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/** 11 * check for mb_string support 12 */ 13if(!defined('UTF8_MBSTRING')){ 14 if(function_exists('mb_substr') && !defined('UTF8_NOMBSTRING')){ 15 define('UTF8_MBSTRING',1); 16 mb_internal_encoding('UTF-8'); 17 }else{ 18 define('UTF8_MBSTRING',0); 19 } 20} 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); $i++) { 95 if (ord($Str[$i]) < 0x80) continue; # 0bbbbbbb 96 elseif ((ord($Str[$i]) & 0xE0) == 0xC0) $n=1; # 110bbbbb 97 elseif ((ord($Str[$i]) & 0xF0) == 0xE0) $n=2; # 1110bbbb 98 elseif ((ord($Str[$i]) & 0xF8) == 0xF0) $n=3; # 11110bbb 99 elseif ((ord($Str[$i]) & 0xFC) == 0xF8) $n=4; # 111110bb 100 elseif ((ord($Str[$i]) & 0xFE) == 0xFC) $n=5; # 1111110b 101 else return false; # Does not match any model 102 for ($j=0; $j<$n; $j++) { # n bytes matching 10bbbbbb follow ? 103 if ((++$i == strlen($Str)) || ((ord($Str[$i]) & 0xC0) != 0x80)) 104 return false; 105 } 106 } 107 return true; 108} 109 110/** 111 * Unicode aware replacement for strlen() 112 * 113 * utf8_decode() converts characters that are not in ISO-8859-1 114 * to '?', which, for the purpose of counting, is alright - It's 115 * even faster than mb_strlen. 116 * 117 * @author <chernyshevsky at hotmail dot com> 118 * @see strlen() 119 * @see utf8_decode() 120 */ 121function utf8_strlen($string){ 122 return strlen(utf8_decode($string)); 123} 124 125/** 126 * UTF-8 aware alternative to substr 127 * 128 * Return part of a string given character offset (and optionally length) 129 * Note: supports use of negative offsets and lengths but will be slower 130 * when doing so 131 * 132 * @author Harry Fuecks <hfuecks@gmail.com> 133 * @param string 134 * @param integer number of UTF-8 characters offset (from left) 135 * @param integer (optional) length in UTF-8 characters from offset 136 * @return mixed string or FALSE if failure 137 */ 138function utf8_substr($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 if ( $offset >= 0 && $length >= 0 ) { 148 if ( $length === null ) { 149 $length = '*'; 150 } else { 151 $strlen = strlen(utf8_decode($str)); 152 if ( $offset > $strlen ) { 153 return ''; 154 } 155 156 if ( ( $offset + $length ) > $strlen ) { 157 $length = '*'; 158 } else { 159 $length = '{'.$length.'}'; 160 } 161 } 162 163 $pattern = '/^.{'.$offset.'}(.'.$length.')/us'; 164 preg_match($pattern, $str, $matches); 165 166 if ( isset($matches[1]) ) { 167 return $matches[1]; 168 } 169 return false; 170 171 } else { 172 // Handle negatives using different, slower technique 173 // From: http://www.php.net/manual/en/function.substr.php#44838 174 preg_match_all('/./u', $str, $ar); 175 if( $length !== null ) { 176 return join('',array_slice($ar[0],$offset,$length)); 177 } else { 178 return join('',array_slice($ar[0],$offset)); 179 } 180 } 181} 182 183 184/** 185 * Unicode aware replacement for substr_replace() 186 * 187 * @author Andreas Gohr <andi@splitbrain.org> 188 * @see substr_replace() 189 */ 190function utf8_substr_replace($string, $replacement, $start , $length=0 ){ 191 $ret = ''; 192 if($start>0) $ret .= utf8_substr($string, 0, $start); 193 $ret .= $replacement; 194 $ret .= utf8_substr($string, $start+$length); 195 return $ret; 196} 197 198/** 199 * Unicode aware replacement for explode 200 * 201 * @TODO support third limit arg 202 * @author Harry Fuecks <hfuecks@gmail.com> 203 * @see explode(); 204 */ 205function utf8_explode($sep, $str) { 206 if ( $sep == '' ) { 207 trigger_error('Empty delimiter',E_USER_WARNING); 208 return FALSE; 209 } 210 211 return preg_split('!'.preg_quote($sep,'!').'!u',$str); 212} 213 214/** 215 * Unicode aware replacement for strrepalce() 216 * 217 * @todo support PHP5 count (fourth arg) 218 * @author Harry Fuecks <hfuecks@gmail.com> 219 * @see strreplace(); 220 */ 221function utf8_str_replace($s,$r,$str){ 222 if(!is_array($s)){ 223 $s = '!'.preg_quote($s,'!').'!u'; 224 }else{ 225 foreach ($s as $k => $v) { 226 $s[$k] = '!'.preg_quote($v).'!u'; 227 } 228 } 229 return preg_replace($s,$r,$str); 230} 231 232/** 233 * Unicode aware replacement for ltrim() 234 * 235 * @author Andreas Gohr <andi@splitbrain.org> 236 * @see ltrim() 237 * @return string 238 */ 239function utf8_ltrim($str,$charlist=''){ 240 if($charlist == '') return ltrim($str); 241 242 //quote charlist for use in a characterclass 243 $charlist = preg_replace('!([\\\\\\-\\]\\[/])!','\\\${1}',$charlist); 244 245 return preg_replace('/^['.$charlist.']+/u','',$str); 246} 247 248/** 249 * Unicode aware replacement for rtrim() 250 * 251 * @author Andreas Gohr <andi@splitbrain.org> 252 * @see rtrim() 253 * @return string 254 */ 255function utf8_rtrim($str,$charlist=''){ 256 if($charlist == '') return rtrim($str); 257 258 //quote charlist for use in a characterclass 259 $charlist = preg_replace('!([\\\\\\-\\]\\[/])!','\\\${1}',$charlist); 260 261 return preg_replace('/['.$charlist.']