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,$UTF8_LOWER_TO_UPPER); 318} 319 320/** 321 * Replace accented UTF-8 characters by unaccented ASCII-7 equivalents 322 * 323 * Use the optional parameter to just deaccent lower ($case = -1) or upper ($case = 1) 324 * letters. Default is to deaccent both cases ($case = 0) 325 * 326 * @author Andreas Gohr <andi@splitbrain.org> 327 */ 328function utf8_deaccent($string,$case=0){ 329 if($case <= 0){ 330 global $UTF8_LOWER_ACCENTS; 331 $string = strtr($string,$UTF8_LOWER_ACCENTS); 332 } 333 if($case >= 0){ 334 global $UTF8_UPPER_ACCENTS; 335 $string = strtr($string,$UTF8_UPPER_ACCENTS); 336 } 337 return $string; 338} 339 340/** 341 * Romanize a non-latin string 342 * 343 * @author Andreas Gohr <andi@splitbrain.org> 344 */ 345function utf8_romanize($string){ 346 if(utf8_isASCII($string)) return $string; //nothing to do 347 348 global $UTF8_ROMANIZATION; 349 return strtr($string,$UTF8_ROMANIZATION); 350} 351 352/** 353 * Removes special characters (nonalphanumeric) from a UTF-8 string 354 * 355 * This function adds the controlchars 0x00 to 0x19 to the array of 356 * stripped chars (they are not included in $UTF8_SPECIAL_CHARS) 357 * 358 * @author Andreas Gohr <andi@splitbrain.org> 359 * @param string $string The UTF8 string to strip of special chars 360 * @param string $repl Replace special with this string 361 * @param string $additional Additional chars to strip (used in regexp char class) 362 */ 363function utf8_stripspecials($string,$repl='',$additional=''){ 364 global $UTF8_SPECIAL_CHARS; 365 global $UTF8_SPECIAL_CHARS2; 366 367 static $specials = null; 368 if(is_null($specials)){ 369# $specials = preg_quote(unicode_to_utf8($UTF8_SPECIAL_CHARS), '/'); 370 $specials = preg_quote($UTF8_SPECIAL_CHARS2, '/'); 371 } 372 373 return preg_replace('/['.$additional.'\x00-\x19'.$specials.']/u',$repl,$string); 374} 375 376/** 377 * This is an Unicode aware replacement for strpos 378 * 379 * @author Leo Feyer <leo@typolight.org> 380 * @see strpos() 381 * @param string 382 * @param string 383 * @param integer 384 * @return integer 385 */ 386function utf8_strpos($haystack, $needle, $offset=0){ 387 $comp = 0; 388 $length = null; 389 390 while (is_null($length) || $length < $offset) { 391 $pos = strpos($haystack, $needle, $offset + $comp); 392 393 if ($pos === false) 394 return false; 395 396 $length = utf8_strlen(substr($haystack, 0, $pos)); 397 398 if ($length < $offset) 399 $comp = $pos - $length; 400 } 401 402 return $length; 403} 404 405 406/** 407 * Encodes UTF-8 characters to HTML entities 408 * 409 * @author Tom N Harris <tnharris@whoopdedo.org> 410 * @author <vpribish at shopping dot com> 411 * @link http://www.php.net/manual/en/function.utf8-decode.php 412 */ 413function utf8_tohtml ($str) { 414 $ret = ''; 415 foreach (utf8_to_unicode($str) as $cp) { 416 if ($cp < 0x80) 417 $ret .= chr($cp); 418 elseif ($cp < 0x100) 419 $ret .= "&#$cp;"; 420 else 421 $ret .= '&#x'.dechex($cp).';'; 422 } 423 return $ret; 424} 425 426/** 427 * Decodes HTML entities to UTF-8 characters 428 * 429 * Convert any &#..; entity to a codepoint, 430 * The entities flag defaults to only decoding numeric entities. 431 * Pass HTML_ENTITIES and named entities, including & < etc. 432 * are handled as well. Avoids the problem that would occur if you 433 * had to decode "&#38;&amp;#38;" 434 * 435 * unhtmlspecialchars(utf8_unhtml($s)) -> "&&" 436 * utf8_unhtml(unhtmlspecialchars($s)) -> "&&#38;" 437 * what it should be -> "&&#38;" 438 * 439 * @author Tom N Harris <tnharris@whoopdedo.org> 440 * @param string $str UTF-8 encoded string 441 * @param boolean $entities Flag controlling decoding of named entities. 442 * @return UTF-8 encoded string with numeric (and named) entities replaced. 443 */ 444function utf8_unhtml($str, $entities=null) { 445 static $decoder = null; 446 if (is_null($decoder)) 447 $decoder = new utf8_entity_decoder(); 448 if (is_null($entities)) 449 return preg_replace_callback('/(&#([Xx])?([0-9A-Za-z]+);)/m', 450 'utf8_decode_numeric', $str); 451 else 452 return preg_replace_callback('/&(#)?([Xx])?([0-9A-Za-z]+);/m', 453 array(&$decoder, 'decode'), $str); 454} 455function utf8_decode_numeric($ent) { 456 switch ($ent[2]) { 457 case 'X': 458 case 'x': 459 $cp = hexdec($ent[3]); 460 break; 461 default: 462 $cp = intval($ent[3]); 463 break; 464 } 465 return unicode_to_utf8(array($cp)); 466} 467class utf8_entity_decoder { 468 var $table; 469 function utf8_entity_decoder() { 470 $table = get_html_translation_table(HTML_ENTITIES); 471 $table = array_flip($table); 472 $this->table = array_map(array(&$this,'makeutf8'), $table); 473 } 474 function makeutf8($c) { 475 return unicode_to_utf8(array(ord($c))); 476 } 477 function decode($ent) { 478 if ($ent[1] == '#') { 479 return utf8_decode_numeric($ent); 480 } elseif (array_key_exists($ent[0],$this->table)) { 481 return $this->table[$ent[0]]; 482 } else { 483 return $ent[0]; 484 } 485 } 486} 487 488/** 489 * Takes an UTF-8 string and returns an array of ints representing the 490 * Unicode characters. Astral planes are supported ie. the ints in the 491 * output can be > 0xFFFF. Occurrances of the BOM are ignored. Surrogates 492 * are not allowed. 493 * 494 * If $strict is set to true the function returns false if the input 495 * string isn't a valid UTF-8 octet sequence and raises a PHP error at 496 * level E_USER_WARNING 497 * 498 * Note: this function has been modified slightly in this library to 499 * trigger errors on encountering bad bytes 500 * 501 * @author <hsivonen@iki.fi> 502 * @author Harry Fuecks <hfuecks@gmail.com> 503 * @param string UTF-8 encoded string 504 * @param boolean Check for invalid sequences? 505 * @return mixed array of unicode code points or false if UTF-8 invalid 506 * @see unicode_to_utf8 507 * @link http://hsivonen.iki.fi/php-utf8/ 508 * @link http://sourceforge.net/projects/phputf8/ 509 */ 510function utf8_to_unicode($str,$strict=false) { 511 $mState = 0; // cached expected number of octets after the current octet 512 // until the beginning of the next UTF8 character sequence 513 $mUcs4 = 0; // cached Unicode character 514 $mBytes = 1; // cached expected number of octets in the current sequence 515 516 $out = array(); 517 518 $len = strlen($str); 519 520 for($i = 0; $i < $len; $i++) { 521 522 $in = ord($str{$i}); 523 524 if ( $mState == 0) { 525 526 // When mState is zero we expect either a US-ASCII character or a 527 // multi-octet sequence. 528 if (0 == (0x80 & ($in))) { 529 // US-ASCII, pass straight through. 530 $out[] = $in; 531 $mBytes = 1; 532 533 } else if (0xC0 == (0xE0 & ($in))) { 534 // First octet of 2 octet sequence 535 $mUcs4 = ($in); 536 $mUcs4 = ($mUcs4 & 0x1F) << 6; 537 $mState = 1; 538 $mBytes = 2; 539 540 } else if (0xE0 == (0xF0 & ($in))) { 541 // First octet of 3 octet sequence 542 $mUcs4 = ($in); 543 $mUcs4 = ($mUcs4 & 0x0F) << 12; 544 $mState = 2; 545 $mBytes = 3; 546 547 } else if (0xF0 == (0xF8 & ($in))) { 548 // First octet of 4 octet sequence 549 $mUcs4 = ($in); 550 $mUcs4 = ($mUcs4 & 0x07) << 18; 551 $mState = 3; 552 $mBytes = 4; 553 554 } else if (0xF8 == (0xFC & ($in))) { 555 /* First octet of 5 octet sequence. 