTRING){ 140 if( $length === null ){ 141 return mb_substr($str, $offset); 142 }else{ 143 return mb_substr($str, $offset, $length); 144 } 145 } 146 147 /* 148 * Notes: 149 * 150 * no mb string support, so we'll use pcre regex's with 'u' flag 151 * pcre only supports repetitions of less than 65536, in order to accept up to MAXINT values for 152 * offset and length, we'll repeat a group of 65535 characters when needed (ok, up to MAXINT-65536) 153 * 154 * substr documentation states false can be returned in some cases (e.g. offset > string length) 155 * mb_substr never returns false, it will return an empty string instead. 156 * 157 * calculating the number of characters in the string is a relatively expensive operation, so 158 * we only carry it out when necessary. It isn't necessary for +ve offsets and no specified length 159 */ 160 161 // cast parameters to appropriate types to avoid multiple notices/warnings 162 $str = (string)$str; // generates E_NOTICE for PHP4 objects, but not PHP5 objects 163 $offset = (int)$offset; 164 if (!is_null($length)) $length = (int)$length; 165 166 // handle trivial cases 167 if ($length === 0) return ''; 168 if ($offset < 0 && $length < 0 && $length < $offset) return ''; 169 170 $offset_pattern = ''; 171 $length_pattern = ''; 172 173 // normalise -ve offsets (we could use a tail anchored pattern, but they are horribly slow!) 174 if ($offset < 0) { 175 $strlen = strlen(utf8_decode($str)); // see notes 176 $offset = $strlen + $offset; 177 if ($offset < 0) $offset = 0; 178 } 179 180 // establish a pattern for offset, a non-captured group equal in length to offset 181 if ($offset > 0) { 182 $Ox = (int)($offset/65535); 183 $Oy = $offset%65535; 184 185 if ($Ox) $offset_pattern = '(?:.{65535}){'.$Ox.'}'; 186 $offset_pattern = '^(?:'.$offset_pattern.'.{'.$Oy.'})'; 187 } else { 188 $offset_pattern = '^'; // offset == 0; just anchor the pattern 189 } 190 191 // establish a pattern for length 192 if (is_null($length)) { 193 $length_pattern = '(.*)$'; // the rest of the string 194 } else { 195 196 if (!isset($strlen)) $strlen = strlen(utf8_decode($str)); // see notes 197 if ($offset > $strlen) return ''; // another trivial case 198 199 if ($length > 0) { 200 201 $length = min($strlen-$offset, $length); // reduce any length that would go passed the end of the string 202 203 $Lx = (int)($length/65535); 204 $Ly = $length%65535; 205 206 // +ve length requires ... a captured group of length characters 207 if ($Lx) $length_pattern = '(?:.{65535}){'.$Lx.'}'; 208 $length_pattern = '('.$length_pattern.'.{'.$Ly.'})'; 209 210 } else if ($length < 0) { 211 212 if ($length < ($offset - $strlen)) return ''; 213 214 $Lx = (int)((-$length)/65535); 215 $Ly = (-$length)%65535; 216 217 // -ve length requires ... capture everything except a group of -length characters 218 // anchored at the tail-end of the string 219 if ($Lx) $length_pattern = '(?:.{65535}){'.$Lx.'}'; 220 $length_pattern = '(.*)(?:'.$length_pattern.'.{'.$Ly.'})$'; 221 } 222 } 223 224 if (!preg_match('#'.$offset_pattern.$length_pattern.'#us',$str,$match)) return ''; 225 return $match[1]; 226} 227 228/** 229 * Unicode aware replacement for substr_replace() 230 * 231 * @author Andreas Gohr <andi@splitbrain.org> 232 * @see substr_replace() 233 */ 234function utf8_substr_replace($string, $replacement, $start , $length=0 ){ 235 $ret = ''; 236 if($start>0) $ret .= utf8_substr($string, 0, $start); 237 $ret .= $replacement; 238 $ret .= utf8_substr($string, $start+$length); 239 return $ret; 240} 241 242/** 243 * Unicode aware replacement for ltrim() 244 * 245 * @author Andreas Gohr <andi@splitbrain.org> 246 * @see ltrim() 247 * @return string 248 */ 249function utf8_ltrim($str,$charlist=''){ 250 if($charlist == '') return ltrim($str); 251 252 //quote charlist for use in a characterclass 253 $charlist = preg_replace('!([\\\\\\-\\]\\[/])!','\\\${1}',$charlist); 254 255 return preg_replace('/^['.$charlist.']+/u','',$str); 256} 257 258/** 259 * Unicode aware replacement for rtrim() 260 * 261 * @author Andreas Gohr <andi@splitbrain.org> 262 * @see rtrim() 263 * @return string 264 */ 265function utf8_rtrim($str,$charlist=''){ 266 if($charlist == '') return rtrim($str); 267 268 //quote charlist for use in a characterclass 269 $charlist = preg_replace('!([\\\\\\-\\]\\[/])!','\\\${1}',$charlist); 270 271 return preg_replace('/['.$charlist.']+$/u','',$str); 272} 273 274/** 275 * Unicode aware replacement for trim() 276 * 277 * @author Andreas Gohr <andi@splitbrain.org> 278 * @see trim() 279 * @return string 280 */ 281function utf8_trim($str,$charlist='') { 282 if($charlist == '') return trim($str); 283 284 return utf8_ltrim(utf8_rtrim($str,$charlist),$charlist); 285} 286 287 288/** 289 * This is a unicode aware replacement for strtolower() 290 * 291 * Uses mb_string extension if available 292 * 293 * @author Leo Feyer <leo@typolight.org> 294 * @see strtolower() 295 * @see utf8_strtoupper() 296 */ 297function utf8_strtolower($string){ 298 if(UTF8_MBSTRING) return mb_strtolower($string,'utf-8'); 299 300 global $UTF8_UPPER_TO_LOWER; 301 return strtr($string,$UTF8_UPPER_TO_LOWER); 302} 303 304/** 305 * This is a unicode aware replacement for strtoupper() 306 * 307 * Uses mb_string extension if available 308 * 309 * @author Leo Feyer <leo@typolight.org> 310 * @see strtoupper() 311 * @see utf8_strtoupper() 312 */ 313function utf8_strtoupper($string){ 314 if(UTF8_MBSTRING) return mb_strtoupper($string,'utf-8'); 315 316 global $UTF8_LOWER_TO_UPPER; 317 return strtr($string,$UTF8_LOWER_TO_UPPER); 318} 319 320/** 321 * UTF-8 aware alternative to ucfirst 322 * Make a string's first character uppercase 323 * 324 * @author Harry Fuecks 325 * @param string 326 * @return string with first character as upper case (if applicable) 327 */ 328function utf8_ucfirst($str){ 329 switch ( utf8_strlen($str) ) { 330 case 0: 331 return ''; 332 case 1: 333 return utf8_strtoupper($str); 334 default: 335 preg_match('/^(.{1})(.*)$/us', $str, $matches); 336 return utf8_strtoupper($matches[1]).$matches[2]; 337 } 338} 339 340/** 341 * UTF-8 aware alternative to ucwords 342 * Uppercase the first character of each word in a string 343 * 344 * @author Harry Fuecks 345 * @param string 346 * @return string with first char of each word uppercase 347 * @see http://www.php.net/ucwords 348 */ 349function utf8_ucwords($str) { 350 // Note: [\x0c\x09\x0b\x0a\x0d\x20] matches; 351 // form feeds, horizontal tabs, vertical tabs, linefeeds and carriage returns 352 // This corresponds to the definition of a "word" defined at http://www.php.net/ucwords 353 $pattern = '/(^|([\x0c\x09\x0b\x0a\x0d\x20]+))([^\x0c\x09\x0b\x0a\x0d\x20]{1})[^\x0c\x09\x0b\x0a\x0d\x20]*/u'; 354 355 return preg_replace_callback($pattern, 'utf8_ucwords_callback',$str); 356} 357 358/** 359 * Callback function for preg_replace_callback call in utf8_ucwords 360 * You don't need to call this yourself 361 * 362 * @author Harry Fuecks 363 * @param array of matches corresponding to a single word 364 * @return string with first char of the word in uppercase 365 * @see utf8_ucwords 366 * @see utf8_strtoupper 367 */ 368function utf8_ucwords_callback($matches) { 369 $leadingws = $matches[2]; 370 $ucfirst = utf8_strtoupper($matches[3]); 371 $ucword = utf8_substr_replace(ltrim($matches[0]),$ucfirst,0,1); 372 return $leadingws . $ucword; 373} 374 375/** 376 * Replace accented UTF-8 characters by unaccented ASCII-7 equivalents 377 * 378 * Use the optional parameter to just deaccent lower ($case = -1) or upper ($case = 1) 379 * letters. Default is to deaccent both cases ($case = 0) 380 * 381 * @author Andreas Gohr <andi@splitbrain.org> 382 */ 383function utf8_deaccent($string,$case=0){ 384 if($case <= 0){ 385 global $UTF8_LOWER_ACCENTS; 386 $string = strtr($string,$UTF8_LOWER_ACCENTS); 387 } 388 if($case >= 0){ 389 global $UTF8_UPPER_ACCENTS; 390 $string = strtr($string,$UTF8_UPPER_ACCENTS); 391 } 392 return $string; 393} 394 395/** 396 * Romanize a non-latin string 397 * 398 * @author Andreas Gohr <andi@splitbrain.org> 399 */ 400function utf8_romanize($string){ 401 if(utf8_isASCII($string)) return $string; //nothing to do 402 403 global $UTF8_ROMANIZATION; 404 return strtr($string,$UTF8_ROMANIZATION); 405} 406 407/** 408 * Removes special characters (nonalphanumeric) from a UTF-8 string 409 * 410 * This function adds the controlchars 0x00 to 0x19 to the array of 411 * stripped chars (they are not included in $UTF8_SPECIAL_CHARS) 412 * 413 * @author Andreas Gohr <andi@splitbrain.org> 414 * @param string $string The UTF8 string to strip of special chars 415 * @param string $repl Replace special with this string 416 * @param string $additional Additional chars to strip (used in regexp char class) 417 */ 418function utf8_stripspecials($string,$repl='',$additional=''){ 419 global $UTF8_SPECIAL_CHARS; 420 global $UTF8_SPECIAL_CHARS2; 421 422 static $specials = null; 423 if(is_null($specials)){ 424# $specials = preg_quote(unicode_to_utf8($UTF8_SPECIAL_CHARS), '/'); 425 $specials = preg_quote($UTF8_SPECIAL_CHARS2, '/'); 426 } 427 428 return preg_replace('/['.