+$/u','',$str); 262} 263 264/** 265 * Unicode aware replacement for trim() 266 * 267 * @author Andreas Gohr <andi@splitbrain.org> 268 * @see trim() 269 * @return string 270 */ 271function utf8_trim($str,$charlist='') { 272 if($charlist == '') return trim($str); 273 274 return utf8_ltrim(utf8_rtrim($str)); 275} 276 277 278/** 279 * This is a unicode aware replacement for strtolower() 280 * 281 * Uses mb_string extension if available 282 * 283 * @author Andreas Gohr <andi@splitbrain.org> 284 * @see strtolower() 285 * @see utf8_strtoupper() 286 */ 287function utf8_strtolower($string){ 288 if(UTF8_MBSTRING) return mb_strtolower($string,'utf-8'); 289 290 global $UTF8_UPPER_TO_LOWER; 291 $uni = utf8_to_unicode($string); 292 $cnt = count($uni); 293 for ($i=0; $i < $cnt; $i++){ 294 if($UTF8_UPPER_TO_LOWER[$uni[$i]]){ 295 $uni[$i] = $UTF8_UPPER_TO_LOWER[$uni[$i]]; 296 } 297 } 298 return unicode_to_utf8($uni); 299} 300 301/** 302 * This is a unicode aware replacement for strtoupper() 303 * 304 * Uses mb_string extension if available 305 * 306 * @author Andreas Gohr <andi@splitbrain.org> 307 * @see strtoupper() 308 * @see utf8_strtoupper() 309 */ 310function utf8_strtoupper($string){ 311 if(UTF8_MBSTRING) return mb_strtoupper($string,'utf-8'); 312 313 global $UTF8_LOWER_TO_UPPER; 314 $uni = utf8_to_unicode($string); 315 $cnt = count($uni); 316 for ($i=0; $i < $cnt; $i++){ 317 if($UTF8_LOWER_TO_UPPER[$uni[$i]]){ 318 $uni[$i] = $UTF8_LOWER_TO_UPPER[$uni[$i]]; 319 } 320 } 321 return unicode_to_utf8($uni); 322} 323 324/** 325 * Replace accented UTF-8 characters by unaccented ASCII-7 equivalents 326 * 327 * Use the optional parameter to just deaccent lower ($case = -1) or upper ($case = 1) 328 * letters. Default is to deaccent both cases ($case = 0) 329 * 330 * @author Andreas Gohr <andi@splitbrain.org> 331 */ 332function utf8_deaccent($string,$case=0){ 333 if($case <= 0){ 334 global $UTF8_LOWER_ACCENTS; 335 $string = str_replace(array_keys($UTF8_LOWER_ACCENTS),array_values($UTF8_LOWER_ACCENTS),$string); 336 } 337 if($case >= 0){ 338 global $UTF8_UPPER_ACCENTS; 339 $string = str_replace(array_keys($UTF8_UPPER_ACCENTS),array_values($UTF8_UPPER_ACCENTS),$string); 340 } 341 return $string; 342} 343 344/** 345 * Romanize a non-latin string 346 * 347 * @author Andreas Gohr <andi@splitbrain.org> 348 */ 349function utf8_romanize($string){ 350 if(utf8_isASCII($string)) return $string; //nothing to do 351 352 global $UTF8_ROMANIZATION; 353 return strtr($string,$UTF8_ROMANIZATION); 354} 355 356/** 357 * Removes special characters (nonalphanumeric) from a UTF-8 string 358 * 359 * This function adds the controlchars 0x00 to 0x19 to the array of 360 * stripped chars (they are not included in $UTF8_SPECIAL_CHARS) 361 * 362 * @author Andreas Gohr <andi@splitbrain.org> 363 * @param string $string The UTF8 string to strip of special chars 364 * @param string $repl Replace special with this string 365 * @param string $additional Additional chars to strip (used in regexp char class) 366 */ 367function utf8_stripspecials($string,$repl='',$additional=''){ 368 global $UTF8_SPECIAL_CHARS; 369 370 static $specials = null; 371 if(is_null($specials)){ 372 $specials = preg_quote(unicode_to_utf8($UTF8_SPECIAL_CHARS), '/'); 373 } 374 375 return preg_replace('/['.$additional.'\x00-\x19'.$specials.']/u',$repl,$string); 376} 377 378/** 379 * This is an Unicode aware replacement for strpos 380 * 381 * Uses mb_string extension if available 382 * 383 * @author Harry Fuecks <hfuecks@gmail.com> 384 * @see strpos() 385 */ 386function utf8_strpos($haystack, $needle,$offset=0) { 387 if(UTF8_MBSTRING) return mb_strpos($haystack,$needle,$offset,'utf-8'); 388 389 if(!$offset){ 390 $ar = utf8_explode($needle, $haystack); 391 if ( count($ar) > 1 ) { 392 return utf8_strlen($ar[0]); 393 } 394 return false; 395 }else{ 396 if ( !is_int($offset) ) { 397 trigger_error('Offset must be an integer',E_USER_WARNING); 398 return false; 399 } 400 401 $haystack = utf8_substr($haystack, $offset); 402 403 if ( false !== ($pos = utf8_strpos($haystack,$needle))){ 404 return $pos + $offset; 405 } 406 return false; 407 } 408} 409 410/** 411 * Encodes UTF-8 characters to HTML entities 412 * 413 * @author <vpribish at shopping dot com> 414 * @link http://www.php.net/manual/en/function.utf8-decode.php 415 */ 416function utf8_tohtml ($str) { 417 $ret = ''; 418 $max = strlen($str); 419 $last = 0; // keeps the index of the last regular character 420 for ($i=0; $i<$max; $i++) { 421 $c = $str{$i}; 422 $c1 = ord($c); 423 if ($c1>>5 == 6) { // 110x xxxx, 110 prefix for 2 bytes unicode 424 $ret .= substr($str, $last, $i-$last); // append all the regular characters we've passed 425 $c1 &= 31; // remove the 3 bit two bytes prefix 426 $c2 = ord($str{++$i}); // the next byte 427 $c2 &= 63; // remove the 2 bit trailing byte prefix 428 $c2 |= (($c1 & 3) << 6); // last 2 bits of c1 become first 2 of c2 429 $c1 >>= 2; // c1 shifts 2 to the right 430 $ret .= '&#' . ($c1 * 100 + $c2) . ';'; // this is the fastest string concatenation 431 $last = $i+1; 432 } 433 } 434 return $ret . substr($str, $last, $i); // append the last batch of regular characters 435} 436 437/** 438 * Takes an UTF-8 string and returns an array of ints representing the 439 * Unicode characters. Astral planes are supported ie. the ints in the 440 * output can be > 0xFFFF. Occurrances of the BOM are ignored. Surrogates 441 * are not allowed. 442 * 443 * If $strict is set to true the function returns false if the input 444 * string isn't a valid UTF-8 octet sequence and raises a PHP error at 445 * level E_USER_WARNING 446 * 447 * Note: this function has been modified slightly in this library to 448 * trigger errors on encountering bad bytes 449 * 450 * @author <hsivonen@iki.fi> 451 * @author Harry Fuecks <hfuecks@gmail.com> 452 * @param string UTF-8 encoded string 453 * @param boolean Check for invalid sequences? 