556 * 557 * This is illegal because the encoded codepoint must be either 558 * (a) not the shortest form or 559 * (b) outside the Unicode range of 0-0x10FFFF. 560 * Rather than trying to resynchronize, we will carry on until the end 561 * of the sequence and let the later error handling code catch it. 562 */ 563 $mUcs4 = ($in); 564 $mUcs4 = ($mUcs4 & 0x03) << 24; 565 $mState = 4; 566 $mBytes = 5; 567 568 } else if (0xFC == (0xFE & ($in))) { 569 // First octet of 6 octet sequence, see comments for 5 octet sequence. 570 $mUcs4 = ($in); 571 $mUcs4 = ($mUcs4 & 1) << 30; 572 $mState = 5; 573 $mBytes = 6; 574 575 } elseif($strict) { 576 /* Current octet is neither in the US-ASCII range nor a legal first 577 * octet of a multi-octet sequence. 578 */ 579 trigger_error( 580 'utf8_to_unicode: Illegal sequence identifier '. 581 'in UTF-8 at byte '.$i, 582 E_USER_WARNING 583 ); 584 return false; 585 586 } 587 588 } else { 589 590 // When mState is non-zero, we expect a continuation of the multi-octet 591 // sequence 592 if (0x80 == (0xC0 & ($in))) { 593 594 // Legal continuation. 595 $shift = ($mState - 1) * 6; 596 $tmp = $in; 597 $tmp = ($tmp & 0x0000003F) << $shift; 598 $mUcs4 |= $tmp; 599 600 /** 601 * End of the multi-octet sequence. mUcs4 now contains the final 602 * Unicode codepoint to be output 603 */ 604 if (0 == --$mState) { 605 606 /* 607 * Check for illegal sequences and codepoints. 608 */ 609 // From Unicode 3.1, non-shortest form is illegal 610 if (((2 == $mBytes) && ($mUcs4 < 0x0080)) || 611 ((3 == $mBytes) && ($mUcs4 < 0x0800)) || 612 ((4 == $mBytes) && ($mUcs4 < 0x10000)) || 613 (4 < $mBytes) || 614 // From Unicode 3.2, surrogate characters are illegal 615 (($mUcs4 & 0xFFFFF800) == 0xD800) || 616 // Codepoints outside the Unicode range are illegal 617 ($mUcs4 > 0x10FFFF)) { 618 619 if($strict){ 620 trigger_error( 621 'utf8_to_unicode: Illegal sequence or codepoint '. 622 'in UTF-8 at byte '.$i, 623 E_USER_WARNING 624 ); 625 626 return false; 627 } 628 629 } 630 631 if (0xFEFF != $mUcs4) { 632 // BOM is legal but we don't want to output it 633 $out[] = $mUcs4; 634 } 635 636 //initialize UTF8 cache 637 $mState = 0; 638 $mUcs4 = 0; 639 $mBytes = 1; 640 } 641 642 } elseif($strict) { 643 /** 644 *((0xC0 & (*in) != 0x80) && (mState != 0)) 645 * Incomplete multi-octet sequence. 646 */ 647 trigger_error( 648 'utf8_to_unicode: Incomplete multi-octet '. 649 ' sequence in UTF-8 at byte '.$i, 650 E_USER_WARNING 651 ); 652 653 return false; 654 } 655 } 656 } 657 return $out; 658} 659 660/** 661 * Takes an array of ints representing the Unicode characters and returns 662 * a UTF-8 string. Astral planes are supported ie. the ints in the 663 * input can be > 0xFFFF. Occurrances of the BOM are ignored. Surrogates 664 * are not allowed. 665 * 666 * If $strict is set to true the function returns false if the input 667 * array contains ints that represent surrogates or are outside the 668 * Unicode range and raises a PHP error at level E_USER_WARNING 669 * 670 * Note: this function has been modified slightly in this library to use 671 * output buffering to concatenate the UTF-8 string (faster) as well as 672 * reference the array by it's keys 673 * 674 * @param array of unicode code points representing a string 675 * @param boolean Check for invalid sequences? 676 * @return mixed UTF-8 string or false if array contains invalid code points 677 * @author <hsivonen@iki.fi> 678 * @author Harry Fuecks <hfuecks@gmail.com> 679 * @see utf8_to_unicode 680 * @link http://hsivonen.iki.fi/php-utf8/ 681 * @link http://sourceforge.net/projects/phputf8/ 682 */ 683function unicode_to_utf8($arr,$strict=false) { 684 if (!is_array($arr)) return ''; 685 ob_start(); 686 687 foreach (array_keys($arr) as $k) { 688 689 # ASCII range (including control chars) 690 if ( ($arr[$k] >= 0) && ($arr[$k] <= 0x007f) ) { 691 692 echo chr($arr[$k]); 693 694 # 2 byte sequence 695 } else if ($arr[$k] <= 0x07ff) { 696 697 echo chr(0xc0 | ($arr[$k] >> 6)); 698 echo chr(0x80 | ($arr[$k] & 0x003f)); 699 700 # Byte order mark (skip) 701 } else if($arr[$k] == 0xFEFF) { 702 703 // nop -- zap the BOM 704 705 # Test for illegal surrogates 706 } else if ($arr[$k] >= 0xD800 && $arr[$k] <= 0xDFFF) { 707 708 // found a surrogate 709 if($strict){ 710 trigger_error( 711 'unicode_to_utf8: Illegal surrogate '. 712 'at index: '.$k.', value: '.$arr[$k], 713 E_USER_WARNING 714 ); 715 return false; 716 } 717 718 # 3 byte sequence 719 } else if ($arr[$k] <= 0xffff) { 720 721 echo chr(0xe0 | ($arr[$k] >> 12)); 722 echo chr(0x80 | (($arr[$k] >> 6) & 0x003f)); 723 echo chr(0x80 | ($arr[$k] & 0x003f)); 724 725 # 4 byte sequence 726 } else if ($arr[$k] <= 0x10ffff) { 727 728 echo chr(0xf0 | ($arr[$k] >> 18)); 729 echo chr(0x80 | (($arr[$k] >> 12) & 0x3f)); 730 echo chr(0x80 | (($arr[$k] >> 6) & 0x3f)); 731 echo chr(0x80 | ($arr[$k] & 0x3f)); 732 733 } elseif($strict) { 734 735 trigger_error( 736 'unicode_to_utf8: Codepoint out of Unicode range '. 737 'at index: '.$k.', value: '.$arr[$k], 738 E_USER_WARNING 739 ); 740 741 // out of range 742 return false; 743 } 744 } 745 746 $result = ob_get_contents(); 747 ob_end_clean(); 748 return $result; 749} 750 751/** 752 * UTF-8 to UTF-16BE conversion. 753 * 754 * Maybe really UCS-2 without mb_string due to utf8_to_unicode limits 755 */ 756function utf8_to_utf16be(&$str, $bom = false) { 757 $out = $bom ? "\xFE\xFF" : ''; 758 if(UTF8_MBSTRING) return $out.mb_convert_encoding($str,'UTF-16BE','UTF-8'); 759 760 $uni = utf8_to_unicode($str); 761 foreach($uni as $cp){ 762 $out .= pack('n',$cp); 763 } 764 return $out; 765} 766 767/** 768 * UTF-8 to UTF-16BE conversion. 769 * 770 * Maybe really UCS-2 without mb_string due to utf8_to_unicode limits 771 */ 772function utf16be_to_utf8(&$str) { 773 $uni = unpack('n*',$str); 774 return unicode_to_utf8($uni); 775} 776 777/** 778 * Replace bad bytes with an alternative character 779 * 780 * ASCII character is recommended for replacement char 781 * 782 * PCRE Pattern to locate bad bytes in a UTF-8 string 783 * Comes from W3 FAQ: Multilingual Forms 784 * Note: modified to include full ASCII range including control chars 785 * 786 * @author Harry Fuecks <hfuecks@gmail.com> 787 * @see http://www.w3.org/International/questions/qa-forms-utf-8 788 * @param string to search 789 * @param string to replace bad bytes with (defaults to '?') - use ASCII 790 * @return string 791 */ 792function utf8_bad_replace($str, $replace = '') { 793 $UTF8_BAD = 794 '([\x00-\x7F]'. # ASCII (including control chars) 795 '|[\xC2-\xDF][\x80-\xBF]'. # non-overlong 2-byte 796 '|\xE0[\xA0-\xBF][\x80-\xBF]'. # excluding overlongs 797 '|[\xE1-\xEC\xEE\xEF][\x80-\xBF]{2}'. # straight 3-byte 798 '|\xED[\x80-\x9F][\x80-\xBF]'. # excluding surrogates 799 '|\xF0[\x90-\xBF][\x80-\xBF]{2}'. # planes 1-3 800 '|[\xF1-\xF3][\x80-\xBF]{3}'. # planes 4-15 801 '|\xF4[\x80-\x8F][\x80-\xBF]{2}'. # plane 16 802 '|(.{1}))'; # invalid byte 803 ob_start(); 804 while (preg_match('/'.$UTF8_BAD.'