$additional.'\x00-\x19'.$specials.']/u',$repl,$string); 429} 430 431/** 432 * This is an Unicode aware replacement for strpos 433 * 434 * @author Leo Feyer <leo@typolight.org> 435 * @see strpos() 436 * @param string 437 * @param string 438 * @param integer 439 * @return integer 440 */ 441function utf8_strpos($haystack, $needle, $offset=0){ 442 $comp = 0; 443 $length = null; 444 445 while (is_null($length) || $length < $offset) { 446 $pos = strpos($haystack, $needle, $offset + $comp); 447 448 if ($pos === false) 449 return false; 450 451 $length = utf8_strlen(substr($haystack, 0, $pos)); 452 453 if ($length < $offset) 454 $comp = $pos - $length; 455 } 456 457 return $length; 458} 459 460 461/** 462 * Encodes UTF-8 characters to HTML entities 463 * 464 * @author Tom N Harris <tnharris@whoopdedo.org> 465 * @author <vpribish at shopping dot com> 466 * @link http://www.php.net/manual/en/function.utf8-decode.php 467 */ 468function utf8_tohtml ($str) { 469 $ret = ''; 470 foreach (utf8_to_unicode($str) as $cp) { 471 if ($cp < 0x80) 472 $ret .= chr($cp); 473 elseif ($cp < 0x100) 474 $ret .= "&#$cp;"; 475 else 476 $ret .= '&#x'.dechex($cp).';'; 477 } 478 return $ret; 479} 480 481/** 482 * Decodes HTML entities to UTF-8 characters 483 * 484 * Convert any &#..; entity to a codepoint, 485 * The entities flag defaults to only decoding numeric entities. 486 * Pass HTML_ENTITIES and named entities, including & < etc. 487 * are handled as well. Avoids the problem that would occur if you 488 * had to decode "&#38;&amp;#38;" 489 * 490 * unhtmlspecialchars(utf8_unhtml($s)) -> "&&" 491 * utf8_unhtml(unhtmlspecialchars($s)) -> "&&#38;" 492 * what it should be -> "&&#38;" 493 * 494 * @author Tom N Harris <tnharris@whoopdedo.org> 495 * @param string $str UTF-8 encoded string 496 * @param boolean $entities Flag controlling decoding of named entities. 497 * @return UTF-8 encoded string with numeric (and named) entities replaced. 498 */ 499function utf8_unhtml($str, $entities=null) { 500 static $decoder = null; 501 if (is_null($decoder)) 502 $decoder = new utf8_entity_decoder(); 503 if (is_null($entities)) 504 return preg_replace_callback('/(&#([Xx])?([0-9A-Za-z]+);)/m', 505 'utf8_decode_numeric', $str); 506 else 507 return preg_replace_callback('/&(#)?([Xx])?([0-9A-Za-z]+);/m', 508 array(&$decoder, 'decode'), $str); 509} 510function utf8_decode_numeric($ent) { 511 switch ($ent[2]) { 512 case 'X': 513 case 'x': 514 $cp = hexdec($ent[3]); 515 break; 516 default: 517 $cp = intval($ent[3]); 518 break; 519 } 520 return unicode_to_utf8(array($cp)); 521} 522class utf8_entity_decoder { 523 var $table; 524 function utf8_entity_decoder() { 525 $table = get_html_translation_table(HTML_ENTITIES); 526 $table = array_flip($table); 527 $this->table = array_map(array(&$this,'makeutf8'), $table); 528 } 529 function makeutf8($c) { 530 return unicode_to_utf8(array(ord($c))); 531 } 532 function decode($ent) { 533 if ($ent[1] == '#') { 534 return utf8_decode_numeric($ent); 535 } elseif (array_key_exists($ent[0],$this->table)) { 536 return $this->table[$ent[0]]; 537 } else { 538 return $ent[0]; 539 } 540 } 541} 542 543/** 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 $strict is set to true the function returns false if the input 550 * string isn't a valid UTF-8 octet sequence and raises a PHP error at 551 * level E_USER_WARNING 552 * 553 * Note: this function has been modified slightly in this library to 554 * trigger errors on encountering bad bytes 555 * 556 * @author <hsivonen@iki.fi> 557 * @author Harry Fuecks <hfuecks@gmail.com> 558 * @param string UTF-8 encoded string 559 * @param boolean Check for invalid sequences? 560 * @return mixed array of unicode code points or false if UTF-8 invalid 561 * @see unicode_to_utf8 562 * @link http://hsivonen.iki.fi/php-utf8/ 563 * @link http://sourceforge.net/projects/phputf8/ 564 */ 565function utf8_to_unicode($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 570 571 $out = array(); 572 573 $len = strlen($str); 574 575 for($i = 0; $i < $len; $i++) { 576 577 $in = ord($str{$i}); 578 579 if ( $mState == 0) { 580 581 // When mState is zero we expect either a US-ASCII character or a 582 // multi-octet sequence. 583 if (0 == (0x80 & ($in))) { 584 // US-ASCII, pass straight through. 585 $out[] = $in; 586 $mBytes = 1; 587 588 } else if (0xC0 == (0xE0 & ($in))) { 589 // First octet of 2 octet sequence 590 $mUcs4 = ($in); 591 $mUcs4 = ($mUcs4 & 0x1F) << 6; 592 $mState = 1; 593 $mBytes = 2; 594 595 } else if (0xE0 == (0xF0 & ($in))) { 596 // First octet of 3 octet sequence 597 $mUcs4 = ($in); 598 $mUcs4 = ($mUcs4 & 0x0F) << 12; 599 $mState = 2; 600 $mBytes = 3; 601 602 } else if (0xF0 == (0xF8 & ($in))) { 603 // First octet of 4 octet sequence 604 $mUcs4 = ($in); 605 $mUcs4 = ($mUcs4 & 0x07) << 18; 606 $mState = 3; 607 $mBytes = 4; 608 609 } else if (0xF8 == (0xFC & ($in))) { 610 /* First octet of 5 octet sequence. 611 * 612 * This is illegal because the encoded codepoint must be either 613 * (a) not the shortest form or 614 * (b) outside the Unicode range of 0-0x10FFFF. 615 * Rather than trying to resynchronize, we will carry on until the end 616 * of the sequence and let the later error handling code catch it. 617 */ 618 $mUcs4 = ($in); 619 $mUcs4 = ($mUcs4 & 0x03) << 24; 620 $mState = 4; 621 $mBytes = 5; 622 623 } else if (0xFC == (0xFE & ($in))) { 624 // First octet of 6 octet sequence, see comments for 5 octet sequence. 625 $mUcs4 = ($in); 626 $mUcs4 = ($mUcs4 & 1) << 30; 627 $mState = 5; 628 $mBytes = 6; 629 630 } elseif($strict) { 631 /* Current octet is neither in the US-ASCII range nor a legal first 632 * octet of a multi-octet sequence. 633 */ 634 trigger_error( 635 'utf8_to_unicode: Illegal sequence identifier '. 636 'in UTF-8 at byte '.$i, 637 E_USER_WARNING 638 ); 639 return false; 640 641 } 642 643 } else { 644 645 // When mState is non-zero, we expect a continuation of the multi-octet 646 // sequence 647 if (0x80 == (0xC0 & ($in))) { 648 649 // Legal continuation. 650 $shift = ($mState - 1) * 6; 651 $tmp = $in; 652 $tmp = ($tmp & 0x0000003F) << $shift; 653 $mUcs4 |= $tmp; 654 655 /** 656 * End of the multi-octet sequence. mUcs4 now contains the final 657 * Unicode codepoint to be output 658 */ 659 if (0 == --$mState) { 660 661 /* 662 * Check for illegal sequences and codepoints. 663 */ 664 // From Unicode 3.1, non-shortest form is illegal 665 if (((2 == $mBytes) && ($mUcs4 < 0x0080)) || 666 ((3 == $mBytes) && ($mUcs4 < 0x0800)) || 667 ((4 == $mBytes) && ($mUcs4 < 0x10000)) || 668 (4 < $mBytes) || 669 // From Unicode 3.2, surrogate characters are illegal 670 (($mUcs4 & 0xFFFFF800) == 0xD800) || 671 // Codepoints outside the Unicode range are illegal 672 ($mUcs4 > 0x10FFFF)) { 673 674 if($strict){ 675 trigger_error( 676 'utf8_to_unicode: Illegal sequence or codepoint '. 677 'in UTF-8 at byte '.$i, 678 E_USER_WARNING 679 ); 680 681 return false; 682 } 683 684 } 685 686 if (0xFEFF != $mUcs4) { 687 // BOM is legal but we don't want to output it 688 $out[] = $mUcs4; 689 } 690 691 //initialize UTF8 cache 692 $mState = 0; 693 $mUcs4 = 0; 694 $mBytes = 1; 695 } 696 697 } elseif($strict) { 698 /** 699 *((0xC0 & (*in) != 0x80) && (mState != 0)) 700 * Incomplete multi-octet sequence. 701 */ 702 trigger_error( 703 'utf8_to_unicode: Incomplete multi-octet '. 704 ' sequence in UTF-8 at byte '.$i, 705 E_USER_WARNING 706 ); 707 708 return false; 709 } 710 } 711 } 712 return $out; 713} 714 715/** 716 * Takes an array of ints representing the Unicode characters and returns 717 * a UTF-8 string. Astral planes are supported ie. the ints in the 718 * input can be > 0xFFFF. Occurrances of the BOM are ignored. Surrogates 719 * are not allowed. 