454 * @return mixed array of unicode code points or FALSE if UTF-8 invalid 455 * @see unicode_to_utf8 456 * @link http://hsivonen.iki.fi/php-utf8/ 457 * @link http://sourceforge.net/projects/phputf8/ 458 */ 459function utf8_to_unicode($str,$strict=false) { 460 $mState = 0; // cached expected number of octets after the current octet 461 // until the beginning of the next UTF8 character sequence 462 $mUcs4 = 0; // cached Unicode character 463 $mBytes = 1; // cached expected number of octets in the current sequence 464 465 $out = array(); 466 467 $len = strlen($str); 468 469 for($i = 0; $i < $len; $i++) { 470 471 $in = ord($str{$i}); 472 473 if ( $mState == 0) { 474 475 // When mState is zero we expect either a US-ASCII character or a 476 // multi-octet sequence. 477 if (0 == (0x80 & ($in))) { 478 // US-ASCII, pass straight through. 479 $out[] = $in; 480 $mBytes = 1; 481 482 } else if (0xC0 == (0xE0 & ($in))) { 483 // First octet of 2 octet sequence 484 $mUcs4 = ($in); 485 $mUcs4 = ($mUcs4 & 0x1F) << 6; 486 $mState = 1; 487 $mBytes = 2; 488 489 } else if (0xE0 == (0xF0 & ($in))) { 490 // First octet of 3 octet sequence 491 $mUcs4 = ($in); 492 $mUcs4 = ($mUcs4 & 0x0F) << 12; 493 $mState = 2; 494 $mBytes = 3; 495 496 } else if (0xF0 == (0xF8 & ($in))) { 497 // First octet of 4 octet sequence 498 $mUcs4 = ($in); 499 $mUcs4 = ($mUcs4 & 0x07) << 18; 500 $mState = 3; 501 $mBytes = 4; 502 503 } else if (0xF8 == (0xFC & ($in))) { 504 /* First octet of 5 octet sequence. 505 * 506 * This is illegal because the encoded codepoint must be either 507 * (a) not the shortest form or 508 * (b) outside the Unicode range of 0-0x10FFFF. 509 * Rather than trying to resynchronize, we will carry on until the end 510 * of the sequence and let the later error handling code catch it. 511 */ 512 $mUcs4 = ($in); 513 $mUcs4 = ($mUcs4 & 0x03) << 24; 514 $mState = 4; 515 $mBytes = 5; 516 517 } else if (0xFC == (0xFE & ($in))) { 518 // First octet of 6 octet sequence, see comments for 5 octet sequence. 519 $mUcs4 = ($in); 520 $mUcs4 = ($mUcs4 & 1) << 30; 521 $mState = 5; 522 $mBytes = 6; 523 524 } elseif($strict) { 525 /* Current octet is neither in the US-ASCII range nor a legal first 526 * octet of a multi-octet sequence. 527 */ 528 trigger_error( 529 'utf8_to_unicode: Illegal sequence identifier '. 530 'in UTF-8 at byte '.$i, 531 E_USER_WARNING 532 ); 533 return FALSE; 534 535 } 536 537 } else { 538 539 // When mState is non-zero, we expect a continuation of the multi-octet 540 // sequence 541 if (0x80 == (0xC0 & ($in))) { 542 543 // Legal continuation. 544 $shift = ($mState - 1) * 6; 545 $tmp = $in; 546 $tmp = ($tmp & 0x0000003F) << $shift; 547 $mUcs4 |= $tmp; 548 549 /** 550 * End of the multi-octet sequence. mUcs4 now contains the final 551 * Unicode codepoint to be output 552 */ 553 if (0 == --$mState) { 554 555 /* 556 * Check for illegal sequences and codepoints. 557 */ 558 // From Unicode 3.1, non-shortest form is illegal 559 if (((2 == $mBytes) && ($mUcs4 < 0x0080)) || 560 ((3 == $mBytes) && ($mUcs4 < 0x0800)) || 561 ((4 == $mBytes) && ($mUcs4 < 0x10000)) || 562 (4 < $mBytes) || 563 // From Unicode 3.2, surrogate characters are illegal 564 (($mUcs4 & 0xFFFFF800) == 0xD800) || 565 // Codepoints outside the Unicode range are illegal 566 ($mUcs4 > 0x10FFFF)) { 567 568 if($strict){ 569 trigger_error( 570 'utf8_to_unicode: Illegal sequence or codepoint '. 571 'in UTF-8 at byte '.$i, 572 E_USER_WARNING 573 ); 574 575 return FALSE; 576 } 577 578 } 579 580 if (0xFEFF != $mUcs4) { 581 // BOM is legal but we don't want to output it 582 $out[] = $mUcs4; 583 } 584 585 //initialize UTF8 cache 586 $mState = 0; 587 $mUcs4 = 0; 588 $mBytes = 1; 589 } 590 591 } elseif($strict) { 592 /** 593 *((0xC0 & (*in) != 0x80) && (mState != 0)) 594 * Incomplete multi-octet sequence. 595 */ 596 trigger_error( 597 'utf8_to_unicode: Incomplete multi-octet '. 598 ' sequence in UTF-8 at byte '.$i, 599 E_USER_WARNING 600 ); 601 602 return FALSE; 603 } 604 } 605 } 606 return $out; 607} 608 609/** 610 * Takes an array of ints representing the Unicode characters and returns 611 * a UTF-8 string. Astral planes are supported ie. the ints in the 612 * input can be > 0xFFFF. Occurrances of the BOM are ignored. Surrogates 613 * are not allowed. 614 * 615 * If $strict is set to true the function returns false if the input 616 * array contains ints that represent surrogates or are outside the 617 * Unicode range and raises a PHP error at level E_USER_WARNING 618 * 619 * Note: this function has been modified slightly in this library to use 620 * output buffering to concatenate the UTF-8 string (faster) as well as 621 * reference the array by it's keys 622 * 623 * @param array of unicode code points representing a string 624 * @param boolean Check for invalid sequences? 625 * @return mixed UTF-8 string or FALSE if array contains invalid code points 626 * @author <hsivonen@iki.fi> 627 * @author Harry Fuecks <hfuecks@gmail.com> 628 * @see utf8_to_unicode 629 * @link http://hsivonen.iki.fi/php-utf8/ 630 * @link http://sourceforge.net/projects/phputf8/ 631 */ 632function unicode_to_utf8($arr,$strict=false) { 633 if (!is_array($arr)) return ''; 634 ob_start(); 635 636 foreach (array_keys($arr) as $k) { 637 638 # ASCII range (including control chars) 639 if ( ($arr[$k] >= 0) && ($arr[$k] <= 0x007f) ) { 640 641 echo chr($arr[$k]); 642 643 # 2 byte sequence 644 } else if ($arr[$k] <= 0x07ff) { 645 646 echo chr(0xc0 | ($arr[$k] >> 6)); 647 echo chr(0x80 | ($arr[$k] & 0x003f)); 648 649 # Byte order mark (skip) 650 } else if($arr[$k] == 0xFEFF) { 651 652 // nop -- zap the BOM 653 654 # Test for illegal surrogates 655 } else if ($arr[$k] >= 0xD800 && $arr[$k] <= 0xDFFF) { 656 657 // found a surrogate 658 if($strict){ 659 trigger_error( 660 'unicode_to_utf8: Illegal surrogate '. 