/S', $str, $matches)) { 805 if ( !isset($matches[2])) { 806 echo $matches[0]; 807 } else { 808 echo $replace; 809 } 810 $str = substr($str,strlen($matches[0])); 811 } 812 $result = ob_get_contents(); 813 ob_end_clean(); 814 return $result; 815} 816 817/** 818 * adjust a byte index into a utf8 string to a utf8 character boundary 819 * 820 * @param $str string utf8 character string 821 * @param $i int byte index into $str 822 * @param $next bool direction to search for boundary, 823 * false = up (current character) 824 * true = down (next character) 825 * 826 * @return int byte index into $str now pointing to a utf8 character boundary 827 * 828 * @author chris smith <chris@jalakai.co.uk> 829 */ 830function utf8_correctIdx(&$str,$i,$next=false) { 831 832 if ($i <= 0) return 0; 833 834 $limit = strlen($str); 835 if ($i>=$limit) return $limit; 836 837 if ($next) { 838 while (($i<$limit) && ((ord($str[$i]) & 0xC0) == 0x80)) $i++; 839 } else { 840 while ($i && ((ord($str[$i]) & 0xC0) == 0x80)) $i--; 841 } 842 843 return $i; 844} 845 846// only needed if no mb_string available 847if(!UTF8_MBSTRING){ 848 /** 849 * UTF-8 Case lookup table 850 * 851 * This lookuptable defines the upper case letters to their correspponding 852 * lower case letter in UTF-8 853 * 854 * @author Andreas Gohr <andi@splitbrain.org> 855 */ 856 global $UTF8_LOWER_TO_UPPER; 857 $UTF8_LOWER_TO_UPPER = array( 858 "ｚ"=>"Ｚ","ｙ"=>"Ｙ","ｘ"=>"Ｘ","ｗ"=>"Ｗ","ｖ"=>"Ｖ","ｕ"=>"Ｕ","ｔ"=>"Ｔ","ｓ"=>"Ｓ","ｒ"=>"Ｒ","ｑ"=>"Ｑ", 859 "ｐ"=>"Ｐ","ｏ"=>"Ｏ","ｎ"=>"Ｎ","ｍ"=>"Ｍ","ｌ"=>"Ｌ","ｋ"=>"Ｋ","ｊ"=>"Ｊ","ｉ"=>"Ｉ","ｈ"=>"Ｈ","ｇ"=>"Ｇ", 860 "ｆ"=>"Ｆ","ｅ"=>"Ｅ","ｄ"=>"Ｄ","ｃ"=>"Ｃ","ｂ"=>"Ｂ","ａ"=>"Ａ","ῳ"=>"ῼ","ῥ"=>"Ῥ","ῡ"=>"Ῡ","ῑ"=>"Ῑ", 861 "ῐ"=>"Ῐ","ῃ"=>"ῌ","ι"=>"Ι","ᾳ"=>"ᾼ","ᾱ"=>"Ᾱ","ᾰ"=>"Ᾰ","ᾧ"=>"ᾯ","ᾦ"=>"ᾮ","ᾥ"=>"ᾭ","ᾤ"=>"ᾬ", 862 "ᾣ"=>"ᾫ","ᾢ"=>"ᾪ","ᾡ"=>"ᾩ","ᾗ"=>"ᾟ","ᾖ"=>"ᾞ","ᾕ"=>"ᾝ","ᾔ"=>"ᾜ","ᾓ"=>"ᾛ","ᾒ"=>"ᾚ","ᾑ"=>"ᾙ", 863 "ᾐ"=>"ᾘ","ᾇ"=>"ᾏ","ᾆ"=>"ᾎ","ᾅ"=>"ᾍ","ᾄ"=>"ᾌ","ᾃ"=>"ᾋ","ᾂ"=>"ᾊ","ᾁ"=>"ᾉ","ᾀ"=>"ᾈ","ώ"=>"Ώ", 864 "ὼ"=>"Ὼ","ύ"=>"Ύ","ὺ"=>"Ὺ","ό"=>"Ό","ὸ"=>"Ὸ","ί"=>"Ί","ὶ"=>"Ὶ","ή"=>"Ή","ὴ"=>"Ὴ","έ"=>"Έ", 865 "ὲ"=>"Ὲ","ά"=>"Ά","ὰ"=>"Ὰ","ὧ"=>"Ὧ","ὦ"=>"Ὦ","ὥ"=>"Ὥ","ὤ"=>"Ὤ","ὣ"=>"Ὣ","ὢ"=>"Ὢ","ὡ"=>"Ὡ", 866 "ὗ"=>"Ὗ","ὕ"=>"Ὕ","ὓ"=>"Ὓ","ὑ"=>"Ὑ","ὅ"=>"Ὅ","ὄ"=>"Ὄ","ὃ"=>"Ὃ","ὂ"=>"Ὂ","ὁ"=>"Ὁ","ὀ"=>"Ὀ", 867 "ἷ"=>"Ἷ","ἶ"=>"Ἶ","ἵ"=>"Ἵ","ἴ"=>"Ἴ","ἳ"=>"Ἳ","ἲ"=>"Ἲ","ἱ"=>"Ἱ","ἰ"=>"Ἰ","ἧ"=>"Ἧ","ἦ"=>"Ἦ", 868 "ἥ"=>"Ἥ","ἤ"=>"Ἤ","ἣ"=>"Ἣ","ἢ"=>"Ἢ","ἡ"=>"Ἡ","ἕ"=>"Ἕ","ἔ"=>"Ἔ","ἓ"=>"Ἓ","ἒ"=>"Ἒ","ἑ"=>"Ἑ", 869 "ἐ"=>"Ἐ","ἇ"=>"Ἇ","ἆ"=>"Ἆ","ἅ"=>"Ἅ","ἄ"=>"Ἄ","ἃ"=>"Ἃ","ἂ"=>"Ἂ","ἁ"=>"Ἁ","ἀ"=>"Ἀ","ỹ"=>"Ỹ", 870 "ỷ"=>"Ỷ","ỵ"=>"Ỵ","ỳ"=>"Ỳ","ự"=>"Ự","ữ"=>"Ữ","ử"=>"Ử","ừ"=>"Ừ","ứ"=>"Ứ","ủ"=>"Ủ","ụ"=>"Ụ", 871 "ợ"=>"Ợ","ỡ"=>"Ỡ","ở"=>"Ở","ờ"=>"Ờ","ớ"=>"Ớ","ộ"=>"Ộ","ỗ"=>"Ỗ","ổ"=>"Ổ","ồ"=>"Ồ","ố"=>"Ố", 872 "ỏ"=>"Ỏ","ọ"=>"Ọ","ị"=>"Ị","ỉ"=>"Ỉ","ệ"=>"Ệ","ễ"=>"Ễ","ể"=>"Ể","ề"=>"Ề","ế"=>"Ế","ẽ"=>"Ẽ", 873 "ẻ"=>"Ẻ","ẹ"=>"Ẹ","ặ"=>"Ặ","ẵ"=>"Ẵ","ẳ"=>"Ẳ","ằ"=>"Ằ","ắ"=>"Ắ","ậ"=>"Ậ","ẫ"=>"Ẫ","ẩ"=>"Ẩ", 874 "ầ"=>"Ầ","ấ"=>"Ấ","ả"=>"Ả","ạ"=>"Ạ","ẛ"=>"Ṡ","ẕ"=>"Ẕ","ẓ"=>"Ẓ","ẑ"=>"Ẑ","ẏ"=>"Ẏ","ẍ"=>"Ẍ", 875 "ẋ"=>"Ẋ","ẉ"=>"Ẉ","ẇ"=>"Ẇ","ẅ"=>"Ẅ","ẃ"=>"Ẃ","ẁ"=>"Ẁ","ṿ"=>"Ṿ","ṽ"=>"Ṽ","ṻ"=>"Ṻ","ṹ"=>"Ṹ", 876 "ṷ"=>"Ṷ","ṵ"=>"Ṵ","ṳ"=>"Ṳ","ṱ"=>"Ṱ","ṯ"=>"Ṯ","ṭ"=>"Ṭ","ṫ"=>"Ṫ","ṩ"=>"Ṩ","ṧ"=>"Ṧ","ṥ"=>"Ṥ", 877 "ṣ"=>"Ṣ","ṡ"=>"Ṡ","ṟ"=>"Ṟ","ṝ"=>"Ṝ","ṛ"=>"Ṛ","ṙ"=>"Ṙ","ṗ"=>"Ṗ","ṕ"=>"Ṕ","ṓ"=>"Ṓ","ṑ"=>"Ṑ", 878 "ṏ"=>"Ṏ","ṍ"=>"Ṍ","ṋ"=>"Ṋ","ṉ"=>"Ṉ","ṇ"=>"Ṇ","ṅ"=>"Ṅ","ṃ"=>"Ṃ","ṁ"=>"Ṁ","ḿ"=>"Ḿ","ḽ"=>"Ḽ", 879 "ḻ"=>"Ḻ","ḹ"=>"Ḹ","ḷ"=>"Ḷ","ḵ"=>"Ḵ","ḳ"=>"Ḳ","ḱ"=>"Ḱ","ḯ"=>"Ḯ","ḭ"=>"Ḭ","ḫ"=>"Ḫ","ḩ"=>"Ḩ", 880 "ḧ"=>"Ḧ","ḥ"=>"Ḥ","ḣ"=>"Ḣ","ḡ"=>"Ḡ","ḟ"=>"Ḟ","ḝ"=>"Ḝ","ḛ"=>"Ḛ","ḙ"=>"Ḙ","ḗ"=>"Ḗ","ḕ"=>"Ḕ", 881 "ḓ"=>"Ḓ","ḑ"=>"Ḑ","ḏ"=>"Ḏ","ḍ"=>"Ḍ","ḋ"=>"Ḋ","ḉ"=>"Ḉ","ḇ"=>"Ḇ","ḅ"=>"Ḅ","ḃ"=>"Ḃ","ḁ"=>"Ḁ", 882 "ֆ"=>"Ֆ","օ"=>"Օ","ք"=>"Ք","փ"=>"Փ","ւ"=>"Ւ","ց"=>"Ց","ր"=>"Ր","տ"=>"Տ","վ"=>"Վ","ս"=>"Ս", 883 "ռ"=>"Ռ","ջ"=>"Ջ","պ"=>"Պ","չ"=>"Չ","ո"=>"Ո","շ"=>"Շ","ն"=>"Ն","յ"=>"Յ","մ"=>"Մ","ճ"=>"Ճ", 884 "ղ"=>"Ղ","ձ"=>"Ձ","հ"=>"Հ","կ"=>"Կ","ծ"=>"Ծ","խ"=>"Խ","լ"=>"Լ","ի"=>"Ի","ժ"=>"Ժ","թ"=>"Թ", 885 "ը"=>"Ը","է"=>"Է","զ"=>"Զ","ե"=>"Ե","դ"=>"Դ","գ"=>"Գ","բ"=>"Բ","ա"=>"Ա","ԏ"=>"Ԏ","ԍ"=>"Ԍ", 886 "ԋ"=>"Ԋ","ԉ"=>"Ԉ","ԇ"=>"Ԇ","ԅ"=>"Ԅ","ԃ"=>"Ԃ","ԁ"=>"Ԁ","ӹ"=>"Ӹ","ӵ"=>"Ӵ","ӳ"=>"Ӳ","ӱ"=>"Ӱ", 887 "ӯ"=>"Ӯ","ӭ"=>"Ӭ","ӫ"=>"Ӫ","ө"=>"Ө","ӧ"=>"Ӧ","ӥ"=>"Ӥ","ӣ"=>"Ӣ","ӡ"=>"Ӡ","ӟ"=>"Ӟ","ӝ"=>"Ӝ", 888 "ӛ"=>"Ӛ","ә"=>"Ә","ӗ"=>"Ӗ","ӕ"=>"Ӕ","ӓ"=>"Ӓ","ӑ"=>"Ӑ","ӎ"=>"Ӎ","ӌ"=>"Ӌ","ӊ"=>"Ӊ","ӈ"=>"Ӈ", 889 "ӆ"=>"Ӆ","ӄ"=>"Ӄ","ӂ"=>"Ӂ","ҿ"=>"Ҿ","ҽ"=>"Ҽ","һ"=>"Һ","ҹ"=>"Ҹ","ҷ"=>"Ҷ","ҵ"=>"Ҵ","ҳ"=>"Ҳ", 890 "ұ"=>"Ұ","ү"=>"Ү","ҭ"=>"Ҭ","ҫ"=>"Ҫ","ҩ"=>"Ҩ","ҧ"=>"Ҧ","ҥ"=>"Ҥ","ң"=>"Ң","ҡ"=>"Ҡ","ҟ"=>"Ҟ", 891 "ҝ"=>"Ҝ","қ"=>"Қ","ҙ"=>"Ҙ","җ"=>"Җ","ҕ"=>"Ҕ","ғ"=>"Ғ","ґ"=>"Ґ","ҏ"=>"Ҏ","ҍ"=>"Ҍ","ҋ"=>"Ҋ", 892 "ҁ"=>"Ҁ","ѿ"=>"Ѿ","ѽ"=>"Ѽ","ѻ"=>"Ѻ","ѹ"=>"Ѹ","ѷ"=>"Ѷ","ѵ"=>"Ѵ","ѳ"=>"Ѳ","ѱ"=>"Ѱ","ѯ"=>"Ѯ", 893 "ѭ"=>"Ѭ","ѫ"=>"Ѫ","ѩ"=>"Ѩ","ѧ"=>"Ѧ","ѥ"=>"Ѥ","ѣ"=>"Ѣ","ѡ"=>"Ѡ","џ"=>"Џ","ў"=>"Ў","ѝ"=>"Ѝ", 894 "ќ"=>"Ќ","ћ"=>"Ћ","њ"=>"Њ","љ"=>"Љ","ј"=>"Ј","ї"=>"Ї","і"=>"І","ѕ"=>"Ѕ","є"=>"Є","ѓ"=>"Ѓ", 895 "ђ"=>"Ђ","ё"=>"Ё","ѐ"=>"Ѐ","я"=>"Я","ю"=>"Ю","э"=>"Э","ь"=>"Ь","ы"=>"Ы","ъ"=>"Ъ","щ"=>"Щ", 896 "ш"=>"Ш","ч"=>"Ч","ц"=>"Ц","х"=>"Х","ф"=>"Ф","у"=>"У","т"=>"Т","с"=>"С","р"=>"Р","п"=>"П", 897 "о"=>"О","н"=>"Н","м"=>"М","л"=>"Л","к"=>"К","й"=>"Й","и"=>"И","з"=>"З","ж"=>"Ж","е"=>"Е", 898 "д"=>"Д","г"=>"Г","в"=>"В","б"=>"Б","а"=>"А","ϵ"=>"Ε","ϲ"=>"Σ","ϱ"=>"Ρ","ϰ"=>"Κ","ϯ"=>"Ϯ", 899 "ϭ"=>"Ϭ","ϫ"=>"Ϫ","ϩ"=>"Ϩ","ϧ"=>"Ϧ","ϥ"=>"Ϥ","ϣ"=>"Ϣ","ϡ"=>"Ϡ","ϟ"=>"Ϟ","ϝ"=>"Ϝ","ϛ"=>"Ϛ", 900 "ϙ"=>"Ϙ","ϖ"=>"Π","ϕ"=>"Φ","ϑ"=>"Θ","ϐ"=>"Β","ώ"=>"Ώ","ύ"=>"Ύ","ό"=>"Ό","ϋ"=>"Ϋ","ϊ"=>"Ϊ", 901 "ω"=>"Ω","ψ"=>"Ψ","χ"=>"Χ","φ"=>"Φ","υ"=>"Υ","τ"=>"Τ","σ"=>"Σ","ς"=>"Σ","ρ"=>"Ρ","π"=>"Π", 902 "ο"=>"Ο","ξ"=>"Ξ","ν"=>"Ν","μ"=>"Μ","λ"=>"Λ","κ"=>"Κ","ι"=>"Ι","θ"=>"Θ","η"=>"Η","ζ"=>"Ζ", 903 "ε"=>"Ε","δ"=>"Δ","γ"=>"Γ","β"=>"Β","α"=>"Α","ί"=>"Ί","ή"=>"Ή","έ"=>"Έ","ά"=>"Ά","ʒ"=>"Ʒ", 904 "ʋ"=>"Ʋ","ʊ"=>"Ʊ","ʈ"=>"Ʈ","ʃ"=>"Ʃ","ʀ"=>"Ʀ","ɵ"=>"Ɵ","ɲ"=>"Ɲ","ɯ"=>"Ɯ","ɩ"=>"Ɩ","ɨ"=>"Ɨ", 905 "ɣ"=>"Ɣ","ɛ"=>"Ɛ","ə"=>"Ə","ɗ"=>"Ɗ","ɖ"=>"Ɖ","ɔ"=>"Ɔ","ɓ"=>"Ɓ","ȳ"=>"Ȳ","ȱ"=>"Ȱ","ȯ"=>"Ȯ", 906 "ȭ"=>"Ȭ","ȫ"=>"Ȫ","ȩ"=>"Ȩ","ȧ"=>"Ȧ","ȥ"=>"Ȥ","ȣ"=>"Ȣ","ȟ"=>"Ȟ","ȝ"=>"Ȝ","ț"=>"Ț","ș"=>"Ș", 907 "ȗ"=>"Ȗ","ȕ"=>"Ȕ","ȓ"=>"Ȓ","ȑ"=>"Ȑ","ȏ"=>"Ȏ","ȍ"=>"Ȍ","ȋ"=>"Ȋ","ȉ"=>"Ȉ","ȇ"=>"Ȇ","ȅ"=>"Ȅ", 908 "ȃ"=>"Ȃ","ȁ"=>"Ȁ","ǿ"=>"Ǿ","ǽ"=>"Ǽ","ǻ"=>"Ǻ","ǹ"=>"Ǹ","ǵ"=>"Ǵ","dz"=>"Dz","ǯ"=>"Ǯ","ǭ"=>"Ǭ", 909 "ǫ"=>"Ǫ","ǩ"=>"Ǩ","ǧ"=>"Ǧ","ǥ"=>"Ǥ","ǣ"=>"Ǣ","ǡ"=>"Ǡ","ǟ"=>"Ǟ","ǝ"=>"Ǝ","ǜ"=>"Ǜ","ǚ"=>"Ǚ", 910 "ǘ"=>"Ǘ","ǖ"=>"Ǖ","ǔ"=>"Ǔ","ǒ"=>"Ǒ","ǐ"=>"Ǐ","ǎ"=>"Ǎ","nj"=>"Nj","lj"=>"Lj","dž"=>"Dž","ƿ"=>"Ƿ", 911 "ƽ"=>"Ƽ","ƹ"=>"Ƹ","ƶ"=>"Ƶ","ƴ"=>"Ƴ","ư"=>"Ư","ƭ"=>"Ƭ","ƨ"=>"Ƨ","ƥ"=>"Ƥ","ƣ"=>"Ƣ","ơ"=>"Ơ", 912 "ƞ"=>"Ƞ","ƙ"=>"Ƙ","ƕ"=>"Ƕ","ƒ"=>"Ƒ","ƌ"=>"Ƌ","ƈ"=>"Ƈ","ƅ"=>"Ƅ","ƃ"=>"Ƃ","ſ"=>"S","ž"=>"Ž", 913 "ż"=>"Ż","ź"=>"Ź","ŷ"=>"Ŷ","ŵ"=>"Ŵ","ų"=>"Ų","ű"=>"Ű","ů"=>"Ů","ŭ"=>"Ŭ","ū"=>"Ū","ũ"=>"Ũ", 914 "ŧ"=>"Ŧ","ť"=>"Ť","ţ"=>"Ţ","š"=>"Š","ş"=>"Ş","ŝ"=>"Ŝ","ś"=>"Ś","ř"=>"Ř","ŗ"=>"Ŗ","ŕ"=>"Ŕ", 915 "œ"=>"Œ","ő"=>"Ő","ŏ"=>"Ŏ","ō"=>"Ō","ŋ"=>"Ŋ","ň"=>"Ň","ņ"=>"Ņ","ń"=>"Ń","ł"=>"Ł","ŀ"=>"Ŀ", 916 "ľ"=>"Ľ","ļ"=>"Ļ","ĺ"=>"Ĺ","ķ"=>"Ķ","ĵ"=>"Ĵ","ij"=>"IJ","ı"=>"I","į"=>"Į","ĭ"=>"Ĭ","ī"=>"Ī", 917 "ĩ"=>"Ĩ","ħ"=>"Ħ","ĥ"=>"Ĥ","ģ"=>"Ģ","ġ"=>"Ġ","ğ"=>"Ğ","ĝ"=>"Ĝ","ě"=>"Ě","ę"=>"Ę","ė"=>"Ė", 918 "ĕ"=>"Ĕ","ē"=>"Ē","đ"=>"Đ","ď"=>"Ď","č"=>"Č","ċ"=>"Ċ","ĉ"=>"Ĉ","ć"=>"Ć","ą"=>"Ą","ă"=>"Ă", 919 "ā"=>"Ā","ÿ"=>"Ÿ","þ"=>"Þ","ý"=>"Ý","ü"=>"Ü","û"=>"Û","ú"=>"Ú","ù"=>"Ù","ø"=>"Ø","ö"=>"Ö", 920 "õ"=>"Õ","ô"=>"Ô","ó"=>"Ó","ò"=>"Ò","ñ"=>"Ñ","ð"=>"Ð","ï"=>"Ï","î"=>"Î","í"=>"Í","ì"=>"Ì", 921 "ë"=>"Ë","ê"=>"Ê","é"=>"É","è"=>"È","ç"=>"Ç","æ"=>"Æ","å"=>"Å","ä"=>"Ä","ã"=>"Ã","â"=>"Â", 922 "á"=>"Á","à"=>"À","µ"=>"Μ","z"=>"Z","y"=>"Y","x"=>"X","w"=>"W","v"=>"V","u"=>"U","t"=>"T", 923 "s"=>"S","r"=>"R","q"=>"Q","p"=>"P","o"=>"O","n"=>"N","m"=>"M","l"=>"L","k"=>"K","j"=>"J", 924 "i"=>"I","h"=>"H","g"=>"G","f"=>"F","e"=>"E","d"=>"D","c"=>"C","b"=>"B","a"=>"A" 925 ); 926 927 /** 928 * UTF-8 Case lookup table 929 * 930 * This lookuptable defines the lower case letters to their correspponding 931 * upper case letter in UTF-8 932 * 933 * @author Andreas Gohr <andi@splitbrain.org> 934 */ 935 global $UTF8_UPPER_TO_LOWER; 