Unaccent a string - PHP Snipplr Social Repository

Revision: 57890

at June 13, 2012 20:40 by MGHollander

Updated Code

/**
 * Unaccent a string 
 *
 * An example string like Ã€Ã˜Ä—Ã¿á¾œá½¨Î¶á½…Ð‘ÑŽ will be translated to AOeyIOzoBY. 
 * More complete than :
 *
 *  strtr(
 *      (string)$str,
 *      "Ã€ÃÃ‚ÃƒÃ„Ã…Ã Ã¡Ã¢Ã£Ã¤Ã¥Ã’Ã“Ã”Ã•Ã–Ã˜Ã²Ã³Ã´ÃµÃ¶Ã¸ÃˆÃ‰ÃŠÃ‹Ã¨Ã©ÃªÃ«Ã‡Ã§ÃŒÃÃŽÃÃ¬ÃÃ®Ã¯Ã™ÃšÃ›ÃœÃ¹ÃºÃ»Ã¼Ã¿Ã‘Ã±",
 *      "aaaaaaaaaaaaooooooooooooeeeeeeeecciiiiiiiiuuuuuuuuynn"
 *  );
 *
 * @author http://www.evaisse.net/2008/php-translit-remove-accent-unaccent-21001
 * @param $str input string
 * @param $utf8 if null, function will detect input string encoding
 * @return string input string without accent
 */
function removeAccents($str, $utf8 = true) {
    $str = (string) $str;
    if (is_null($utf8)) {
        if (!function_exists('mb_detect_encoding')) {
            $utf8 = (strtolower(mb_detect_encoding($str)) == 'utf-8');
        } else {
            $length = strlen($str);
            $utf8 = true;
            
            for ($i = 0; $i < $length; $i++) {
                $c = ord($str[$i]);
                
                if ($c < 0x80) $n = 0; // 0bbbbbbb
                elseif (($c & 0xE0) == 0xC0) $n = 1; // 110bbbbb
                elseif (($c & 0xF0) == 0xE0) $n = 2; // 1110bbbb
                elseif (($c & 0xF8) == 0xF0) $n = 3; // 11110bbb
                elseif (($c & 0xFC) == 0xF8) $n = 4; // 111110bb
                elseif (($c & 0xFE) == 0xFC) $n = 5; // 1111110b
                else return false; // Does not match any model
                
                for ($j = 0; $j < $n; $j++) { // n bytes matching 10bbbbbb follow ?
                    if ((++$i == $length) || ((ord($str[$i]) & 0xC0) != 0x80)) {
                        $utf8 = false;
                        break;
                    }
                }
            }
        }
    }
    