661 'at index: '.$k.', value: '.$arr[$k], 662 E_USER_WARNING 663 ); 664 return FALSE; 665 } 666 667 # 3 byte sequence 668 } else if ($arr[$k] <= 0xffff) { 669 670 echo chr(0xe0 | ($arr[$k] >> 12)); 671 echo chr(0x80 | (($arr[$k] >> 6) & 0x003f)); 672 echo chr(0x80 | ($arr[$k] & 0x003f)); 673 674 # 4 byte sequence 675 } else if ($arr[$k] <= 0x10ffff) { 676 677 echo chr(0xf0 | ($arr[$k] >> 18)); 678 echo chr(0x80 | (($arr[$k] >> 12) & 0x3f)); 679 echo chr(0x80 | (($arr[$k] >> 6) & 0x3f)); 680 echo chr(0x80 | ($arr[$k] & 0x3f)); 681 682 } elseif($strict) { 683 684 trigger_error( 685 'unicode_to_utf8: Codepoint out of Unicode range '. 686 'at index: '.$k.', value: '.$arr[$k], 687 E_USER_WARNING 688 ); 689 690 // out of range 691 return FALSE; 692 } 693 } 694 695 $result = ob_get_contents(); 696 ob_end_clean(); 697 return $result; 698} 699 700/** 701 * UTF-8 to UTF-16BE conversion. 702 * 703 * Maybe really UCS-2 without mb_string due to utf8_to_unicode limits 704 */ 705function utf8_to_utf16be(&$str, $bom = false) { 706 $out = $bom ? "\xFE\xFF" : ''; 707 if(UTF8_MBSTRING) return $out.mb_convert_encoding($str,'UTF-16BE','UTF-8'); 708 709 $uni = utf8_to_unicode($str); 710 foreach($uni as $cp){ 711 $out .= pack('n',$cp); 712 } 713 return $out; 714} 715 716/** 717 * UTF-8 to UTF-16BE conversion. 718 * 719 * Maybe really UCS-2 without mb_string due to utf8_to_unicode limits 720 */ 721function utf16be_to_utf8(&$str) { 722 $uni = unpack('n*',$str); 723 return unicode_to_utf8($uni); 724} 725 726/** 727 * Replace bad bytes with an alternative character 728 * 729 * ASCII character is recommended for replacement char 730 * 731 * PCRE Pattern to locate bad bytes in a UTF-8 string 732 * Comes from W3 FAQ: Multilingual Forms 733 * Note: modified to include full ASCII range including control chars 734 * 735 * @author Harry Fuecks <hfuecks@gmail.com> 736 * @see http://www.w3.org/International/questions/qa-forms-utf-8 737 * @param string to search 738 * @param string to replace bad bytes with (defaults to '?') - use ASCII 739 * @return string 740 */ 741function utf8_bad_replace($str, $replace = '') { 742 $UTF8_BAD = 743 '([\x00-\x7F]'. # ASCII (including control chars) 744 '|[\xC2-\xDF][\x80-\xBF]'. # non-overlong 2-byte 745 '|\xE0[\xA0-\xBF][\x80-\xBF]'. # excluding overlongs 746 '|[\xE1-\xEC\xEE\xEF][\x80-\xBF]{2}'. # straight 3-byte 747 '|\xED[\x80-\x9F][\x80-\xBF]'. # excluding surrogates 748 '|\xF0[\x90-\xBF][\x80-\xBF]{2}'. # planes 1-3 749 '|[\xF1-\xF3][\x80-\xBF]{3}'. # planes 4-15 750 '|\xF4[\x80-\x8F][\x80-\xBF]{2}'. # plane 16 751 '|(.{1}))'; # invalid byte 752 ob_start(); 753 while (preg_match('/'.$UTF8_BAD.'/S', $str, $matches)) { 754 if ( !isset($matches[2])) { 755 echo $matches[0]; 756 } else { 757 echo $replace; 758 } 759 $str = substr($str,strlen($matches[0])); 760 } 761 $result = ob_get_contents(); 762 ob_end_clean(); 763 return $result; 764} 765 766/** 767 * adjust a byte index into a utf8 string to a utf8 character boundary 768 * 769 * @param $str string utf8 character string 770 * @param $i int byte index into $str 771 * @param $next bool direction to search for boundary, 772 * false = up (current character) 773 * true = down (next character) 774 * 775 * @return int byte index into $str now pointing to a utf8 character boundary 776 * 777 * @author chris smith <chris@jalakai.co.uk> 778 */ 779function utf8_correctIdx(&$str,$i,$next=false) { 780 781 if ($i <= 0) return 0; 782 783 $limit = strlen($str); 784 if ($i>=$limit) return $limit; 785 786 if ($next) { 787 while (($i<$limit) && ((ord($str[$i]) & 0xC0) == 0x80)) $i++; 788 } else { 789 while ($i && ((ord($str[$i]) & 0xC0) == 0x80)) $i--; 790 } 791 792 return $i; 793} 794 795// only needed if no mb_string available 796if(!UTF8_MBSTRING){ 797 798 /** 799 * UTF-8 Case lookup table 800 * 801 * This lookuptable defines the upper case letters to their correspponding 802 * lower case letter in UTF-8 803 * 804 * @author Andreas Gohr <andi@splitbrain.org> 805 */ 806 global $UTF8_LOWER_TO_UPPER; 807 $UTF8_LOWER_TO_UPPER = array( 808 0x0061=>0x0041, 0x03C6=>0x03A6, 0x0163=>0x0162, 0x00E5=>0x00C5, 0x0062=>0x0042, 809 0x013A=>0x0139, 0x00E1=>0x00C1, 0x0142=>0x0141, 0x03CD=>0x038E, 0x0101=>0x0100, 810 0x0491=>0x0490, 0x03B4=>0x0394, 0x015B=>0x015A, 0x0064=>0x0044, 0x03B3=>0x0393, 811 0x00F4=>0x00D4, 0x044A=>0x042A, 0x0439=>0x0419, 0x0113=>0x0112, 0x043C=>0x041C, 812 0x015F=>0x015E, 0x0144=>0x0143, 0x00EE=>0x00CE, 0x045E=>0x040E, 0x044F=>0x042F, 813 0x03BA=>0x039A, 0x0155=>0x0154, 0x0069=>0x0049, 0x0073=>0x0053, 0x1E1F=>0x1E1E, 814 0x0135=>0x0134, 0x0447=>0x0427, 0x03C0=>0x03A0, 0x0438=>0x0418, 0x00F3=>0x00D3, 815 0x0440=>0x0420, 0x0454=>0x0404, 0x0435=>0x0415, 0x0449=>0x0429, 0x014B=>0x014A, 816 0x0431=>0x0411, 0x0459=>0x0409, 0x1E03=>0x1E02, 0x00F6=>0x00D6, 0x00F9=>0x00D9, 817 0x006E=>0x004E, 0x0451=>0x0401, 0x03C4=>0x03A4, 0x0443=>0x0423, 0x015D=>0x015C, 818 0x0453=>0x0403, 0x03C8=>0x03A8, 0x0159=>0x0158, 0x0067=>0x0047, 0x00E4=>0x00C4, 819 0x03AC=>0x0386, 0x03AE=>0x0389, 0x0167=>0x0166, 0x03BE=>0x039E, 0x0165=>0x0164, 820 0x0117=>0x0116, 0x0109=>0x0108, 0x0076=>0x0056, 0x00FE=>0x00DE, 0x0157=>0x0156, 821 0x00FA=>0x00DA, 0x1E61=>0x1E60, 0x1E83=>0x1E82, 0x00E2=>0x00C2, 0x0119=>0x0118, 822 0x0146=>0x0145, 0x0070=>0x0050, 0x0151=>0x0150, 0x044E=>0x042E, 