936 $UTF8_UPPER_TO_LOWER = array ( 937 "Ｚ"=>"ｚ","Ｙ"=>"ｙ","Ｘ"=>"ｘ","Ｗ"=>"ｗ","Ｖ"=>"ｖ","Ｕ"=>"ｕ","Ｔ"=>"ｔ","Ｓ"=>"ｓ","Ｒ"=>"ｒ","Ｑ"=>"ｑ", 938 "Ｐ"=>"ｐ","Ｏ"=>"ｏ","Ｎ"=>"ｎ","Ｍ"=>"ｍ","Ｌ"=>"ｌ","Ｋ"=>"ｋ","Ｊ"=>"ｊ","Ｉ"=>"ｉ","Ｈ"=>"ｈ","Ｇ"=>"ｇ", 939 "Ｆ"=>"ｆ","Ｅ"=>"ｅ","Ｄ"=>"ｄ","Ｃ"=>"ｃ","Ｂ"=>"ｂ","Ａ"=>"ａ","ῼ"=>"ῳ","Ῥ"=>"ῥ","Ῡ"=>"ῡ","Ῑ"=>"ῑ", 940 "Ῐ"=>"ῐ","ῌ"=>"ῃ","Ι"=>"ι","ᾼ"=>"ᾳ","Ᾱ"=>"ᾱ","Ᾰ"=>"ᾰ","ᾯ"=>"ᾧ","ᾮ"=>"ᾦ","ᾭ"=>"ᾥ","ᾬ"=>"ᾤ", 941 "ᾫ"=>"ᾣ","ᾪ"=>"ᾢ","ᾩ"=>"ᾡ","ᾟ"=>"ᾗ","ᾞ"=>"ᾖ","ᾝ"=>"ᾕ","ᾜ"=>"ᾔ","ᾛ"=>"ᾓ","ᾚ"=>"ᾒ","ᾙ"=>"ᾑ", 942 "ᾘ"=>"ᾐ","ᾏ"=>"ᾇ","ᾎ"=>"ᾆ","ᾍ"=>"ᾅ","ᾌ"=>"ᾄ","ᾋ"=>"ᾃ","ᾊ"=>"ᾂ","ᾉ"=>"ᾁ","ᾈ"=>"ᾀ","Ώ"=>"ώ", 943 "Ὼ"=>"ὼ","Ύ"=>"ύ","Ὺ"=>"ὺ","Ό"=>"ό","Ὸ"=>"ὸ","Ί"=>"ί","Ὶ"=>"ὶ","Ή"=>"ή","Ὴ"=>"ὴ","Έ"=>"έ", 944 "Ὲ"=>"ὲ","Ά"=>"ά","Ὰ"=>"ὰ","Ὧ"=>"ὧ","Ὦ"=>"ὦ","Ὥ"=>"ὥ","Ὤ"=>"ὤ","Ὣ"=>"ὣ","Ὢ"=>"ὢ","Ὡ"=>"ὡ", 945 "Ὗ"=>"ὗ","Ὕ"=>"ὕ","Ὓ"=>"ὓ","Ὑ"=>"ὑ","Ὅ"=>"ὅ","Ὄ"=>"ὄ","Ὃ"=>"ὃ","Ὂ"=>"ὂ","Ὁ"=>"ὁ","Ὀ"=>"ὀ", 946 "Ἷ"=>"ἷ","Ἶ"=>"ἶ","Ἵ"=>"ἵ","Ἴ"=>"ἴ","Ἳ"=>"ἳ","Ἲ"=>"ἲ","Ἱ"=>"ἱ","Ἰ"=>"ἰ","Ἧ"=>"ἧ","Ἦ"=>"ἦ", 947 "Ἥ"=>"ἥ","Ἤ"=>"ἤ","Ἣ"=>"ἣ","Ἢ"=>"ἢ","Ἡ"=>"ἡ","Ἕ"=>"ἕ","Ἔ"=>"ἔ","Ἓ"=>"ἓ","Ἒ"=>"ἒ","Ἑ"=>"ἑ", 948 "Ἐ"=>"ἐ","Ἇ"=>"ἇ","Ἆ"=>"ἆ","Ἅ"=>"ἅ","Ἄ"=>"ἄ","Ἃ"=>"ἃ","Ἂ"=>"ἂ","Ἁ"=>"ἁ","Ἀ"=>"ἀ","Ỹ"=>"ỹ", 949 "Ỷ"=>"ỷ","Ỵ"=>"ỵ","Ỳ"=>"ỳ","Ự"=>"ự","Ữ"=>"ữ","Ử"=>"ử","Ừ"=>"ừ","Ứ"=>"ứ","Ủ"=>"ủ","Ụ"=>"ụ", 950 "Ợ"=>"ợ","Ỡ"=>"ỡ","Ở"=>"ở","Ờ"=>"ờ","Ớ"=>"ớ","Ộ"=>"ộ","Ỗ"=>"ỗ","Ổ"=>"ổ","Ồ"=>"ồ","Ố"=>"ố", 951 "Ỏ"=>"ỏ","Ọ"=>"ọ","Ị"=>"ị","Ỉ"=>"ỉ","Ệ"=>"ệ","Ễ"=>"ễ","Ể"=>"ể","Ề"=>"ề","Ế"=>"ế","Ẽ"=>"ẽ", 952 "Ẻ"=>"ẻ","Ẹ"=>"ẹ","Ặ"=>"ặ","Ẵ"=>"ẵ","Ẳ"=>"ẳ","Ằ"=>"ằ","Ắ"=>"ắ","Ậ"=>"ậ","Ẫ"=>"ẫ","Ẩ"=>"ẩ", 953 "Ầ"=>"ầ","Ấ"=>"ấ","Ả"=>"ả","Ạ"=>"ạ","Ṡ"=>"ẛ","Ẕ"=>"ẕ","Ẓ"=>"ẓ","Ẑ"=>"ẑ","Ẏ"=>"ẏ","Ẍ"=>"ẍ", 954 "Ẋ"=>"ẋ","Ẉ"=>"ẉ","Ẇ"=>"ẇ","Ẅ"=>"ẅ","Ẃ"=>"ẃ","Ẁ"=>"ẁ","Ṿ"=>"ṿ","Ṽ"=>"ṽ","Ṻ"=>"ṻ","Ṹ"=>"ṹ", 955 "Ṷ"=>"ṷ","Ṵ"=>"ṵ","Ṳ"=>"ṳ","Ṱ"=>"ṱ","Ṯ"=>"ṯ","Ṭ"=>"ṭ","Ṫ"=>"ṫ","Ṩ"=>"ṩ","Ṧ"=>"ṧ","Ṥ"=>"ṥ", 956 "Ṣ"=>"ṣ","Ṡ"=>"ṡ","Ṟ"=>"ṟ","Ṝ"=>"ṝ","Ṛ"=>"ṛ","Ṙ"=>"ṙ","Ṗ"=>"ṗ","Ṕ"=>"ṕ","Ṓ"=>"ṓ","Ṑ"=>"ṑ", 957 "Ṏ"=>"ṏ","Ṍ"=>"ṍ","Ṋ"=>"ṋ","Ṉ"=>"ṉ","Ṇ"=>"ṇ","Ṅ"=>"ṅ","Ṃ"=>"ṃ","Ṁ"=>"ṁ","Ḿ"=>"ḿ","Ḽ"=>"ḽ", 958 "Ḻ"=>"ḻ","Ḹ"=>"ḹ","Ḷ"=>"ḷ","Ḵ"=>"ḵ","Ḳ"=>"ḳ","Ḱ"=>"ḱ","Ḯ"=>"ḯ","Ḭ"=>"ḭ","Ḫ"=>"ḫ","Ḩ"=>"ḩ", 959 "Ḧ"=>"ḧ","Ḥ"=>"ḥ","Ḣ"=>"ḣ","Ḡ"=>"ḡ","Ḟ"=>"ḟ","Ḝ"=>"ḝ","Ḛ"=>"ḛ","Ḙ"=>"ḙ","Ḗ"=>"ḗ","Ḕ"=>"ḕ", 960 "Ḓ"=>"ḓ","Ḑ"=>"ḑ","Ḏ"=>"ḏ","Ḍ"=>"ḍ","Ḋ"=>"ḋ","Ḉ"=>"ḉ","Ḇ"=>"ḇ","Ḅ"=>"ḅ","Ḃ"=>"ḃ","Ḁ"=>"ḁ", 961 "Ֆ"=>"ֆ","Օ"=>"օ","Ք"=>"ք","Փ"=>"փ","Ւ"=>"ւ","Ց"=>"ց","Ր"=>"ր","Տ"=>"տ","Վ"=>"վ","Ս"=>"ս", 962 "Ռ"=>"ռ","Ջ"=>"ջ","Պ"=>"պ","Չ"=>"չ","Ո"=>"ո","Շ"=>"շ","Ն"=>"ն","Յ"=>"յ","Մ"=>"մ","Ճ"=>"ճ", 963 "Ղ"=>"ղ","Ձ"=>"ձ","Հ"=>"հ","Կ"=>"կ","Ծ"=>"ծ","Խ"=>"խ","Լ"=>"լ","Ի"=>"ի","Ժ"=>"ժ","Թ"=>"թ", 964 "Ը"=>"ը","Է"=>"է","Զ"=>"զ","Ե"=>"ե","Դ"=>"դ","Գ"=>"գ","Բ"=>"բ","Ա"=>"ա","Ԏ"=>"ԏ","Ԍ"=>"ԍ", 965 "Ԋ"=>"ԋ","Ԉ"=>"ԉ","Ԇ"=>"ԇ","Ԅ"=>"ԅ","Ԃ"=>"ԃ","Ԁ"=>"ԁ","Ӹ"=>"ӹ","Ӵ"=>"ӵ","Ӳ"=>"ӳ","Ӱ"=>"ӱ", 966 "Ӯ"=>"ӯ","Ӭ"=>"ӭ","Ӫ"=>"ӫ","Ө"=>"ө","Ӧ"=>"ӧ","Ӥ"=>"ӥ","Ӣ"=>"ӣ","Ӡ"=>"ӡ","Ӟ"=>"ӟ","Ӝ"=>"ӝ", 967 "Ӛ"=>"ӛ","Ә"=>"ә","Ӗ"=>"ӗ","Ӕ"=>"ӕ","Ӓ"=>"ӓ","Ӑ"=>"ӑ","Ӎ"=>"ӎ","Ӌ"=>"ӌ","Ӊ"=>"ӊ","Ӈ"=>"ӈ", 968 "Ӆ"=>"ӆ","Ӄ"=>"ӄ","Ӂ"=>"ӂ","Ҿ"=>"ҿ","Ҽ"=>"ҽ","Һ"=>"һ","Ҹ"=>"ҹ","Ҷ"=>"ҷ","Ҵ"=>"ҵ","Ҳ"=>"ҳ", 969 "Ұ"=>"ұ","Ү"=>"ү","Ҭ"=>"ҭ","Ҫ"=>"ҫ","Ҩ"=>"ҩ","Ҧ"=>"ҧ","Ҥ"=>"ҥ","Ң"=>"ң","Ҡ"=>"ҡ","Ҟ"=>"ҟ", 970 "Ҝ"=>"ҝ","Қ"=>"қ","Ҙ"=>"ҙ","Җ"=>"җ","Ҕ"=>"ҕ","Ғ"=>"ғ","Ґ"=>"ґ","Ҏ"=>"ҏ","Ҍ"=>"ҍ","Ҋ"=>"ҋ", 971 "Ҁ"=>"ҁ","Ѿ"=>"ѿ","Ѽ"=>"ѽ","Ѻ"=>"ѻ","Ѹ"=>"ѹ","Ѷ"=>"ѷ","Ѵ"=>"ѵ","Ѳ"=>"ѳ","Ѱ"=>"ѱ","Ѯ"=>"ѯ", 972 "Ѭ"=>"ѭ","Ѫ"=>"ѫ","Ѩ"=>"ѩ","Ѧ"=>"ѧ","Ѥ"=>"ѥ","Ѣ"=>"ѣ","Ѡ"=>"ѡ","Џ"=>"џ","Ў"=>"ў","Ѝ"=>"ѝ", 973 "Ќ"=>"ќ","Ћ"=>"ћ","Њ"=>"њ","Љ"=>"љ","Ј"=>"ј","Ї"=>"ї","І"=>"і","Ѕ"=>"ѕ","Є"=>"є","Ѓ"=>"ѓ", 974 "Ђ"=>"ђ","Ё"=>"ё","Ѐ"=>"ѐ","Я"=>"я","Ю"=>"ю","Э"=>"э","Ь"=>"ь","Ы"=>"ы","Ъ"=>"ъ","Щ"=>"щ", 975 "Ш"=>"ш","Ч"=>"ч","Ц"=>"ц","Х"=>"х","Ф"=>"ф","У"=>"у","Т"=>"т","С"=>"с","Р"=>"р","П"=>"п", 976 "О"=>"о","Н"=>"н","М"=>"м","Л"=>"л","К"=>"к","Й"=>"й","И"=>"и","З"=>"з","Ж"=>"ж","Е"=>"е", 977 "Д"=>"д","Г"=>"г","В"=>"в","Б"=>"б","А"=>"а","Ε"=>"ϵ","Σ"=>"ϲ","Ρ"=>"ϱ","Κ"=>"ϰ","Ϯ"=>"ϯ", 978 "Ϭ"=>"ϭ","Ϫ"=>"ϫ","Ϩ"=>"ϩ","Ϧ"=>"ϧ","Ϥ"=>"ϥ","Ϣ"=>"ϣ","Ϡ"=>"ϡ","Ϟ"=>"ϟ","Ϝ"=>"ϝ","Ϛ"=>"ϛ", 979 "Ϙ"=>"ϙ","Π"=>"ϖ","Φ"=>"ϕ","Θ"=>"ϑ","Β"=>"ϐ","Ώ"=>"ώ","Ύ"=>"ύ","Ό"=>"ό","Ϋ"=>"ϋ","Ϊ"=>"ϊ", 980 "Ω"=>"ω","Ψ"=>"ψ","Χ"=>"χ","Φ"=>"φ","Υ"=>"υ","Τ"=>"τ","Σ"=>"σ","Σ"=>"ς","Ρ"=>"ρ","Π"=>"π", 981 "Ο"=>"ο","Ξ"=>"ξ","Ν"=>"ν","Μ"=>"μ","Λ"=>"λ","Κ"=>"κ","Ι"=>"ι","Θ"=>"θ","Η"=>"η","Ζ"=>"ζ", 982 "Ε"=>"ε","Δ"=>"δ","Γ"=>"γ","Β"=>"β","Α"=>"α","Ί"=>"ί","Ή"=>"ή","Έ"=>"έ","Ά"=>"ά","Ʒ"=>"ʒ", 983 "Ʋ"=>"ʋ","Ʊ"=>"ʊ","Ʈ"=>"ʈ","Ʃ"=>"ʃ","Ʀ"=>"ʀ","Ɵ"=>"ɵ","Ɲ"=>"ɲ","Ɯ"=>"ɯ","Ɩ"=>"ɩ","Ɨ"=>"ɨ", 984 "Ɣ"=>"ɣ","Ɛ"=>"ɛ","Ə"=>"ə","Ɗ"=>"ɗ","Ɖ"=>"ɖ","Ɔ"=>"ɔ","Ɓ"=>"ɓ","Ȳ"=>"ȳ","Ȱ"=>"ȱ","Ȯ"=>"ȯ", 985 "Ȭ"=>"ȭ","Ȫ"=>"ȫ","Ȩ"=>"ȩ","Ȧ"=>"ȧ","Ȥ"=>"ȥ","Ȣ"=>"ȣ","Ȟ"=>"ȟ","Ȝ"=>"ȝ","Ț"=>"ț","Ș"=>"ș", 986 "Ȗ"=>"ȗ","Ȕ"=>"ȕ","Ȓ"=>"ȓ","Ȑ"=>"ȑ","Ȏ"=>"ȏ","Ȍ"=>"ȍ","Ȋ"=>"ȋ","Ȉ"=>"ȉ","Ȇ"=>"ȇ","Ȅ"=>"ȅ", 987 "Ȃ"=>"ȃ","Ȁ"=>"ȁ","Ǿ"=>"ǿ","Ǽ"=>"ǽ","Ǻ"=>"ǻ","Ǹ"=>"ǹ","Ǵ"=>"ǵ","Dz"=>"dz","Ǯ"=>"ǯ","Ǭ"=>"ǭ", 988 "Ǫ"=>"ǫ","Ǩ"=>"ǩ","Ǧ"=>"ǧ","Ǥ"=>"ǥ","Ǣ"=>"ǣ","Ǡ"=>"ǡ","Ǟ"=>"ǟ","Ǝ"=>"ǝ","Ǜ"=>"ǜ","Ǚ"=>"ǚ", 989 "Ǘ"=>"ǘ","Ǖ"=>"ǖ","Ǔ"=>"ǔ","Ǒ"=>"ǒ","Ǐ"=>"ǐ","Ǎ"=>"ǎ","Nj"=>"nj","Lj"=>"lj","Dž"=>"dž","Ƿ"=>"ƿ", 990 "Ƽ"=>"ƽ","Ƹ"=>"ƹ","Ƶ"=>"ƶ","Ƴ"=>"ƴ","Ư"=>"ư","Ƭ"=>"ƭ","Ƨ"=>"ƨ","Ƥ"=>"ƥ","Ƣ"=>"ƣ","Ơ"=>"ơ", 991 "Ƞ"=>"ƞ","Ƙ"=>"ƙ","Ƕ"=>"ƕ","Ƒ"=>"ƒ","Ƌ"=>"ƌ","Ƈ"=>"ƈ","Ƅ"=>"ƅ","Ƃ"=>"ƃ","S"=>"ſ","Ž"=>"ž", 992 "Ż"=>"ż","Ź"=>"ź","Ŷ"=>"ŷ","Ŵ"=>"ŵ","Ų"=>"ų","Ű"=>"ű","Ů"=>"ů","Ŭ"=>"ŭ","Ū"=>"ū","Ũ"=>"ũ", 993 "Ŧ"=>"ŧ","Ť"=>"ť","Ţ"=>"ţ","Š"=>"š","Ş"=>"ş","Ŝ"=>"ŝ","Ś"=>"ś","Ř"=>"ř","Ŗ"=>"ŗ","Ŕ"=>"ŕ", 994 "Œ"=>"œ","Ő"=>"ő","Ŏ"=>"ŏ","Ō"=>"ō","Ŋ"=>"ŋ","Ň"=>"ň","Ņ"=>"ņ","Ń"=>"ń","Ł"=>"ł","Ŀ"=>"ŀ", 995 "Ľ"=>"ľ","Ļ"=>"ļ","Ĺ"=>"ĺ","Ķ"=>"ķ","Ĵ"=>"ĵ","IJ"=>"ij","I"=>"ı","Į"=>"į","Ĭ"=>"ĭ","Ī"=>"ī", 996 "Ĩ"=>"ĩ","Ħ"=>"ħ","Ĥ"=>"ĥ","Ģ"=>"ģ","Ġ"=>"ġ","Ğ"=>"ğ","Ĝ"=>"ĝ","Ě"=>"ě","Ę"=>"ę","Ė"=>"ė", 997 "Ĕ"=>"ĕ","Ē"=>"ē","Đ"=>"đ","Ď"=>"ď","Č"=>"č","Ċ"=>"ċ","Ĉ"=>"ĉ","Ć"=>"ć","Ą"=>"ą","Ă"=>"ă", 998 "Ā"=>"ā","Ÿ"=>"ÿ","Þ"=>"þ","Ý"=>"ý","Ü"=>"ü","Û"=>"û","Ú"=>"ú","Ù"=>"ù","Ø"=>"ø","Ö"=>"ö", 999 "Õ"=>"õ","Ô"=>"ô","Ó"=>"ó","Ò"=>"ò","Ñ"=>"ñ","Ð"=>"ð","Ï"=>"ï","Î"=>"î","Í"=>"í","Ì"=>"ì", 1000 "Ë"=>"ë","Ê"=>"ê","É"=>"é","È"=>"è","Ç"=>"ç","Æ"=>"æ","Å"=>"å","Ä"=>"ä","Ã"=>"ã","Â"=>"â", 1001 "Á"=>"á","À"=>"à","Μ"=>"µ","Z"=>"z","Y"=>"y","X"=>"x","W"=>"w","V"=>"v","U"=>"u","T"=>"t", 1002 "S"=>"s","R"=>"r","Q"=>"q","P"=>"p","O"=>"o","N"=>"n","M"=>"m","L"=>"l","K"=>"k","J"=>"j", 1003 "I"=>"i","H"=>"h","G"=>"g","F"=>"f","E"=>"e","D"=>"d","C"=>"c","B"=>"b","A"=>"a" 1004 ); 1005}; // end of case lookup tables 1006 1007/** 1008 * UTF-8 lookup table for lower case accented letters 1009 * 1010 * This lookuptable defines replacements for accented characters from the ASCII-7 1011 * range. This are lower case letters only. 1012 * 1013 * @author Andreas Gohr <andi@splitbrain.org> 1014 * @see utf8_deaccent() 1015 */ 1016global $UTF8_LOWER_ACCENTS; 1017$UTF8_LOWER_ACCENTS = array( 1018 'à' => 'a', 'ô' => 'o', 'ď' => 'd', 'ḟ' => 'f', 'ë' => 'e', 'š' => 's', 'ơ' => 'o', 1019 'ß' => 'ss', 'ă' => 'a', 'ř' => 'r', 'ț' => 't', 'ň' => 'n', 'ā' => 'a', 'ķ' => 'k', 1020 'ŝ' => 's', 'ỳ' => 'y', 'ņ' => 'n', 'ĺ' => 'l', 'ħ' => 'h', 'ṗ' => 'p', 'ó' => 'o', 1021 'ú' => 'u', 'ě' => 'e', 'é' => 'e', 'ç' => 'c', 'ẁ' => 'w', 'ċ' => 'c', 'õ' => 'o', 1022 'ṡ' => 's', 'ø' => 'o', 'ģ' => 'g', 'ŧ' => 't', 'ș' => 's', 'ė' => 'e', 'ĉ' => 'c', 1023 'ś' => 's', 'î' => 'i', 'ű' => 'u', 'ć' => 'c', 'ę' => 'e', 'ŵ' => 'w', 'ṫ' => 't', 1024 'ū' => 'u', 'č' => 'c', 