    if (!$utf8) {
        $str = utf8_encode($str);
    }
    
    $transliteration = array(
        'Ä²' => 'I', 'Ã–' => 'O', 'Å’' => 'O', 'Ãœ' => 'U', 'Ã¤' => 'a', 'Ã¦' => 'a',
        'Ä³' => 'i', 'Ã¶' => 'o', 'Å“' => 'o', 'Ã¼' => 'u', 'ÃŸ' => 's', 'Å¿' => 's',
        'Ã€' => 'A', 'Ã' => 'A', 'Ã‚' => 'A', 'Ãƒ' => 'A', 'Ã„' => 'A', 'Ã…' => 'A',
        'Ã†' => 'A', 'Ä€' => 'A', 'Ä„' => 'A', 'Ä‚' => 'A', 'Ã‡' => 'C', 'Ä†' => 'C',
        'ÄŒ' => 'C', 'Äˆ' => 'C', 'ÄŠ' => 'C', 'ÄŽ' => 'D', 'Ä' => 'D', 'Ãˆ' => 'E',
        'Ã‰' => 'E', 'ÃŠ' => 'E', 'Ã‹' => 'E', 'Ä’' => 'E', 'Ä˜' => 'E', 'Äš' => 'E',
        'Ä”' => 'E', 'Ä–' => 'E', 'Äœ' => 'G', 'Äž' => 'G', 'Ä ' => 'G', 'Ä¢' => 'G',
        'Ä¤' => 'H', 'Ä¦' => 'H', 'ÃŒ' => 'I', 'Ã' => 'I', 'ÃŽ' => 'I', 'Ã' => 'I',
        'Äª' => 'I', 'Ä¨' => 'I', 'Ä¬' => 'I', 'Ä®' => 'I', 'Ä°' => 'I', 'Ä´' => 'J',
        'Ä¶' => 'K', 'Ä½' => 'K', 'Ä¹' => 'K', 'Ä»' => 'K', 'Ä¿' => 'K', 'Å' => 'L',
        'Ã‘' => 'N', 'Åƒ' => 'N', 'Å‡' => 'N', 'Å…' => 'N', 'ÅŠ' => 'N', 'Ã’' => 'O',
        'Ã“' => 'O', 'Ã”' => 'O', 'Ã•' => 'O', 'Ã˜' => 'O', 'ÅŒ' => 'O', 'Å' => 'O',
        'ÅŽ' => 'O', 'Å”' => 'R', 'Å˜' => 'R', 'Å–' => 'R', 'Åš' => 'S', 'Åž' => 'S',
        'Åœ' => 'S', 'È˜' => 'S', 'Å ' => 'S', 'Å¤' => 'T', 'Å¢' => 'T', 'Å¦' => 'T',
        'Èš' => 'T', 'Ã™' => 'U', 'Ãš' => 'U', 'Ã›' => 'U', 'Åª' => 'U', 'Å®' => 'U',
        'Å°' => 'U', 'Å¬' => 'U', 'Å¨' => 'U', 'Å²' => 'U', 'Å´' => 'W', 'Å¶' => 'Y',
        'Å¸' => 'Y', 'Ã' => 'Y', 'Å¹' => 'Z', 'Å»' => 'Z', 'Å½' => 'Z', 'Ã ' => 'a',
        'Ã¡' => 'a', 'Ã¢' => 'a', 'Ã£' => 'a', 'Ä' => 'a', 'Ä…' => 'a', 'Äƒ' => 'a',
        'Ã¥' => 'a', 'Ã§' => 'c', 'Ä‡' => 'c', 'Ä' => 'c', 'Ä‰' => 'c', 'Ä‹' => 'c',
        'Ä' => 'd', 'Ä‘' => 'd', 'Ã¨' => 'e', 'Ã©' => 'e', 'Ãª' => 'e', 'Ã«' => 'e',
        'Ä“' => 'e', 'Ä™' => 'e', 'Ä›' => 'e', 'Ä•' => 'e', 'Ä—' => 'e', 'Æ’' => 'f',
        'Ä' => 'g', 'ÄŸ' => 'g', 'Ä¡' => 'g', 'Ä£' => 'g', 'Ä¥' => 'h', 'Ä§' => 'h',
        'Ã¬' => 'i', 'Ã' => 'i', 'Ã®' => 'i', 'Ã¯' => 'i', 'Ä«' => 'i', 'Ä©' => 'i',
        'Ä' => 'i', 'Ä¯' => 'i', 'Ä±' => 'i', 'Äµ' => 'j', 'Ä·' => 'k', 'Ä¸' => 'k',
        'Å‚' => 'l', 'Ä¾' => 'l', 'Äº' => 'l', 'Ä¼' => 'l', 'Å€' => 'l', 'Ã±' => 'n',
        'Å„' => 'n', 'Åˆ' => 'n', 'Å†' => 'n', 'Å‰' => 'n', 'Å‹' => 'n', 'Ã²' => 'o',
        'Ã³' => 'o', 'Ã´' => 'o', 'Ãµ' => 'o', 'Ã¸' => 'o', 'Å' => 'o', 'Å‘' => 'o',
        'Å' => 'o', 'Å•' => 'r', 'Å™' => 'r', 'Å—' => 'r', 'Å›' => 's', 'Å¡' => 's',
        'Å¥' => 't', 'Ã¹' => 'u', 'Ãº' => 'u', 'Ã»' => 'u', 'Å«' => 'u', 'Å¯' => 'u',
        'Å±' => 'u', 'Å' => 'u', 'Å©' => 'u', 'Å³' => 'u', 'Åµ' => 'w', 'Ã¿' => 'y',
        'Ã½' => 'y', 'Å·' => 'y', 'Å¼' => 'z', 'Åº' => 'z', 'Å¾' => 'z', 'Î‘' => 'A',
        'Î†' => 'A', 'á¼ˆ' => 'A', 'á¼‰' => 'A', 'á¼Š' => 'A', 'á¼‹' => 'A', 'á¼Œ' => 'A',
        'á¼' => 'A', 'á¼Ž' => 'A', 'á¼' => 'A', 'á¾ˆ' => 'A', 'á¾‰' => 'A', 'á¾Š' => 'A',
        'á¾‹' => 'A', 'á¾Œ' => 'A', 'á¾' => 'A', 'á¾Ž' => 'A', 'á¾' => 'A', 'á¾¸' => 'A',
        'á¾¹' => 'A', 'á¾º' => 'A', 'á¾¼' => 'A', 'Î’' => 'B', 'Î“' => 'G', 'Î”' => 'D',
        'Î•' => 'E', 'Îˆ' => 'E', 'á¼˜' => 'E', 'á¼™' => 'E', 'á¼š' => 'E', 'á¼›' => 'E',
        'á¼œ' => 'E', 'á¼' => 'E', 'á¿ˆ' => 'E', 'Î–' => 'Z', 'Î—' => 'I', 'Î‰' => 'I',
        'á¼¨' => 'I', 'á¼©' => 'I', 'á¼ª' => 'I', 'á¼«' => 'I', 'á¼¬' => 'I', 'á¼' => 'I',
        'á¼®' => 'I', 'á¼¯' => 'I', 'á¾˜' => 'I', 'á¾™' => 'I', 'á¾š' => 'I', 'á¾›' => 'I',
        'á¾œ' => 'I', 'á¾' => 'I', 'á¾ž' => 'I', 'á¾Ÿ' => 'I', 'á¿Š' => 'I', 'á¿Œ' => 'I',
        'Î˜' => 'T', 'Î™' => 'I', 'ÎŠ' => 'I', 'Îª' => 'I', 'á¼¸' => 'I', 'á¼¹' => 'I',
        'á¼º' => 'I', 'á¼»' => 'I', 'á¼¼' => 'I', 'á¼½' => 'I', 'á¼¾' => 'I', 'á¼¿' => 'I',
        'á¿˜' => 'I', 'á¿™' => 'I', 'á¿š' => 'I', 'Îš' => 'K', 'Î›' => 'L', 'Îœ' => 'M',
        'Î' => 'N', 'Îž' => 'K', 'ÎŸ' => 'O', 'ÎŒ' => 'O', 'á½ˆ' => 'O', 'á½‰' => 'O',
        'á½Š' => 'O', 'á½‹' => 'O', 'á½Œ' => 'O', 'á½' => 'O', 'á¿¸' => 'O', 'Î ' => 'P',
        'Î¡' => 'R', 'á¿¬' => 'R', 'Î£' => 'S', 'Î¤' => 'T', 'Î¥' => 'Y', 'ÎŽ' => 'Y',
        'Î«' => 'Y', 'á½™' => 'Y', 'á½›' => 'Y', 'á½' => 'Y', 'á½Ÿ' => 'Y', 'á¿¨' => 'Y',
        'á¿©' => 'Y', 'á¿ª' => 'Y', 'Î¦' => 'F', 'Î§' => 'X', 'Î¨' => 'P', 'Î©' => 'O',
        'Î' => 'O', 'á½¨' => 'O', 'á½©' => 'O', 'á½ª' => 'O', 'á½«' => 'O', 'á½¬' => 'O',
        'á½' => 'O', 'á½®' => 'O', 'á½¯' => 'O', 'á¾¨' => 'O', 'á¾©' => 'O', 'á¾ª' => 'O',
        'á¾«' => 'O', 'á¾¬' => 'O', 'á¾' => 'O', 'á¾®' => 'O', 'á¾¯' => 'O', 'á¿º' => 'O',
        'á¿¼' => 'O', 'Î±' => 'a', 'Î¬' => 'a', 'á¼€' => 'a', 'á¼' => 'a', 'á¼‚' => 'a',
        'á¼ƒ' => 'a', 'á¼„' => 'a', 'á¼…' => 'a', 'á¼†' => 'a', 'á¼‡' => 'a', 'á¾€' => 'a',
        'á¾' => 'a', 'á¾‚' => 'a', 'á¾ƒ' => 'a', 'á¾„' => 'a', 'á¾…' => 'a', 'á¾†' => 'a',
        'á¾‡' => 'a', 'á½°' => 'a', 'á¾°' => 'a', 'á¾±' => 'a', 'á¾²' => 'a', 'á¾³' => 'a',
        'á¾´' => 'a', 'á¾¶' => 'a', 'á¾·' => 'a', 'Î²' => 'b', 'Î³' => 'g', 'Î´' => 'd',
        'Îµ' => 'e', 'Î' => 'e', 'á¼' => 'e', 'á¼‘' => 'e', 'á¼’' => 'e', 'á¼“' => 'e',
        'á¼”' => 'e', 'á¼•' => 'e', 'á½²' => 'e', 'Î¶' => 'z', 'Î·' => 'i', 'Î®' => 'i',
        'á¼ ' => 'i', 'á¼¡' => 'i', 'á¼¢' => 'i', 'á¼£' => 'i', 'á¼¤' => 'i', 'á¼¥' => 'i',
        'á¼¦' => 'i', 'á¼§' => 'i', 'á¾' => 'i', 'á¾‘' => 'i', 'á¾’' => 'i', 'á¾“' => 'i',
        'á¾”' => 'i', 'á¾•' => 'i', 'á¾–' => 'i', 'á¾—' => 'i', 'á½´' => 'i', 'á¿‚' => 'i',
        'á¿ƒ' => 'i', 'á¿„' => 'i', 'á¿†' => 'i', 'á¿‡' => 'i', 'Î¸' => 't', 'Î¹' => 'i',
        'Î¯' => 'i', 'ÏŠ' => 'i', 'Î' => 'i', 'á¼°' => 'i', 'á¼±' => 'i', 'á¼²' => 'i',
        'á¼³' => 'i', 'á¼´' => 'i', 'á¼µ' => 'i', 'á¼¶' => 'i', 'á¼·' => 'i', 'á½¶' => 'i',
        'á¿' => 'i', 'á¿‘' => 'i', 'á¿’' => 'i', 'á¿–' => 'i', 'á¿—' => 'i', 'Îº' => 'k',
        'Î»' => 'l', 'Î¼' => 'm', 'Î½' => 'n', 'Î¾' => 'k', 'Î¿' => 'o', 'ÏŒ' => 'o',
        'á½€' => 'o', 'á½' => 'o', 'á½‚' => 'o', 'á½ƒ' => 'o', 'á½„' => 'o', 'á½…' => 'o',
        'á½¸' => 'o', 'Ï€' => 'p', 'Ï' => 'r', 'á¿¤' => 'r', 'á¿¥' => 'r', 'Ïƒ' => 's',
        'Ï‚' => 's', 'Ï„' => 't', 'Ï…' => 'y', 'Ï' => 'y', 'Ï‹' => 'y', 'Î°' => 'y',
        'á½' => 'y', 'á½‘' => 'y', 'á½’' => 'y', 'á½“' => 'y', 'á½”' => 'y', 'á½•' => 'y',
        'á½–' => 'y', 'á½—' => 'y', 'á½º' => 'y', 'á¿ ' => 'y', 'á¿¡' => 'y', 'á¿¢' => 'y',
        'á¿¦' => 'y', 'á¿§' => 'y', 'Ï†' => 'f', 'Ï‡' => 'x', 'Ïˆ' => 'p', 'Ï‰' => 'o',
        'ÏŽ' => 'o', 'á½ ' => 'o', 'á½¡' => 'o', 'á½¢' => 'o', 'á½£' => 'o', 'á½¤' => 'o',
        'á½¥' => 'o', 'á½¦' => 'o', 'á½§' => 'o', 'á¾ ' => 'o', 'á¾¡' => 'o', 'á¾¢' => 'o',
        'á¾£' => 'o', 'á¾¤' => 'o', 'á¾¥' => 'o', 'á¾¦' => 'o', 'á¾§' => 'o', 'á½¼' => 'o',
        'á¿²' => 'o', 'á¿³' => 'o', 'á¿´' => 'o', 'á¿¶' => 'o', 'á¿·' => 'o', 'Ð' => 'A',
        'Ð‘' => 'B', 'Ð’' => 'V', 'Ð“' => 'G', 'Ð”' => 'D', 'Ð•' => 'E', 'Ð' => 'E',
        'Ð–' => 'Z', 'Ð—' => 'Z', 'Ð˜' => 'I', 'Ð™' => 'I', 'Ðš' => 'K', 'Ð›' => 'L',
        'Ðœ' => 'M', 'Ð' => 'N', 'Ðž' => 'O', 'ÐŸ' => 'P', 'Ð ' => 'R', 'Ð¡' => 'S',
        'Ð¢' => 'T', 'Ð£' => 'U', 'Ð¤' => 'F', 'Ð¥' => 'K', 'Ð¦' => 'T', 'Ð§' => 'C',
        'Ð¨' => 'S', 'Ð©' => 'S', 'Ð«' => 'Y', 'Ð' => 'E', 'Ð®' => 'Y', 'Ð¯' => 'Y',
        'Ð°' => 'A', 'Ð±' => 'B', 'Ð²' => 'V', 'Ð³' => 'G', 'Ð´' => 'D', 'Ðµ' => 'E',
        'Ñ‘' => 'E', 'Ð¶' => 'Z', 'Ð·' => 'Z', 'Ð¸' => 'I', 'Ð¹' => 'I', 'Ðº' => 'K',
        'Ð»' => 'L', 'Ð¼' => 'M', 'Ð½' => 'N', 'Ð¾' => 'O', 'Ð¿' => 'P', 'Ñ€' => 'R',
        'Ñ' => 'S', 'Ñ‚' => 'T', 'Ñƒ' => 'U', 'Ñ„' => 'F', 'Ñ…' => 'K', 'Ñ†' => 'T',
        'Ñ‡' => 'C', 'Ñˆ' => 'S', 'Ñ‰' => 'S', 'Ñ‹' => 'Y', 'Ñ' => 'E', 'ÑŽ' => 'Y',
        'Ñ' => 'Y', 'Ã°' => 'd', 'Ã' => 'D', 'Ã¾' => 't', 'Ãž' => 'T', 'áƒ' => 'a',
        'áƒ‘' => 'b', 'áƒ’' => 'g', 'áƒ“' => 'd', 'áƒ”' => 'e', 'áƒ•' => 'v', 'áƒ–' => 'z',
        'áƒ—' => 't', 'áƒ˜' => 'i', 'áƒ™' => 'k', 'áƒš' => 'l', 'áƒ›' => 'm', 'áƒœ' => 'n',
        'áƒ' => 'o', 'áƒž' => 'p', 'áƒŸ' => 'z', 'áƒ ' => 'r', 'áƒ¡' => 's', 'áƒ¢' => 't',
        'áƒ£' => 'u', 'áƒ¤' => 'p', 'áƒ¥' => 'k', 'áƒ¦' => 'g', 'áƒ§' => 'q', 'áƒ¨' => 's',
        'áƒ©' => 'c', 'áƒª' => 't', 'áƒ«' => 'd', 'áƒ¬' => 't', 'áƒ' => 'c', 'áƒ®' => 'k',
        'áƒ¯' => 'j', 'áƒ°' => 'h',
    );
    