0x0129=>0x0128, 823 0x03C7=>0x03A7, 0x013E=>0x013D, 0x0442=>0x0422, 0x007A=>0x005A, 0x0448=>0x0428, 824 0x03C1=>0x03A1, 0x1E81=>0x1E80, 0x016D=>0x016C, 0x00F5=>0x00D5, 0x0075=>0x0055, 825 0x0177=>0x0176, 0x00FC=>0x00DC, 0x1E57=>0x1E56, 0x03C3=>0x03A3, 0x043A=>0x041A, 826 0x006D=>0x004D, 0x016B=>0x016A, 0x0171=>0x0170, 0x0444=>0x0424, 0x00EC=>0x00CC, 827 0x0169=>0x0168, 0x03BF=>0x039F, 0x006B=>0x004B, 0x00F2=>0x00D2, 0x00E0=>0x00C0, 828 0x0434=>0x0414, 0x03C9=>0x03A9, 0x1E6B=>0x1E6A, 0x00E3=>0x00C3, 0x044D=>0x042D, 829 0x0436=>0x0416, 0x01A1=>0x01A0, 0x010D=>0x010C, 0x011D=>0x011C, 0x00F0=>0x00D0, 830 0x013C=>0x013B, 0x045F=>0x040F, 0x045A=>0x040A, 0x00E8=>0x00C8, 0x03C5=>0x03A5, 831 0x0066=>0x0046, 0x00FD=>0x00DD, 0x0063=>0x0043, 0x021B=>0x021A, 0x00EA=>0x00CA, 832 0x03B9=>0x0399, 0x017A=>0x0179, 0x00EF=>0x00CF, 0x01B0=>0x01AF, 0x0065=>0x0045, 833 0x03BB=>0x039B, 0x03B8=>0x0398, 0x03BC=>0x039C, 0x045C=>0x040C, 0x043F=>0x041F, 834 0x044C=>0x042C, 0x00FE=>0x00DE, 0x00F0=>0x00D0, 0x1EF3=>0x1EF2, 0x0068=>0x0048, 835 0x00EB=>0x00CB, 0x0111=>0x0110, 0x0433=>0x0413, 0x012F=>0x012E, 0x00E6=>0x00C6, 836 0x0078=>0x0058, 0x0161=>0x0160, 0x016F=>0x016E, 0x03B1=>0x0391, 0x0457=>0x0407, 837 0x0173=>0x0172, 0x00FF=>0x0178, 0x006F=>0x004F, 0x043B=>0x041B, 0x03B5=>0x0395, 838 0x0445=>0x0425, 0x0121=>0x0120, 0x017E=>0x017D, 0x017C=>0x017B, 0x03B6=>0x0396, 839 0x03B2=>0x0392, 0x03AD=>0x0388, 0x1E85=>0x1E84, 0x0175=>0x0174, 0x0071=>0x0051, 840 0x0437=>0x0417, 0x1E0B=>0x1E0A, 0x0148=>0x0147, 0x0105=>0x0104, 0x0458=>0x0408, 841 0x014D=>0x014C, 0x00ED=>0x00CD, 0x0079=>0x0059, 0x010B=>0x010A, 0x03CE=>0x038F, 842 0x0072=>0x0052, 0x0430=>0x0410, 0x0455=>0x0405, 0x0452=>0x0402, 0x0127=>0x0126, 843 0x0137=>0x0136, 0x012B=>0x012A, 0x03AF=>0x038A, 0x044B=>0x042B, 0x006C=>0x004C, 844 0x03B7=>0x0397, 0x0125=>0x0124, 0x0219=>0x0218, 0x00FB=>0x00DB, 0x011F=>0x011E, 845 0x043E=>0x041E, 0x1E41=>0x1E40, 0x03BD=>0x039D, 0x0107=>0x0106, 0x03CB=>0x03AB, 846 0x0446=>0x0426, 0x00FE=>0x00DE, 0x00E7=>0x00C7, 0x03CA=>0x03AA, 0x0441=>0x0421, 847 0x0432=>0x0412, 0x010F=>0x010E, 0x00F8=>0x00D8, 0x0077=>0x0057, 0x011B=>0x011A, 848 0x0074=>0x0054, 0x006A=>0x004A, 0x045B=>0x040B, 0x0456=>0x0406, 0x0103=>0x0102, 849 0x03BB=>0x039B, 0x00F1=>0x00D1, 0x043D=>0x041D, 0x03CC=>0x038C, 0x00E9=>0x00C9, 850 0x00F0=>0x00D0, 0x0457=>0x0407, 0x0123=>0x0122, 851 ); 852 853 /** 854 * UTF-8 Case lookup table 855 * 856 * This lookuptable defines the lower case letters to their correspponding 857 * upper case letter in UTF-8 (it does so by flipping $UTF8_LOWER_TO_UPPER) 858 * 859 * @author Andreas Gohr <andi@splitbrain.org> 860 */ 861 global $UTF8_UPPER_TO_LOWER; 862 $UTF8_UPPER_TO_LOWER = @array_flip($UTF8_LOWER_TO_UPPER); 863 864} // end of case lookup tables 865 866 867/** 868 * UTF-8 lookup table for lower case accented letters 869 * 870 * This lookuptable defines replacements for accented characters from the ASCII-7 871 * range. This are lower case letters only. 872 * 873 * @author Andreas Gohr <andi@splitbrain.org> 874 * @see utf8_deaccent() 875 */ 876global $UTF8_LOWER_ACCENTS; 877$UTF8_LOWER_ACCENTS = array( 878 'à' => 'a', 'ô' => 'o', 'ď' => 'd', 'ḟ' => 'f', 'ë' => 'e', 'š' => 's', 'ơ' => 'o', 879 'ß' => 'ss', 'ă' => 'a', 'ř' => 'r', 'ț' => 't', 'ň' => 'n', 'ā' => 'a', 'ķ' => 'k', 880 'ŝ' => 's', 'ỳ' => 'y', 'ņ' => 'n', 'ĺ' => 'l', 'ħ' => 'h', 'ṗ' => 'p', 'ó' => 'o', 881 'ú' => 'u', 'ě' => 'e', 'é' => 'e', 'ç' => 'c', 'ẁ' => 'w', 'ċ' => 'c', 'õ' => 'o', 882 'ṡ' => 's', 'ø' => 'o', 'ģ' => 'g', 'ŧ' => 't', 'ș' => 's', 'ė' => 'e', 'ĉ' => 'c', 883 'ś' => 's', 'î' => 'i', 'ű' => 'u', 'ć' => 'c', 'ę' => 'e', 'ŵ' => 'w', 'ṫ' => 't', 884 'ū' => 'u', 'č' => 'c', 'ö' => 'oe', 'è' => 'e', 'ŷ' => 'y', 'ą' => 'a', 'ł' => 'l', 885 'ų' => 'u', 'ů' => 'u', 'ş' => 's', 'ğ' => 'g', 'ļ' => 'l', 'ƒ' => 'f', 'ž' => 'z', 886 'ẃ' => 'w', 'ḃ' => 'b', 'å' => 'a', 'ì' => 'i', 'ï' => 'i', 'ḋ' => 'd', 'ť' => 't', 887 'ŗ' => 'r', 'ä' => 'ae', 'í' => 'i', 'ŕ' => 'r', 'ê' => 'e', 'ü' => 'ue', 'ò' => 'o', 888 'ē' => 'e', 'ñ' => 'n', 'ń' => 'n', 'ĥ' => 'h', 'ĝ' => 'g', 'đ' => 'd', 'ĵ' => 'j', 889 'ÿ' => 'y', 'ũ' => 'u', 'ŭ' => 'u', 'ư' => 'u', 'ţ' => 't', 'ý' => 'y', 'ő' => 'o', 890 'â' => 'a', 'ľ' => 'l', 'ẅ' => 'w', 'ż' => 'z', 'ī' => 'i', 'ã' => 'a', 'ġ' => 'g', 891 'ṁ' => 'm', 'ō' => 'o', 'ĩ' => 'i', 'ù' => 'u', 'į' => 'i', 'ź' => 'z', 'á' => 'a', 892 'û' => 'u', 'þ' => 'th', 'ð' => 'dh', 'æ' => 'ae', 'µ' => 'u', 'ĕ' => 'e', 893); 894 895/** 896 * UTF-8 lookup table for upper case accented letters 897 * 898 * This lookuptable defines replacements for accented characters from the ASCII-7 899 * range. This are upper case letters only. 900 * 901 * @author Andreas Gohr <andi@splitbrain.org> 902 * @see utf8_deaccent() 903 */ 904global $UTF8_UPPER_ACCENTS; 905$UTF8_UPPER_ACCENTS = array( 906 'À' => 'A', 'Ô' => 'O', 'Ď' => 'D', 'Ḟ' => 'F', 'Ë' => 'E', 'Š' => 'S', 'Ơ' => 'O', 907 'Ă' => 'A', 'Ř' => 'R', 'Ț' => 'T', 'Ň' => 'N', 'Ā' => 'A', 'Ķ' => 'K', 908 'Ŝ' => 'S', 'Ỳ' => 'Y', 'Ņ' => 'N', 'Ĺ' => 'L', 'Ħ' => 'H', 'Ṗ' => 'P', 'Ó' => 'O', 909 'Ú' => 'U', 'Ě' => 'E', 'É' => 'E', 'Ç' => 'C', 'Ẁ' => 'W', 'Ċ' => 'C', 'Õ' => 'O', 910 'Ṡ' => 'S', 'Ø' => 'O', 'Ģ' => 'G', 'Ŧ' => 'T', 'Ș' => 'S', 'Ė' => 'E', 'Ĉ' => 'C', 911 'Ś' => 'S', 'Î' => 'I', 'Ű' => 'U', 'Ć' => 'C', 'Ę' => 'E', 'Ŵ' => 'W', 'Ṫ' => 'T', 912 'Ū' => 'U', 'Č' => 'C', 'Ö' => 'Oe', 'È' => 'E', 'Ŷ' => 'Y', 'Ą' => 'A', 'Ł' => 'L', 913 'Ų' => 'U', 'Ů' => 'U', 'Ş' => 'S', 'Ğ' => 'G', 'Ļ' => 'L', 'Ƒ' => 