'ö' => 'oe', 'è' => 'e', 'ŷ' => 'y', 'ą' => 'a', 'ł' => 'l', 1025 'ų' => 'u', 'ů' => 'u', 'ş' => 's', 'ğ' => 'g', 'ļ' => 'l', 'ƒ' => 'f', 'ž' => 'z', 1026 'ẃ' => 'w', 'ḃ' => 'b', 'å' => 'a', 'ì' => 'i', 'ï' => 'i', 'ḋ' => 'd', 'ť' => 't', 1027 'ŗ' => 'r', 'ä' => 'ae', 'í' => 'i', 'ŕ' => 'r', 'ê' => 'e', 'ü' => 'ue', 'ò' => 'o', 1028 'ē' => 'e', 'ñ' => 'n', 'ń' => 'n', 'ĥ' => 'h', 'ĝ' => 'g', 'đ' => 'd', 'ĵ' => 'j', 1029 'ÿ' => 'y', 'ũ' => 'u', 'ŭ' => 'u', 'ư' => 'u', 'ţ' => 't', 'ý' => 'y', 'ő' => 'o', 1030 'â' => 'a', 'ľ' => 'l', 'ẅ' => 'w', 'ż' => 'z', 'ī' => 'i', 'ã' => 'a', 'ġ' => 'g', 1031 'ṁ' => 'm', 'ō' => 'o', 'ĩ' => 'i', 'ù' => 'u', 'į' => 'i', 'ź' => 'z', 'á' => 'a', 1032 'û' => 'u', 'þ' => 'th', 'ð' => 'dh', 'æ' => 'ae', 'µ' => 'u', 'ĕ' => 'e', 1033); 1034 1035/** 1036 * UTF-8 lookup table for upper case accented letters 1037 * 1038 * This lookuptable defines replacements for accented characters from the ASCII-7 1039 * range. This are upper case letters only. 1040 * 1041 * @author Andreas Gohr <andi@splitbrain.org> 1042 * @see utf8_deaccent() 1043 */ 1044global $UTF8_UPPER_ACCENTS; 1045$UTF8_UPPER_ACCENTS = array( 1046 'À' => 'A', 'Ô' => 'O', 'Ď' => 'D', 'Ḟ' => 'F', 'Ë' => 'E', 'Š' => 'S', 'Ơ' => 'O', 1047 'Ă' => 'A', 'Ř' => 'R', 'Ț' => 'T', 'Ň' => 'N', 'Ā' => 'A', 'Ķ' => 'K', 1048 'Ŝ' => 'S', 'Ỳ' => 'Y', 'Ņ' => 'N', 'Ĺ' => 'L', 'Ħ' => 'H', 'Ṗ' => 'P', 'Ó' => 'O', 1049 'Ú' => 'U', 'Ě' => 'E', 'É' => 'E', 'Ç' => 'C', 'Ẁ' => 'W', 'Ċ' => 'C', 'Õ' => 'O', 1050 'Ṡ' => 'S', 'Ø' => 'O', 'Ģ' => 'G', 'Ŧ' => 'T', 'Ș' => 'S', 'Ė' => 'E', 'Ĉ' => 'C', 1051 'Ś' => 'S', 'Î' => 'I', 'Ű' => 'U', 'Ć' => 'C', 'Ę' => 'E', 'Ŵ' => 'W', 'Ṫ' => 'T', 1052 'Ū' => 'U', 'Č' => 'C', 'Ö' => 'Oe', 'È' => 'E', 'Ŷ' => 'Y', 'Ą' => 'A', 'Ł' => 'L', 1053 'Ų' => 'U', 'Ů' => 'U', 'Ş' => 'S', 'Ğ' => 'G', 'Ļ' => 'L', 'Ƒ' => 'F', 'Ž' => 'Z', 1054 'Ẃ' => 'W', 'Ḃ' => 'B', 'Å' => 'A', 'Ì' => 'I', 'Ï' => 'I', 'Ḋ' => 'D', 'Ť' => 'T', 1055 'Ŗ' => 'R', 'Ä' => 'Ae', 'Í' => 'I', 'Ŕ' => 'R', 'Ê' => 'E', 'Ü' => 'Ue', 'Ò' => 'O', 1056 'Ē' => 'E', 'Ñ' => 'N', 'Ń' => 'N', 'Ĥ' => 'H', 'Ĝ' => 'G', 'Đ' => 'D', 'Ĵ' => 'J', 1057 'Ÿ' => 'Y', 'Ũ' => 'U', 'Ŭ' => 'U', 'Ư' => 'U', 'Ţ' => 'T', 'Ý' => 'Y', 'Ő' => 'O', 1058 'Â' => 'A', 'Ľ' => 'L', 'Ẅ' => 'W', 'Ż' => 'Z', 'Ī' => 'I', 'Ã' => 'A', 'Ġ' => 'G', 1059 'Ṁ' => 'M', 'Ō' => 'O', 'Ĩ' => 'I', 'Ù' => 'U', 'Į' => 'I', 'Ź' => 'Z', 'Á' => 'A', 1060 'Û' => 'U', 'Þ' => 'Th', 'Ð' => 'Dh', 'Æ' => 'Ae', 'Ĕ' => 'E', 1061); 1062 1063/** 1064 * UTF-8 array of common special characters 1065 * 1066 * This array should contain all special characters (not a letter or digit) 1067 * defined in the various local charsets - it's not a complete list of non-alphanum 1068 * characters in UTF-8. It's not perfect but should match most cases of special 1069 * chars. 1070 * 1071 * The controlchars 0x00 to 0x19 are _not_ included in this array. The space 0x20 is! 1072 * These chars are _not_ in the array either: _ (0x5f), : 0x3a, . 0x2e, - 0x2d, * 0x2a 1073 * 1074 * @author Andreas Gohr <andi@splitbrain.org> 1075 * @see utf8_stripspecials() 1076 */ 1077global $UTF8_SPECIAL_CHARS; 1078$UTF8_SPECIAL_CHARS = array( 1079 0x001a, 0x001b, 0x001c, 0x001d, 0x001e, 0x001f, 0x0020, 0x0021, 0x0022, 0x0023, 1080 0x0024, 0x0025, 0x0026, 0x0027, 0x0028, 0x0029, 0x002b, 0x002c, 1081 0x002f, 0x003b, 0x003c, 0x003d, 0x003e, 0x003f, 0x0040, 0x005b, 1082 0x005c, 0x005d, 0x005e, 0x0060, 0x007b, 0x007c, 0x007d, 0x007e, 1083 0x007f, 0x0080, 0x0081, 0x0082, 0x0083, 0x0084, 0x0085, 0x0086, 0x0087, 0x0088, 1084 0x0089, 0x008a, 0x008b, 0x008c, 0x008d, 0x008e, 0x008f, 0x0090, 0x0091, 0x0092, 1085 0x0093, 0x0094, 0x0095, 0x0096, 0x0097, 0x0098, 0x0099, 0x009a, 0x009b, 0x009c, 1086 0x009d, 0x009e, 0x009f, 0x00a0, 0x00a1, 0x00a2, 0x00a3, 0x00a4, 0x00a5, 0x00a6, 1087 0x00a7, 0x00a8, 0x00a9, 0x00aa, 0x00ab, 0x00ac, 0x00ad, 0x00ae, 0x00af, 0x00b0, 1088 0x00b1, 0x00b2, 0x00b3, 0x00b4, 0x00b5, 0x00b6, 0x00b7, 0x00b8, 0x00b9, 0x00ba, 1089 0x00bb, 0x00bc, 0x00bd, 0x00be, 0x00bf, 0x00d7, 0x00f7, 0x02c7, 0x02d8, 0x02d9, 1090 0x02da, 0x02db, 0x02dc, 0x02dd, 0x0300, 0x0301, 0x0303, 0x0309, 0x0323, 0x0384, 1091 0x0385, 0x0387, 0x03b2, 0x03c6, 0x03d1, 0x03d2, 0x03d5, 0x03d6, 0x05b0, 0x05b1, 1092 0x05b2, 0x05b3, 0x05b4, 0x05b5, 0x05b6, 0x05b7, 0x05b8, 0x05b9, 0x05bb, 0x05bc, 1093 0x05bd, 0x05be, 0x05bf, 0x05c0, 0x05c1, 0x05c2, 0x05c3, 0x05f3, 0x05f4, 0x060c, 1094 0x061b, 0x061f, 0x0640, 0x064b, 0x064c, 0x064d, 0x064e, 0x064f, 0x0650, 0x0651, 1095 0x0652, 0x066a, 0x0e3f, 0x200c, 0x200d, 0x200e, 0x200f, 0x2013, 0x2014, 0x2015, 1096 0x2017, 0x2018, 0x2019, 0x201a, 0x201c, 0x201d, 0x201e, 0x2020, 0x2021, 0x2022, 1097 0x2026, 0x2030, 0x2032, 0x2033, 0x2039, 0x203a, 0x2044, 0x20a7, 0x20aa, 0x20ab, 1098 0x20ac, 0x2116, 0x2118, 0x2122, 0x2126, 0x2135, 0x2190, 0x2191, 0x2192, 0x2193, 1099 0x2194, 0x2195, 0x21b5, 0x21d0, 0x21d1, 0x21d2, 0x21d3, 0x21d4, 0x2200, 0x2202, 1100 0x2203, 0x2205, 0x2206, 0x2207, 0x2208, 0x2209, 0x220b, 0x220f, 0x2211, 0x2212, 1101 0x2215, 0x2217, 0x2219, 0x221a, 0x221d, 0x221e, 0x2220, 0x2227, 0x2228, 0x2229, 1102 0x222a, 0x222b, 0x2234, 0x223c, 0x2245, 0x2248, 0x2260, 0x2261, 0x2264, 0x2265, 1103 0x2282, 0x2283, 0x2284, 0x2286, 0x2287, 0x2295, 0x2297, 0x22a5, 0x22c5, 0x2310, 1104 0x2320, 0x2321, 0x2329, 0x232a, 0x2469, 0x2500, 0x2502, 0x250c, 0x2510, 0x2514, 1105 0x2518, 0x251c, 0x2524, 0x252c, 0x2534, 0x253c, 0x2550, 0x2551, 0x2552, 0x2553, 1106 0x2554, 0x2555, 0x2556, 0x2557, 0x2558, 0x2559, 0x255a, 0x255b, 0x255c, 0x255d, 1107 0x255e, 0x255f, 0x2560, 0x2561, 0x2562, 0x2563, 0x2564, 0x2565, 0x2566, 0x2567, 1108 0x2568, 0x2569, 0x256a, 0x256b, 0x256c, 0x2580, 0x2584, 0x2588, 0x258c, 0x2590, 1109 0x2591, 0x2592, 0x2593, 0x25a0, 0x25b2, 0x25bc, 0x25c6, 0x25ca, 0x25cf, 0x25d7, 1110 0x2605, 0x260e, 0x261b, 0x261e, 0x2660, 0x2663, 0x2665, 0x2666, 0x2701, 0x2702, 1111 0x2703, 0x2704, 0x2706, 0x2707, 0x2708, 0x2709, 0x270c, 0x270d, 0x270e, 0x270f, 1112 0x2710, 0x2711, 0x2712, 0x2713, 0x2714, 0x2715, 0x2716, 0x2717, 0x2718, 0x2719, 1113 0x271a, 0x271b, 0x271c, 0x271d, 0x271e, 0x271f, 0x2720, 0x2721, 0x2722, 0x2723, 1114 0x2724, 0x2725, 0x2726, 0x2727, 0x2729, 0x272a, 0x272b, 0x272c, 0x272d, 0x272e, 1115 0x272f, 0x2730, 0x2731, 0x2732, 0x2733, 0x2734, 0x2735, 0x2736, 0x2737, 0x2738, 1116 0x2739, 0x273a, 0x273b, 0x273c, 0x273d, 0x273e, 0x273f, 0x2740, 0x2741, 0x2742, 1117 0x2743, 0x2744, 0x2745, 0x2746, 0x2747, 0x2748, 0x2749, 0x274a, 0x274b, 0x274d, 1118 0x274f, 0x2750, 0x2751, 0x2752, 0x2756, 0x2758, 0x2759, 0x275a, 0x275b, 0x275c, 1119 0x275d, 0x275e, 0x2761, 0x2762, 0x2763, 0x2764, 0x2765, 0x2766, 0x2767, 0x277f, 1120 0x2789, 0x2793, 0x2794, 0x2798, 0x2799, 0x279a, 0x279b, 0x279c, 0x279d, 0x279e, 1121 0x279f, 0x27a0, 0x27a1, 0x27a2, 0x27a3, 0x27a4, 0x27a5, 0x27a6, 0x27a7, 0x27a8, 1122 0x27a9, 0x27aa, 0x27ab, 0x27ac, 0x27ad, 0x27ae, 0x27af, 0x27b1, 0x27b2, 0x27b3, 1123 0x27b4, 0x27b5, 0x27b6, 0x27b7, 0x27b8, 0x27b9, 0x27ba, 0x27bb, 0x27bc, 0x27bd, 1124 0x27be, 0x3000, 0x3001, 0x3002, 0x3003, 0x3008, 0x3009, 0x300a, 0x300b, 0x300c, 1125 0x300d, 0x300e, 0x300f, 0x3010, 0x3011, 0x3012, 0x3014, 0x3015, 0x3016, 0x3017, 1126 0x3018, 0x3019, 0x301a, 0x301b, 0x3036, 1127 0xf6d9, 0xf6da, 0xf6db, 0xf8d7, 0xf8d8, 0xf8d9, 0xf8da, 0xf8db, 0xf8dc, 1128 0xf8dd, 0xf8de, 0xf8df, 0xf8e0, 0xf8e1, 0xf8e2, 0xf8e3, 0xf8e4, 0xf8e5, 0xf8e6, 1129 0xf8e7, 0xf8e8, 0xf8e9, 0xf8ea, 0xf8eb, 0xf8ec, 0xf8ed, 0xf8ee, 0xf8ef, 0xf8f0, 1130 0xf8f1, 0xf8f2, 0xf8f3, 0xf8f4, 0xf8f5, 0xf8f6, 0xf8f7, 0xf8f8, 0xf8f9, 0xf8fa, 1131 0xf8fb, 0xf8fc, 0xf8fd, 0xf8fe, 0xfe7c, 0xfe7d, 1132 0xff01, 0xff02, 0xff03, 0xff04, 0xff05, 0xff06, 0xff07, 0xff08, 0xff09, 1133 0xff09, 0xff0a, 0xff0b, 0xff0c, 0xff0d, 0xff0e, 0xff0f, 0xff1a, 0xff1b, 0xff1c, 1134 0xff1d, 0xff1e, 0xff1f, 0xff20, 0xff3b, 0xff3c, 0xff3d, 0xff3e, 0xff40, 0xff5b, 1135 0xff5c, 0xff5d, 0xff5e, 0xff5f, 0xff60, 0xff61, 0xff62, 0xff63, 0xff64, 0xff65, 1136 0xffe0, 0xffe1, 0xffe2, 0xffe3, 0xffe4, 0xffe5, 0xffe6, 0xffe8, 0xffe9, 0xffea, 1137 0xffeb, 0xffec, 0xffed, 0xffee, 1138); 1139 1140// utf8 version of above data 1141global $UTF8_SPECIAL_CHARS2; 1142$UTF8_SPECIAL_CHARS2 = 1143 "\x1A".' !"