    return str_replace(array_keys($transliteration), array_values($transliteration), $str);
}

Revision: 57889

at June 13, 2012 20:37 by MGHollander

Updated Code

<?php

/**
 * Unaccent a string 
 *
 * An example string like Ã€Ã˜Ä—Ã¿á¾œá½¨Î¶á½…Ð‘ÑŽ will be translated to AOeyIOzoBY. 
 * More complete than :
 *
 *  strtr(
 *      (string)$str,
 *      "Ã€ÃÃ‚ÃƒÃ„Ã…Ã Ã¡Ã¢Ã£Ã¤Ã¥Ã’Ã“Ã”Ã•Ã–Ã˜Ã²Ã³Ã´ÃµÃ¶Ã¸ÃˆÃ‰ÃŠÃ‹Ã¨Ã©ÃªÃ«Ã‡Ã§ÃŒÃÃŽÃÃ¬ÃÃ®Ã¯Ã™ÃšÃ›ÃœÃ¹ÃºÃ»Ã¼Ã¿Ã‘Ã±",
 *      "aaaaaaaaaaaaooooooooooooeeeeeeeecciiiiiiiiuuuuuuuuynn"
 *  );
 *
 * @author http://www.evaisse.net/2008/php-translit-remove-accent-unaccent-21001
 * @param $str input string
 * @param $utf8 if null, function will detect input string encoding
 * @return string input string without accent
 */
function removeAccents($str, $utf8 = true) {
    $str = (string) $str;
    if (is_null($utf8)) {
        if (!function_exists('mb_detect_encoding')) {
            $utf8 = (strtolower(mb_detect_encoding($str)) == 'utf-8');
        } else {
            $length = strlen($str);
            $utf8 = true;
            
            for ($i = 0; $i < $length; $i++) {
                $c = ord($str[$i]);
                
                if ($c < 0x80) $n = 0; // 0bbbbbbb
                elseif (($c & 0xE0) == 0xC0) $n = 1; // 110bbbbb
                elseif (($c & 0xF0) == 0xE0) $n = 2; // 1110bbbb
                elseif (($c & 0xF8) == 0xF0) $n = 3; // 11110bbb
                elseif (($c & 0xFC) == 0xF8) $n = 4; // 111110bb
                elseif (($c & 0xFE) == 0xFC) $n = 5; // 1111110b
                else return false; // Does not match any model
                
                for ($j = 0; $j < $n; $j++) { // n bytes matching 10bbbbbb follow ?
                    if ((++$i == $length) || ((ord($str[$i]) & 0xC0) != 0x80)) {
                        $utf8 = false;
                        break;
                    }
                }
            }
        }
    }
    