720 * 721 * If $strict is set to true the function returns false if the input 722 * array contains ints that represent surrogates or are outside the 723 * Unicode range and raises a PHP error at level E_USER_WARNING 724 * 725 * Note: this function has been modified slightly in this library to use 726 * output buffering to concatenate the UTF-8 string (faster) as well as 727 * reference the array by it's keys 728 * 729 * @param array of unicode code points representing a string 730 * @param boolean Check for invalid sequences? 731 * @return mixed UTF-8 string or false if array contains invalid code points 732 * @author <hsivonen@iki.fi> 733 * @author Harry Fuecks <hfuecks@gmail.com> 734 * @see utf8_to_unicode 735 * @link http://hsivonen.iki.fi/php-utf8/ 736 * @link http://sourceforge.net/projects/phputf8/ 737 */ 738function unicode_to_utf8($arr,$strict=false) { 739 if (!is_array($arr)) return ''; 740 ob_start(); 741 742 foreach (array_keys($arr) as $k) { 743 744 # ASCII range (including control chars) 745 if ( ($arr[$k] >= 0) && ($arr[$k] <= 0x007f) ) { 746 747 echo chr($arr[$k]); 748 749 # 2 byte sequence 750 } else if ($arr[$k] <= 0x07ff) { 751 752 echo chr(0xc0 | ($arr[$k] >> 6)); 753 echo chr(0x80 | ($arr[$k] & 0x003f)); 754 755 # Byte order mark (skip) 756 } else if($arr[$k] == 0xFEFF) { 757 758 // nop -- zap the BOM 759 760 # Test for illegal surrogates 761 } else if ($arr[$k] >= 0xD800 && $arr[$k] <= 0xDFFF) { 762 763 // found a surrogate 764 if($strict){ 765 trigger_error( 766 'unicode_to_utf8: Illegal surrogate '. 767 'at index: '.$k.', value: '.$arr[$k], 768 E_USER_WARNING 769 ); 770 return false; 771 } 772 773 # 3 byte sequence 774 } else if ($arr[$k] <= 0xffff) { 775 776 echo chr(0xe0 | ($arr[$k] >> 12)); 777 echo chr(0x80 | (($arr[$k] >> 6) & 0x003f)); 778 echo chr(0x80 | ($arr[$k] & 0x003f)); 779 780 # 4 byte sequence 781 } else if ($arr[$k] <= 0x10ffff) { 782 783 echo chr(0xf0 | ($arr[$k] >> 18)); 784 echo chr(0x80 | (($arr[$k] >> 12) & 0x3f)); 785 echo chr(0x80 | (($arr[$k] >> 6) & 0x3f)); 786 echo chr(0x80 | ($arr[$k] & 0x3f)); 787 788 } elseif($strict) { 789 790 trigger_error( 791 'unicode_to_utf8: Codepoint out of Unicode range '. 792 'at index: '.$k.', value: '.$arr[$k], 793 E_USER_WARNING 794 ); 795 796 // out of range 797 return false; 798 } 799 } 800 801 $result = ob_get_contents(); 802 ob_end_clean(); 803 return $result; 804} 805 806/** 807 * UTF-8 to UTF-16BE conversion. 808 * 809 * Maybe really UCS-2 without mb_string due to utf8_to_unicode limits 810 */ 811function utf8_to_utf16be(&$str, $bom = false) { 812 $out = $bom ? "\xFE\xFF" : ''; 813 if(UTF8_MBSTRING) return $out.mb_convert_encoding($str,'UTF-16BE','UTF-8'); 814 815 $uni = utf8_to_unicode($str); 816 foreach($uni as $cp){ 817 $out .= pack('n',$cp); 818 } 819 return $out; 820} 821 822/** 823 * UTF-8 to UTF-16BE conversion. 824 * 825 * Maybe really UCS-2 without mb_string due to utf8_to_unicode limits 826 */ 827function utf16be_to_utf8(&$str) { 828 $uni = unpack('n*',$str); 829 return unicode_to_utf8($uni); 830} 831 832/** 833 * Replace bad bytes with an alternative character 834 * 835 * ASCII character is recommended for replacement char 836 * 837 * PCRE Pattern to locate bad bytes in a UTF-8 string 838 * Comes from W3 FAQ: Multilingual Forms 839 * Note: modified to include full ASCII range including control chars 840 * 841 * @author Harry Fuecks <hfuecks@gmail.com> 842 * @see http://www.w3.org/International/questions/qa-forms-utf-8 843 * @param string to search 844 * @param string to replace bad bytes with (defaults to '?') - use ASCII 845 * @return string 846 */ 847function utf8_bad_replace($str, $replace = '') { 848 $UTF8_BAD = 849 '([\x00-\x7F]'. # ASCII (including control chars) 850 '|[\xC2-\xDF][\x80-\xBF]'. # non-overlong 2-byte 851 '|\xE0[\xA0-\xBF][\x80-\xBF]'. # excluding overlongs 852 '|[\xE1-\xEC\xEE\xEF][\x80-\xBF]{2}'. # straight 3-byte 853 '|\xED[\x80-\x9F][\x80-\xBF]'. # excluding surrogates 854 '|\xF0[\x90-\xBF][\x80-\xBF]{2}'. # planes 1-3 855 '|[\xF1-\xF3][\x80-\xBF]{3}'. # planes 4-15 856 '|\xF4[\x80-\x8F][\x80-\xBF]{2}'. # plane 16 857 '|(.{1}))'; # invalid byte 858 ob_start(); 859 while (preg_match('/'.$UTF8_BAD.'/S', $str, $matches)) { 860 if ( !isset($matches[2])) { 861 echo $matches[0]; 862 } else { 863 echo $replace; 864 } 865 $str = substr($str,strlen($matches[0])); 866 } 867 $result = ob_get_contents(); 868 ob_end_clean(); 869 return $result; 870} 871 872/** 873 * adjust a byte index into a utf8 string to a utf8 character boundary 874 * 875 * @param $str string utf8 character string 876 * @param $i int byte index into $str 877 * @param $next bool direction to search for boundary, 878 * false = up (current character) 879 * true = down (next character) 880 * 881 * @return int byte index into $str now pointing to a utf8 character boundary 882 * 883 * @author chris smith <chris@jalakai.co.uk> 884 */ 885function utf8_correctIdx(&$str,$i,$next=false) { 886 887 if ($i <= 0) return 0; 888 889 $limit = strlen($str); 890 if ($i>=$limit) return $limit; 891 892 if ($next) { 893 while (($i<$limit) && ((ord($str[$i]) & 0xC0) == 0x80)) $i++; 894 } else { 895 while ($i && ((ord($str[$i]) & 0xC0) == 0x80)) $i--; 896 } 897 898 return $i; 899} 900 901// only needed if no mb_string available 902if(!UTF8_MBSTRING){ 903 /** 904 * UTF-8 Case lookup table 905 * 906 * This lookuptable defines the upper case letters to their correspponding 907 * lower case letter in UTF-8 908 * 909 * @author Andreas Gohr <andi@splitbrain.org> 910 */ 911 global $UTF8_LOWER_TO_UPPER; 912 $UTF8_LOWER_TO_UPPER = array( 913 "ｚ"=>"Ｚ","ｙ"=>"Ｙ","ｘ"=>"Ｘ","ｗ"=>"Ｗ","ｖ"=>"Ｖ","ｕ"=>"Ｕ","ｔ"=>"Ｔ","ｓ"=>"Ｓ","ｒ"=>"Ｒ","ｑ"=>"Ｑ", 914 "ｐ"=>"Ｐ","ｏ"=>"Ｏ","ｎ"=>"Ｎ","ｍ"=>"Ｍ","ｌ"=>"Ｌ","ｋ"=>"Ｋ","ｊ"=>"Ｊ","ｉ"=>"Ｉ","ｈ"=>"Ｈ","ｇ"=>"Ｇ", 915 "ｆ"=>"Ｆ","ｅ"=>"Ｅ","ｄ"=>"Ｄ","ｃ"=>"Ｃ","ｂ"=>"Ｂ","ａ"=>"Ａ","ῳ"=>"ῼ","ῥ"=>"Ῥ","ῡ"=>"Ῡ","ῑ"=>"Ῑ", 916 "ῐ"=>"Ῐ","ῃ"=>"ῌ","ι"=>"Ι","ᾳ"=>"ᾼ","ᾱ"=>"Ᾱ","ᾰ"=>"Ᾰ","ᾧ"=>"ᾯ","ᾦ"=>"ᾮ","ᾥ"=>"ᾭ","ᾤ"=>"ᾬ", 917 "ᾣ"=>"ᾫ","ᾢ"=>"ᾪ","ᾡ"=>"ᾩ","ᾗ"=>"ᾟ","ᾖ"=>"ᾞ","ᾕ"=>"ᾝ","ᾔ"=>"ᾜ","ᾓ"=>"ᾛ","ᾒ"=>"ᾚ","ᾑ"=>"ᾙ", 918 "ᾐ"=>"ᾘ","ᾇ"=>"ᾏ","ᾆ"=>"ᾎ","ᾅ"=>"ᾍ","ᾄ"=>"ᾌ","ᾃ"=>"ᾋ","ᾂ"=>"ᾊ","ᾁ"=>"ᾉ","ᾀ"=>"ᾈ","ώ"=>"Ώ", 919 "ὼ"=>"Ὼ","ύ"=>"Ύ","ὺ"=>"Ὺ","ό"=>"Ό","ὸ"=>"Ὸ","ί"=>"Ί","ὶ"=>"Ὶ","ή"=>"Ή","ὴ"=>"Ὴ","έ"=>"Έ", 920 "ὲ"=>"Ὲ","ά"=>"Ά","ὰ"=>"Ὰ","ὧ"=>"Ὧ","ὦ"=>"Ὦ","ὥ"=>"Ὥ","ὤ"=>"Ὤ","ὣ"=>"Ὣ","ὢ"=>"Ὢ","ὡ"=>"Ὡ", 921 "ὗ"=>"Ὗ","ὕ"=>"Ὕ","ὓ"=>"Ὓ","ὑ"=>"Ὑ","ὅ"=>"Ὅ","ὄ"=>"Ὄ","ὃ"=>"Ὃ","ὂ"=>"Ὂ","ὁ"=>"Ὁ","ὀ"=>"Ὀ", 922 "ἷ"=>"Ἷ","ἶ"=>"Ἶ","ἵ"=>"Ἵ","ἴ"=>"Ἴ","ἳ"=>"Ἳ","ἲ"=>"Ἲ","ἱ"=>"Ἱ","ἰ"=>"Ἰ","ἧ"=>"Ἧ","ἦ"=>"Ἦ", 923 "ἥ"=>"Ἥ","ἤ"=>"Ἤ","ἣ"=>"Ἣ","ἢ"=>"Ἢ","ἡ"=>"Ἡ","ἕ"=>"Ἕ","ἔ"=>"Ἔ","ἓ"=>"Ἓ","ἒ"=>"Ἒ","ἑ"=>"Ἑ", 924 "ἐ"=>"Ἐ","ἇ"=>"Ἇ","ἆ"=>"Ἆ","ἅ"=>"Ἅ","ἄ"=>"Ἄ","ἃ"=>"Ἃ","ἂ"=>"Ἂ","ἁ"=>"Ἁ","ἀ"=>"Ἀ","ỹ"=>"Ỹ", 925 "ỷ"=>"Ỷ","ỵ"=>"Ỵ","ỳ"=>"Ỳ","ự"=>"Ự","ữ"=>"Ữ","ử"=>"Ử","ừ"=>"Ừ","ứ"=>"Ứ","ủ"=>"Ủ","ụ"=>"Ụ", 926 "ợ"=>"Ợ","ỡ"=>"Ỡ","ở"=>"Ở","ờ"=>"Ờ","ớ"=>"Ớ","ộ"=>"Ộ","ỗ"=>"Ỗ","ổ"=>"Ổ","ồ"=>"Ồ","ố"=>"Ố", 927 "ỏ"=>"Ỏ","ọ"=>"Ọ","ị"=>"Ị","ỉ"=>"Ỉ","ệ"=>"Ệ","ễ"=>"Ễ","ể"=>"Ể","ề"=>"Ề","ế"=>"Ế","ẽ"=>"Ẽ", 928 "ẻ"=>"Ẻ","ẹ"=>"Ẹ","ặ"=>"Ặ","ẵ"=>"Ẵ","ẳ"=>"Ẳ","ằ"=>"Ằ","ắ"=>"Ắ","ậ"=>"Ậ","ẫ"=>"Ẫ","ẩ"=>"Ẩ", 929 "ầ"=>"Ầ","ấ"=>"Ấ","ả"=>"Ả","ạ"=>"Ạ","ẛ"=>"Ṡ","ẕ"=>"Ẕ","ẓ"=>"Ẓ","ẑ"=>"Ẑ","ẏ"=>"Ẏ","ẍ"=>"Ẍ", 930 "ẋ"=>"Ẋ","ẉ"=>"Ẉ","ẇ"=>"Ẇ","ẅ"=>"Ẅ","ẃ"=>"Ẃ","ẁ"=>"Ẁ","ṿ"=>"Ṿ","ṽ"=>"Ṽ","ṻ"=>"Ṻ","ṹ"=>"Ṹ", 931 "ṷ"=>"Ṷ","ṵ"=>"Ṵ","ṳ"=>"Ṳ","ṱ"=>"Ṱ","ṯ"=>"Ṯ","ṭ"=>"Ṭ","ṫ"=>"Ṫ","ṩ"=>"Ṩ","ṧ"=>"Ṧ","ṥ"=>"Ṥ", 932 "ṣ"=>"Ṣ","ṡ"=>"Ṡ","ṟ"=>"Ṟ","ṝ"=>"Ṝ","ṛ"=>"Ṛ","ṙ"=>"Ṙ","ṗ"=>"Ṗ","ṕ"=>"Ṕ","ṓ"=>"Ṓ","ṑ"=>"Ṑ", 933 "ṏ"=>"Ṏ","ṍ"=>"Ṍ","ṋ"=>"Ṋ","ṉ"=>"Ṉ","ṇ"=>"Ṇ","ṅ"=>"Ṅ","ṃ"=>"Ṃ","ṁ"=>"Ṁ","ḿ"=>"Ḿ","ḽ"=>"Ḽ", 934 "ḻ"=>"Ḻ","ḹ"=>"Ḹ","ḷ"=>"Ḷ","ḵ"=>"Ḵ","ḳ"=>"Ḳ","ḱ"=>"Ḱ","ḯ"=>"Ḯ","ḭ"=>"Ḭ","ḫ"=>"Ḫ","ḩ"=>"Ḩ", 935 "ḧ"=>"Ḧ","ḥ"=>"Ḥ","ḣ"=>"Ḣ","ḡ"=>"Ḡ","ḟ"=>"Ḟ","ḝ"=>"Ḝ","ḛ"=>"Ḛ","ḙ"=>"Ḙ","ḗ"=>"Ḗ","ḕ"=>"Ḕ", 936 "ḓ"=>"Ḓ","ḑ"=>"Ḑ","ḏ"=>"Ḏ","ḍ"=>"Ḍ","ḋ"=>"Ḋ","ḉ"=>"Ḉ","ḇ"=>"Ḇ","ḅ"=>"Ḅ","ḃ"=>"Ḃ","ḁ"=>"Ḁ", 937 "ֆ"=>"Ֆ","օ"=>"Օ","ք"=>"Ք","փ"=>"Փ","ւ"=>"Ւ","ց"=>"Ց","ր"=>"Ր","տ"=>"Տ","վ"=>"Վ","ս"=>"Ս", 938 "ռ"=>"Ռ","ջ"=>"Ջ","պ"=>"Պ","չ"=>"Չ","ո"=>"Ո","շ"=>"Շ","ն"=>"Ն","յ"=>"Յ","մ"=>"Մ","ճ"=>"Ճ", 939 "ղ"=>"Ղ","ձ"=>"Ձ","հ"=>"Հ","կ"=>"Կ","ծ"=>"Ծ","խ"=>"Խ","լ"=>"Լ","ի"=>"Ի","ժ"=>"Ժ","թ"=>"Թ", 940 "ը"=>"Ը","է"=>"Է","զ"=>"Զ","ե"=>"Ե","դ"=>"Դ","գ"=>"Գ","բ"=>"Բ","ա"=>"Ա","ԏ"=>"Ԏ","ԍ"=>"Ԍ", 941 "ԋ"=>"Ԋ","ԉ"=>"Ԉ","ԇ"=>"Ԇ","ԅ"=>"Ԅ","ԃ"=>"Ԃ","ԁ"=>"Ԁ","ӹ"=>"Ӹ","ӵ"=>"Ӵ","ӳ"=>"Ӳ","ӱ"=>"Ӱ", 942 "ӯ"=>"Ӯ","ӭ"=>"Ӭ","ӫ"=>"Ӫ","ө"=>"Ө","ӧ"=>"Ӧ","ӥ"=>"Ӥ","ӣ"=>"Ӣ","ӡ"=>"Ӡ","ӟ"=>"Ӟ","ӝ"=>"Ӝ", 943 "ӛ"=>"Ӛ","ә"=>"Ә","ӗ"=>"Ӗ","ӕ"=>"Ӕ","ӓ"=>"Ӓ","ӑ"=>"Ӑ","ӎ"=>"Ӎ","ӌ"=>"Ӌ","ӊ"=>"Ӊ","ӈ"=>"Ӈ", 944 "ӆ"=>"Ӆ","ӄ"=>"Ӄ","ӂ"=>"Ӂ","ҿ"=>"Ҿ","ҽ"=>"Ҽ","һ"=>"Һ","ҹ"=>"Ҹ","ҷ"=>"Ҷ","ҵ"=>"Ҵ","ҳ"=>"Ҳ", 945 "ұ"=>"Ұ","ү"=>"Ү","ҭ"=>"Ҭ","ҫ"=>"Ҫ","ҩ"=>"Ҩ","ҧ"=>"Ҧ","ҥ"=>"Ҥ","ң"=>"Ң","ҡ"=>"Ҡ","ҟ"=>"Ҟ", 946 "ҝ"=>"Ҝ","қ"=>"Қ","ҙ"=>"Ҙ","җ"=>"Җ","ҕ"=>"Ҕ","ғ"=>"Ғ","ґ"=>"Ґ","ҏ"=>"Ҏ","ҍ"=>"Ҍ","ҋ"=>"Ҋ", 947 "ҁ"=>"Ҁ","ѿ"=>"Ѿ","ѽ"=>"Ѽ","ѻ"=>"Ѻ","ѹ"=>"Ѹ","ѷ"=>"Ѷ","ѵ"=>"Ѵ","ѳ"=>"Ѳ","ѱ"=>"Ѱ","ѯ"=>"Ѯ", 948 "ѭ"=>"Ѭ","ѫ"=>"Ѫ","ѩ"=>"Ѩ","ѧ"=>"Ѧ","ѥ"=>"Ѥ","ѣ"=>"Ѣ","ѡ"=>"Ѡ","џ"=>"Џ","ў"=>"Ў","ѝ"=>"Ѝ", 949 "ќ"=>"Ќ","ћ"=>"Ћ","њ"=>"Њ","љ"=>"Љ","ј"=>"Ј","ї"=>"Ї","і"=>"І","ѕ"=>"Ѕ","є"=>"Є","ѓ"=>"Ѓ", 950 "ђ"=>"Ђ","ё"=>"Ё","ѐ"=>"Ѐ","я"=>"Я","ю"=>"Ю","э"=>"Э","ь"=>"Ь","ы"=>"Ы","ъ"=>"Ъ","щ"=>"Щ", 951 "ш"=>"Ш","ч"=>"Ч","ц"=>"Ц","х"=>"Х","ф"=>"Ф","у"=>"У","т"=>"Т","с"=>"С","р"=>"Р","п"=>"П", 952 "о"=>"О","н"=>"Н","м"=>"М","л"=>"Л","к"=>"К","й"=>"Й","и"=>"И","з"=>"З","ж"=>"Ж","е"=>"Е", 953 "д"=>"Д","г"=>"Г","в"=>"В","б"=>"Б","а"=>"А","ϵ"=>"Ε","ϲ"=>"Σ","ϱ"=>"Ρ","ϰ"=>"Κ","ϯ"=>"Ϯ", 954 "ϭ"=>"Ϭ","ϫ"=>"Ϫ","ϩ"=>"Ϩ","ϧ"=>"Ϧ","ϥ"=>"Ϥ","ϣ"=>"Ϣ","ϡ"=>"Ϡ","ϟ"=>"Ϟ","ϝ"=>"Ϝ","ϛ"=>"Ϛ", 955 "ϙ"=>"Ϙ","ϖ"=>"Π","ϕ"=>"Φ","ϑ"=>"Θ","ϐ"=>"Β","ώ"=>"Ώ","ύ"=>"Ύ","ό"=>"Ό","ϋ"=>"Ϋ","ϊ"=>"Ϊ", 956 "ω"=>"Ω","ψ"=>"Ψ","χ"=>"Χ","φ"=>"Φ","υ"=>"Υ","τ"=>"Τ","σ"=>"Σ","ς"=>"Σ","ρ"=>"Ρ","π"=>"Π", 957 "ο"=>"Ο","ξ"=>"Ξ","ν"=>"Ν","μ"=>"Μ","λ"=>"Λ","κ"=>"Κ","ι"=>"Ι","θ"=>"Θ","η"=>"Η","ζ"=>"Ζ", 958 "ε"=>"Ε","δ"=>"Δ","γ"=>"Γ","β"=>"Β","α"=>"Α","ί"=>"Ί","ή"=>"Ή","έ"=>"Έ","ά"=>"Ά","ʒ"=>"Ʒ", 959 "ʋ"=>"Ʋ","ʊ"=>"Ʊ","ʈ"=>"Ʈ","ʃ"=>"Ʃ","ʀ"=>"Ʀ","ɵ"=>"Ɵ","ɲ"=>"Ɲ","ɯ"=>"Ɯ","ɩ"=>"Ɩ","ɨ"=>"Ɨ", 960 "ɣ"=>"Ɣ","ɛ"=>"Ɛ","ə"=>"Ə","ɗ"=>"Ɗ","ɖ"=>"Ɖ","ɔ"=>"Ɔ","ɓ"=>"Ɓ","ȳ"=>"Ȳ","ȱ"=>"Ȱ","ȯ"=>"Ȯ", 961 "ȭ"=>"Ȭ","ȫ"=>"Ȫ","ȩ"=>"Ȩ","ȧ"=>"Ȧ","ȥ"=>"Ȥ","ȣ"=>"Ȣ","ȟ"=>"Ȟ","ȝ"=>"Ȝ","ț"=>"Ț","ș"=>"Ș", 962 "ȗ"=>"Ȗ","ȕ"=>"Ȕ","ȓ"=>"Ȓ","ȑ"=>"Ȑ","ȏ"=>"Ȏ","ȍ"=>"Ȍ","ȋ"=>"Ȋ","ȉ"=>"Ȉ","ȇ"=>"Ȇ","ȅ"=>"Ȅ", 963 "ȃ"=>"Ȃ","ȁ"=>"Ȁ","ǿ"=>"Ǿ","ǽ"=>"Ǽ","ǻ"=>"Ǻ","ǹ"=>"Ǹ","ǵ"=>"Ǵ","dz"=>"Dz","ǯ"=>"Ǯ","ǭ"=>"Ǭ", 964 "ǫ"=>"Ǫ","ǩ"=>"Ǩ","ǧ"=>"Ǧ","ǥ"=>"Ǥ","ǣ"=>"Ǣ","ǡ"=>"Ǡ","ǟ"=>"Ǟ","ǝ"=>"Ǝ","ǜ"=>"Ǜ","ǚ"=>"Ǚ", 965 "ǘ"=>"Ǘ","ǖ"=>"Ǖ","ǔ"=>"Ǔ","ǒ"=>"Ǒ","ǐ"=>"Ǐ","ǎ"=>"Ǎ","nj"=>"Nj","lj"=>"Lj","dž"=>"Dž","ƿ"=>"Ƿ", 966 "ƽ"=>"Ƽ","ƹ"=>"Ƹ","ƶ"=>"Ƶ","ƴ"=>"Ƴ","ư"=>"Ư","ƭ"=>"Ƭ","ƨ"=>"Ƨ","ƥ"=>"Ƥ","ƣ"=>"Ƣ","ơ"=>"Ơ", 967 "ƞ"=>"Ƞ","ƙ"=>"Ƙ","ƕ"=>"Ƕ","ƒ"=>"Ƒ","ƌ"=>"Ƌ","ƈ"=>"Ƈ","ƅ"=>"Ƅ","ƃ"=>"Ƃ","ſ"=>"S","ž"=>"Ž", 968 "ż"=>"Ż","ź"=>"Ź","ŷ"=>"Ŷ","ŵ"=>"Ŵ","ų"=>"Ų","ű"=>"Ű","ů"=>"Ů","ŭ"=>"Ŭ","ū"=>"Ū","ũ"=>"Ũ", 969 "ŧ"=>"Ŧ","ť"=>"Ť","ţ"=>"Ţ","š"=>"Š","ş"=>"Ş","ŝ"=>"Ŝ","ś"=>"Ś","ř"=>"Ř","ŗ"=>"Ŗ","ŕ"=>"Ŕ", 970 "œ"=>"Œ","ő"=>"Ő","ŏ"=>"Ŏ","ō"=>"Ō","ŋ"=>"Ŋ","ň"=>"Ň","ņ"=>"Ņ","ń"=>"Ń","ł"=>"Ł","ŀ"=>"Ŀ", 971 "ľ"=>"Ľ","ļ"=>"Ļ","ĺ"=>"Ĺ","ķ"=>"Ķ","ĵ"=>"Ĵ","ij"=>"IJ","ı"=>"I","į"=>"Į","ĭ"=>"Ĭ","ī"=>"Ī", 972 "ĩ"=>"Ĩ","ħ"=>"Ħ","ĥ"=>"Ĥ","ģ"=>"Ģ","ġ"=>"Ġ","ğ"=>"Ğ","ĝ"=>"Ĝ","ě"=>"Ě","ę"=>"Ę","ė"=>"Ė", 973 "ĕ"=>"Ĕ","ē"=>"Ē","đ"=>"Đ","ď"=>"Ď","č"=>"Č","ċ"=>"Ċ","ĉ"=>"Ĉ","ć"=>"Ć","ą"=>"Ą","ă"=>"Ă", 974 "ā"=>"Ā","ÿ"=>"Ÿ","þ"=>"Þ","ý"=>"Ý","ü"=>"Ü","û"=>"Û","ú"=>"Ú","ù"=>"Ù","ø"=>"Ø","ö"=>"Ö", 975 "õ"=>"Õ","ô"=>"Ô","ó"=>"Ó","ò"=>"Ò","ñ"=>"Ñ","ð"=>"Ð","ï"=>"Ï","î"=>"Î","í"=>"Í","ì"=>"Ì", 976 "ë"=>"Ë","ê"=>"Ê","é"=>"É","è"=>"È","ç"=>"Ç","æ"=>"Æ","å"=>"Å","ä"=>"Ä","ã"=>"Ã","â"=>"Â", 977 "á"=>"Á","à"=>"À","µ"=>"Μ","z"=>"Z","y"=>"Y","x"=>"X","w"=>"W","v"=>"V","u"=>"U","t"=>"T", 978 "s"=>"S","r"=>"R","q"=>"Q","p"=>"P","o"=>"O","n"=>"N","m"=>"M","l"=>"L","k"=>"K","j"=>"J", 979 "i"=>"I","h"=>"H","g"=>"G","f"=>"F","e"=>"E","d"=>"D","c"=>"C","b"=>"B","a"=>"A" 980 ); 981 982 /** 983 * UTF-8 Case lookup table 984 * 985 * This lookuptable defines the lower case letters to their correspponding 986 * upper case letter in UTF-8 987 * 988 * @author Andreas Gohr <andi@splitbrain.org> 989 */ 990 global $UTF8_UPPER_TO_LOWER; 991 $UTF8_UPPER_TO_LOWER = array ( 992 "Ｚ"=>"ｚ","Ｙ"=>"ｙ","Ｘ"=>"ｘ","Ｗ"=>"ｗ","Ｖ"=>"ｖ","Ｕ"=>"ｕ","Ｔ"=>"ｔ","Ｓ"=>"ｓ","Ｒ"=>"ｒ","Ｑ"=>"ｑ", 993 "Ｐ"=>"ｐ","Ｏ"=>"ｏ","Ｎ"=>"ｎ","Ｍ"=>"ｍ","Ｌ"=>"ｌ","Ｋ"=>"ｋ","Ｊ"=>"ｊ","Ｉ"=>"ｉ","Ｈ"=>"ｈ","Ｇ"=>"ｇ", 994 "Ｆ"=>"ｆ","Ｅ"=>"ｅ","Ｄ"=>"ｄ","Ｃ"=>"ｃ","Ｂ"=>"ｂ","Ａ"=>"ａ","ῼ"=>"ῳ","Ῥ"=>"ῥ","Ῡ"=>"ῡ","Ῑ"=>"ῑ", 995 "Ῐ"=>"ῐ","ῌ"=>"ῃ","Ι"=>"ι","ᾼ"=>"ᾳ","Ᾱ"=>"ᾱ","Ᾰ"=>"ᾰ","ᾯ"=>"ᾧ","ᾮ"=>"ᾦ","ᾭ"=>"ᾥ","ᾬ"=>"ᾤ", 996 "ᾫ"=>"ᾣ","ᾪ"=>"ᾢ","ᾩ"=>"ᾡ","ᾟ"=>"ᾗ","ᾞ"=>"ᾖ","ᾝ"=>"ᾕ","ᾜ"=>"ᾔ","ᾛ"=>"ᾓ","ᾚ"=>"ᾒ","ᾙ"=>"ᾑ", 997 "ᾘ"=>"ᾐ","ᾏ"=>"ᾇ","ᾎ"=>"ᾆ","ᾍ"=>"ᾅ","ᾌ"=>"ᾄ","ᾋ"=>"ᾃ","ᾊ"=>"ᾂ","ᾉ"=>"ᾁ","ᾈ"=>"ᾀ","Ώ"=>"ώ", 998 "Ὼ"=>"ὼ","Ύ"=>"ύ","Ὺ"=>"ὺ","Ό"=>"ό","Ὸ"=>"ὸ","Ί"=>"ί","Ὶ"=>"ὶ","Ή"=>"ή","Ὴ"=>"ὴ","Έ"=>"έ", 999 "Ὲ"=>"ὲ","Ά"=>"ά","Ὰ"=>"ὰ","Ὧ"=>"ὧ","Ὦ"=>"ὦ","Ὥ"=>"ὥ","Ὤ"=>"ὤ","Ὣ"=>"ὣ","Ὢ"=>"ὢ","Ὡ"=>"ὡ", 1000 "Ὗ"=>"ὗ","Ὕ"=>"ὕ","Ὓ"=>"ὓ","Ὑ"=>"ὑ","Ὅ"=>"ὅ","Ὄ"=>"ὄ","Ὃ"=>"ὃ","Ὂ"=>"ὂ","Ὁ"=>"ὁ","Ὀ"=>"ὀ", 1001 "Ἷ"=>"ἷ","Ἶ"=>"ἶ","Ἵ"=>"ἵ","Ἴ"=>"ἴ","Ἳ"=>"ἳ","Ἲ"=>"ἲ","Ἱ"=>"ἱ","Ἰ"=>"ἰ","Ἧ"=>"ἧ","Ἦ"=>"ἦ", 1002 "Ἥ"=>"ἥ","Ἤ"=>"ἤ","Ἣ"=>"ἣ","Ἢ"=>"ἢ","Ἡ"=>"ἡ","Ἕ"=>"ἕ","Ἔ"=>"ἔ","Ἓ"=>"ἓ","Ἒ"=>"ἒ","Ἑ"=>"ἑ", 1003 "Ἐ"=>"ἐ","Ἇ"=>"ἇ","Ἆ"=>"ἆ","Ἅ"=>"ἅ","Ἄ"=>"ἄ","Ἃ"=>"ἃ","Ἂ"=>"ἂ","Ἁ"=>"ἁ","Ἀ"=>"ἀ","Ỹ"=>"ỹ", 1004 "Ỷ"=>"ỷ","Ỵ"=>"ỵ","Ỳ"=>"ỳ","Ự"=>"ự","Ữ"=>"ữ","Ử"=>"ử","Ừ"=>"ừ","Ứ"=>"ứ","Ủ"=>"ủ","Ụ"=>"ụ", 1005 "Ợ"=>"ợ","Ỡ"=>"ỡ","Ở"=>"ở","Ờ"=>"ờ","Ớ"=>"ớ","Ộ"=>"ộ","Ỗ"=>"ỗ","Ổ"=>"ổ","Ồ"=>"ồ","Ố"=>"ố", 1006 "Ỏ"=>"ỏ","Ọ"=>"ọ","Ị"=>"ị","Ỉ"=>"ỉ","Ệ"=>"ệ","Ễ"=>"ễ","Ể"=>"ể","Ề"=>"ề","Ế"=>"ế","Ẽ"=>"ẽ", 1007 "Ẻ"=>"ẻ","Ẹ"=>"ẹ","Ặ"=>"ặ","Ẵ"=>"ẵ","Ẳ"=>"ẳ","Ằ"=>"ằ","Ắ"=>"ắ","Ậ"=>"ậ","Ẫ"=>"ẫ","Ẩ"=>"ẩ", 1008 "Ầ"=>"ầ","Ấ"=>"ấ","Ả"=>"ả","Ạ"=>"ạ","Ṡ"=>"ẛ","Ẕ"=>"ẕ","Ẓ"=>"ẓ","Ẑ"=>"ẑ","Ẏ"=>"ẏ","Ẍ"=>"ẍ", 1009 "Ẋ"=>"ẋ","Ẉ"=>"ẉ","Ẇ"=>"ẇ","Ẅ"=>"ẅ","Ẃ"=>"ẃ","Ẁ"=>"ẁ","Ṿ"=>"ṿ","Ṽ"=>"ṽ","Ṻ"=>"ṻ","Ṹ"=>"ṹ", 1010 "Ṷ"=>"ṷ","Ṵ"=>"ṵ","Ṳ"=>"ṳ","Ṱ"=>"ṱ","Ṯ"=>"ṯ","Ṭ"=>"ṭ","Ṫ"=>"ṫ","Ṩ"=>"ṩ","Ṧ"=>"ṧ","Ṥ"=>"ṥ", 1011 "Ṣ"=>"ṣ","Ṡ"=>"ṡ","Ṟ"=>"ṟ","Ṝ"=>"ṝ","Ṛ"=>"ṛ","Ṙ"=>"ṙ","Ṗ"=>"ṗ","Ṕ"=>"ṕ","Ṓ"=>"ṓ","Ṑ"=>"ṑ", 1012 "Ṏ"=>"ṏ","Ṍ"=>"ṍ","Ṋ"=>"ṋ","Ṉ"=>"ṉ","Ṇ"=>"ṇ","Ṅ"=>"ṅ","Ṃ"=>"ṃ","Ṁ"=>"ṁ","Ḿ"=>"ḿ","Ḽ"=>"ḽ", 1013 "Ḻ"=>"ḻ","Ḹ"=>"ḹ","Ḷ"=>"ḷ","Ḵ"=>"ḵ","Ḳ"=>"ḳ","Ḱ"=>"ḱ","Ḯ"=>"ḯ","Ḭ"=>"ḭ","Ḫ"=>"ḫ","Ḩ"=>"ḩ", 1014 "Ḧ"=>"ḧ","Ḥ"=>"ḥ","Ḣ"=>"ḣ","Ḡ"=>"ḡ","Ḟ"=>"ḟ","Ḝ"=>"ḝ","Ḛ"=>"ḛ","Ḙ"=>"ḙ","Ḗ"=>"ḗ","Ḕ"=>"ḕ", 1015 "Ḓ"=>"ḓ","Ḑ"=>"ḑ","Ḏ"=>"ḏ","Ḍ"=>"ḍ","Ḋ"=>"ḋ","Ḉ"=>"ḉ","Ḇ"=>"ḇ","Ḅ"=>"ḅ","Ḃ"=>"ḃ","Ḁ"=>"ḁ", 1016 "Ֆ"=>"ֆ","Օ"=>"օ","Ք"=>"ք","Փ"=>"փ","Ւ"=>"ւ","Ց"=>"ց","Ր"=>"ր","Տ"=>"տ","Վ"=>"վ","Ս"=>"ս", 1017 "Ռ"=>"ռ","Ջ"=>"ջ","Պ"=>"պ","Չ"=>"չ","Ո"=>"ո","Շ"=>"շ","Ն"=>"ն","Յ"=>"յ","Մ"=>"մ","Ճ"=>"ճ", 1018 "Ղ"=>"ղ","Ձ"=>"ձ","Հ"=>"հ","Կ"=>"կ","Ծ"=>"ծ","Խ"=>"խ","Լ"=>"լ","Ի"=>"ի","Ժ"=>"ժ","Թ"=>"թ", 1019 "Ը"=>"ը","Է"=>"է","Զ"=>"զ","Ե"=>"ե","Դ"=>"դ","Գ"=>"գ","Բ"=>"բ","Ա"=>"ա","Ԏ"=>"ԏ","Ԍ"=>"ԍ", 1020 "Ԋ"=>"ԋ","Ԉ"=>"ԉ","Ԇ"=>"ԇ","Ԅ"=>"ԅ","Ԃ"=>"ԃ","Ԁ"=>"ԁ","Ӹ"=>"ӹ","Ӵ"=>"ӵ","Ӳ"=>"ӳ","Ӱ"=>"ӱ", 1021 "Ӯ"=>"ӯ","Ӭ"=>"ӭ","Ӫ"=>"ӫ","Ө"=>"ө","Ӧ"=>"ӧ","Ӥ"=>"ӥ","Ӣ"=>"ӣ","Ӡ"=>"ӡ","Ӟ"=>"ӟ","Ӝ"=>"ӝ", 1022 "Ӛ"=>"ӛ","Ә"=>"ә","Ӗ"=>"ӗ","Ӕ"=>"ӕ","Ӓ"=>"ӓ","Ӑ"=>"ӑ","Ӎ"=>"ӎ","Ӌ"=>"ӌ","Ӊ"=>"ӊ","Ӈ"=>"ӈ", 1023 "Ӆ"=>"ӆ","Ӄ"=>"ӄ","Ӂ"=>"ӂ","Ҿ"=>"ҿ","Ҽ"=>"ҽ","Һ"=>"һ","Ҹ"=>"ҹ","Ҷ"=>"ҷ","Ҵ"=>"ҵ","Ҳ"=>"ҳ", 1024 "Ұ"=>"ұ","Ү"=>"ү","Ҭ"=>"ҭ","Ҫ"=>"ҫ","Ҩ"=>"ҩ","Ҧ"=>"ҧ","Ҥ"=>"ҥ","Ң"=>"ң","Ҡ"=>"ҡ","Ҟ"=>"ҟ", 1025 "Ҝ"=>"ҝ","Қ"=>"қ","Ҙ"=>"ҙ","Җ"=>"җ","Ҕ"=>"ҕ","Ғ"=>"ғ","Ґ"=>"ґ","Ҏ"=>"ҏ","Ҍ"=>"ҍ","Ҋ"=>"ҋ", 1026 "Ҁ"=>"ҁ","Ѿ"=>"ѿ","Ѽ"=>"ѽ","Ѻ"=>"ѻ","Ѹ"=>"ѹ","Ѷ"=>"ѷ","Ѵ"=>"ѵ","Ѳ"=>"ѳ","Ѱ"=>"ѱ","Ѯ"=>"ѯ", 1027 "Ѭ"=>"ѭ","Ѫ"=>"ѫ","Ѩ"=>"ѩ","Ѧ"=>"ѧ","Ѥ"=>"ѥ","Ѣ"=>"ѣ","Ѡ"=>"ѡ","Џ"=>"џ","Ў"=>"ў","Ѝ"=>"ѝ", 1028 "Ќ"=>"ќ","Ћ"=>"ћ","Њ"=>"њ","Љ"=>"љ","Ј"=>"ј","Ї"=>"ї","І"=>"і","Ѕ"=>"ѕ","Є"=>"є","Ѓ"=>"ѓ", 1029 "Ђ"=>"ђ","Ё"=>"ё","Ѐ"=>"ѐ","Я"=>"я","Ю"=>"ю","Э"=>"э","Ь"=>"ь","Ы"=>"ы","Ъ"=>"ъ","Щ"=>"щ", 1030 "Ш"=>"ш","Ч"=>"ч","Ц"=>"ц","Х"=>"х","Ф"=>"ф","У"=>"у","Т"=>"т","С"=>"с","Р"=>"р","П"=>"п", 1031 "О"=>"о","Н"=>"н","М"=>"м","Л"=>"л","К"=>"к","Й"=>"й","И"=>"и","З"=>"з","Ж"=>"ж","Е"=>"е", 1032 "Д"=>"д","Г"=>"г","В"=>"в","Б"=>"б","А"=>"а","Ε"=>"ϵ","Σ"=>"ϲ","Ρ"=>"ϱ","Κ"=>"ϰ","Ϯ"=>"ϯ", 1033 "Ϭ"=>"ϭ","Ϫ"=>"ϫ","Ϩ"=>"ϩ","Ϧ"=>"ϧ","Ϥ"=>"ϥ","Ϣ"=>"ϣ","Ϡ"=>"ϡ","Ϟ"=>"ϟ","Ϝ"=>"ϝ","Ϛ"=>"ϛ", 1034 "Ϙ"=>"ϙ","Π"=>"ϖ","Φ"=>"ϕ","Θ"=>"ϑ","Β"=>"ϐ","Ώ"=>"ώ","Ύ"=>"ύ","Ό"=>"ό","Ϋ"=>"ϋ","Ϊ"=>"ϊ", 1035 "Ω"=>"ω","Ψ"=>"ψ","Χ"=>"χ","Φ"=>"φ","Υ"=>"υ","Τ"=>"τ","Σ"=>"σ","Σ"=>"ς","Ρ"=>"ρ","Π"=>"π", 1036 "Ο"=>"ο","Ξ"=>"ξ","Ν"=>"ν","Μ"=>"μ","Λ"=>"λ","Κ"=>"κ","Ι"=>"ι","Θ"=>"θ","Η"=>"η","Ζ"=>"ζ", 1037 "Ε"=>"ε","Δ"=>"δ","Γ"=>"γ","Β"=>"β","Α"=>"α","Ί"=>"ί","Ή"=>"ή","Έ"=>"έ","Ά"=>"ά","Ʒ"=>"ʒ", 1038 "Ʋ"=>"ʋ","Ʊ"=>"ʊ","Ʈ"=>"ʈ","Ʃ"=>"ʃ","Ʀ"=>"ʀ","Ɵ"=>"ɵ","Ɲ"=>"ɲ","Ɯ"=>"ɯ","Ɩ"=>"ɩ","Ɨ"=>"ɨ", 1039 "Ɣ"=>"ɣ","Ɛ"=>"ɛ","Ə"=>"ə","Ɗ"=>"ɗ","Ɖ"=>"ɖ","Ɔ"=>"ɔ","Ɓ"=>"ɓ","Ȳ"=>"ȳ","Ȱ"=>"ȱ","Ȯ"=>"ȯ", 1040 "Ȭ"=>"ȭ","Ȫ"=>"ȫ","Ȩ"=>"ȩ","Ȧ"=>"ȧ","Ȥ"=>"ȥ","Ȣ"=>"ȣ","Ȟ"=>"ȟ","Ȝ"=>"ȝ","Ț"=>"ț","Ș"=>"ș", 1041 "Ȗ"=>"ȗ","Ȕ"=>"ȕ","Ȓ"=>"ȓ","Ȑ"=>"ȑ","Ȏ"=>"ȏ","Ȍ"=>"ȍ","Ȋ"=>"ȋ","Ȉ"=>"ȉ","Ȇ"=>"ȇ","Ȅ"=>"ȅ", 1042 "Ȃ"=>"ȃ","Ȁ"=>"ȁ","Ǿ"=>"ǿ","Ǽ"=>"ǽ","Ǻ"=>"ǻ","Ǹ"=>"ǹ","Ǵ"=>"ǵ","Dz"=>"dz","Ǯ"=>"ǯ","Ǭ"=>"ǭ", 1043 "Ǫ"=>"ǫ","Ǩ"=>"ǩ","Ǧ"=>"ǧ","Ǥ"=>"ǥ","Ǣ"=>"ǣ","Ǡ"=>"ǡ","Ǟ"=>"ǟ","Ǝ"=>"ǝ","Ǜ"=>"ǜ","Ǚ"=>"ǚ", 1044 "Ǘ"=>"ǘ","Ǖ"=>"ǖ","Ǔ"=>"ǔ","Ǒ"=>"ǒ","Ǐ"=>"ǐ","Ǎ"=>"ǎ","Nj"=>"nj","Lj"=>"lj","Dž"=>"dž","Ƿ"=>"ƿ", 1045 "Ƽ"=>"ƽ","Ƹ"=>"ƹ","Ƶ"=>"ƶ","Ƴ"=>"ƴ","Ư"=>"ư","Ƭ"=>"ƭ","Ƨ"=>"ƨ","Ƥ"=>"ƥ","Ƣ"=>"ƣ","Ơ"=>"ơ", 1046 "Ƞ"=>"ƞ","Ƙ"=>"ƙ","Ƕ"=>"ƕ","Ƒ"=>"ƒ","Ƌ"=>"ƌ","Ƈ"=>"ƈ","Ƅ"=>"ƅ","Ƃ"=>"ƃ","S"=>"ſ","Ž"=>"ž", 1047 "Ż"=>"ż","Ź"=>"ź","Ŷ"=>"ŷ","Ŵ"=>"ŵ","Ų"=>"ų","Ű"=>"ű","Ů"=>"ů","Ŭ"=>"ŭ","Ū"=>"ū","Ũ"=>"ũ", 1048 "Ŧ"=>"ŧ","Ť"=>"ť","Ţ"=>"ţ","Š"=>"š","Ş"=>"ş","Ŝ"=>"ŝ","Ś"=>"ś","Ř"=>"ř","Ŗ"=>"ŗ","Ŕ"=>"ŕ", 1049 "Œ"=>"œ","Ő"=>"ő","Ŏ"=>"ŏ","Ō"=>"ō","Ŋ"=>"ŋ","Ň"=>"ň","Ņ"=>"ņ","Ń"=>"ń","Ł"=>"ł","Ŀ"=>"ŀ", 1050 "Ľ"=>"ľ","Ļ"=>"ļ","Ĺ"=>"ĺ","Ķ"=>"ķ","Ĵ"=>"ĵ","IJ"=>"ij","I"=>"ı","Į"=>"į","Ĭ"=>"ĭ","Ī"=>"ī", 1051 "Ĩ"=>"ĩ","Ħ"=>"ħ","Ĥ"=>"ĥ","Ģ"=>"ģ","Ġ"=>"ġ","Ğ"=>"ğ","Ĝ"=>"ĝ","Ě"=>"ě","Ę"=>"ę","Ė"=>"ė", 1052 "Ĕ"=>"ĕ","Ē"=>"ē","Đ"=>"đ","Ď"=>"ď","Č"=>"č","Ċ"=>"ċ","Ĉ"=>"ĉ","Ć"=>"ć","Ą"=>"ą","Ă"=>"ă", 1053 "Ā"=>"ā","Ÿ"=>"ÿ","Þ"=>"þ","Ý"=>"ý","Ü"=>"ü","Û"=>"û","Ú"=>"ú","Ù"=>"ù","Ø"=>"ø","Ö"=>"ö", 1054 "Õ"=>"õ","Ô"=>"ô","Ó"=>"ó","Ò"=>"ò","Ñ"=>"ñ","Ð"=>"ð","Ï"=>"ï","Î"=>"î","Í"=>"í","Ì"=>"ì", 1055 "Ë"=>"ë","Ê"=>"ê","É"=>"é","È"=>"è","Ç"=>"ç","Æ"=>"æ","Å"=>"å","Ä"=>"ä","Ã"=>"ã","Â"=>"â", 1056 "Á"=>"á","À"=>"à","Μ"=>"µ","Z"=>"z","Y"=>"y","X"=>"x","W"=>"w","V"=>"v","U"=>"u","T"=>"t", 1057 "S"=>"s","R"=>"r","Q"=>"q","P"=>"p","O"=>"o","N"=>"n","M"=>"m","L"=>"l","K"=>"k","J"=>"j", 1058 "I"=>"i","H"=>"h","G"=>"g","F"=>"f","E"=>"e","D"=>"d","C"=>"c","B"=>"b","A"=>"a" 1059 ); 1060}; // end of case lookup tables 1061 1062/** 1063 * UTF-8 lookup table for lower case accented letters 1064 * 1065 * This lookuptable defines replacements for accented characters from the ASCII-7 1066 * range. This are lower case letters only. 1067 * 1068 * @author Andreas Gohr <andi@splitbrain.org> 1069 * @see utf8_deaccent() 1070 */ 1071global $UTF8_LOWER_ACCENTS; 1072$UTF8_LOWER_ACCENTS = array( 1073 'à' => 'a', 'ô' => 'o', 'ď' => 'd', 'ḟ' => 'f', 'ë' => 'e', 'š' => 's', 'ơ' => 'o', 1074 'ß' => 'ss', 'ă' => 'a', 'ř' => 'r', 'ț' => 't', 'ň' => 'n', 'ā' => 'a', 'ķ' => 'k', 1075 'ŝ' => 's', 'ỳ' => 'y', 'ņ' => 'n', 'ĺ' => 'l', 'ħ' => 'h', 'ṗ' => 'p', 'ó' => 'o', 1076 'ú' => 'u', 'ě' => 'e', 'é' => 'e', 'ç' => 'c', 'ẁ' => 'w', 'ċ' => 'c', 'õ' => 'o', 1077 'ṡ' => 's', 'ø' => 'o', 'ģ' => 'g', 'ŧ' => 't', 'ș' => 's', 'ė' => 'e', 'ĉ' => 'c', 1078 'ś' => 's', 'î' => 'i', 'ű' => 'u', 'ć' => 'c', 'ę' => 'e', 'ŵ' => 'w', 'ṫ' => 't', 1079 'ū' => 'u', 'č' => 'c', 'ö' => 'oe', 'è' => 'e', 'ŷ' => 'y', 'ą' => 'a', 'ł' => 'l', 1080 'ų' => 'u', 'ů' => 'u', 'ş' => 's', 'ğ' => 'g', 'ļ' => 'l', 'ƒ' => 'f', 'ž' => 'z', 1081 'ẃ' => 'w', 'ḃ' => 'b', 'å' => 'a', 'ì' => 'i', 'ï' => 'i', 'ḋ' => 'd', 'ť' => 't', 1082 'ŗ' => 'r', 'ä' => 'ae', 'í' => 'i', 'ŕ' => 'r', 'ê' => 'e', 'ü' => 'ue', 'ò' => 'o', 1083 'ē' => 'e', 'ñ' => 'n', 'ń' => 'n', 'ĥ' => 'h', 'ĝ' => 'g', 'đ' => 'd', 'ĵ' => 'j', 1084 'ÿ' => 'y', 'ũ' => 'u', 'ŭ' => 'u', 'ư' => 'u', 'ţ' => 't', 'ý' => 'y', 'ő' => 'o', 1085 'â' => 'a', 'ľ' => 'l', 'ẅ' => 'w', 'ż' => 'z', 'ī' => 'i', 'ã' => 'a', 'ġ' => 'g', 1086 'ṁ' => 'm', 'ō' => 'o', 'ĩ' => 'i', 'ù' => 'u', 'į' => 'i', 'ź' => 'z', 'á' => 'a', 1087 'û' => 'u', 'þ' => 'th', 'ð' => 'dh', 'æ' => 'ae', 'µ' => 'u', 'ĕ' => 'e', 1088); 1089 1090/** 1091 * UTF-8 lookup table for upper case accented letters 1092 * 1093 * This lookuptable defines replacements for accented characters from the ASCII-7 1094 * range. This are upper case letters only. 1095 * 1096 * @author Andreas Gohr <andi@splitbrain.org> 1097 * @see utf8_deaccent() 1098 */ 1099global $UTF8_UPPER_ACCENTS; 1100$UTF8_UPPER_ACCENTS = array( 1101 'À' => 'A', 'Ô' => 'O', 'Ď' => 'D', 'Ḟ' => 'F', 'Ë' => 'E', 'Š' => 'S', 'Ơ' => 'O', 1102 'Ă' => 'A', 'Ř' => 'R', 'Ț' => 'T', 'Ň' => 'N', 'Ā' => 'A', 'Ķ' => 'K', 1103 'Ŝ' => 'S', 'Ỳ' => 'Y', 'Ņ' => 'N', 'Ĺ' => 'L', 'Ħ' => 'H', 'Ṗ' => 'P', 'Ó' => 'O', 1104 'Ú' => 'U', 'Ě' => 'E', 'É' => 'E', 'Ç' => 'C', 'Ẁ' => 'W', 'Ċ' => 'C', 'Õ' => 'O', 1105 'Ṡ' => 'S', 'Ø' => 'O', 'Ģ' => 'G', 'Ŧ' => 'T', 'Ș' => 'S', 'Ė' => 'E', 'Ĉ' => 'C', 1106 'Ś' => 'S', 'Î' => 'I', 'Ű' => 'U', 'Ć' => 'C', 'Ę' => 'E', 'Ŵ' => 'W', 'Ṫ' => 'T', 1107 'Ū' => 'U', 'Č' => 'C', 'Ö' => 'Oe', 'È' => 'E', 'Ŷ' => 'Y', 'Ą' => 'A', 'Ł' => 'L', 1108 'Ų' => 'U', 'Ů' => 'U', 'Ş' => 'S', 'Ğ' => 'G', 'Ļ' => 'L', 'Ƒ' => 'F', 'Ž' => 'Z', 1109 'Ẃ' => 'W', 'Ḃ' => 'B', 'Å' => 'A', 'Ì' => 'I', 'Ï' => 'I', 'Ḋ' => 'D', 'Ť' => 'T', 1110 'Ŗ' => 'R', 'Ä' => 'Ae', 'Í' => 'I', 'Ŕ' => 'R', 'Ê' => 'E', 'Ü' => 'Ue', 'Ò' => 'O', 1111 'Ē' => 'E', 'Ñ' => 'N', 'Ń' => 'N', 'Ĥ' => 'H', 'Ĝ' => 'G', 'Đ' => 'D', 'Ĵ' => 'J', 1112 'Ÿ' => 'Y', 'Ũ' => 'U', 'Ŭ' => 'U', 'Ư' => 'U', 'Ţ' => 'T', 'Ý' => 'Y', 'Ő' => 'O', 1113 'Â' => 'A', 'Ľ' => 'L', 'Ẅ' => 'W', 'Ż' => 'Z', 'Ī' => 'I', 'Ã' => 'A', 'Ġ' => 'G', 1114 'Ṁ' => 'M', 'Ō' => 'O', 'Ĩ' => 'I', 'Ù' => 'U', 'Į' => 'I', 'Ź' => 'Z', 'Á' => 'A', 1115 'Û' => 'U', 'Þ' => 'Th', 'Ð' => 'Dh', 'Æ' => 'Ae', 'Ĕ' => 'E', 1116); 1117 1118/** 1119 * UTF-8 array of common special characters 1120 * 1121 * This array should contain all special characters (not a letter or digit) 1122 * defined in the various local charsets - it's not a complete list of non-alphanum 1123 * characters in UTF-8. It's not perfect but should match most cases of special 1124 * chars. 1125 * 1126 * The controlchars 0x00 to 0x19 are _not_ included in this array. The space 0x20 is! 1127 * These chars are _not_ in the array either: _ (0x5f), : 0x3a, . 0x2e, - 0x2d, * 0x2a 1128 * 1129 * @author Andreas Gohr <andi@splitbrain.org> 1130 * @see utf8_stripspecials() 1131 */ 1132global $UTF8_SPECIAL_CHARS; 1133$UTF8_SPECIAL_CHARS = array( 1134 0x001a, 0x001b, 0x001c, 0x001d, 0x001e, 0x001f, 0x0020, 0x0021, 0x0022, 0x0023, 1135 0x0024, 0x0025, 0x0026, 0x0027, 0x0028, 0x0029, 0x002b, 0x002c, 1136 0x002f, 0x003b, 0x003c, 0x003d, 0x003e, 0x003f, 0x0040, 0x005b, 1137 0x005c, 0x005d, 0x005e, 0x0060, 0x007b, 0x007c, 0x007d, 0x007e, 1138 0x007f, 0x0080, 0x0081, 0x0082, 0x0083, 0x0084, 0x0085, 0x0086, 0x0087, 0x0088, 1139 0x0089, 0x008a, 0x008b, 0x008c, 0x008d, 0x008e, 0x008f, 0x0090, 0x0091, 0x0092, 1140 0x0093, 0x0094, 0x0095, 0x0096, 0x0097, 0x0098, 0x0099, 0x009a, 0x009b, 0x009c, 1141 0x009d, 0x009e, 0x009f, 0x00a0, 0x00a1, 0x00a2, 0x00a3, 0x00a4, 0x00a5, 0x00a6, 1142 0x00a7, 0x00a8, 0x00a9, 0x00aa, 0x00ab, 0x00ac, 0x00ad, 0x00ae, 0x00af, 0x00b0, 1143 0x00b1, 0x00b2, 0x00b3, 0x00b4, 0x00b5, 0x00b6, 0x00b7, 0x00b8, 0x00b9, 0x00ba, 1144 0x00bb, 0x00bc, 0x00bd, 0x00be, 0x00bf, 0x00d7, 0x00f7, 0x02c7, 0x02d8, 0x02d9, 1145 0x02da, 0x02db, 0x02dc, 0x02dd, 0x0300, 0x0301, 0x0303, 0x0309, 0x0323, 0x0384, 1146 0x0385, 0x0387, 0x03c6, 0x03d1, 0x03d2, 0x03d5, 0x03d6, 0x05b0, 0x05b1, 1147 0x05b2, 0x05b3, 0x05b4, 0x05b5, 0x05b6, 0x05b7, 0x05b8, 0x05b9, 0x05bb, 0x05bc, 1148 0x05bd, 0x05be, 0x05bf, 0x05c0, 0x05c1, 0x05c2, 0x05c3, 0x05f3, 0x05f4, 0x060c, 1149 0x061b, 0x061f, 0x0640, 0x064b, 0x064c, 0x064d, 0x064e, 0x064f, 0x0650, 0x0651, 1150 0x0652, 0x066a, 0x0e3f, 0x200c, 0x200d, 0x200e, 0x200f, 0x2013, 0x2014, 0x2015, 1151 0x2017, 0x2018, 0x2019, 0x201a, 0x201c, 0x201d, 0x201e, 0x2020, 0x2021, 0x2022, 1152 0x2026, 0x2030, 0x2032, 0x2033, 0x2039, 0x203a, 0x2044, 0x20a7, 0x20aa, 0x20ab, 1153 0x20ac, 0x2116, 0x2118, 0x2122, 0x2126, 0x2135, 0x2190, 0x2191, 0x2192, 0x2193, 1154 0x2194, 0x2195, 0x21b5, 0x21d0, 0x21d1, 0x21d2, 0x21d3, 0x21d4, 0x2200, 0x2202, 1155 0x2203, 0x2205, 0x2206, 0x2207, 0x2208, 0x2209, 0x220b, 0x220f, 0x2211, 0x2212, 1156 0x2215, 0x2217, 0x2219, 0x221a, 0x221d, 0x221e, 0x2220, 0x2227, 0x2228, 0x2229, 1157 0x222a, 0x222b, 0x2234, 0x223c, 0x2245, 0x2248, 0x2260, 0x2261, 0x2264, 0x2265, 1158 0x2282, 0x2283, 0x2284, 0x2286, 0x2287, 0x2295, 0x2297, 0x22a5, 0x22c5, 0x2310, 1159 0x2320, 0x2321, 0x2329, 0x232a, 0x2469, 0x2500, 0x2502, 0x250c, 0x2510, 0x2514, 1160 