#$%&\'()+,/;<=>?@[\]^`{|}~€‚ƒ„…†‡ˆ‰Š‹ŒŽ‘’“”•�'. 1144 '�—˜™š›œžŸ ¡¢£¤¥¦§¨©ª«¬®¯°±²³´µ¶·¸¹º»¼½�'. 1145 '�¿×÷ˇ˘˙˚˛˜˝̣̀́̃̉΄΅·βφϑϒϕϖְֱֲֳִֵֶַָֹֻּֽ־ֿ�'. 1146 '�ׁׂ׃׳״،؛؟ـًٌٍَُِّْ٪฿–—―‗‘’‚“”�'. 1147 '��†‡•…‰′″‹›⁄₧₪₫€№℘™Ωℵ←↑→↓↔↕↵'. 1148 '⇐⇑⇒⇓⇔∀∂∃∅∆∇∈∉∋∏∑−∕∗∙√∝∞∠∧∨�'. 1149 '�∪∫∴∼≅≈≠≡≤≥⊂⊃⊄⊆⊇⊕⊗⊥⋅⌐⌠⌡〈〉⑩─�'. 1150 '��┌┐└┘├┤┬┴┼═║╒╓╔╕╖╗╘╙╚╛╜╝╞╟╠'. 1151 '╡╢╣╤╥╦╧╨╩╪╫╬▀▄█▌▐░▒▓■▲▼◆◊●�'. 1152 '�★☎☛☞♠♣♥♦✁✂✃✄✆✇✈✉✌✍✎✏✐✑✒✓✔✕�'. 1153 '��✗✘✙✚✛✜✝✞✟✠✡✢✣✤✥✦✧✩✪✫✬✭✮✯✰✱'. 1154 '✲✳✴✵✶✷✸✹✺✻✼✽✾✿❀❁❂❃❄❅❆❇❈❉❊❋�'. 1155 '�❏❐❑❒❖❘❙❚❛❜❝❞❡❢❣❤❥❦❧❿➉➓➔➘➙➚�'. 1156 '��➜➝➞➟➠➡➢➣➤➥➦➧➨➩➪➫➬➭➮➯➱➲➳➴➵➶'. 1157 '➷➸➹➺➻➼➽➾'. 1158 ' 、。〃〈〉《》「」『』【】〒〔〕〖〗〘〙〚〛〶'. 1159 '�'. 1160 '�ﹼﹽ'. 1161 '！＂＃＄％＆＇（）＊＋，－．／：；＜＝＞？＠［＼］＾｀｛｜｝～'. 1162 '｟｠｡｢｣､･￠￡￢￣￤￥￦￨￩￪￫￬￭￮'; 1163 1164/** 1165 * Romanization lookup table 1166 * 1167 * This lookup tables provides a way to transform strings written in a language 1168 * different from the ones based upon latin letters into plain ASCII. 1169 * 1170 * Please note: this is not a scientific transliteration table. It only works 1171 * oneway from nonlatin to ASCII and it works by simple character replacement 1172 * only. Specialities of each language are not supported. 1173 * 1174 * @author Andreas Gohr <andi@splitbrain.org> 1175 * @author Vitaly Blokhin <vitinfo@vitn.com> 1176 * @link http://www.uconv.com/translit.htm 1177 * @author Bisqwit <bisqwit@iki.fi> 1178 * @link http://kanjidict.stc.cx/hiragana.php?src=2 1179 * @link http://www.translatum.gr/converter/greek-transliteration.htm 1180 * @link http://en.wikipedia.org/wiki/Royal_Thai_General_System_of_Transcription 1181 * @link http://www.btranslations.com/resources/romanization/korean.asp 1182 * @author Arthit Suriyawongkul <arthit@gmail.com> 1183 * @author Denis Scheither <amorphis@uni-bremen.de> 1184 */ 1185global $UTF8_ROMANIZATION; 1186$UTF8_ROMANIZATION = array( 1187 //russian cyrillic 1188 'а'=>'a','А'=>'A','б'=>'b','Б'=>'B','в'=>'v','В'=>'V','г'=>'g','Г'=>'G', 1189 'д'=>'d','Д'=>'D','е'=>'e','Е'=>'E','ё'=>'jo','Ё'=>'Jo','ж'=>'zh','Ж'=>'Zh', 1190 'з'=>'z','З'=>'Z','и'=>'i','И'=>'I','й'=>'j','Й'=>'J','к'=>'k','К'=>'K', 1191 'л'=>'l','Л'=>'L','м'=>'m','М'=>'M','н'=>'n','Н'=>'N','о'=>'o','О'=>'O', 1192 'п'=>'p','П'=>'P','р'=>'r','Р'=>'R','с'=>'s','С'=>'S','т'=>'t','Т'=>'T', 1193 'у'=>'u','У'=>'U','ф'=>'f','Ф'=>'F','х'=>'x','Х'=>'X','ц'=>'c','Ц'=>'C', 1194 'ч'=>'ch','Ч'=>'Ch','ш'=>'sh','Ш'=>'Sh','щ'=>'sch','Щ'=>'Sch','ъ'=>'', 1195 'Ъ'=>'','ы'=>'y','Ы'=>'Y','ь'=>'','Ь'=>'','э'=>'eh','Э'=>'Eh','ю'=>'ju', 1196 'Ю'=>'Ju','я'=>'ja','Я'=>'Ja', 1197 // Ukrainian cyrillic 1198 'Ґ'=>'Gh','ґ'=>'gh','Є'=>'Je','є'=>'je','І'=>'I','і'=>'i','Ї'=>'Ji','ї'=>'ji', 1199 // Georgian 1200 'ა'=>'a','ბ'=>'b','გ'=>'g','დ'=>'d','ე'=>'e','ვ'=>'v','ზ'=>'z','თ'=>'th', 1201 'ი'=>'i','კ'=>'p','ლ'=>'l','მ'=>'m','ნ'=>'n','ო'=>'o','პ'=>'p','ჟ'=>'zh', 1202 'რ'=>'r','ს'=>'s','ტ'=>'t','უ'=>'u','ფ'=>'ph','ქ'=>'kh','ღ'=>'gh','ყ'=>'q', 1203 'შ'=>'sh','ჩ'=>'ch','ც'=>'c','ძ'=>'dh','წ'=>'w','ჭ'=>'j','ხ'=>'x','ჯ'=>'jh', 1204 'ჰ'=>'xh', 1205 //Sanskrit 1206 'अ'=>'a','आ'=>'ah','इ'=>'i','ई'=>'ih','उ'=>'u','ऊ'=>'uh','ऋ'=>'ry', 1207 'ॠ'=>'ryh','ऌ'=>'ly','ॡ'=>'lyh','ए'=>'e','ऐ'=>'ay','ओ'=>'o','औ'=>'aw', 1208 'अं'=>'amh','अः'=>'aq','क'=>'k','ख'=>'kh','ग'=>'g','घ'=>'gh','ङ'=>'nh', 1209 'च'=>'c','छ'=>'ch','ज'=>'j','झ'=>'jh','ञ'=>'ny','ट'=>'tq','ठ'=>'tqh', 1210 'ड'=>'dq','ढ'=>'dqh','ण'=>'nq','त'=>'t','थ'=>'th','द'=>'d','ध'=>'dh', 1211 'न'=>'n','प'=>'p','फ'=>'ph','ब'=>'b','भ'=>'bh','म'=>'m','य'=>'z','र'=>'r', 1212 'ल'=>'l','व'=>'v','श'=>'sh','ष'=>'sqh','स'=>'s','ह'=>'x', 1213 //Hebrew 1214 'א'=>'a', 'ב'=>'b','ג'=>'g','ד'=>'d','ה'=>'h','ו'=>'v','ז'=>'z','ח'=>'kh','ט'=>'th', 1215 'י'=>'y','ך'=>'h','כ'=>'k','ל'=>'l','ם'=>'m','מ'=>'m','ן'=>'n','נ'=>'n', 1216 'ס'=>'s','ע'=>'ah','ף'=>'f','פ'=>'p','ץ'=>'c','צ'=>'c','ק'=>'q','ר'=>'r', 1217 'ש'=>'sh','ת'=>'t', 1218 //Arabic 1219 'ا'=>'a','ب'=>'b','ت'=>'t','ث'=>'th','ج'=>'g','ح'=>'xh','خ'=>'x','د'=>'d', 1220 'ذ'=>'dh','ر'=>'r','ز'=>'z','س'=>'s','ش'=>'sh','ص'=>'s\'','ض'=>'d\'', 1221 'ط'=>'t\'','ظ'=>'z\'','ع'=>'y','غ'=>'gh','ف'=>'f','ق'=>'q','ك'=>'k', 1222 'ل'=>'l','م'=>'m','ن'=>'n','ه'=>'x\'','و'=>'u','ي'=>'i', 1223 1224 // Japanese characters (last update: 2008-05-09) 1225 1226 // Japanese hiragana 1227 1228 // 3 character syllables, っ doubles the consonant after 1229 'っちゃ'=>'ccha','っちぇ'=>'cche','っちょ'=>'ccho','っちゅ'=>'cchu', 1230 'っびゃ'=>'bbya','っびぇ'=>'bbye','っびぃ'=>'bbyi','っびょ'=>'bbyo','っびゅ'=>'bbyu', 1231 'っぴゃ'=>'ppya','っぴぇ'=>'ppye','っぴぃ'=>'ppyi','っぴょ'=>'ppyo','っぴゅ'=>'ppyu', 1232 'っちゃ'=>'ccha','っちぇ'=>'cche','っち'=>'cchi','っちょ'=>'ccho','っちゅ'=>'cchu', 1233 // 'っひゃ'=>'hya','っひぇ'=>'hye','っひぃ'=>'hyi','っひょ'=>'hyo','っひゅ'=>'hyu', 1234 'っきゃ'=>'kkya','っきぇ'=>'kkye','っきぃ'=>'kkyi','っきょ'=>'kkyo','っきゅ'=>'kkyu', 1235 'っぎゃ'=>'ggya','っぎぇ'=>'ggye','っぎぃ'=>'ggyi','っぎょ'=>'ggyo','っぎゅ'=>'ggyu', 1236 'っみゃ'=>'mmya','っみぇ'=>'mmye','っみぃ'=>'mmyi','っみょ'=>'mmyo','っみゅ'=>'mmyu', 1237 'っにゃ'=>'nnya','っにぇ'=>'nnye','っにぃ'=>'nnyi','っにょ'=>'nnyo','っにゅ'=>'nnyu', 1238 'っりゃ'=>'rrya','っりぇ'=>'rrye','っりぃ'=>'rryi','っりょ'=>'rryo','っりゅ'=>'rryu', 1239 'っしゃ'=>'ssha','っしぇ'=>'sshe','っし'=>'sshi','っしょ'=>'ssho','っしゅ'=>'sshu', 1240 1241 // seperate hiragana 'n' ('n' + 'i' != 'ni', normally we would write "kon'nichi wa" but the apostrophe would be converted to _ anyway) 1242 'んあ'=>'n_a','んえ'=>'n_e','んい'=>'n_i','んお'=>'n_o','んう'=>'n_u', 1243 'んや'=>'n_ya','んよ'=>'n_yo','んゆ'=>'n_yu', 1244 1245 // 2 character syllables - normal 1246 'ふぁ'=>'fa','ふぇ'=>'fe','ふぃ'=>'fi','ふぉ'=>'fo', 1247 'ちゃ'=>'cha','ちぇ'=>'che','ち'=>'chi','ちょ'=>'cho','ちゅ'=>'chu', 1248 'ひゃ'=>'hya','ひぇ'=>'hye','ひぃ'=>'hyi','ひょ'=>'hyo','ひゅ'=>'hyu', 1249 'びゃ'=>'bya','びぇ'=>'bye','びぃ'=>'byi','びょ'=>'byo','びゅ'=>'byu', 1250 'ぴゃ'=>'pya','ぴぇ'=>'pye','ぴぃ'=>'pyi','ぴょ'=>'pyo','ぴゅ'=>'pyu', 1251 'きゃ'=>'kya','きぇ'=>'kye','きぃ'=>'kyi','きょ'=>'kyo','きゅ'=>'kyu', 1252 'ぎゃ'=>'gya','ぎぇ'=>'gye','ぎぃ'=>'gyi','ぎょ'=>'gyo','ぎゅ'=>'gyu', 1253 'みゃ'=>'mya','みぇ'=>'mye','みぃ'=>'myi','みょ'=>'myo','みゅ'=>'myu', 1254 'にゃ'=>'nya','にぇ'=>'nye','にぃ'=>'nyi','にょ'=>'nyo','にゅ'=>'nyu', 1255 'りゃ'=>'rya','りぇ'=>'rye','りぃ'=>'ryi','りょ'=>'ryo','りゅ'=>'ryu', 1256 'しゃ'=>'sha','しぇ'=>'she','し'=>'shi','しょ'=>'sho','しゅ'=>'shu', 1257 'じゃ'=>'ja','じぇ'=>'je','じょ'=>'jo','じゅ'=>'ju', 1258 'うぇ'=>'we','うぃ'=>'wi', 1259 'いぇ'=>'ye', 1260 1261 // 2 character syllables, っ doubles the consonant after 1262 'っば'=>'bba','っべ'=>'bbe','っび'=>'bbi','っぼ'=>'bbo','っぶ'=>'bbu', 1263 'っぱ'=>'ppa','っぺ'=>'ppe','っぴ'=>'ppi','っぽ'=>'ppo','っぷ'=>'ppu', 1264 'った'=>'tta','って'=>'tte','っち'=>'cchi','っと'=>'tto','っつ'=>'ttsu', 1265 'っだ'=>'dda','っで'=>'dde','っぢ'=>'ddi','っど'=>'ddo','っづ'=>'ddu', 1266 'っが'=>'gga','っげ'=>'gge','っぎ'=>'ggi','っご'=>'ggo','っぐ'=>'ggu', 1267 'っか'=>'kka','っけ'=>'kke','っき'=>'kki','っこ'=>'kko','っく'=>'kku', 1268 'っま'=>'mma','っめ'=>'mme','っみ'=>'mmi','っも'=>'mmo','っむ'=>'mmu', 