    if (!$utf8) {
        $str = utf8_encode($str);
    }
    
    $transliteration = array(
        'Ä²' => 'I', 'Ã–' => 'O', 'Å’' => 'O', 'Ãœ' => 'U', 'Ã¤' => 'a', 'Ã¦' => 'a',
        'Ä³' => 'i', 'Ã¶' => 'o', 'Å“' => 'o', 'Ã¼' => 'u', 'ÃŸ' => 's', 'Å¿' => 's',
        'Ã€' => 'A', 'Ã' => 'A', 'Ã‚' => 'A', 'Ãƒ' => 'A', 'Ã„' => 'A', 'Ã…' => 'A',
        'Ã†' => 'A', 'Ä€' => 'A', 'Ä„' => 'A', 'Ä‚' => 'A', 'Ã‡' => 'C', 'Ä†' => 'C',
        'ÄŒ' => 'C', 'Äˆ' => 'C', 'ÄŠ' => 'C', 'ÄŽ' => 'D', 'Ä' => 'D', 'Ãˆ' => 'E',
        'Ã‰' => 'E', 'ÃŠ' => 'E', 'Ã‹' => 'E', 'Ä’' => 'E', 'Ä˜' => 'E', 'Äš' => 'E',
        'Ä”' => 'E', 'Ä–' => 'E', 'Äœ' => 'G', 'Äž' => 'G', 'Ä ' => 'G', 'Ä¢' => 'G',
        'Ä¤' => 'H', 'Ä¦' => 'H', 'ÃŒ' => 'I', 'Ã' => 'I', 'ÃŽ' => 'I', 'Ã' => 'I',
        'Äª' => 'I', 'Ä¨' => 'I', 'Ä¬' => 'I', 'Ä®' => 'I', 'Ä°' => 'I', 'Ä´' => 'J',
        'Ä¶' => 'K', 'Ä½' => 'K', 'Ä¹' => 'K', 'Ä»' => 'K', 'Ä¿' => 'K', 'Å' => 'L',
        'Ã‘' => 'N', 'Åƒ' => 'N', 'Å‡' => 'N', 'Å…' => 'N', 'ÅŠ' => 'N', 'Ã’' => 'O',
        'Ã“' => 'O', 'Ã”' => 'O', 'Ã•' => 'O', 'Ã˜' => 'O', 'ÅŒ' => 'O', 'Å' => 'O',
        'ÅŽ' => 'O', 'Å”' => 'R', 'Å˜' => 'R', 'Å–' => 'R', 'Åš' => 'S', 'Åž' => 'S',
        'Åœ' => 'S', 'È˜' => 'S', 'Å ' => 'S', 'Å¤' => 'T', 'Å¢' => 'T', 'Å¦' => 'T',
        'Èš' => 'T', 'Ã™' => 'U', 'Ãš' => 'U', 'Ã›' => 'U', 'Åª' => 'U', 'Å®' => 'U',
        'Å°' => 'U', 'Å¬' => 'U', 'Å¨' => 'U', 'Å²' => 'U', 'Å´' => 'W', 'Å¶' => 'Y',
        'Å¸' => 'Y', 'Ã' => 'Y', 'Å¹' => 'Z', 'Å»' => 'Z', 'Å½' => 'Z', 'Ã ' => 'a',
        'Ã¡' => 'a', 'Ã¢' => 'a', 'Ã£' => 'a', 'Ä' => 'a', 'Ä…' => 'a', 'Äƒ' => 'a',
        'Ã¥' => 'a', 'Ã§' => 'c', 'Ä‡' => 'c', 'Ä' => 'c', 'Ä‰' => 'c', 'Ä‹' => 'c',
        'Ä' => 'd', 'Ä‘' => 'd', 'Ã¨' => 'e', 'Ã©' => 'e', 'Ãª' => 'e', 'Ã«' => 'e',
        'Ä“' => 'e', 'Ä™' => 'e', 'Ä›' => 'e', 'Ä•' => 'e', 'Ä—' => 'e', 'Æ’' => 'f',
        'Ä' => 'g', 'ÄŸ' => 'g', 'Ä¡' => 'g', 'Ä£' => 'g', 'Ä¥' => 'h', 'Ä§' => 'h',
        'Ã¬' => 'i', 'Ã' => 'i', 'Ã®' => 'i', 'Ã¯' => 'i', 'Ä«' => 'i', 'Ä©' => 'i',
        'Ä' => 'i', 'Ä¯' => 'i', 'Ä±' => 'i', 'Äµ' => 'j', 'Ä·' => 'k', 'Ä¸' => 'k',
        'Å‚' => 'l', 'Ä¾' => 'l', 'Äº' => 'l', 'Ä¼' => 'l', 'Å€' => 'l', 'Ã±' => 'n',
        'Å„' => 'n', 'Åˆ' => 'n', 'Å†' => 'n', 'Å‰' => 'n', 'Å‹' => 'n', 'Ã²' => 'o',
        'Ã³' => 'o', 'Ã´' => 'o', 'Ãµ' => 'o', 'Ã¸' => 'o', 'Å' => 'o', 'Å‘' => 'o',
        'Å' => 'o', 'Å•' => 'r', 'Å™' => 'r', 'Å—' => 'r', 'Å›' => 's', 'Å¡' => 's',
        'Å¥' => 't', 'Ã¹' => 'u', 'Ãº' => 'u', 'Ã»' => 'u', 'Å«' => 'u', 'Å¯' => 'u',
        'Å±' => 'u', 'Å' => 'u', 'Å©' => 'u', 'Å³' => 'u', 'Åµ' => 'w', 'Ã¿' => 'y',
        'Ã½' => 'y', 'Å·' => 'y', 'Å¼' => 'z', 'Åº' => 'z', 'Å¾' => 'z', 'Î‘' => 'A',
        'Î†' => 'A', 'á¼ˆ' => 'A', 'á¼‰' => 'A', 'á¼Š' => 'A', 'á¼‹' => 'A', 'á¼Œ' => 'A',
        'á¼' => 'A', 'á¼Ž' => 'A', 'á¼' => 'A', 'á¾ˆ' => 'A', 'á¾‰' => 'A', 'á¾Š' => 'A',
        'á¾‹' => 'A', 'á¾Œ' => 'A', 'á¾' => 'A', 'á¾Ž' => 'A', 'á¾' => 'A', 'á¾¸' => 'A',
        'á¾¹' => 'A', 'á¾º' => 'A', 'á¾¼' => 'A', 'Î’' => 'B', 'Î“' => 'G', 'Î”' => 'D',
        'Î•' => 'E', 'Îˆ' => 'E', 'á¼˜' => 'E', 'á¼™' => 'E', 'á¼š' => 'E', 'á¼›' => 'E',
        'á¼œ' => 'E', 'á¼' => 'E', 'á¿ˆ' => 'E', 'Î–' => 'Z', 'Î—' => 'I', 'Î‰' => 'I',
        'á¼¨' => 'I', 'á¼©' => 'I', 'á¼ª' => 'I', 'á¼«' => 'I', 'á¼¬' => 'I', 'á¼' => 'I',
        'á¼®' => 'I', 'á¼¯' => 'I', 'á¾˜' => 'I', 'á¾™' => 'I', 'á¾š' => 'I', 'á¾›' => 'I',
        'á¾œ' => 'I', 'á¾' => 'I', 'á¾ž' => 'I', 'á¾Ÿ' => 'I', 'á¿Š' => 'I', 'á¿Œ' => 'I',
        'Î˜' => 'T', 'Î™' => 'I', 'ÎŠ' => 'I', 'Îª' => 'I', 'á¼¸' => 'I', 'á¼¹' => 'I',
        'á¼º' => 'I', 'á¼»' => 'I', 'á¼¼' => 'I', 'á¼½' => 'I', 'á¼¾' => 'I', 'á¼¿' => 'I',
        'á¿˜' => 'I', 'á¿™' => 'I', 'á¿š' => 'I', 'Îš' => 'K', 'Î›' => 'L', 'Îœ' => 'M',
        'Î' => 'N', 'Îž' => 'K', 'ÎŸ' => 'O', 'ÎŒ' => 'O', 'á½ˆ' => 'O', 'á½‰' => 'O',
        'á½Š' => 'O', 'á½‹' => 'O', 'á½Œ' => 'O', 'á½' => 'O', 'á¿¸' => 'O', 'Î ' => 'P',
        'Î¡' => 'R', 'á¿¬' => 'R', 'Î£' => 'S', 'Î¤' => 'T', 'Î¥' => 'Y', 'ÎŽ' => 'Y',
        'Î«' => 'Y', 'á½™' => 'Y', 'á½›' => 'Y', 'á½' => 'Y', 'á½Ÿ' => 'Y', 'á¿¨' => 'Y',
        'á¿©' => 'Y', 'á¿ª' => 'Y', 'Î¦' => 'F', 'Î§' => 'X', 'Î¨' => 'P', 'Î©' => 'O',
        'Î' => 'O', 'á½¨' => 'O', 'á½©' => 'O', 'á½ª' => 'O', 'á½«' => 'O', 'á½¬' => 'O',
        'á½' => 'O', 'á½®' => 'O', 'á½¯' => 'O', 'á¾¨' => 'O', 'á¾©' => 'O', 'á¾ª' => 'O',
        'á¾«' => 'O', 'á¾¬' => 'O', 'á¾' => 'O', 'á¾®' => 'O', 'á¾¯' => 'O', 'á¿º' => 'O',
        'á¿¼' => 'O', 'Î±' => 'a', 'Î¬' => 'a', 'á¼€' => 'a', 'á¼' => 'a', 'á¼‚' => 'a',
        'á¼ƒ' => 'a', 'á¼„' => 'a', 'á¼…' => 'a', 'á¼†' => 'a', 'á¼‡' => 'a', 'á¾€' => 'a',
        'á¾' => 'a', 'á¾‚' => 'a', 'á¾ƒ' => 'a', 'á¾„' => 'a', 'á¾…' => 'a', 'á¾†' => 'a',
        'á¾‡' => 'a', 'á½°' => 'a', 'á¾°' => 'a', 'á¾±' => 'a', 'á¾²' => 'a', 'á¾³' => 'a',
        'á¾´' => 'a', 'á¾¶' => 'a', 'á¾·' => 'a', 'Î²' => 'b', 'Î³' => 'g', 'Î´' => 'd',
        'Îµ' => 'e', 'Î' => 'e', 'á¼' => 'e', 'á¼‘' => 'e', 'á¼’' => 'e', 'á¼“' => 'e',
        'á¼”' => 'e', 'á¼•' => 'e', 'á½²' => 'e', 'Î¶' => 'z', 'Î·' => 'i', 'Î®' => 'i',
        'á¼ ' => 'i', 'á¼¡' => 'i', 'á¼¢' => 'i', 'á¼£' => 'i', 'á¼¤' => 'i', 'á¼¥' => 'i',
        'á¼¦' => 'i', 'á¼§' => 'i', 'á¾' => 'i', 'á¾‘' => 'i', 'á¾’' => 'i', 'á¾“' => 'i',
        'á¾”' => 'i', 'á¾•' => 'i', 'á¾–' => 'i', 'á¾—' => 'i', 'á½´' => 'i', 'á¿‚' => 'i',
        'á¿ƒ' => 'i', 'á¿„' => 'i', 'á¿†' => 'i', 'á¿‡' => 'i', 'Î¸' => 't', 'Î¹' => 'i',
        'Î¯' => 'i', 'ÏŠ' => 'i', 'Î' => 'i', 'á¼°' => 'i', 'á¼±' => 'i', 'á¼²' => 'i',
        'á¼³' => 'i', 'á¼´' => 'i', 'á¼µ' => 'i', 'á¼¶' => 'i', 'á¼·' => 'i', 'á½¶' => 'i',
        'á¿' => 'i', 'á¿‘' => 'i', 'á¿’' => 'i', 'á¿–' => 'i', 'á¿—' => 'i', 'Îº' => 'k',
        'Î»' => 'l', 'Î¼' => 'm', 'Î½' => 'n', 'Î¾' => 'k', 'Î¿' => 'o', 'ÏŒ' => 'o',
        'á½€' => 'o', 'á½' => 'o', 'á½‚' => 'o', 'á½ƒ' => 'o', 'á½„' => 'o', 'á½…' => 'o',
        'á½¸' => 'o', 'Ï€' => 'p', 'Ï' => 'r', 'á¿¤' => 'r', 'á¿¥' => 'r', 'Ïƒ' => 's',
        'Ï‚' => 's', 'Ï„' => 't', 'Ï…' => 'y', 'Ï' => 'y', 'Ï‹' => 'y', 'Î°' => 'y',
        'á½' => 'y', 'á½‘' => 'y', 'á½’' => 'y', 'á½“' => 'y', 'á½”' => 'y', 'á½•' => 'y',
        'á½–' => 'y', 'á½—' => 'y', 'á½º' => 'y', 'á¿ ' => 'y', 'á¿¡' => 'y', 'á¿¢' => 'y',
        'á¿¦' => 'y', 'á¿§' => 'y', 'Ï†' => 'f', 'Ï‡' => 'x', 'Ïˆ' => 'p', 'Ï‰' => 'o',
        'ÏŽ' => 'o', 'á½ ' => 'o', 'á½¡' => 'o', 'á½¢' => 'o', 'á½£' => 'o', 'á½¤' => 'o',
        'á½¥' => 'o', 'á½¦' => 'o', 'á½§' => 'o', 'á¾ ' => 'o', 'á¾¡' => 'o', 'á¾¢' => 'o',
        'á¾£' => 'o', 'á¾¤' => 'o', 'á¾¥' => 'o', 'á¾¦' => 'o', 'á¾§' => 'o', 'á½¼' => 'o',
        'á¿²' => 'o', 'á¿³' => 'o', 'á¿´' => 'o', 'á¿¶' => 'o', 'á¿·' => 'o', 'Ð' => 'A',
        'Ð‘' => 'B', 'Ð’' => 'V', 'Ð“' => 'G', 'Ð”' => 'D', 'Ð•' => 'E', 'Ð' => 'E',
        'Ð–' => 'Z', 'Ð—' => 'Z', 'Ð˜' => 'I', 'Ð™' => 'I', 'Ðš' => 'K', 'Ð›' => 'L',
        'Ðœ' => 'M', 'Ð' => 'N', 'Ðž' => 'O', 'ÐŸ' => 'P', 'Ð ' => 'R', 'Ð¡' => 'S',
        'Ð¢' => 'T', 'Ð£' => 'U', 'Ð¤' => 'F', 'Ð¥' => 'K', 'Ð¦' => 'T', 'Ð§' => 'C',
        'Ð¨' => 'S', 'Ð©' => 'S', 'Ð«' => 'Y', 'Ð' => 'E', 'Ð®' => 'Y', 'Ð¯' => 'Y',
        'Ð°' => 'A', 'Ð±' => 'B', 'Ð²' => 'V', 'Ð³' => 'G', 'Ð´' => 'D', 'Ðµ' => 'E',
        'Ñ‘' => 'E', 'Ð¶' => 'Z', 'Ð·' => 'Z', 'Ð¸' => 'I', 'Ð¹' => 'I', 'Ðº' => 'K',
        'Ð»' => 'L', 'Ð¼' => 'M', 'Ð½' => 'N', 'Ð¾' => 'O', 'Ð¿' => 'P', 'Ñ€' => 'R',
        'Ñ' => 'S', 'Ñ‚' => 'T', 'Ñƒ' => 'U', 'Ñ„' => 'F', 'Ñ…' => 'K', 'Ñ†' => 'T',
        'Ñ‡' => 'C', 'Ñˆ' => 'S', 'Ñ‰' => 'S', 'Ñ‹' => 'Y', 'Ñ' => 'E', 'ÑŽ' => 'Y',
        'Ñ' => 'Y', 'Ã°' => 'd', 'Ã' => 'D', 'Ã¾' => 't', 'Ãž' => 'T', 'áƒ' => 'a',
        'áƒ‘' => 'b', 'áƒ’' => 'g', 'áƒ“' => 'd', 'áƒ”' => 'e', 'áƒ•' => 'v', 'áƒ–' => 'z',
        'áƒ—' => 't', 'áƒ˜' => 'i', 'áƒ™' => 'k', 'áƒš' => 'l', 'áƒ›' => 'm', 'áƒœ' => 'n',
        'áƒ' => 'o', 'áƒž' => 'p', 'áƒŸ' => 'z', 'áƒ ' => 'r', 'áƒ¡' => 's', 'áƒ¢' => 't',
        'áƒ£' => 'u', 'áƒ¤' => 'p', 'áƒ¥' => 'k', 'áƒ¦' => 'g', 'áƒ§' => 'q', 'áƒ¨' => 's',
        'áƒ©' => 'c', 'áƒª' => 't', 'áƒ«' => 'd', 'áƒ¬' => 't', 'áƒ' => 'c', 'áƒ®' => 'k',
        'áƒ¯' => 'j', 'áƒ°' => 'h',
    );
    