'F', 'Ž' => 'Z', 914 'Ẃ' => 'W', 'Ḃ' => 'B', 'Å' => 'A', 'Ì' => 'I', 'Ï' => 'I', 'Ḋ' => 'D', 'Ť' => 'T', 915 'Ŗ' => 'R', 'Ä' => 'Ae', 'Í' => 'I', 'Ŕ' => 'R', 'Ê' => 'E', 'Ü' => 'Ue', 'Ò' => 'O', 916 'Ē' => 'E', 'Ñ' => 'N', 'Ń' => 'N', 'Ĥ' => 'H', 'Ĝ' => 'G', 'Đ' => 'D', 'Ĵ' => 'J', 917 'Ÿ' => 'Y', 'Ũ' => 'U', 'Ŭ' => 'U', 'Ư' => 'U', 'Ţ' => 'T', 'Ý' => 'Y', 'Ő' => 'O', 918 'Â' => 'A', 'Ľ' => 'L', 'Ẅ' => 'W', 'Ż' => 'Z', 'Ī' => 'I', 'Ã' => 'A', 'Ġ' => 'G', 919 'Ṁ' => 'M', 'Ō' => 'O', 'Ĩ' => 'I', 'Ù' => 'U', 'Į' => 'I', 'Ź' => 'Z', 'Á' => 'A', 920 'Û' => 'U', 'Þ' => 'Th', 'Ð' => 'Dh', 'Æ' => 'Ae', 'Ĕ' => 'E', 921); 922 923/** 924 * UTF-8 array of common special characters 925 * 926 * This array should contain all special characters (not a letter or digit) 927 * defined in the various local charsets - it's not a complete list of non-alphanum 928 * characters in UTF-8. It's not perfect but should match most cases of special 929 * chars. 930 * 931 * The controlchars 0x00 to 0x19 are _not_ included in this array. The space 0x20 is! 932 * These chars are _not_ in the array either: _ (0x5f), : 0x3a, . 0x2e, - 0x2d, * 0x2a 933 * 934 * @author Andreas Gohr <andi@splitbrain.org> 935 * @see utf8_stripspecials() 936 */ 937global $UTF8_SPECIAL_CHARS; 938$UTF8_SPECIAL_CHARS = array( 939 0x001a, 0x001b, 0x001c, 0x001d, 0x001e, 0x001f, 0x0020, 0x0021, 0x0022, 0x0023, 940 0x0024, 0x0025, 0x0026, 0x0027, 0x0028, 0x0029, 0x002b, 0x002c, 941 0x002f, 0x003b, 0x003c, 0x003d, 0x003e, 0x003f, 0x0040, 0x005b, 942 0x005c, 0x005d, 0x005e, 0x0060, 0x007b, 0x007c, 0x007d, 0x007e, 943 0x007f, 0x0080, 0x0081, 0x0082, 0x0083, 0x0084, 0x0085, 0x0086, 0x0087, 0x0088, 944 0x0089, 0x008a, 0x008b, 0x008c, 0x008d, 0x008e, 0x008f, 0x0090, 0x0091, 0x0092, 945 0x0093, 0x0094, 0x0095, 0x0096, 0x0097, 0x0098, 0x0099, 0x009a, 0x009b, 0x009c, 946 0x009d, 0x009e, 0x009f, 0x00a0, 0x00a1, 0x00a2, 0x00a3, 0x00a4, 0x00a5, 0x00a6, 947 0x00a7, 0x00a8, 0x00a9, 0x00aa, 0x00ab, 0x00ac, 0x00ad, 0x00ae, 0x00af, 0x00b0, 948 0x00b1, 0x00b2, 0x00b3, 0x00b4, 0x00b5, 0x00b6, 0x00b7, 0x00b8, 0x00b9, 0x00ba, 949 0x00bb, 0x00bc, 0x00bd, 0x00be, 0x00bf, 0x00d7, 0x00f7, 0x02c7, 0x02d8, 0x02d9, 950 0x02da, 0x02db, 0x02dc, 0x02dd, 0x0300, 0x0301, 0x0303, 0x0309, 0x0323, 0x0384, 951 0x0385, 0x0387, 0x03b2, 0x03c6, 0x03d1, 0x03d2, 0x03d5, 0x03d6, 0x05b0, 0x05b1, 952 0x05b2, 0x05b3, 0x05b4, 0x05b5, 0x05b6, 0x05b7, 0x05b8, 0x05b9, 0x05bb, 0x05bc, 953 0x05bd, 0x05be, 0x05bf, 0x05c0, 0x05c1, 0x05c2, 0x05c3, 0x05f3, 0x05f4, 0x060c, 954 0x061b, 0x061f, 0x0640, 0x064b, 0x064c, 0x064d, 0x064e, 0x064f, 0x0650, 0x0651, 955 0x0652, 0x066a, 0x0e3f, 0x200c, 0x200d, 0x200e, 0x200f, 0x2013, 0x2014, 0x2015, 956 0x2017, 0x2018, 0x2019, 0x201a, 0x201c, 0x201d, 0x201e, 0x2020, 0x2021, 0x2022, 957 0x2026, 0x2030, 0x2032, 0x2033, 0x2039, 0x203a, 0x2044, 0x20a7, 0x20aa, 0x20ab, 958 0x20ac, 0x2116, 0x2118, 0x2122, 0x2126, 0x2135, 0x2190, 0x2191, 0x2192, 0x2193, 959 0x2194, 0x2195, 0x21b5, 0x21d0, 0x21d1, 0x21d2, 0x21d3, 0x21d4, 0x2200, 0x2202, 960 0x2203, 0x2205, 0x2206, 0x2207, 0x2208, 0x2209, 0x220b, 0x220f, 0x2211, 0x2212, 961 0x2215, 0x2217, 0x2219, 0x221a, 0x221d, 0x221e, 0x2220, 0x2227, 0x2228, 0x2229, 962 0x222a, 0x222b, 0x2234, 0x223c, 0x2245, 0x2248, 0x2260, 0x2261, 0x2264, 0x2265, 963 0x2282, 0x2283, 0x2284, 0x2286, 0x2287, 0x2295, 0x2297, 0x22a5, 0x22c5, 0x2310, 964 0x2320, 0x2321, 0x2329, 0x232a, 0x2469, 0x2500, 0x2502, 0x250c, 0x2510, 0x2514, 965 0x2518, 0x251c, 0x2524, 0x252c, 0x2534, 0x253c, 0x2550, 0x2551, 0x2552, 0x2553, 966 0x2554, 0x2555, 0x2556, 0x2557, 0x2558, 0x2559, 0x255a, 0x255b, 0x255c, 0x255d, 967 0x255e, 0x255f, 0x2560, 0x2561, 0x2562, 0x2563, 0x2564, 0x2565, 0x2566, 0x2567, 968 0x2568, 0x2569, 0x256a, 0x256b, 0x256c, 0x2580, 0x2584, 0x2588, 0x258c, 0x2590, 969 0x2591, 0x2592, 0x2593, 0x25a0, 0x25b2, 0x25bc, 0x25c6, 0x25ca, 0x25cf, 0x25d7, 970 0x2605, 0x260e, 0x261b, 0x261e, 0x2660, 0x2663, 0x2665, 0x2666, 0x2701, 0x2702, 971 0x2703, 0x2704, 0x2706, 0x2707, 0x2708, 0x2709, 0x270c, 0x270d, 0x270e, 0x270f, 972 0x2710, 0x2711, 0x2712, 0x2713, 0x2714, 0x2715, 0x2716, 0x2717, 0x2718, 0x2719, 973 0x271a, 0x271b, 0x271c, 0x271d, 0x271e, 0x271f, 0x2720, 0x2721, 0x2722, 0x2723, 974 0x2724, 0x2725, 0x2726, 0x2727, 0x2729, 0x272a, 0x272b, 0x272c, 0x272d, 0x272e, 975 0x272f, 0x2730, 0x2731, 0x2732, 0x2733, 0x2734, 0x2735, 0x2736, 0x2737, 0x2738, 976 0x2739, 0x273a, 0x273b, 0x273c, 0x273d, 0x273e, 0x273f, 0x2740, 0x2741, 0x2742, 977 0x2743, 0x2744, 0x2745, 0x2746, 0x2747, 0x2748, 0x2749, 0x274a, 0x274b, 0x274d, 978 0x274f, 0x2750, 0x2751, 0x2752, 0x2756, 0x2758, 0x2759, 0x275a, 0x275b, 0x275c, 979 0x275d, 0x275e, 0x2761, 0x2762, 0x2763, 0x2764, 0x2765, 0x2766, 0x2767, 0x277f, 980 0x2789, 0x2793, 0x2794, 0x2798, 0x2799, 0x279a, 0x279b, 0x279c, 0x279d, 0x279e, 981 0x279f, 0x27a0, 0x27a1, 0x27a2, 0x27a3, 0x27a4, 0x27a5, 0x27a6, 0x27a7, 0x27a8, 982 0x27a9, 0x27aa, 0x27ab, 0x27ac, 0x27ad, 0x27ae, 0x27af, 0x27b1, 0x27b2, 0x27b3, 983 0x27b4, 0x27b5, 0x27b6, 0x27b7, 0x27b8, 0x27b9, 0x27ba, 0x27bb, 0x27bc, 0x27bd, 984 0x27be, 0xf6d9, 0xf6da, 0xf6db, 0xf8d7, 0xf8d8, 0xf8d9, 0xf8da, 0xf8db, 0xf8dc, 985 0xf8dd, 0xf8de, 0xf8df, 0xf8e0, 0xf8e1, 0xf8e2, 0xf8e3, 0xf8e4, 0xf8e5, 0xf8e6, 986 0xf8e7, 0xf8e8, 0xf8e9, 0xf8ea, 0xf8eb, 0xf8ec, 0xf8ed, 0xf8ee, 0xf8ef, 0xf8f0, 987 0xf8f1, 0xf8f2, 0xf8f3, 0xf8f4, 0xf8f5, 0xf8f6, 0xf8f7, 0xf8f8, 0xf8f9, 0xf8fa, 988 0xf8fb, 0xf8fc, 0xf8fd, 0xf8fe, 0xfe7c, 0xfe7d, 989); 990 991/** 992 * Romanization lookup table 993 * 994 * This lookup tables provides a way to transform strings written in a language 995 * different from the ones based upon latin letters into plain ASCII. 