1269 'っな'=>'nna','っね'=>'nne','っに'=>'nni','っの'=>'nno','っぬ'=>'nnu', 1270 'っら'=>'rra','っれ'=>'rre','っり'=>'rri','っろ'=>'rro','っる'=>'rru', 1271 'っさ'=>'ssa','っせ'=>'sse','っし'=>'sshi','っそ'=>'sso','っす'=>'ssu', 1272 'っざ'=>'zza','っぜ'=>'zze','っじ'=>'jji','っぞ'=>'zzo','っず'=>'zzu', 1273 1274 // 1 character syllabels 1275 'あ'=>'a','え'=>'e','い'=>'i','お'=>'o','う'=>'u','ん'=>'n', 1276 'は'=>'ha','へ'=>'he','ひ'=>'hi','ほ'=>'ho','ふ'=>'fu', 1277 'ば'=>'ba','べ'=>'be','び'=>'bi','ぼ'=>'bo','ぶ'=>'bu', 1278 'ぱ'=>'pa','ぺ'=>'pe','ぴ'=>'pi','ぽ'=>'po','ぷ'=>'pu', 1279 'た'=>'ta','て'=>'te','ち'=>'chi','と'=>'to','つ'=>'tsu', 1280 'だ'=>'da','で'=>'de','ぢ'=>'di','ど'=>'do','づ'=>'du', 1281 'が'=>'ga','げ'=>'ge','ぎ'=>'gi','ご'=>'go','ぐ'=>'gu', 1282 'か'=>'ka','け'=>'ke','き'=>'ki','こ'=>'ko','く'=>'ku', 1283 'ま'=>'ma','め'=>'me','み'=>'mi','も'=>'mo','む'=>'mu', 1284 'な'=>'na','ね'=>'ne','に'=>'ni','の'=>'no','ぬ'=>'nu', 1285 'ら'=>'ra','れ'=>'re','り'=>'ri','ろ'=>'ro','る'=>'ru', 1286 'さ'=>'sa','せ'=>'se','し'=>'shi','そ'=>'so','す'=>'su', 1287 'わ'=>'wa','を'=>'wo', 1288 'ざ'=>'za','ぜ'=>'ze','じ'=>'ji','ぞ'=>'zo','ず'=>'zu', 1289 'や'=>'ya','よ'=>'yo','ゆ'=>'yu', 1290 // old characters 1291 'ゑ'=>'we','ゐ'=>'wi', 1292 1293 // convert what's left (probably only kicks in when something's missing above) 1294 // 'ぁ'=>'a','ぇ'=>'e','ぃ'=>'i','ぉ'=>'o','ぅ'=>'u', 1295 // 'ゃ'=>'ya','ょ'=>'yo','ゅ'=>'yu', 1296 1297 // never seen one of those (disabled for the moment) 1298 // 'ヴぁ'=>'va','ヴぇ'=>'ve','ヴぃ'=>'vi','ヴぉ'=>'vo','ヴ'=>'vu', 1299 // 'でゃ'=>'dha','でぇ'=>'dhe','でぃ'=>'dhi','でょ'=>'dho','でゅ'=>'dhu', 1300 // 'どぁ'=>'dwa','どぇ'=>'dwe','どぃ'=>'dwi','どぉ'=>'dwo','どぅ'=>'dwu', 1301 // 'ぢゃ'=>'dya','ぢぇ'=>'dye','ぢぃ'=>'dyi','ぢょ'=>'dyo','ぢゅ'=>'dyu', 1302 // 'ふぁ'=>'fwa','ふぇ'=>'fwe','ふぃ'=>'fwi','ふぉ'=>'fwo','ふぅ'=>'fwu', 1303 // 'ふゃ'=>'fya','ふぇ'=>'fye','ふぃ'=>'fyi','ふょ'=>'fyo','ふゅ'=>'fyu', 1304 // 'すぁ'=>'swa','すぇ'=>'swe','すぃ'=>'swi','すぉ'=>'swo','すぅ'=>'swu', 1305 // 'てゃ'=>'tha','てぇ'=>'the','てぃ'=>'thi','てょ'=>'tho','てゅ'=>'thu', 1306 // 'つゃ'=>'tsa','つぇ'=>'tse','つぃ'=>'tsi','つょ'=>'tso','つ'=>'tsu', 1307 // 'とぁ'=>'twa','とぇ'=>'twe','とぃ'=>'twi','とぉ'=>'two','とぅ'=>'twu', 1308 // 'ヴゃ'=>'vya','ヴぇ'=>'vye','ヴぃ'=>'vyi','ヴょ'=>'vyo','ヴゅ'=>'vyu', 1309 // 'うぁ'=>'wha','うぇ'=>'whe','うぃ'=>'whi','うぉ'=>'who','うぅ'=>'whu', 1310 // 'じゃ'=>'zha','じぇ'=>'zhe','じぃ'=>'zhi','じょ'=>'zho','じゅ'=>'zhu', 1311 // 'じゃ'=>'zya','じぇ'=>'zye','じぃ'=>'zyi','じょ'=>'zyo','じゅ'=>'zyu', 1312 1313 // 'spare' characters from other romanization systems 1314 // 'だ'=>'da','で'=>'de','ぢ'=>'di','ど'=>'do','づ'=>'du', 1315 // 'ら'=>'la','れ'=>'le','り'=>'li','ろ'=>'lo','る'=>'lu', 1316 // 'さ'=>'sa','せ'=>'se','し'=>'si','そ'=>'so','す'=>'su', 1317 // 'ちゃ'=>'cya','ちぇ'=>'cye','ちぃ'=>'cyi','ちょ'=>'cyo','ちゅ'=>'cyu', 1318 //'じゃ'=>'jya','じぇ'=>'jye','じぃ'=>'jyi','じょ'=>'jyo','じゅ'=>'jyu', 1319 //'りゃ'=>'lya','りぇ'=>'lye','りぃ'=>'lyi','りょ'=>'lyo','りゅ'=>'lyu', 1320 //'しゃ'=>'sya','しぇ'=>'sye','しぃ'=>'syi','しょ'=>'syo','しゅ'=>'syu', 1321 //'ちゃ'=>'tya','ちぇ'=>'tye','ちぃ'=>'tyi','ちょ'=>'tyo','ちゅ'=>'tyu', 1322 //'し'=>'ci',,い'=>'yi','ぢ'=>'dzi', 1323 //'っじゃ'=>'jja','っじぇ'=>'jje','っじ'=>'jji','っじょ'=>'jjo','っじゅ'=>'jju', 1324 1325 1326 // Japanese katakana 1327 1328 // 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) 1329 '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', 1330 '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', 1331 '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', 1332 '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', 1333 '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', 1334 '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', 1335 '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', 1336 'ッシャー'=>'sshaa','ッシェー'=>'sshee','ッシー'=>'sshii','ッショー'=>'sshoo','ッシュー'=>'sshuu', 1337 'ッチャー'=>'cchaa','ッチェー'=>'cchee','ッチー'=>'cchii','ッチョー'=>'cchoo','ッチュー'=>'cchuu', 1338 'ッティー'=>'ttii', 1339 'ッヂィー'=>'ddii', 1340 1341 // 3 character syllables - doubled vowels 1342 'ファー'=>'faa','フェー'=>'fee','フィー'=>'fii','フォー'=>'foo', 1343 'フャー'=>'fyaa','フェー'=>'fyee','フィー'=>'fyii','フョー'=>'fyoo','フュー'=>'fyuu', 1344 'ヒャー'=>'hyaa','ヒェー'=>'hyee','ヒィー'=>'hyii','ヒョー'=>'hyoo','ヒュー'=>'hyuu', 1345 'ビャー'=>'byaa','ビェー'=>'byee','ビィー'=>'byii','ビョー'=>'byoo','ビュー'=>'byuu', 1346 'ピャー'=>'pyaa','ピェー'=>'pyee','ピィー'=>'pyii','ピョー'=>'pyoo','ピュー'=>'pyuu', 1347 'キャー'=>'kyaa','キェー'=>'kyee','キィー'=>'kyii','キョー'=>'kyoo','キュー'=>'kyuu', 1348 'ギャー'=>'gyaa','ギェー'=>'gyee','ギィー'=>'gyii','ギョー'=>'gyoo','ギュー'=>'gyuu', 1349 'ミャー'=>'myaa','ミェー'=>'myee','ミィー'=>'myii','ミョー'=>'myoo','ミュー'=>'myuu', 1350 'ニャー'=>'nyaa','ニェー'=>'nyee','ニィー'=>'nyii','ニョー'=>'nyoo','ニュー'=>'nyuu', 1351 'リャー'=>'ryaa','リェー'=>'ryee','リィー'=>'ryii','リョー'=>'ryoo','リュー'=>'ryuu', 1352 'シャー'=>'shaa','シェー'=>'shee','シー'=>'shii','ショー'=>'shoo','シュー'=>'shuu', 1353 'ジャー'=>'jaa','ジェー'=>'jee','ジー'=>'jii','ジョー'=>'joo','ジュー'=>'juu', 1354 'スァー'=>'swaa','スェー'=>'swee','スィー'=>'swii','スォー'=>'swoo','スゥー'=>'swuu', 1355 'デァー'=>'daa','デェー'=>'dee','ディー'=>'dii','デォー'=>'doo','デゥー'=>'duu', 1356 'チャー'=>'chaa','チェー'=>'chee','チー'=>'chii','チョー'=>'choo','チュー'=>'chuu', 1357 'ヂャー'=>'dyaa','ヂェー'=>'dyee','ヂィー'=>'dyii','ヂョー'=>'dyoo','ヂュー'=>'dyuu', 1358 'ツャー'=>'tsaa','ツェー'=>'tsee','ツィー'=>'tsii','ツョー'=>'tsoo','ツー'=>'tsuu', 1359 'トァー'=>'twaa','トェー'=>'twee','トィー'=>'twii','トォー'=>'twoo','トゥー'=>'twuu', 1360 'ドァー'=>'dwaa','ドェー'=>'dwee','ドィー'=>'dwii','ドォー'=>'dwoo','ドゥー'=>'dwuu', 1361 'ウァー'=>'whaa','ウェー'=>'whee','ウィー'=>'whii','ウォー'=>'whoo','ウゥー'=>'whuu', 1362 'ヴャー'=>'vyaa','ヴェー'=>'vyee','ヴィー'=>'vyii','ヴョー'=>'vyoo','ヴュー'=>'vyuu', 1363 'ヴァー'=>'vaa','ヴェー'=>'vee','ヴィー'=>'vii','ヴォー'=>'voo','ヴー'=>'vuu', 1364 'ウェー'=>'wee','ウィー'=>'wii', 1365 'イェー'=>'yee', 1366 'ティー'=>'tii', 1367 'ヂィー'=>'dii', 1368 1369 // 3 character syllables - doubled consonants 1370 'ッビャ'=>'bbya','ッビェ'=>'bbye','ッビィ'=>'bbyi','ッビョ'=>'bbyo','ッビュ'=>'bbyu', 1371 'ッピャ'=>'ppya','ッピェ'=>'ppye','ッピィ'=>'ppyi','ッピョ'=>'ppyo','ッピュ'=>'ppyu', 1372 'ッキャ'=>'kkya','ッキェ'=>'kkye','ッキィ'=>'kkyi','ッキョ'=>'kkyo','ッキュ'=>'kkyu', 1373 'ッギャ'=>'ggya','ッギェ'=>'ggye','ッギィ'=>'ggyi','ッギョ'=>'ggyo','ッギュ'=>'ggyu', 1374 'ッミャ'=>'mmya','ッミェ'=>'mmye','ッミィ'=>'mmyi','ッミョ'=>'mmyo','ッミュ'=>'mmyu', 1375 'ッニャ'=>'nnya','ッニェ'=>'nnye','ッニィ'=>'nnyi','ッニョ'=>'nnyo','ッニュ'=>'nnyu', 1376 'ッリャ'=>'rrya','ッリェ'=>'rrye','ッリィ'=>'rryi','ッリョ'=>'rryo','ッリュ'=>'rryu', 1377 'ッシャ'=>'ssha','ッシェ'=>'sshe','ッシ'=>'sshi','ッショ'=>'ssho','ッシュ'=>'sshu', 1378 'ッチャ'=>'ccha','ッチェ'=>'cche','ッチ'=>'cchi','ッチョ'=>'ccho','ッチュ'=>'cchu', 1379 'ッティ'=>'tti', 1380 'ッヂィ'=>'ddi', 1381 1382 // 3 character syllables - doubled vowel and consonants 1383 'ッバー'=>'bbaa','ッベー'=>'bbee','ッビー'=>'bbii','ッボー'=>'bboo','ッブー'=>'bbuu', 1384 'ッパー'=>'ppaa','ッペー'=>'ppee','ッピー'=>'ppii','ッポー'=>'ppoo','ップー'=>'ppuu', 1385 'ッケー'=>'kkee','ッキー'=>'kkii','ッコー'=>'kkoo','ックー'=>'kkuu','ッカー'=>'kkaa', 1386 'ッガー'=>'ggaa','ッゲー'=>'ggee','ッギー'=>'ggii','ッゴー'=>'ggoo','ッグー'=>'gguu', 1387 'ッマー'=>'maa','ッメー'=>'mee','ッミー'=>'mii','ッモー'=>'moo','ッムー'=>'muu', 1388 'ッナー'=>'nnaa','ッネー'=>'nnee','ッニー'=>'nnii','ッノー'=>'nnoo','ッヌー'=>'nnuu', 1389 'ッラー'=>'rraa','ッレー'=>'rree','ッリー'=>'rrii','ッロー'=>'rroo','ッルー'=>'rruu', 1390 'ッサー'=>'ssaa','ッセー'=>'ssee','ッシー'=>'sshii','ッソー'=>'ssoo','ッスー'=>'ssuu', 1391 'ッザー'=>'zzaa','ッゼー'=>'zzee','ッジー'=>'jjii','ッゾー'=>'zzoo','ッズー'=>'zzuu', 1392 'ッター'=>'ttaa','ッテー'=>'ttee','ッチー'=>'chii','ットー'=>'ttoo','ッツー'=>'ttsuu', 1393 'ッダー'=>'ddaa','ッデー'=>'ddee','ッヂー'=>'ddii','ッドー'=>'ddoo','ッヅー'=>'dduu', 1394 1395 // 2 character syllables - normal 1396 'ファ'=>'fa','フェ'=>'fe','フィ'=>'fi','フォ'=>'fo','フゥ'=>'fu', 1397 // 