0x2518, 0x251c, 0x2524, 0x252c, 0x2534, 0x253c, 0x2550, 0x2551, 0x2552, 0x2553, 1161 0x2554, 0x2555, 0x2556, 0x2557, 0x2558, 0x2559, 0x255a, 0x255b, 0x255c, 0x255d, 1162 0x255e, 0x255f, 0x2560, 0x2561, 0x2562, 0x2563, 0x2564, 0x2565, 0x2566, 0x2567, 1163 0x2568, 0x2569, 0x256a, 0x256b, 0x256c, 0x2580, 0x2584, 0x2588, 0x258c, 0x2590, 1164 0x2591, 0x2592, 0x2593, 0x25a0, 0x25b2, 0x25bc, 0x25c6, 0x25ca, 0x25cf, 0x25d7, 1165 0x2605, 0x260e, 0x261b, 0x261e, 0x2660, 0x2663, 0x2665, 0x2666, 0x2701, 0x2702, 1166 0x2703, 0x2704, 0x2706, 0x2707, 0x2708, 0x2709, 0x270c, 0x270d, 0x270e, 0x270f, 1167 0x2710, 0x2711, 0x2712, 0x2713, 0x2714, 0x2715, 0x2716, 0x2717, 0x2718, 0x2719, 1168 0x271a, 0x271b, 0x271c, 0x271d, 0x271e, 0x271f, 0x2720, 0x2721, 0x2722, 0x2723, 1169 0x2724, 0x2725, 0x2726, 0x2727, 0x2729, 0x272a, 0x272b, 0x272c, 0x272d, 0x272e, 1170 0x272f, 0x2730, 0x2731, 0x2732, 0x2733, 0x2734, 0x2735, 0x2736, 0x2737, 0x2738, 1171 0x2739, 0x273a, 0x273b, 0x273c, 0x273d, 0x273e, 0x273f, 0x2740, 0x2741, 0x2742, 1172 0x2743, 0x2744, 0x2745, 0x2746, 0x2747, 0x2748, 0x2749, 0x274a, 0x274b, 0x274d, 1173 0x274f, 0x2750, 0x2751, 0x2752, 0x2756, 0x2758, 0x2759, 0x275a, 0x275b, 0x275c, 1174 0x275d, 0x275e, 0x2761, 0x2762, 0x2763, 0x2764, 0x2765, 0x2766, 0x2767, 0x277f, 1175 0x2789, 0x2793, 0x2794, 0x2798, 0x2799, 0x279a, 0x279b, 0x279c, 0x279d, 0x279e, 1176 0x279f, 0x27a0, 0x27a1, 0x27a2, 0x27a3, 0x27a4, 0x27a5, 0x27a6, 0x27a7, 0x27a8, 1177 0x27a9, 0x27aa, 0x27ab, 0x27ac, 0x27ad, 0x27ae, 0x27af, 0x27b1, 0x27b2, 0x27b3, 1178 0x27b4, 0x27b5, 0x27b6, 0x27b7, 0x27b8, 0x27b9, 0x27ba, 0x27bb, 0x27bc, 0x27bd, 1179 0x27be, 0x3000, 0x3001, 0x3002, 0x3003, 0x3008, 0x3009, 0x300a, 0x300b, 0x300c, 1180 0x300d, 0x300e, 0x300f, 0x3010, 0x3011, 0x3012, 0x3014, 0x3015, 0x3016, 0x3017, 1181 0x3018, 0x3019, 0x301a, 0x301b, 0x3036, 1182 0xf6d9, 0xf6da, 0xf6db, 0xf8d7, 0xf8d8, 0xf8d9, 0xf8da, 0xf8db, 0xf8dc, 1183 0xf8dd, 0xf8de, 0xf8df, 0xf8e0, 0xf8e1, 0xf8e2, 0xf8e3, 0xf8e4, 0xf8e5, 0xf8e6, 1184 0xf8e7, 0xf8e8, 0xf8e9, 0xf8ea, 0xf8eb, 0xf8ec, 0xf8ed, 0xf8ee, 0xf8ef, 0xf8f0, 1185 0xf8f1, 0xf8f2, 0xf8f3, 0xf8f4, 0xf8f5, 0xf8f6, 0xf8f7, 0xf8f8, 0xf8f9, 0xf8fa, 1186 0xf8fb, 0xf8fc, 0xf8fd, 0xf8fe, 0xfe7c, 0xfe7d, 1187 0xff01, 0xff02, 0xff03, 0xff04, 0xff05, 0xff06, 0xff07, 0xff08, 0xff09, 1188 0xff09, 0xff0a, 0xff0b, 0xff0c, 0xff0d, 0xff0e, 0xff0f, 0xff1a, 0xff1b, 0xff1c, 1189 0xff1d, 0xff1e, 0xff1f, 0xff20, 0xff3b, 0xff3c, 0xff3d, 0xff3e, 0xff40, 0xff5b, 1190 0xff5c, 0xff5d, 0xff5e, 0xff5f, 0xff60, 0xff61, 0xff62, 0xff63, 0xff64, 0xff65, 1191 0xffe0, 0xffe1, 0xffe2, 0xffe3, 0xffe4, 0xffe5, 0xffe6, 0xffe8, 0xffe9, 0xffea, 1192 0xffeb, 0xffec, 0xffed, 0xffee, 1193 0x01d6fc, 0x01d6fd, 0x01d6fe, 0x01d6ff, 0x01d700, 0x01d701, 0x01d702, 0x01d703, 1194 0x01d704, 0x01d705, 0x01d706, 0x01d707, 0x01d708, 0x01d709, 0x01d70a, 0x01d70b, 1195 0x01d70c, 0x01d70d, 0x01d70e, 0x01d70f, 0x01d710, 0x01d711, 0x01d712, 0x01d713, 1196 0x01d714, 0x01d715, 0x01d716, 0x01d717, 0x01d718, 0x01d719, 0x01d71a, 0x01d71b 1197); 1198 1199// utf8 version of above data 1200global $UTF8_SPECIAL_CHARS2; 1201$UTF8_SPECIAL_CHARS2 = 1202 "\x1A".' !"#$%&\'()+,/;<=>?@[\]^`{|}~€‚ƒ„…†‡ˆ‰Š‹ŒŽ‘’“”•�'. 1203 '�—˜™š›œžŸ ¡¢£¤¥¦§¨©ª«¬®¯°±²³´µ¶·¸¹º»¼½�'. 1204 '�¿×÷ˇ˘˙˚˛˜˝̣̀́̃̉΄΅·ϖְֱֲֳִֵֶַָֹֻּֽ־ֿ�'. 1205 '�ׁׂ׃׳״،؛؟ـًٌٍَُِّْ٪฿–—―‗‘’‚“”�'. 1206 '��†‡•…‰′″‹›⁄₧₪₫€№℘™Ωℵ←↑→↓↔↕↵'. 1207 '⇐⇑⇒⇓⇔∀∂∃∅∆∇∈∉∋∏∑−∕∗∙√∝∞∠∧∨�'. 1208 '�∪∫∴∼≅≈≠≡≤≥⊂⊃⊄⊆⊇⊕⊗⊥⋅⌐⌠⌡〈〉⑩─�'. 1209 '��┌┐└┘├┤┬┴┼═║╒╓╔╕╖╗╘╙╚╛╜╝╞╟╠'. 1210 '╡╢╣╤╥╦╧╨╩╪╫╬▀▄█▌▐░▒▓■▲▼◆◊●�'. 1211 '�★☎☛☞♠♣♥♦✁✂✃✄✆✇✈✉✌✍✎✏✐✑✒✓✔✕�'. 1212 '��✗✘✙✚✛✜✝✞✟✠✡✢✣✤✥✦✧✩✪✫✬✭✮✯✰✱'. 1213 '✲✳✴✵✶✷✸✹✺✻✼✽✾✿❀❁❂❃❄❅❆❇❈❉❊❋�'. 1214 '�❏❐❑❒❖❘❙❚❛❜❝❞❡❢❣❤❥❦❧❿➉➓➔➘➙➚�'. 1215 '��➜➝➞➟➠➡➢➣➤➥➦➧➨➩➪➫➬➭➮➯➱➲➳➴➵➶'. 1216 '➷➸➹➺➻➼➽➾'. 1217 ' 、。〃〈〉《》「」『』【】〒〔〕〖〗〘〙〚〛〶'. 1218 '�'. 1219 '�ﹼﹽ'. 1220 '！＂＃＄％＆＇（）＊＋，－．／：；＜＝＞？＠［＼］＾｀｛｜｝～'. 1221 '｟｠｡｢｣､･￠￡￢￣￤￥￦￨￩￪￫￬￭￮'. 1222 '����������������������������������������������������������������'; 1223 1224/** 1225 * Romanization lookup table 1226 * 1227 * This lookup tables provides a way to transform strings written in a language 1228 * different from the ones based upon latin letters into plain ASCII. 1229 * 1230 * Please note: this is not a scientific transliteration table. It only works 1231 * oneway from nonlatin to ASCII and it works by simple character replacement 1232 * only. Specialities of each language are not supported. 1233 * 1234 * @author Andreas Gohr <andi@splitbrain.org> 1235 * @author Vitaly Blokhin <vitinfo@vitn.com> 1236 * @link http://www.uconv.com/translit.htm 1237 * @author Bisqwit <bisqwit@iki.fi> 1238 * @link http://kanjidict.stc.cx/hiragana.php?src=2 1239 * @link http://www.translatum.gr/converter/greek-transliteration.htm 1240 * @link http://en.wikipedia.org/wiki/Royal_Thai_General_System_of_Transcription 1241 * @link http://www.btranslations.com/resources/romanization/korean.asp 1242 * @author Arthit Suriyawongkul <arthit@gmail.com> 1243 * @author Denis Scheither <amorphis@uni-bremen.de> 1244 */ 1245global $UTF8_ROMANIZATION; 1246$UTF8_ROMANIZATION = array( 1247 // scandinavian - differs from what we do in deaccent 1248 'å'=>'a','Å'=>'A','ä'=>'a','Ä'=>'A','ö'=>'o','Ö'=>'O', 1249 1250 //russian cyrillic 1251 'а'=>'a','А'=>'A','б'=>'b','Б'=>'B','в'=>'v','В'=>'V','г'=>'g','Г'=>'G', 1252 'д'=>'d','Д'=>'D','е'=>'e','Е'=>'E','ё'=>'jo','Ё'=>'Jo','ж'=>'zh','Ж'=>'Zh', 1253 'з'=>'z','З'=>'Z','и'=>'i','И'=>'I','й'=>'j','Й'=>'J','к'=>'k','К'=>'K', 1254 'л'=>'l','Л'=>'L','м'=>'m','М'=>'M','н'=>'n','Н'=>'N','о'=>'o','О'=>'O', 1255 'п'=>'p','П'=>'P','р'=>'r','Р'=>'R','с'=>'s','С'=>'S','т'=>'t','Т'=>'T', 1256 'у'=>'u','У'=>'U','ф'=>'f','Ф'=>'F','х'=>'x','Х'=>'X','ц'=>'c','Ц'=>'C', 1257 'ч'=>'ch','Ч'=>'Ch','ш'=>'sh','Ш'=>'Sh','щ'=>'sch','Щ'=>'Sch','ъ'=>'', 1258 'Ъ'=>'','ы'=>'y','Ы'=>'Y','ь'=>'','Ь'=>'','э'=>'eh','Э'=>'Eh','ю'=>'ju', 1259 'Ю'=>'Ju','я'=>'ja','Я'=>'Ja', 1260 // Ukrainian cyrillic 1261 'Ґ'=>'Gh','ґ'=>'gh','Є'=>'Je','є'=>'je','І'=>'I','і'=>'i','Ї'=>'Ji','ї'=>'ji', 1262 // Georgian 1263 'ა'=>'a','ბ'=>'b','გ'=>'g','დ'=>'d','ე'=>'e','ვ'=>'v','ზ'=>'z','თ'=>'th', 1264 'ი'=>'i','კ'=>'p','ლ'=>'l','მ'=>'m','ნ'=>'n','ო'=>'o','პ'=>'p','ჟ'=>'zh', 1265 'რ'=>'r','ს'=>'s','ტ'=>'t','უ'=>'u','ფ'=>'ph','ქ'=>'kh','ღ'=>'gh','ყ'=>'q', 1266 'შ'=>'sh','ჩ'=>'ch','ც'=>'c','ძ'=>'dh','წ'=>'w','ჭ'=>'j','ხ'=>'x','ჯ'=>'jh', 1267 'ჰ'=>'xh', 1268 //Sanskrit 1269 'अ'=>'a','आ'=>'ah','इ'=>'i','ई'=>'ih','उ'=>'u','ऊ'=>'uh','ऋ'=>'ry', 1270 'ॠ'=>'ryh','ऌ'=>'ly','ॡ'=>'lyh','ए'=>'e','ऐ'=>'ay','ओ'=>'o','औ'=>'aw', 1271 'अं'=>'amh','अः'=>'aq','क'=>'k','ख'=>'kh','ग'=>'g','घ'=>'gh','ङ'=>'nh', 1272 'च'=>'c','छ'=>'ch','ज'=>'j','झ'=>'jh','ञ'=>'ny','ट'=>'tq','ठ'=>'tqh', 1273 'ड'=>'dq','ढ'=>'dqh','ण'=>'nq','त'=>'t','थ'=>'th','द'=>'d','ध'=>'dh', 1274 'न'=>'n','प'=>'p','फ'=>'ph','ब'=>'b','भ'=>'bh','म'=>'m','य'=>'z','र'=>'r', 1275 'ल'=>'l','व'=>'v','श'=>'sh','ष'=>'sqh','स'=>'s','ह'=>'x', 1276 //Hebrew 1277 'א'=>'a', 'ב'=>'b','ג'=>'g','ד'=>'d','ה'=>'h','ו'=>'v','ז'=>'z','ח'=>'kh','ט'=>'th', 1278 'י'=>'y','ך'=>'h','כ'=>'k','ל'=>'l','ם'=>'m','מ'=>'m','ן'=>'n','נ'=>'n', 1279 'ס'=>'s','ע'=>'ah','ף'=>'f','פ'=>'p','ץ'=>'c','צ'=>'c','ק'=>'q','ר'=>'r', 1280 'ש'=>'sh','ת'=>'t', 1281 //Arabic 1282 'ا'=>'a','ب'=>'b','ت'=>'t','ث'=>'th','ج'=>'g','ح'=>'xh','خ'=>'x','د'=>'d', 1283 'ذ'=>'dh','ر'=>'r','ز'=>'z','س'=>'s','ش'=>'sh','ص'=>'s\'','ض'=>'d\'', 1284 'ط'=>'t\'','ظ'=>'z\'','ع'=>'y','غ'=>'gh','ف'=>'f','ق'=>'q','ك'=>'k', 1285 'ل'=>'l','م'=>'m','ن'=>'n','ه'=>'x\'','و'=>'u','ي'=>'i', 1286 1287 // Japanese characters (last update: 2008-05-09) 1288 1289 // Japanese hiragana 1290 1291 // 3 character syllables, っ doubles the consonant after 1292 'っちゃ'=>'ccha','っちぇ'=>'cche','っちょ'=>'ccho','っちゅ'=>'cchu', 1293 'っびゃ'=>'bbya','っびぇ'=>'bbye','っびぃ'=>'bbyi','っびょ'=>'bbyo','っびゅ'=>'bbyu', 1294 'っぴゃ'=>'ppya','っぴぇ'=>'ppye','っぴぃ'=>'ppyi','っぴょ'=>'ppyo','っぴゅ'=>'ppyu', 1295 'っちゃ'=>'ccha','っちぇ'=>'cche','っち'=>'cchi','っちょ'=>'ccho','っちゅ'=>'cchu', 1296 // 'っひゃ'=>'hya','っひぇ'=>'hye','っひぃ'=>'hyi','っひょ'=>'hyo','っひゅ'=>'hyu', 1297 'っきゃ'=>'kkya','っきぇ'=>'kkye','っきぃ'=>'kkyi','っきょ'=>'kkyo','っきゅ'=>'kkyu', 1298 'っぎゃ'=>'ggya','っぎぇ'=>'ggye','っぎぃ'=>'ggyi','っぎょ'=>'ggyo','っぎゅ'=>'ggyu', 1299 'っみゃ'=>'mmya','っみぇ'=>'mmye','っみぃ'=>'mmyi','っみょ'=>'mmyo','っみゅ'=>'mmyu', 1300 'っにゃ'=>'nnya','っにぇ'=>'nnye','っにぃ'=>'nnyi','っにょ'=>'nnyo','っにゅ'=>'nnyu', 1301 'っりゃ'=>'rrya','っりぇ'=>'rrye','っりぃ'=>'rryi','っりょ'=>'rryo','っりゅ'=>'rryu', 1302 'っしゃ'=>'ssha','っしぇ'=>'sshe','っし'=>'sshi','っしょ'=>'ssho','っしゅ'=>'sshu', 