996 * 997 * Please note: this is not a scientific transliteration table. It only works 998 * oneway from nonlatin to ASCII and it works by simple character replacement 999 * only. Specialities of each language are not supported. 1000 * 1001 * @author Andreas Gohr <andi@splitbrain.org> 1002 * @author Vitaly Blokhin <vitinfo@vitn.com> 1003 * @link http://www.uconv.com/translit.htm 1004 * @author Bisqwit <bisqwit@iki.fi> 1005 * @link http://kanjidict.stc.cx/hiragana.php?src=2 1006 * @link http://www.translatum.gr/converter/greek-transliteration.htm 1007 * @link http://en.wikipedia.org/wiki/Royal_Thai_General_System_of_Transcription 1008 * @link http://www.btranslations.com/resources/romanization/korean.asp 1009 */ 1010global $UTF8_ROMANIZATION; 1011$UTF8_ROMANIZATION = array( 1012 //russian cyrillic 1013 'а'=>'a','А'=>'A','б'=>'b','Б'=>'B','в'=>'v','В'=>'V','г'=>'g','Г'=>'G', 1014 'д'=>'d','Д'=>'D','е'=>'e','Е'=>'E','ё'=>'jo','Ё'=>'Jo','ж'=>'zh','Ж'=>'Zh', 1015 'з'=>'z','З'=>'Z','и'=>'i','И'=>'I','й'=>'j','Й'=>'J','к'=>'k','К'=>'K', 1016 'л'=>'l','Л'=>'L','м'=>'m','М'=>'M','н'=>'n','Н'=>'N','о'=>'o','О'=>'O', 1017 'п'=>'p','П'=>'P','р'=>'r','Р'=>'R','с'=>'s','С'=>'S','т'=>'t','Т'=>'T', 1018 'у'=>'u','У'=>'U','ф'=>'f','Ф'=>'F','х'=>'x','Х'=>'X','ц'=>'c','Ц'=>'C', 1019 'ч'=>'ch','Ч'=>'Ch','ш'=>'sh','Ш'=>'Sh','щ'=>'sch','Щ'=>'Sch','ъ'=>'', 1020 'Ъ'=>'','ы'=>'y','Ы'=>'Y','ь'=>'\'','Ь'=>'\'','э'=>'eh','Э'=>'Eh','ю'=>'ju', 1021 'Ю'=>'Ju','я'=>'ja','Я'=>'Ja', 1022 // Ukrainian cyrillic 1023 'Ґ'=>'Gh','ґ'=>'gh','Є'=>'Je','є'=>'je','І'=>'I','і'=>'i','Ї'=>'Ji','ї'=>'ji', 1024 // Georgian 1025 'ა'=>'a','ბ'=>'b','გ'=>'g','დ'=>'d','ე'=>'e','ვ'=>'v','ზ'=>'z','თ'=>'th', 1026 'ი'=>'i','კ'=>'p','ლ'=>'l','მ'=>'m','ნ'=>'n','ო'=>'o','პ'=>'p','ჟ'=>'zh', 1027 'რ'=>'r','ს'=>'s','ტ'=>'t','უ'=>'u','ფ'=>'ph','ქ'=>'kh','ღ'=>'gh','ყ'=>'q', 1028 'შ'=>'sh','ჩ'=>'ch','ც'=>'c','ძ'=>'dh','წ'=>'w','ჭ'=>'j','ხ'=>'x','ჯ'=>'jh', 1029 'ჰ'=>'xh', 1030 //Sanskrit 1031 'अ'=>'a','आ'=>'ah','इ'=>'i','ई'=>'ih','उ'=>'u','ऊ'=>'uh','ऋ'=>'ry', 1032 'ॠ'=>'ryh','ऌ'=>'ly','ॡ'=>'lyh','ए'=>'e','ऐ'=>'ay','ओ'=>'o','औ'=>'aw', 1033 'अं'=>'amh','अः'=>'aq','क'=>'k','ख'=>'kh','ग'=>'g','घ'=>'gh','ङ'=>'nh', 1034 'च'=>'c','छ'=>'ch','ज'=>'j','झ'=>'jh','ञ'=>'ny','ट'=>'tq','ठ'=>'tqh', 1035 'ड'=>'dq','ढ'=>'dqh','ण'=>'nq','त'=>'t','थ'=>'th','द'=>'d','ध'=>'dh', 1036 'न'=>'n','प'=>'p','फ'=>'ph','ब'=>'b','भ'=>'bh','म'=>'m','य'=>'z','र'=>'r', 1037 'ल'=>'l','व'=>'v','श'=>'sh','ष'=>'sqh','स'=>'s','ह'=>'x', 1038 //Hebrew 1039 'א'=>'a', 'ב'=>'b','ג'=>'g','ד'=>'d','ה'=>'h','ו'=>'v','ז'=>'z','ח'=>'kh','ט'=>'th', 1040 'י'=>'y','ך'=>'h','כ'=>'k','ל'=>'l','ם'=>'m','מ'=>'m','ן'=>'n','נ'=>'n', 1041 'ס'=>'s','ע'=>'ah','ף'=>'f','פ'=>'p','ץ'=>'c','צ'=>'c','ק'=>'q','ר'=>'r', 1042 'ש'=>'sh','ת'=>'t', 1043 //Arabic 1044 'ا'=>'a','ب'=>'b','ت'=>'t','ث'=>'th','ج'=>'g','ح'=>'xh','خ'=>'x','د'=>'d', 1045 'ذ'=>'dh','ر'=>'r','ز'=>'z','س'=>'s','ش'=>'sh','ص'=>'s\'','ض'=>'d\'', 1046 'ط'=>'t\'','ظ'=>'z\'','ع'=>'y','غ'=>'gh','ف'=>'f','ق'=>'q','ك'=>'k', 1047 'ل'=>'l','م'=>'m','ن'=>'n','ه'=>'x\'','و'=>'u','ي'=>'i', 1048 1049 // Japanese hiragana 1050 'あ'=>'a','え'=>'e','い'=>'i','お'=>'o','う'=>'u','ば'=>'ba','べ'=>'be', 1051 'び'=>'bi','ぼ'=>'bo','ぶ'=>'bu','し'=>'ci','だ'=>'da','で'=>'de','ぢ'=>'di', 1052 'ど'=>'do','づ'=>'du','ふぁ'=>'fa','ふぇ'=>'fe','ふぃ'=>'fi','ふぉ'=>'fo', 1053 'ふ'=>'fu','が'=>'ga','げ'=>'ge','ぎ'=>'gi','ご'=>'go','ぐ'=>'gu','は'=>'ha', 1054 'へ'=>'he','ひ'=>'hi','ほ'=>'ho','ふ'=>'hu','じゃ'=>'ja','じぇ'=>'je', 1055 'じ'=>'ji','じょ'=>'jo','じゅ'=>'ju','か'=>'ka','け'=>'ke','き'=>'ki', 1056 'こ'=>'ko','く'=>'ku','ら'=>'la','れ'=>'le','り'=>'li','ろ'=>'lo','る'=>'lu', 1057 'ま'=>'ma','め'=>'me','み'=>'mi','も'=>'mo','む'=>'mu','な'=>'na','ね'=>'ne', 1058 'に'=>'ni','の'=>'no','ぬ'=>'nu','ぱ'=>'pa','ぺ'=>'pe','ぴ'=>'pi','ぽ'=>'po', 1059 'ぷ'=>'pu','ら'=>'ra','れ'=>'re','り'=>'ri','ろ'=>'ro','る'=>'ru','さ'=>'sa', 1060 'せ'=>'se','し'=>'si','そ'=>'so','す'=>'su','た'=>'ta','て'=>'te','ち'=>'ti', 1061 'と'=>'to','つ'=>'tu','ヴぁ'=>'va','ヴぇ'=>'ve','ヴぃ'=>'vi','ヴぉ'=>'vo', 1062 'ヴ'=>'vu','わ'=>'wa','うぇ'=>'we','うぃ'=>'wi','を'=>'wo','や'=>'ya','いぇ'=>'ye', 1063 'い'=>'yi','よ'=>'yo','ゆ'=>'yu','ざ'=>'za','ぜ'=>'ze','じ'=>'zi','ぞ'=>'zo', 1064 'ず'=>'zu','びゃ'=>'bya','びぇ'=>'bye','びぃ'=>'byi','びょ'=>'byo','びゅ'=>'byu', 1065 'ちゃ'=>'cha','ちぇ'=>'che','ち'=>'chi','ちょ'=>'cho','ちゅ'=>'chu','ちゃ'=>'cya', 1066 'ちぇ'=>'cye','ちぃ'=>'cyi','ちょ'=>'cyo','ちゅ'=>'cyu','でゃ'=>'dha','でぇ'=>'dhe', 1067 'でぃ'=>'dhi','でょ'=>'dho','でゅ'=>'dhu','どぁ'=>'dwa','どぇ'=>'dwe','どぃ'=>'dwi', 1068 'どぉ'=>'dwo','どぅ'=>'dwu','ぢゃ'=>'dya','ぢぇ'=>'dye','ぢぃ'=>'dyi','ぢょ'=>'dyo', 1069 'ぢゅ'=>'dyu','ぢ'=>'dzi','ふぁ'=>'fwa','ふぇ'=>'fwe','ふぃ'=>'fwi','ふぉ'=>'fwo', 1070 'ふぅ'=>'fwu','ふゃ'=>'fya','ふぇ'=>'fye','ふぃ'=>'fyi','ふょ'=>'fyo','ふゅ'=>'fyu', 1071 'ぎゃ'=>'gya','ぎぇ'=>'gye','ぎぃ'=>'gyi','ぎょ'=>'gyo','ぎゅ'=>'gyu','ひゃ'=>'hya', 1072 'ひぇ'=>'hye','ひぃ'=>'hyi','ひょ'=>'hyo','ひゅ'=>'hyu','じゃ'=>'jya','じぇ'=>'jye', 1073 'じぃ'=>'jyi','じょ'=>'jyo','じゅ'=>'jyu','きゃ'=>'kya','きぇ'=>'kye','きぃ'=>'kyi', 1074 'きょ'=>'kyo','きゅ'=>'kyu','りゃ'=>'lya','りぇ'=>'lye','りぃ'=>'lyi','りょ'=>'lyo', 1075 'りゅ'=>'lyu','みゃ'=>'mya','みぇ'=>'mye','みぃ'=>'myi','みょ'=>'myo','みゅ'=>'myu', 1076 'ん'=>'n','にゃ'=>'nya','にぇ'=>'nye','にぃ'=>'nyi','にょ'=>'nyo','にゅ'=>'nyu', 1077 'ぴゃ'=>'pya','ぴぇ'=>'pye','ぴぃ'=>'pyi','ぴょ'=>'pyo','ぴゅ'=>'pyu','りゃ'=>'rya', 1078 'りぇ'=>'rye','りぃ'=>'ryi','りょ'=>'ryo','りゅ'=>'ryu','しゃ'=>'sha','しぇ'=>'she', 1079 