'フャ'=>'fya','フェ'=>'fye','フィ'=>'fyi','フョ'=>'fyo','フュ'=>'fyu', 1398 'フャ'=>'fa','フェ'=>'fe','フィ'=>'fi','フョ'=>'fo','フュ'=>'fu', 1399 'ヒャ'=>'hya','ヒェ'=>'hye','ヒィ'=>'hyi','ヒョ'=>'hyo','ヒュ'=>'hyu', 1400 'ビャ'=>'bya','ビェ'=>'bye','ビィ'=>'byi','ビョ'=>'byo','ビュ'=>'byu', 1401 'ピャ'=>'pya','ピェ'=>'pye','ピィ'=>'pyi','ピョ'=>'pyo','ピュ'=>'pyu', 1402 'キャ'=>'kya','キェ'=>'kye','キィ'=>'kyi','キョ'=>'kyo','キュ'=>'kyu', 1403 'ギャ'=>'gya','ギェ'=>'gye','ギィ'=>'gyi','ギョ'=>'gyo','ギュ'=>'gyu', 1404 'ミャ'=>'mya','ミェ'=>'mye','ミィ'=>'myi','ミョ'=>'myo','ミュ'=>'myu', 1405 'ニャ'=>'nya','ニェ'=>'nye','ニィ'=>'nyi','ニョ'=>'nyo','ニュ'=>'nyu', 1406 'リャ'=>'rya','リェ'=>'rye','リィ'=>'ryi','リョ'=>'ryo','リュ'=>'ryu', 1407 'シャ'=>'sha','シェ'=>'she','ショ'=>'sho','シュ'=>'shu', 1408 'ジャ'=>'ja','ジェ'=>'je','ジョ'=>'jo','ジュ'=>'ju', 1409 'スァ'=>'swa','スェ'=>'swe','スィ'=>'swi','スォ'=>'swo','スゥ'=>'swu', 1410 'デァ'=>'da','デェ'=>'de','ディ'=>'di','デォ'=>'do','デゥ'=>'du', 1411 'チャ'=>'cha','チェ'=>'che','チ'=>'chi','チョ'=>'cho','チュ'=>'chu', 1412 // 'ヂャ'=>'dya','ヂェ'=>'dye','ヂィ'=>'dyi','ヂョ'=>'dyo','ヂュ'=>'dyu', 1413 'ツャ'=>'tsa','ツェ'=>'tse','ツィ'=>'tsi','ツョ'=>'tso','ツ'=>'tsu', 1414 'トァ'=>'twa','トェ'=>'twe','トィ'=>'twi','トォ'=>'two','トゥ'=>'twu', 1415 'ドァ'=>'dwa','ドェ'=>'dwe','ドィ'=>'dwi','ドォ'=>'dwo','ドゥ'=>'dwu', 1416 'ウァ'=>'wha','ウェ'=>'whe','ウィ'=>'whi','ウォ'=>'who','ウゥ'=>'whu', 1417 'ヴャ'=>'vya','ヴェ'=>'vye','ヴィ'=>'vyi','ヴョ'=>'vyo','ヴュ'=>'vyu', 1418 'ヴァ'=>'va','ヴェ'=>'ve','ヴィ'=>'vi','ヴォ'=>'vo','ヴ'=>'vu', 1419 'ウェ'=>'we','ウィ'=>'wi', 1420 'イェ'=>'ye', 1421 'ティ'=>'ti', 1422 'ヂィ'=>'di', 1423 1424 // 2 character syllables - doubled vocal 1425 'アー'=>'aa','エー'=>'ee','イー'=>'ii','オー'=>'oo','ウー'=>'uu', 1426 'ダー'=>'daa','デー'=>'dee','ヂー'=>'dii','ドー'=>'doo','ヅー'=>'duu', 1427 'ハー'=>'haa','ヘー'=>'hee','ヒー'=>'hii','ホー'=>'hoo','フー'=>'fuu', 1428 'バー'=>'baa','ベー'=>'bee','ビー'=>'bii','ボー'=>'boo','ブー'=>'buu', 1429 'パー'=>'paa','ペー'=>'pee','ピー'=>'pii','ポー'=>'poo','プー'=>'puu', 1430 'ケー'=>'kee','キー'=>'kii','コー'=>'koo','クー'=>'kuu','カー'=>'kaa', 1431 'ガー'=>'gaa','ゲー'=>'gee','ギー'=>'gii','ゴー'=>'goo','グー'=>'guu', 1432 'マー'=>'maa','メー'=>'mee','ミー'=>'mii','モー'=>'moo','ムー'=>'muu', 1433 'ナー'=>'naa','ネー'=>'nee','ニー'=>'nii','ノー'=>'noo','ヌー'=>'nuu', 1434 'ラー'=>'raa','レー'=>'ree','リー'=>'rii','ロー'=>'roo','ルー'=>'ruu', 1435 'サー'=>'saa','セー'=>'see','シー'=>'shii','ソー'=>'soo','スー'=>'suu', 1436 'ザー'=>'zaa','ゼー'=>'zee','ジー'=>'jii','ゾー'=>'zoo','ズー'=>'zuu', 1437 'ター'=>'taa','テー'=>'tee','チー'=>'chii','トー'=>'too','ツー'=>'tsuu', 1438 'ワー'=>'waa','ヲー'=>'woo', 1439 'ヤー'=>'yaa','ヨー'=>'yoo','ユー'=>'yuu', 1440 'ヵー'=>'kaa','ヶー'=>'kee', 1441 // old characters 1442 'ヱー'=>'wee','ヰー'=>'wii', 1443 1444 // seperate katakana 'n' 1445 'ンア'=>'n_a','ンエ'=>'n_e','ンイ'=>'n_i','ンオ'=>'n_o','ンウ'=>'n_u', 1446 'ンヤ'=>'n_ya','ンヨ'=>'n_yo','ンユ'=>'n_yu', 1447 1448 // 2 character syllables - doubled consonants 1449 'ッバ'=>'bba','ッベ'=>'bbe','ッビ'=>'bbi','ッボ'=>'bbo','ッブ'=>'bbu', 1450 'ッパ'=>'ppa','ッペ'=>'ppe','ッピ'=>'ppi','ッポ'=>'ppo','ップ'=>'ppu', 1451 'ッケ'=>'kke','ッキ'=>'kki','ッコ'=>'kko','ック'=>'kku','ッカ'=>'kka', 1452 'ッガ'=>'gga','ッゲ'=>'gge','ッギ'=>'ggi','ッゴ'=>'ggo','ッグ'=>'ggu', 1453 'ッマ'=>'ma','ッメ'=>'me','ッミ'=>'mi','ッモ'=>'mo','ッム'=>'mu', 1454 'ッナ'=>'nna','ッネ'=>'nne','ッニ'=>'nni','ッノ'=>'nno','ッヌ'=>'nnu', 1455 'ッラ'=>'rra','ッレ'=>'rre','ッリ'=>'rri','ッロ'=>'rro','ッル'=>'rru', 1456 'ッサ'=>'ssa','ッセ'=>'sse','ッシ'=>'sshi','ッソ'=>'sso','ッス'=>'ssu', 1457 'ッザ'=>'zza','ッゼ'=>'zze','ッジ'=>'jji','ッゾ'=>'zzo','ッズ'=>'zzu', 1458 'ッタ'=>'tta','ッテ'=>'tte','ッチ'=>'cchi','ット'=>'tto','ッツ'=>'ttsu', 1459 'ッダ'=>'dda','ッデ'=>'dde','ッヂ'=>'ddi','ッド'=>'ddo','ッヅ'=>'ddu', 1460 1461 // 1 character syllables 1462 'ア'=>'a','エ'=>'e','イ'=>'i','オ'=>'o','ウ'=>'u','ン'=>'n', 1463 'ハ'=>'ha','ヘ'=>'he','ヒ'=>'hi','ホ'=>'ho','フ'=>'fu', 1464 'バ'=>'ba','ベ'=>'be','ビ'=>'bi','ボ'=>'bo','ブ'=>'bu', 1465 'パ'=>'pa','ペ'=>'pe','ピ'=>'pi','ポ'=>'po','プ'=>'pu', 1466 'ケ'=>'ke','キ'=>'ki','コ'=>'ko','ク'=>'ku','カ'=>'ka', 1467 'ガ'=>'ga','ゲ'=>'ge','ギ'=>'gi','ゴ'=>'go','グ'=>'gu', 1468 'マ'=>'ma','メ'=>'me','ミ'=>'mi','モ'=>'mo','ム'=>'mu', 1469 'ナ'=>'na','ネ'=>'ne','ニ'=>'ni','ノ'=>'no','ヌ'=>'nu', 1470 'ラ'=>'ra','レ'=>'re','リ'=>'ri','ロ'=>'ro','ル'=>'ru', 1471 'サ'=>'sa','セ'=>'se','シ'=>'shi','ソ'=>'so','ス'=>'su', 1472 'ザ'=>'za','ゼ'=>'ze','ジ'=>'ji','ゾ'=>'zo','ズ'=>'zu', 1473 'タ'=>'ta','テ'=>'te','チ'=>'chi','ト'=>'to','ツ'=>'tsu', 1474 'ダ'=>'da','デ'=>'de','ヂ'=>'di','ド'=>'do','ヅ'=>'du', 1475 'ワ'=>'wa','ヲ'=>'wo', 1476 'ヤ'=>'ya','ヨ'=>'yo','ユ'=>'yu', 1477 'ヵ'=>'ka','ヶ'=>'ke', 1478 // old characters 1479 'ヱ'=>'we','ヰ'=>'wi', 1480 1481 // convert what's left (probably only kicks in when something's missing above) 1482 'ァ'=>'a','ェ'=>'e','ィ'=>'i','ォ'=>'o','ゥ'=>'u', 1483 'ャ'=>'ya','ョ'=>'yo','ュ'=>'yu', 1484 1485 // special characters 1486 '・'=>'_','、'=>'_', 1487 'ー'=>'_', // when used with hiragana (seldom), this character would not be converted otherwise 1488 1489 // 'ラ'=>'la','レ'=>'le','リ'=>'li','ロ'=>'lo','ル'=>'lu', 1490 // 'チャ'=>'cya','チェ'=>'cye','チィ'=>'cyi','チョ'=>'cyo','チュ'=>'cyu', 1491 //'デャ'=>'dha','デェ'=>'dhe','ディ'=>'dhi','デョ'=>'dho','デュ'=>'dhu', 1492 // 'リャ'=>'lya','リェ'=>'lye','リィ'=>'lyi','リョ'=>'lyo','リュ'=>'lyu', 1493 // 'テャ'=>'tha','テェ'=>'the','ティ'=>'thi','テョ'=>'tho','テュ'=>'thu', 1494 //'ファ'=>'fwa','フェ'=>'fwe','フィ'=>'fwi','フォ'=>'fwo','フゥ'=>'fwu', 1495 //'チャ'=>'tya','チェ'=>'tye','チィ'=>'tyi','チョ'=>'tyo','チュ'=>'tyu', 1496 // 'ジャ'=>'jya','ジェ'=>'jye','ジィ'=>'jyi','ジョ'=>'jyo','ジュ'=>'jyu', 1497 // 'ジャ'=>'zha','ジェ'=>'zhe','ジィ'=>'zhi','ジョ'=>'zho','ジュ'=>'zhu', 1498 //'ジャ'=>'zya','ジェ'=>'zye','ジィ'=>'zyi','ジョ'=>'zyo','ジュ'=>'zyu', 1499 //'シャ'=>'sya','シェ'=>'sye','シィ'=>'syi','ショ'=>'syo','シュ'=>'syu', 1500 //'シ'=>'ci','フ'=>'hu',シ'=>'si','チ'=>'ti','ツ'=>'tu','イ'=>'yi','ヂ'=>'dzi', 1501 1502 // "Greeklish" 1503 'Γ'=>'G','Δ'=>'E','Θ'=>'Th','Λ'=>'L','Ξ'=>'X','Π'=>'P','Σ'=>'S','Φ'=>'F','Ψ'=>'Ps', 1504 'γ'=>'g','δ'=>'e','θ'=>'th','λ'=>'l','ξ'=>'x','π'=>'p','σ'=>'s','φ'=>'f','ψ'=>'ps', 1505 1506 // Thai 1507 'ก'=>'k','ข'=>'kh','ฃ'=>'kh','ค'=>'kh','ฅ'=>'kh','ฆ'=>'kh','ง'=>'ng','จ'=>'ch', 1508 'ฉ'=>'ch','ช'=>'ch','ซ'=>'s','ฌ'=>'ch','ญ'=>'y','ฎ'=>'d','ฏ'=>'t','ฐ'=>'th', 1509 'ฑ'=>'d','ฒ'=>'th','ณ'=>'n','ด'=>'d','ต'=>'t','ถ'=>'th','ท'=>'th','ธ'=>'th', 1510 'น'=>'n','บ'=>'b','ป'=>'p','ผ'=>'ph','ฝ'=>'f','พ'=>'ph','ฟ'=>'f','ภ'=>'ph', 1511 'ม'=>'m','ย'=>'y','ร'=>'r','ฤ'=>'rue','ฤๅ'=>'rue','ล'=>'l','ฦ'=>'lue', 1512 'ฦๅ'=>'lue','ว'=>'w','ศ'=>'s','ษ'=>'s','ส'=>'s','ห'=>'h','ฬ'=>'l','ฮ'=>'h', 1513 'ะ'=>'a','ั'=>'a','รร'=>'a','า'=>'a','ๅ'=>'a','ำ'=>'am','ํา'=>'am', 1514 'ิ'=>'i','ี'=>'i','ึ'=>'ue','ี'=>'ue','ุ'=>'u','ู'=>'u', 1515 'เ'=>'e','แ'=>'ae','โ'=>'o','อ'=>'o', 1516 'ียะ'=>'ia','ีย'=>'ia','ือะ'=>'uea','ือ'=>'uea','ัวะ'=>'ua','ัว'=>'ua', 1517 'ใ'=>'ai','ไ'=>'ai','ัย'=>'ai','าย'=>'ai','าว'=>'ao', 1518 'ุย'=>'ui','อย'=>'oi','ือย'=>'ueai','วย'=>'uai', 1519 'ิว'=>'io','็ว'=>'eo','ียว'=>'iao', 1520 '่'=>'','้'=>'','๊'=>'','๋'=>'','็'=>'', 1521 '์'=>'','๎'=>'','ํ'=>'','ฺ'=>'', 1522 'ๆ'=>'2','๏'=>'o','ฯ'=>'-','๚'=>'-','๛'=>'-', 1523 '๐'=>'0','๑'=>'1','๒'=>'2','๓'=>'3','๔'=>'4', 1524 '๕'=>'5','๖'=>'6','๗'=>'7','๘'=>'8','๙'=>'9', 1525 1526 // Korean 1527 'ㄱ'=>'k','ㅋ'=>'kh','ㄲ'=>'kk','ㄷ'=>'t','ㅌ'=>'th','ㄸ'=>'tt','ㅂ'=>'p', 1528 'ㅍ'=>'ph','ㅃ'=>'pp','ㅈ'=>'c','ㅊ'=>'ch','ㅉ'=>'cc','ㅅ'=>'s','ㅆ'=>'ss', 1529 'ㅎ'=>'h','ㅇ'=>'ng','ㄴ'=>'n','ㄹ'=>'l','ㅁ'=>'m', 'ㅏ'=>'a','ㅓ'=>'e','ㅗ'=>'o', 1530 'ㅜ'=>'wu','ㅡ'=>'u','ㅣ'=>'i','ㅐ'=>'ay','ㅔ'=>'ey','ㅚ'=>'oy','ㅘ'=>'wa','ㅝ'=>'we', 1531 'ㅟ'=>'wi','ㅙ'=>'way','ㅞ'=>'wey','ㅢ'=>'uy','ㅑ'=>'ya','ㅕ'=>'ye','ㅛ'=>'oy', 1532 'ㅠ'=>'yu','ㅒ'=>'yay','ㅖ'=>'yey', 1533); 1534 1535//Setup VIM: ex: et ts=2 enc=utf-8 : 1536 1537