    return str_replace(array_keys($transliteration), array_values($transliteration), $str);
}

Revision: 57888

at June 13, 2012 20:36 by MGHollander

Updated Code

<?php

/**
 * Unaccent a string 
 *
 * An example string like Ã€Ã˜Ä—Ã¿á¾œá½¨Î¶á½…Ð‘ÑŽ will be translated to AOeyIOzoBY. 
 * More complete than :
 *
 *  strtr(
 *      (string)$str,
 *      "Ã€ÃÃ‚ÃƒÃ„Ã…Ã Ã¡Ã¢Ã£Ã¤Ã¥Ã’Ã“Ã”Ã•Ã–Ã˜Ã²Ã³Ã´ÃµÃ¶Ã¸ÃˆÃ‰ÃŠÃ‹Ã¨Ã©ÃªÃ«Ã‡Ã§ÃŒÃÃŽÃÃ¬ÃÃ®Ã¯Ã™ÃšÃ›ÃœÃ¹ÃºÃ»Ã¼Ã¿Ã‘Ã±",
 *      "aaaaaaaaaaaaooooooooooooeeeeeeeecciiiiiiiiuuuuuuuuynn"
 *  );
 *
 * @author http://www.evaisse.net/2008/php-translit-remove-accent-unaccent-21001
 * @param $str input string
 * @param $utf8 if null, function will detect input string encoding
 * @return string input string without accent
 */
function remove_accents($str, $utf8 = true) {
    $str = (string) $str;
    if (is_null($utf8)) {
        if (!function_exists('mb_detect_encoding')) {
            $utf8 = (strtolower(mb_detect_encoding($str)) == 'utf-8');
        } else {
            $length = strlen($str);
            $utf8 = true;
            
            for ($i = 0; $i < $length; $i++) {
                $c = ord($str[$i]);
                
                if ($c < 0x80) $n = 0; // 0bbbbbbb
                elseif (($c & 0xE0) == 0xC0) $n = 1; // 110bbbbb
                elseif (($c & 0xF0) == 0xE0) $n = 2; // 1110bbbb
                elseif (($c & 0xF8) == 0xF0) $n = 3; // 11110bbb
                elseif (($c & 0xFC) == 0xF8) $n = 4; // 111110bb
                elseif (($c & 0xFE) == 0xFC) $n = 5; // 1111110b
                else return false; // Does not match any model
                
                for ($j = 0; $j < $n; $j++) { // n bytes matching 10bbbbbb follow ?
                    if ((++$i == $length) || ((ord($str[$i]) & 0xC0) != 0x80)) {
                        $utf8 = false;
                        break;
                    }
                }
            }
        }
    }
    