'し'=>'shi','しょ'=>'sho','しゅ'=>'shu','すぁ'=>'swa','すぇ'=>'swe','すぃ'=>'swi', 1080 'すぉ'=>'swo','すぅ'=>'swu','しゃ'=>'sya','しぇ'=>'sye','しぃ'=>'syi','しょ'=>'syo', 1081 'しゅ'=>'syu','てゃ'=>'tha','てぇ'=>'the','てぃ'=>'thi','てょ'=>'tho','てゅ'=>'thu', 1082 'つゃ'=>'tsa','つぇ'=>'tse','つぃ'=>'tsi','つょ'=>'tso','つ'=>'tsu','とぁ'=>'twa', 1083 'とぇ'=>'twe','とぃ'=>'twi','とぉ'=>'two','とぅ'=>'twu','ちゃ'=>'tya','ちぇ'=>'tye', 1084 'ちぃ'=>'tyi','ちょ'=>'tyo','ちゅ'=>'tyu','ヴゃ'=>'vya','ヴぇ'=>'vye','ヴぃ'=>'vyi', 1085 'ヴょ'=>'vyo','ヴゅ'=>'vyu','うぁ'=>'wha','うぇ'=>'whe','うぃ'=>'whi','うぉ'=>'who', 1086 'うぅ'=>'whu','ゑ'=>'wye','ゐ'=>'wyi','じゃ'=>'zha','じぇ'=>'zhe','じぃ'=>'zhi', 1087 'じょ'=>'zho','じゅ'=>'zhu','じゃ'=>'zya','じぇ'=>'zye','じぃ'=>'zyi','じょ'=>'zyo', 1088 'じゅ'=>'zyu', 1089 // Japanese katakana 1090 'ア'=>'a','エ'=>'e','イ'=>'i','オ'=>'o','ウ'=>'u','バ'=>'ba','ベ'=>'be','ビ'=>'bi', 1091 'ボ'=>'bo','ブ'=>'bu','シ'=>'ci','ダ'=>'da','デ'=>'de','ヂ'=>'di','ド'=>'do', 1092 'ヅ'=>'du','ファ'=>'fa','フェ'=>'fe','フィ'=>'fi','フォ'=>'fo','フ'=>'fu','ガ'=>'ga', 1093 'ゲ'=>'ge','ギ'=>'gi','ゴ'=>'go','グ'=>'gu','ハ'=>'ha','ヘ'=>'he','ヒ'=>'hi','ホ'=>'ho', 1094 'フ'=>'hu','ジャ'=>'ja','ジェ'=>'je','ジ'=>'ji','ジョ'=>'jo','ジュ'=>'ju','カ'=>'ka', 1095 'ケ'=>'ke','キ'=>'ki','コ'=>'ko','ク'=>'ku','ラ'=>'la','レ'=>'le','リ'=>'li','ロ'=>'lo', 1096 'ル'=>'lu','マ'=>'ma','メ'=>'me','ミ'=>'mi','モ'=>'mo','ム'=>'mu','ナ'=>'na','ネ'=>'ne', 1097 'ニ'=>'ni','ノ'=>'no','ヌ'=>'nu','パ'=>'pa','ペ'=>'pe','ピ'=>'pi','ポ'=>'po','プ'=>'pu', 1098 'ラ'=>'ra','レ'=>'re','リ'=>'ri','ロ'=>'ro','ル'=>'ru','サ'=>'sa','セ'=>'se','シ'=>'si', 1099 'ソ'=>'so','ス'=>'su','タ'=>'ta','テ'=>'te','チ'=>'ti','ト'=>'to','ツ'=>'tu','ヴァ'=>'va', 1100 'ヴェ'=>'ve','ヴィ'=>'vi','ヴォ'=>'vo','ヴ'=>'vu','ワ'=>'wa','ウェ'=>'we','ウィ'=>'wi', 1101 'ヲ'=>'wo','ヤ'=>'ya','イェ'=>'ye','イ'=>'yi','ヨ'=>'yo','ユ'=>'yu','ザ'=>'za','ゼ'=>'ze', 1102 'ジ'=>'zi','ゾ'=>'zo','ズ'=>'zu','ビャ'=>'bya','ビェ'=>'bye','ビィ'=>'byi','ビョ'=>'byo', 1103 'ビュ'=>'byu','チャ'=>'cha','チェ'=>'che','チ'=>'chi','チョ'=>'cho','チュ'=>'chu', 1104 'チャ'=>'cya','チェ'=>'cye','チィ'=>'cyi','チョ'=>'cyo','チュ'=>'cyu','デャ'=>'dha', 1105 'デェ'=>'dhe','ディ'=>'dhi','デョ'=>'dho','デュ'=>'dhu','ドァ'=>'dwa','ドェ'=>'dwe', 1106 'ドィ'=>'dwi','ドォ'=>'dwo','ドゥ'=>'dwu','ヂャ'=>'dya','ヂェ'=>'dye','ヂィ'=>'dyi', 1107 'ヂョ'=>'dyo','ヂュ'=>'dyu','ヂ'=>'dzi','ファ'=>'fwa','フェ'=>'fwe','フィ'=>'fwi', 1108 'フォ'=>'fwo','フゥ'=>'fwu','フャ'=>'fya','フェ'=>'fye','フィ'=>'fyi','フョ'=>'fyo', 1109 'フュ'=>'fyu','ギャ'=>'gya','ギェ'=>'gye','ギィ'=>'gyi','ギョ'=>'gyo','ギュ'=>'gyu', 1110 'ヒャ'=>'hya','ヒェ'=>'hye','ヒィ'=>'hyi','ヒョ'=>'hyo','ヒュ'=>'hyu','ジャ'=>'jya', 1111 'ジェ'=>'jye','ジィ'=>'jyi','ジョ'=>'jyo','ジュ'=>'jyu','キャ'=>'kya','キェ'=>'kye', 1112 'キィ'=>'kyi','キョ'=>'kyo','キュ'=>'kyu','リャ'=>'lya','リェ'=>'lye','リィ'=>'lyi', 1113 'リョ'=>'lyo','リュ'=>'lyu','ミャ'=>'mya','ミェ'=>'mye','ミィ'=>'myi','ミョ'=>'myo', 1114 'ミュ'=>'myu','ン'=>'n','ニャ'=>'nya','ニェ'=>'nye','ニィ'=>'nyi','ニョ'=>'nyo', 1115 'ニュ'=>'nyu','ピャ'=>'pya','ピェ'=>'pye','ピィ'=>'pyi','ピョ'=>'pyo','ピュ'=>'pyu', 1116 'リャ'=>'rya','リェ'=>'rye','リィ'=>'ryi','リョ'=>'ryo','リュ'=>'ryu','シャ'=>'sha', 1117 'シェ'=>'she','シ'=>'shi','ショ'=>'sho','シュ'=>'shu','スァ'=>'swa','スェ'=>'swe', 1118 'スィ'=>'swi','スォ'=>'swo','スゥ'=>'swu','シャ'=>'sya','シェ'=>'sye','シィ'=>'syi', 1119 'ショ'=>'syo','シュ'=>'syu','テャ'=>'tha','テェ'=>'the','ティ'=>'thi','テョ'=>'tho', 1120 'テュ'=>'thu','ツャ'=>'tsa','ツェ'=>'tse','ツィ'=>'tsi','ツョ'=>'tso','ツ'=>'tsu', 1121 'トァ'=>'twa','トェ'=>'twe','トィ'=>'twi','トォ'=>'two','トゥ'=>'twu','チャ'=>'tya', 1122 'チェ'=>'tye','チィ'=>'tyi','チョ'=>'tyo','チュ'=>'tyu','ヴャ'=>'vya','ヴェ'=>'vye', 1123 'ヴィ'=>'vyi','ヴョ'=>'vyo','ヴュ'=>'vyu','ウァ'=>'wha','ウェ'=>'whe','ウィ'=>'whi', 1124 'ウォ'=>'who','ウゥ'=>'whu','ヱ'=>'wye','ヰ'=>'wyi','ジャ'=>'zha','ジェ'=>'zhe', 1125 'ジィ'=>'zhi','ジョ'=>'zho','ジュ'=>'zhu','ジャ'=>'zya','ジェ'=>'zye','ジィ'=>'zyi', 1126 'ジョ'=>'zyo','ジュ'=>'zyu', 1127 1128 // "Greeklish" 1129 'Γ'=>'G','Δ'=>'E','Θ'=>'Th','Λ'=>'L','Ξ'=>'X','Π'=>'P','Σ'=>'S','Φ'=>'F','Ψ'=>'Ps', 1130 'γ'=>'g','δ'=>'e','θ'=>'th','λ'=>'l','ξ'=>'x','π'=>'p','σ'=>'s','φ'=>'f','ψ'=>'ps', 1131 1132 // Thai 1133 'ก'=>'k','ข'=>'kh','ฃ'=>'kh','ค'=>'kh','ฅ'=>'kh','ฆ'=>'kh','ง'=>'ng','จ'=>'ch', 1134 'ฉ'=>'ch','ช'=>'ch','ซ'=>'s','ฌ'=>'ch','ญ'=>'y','ฎ'=>'d','ฏ'=>'t','ฐ'=>'th', 1135 'ฑ'=>'d','ฒ'=>'th','ณ'=>'n','ด'=>'d','ต'=>'t','ถ'=>'th','ท'=>'th','ธ'=>'th', 1136 'น'=>'n','บ'=>'b','ป'=>'p','ผ'=>'ph','ฝ'=>'f','พ'=>'ph','ฟ'=>'f','ภ'=>'ph', 1137 'ม'=>'m','ย'=>'y','ร'=>'r','ฤ'=>'rue','ฤๅ'=>'rue','ล'=>'l','ฦ'=>'lue', 1138 'ฦๅ'=>'lue','ว'=>'w','ศ'=>'s','ษ'=>'s','ส'=>'s','ห'=>'h','ฬ'=>'l','ฮ'=>'h', 1139 'ะ'=>'a','–ั'=>'a','รร'=>'a','า'=>'a','รร'=>'an','ำ'=>'am','–ิ'=>'i','–ี'=>'i', 1140 '–ึ'=>'ue','–ื'=>'ue','–ุ'=>'u','–ู'=>'u','เะ'=>'e','เ–็'=>'e','เ'=>'e','แะ'=>'ae', 1141 'แ'=>'ae','โะ'=>'o','โ'=>'o','เาะ'=>'o','อ'=>'o','เอะ'=>'oe','เ–ิ'=>'oe', 1142 'เอ'=>'oe','เ–ียะ'=>'ia','เ–ีย'=>'ia','เ–ือะ'=>'uea','เ–ือ'=>'uea','–ัวะ'=>'ua', 1143 '–ัว'=>'ua','ว'=>'ua','ใ'=>'ai','ไ'=>'ai','–ัย'=>'ai','ไย'=>'ai','าย'=>'ai', 1144 'เา'=>'ao','าว'=>'ao','–ุย'=>'ui','โย'=>'oi','อย'=>'oi','เย'=>'oei','เ–ือย'=>'ueai', 1145 'วย'=>'uai','–ิว'=>'io','เ–็ว'=>'eo','เว'=>'eo','แ–็ว'=>'aeo','แว'=>'aeo', 1146 'เ–ียว'=>'iao', 1147 1148 // Korean 1149 'ㄱ'=>'k','ㅋ'=>'kh','ㄲ'=>'kk','ㄷ'=>'t','ㅌ'=>'th','ㄸ'=>'tt','ㅂ'=>'p', 1150 'ㅍ'=>'ph','ㅃ'=>'pp','ㅈ'=>'c','ㅊ'=>'ch','ㅉ'=>'cc','ㅅ'=>'s','ㅆ'=>'ss', 1151 'ㅎ'=>'h','ㅇ'=>'ng','ㄴ'=>'n','ㄹ'=>'l','ㅁ'=>'m', 'ㅏ'=>'a','ㅓ'=>'e','ㅗ'=>'o', 1152 'ㅜ'=>'wu','ㅡ'=>'u','ㅣ'=>'i','ㅐ'=>'ay','ㅔ'=>'ey','ㅚ'=>'oy','ㅘ'=>'wa','ㅝ'=>'we', 1153 'ㅟ'=>'wi','ㅙ'=>'way','ㅞ'=>'wey','ㅢ'=>'uy','ㅑ'=>'ya','ㅕ'=>'ye','ㅛ'=>'oy', 1154 'ㅠ'=>'yu','ㅒ'=>'yay','ㅖ'=>'yey', 1155); 1156 1157//Setup VIM: ex: et ts=2 enc=utf-8 : 1158 1159