1303 1304 // seperate hiragana 'n' ('n' + 'i' != 'ni', normally we would write "kon'nichi wa" but the apostrophe would be converted to _ anyway) 1305 'んあ'=>'n_a','んえ'=>'n_e','んい'=>'n_i','んお'=>'n_o','んう'=>'n_u', 1306 'んや'=>'n_ya','んよ'=>'n_yo','んゆ'=>'n_yu', 1307 1308 // 2 character syllables - normal 1309 'ふぁ'=>'fa','ふぇ'=>'fe','ふぃ'=>'fi','ふぉ'=>'fo', 1310 'ちゃ'=>'cha','ちぇ'=>'che','ち'=>'chi','ちょ'=>'cho','ちゅ'=>'chu', 1311 'ひゃ'=>'hya','ひぇ'=>'hye','ひぃ'=>'hyi','ひょ'=>'hyo','ひゅ'=>'hyu', 1312 'びゃ'=>'bya','びぇ'=>'bye','びぃ'=>'byi','びょ'=>'byo','びゅ'=>'byu', 1313 'ぴゃ'=>'pya','ぴぇ'=>'pye','ぴぃ'=>'pyi','ぴょ'=>'pyo','ぴゅ'=>'pyu', 1314 'きゃ'=>'kya','きぇ'=>'kye','きぃ'=>'kyi','きょ'=>'kyo','きゅ'=>'kyu', 1315 'ぎゃ'=>'gya','ぎぇ'=>'gye','ぎぃ'=>'gyi','ぎょ'=>'gyo','ぎゅ'=>'gyu', 1316 'みゃ'=>'mya','みぇ'=>'mye','みぃ'=>'myi','みょ'=>'myo','みゅ'=>'myu', 1317 'にゃ'=>'nya','にぇ'=>'nye','にぃ'=>'nyi','にょ'=>'nyo','にゅ'=>'nyu', 1318 'りゃ'=>'rya','りぇ'=>'rye','りぃ'=>'ryi','りょ'=>'ryo','りゅ'=>'ryu', 1319 'しゃ'=>'sha','しぇ'=>'she','し'=>'shi','しょ'=>'sho','しゅ'=>'shu', 1320 'じゃ'=>'ja','じぇ'=>'je','じょ'=>'jo','じゅ'=>'ju', 1321 'うぇ'=>'we','うぃ'=>'wi', 1322 'いぇ'=>'ye', 1323 1324 // 2 character syllables, っ doubles the consonant after 1325 'っば'=>'bba','っべ'=>'bbe','っび'=>'bbi','っぼ'=>'bbo','っぶ'=>'bbu', 1326 'っぱ'=>'ppa','っぺ'=>'ppe','っぴ'=>'ppi','っぽ'=>'ppo','っぷ'=>'ppu', 1327 'った'=>'tta','って'=>'tte','っち'=>'cchi','っと'=>'tto','っつ'=>'ttsu', 1328 'っだ'=>'dda','っで'=>'dde','っぢ'=>'ddi','っど'=>'ddo','っづ'=>'ddu', 1329 'っが'=>'gga','っげ'=>'gge','っぎ'=>'ggi','っご'=>'ggo','っぐ'=>'ggu', 1330 'っか'=>'kka','っけ'=>'kke','っき'=>'kki','っこ'=>'kko','っく'=>'kku', 1331 'っま'=>'mma','っめ'=>'mme','っみ'=>'mmi','っも'=>'mmo','っむ'=>'mmu', 1332 'っな'=>'nna','っね'=>'nne','っに'=>'nni','っの'=>'nno','っぬ'=>'nnu', 1333 'っら'=>'rra','っれ'=>'rre','っり'=>'rri','っろ'=>'rro','っる'=>'rru', 1334 'っさ'=>'ssa','っせ'=>'sse','っし'=>'sshi','っそ'=>'sso','っす'=>'ssu', 1335 'っざ'=>'zza','っぜ'=>'zze','っじ'=>'jji','っぞ'=>'zzo','っず'=>'zzu', 1336 1337 // 1 character syllabels 1338 'あ'=>'a','え'=>'e','い'=>'i','お'=>'o','う'=>'u','ん'=>'n', 1339 'は'=>'ha','へ'=>'he','ひ'=>'hi','ほ'=>'ho','ふ'=>'fu', 1340 'ば'=>'ba','べ'=>'be','び'=>'bi','ぼ'=>'bo','ぶ'=>'bu', 1341 'ぱ'=>'pa','ぺ'=>'pe','ぴ'=>'pi','ぽ'=>'po','ぷ'=>'pu', 1342 'た'=>'ta','て'=>'te','ち'=>'chi','と'=>'to','つ'=>'tsu', 1343 'だ'=>'da','で'=>'de','ぢ'=>'di','ど'=>'do','づ'=>'du', 1344 'が'=>'ga','げ'=>'ge','ぎ'=>'gi','ご'=>'go','ぐ'=>'gu', 1345 'か'=>'ka','け'=>'ke','き'=>'ki','こ'=>'ko','く'=>'ku', 1346 'ま'=>'ma','め'=>'me','み'=>'mi','も'=>'mo','む'=>'mu', 1347 'な'=>'na','ね'=>'ne','に'=>'ni','の'=>'no','ぬ'=>'nu', 1348 'ら'=>'ra','れ'=>'re','り'=>'ri','ろ'=>'ro','る'=>'ru', 1349 'さ'=>'sa','せ'=>'se','し'=>'shi','そ'=>'so','す'=>'su', 1350 'わ'=>'wa','を'=>'wo', 1351 'ざ'=>'za','ぜ'=>'ze','じ'=>'ji','ぞ'=>'zo','ず'=>'zu', 1352 'や'=>'ya','よ'=>'yo','ゆ'=>'yu', 1353 // old characters 1354 'ゑ'=>'we','ゐ'=>'wi', 1355 1356 // convert what's left (probably only kicks in when something's missing above) 1357 // 'ぁ'=>'a','ぇ'=>'e','ぃ'=>'i','ぉ'=>'o','ぅ'=>'u', 1358 // 'ゃ'=>'ya','ょ'=>'yo','ゅ'=>'yu', 1359 1360 // never seen one of those (disabled for the moment) 1361 // 'ヴぁ'=>'va','ヴぇ'=>'ve','ヴぃ'=>'vi','ヴぉ'=>'vo','ヴ'=>'vu', 1362 // 'でゃ'=>'dha','でぇ'=>'dhe','でぃ'=>'dhi','でょ'=>'dho','でゅ'=>'dhu', 1363 // 'どぁ'=>'dwa','どぇ'=>'dwe','どぃ'=>'dwi','どぉ'=>'dwo','どぅ'=>'dwu', 1364 // 'ぢゃ'=>'dya','ぢぇ'=>'dye','ぢぃ'=>'dyi','ぢょ'=>'dyo','ぢゅ'=>'dyu', 1365 // 'ふぁ'=>'fwa','ふぇ'=>'fwe','ふぃ'=>'fwi','ふぉ'=>'fwo','ふぅ'=>'fwu', 1366 // 'ふゃ'=>'fya','ふぇ'=>'fye','ふぃ'=>'fyi','ふょ'=>'fyo','ふゅ'=>'fyu', 1367 // 'すぁ'=>'swa','すぇ'=>'swe','すぃ'=>'swi','すぉ'=>'swo','すぅ'=>'swu', 1368 // 'てゃ'=>'tha','てぇ'=>'the','てぃ'=>'thi','てょ'=>'tho','てゅ'=>'thu', 1369 // 'つゃ'=>'tsa','つぇ'=>'tse','つぃ'=>'tsi','つょ'=>'tso','つ'=>'tsu', 1370 // 'とぁ'=>'twa','とぇ'=>'twe','とぃ'=>'twi','とぉ'=>'two','とぅ'=>'twu', 1371 // 'ヴゃ'=>'vya','ヴぇ'=>'vye','ヴぃ'=>'vyi','ヴょ'=>'vyo','ヴゅ'=>'vyu', 1372 // 'うぁ'=>'wha','うぇ'=>'whe','うぃ'=>'whi','うぉ'=>'who','うぅ'=>'whu', 1373 // 'じゃ'=>'zha','じぇ'=>'zhe','じぃ'=>'zhi','じょ'=>'zho','じゅ'=>'zhu', 1374 // 'じゃ'=>'zya','じぇ'=>'zye','じぃ'=>'zyi','じょ'=>'zyo','じゅ'=>'zyu', 1375 1376 // 'spare' characters from other romanization systems 1377 // 'だ'=>'da','で'=>'de','ぢ'=>'di','ど'=>'do','づ'=>'du', 1378 // 'ら'=>'la','れ'=>'le','り'=>'li','ろ'=>'lo','る'=>'lu', 1379 // 'さ'=>'sa','せ'=>'se','し'=>'si','そ'=>'so','す'=>'su', 1380 // 'ちゃ'=>'cya','ちぇ'=>'cye','ちぃ'=>'cyi','ちょ'=>'cyo','ちゅ'=>'cyu', 1381 //'じゃ'=>'jya','じぇ'=>'jye','じぃ'=>'jyi','じょ'=>'jyo','じゅ'=>'jyu', 1382 //'りゃ'=>'lya','りぇ'=>'lye','りぃ'=>'lyi','りょ'=>'lyo','りゅ'=>'lyu', 1383 //'しゃ'=>'sya','しぇ'=>'sye','しぃ'=>'syi','しょ'=>'syo','しゅ'=>'syu', 1384 //'ちゃ'=>'tya','ちぇ'=>'tye','ちぃ'=>'tyi','ちょ'=>'tyo','ちゅ'=>'tyu', 1385 //'し'=>'ci',,い'=>'yi','ぢ'=>'dzi', 1386 //'っじゃ'=>'jja','っじぇ'=>'jje','っじ'=>'jji','っじょ'=>'jjo','っじゅ'=>'jju', 1387 1388 1389 // Japanese katakana 1390 1391 // 4 character syllables: ッ doubles the consonant after, ー doubles the vowel before (usualy written with macron, but we don't want that in our URLs) 1392 'ッビャー'=>'bbyaa','ッビェー'=>'bbyee','ッビィー'=>'bbyii','ッビョー'=>'bbyoo','ッビュー'=>'bbyuu', 1393 'ッピャー'=>'ppyaa','ッピェー'=>'ppyee','ッピィー'=>'ppyii','ッピョー'=>'ppyoo','ッピュー'=>'ppyuu', 1394 'ッキャー'=>'kkyaa','ッキェー'=>'kkyee','ッキィー'=>'kkyii','ッキョー'=>'kkyoo','ッキュー'=>'kkyuu', 1395 'ッギャー'=>'ggyaa','ッギェー'=>'ggyee','ッギィー'=>'ggyii','ッギョー'=>'ggyoo','ッギュー'=>'ggyuu', 1396 'ッミャー'=>'mmyaa','ッミェー'=>'mmyee','ッミィー'=>'mmyii','ッミョー'=>'mmyoo','ッミュー'=>'mmyuu', 1397 'ッニャー'=>'nnyaa','ッニェー'=>'nnyee','ッニィー'=>'nnyii','ッニョー'=>'nnyoo','ッニュー'=>'nnyuu', 1398 'ッリャー'=>'rryaa','ッリェー'=>'rryee','ッリィー'=>'rryii','ッリョー'=>'rryoo','ッリュー'=>'rryuu', 1399 'ッシャー'=>'sshaa','ッシェー'=>'sshee','ッシー'=>'sshii','ッショー'=>'sshoo','ッシュー'=>'sshuu', 1400 'ッチャー'=>'cchaa','ッチェー'=>'cchee','ッチー'=>'cchii','ッチョー'=>'cchoo','ッチュー'=>'cchuu', 1401 'ッティー'=>'ttii', 1402 'ッヂィー'=>'ddii', 1403 1404 // 3 character syllables - doubled vowels 1405 'ファー'=>'faa','フェー'=>'fee','フィー'=>'fii','フォー'=>'foo', 1406 'フャー'=>'fyaa','フェー'=>'fyee','フィー'=>'fyii','フョー'=>'fyoo','フュー'=>'fyuu', 1407 'ヒャー'=>'hyaa','ヒェー'=>'hyee','ヒィー'=>'hyii','ヒョー'=>'hyoo','ヒュー'=>'hyuu', 1408 'ビャー'=>'byaa','ビェー'=>'byee','ビィー'=>'byii','ビョー'=>'byoo','ビュー'=>'byuu', 1409 'ピャー'=>'pyaa','ピェー'=>'pyee','ピィー'=>'pyii','ピョー'=>'pyoo','ピュー'=>'pyuu', 1410 'キャー'=>'kyaa','キェー'=>'kyee','キィー'=>'kyii','キョー'=>'kyoo','キュー'=>'kyuu', 1411 'ギャー'=>'gyaa','ギェー'=>'gyee','ギィー'=>'gyii','ギョー'=>'gyoo','ギュー'=>'gyuu', 1412 'ミャー'=>'myaa','ミェー'=>'myee','ミィー'=>'myii','ミョー'=>'myoo','ミュー'=>'myuu', 1413 'ニャー'=>'nyaa','ニェー'=>'nyee','ニィー'=>'nyii','ニョー'=>'nyoo','ニュー'=>'nyuu', 1414 'リャー'=>'ryaa','リェー'=>'ryee','リィー'=>'ryii','リョー'=>'ryoo','リュー'=>'ryuu', 1415 'シャー'=>'shaa','シェー'=>'shee','シー'=>'shii','ショー'=>'shoo','シュー'=>'shuu', 1416 'ジャー'=>'jaa','ジェー'=>'jee','ジー'=>'jii','ジョー'=>'joo','ジュー'=>'juu', 1417 'スァー'=>'swaa','スェー'=>'swee','スィー'=>'swii','スォー'=>'swoo','スゥー'=>'swuu', 1418 'デァー'=>'daa','デェー'=>'dee','ディー'=>'dii','デォー'=>'doo','デゥー'=>'duu', 1419 'チャー'=>'chaa','チェー'=>'chee','チー'=>'chii','チョー'=>'choo','チュー'=>'chuu', 1420 'ヂャー'=>'dyaa','ヂェー'=>'dyee','ヂィー'=>'dyii','ヂョー'=>'dyoo','ヂュー'=>'dyuu', 1421 'ツャー'=>'tsaa','ツェー'=>'tsee','ツィー'=>'tsii','ツョー'=>'tsoo','ツー'=>'tsuu', 1422 'トァー'=>'twaa','トェー'=>'twee','トィー'=>'twii','トォー'=>'twoo','トゥー'=>'twuu', 1423 'ドァー'=>'dwaa','ドェー'=>'dwee','ドィー'=>'dwii','ドォー'=>'dwoo','ドゥー'=>'dwuu', 1424 'ウァー'=>'whaa','ウェー'=>'whee','ウィー'=>'whii','ウォー'=>'whoo','ウゥー'=>'whuu', 1425 'ヴャー'=>'vyaa','ヴェー'=>'vyee','ヴィー'=>'vyii','ヴョー'=>'vyoo','ヴュー'=>'vyuu', 1426 'ヴァー'=>'vaa','ヴェー'=>'vee','ヴィー'=>'vii','ヴォー'=>'voo','ヴー'=>'vuu', 1427 'ウェー'=>'wee','ウィー'=>'wii', 1428 'イェー'=>'yee', 1429 'ティー'=>'tii', 1430 'ヂィー'=>'dii', 1431 1432 // 3 character syllables - doubled consonants 1433 'ッビャ'=>'bbya','ッビェ'=>'bbye','ッビィ'=>'bbyi','ッビョ'=>'bbyo','ッビュ'=>'bbyu', 1434 'ッピャ'=>'ppya','ッピェ'=>'ppye','ッピィ'=>'ppyi','ッピョ'=>'ppyo','ッピュ'=>'ppyu', 1435 'ッキャ'=>'kkya','ッキェ'=>'kkye','ッキィ'=>'kkyi','ッキョ'=>'kkyo','ッキュ'=>'kkyu', 1436 'ッギャ'=>'ggya','ッギェ'=>'ggye','ッギィ'=>'ggyi','ッギョ'=>'ggyo','ッギュ'=>'ggyu', 1437 'ッミャ'=>'mmya','ッミェ'=>'mmye','ッミィ'=>'mmyi','ッミョ'=>'mmyo','ッミュ'=>'mmyu', 1438 'ッニャ'=>'nnya','ッニェ'=>'nnye','ッニィ'=>'nnyi','ッニョ'=>'nnyo','ッニュ'=>'nnyu', 1439 'ッリャ'=>'rrya','ッリェ'=>'rrye','ッリィ'=>'rryi','ッリョ'=>'rryo','ッリュ'=>'rryu', 1440 'ッシャ'=>'ssha','ッシェ'=>'sshe','ッシ'=>'sshi','ッショ'=>'ssho','ッシュ'=>'sshu', 1441 'ッチャ'=>'ccha','ッチェ'=>'cche','ッチ'=>'cchi','ッチョ'=>'ccho','ッチュ'=>'cchu', 1442 'ッティ'=>'tti', 1443 'ッヂィ'=>'ddi', 1444 1445 // 3 character syllables - doubled vowel and consonants 1446 