    if (!$utf8) {
        $str = utf8_encode($str);
    }
    
    $transliteration = array(
        'Ä²' => 'I', 'Ã–' => 'O', 'Å’' => 'O', 'Ãœ' => 'U', 'Ã¤' => 'a', 'Ã¦' => 'a',
        'Ä³' => 'i', 'Ã¶' => 'o', 'Å“' => 'o', 'Ã¼' => 'u', 'ÃŸ' => 's', 'Å¿' => 's',
        'Ã€' => 'A', 'Ã' => 'A', 'Ã‚' => 'A', 'Ãƒ' => 'A', 'Ã„' => 'A', 'Ã…' => 'A',
        'Ã†' => 'A', 'Ä€' => 'A', 'Ä„' => 'A', 'Ä‚' => 'A', 'Ã‡' => 'C', 'Ä†' => 'C',
        'ÄŒ' => 'C', 'Äˆ' => 'C', 'ÄŠ' => 'C', 'ÄŽ' => 'D', 'Ä' => 'D', 'Ãˆ' => 'E',
        'Ã‰' => 'E', 'ÃŠ' => 'E', 'Ã‹' => 'E', 'Ä’' => 'E', 'Ä˜' => 'E', 'Äš' => 'E',
        'Ä”' => 'E', 'Ä–' => 'E', 'Äœ' => 'G', 'Äž' => 'G', 'Ä ' => 'G', 'Ä¢' => 'G',
        'Ä¤' => 'H', 'Ä¦' => 'H', 'ÃŒ' => 'I', 'Ã' => 'I', 'ÃŽ' => 'I', 'Ã' => 'I',
        'Äª' => 'I', 'Ä¨' => 'I', 'Ä¬' => 'I', 'Ä®' => 'I', 'Ä°' => 'I', 'Ä´' => 'J',
        'Ä¶' => 'K', 'Ä½' => 'K', 'Ä¹' => 'K', 'Ä»' => 'K', 'Ä¿' => 'K', 'Å' => 'L',
        'Ã‘' => 'N', 'Åƒ' => 'N', 'Å‡' => 'N', 'Å…' => 'N', 'ÅŠ' => 'N', 'Ã’' => 'O',
        'Ã“' => 'O', 'Ã”' => 'O', 'Ã•' => 'O', 'Ã˜' => 'O', 'ÅŒ' => 'O', 'Å' => 'O',
        'ÅŽ' => 'O', 'Å”' => 'R', 'Å˜' => 'R', 'Å–' => 'R', 'Åš' => 'S', 'Åž' => 'S',
        'Åœ' => 'S', 'È˜' => 'S', 'Å ' => 'S', 'Å¤' => 'T', 'Å¢' => 'T', 'Å¦' => 'T',
        'Èš' => 'T', 'Ã™' => 'U', 'Ãš' => 'U', 'Ã›' => 'U', 'Åª' => 'U', 'Å®' => 'U',
        'Å°' => 'U', 'Å¬' => 'U', 'Å¨' => 'U', 'Å²' => 'U', 'Å´' => 'W', 'Å¶' => 'Y',
        'Å¸' => 'Y', 'Ã' => 'Y', 'Å¹' => 'Z', 'Å»' => 'Z', 'Å½' => 'Z', 'Ã ' => 'a',
        'Ã¡' => 'a', 'Ã¢' => 'a', 'Ã£' => 'a', 'Ä' => 'a', 'Ä…' => 'a', 'Äƒ' => 'a',
        'Ã¥' => 'a', 'Ã§' => 'c', 'Ä‡' => 'c', 'Ä' => 'c', 'Ä‰' => 'c', 'Ä‹' => 'c',
        'Ä' => 'd', 'Ä‘' => 'd', 'Ã¨' => 'e', 'Ã©' => 'e', 'Ãª' => 'e', 'Ã«' => 'e',
        'Ä“' => 'e', 'Ä™' => 'e', 'Ä›' => 'e', 'Ä•' => 'e', 'Ä—' => 'e', 'Æ’' => 'f',
        'Ä' => 'g', 'ÄŸ' => 'g', 'Ä¡' => 'g', 'Ä£' => 'g', 'Ä¥' => 'h', 'Ä§' => 'h',
        'Ã¬' => 'i', 'Ã' => 'i', 'Ã®' => 'i', 'Ã¯' => 'i', 'Ä«' => 'i', 'Ä©' => 'i',
        'Ä' => 'i', 'Ä¯' => 'i', 'Ä±' => 'i', 'Äµ' => 'j', 'Ä·' => 'k', 'Ä¸' => 'k',
        'Å‚' => 'l', 'Ä¾' => 'l', 'Äº' => 'l', 'Ä¼' => 'l', 'Å€' => 'l', 'Ã±' => 'n',
        'Å„' => 'n', 'Åˆ' => 'n', 'Å†' => 'n', 'Å‰' => 'n', 'Å‹' => 'n', 'Ã²' => 'o',
        'Ã³' => 'o', 'Ã´' => 'o', 'Ãµ' => 'o', 'Ã¸' => 'o', 'Å' => 'o', 'Å‘' => 'o',
        'Å' => 'o', 'Å•' => 'r', 'Å™' => 'r', 'Å—' => 'r', 'Å›' => 's', 'Å¡' => 's',
        'Å¥' => 't', 'Ã¹' => 'u', 'Ãº' => 'u', 'Ã»' => 'u', 'Å«' => 'u', 'Å¯' => 'u',
        'Å±' => 'u', 'Å' => 'u', 'Å©' => 'u', 'Å³' => 'u', 'Åµ' => 'w', 'Ã¿' => 'y',
        'Ã½' => 'y', 'Å·' => 'y', 'Å¼' => 'z', 'Åº' => 'z', 'Å¾' => 'z', 'Î‘' => 'A',
        'Î†' => 'A', 'á¼ˆ' => 'A', 'á¼‰' => 'A', 'á¼Š' => 'A', 'á¼‹' => 'A', 'á¼Œ' => 'A',
        'á¼' => 'A', 'á¼Ž' => 'A', 'á¼' => 'A', 'á¾ˆ' => 'A', 'á¾‰' => 'A', 'á¾Š' => 'A',
        'á¾‹' => 'A', 'á¾Œ' => 'A', 'á¾' => 'A', 'á¾Ž' => 'A', 'á¾' => 'A', 'á¾¸' => 'A',
        'á¾¹' => 'A', 'á¾º' => 'A', 'á¾¼' => 'A', 'Î’' => 'B', 'Î“' => 'G', 'Î”' => 'D',
        'Î•' => 'E', 'Îˆ' => 'E', 'á¼˜' => 'E', 'á¼™' => 'E', 'á¼š' => 'E', 'á¼›' => 'E',
        'á¼œ' => 'E', 'á¼' => 'E', 'á¿ˆ' => 'E', 'Î–' => 'Z', 'Î—' => 'I', 'Î‰' => 'I',
        'á¼¨' => 'I', 'á¼©' => 'I', 'á¼ª' => 'I', 'á¼«' => 'I', 'á¼¬' => 'I', 'á¼' => 'I',
        'á¼®' => 'I', 'á¼¯' => 'I', 'á¾˜' => 'I', 'á¾™' => 'I', 'á¾š' => 'I', 'á¾›' => 'I',
        'á¾œ' => 'I', 'á¾' => 'I', 'á¾ž' => 'I', 'á¾Ÿ' => 'I', 'á¿Š' => 'I', 'á¿Œ' => 'I',
        'Î˜' => 'T', 'Î™' => 'I', 'ÎŠ' => 'I', 'Îª' => 'I', 'á¼¸' => 'I', 'á¼¹' => 'I',
        'á¼º' => 'I', 'á¼»' => 'I', 'á¼¼' => 'I', 'á¼½' => 'I', 'á¼¾' => 'I', 'á¼¿' => 'I',
        'á¿˜' => 'I', 'á¿™' => 'I', 'á¿š' => 'I', 'Îš' => 'K', 'Î›' => 'L', 'Îœ' => 'M',
        'Î' => 'N', 'Îž' => 'K', 'ÎŸ' => 'O', 'ÎŒ' => 'O', 'á½ˆ' => 'O', 'á½‰' => 'O',
        'á½Š' => 'O', 'á½‹' => 'O', 'á½Œ' => 'O', 'á½' => 'O', 'á¿¸' => 'O', 'Î ' => 'P',
        'Î¡' => 'R', 'á¿¬' => 'R', 'Î£' => 'S', 'Î¤' => 'T', 'Î¥' => 'Y', 'ÎŽ' => 'Y',
        'Î«' => 'Y', 'á½™' => 'Y', 'á½›' => 'Y', 'á½' => 'Y', 'á½Ÿ' => 'Y', 'á¿¨' => 'Y',
        'á¿©' => 'Y', 'á¿ª' => 'Y', 'Î¦' => 'F', 'Î§' => 'X', 'Î¨' => 'P', 'Î©' => 'O',
        'Î' => 'O', 'á½¨' => 'O', 'á½©' => 'O', 'á½ª' => 'O', 'á½«' => 'O', 'á½¬' => 'O',
        'á½' => 'O', 'á½®' => 'O', 'á½¯' => 'O', 'á¾¨' => 'O', 'á¾©' => 'O', 'á¾ª' => 'O',
        'á¾«' => 'O', 'á¾¬' => 'O', 'á¾' => 'O', 'á¾®' => 'O', 'á¾¯' => 'O', 'á¿º' => 'O',
        'á¿¼' => 'O', 'Î±' => 'a', 'Î¬' => 'a', 'á¼€' => 'a', 'á¼' => 'a', 'á¼‚' => 'a',
        'á¼ƒ' => 'a', 'á¼„' => 'a', 'á¼…' => 'a', 'á¼†' => 'a', 'á¼‡' => 'a', 'á¾€' => 'a',
        'á¾' => 'a', 'á¾‚' => 'a', 'á¾ƒ' => 'a', 'á¾„' => 'a', 'á¾…' => 'a', 'á¾†' => 'a',
        'á¾‡' => 'a', 'á½°' => 'a', 'á¾°' => 'a', 'á¾±' => 'a', 'á¾²' => 'a', 'á¾³' => 'a',
        'á¾´' => 'a', 'á¾¶' => 'a', 'á¾·' => 'a', 'Î²' => 'b', 'Î³' => 'g', 'Î´' => 'd',
        'Îµ' => 'e', 'Î' => 'e', 'á¼' => 'e', 'á¼‘' => 'e', 'á¼’' => 'e', 'á¼“' => 'e',
        'á¼”' => 'e', 'á¼•' => 'e', 'á½²' => 'e', 'Î¶' => 'z', 'Î·' => 'i', 'Î®' => 'i',
        'á¼ ' => 'i', 'á¼¡' => 'i', 'á¼¢' => 'i', 'á¼£' => 'i', 'á¼¤' => 'i', 'á¼¥' => 'i',
        'á¼¦' => 'i', 'á¼§' => 'i', 'á¾' => 'i', 'á¾‘' => 'i', 'á¾’' => 'i', 'á¾“' => 'i',
        'á¾”' => 'i', 'á¾•' => 'i', 'á¾–' => 'i', 'á¾—' => 'i', 'á½´' => 'i', 'á¿‚' => 'i',
        'á¿ƒ' => 'i', 'á¿„' => 'i', 'á¿†' => 'i', 'á¿‡' => 'i', 'Î¸' => 't', 'Î¹' => 'i',
        'Î¯' => 'i', 'ÏŠ' => 'i', 'Î' => 'i', 'á¼°' => 'i', 'á¼±' => 'i', 'á¼²' => 'i',
        'á¼³' => 'i', 'á¼´' => 'i', 'á¼µ' => 'i', 'á¼¶' => 'i', 'á¼·' => 'i', 'á½¶' => 'i',
        'á¿' => 'i', 'á¿‘' => 'i', 'á¿’' => 'i', 'á¿–' => 'i', 'á¿—' => 'i', 'Îº' => 'k',
        'Î»' => 'l', 'Î¼' => 'm', 'Î½' => 'n', 'Î¾' => 'k', 'Î¿' => 'o', 'ÏŒ' => 'o',
        'á½€' => 'o', 'á½' => 'o', 'á½‚' => 'o', 'á½ƒ' => 'o', 'á½„' => 'o', 'á½…' => 'o',
        'á½¸' => 'o', 'Ï€' => 'p', 'Ï' => 'r', 'á¿¤' => 'r', 'á¿¥' => 'r', 'Ïƒ' => 's',
        'Ï‚' => 's', 'Ï„' => 't', 'Ï…' => 'y', 'Ï' => 'y', 'Ï‹' => 'y', 'Î°' => 'y',
        'á½' => 'y', 'á½‘' => 'y', 'á½’' => 'y', 'á½“' => 'y', 'á½”' => 'y', 'á½•' => 'y',
        'á½–' => 'y', 'á½—' => 'y', 'á½º' => 'y', 'á¿ ' => 'y', 'á¿¡' => 'y', 'á¿¢' => 'y',
        'á¿¦' => 'y', 'á¿§' => 'y', 'Ï†' => 'f', 'Ï‡' => 'x', 'Ïˆ' => 'p', 'Ï‰' => 'o',
        'ÏŽ' => 'o', 'á½ ' => 'o', 'á½¡' => 'o', 'á½¢' => 'o', 'á½£' => 'o', 'á½¤' => 'o',
        'á½¥' => 'o', 'á½¦' => 'o', 'á½§' => 'o', 'á¾ ' => 'o', 'á¾¡' => 'o', 'á¾¢' => 'o',
        'á¾£' => 'o', 'á¾¤' => 'o', 'á¾¥' => 'o', 'á¾¦' => 'o', 'á¾§' => 'o', 'á½¼' => 'o',
        'á¿²' => 'o', 'á¿³' => 'o', 'á¿´' => 'o', 'á¿¶' => 'o', 'á¿·' => 'o', 'Ð' => 'A',
        'Ð‘' => 'B', 'Ð’' => 'V', 'Ð“' => 'G', 'Ð”' => 'D', 'Ð•' => 'E', 'Ð' => 'E',
        'Ð–' => 'Z', 'Ð—' => 'Z', 'Ð˜' => 'I', 'Ð™' => 'I', 'Ðš' => 'K', 'Ð›' => 'L',
        'Ðœ' => 'M', 'Ð' => 'N', 'Ðž' => 'O', 'ÐŸ' => 'P', 'Ð ' => 'R', 'Ð¡' => 'S',
        'Ð¢' => 'T', 'Ð£' => 'U', 'Ð¤' => 'F', 'Ð¥' => 'K', 'Ð¦' => 'T', 'Ð§' => 'C',
        'Ð¨' => 'S', 'Ð©' => 'S', 'Ð«' => 'Y', 'Ð' => 'E', 'Ð®' => 'Y', 'Ð¯' => 'Y',
        'Ð°' => 'A', 'Ð±' => 'B', 'Ð²' => 'V', 'Ð³' => 'G', 'Ð´' => 'D', 'Ðµ' => 'E',
        'Ñ‘' => 'E', 'Ð¶' => 'Z', 'Ð·' => 'Z', 'Ð¸' => 'I', 'Ð¹' => 'I', 'Ðº' => 'K',
        'Ð»' => 'L', 'Ð¼' => 'M', 'Ð½' => 'N', 'Ð¾' => 'O', 'Ð¿' => 'P', 'Ñ€' => 'R',
        'Ñ' => 'S', 'Ñ‚' => 'T', 'Ñƒ' => 'U', 'Ñ„' => 'F', 'Ñ…' => 'K', 'Ñ†' => 'T',
        'Ñ‡' => 'C', 'Ñˆ' => 'S', 'Ñ‰' => 'S', 'Ñ‹' => 'Y', 'Ñ' => 'E', 'ÑŽ' => 'Y',
        'Ñ' => 'Y', 'Ã°' => 'd', 'Ã' => 'D', 'Ã¾' => 't', 'Ãž' => 'T', 'áƒ' => 'a',
        'áƒ‘' => 'b', 'áƒ’' => 'g', 'áƒ“' => 'd', 'áƒ”' => 'e', 'áƒ•' => 'v', 'áƒ–' => 'z',
        'áƒ—' => 't', 'áƒ˜' => 'i', 'áƒ™' => 'k', 'áƒš' => 'l', 'áƒ›' => 'm', 'áƒœ' => 'n',
        'áƒ' => 'o', 'áƒž' => 'p', 'áƒŸ' => 'z', 'áƒ ' => 'r', 'áƒ¡' => 's', 'áƒ¢' => 't',
        'áƒ£' => 'u', 'áƒ¤' => 'p', 'áƒ¥' => 'k', 'áƒ¦' => 'g', 'áƒ§' => 'q', 'áƒ¨' => 's',
        'áƒ©' => 'c', 'áƒª' => 't', 'áƒ«' => 'd', 'áƒ¬' => 't', 'áƒ' => 'c', 'áƒ®' => 'k',
        'áƒ¯' => 'j', 'áƒ°' => 'h',
    );
    