'ッバー'=>'bbaa','ッベー'=>'bbee','ッビー'=>'bbii','ッボー'=>'bboo','ッブー'=>'bbuu', 1447 'ッパー'=>'ppaa','ッペー'=>'ppee','ッピー'=>'ppii','ッポー'=>'ppoo','ップー'=>'ppuu', 1448 'ッケー'=>'kkee','ッキー'=>'kkii','ッコー'=>'kkoo','ックー'=>'kkuu','ッカー'=>'kkaa', 1449 'ッガー'=>'ggaa','ッゲー'=>'ggee','ッギー'=>'ggii','ッゴー'=>'ggoo','ッグー'=>'gguu', 1450 'ッマー'=>'maa','ッメー'=>'mee','ッミー'=>'mii','ッモー'=>'moo','ッムー'=>'muu', 1451 'ッナー'=>'nnaa','ッネー'=>'nnee','ッニー'=>'nnii','ッノー'=>'nnoo','ッヌー'=>'nnuu', 1452 'ッラー'=>'rraa','ッレー'=>'rree','ッリー'=>'rrii','ッロー'=>'rroo','ッルー'=>'rruu', 1453 'ッサー'=>'ssaa','ッセー'=>'ssee','ッシー'=>'sshii','ッソー'=>'ssoo','ッスー'=>'ssuu', 1454 'ッザー'=>'zzaa','ッゼー'=>'zzee','ッジー'=>'jjii','ッゾー'=>'zzoo','ッズー'=>'zzuu', 1455 'ッター'=>'ttaa','ッテー'=>'ttee','ッチー'=>'chii','ットー'=>'ttoo','ッツー'=>'ttsuu', 1456 'ッダー'=>'ddaa','ッデー'=>'ddee','ッヂー'=>'ddii','ッドー'=>'ddoo','ッヅー'=>'dduu', 1457 1458 // 2 character syllables - normal 1459 'ファ'=>'fa','フェ'=>'fe','フィ'=>'fi','フォ'=>'fo','フゥ'=>'fu', 1460 // 'フャ'=>'fya','フェ'=>'fye','フィ'=>'fyi','フョ'=>'fyo','フュ'=>'fyu', 1461 'フャ'=>'fa','フェ'=>'fe','フィ'=>'fi','フョ'=>'fo','フュ'=>'fu', 1462 'ヒャ'=>'hya','ヒェ'=>'hye','ヒィ'=>'hyi','ヒョ'=>'hyo','ヒュ'=>'hyu', 1463 'ビャ'=>'bya','ビェ'=>'bye','ビィ'=>'byi','ビョ'=>'byo','ビュ'=>'byu', 1464 'ピャ'=>'pya','ピェ'=>'pye','ピィ'=>'pyi','ピョ'=>'pyo','ピュ'=>'pyu', 1465 'キャ'=>'kya','キェ'=>'kye','キィ'=>'kyi','キョ'=>'kyo','キュ'=>'kyu', 1466 'ギャ'=>'gya','ギェ'=>'gye','ギィ'=>'gyi','ギョ'=>'gyo','ギュ'=>'gyu', 1467 'ミャ'=>'mya','ミェ'=>'mye','ミィ'=>'myi','ミョ'=>'myo','ミュ'=>'myu', 1468 'ニャ'=>'nya','ニェ'=>'nye','ニィ'=>'nyi','ニョ'=>'nyo','ニュ'=>'nyu', 1469 'リャ'=>'rya','リェ'=>'rye','リィ'=>'ryi','リョ'=>'ryo','リュ'=>'ryu', 1470 'シャ'=>'sha','シェ'=>'she','ショ'=>'sho','シュ'=>'shu', 1471 'ジャ'=>'ja','ジェ'=>'je','ジョ'=>'jo','ジュ'=>'ju', 1472 'スァ'=>'swa','スェ'=>'swe','スィ'=>'swi','スォ'=>'swo','スゥ'=>'swu', 1473 'デァ'=>'da','デェ'=>'de','ディ'=>'di','デォ'=>'do','デゥ'=>'du', 1474 'チャ'=>'cha','チェ'=>'che','チ'=>'chi','チョ'=>'cho','チュ'=>'chu', 1475 // 'ヂャ'=>'dya','ヂェ'=>'dye','ヂィ'=>'dyi','ヂョ'=>'dyo','ヂュ'=>'dyu', 1476 'ツャ'=>'tsa','ツェ'=>'tse','ツィ'=>'tsi','ツョ'=>'tso','ツ'=>'tsu', 1477 'トァ'=>'twa','トェ'=>'twe','トィ'=>'twi','トォ'=>'two','トゥ'=>'twu', 1478 'ドァ'=>'dwa','ドェ'=>'dwe','ドィ'=>'dwi','ドォ'=>'dwo','ドゥ'=>'dwu', 1479 'ウァ'=>'wha','ウェ'=>'whe','ウィ'=>'whi','ウォ'=>'who','ウゥ'=>'whu', 1480 'ヴャ'=>'vya','ヴェ'=>'vye','ヴィ'=>'vyi','ヴョ'=>'vyo','ヴュ'=>'vyu', 1481 'ヴァ'=>'va','ヴェ'=>'ve','ヴィ'=>'vi','ヴォ'=>'vo','ヴ'=>'vu', 1482 'ウェ'=>'we','ウィ'=>'wi', 1483 'イェ'=>'ye', 1484 'ティ'=>'ti', 1485 'ヂィ'=>'di', 1486 1487 // 2 character syllables - doubled vocal 1488 'アー'=>'aa','エー'=>'ee','イー'=>'ii','オー'=>'oo','ウー'=>'uu', 1489 'ダー'=>'daa','デー'=>'dee','ヂー'=>'dii','ドー'=>'doo','ヅー'=>'duu', 1490 'ハー'=>'haa','ヘー'=>'hee','ヒー'=>'hii','ホー'=>'hoo','フー'=>'fuu', 1491 'バー'=>'baa','ベー'=>'bee','ビー'=>'bii','ボー'=>'boo','ブー'=>'buu', 1492 'パー'=>'paa','ペー'=>'pee','ピー'=>'pii','ポー'=>'poo','プー'=>'puu', 1493 'ケー'=>'kee','キー'=>'kii','コー'=>'koo','クー'=>'kuu','カー'=>'kaa', 1494 'ガー'=>'gaa','ゲー'=>'gee','ギー'=>'gii','ゴー'=>'goo','グー'=>'guu', 1495 'マー'=>'maa','メー'=>'mee','ミー'=>'mii','モー'=>'moo','ムー'=>'muu', 1496 'ナー'=>'naa','ネー'=>'nee','ニー'=>'nii','ノー'=>'noo','ヌー'=>'nuu', 1497 'ラー'=>'raa','レー'=>'ree','リー'=>'rii','ロー'=>'roo','ルー'=>'ruu', 1498 'サー'=>'saa','セー'=>'see','シー'=>'shii','ソー'=>'soo','スー'=>'suu', 1499 'ザー'=>'zaa','ゼー'=>'zee','ジー'=>'jii','ゾー'=>'zoo','ズー'=>'zuu', 1500 'ター'=>'taa','テー'=>'tee','チー'=>'chii','トー'=>'too','ツー'=>'tsuu', 1501 'ワー'=>'waa','ヲー'=>'woo', 1502 'ヤー'=>'yaa','ヨー'=>'yoo','ユー'=>'yuu', 1503 'ヵー'=>'kaa','ヶー'=>'kee', 1504 // old characters 1505 'ヱー'=>'wee','ヰー'=>'wii', 1506 1507 // seperate katakana 'n' 1508 'ンア'=>'n_a','ンエ'=>'n_e','ンイ'=>'n_i','ンオ'=>'n_o','ンウ'=>'n_u', 1509 'ンヤ'=>'n_ya','ンヨ'=>'n_yo','ンユ'=>'n_yu', 1510 1511 // 2 character syllables - doubled consonants 1512 'ッバ'=>'bba','ッベ'=>'bbe','ッビ'=>'bbi','ッボ'=>'bbo','ッブ'=>'bbu', 1513 'ッパ'=>'ppa','ッペ'=>'ppe','ッピ'=>'ppi','ッポ'=>'ppo','ップ'=>'ppu', 1514 'ッケ'=>'kke','ッキ'=>'kki','ッコ'=>'kko','ック'=>'kku','ッカ'=>'kka', 1515 'ッガ'=>'gga','ッゲ'=>'gge','ッギ'=>'ggi','ッゴ'=>'ggo','ッグ'=>'ggu', 1516 'ッマ'=>'ma','ッメ'=>'me','ッミ'=>'mi','ッモ'=>'mo','ッム'=>'mu', 1517 'ッナ'=>'nna','ッネ'=>'nne','ッニ'=>'nni','ッノ'=>'nno','ッヌ'=>'nnu', 1518 'ッラ'=>'rra','ッレ'=>'rre','ッリ'=>'rri','ッロ'=>'rro','ッル'=>'rru', 1519 'ッサ'=>'ssa','ッセ'=>'sse','ッシ'=>'sshi','ッソ'=>'sso','ッス'=>'ssu', 1520 'ッザ'=>'zza','ッゼ'=>'zze','ッジ'=>'jji','ッゾ'=>'zzo','ッズ'=>'zzu', 1521 'ッタ'=>'tta','ッテ'=>'tte','ッチ'=>'cchi','ット'=>'tto','ッツ'=>'ttsu', 1522 'ッダ'=>'dda','ッデ'=>'dde','ッヂ'=>'ddi','ッド'=>'ddo','ッヅ'=>'ddu', 1523 1524 // 1 character syllables 1525 'ア'=>'a','エ'=>'e','イ'=>'i','オ'=>'o','ウ'=>'u','ン'=>'n', 1526 'ハ'=>'ha','ヘ'=>'he','ヒ'=>'hi','ホ'=>'ho','フ'=>'fu', 1527 'バ'=>'ba','ベ'=>'be','ビ'=>'bi','ボ'=>'bo','ブ'=>'bu', 1528 'パ'=>'pa','ペ'=>'pe','ピ'=>'pi','ポ'=>'po','プ'=>'pu', 1529 'ケ'=>'ke','キ'=>'ki','コ'=>'ko','ク'=>'ku','カ'=>'ka', 1530 'ガ'=>'ga','ゲ'=>'ge','ギ'=>'gi','ゴ'=>'go','グ'=>'gu', 1531 'マ'=>'ma','メ'=>'me','ミ'=>'mi','モ'=>'mo','ム'=>'mu', 1532 'ナ'=>'na','ネ'=>'ne','ニ'=>'ni','ノ'=>'no','ヌ'=>'nu', 1533 'ラ'=>'ra','レ'=>'re','リ'=>'ri','ロ'=>'ro','ル'=>'ru', 1534 'サ'=>'sa','セ'=>'se','シ'=>'shi','ソ'=>'so','ス'=>'su', 1535 'ザ'=>'za','ゼ'=>'ze','ジ'=>'ji','ゾ'=>'zo','ズ'=>'zu', 1536 'タ'=>'ta','テ'=>'te','チ'=>'chi','ト'=>'to','ツ'=>'tsu', 1537 'ダ'=>'da','デ'=>'de','ヂ'=>'di','ド'=>'do','ヅ'=>'du', 1538 'ワ'=>'wa','ヲ'=>'wo', 1539 'ヤ'=>'ya','ヨ'=>'yo','ユ'=>'yu', 1540 'ヵ'=>'ka','ヶ'=>'ke', 1541 // old characters 1542 'ヱ'=>'we','ヰ'=>'wi', 1543 1544 // convert what's left (probably only kicks in when something's missing above) 1545 'ァ'=>'a','ェ'=>'e','ィ'=>'i','ォ'=>'o','ゥ'=>'u', 1546 'ャ'=>'ya','ョ'=>'yo','ュ'=>'yu', 1547 1548 // special characters 1549 '・'=>'_','、'=>'_', 1550 'ー'=>'_', // when used with hiragana (seldom), this character would not be converted otherwise 1551 1552 // 'ラ'=>'la','レ'=>'le','リ'=>'li','ロ'=>'lo','ル'=>'lu', 1553 // 'チャ'=>'cya','チェ'=>'cye','チィ'=>'cyi','チョ'=>'cyo','チュ'=>'cyu', 1554 //'デャ'=>'dha','デェ'=>'dhe','ディ'=>'dhi','デョ'=>'dho','デュ'=>'dhu', 1555 // 'リャ'=>'lya','リェ'=>'lye','リィ'=>'lyi','リョ'=>'lyo','リュ'=>'lyu', 1556 // 'テャ'=>'tha','テェ'=>'the','ティ'=>'thi','テョ'=>'tho','テュ'=>'thu', 1557 //'ファ'=>'fwa','フェ'=>'fwe','フィ'=>'fwi','フォ'=>'fwo','フゥ'=>'fwu', 1558 //'チャ'=>'tya','チェ'=>'tye','チィ'=>'tyi','チョ'=>'tyo','チュ'=>'tyu', 1559 // 'ジャ'=>'jya','ジェ'=>'jye','ジィ'=>'jyi','ジョ'=>'jyo','ジュ'=>'jyu', 1560 // 'ジャ'=>'zha','ジェ'=>'zhe','ジィ'=>'zhi','ジョ'=>'zho','ジュ'=>'zhu', 1561 //'ジャ'=>'zya','ジェ'=>'zye','ジィ'=>'zyi','ジョ'=>'zyo','ジュ'=>'zyu', 1562 //'シャ'=>'sya','シェ'=>'sye','シィ'=>'syi','ショ'=>'syo','シュ'=>'syu', 1563 //'シ'=>'ci','フ'=>'hu',シ'=>'si','チ'=>'ti','ツ'=>'tu','イ'=>'yi','ヂ'=>'dzi', 1564 1565 // "Greeklish" 1566 'Γ'=>'G','Δ'=>'E','Θ'=>'Th','Λ'=>'L','Ξ'=>'X','Π'=>'P','Σ'=>'S','Φ'=>'F','Ψ'=>'Ps', 1567 'γ'=>'g','δ'=>'e','θ'=>'th','λ'=>'l','ξ'=>'x','π'=>'p','σ'=>'s','φ'=>'f','ψ'=>'ps', 1568 1569 // Thai 1570 'ก'=>'k','ข'=>'kh','ฃ'=>'kh','ค'=>'kh','ฅ'=>'kh','ฆ'=>'kh','ง'=>'ng','จ'=>'ch', 1571 'ฉ'=>'ch','ช'=>'ch','ซ'=>'s','ฌ'=>'ch','ญ'=>'y','ฎ'=>'d','ฏ'=>'t','ฐ'=>'th', 1572 'ฑ'=>'d','ฒ'=>'th','ณ'=>'n','ด'=>'d','ต'=>'t','ถ'=>'th','ท'=>'th','ธ'=>'th', 1573 'น'=>'n','บ'=>'b','ป'=>'p','ผ'=>'ph','ฝ'=>'f','พ'=>'ph','ฟ'=>'f','ภ'=>'ph', 1574 'ม'=>'m','ย'=>'y','ร'=>'r','ฤ'=>'rue','ฤๅ'=>'rue','ล'=>'l','ฦ'=>'lue', 1575 'ฦๅ'=>'lue','ว'=>'w','ศ'=>'s','ษ'=>'s','ส'=>'s','ห'=>'h','ฬ'=>'l','ฮ'=>'h', 1576 'ะ'=>'a','ั'=>'a','รร'=>'a','า'=>'a','ๅ'=>'a','ำ'=>'am','ํา'=>'am', 1577 'ิ'=>'i','ี'=>'i','ึ'=>'ue','ี'=>'ue','ุ'=>'u','ู'=>'u', 1578 'เ'=>'e','แ'=>'ae','โ'=>'o','อ'=>'o', 1579 'ียะ'=>'ia','ีย'=>'ia','ือะ'=>'uea','ือ'=>'uea','ัวะ'=>'ua','ัว'=>'ua', 1580 'ใ'=>'ai','ไ'=>'ai','ัย'=>'ai','าย'=>'ai','าว'=>'ao', 1581 'ุย'=>'ui','อย'=>'oi','ือย'=>'ueai','วย'=>'uai', 1582 'ิว'=>'io','็ว'=>'eo','ียว'=>'iao', 1583 '่'=>'','้'=>'','๊'=>'','๋'=>'','็'=>'', 1584 '์'=>'','๎'=>'','ํ'=>'','ฺ'=>'', 1585 'ๆ'=>'2','๏'=>'o','ฯ'=>'-','๚'=>'-','๛'=>'-', 1586 '๐'=>'0','๑'=>'1','๒'=>'2','๓'=>'3','๔'=>'4', 1587 '๕'=>'5','๖'=>'6','๗'=>'7','๘'=>'8','๙'=>'9', 1588 1589 // Korean 1590 'ㄱ'=>'k','ㅋ'=>'kh','ㄲ'=>'kk','ㄷ'=>'t','ㅌ'=>'th','ㄸ'=>'tt','ㅂ'=>'p', 1591 'ㅍ'=>'ph','ㅃ'=>'pp','ㅈ'=>'c','ㅊ'=>'ch','ㅉ'=>'cc','ㅅ'=>'s','ㅆ'=>'ss', 1592 'ㅎ'=>'h','ㅇ'=>'ng','ㄴ'=>'n','ㄹ'=>'l','ㅁ'=>'m', 'ㅏ'=>'a','ㅓ'=>'e','ㅗ'=>'o', 1593 'ㅜ'=>'wu','ㅡ'=>'u','ㅣ'=>'i','ㅐ'=>'ay','ㅔ'=>'ey','ㅚ'=>'oy','ㅘ'=>'wa','ㅝ'=>'we', 1594 'ㅟ'=>'wi','ㅙ'=>'way','ㅞ'=>'wey','ㅢ'=>'uy','ㅑ'=>'ya','ㅕ'=>'ye','ㅛ'=>'oy', 1595 'ㅠ'=>'yu','ㅒ'=>'yay','ㅖ'=>'yey', 1596); 1597 1598//Setup VIM: ex: et ts=2 enc=utf-8 : 1599 1600