    return str_replace(array_keys($transliteration), array_values($transliteration), $str);
}

Revision: 57887

at June 13, 2012 20:34 by MGHollander

Updated Code

<?php

/**
 * Unaccent a string 
 *
 * An example string like Ã€Ã˜Ä—Ã¿á¾œá½¨Î¶á½…Ð‘ÑŽ will be translated to AOeyIOzoBY. 
 * More complete than :
 *
 *  strtr(
 *      (string)$str,
 *      "Ã€ÃÃ‚ÃƒÃ„Ã…Ã Ã¡Ã¢Ã£Ã¤Ã¥Ã’Ã“Ã”Ã•Ã–Ã˜Ã²Ã³Ã´ÃµÃ¶Ã¸ÃˆÃ‰ÃŠÃ‹Ã¨Ã©ÃªÃ«Ã‡Ã§ÃŒÃÃŽÃÃ¬ÃÃ®Ã¯Ã™ÃšÃ›ÃœÃ¹ÃºÃ»Ã¼Ã¿Ã‘Ã±",
 *      "aaaaaaaaaaaaooooooooooooeeeeeeeecciiiiiiiiuuuuuuuuynn"
 *  );
 *
 * @author http://www.evaisse.net/2008/php-translit-remove-accent-unaccent-21001
 * @param $str input string
 * @param $utf8 if null, function will detect input string encoding
 * @return string input string without accent
 */
public function remove_accents($str, $utf8 = true) {
    $str = (string) $str;
    if (is_null($utf8)) {
        if (!function_exists('mb_detect_encoding')) {
            $utf8 = (strtolower(mb_detect_encoding($str)) == 'utf-8');
        } else {
            $length = strlen($str);
            $utf8 = true;
            
            for ($i = 0; $i < $length; $i++) {
                $c = ord($str[$i]);
                
                if ($c < 0x80) $n = 0; // 0bbbbbbb
                elseif (($c & 0xE0) == 0xC0) $n=1; // 110bbbbb
                elseif (($c & 0xF0) == 0xE0) $n=2; // 1110bbbb
                elseif (($c & 0xF8) == 0xF0) $n=3; // 11110bbb
                elseif (($c & 0xFC) == 0xF8) $n=4; // 111110bb
                elseif (($c & 0xFE) == 0xFC) $n=5; // 1111110b
                else return false; // Does not match any model
                
                for ($j = 0; $j < $n; $j++) { // n bytes matching 10bbbbbb follow ?
                    if ((++$i == $length) || ((ord($str[$i]) & 0xC0) != 0x80)) {
                        $utf8 = false;
                        break;
                    }
                }
            }
        }
    }
    
    if (!$utf8) {
        $str = utf8_encode($str);
    }
    
    $transliteration = array(
        'Ä²' => 'I', 'Ã–' => 'O', 'Å’' => 'O', 'Ãœ' => 'U', 'Ã¤' => 'a', 'Ã¦' => 'a',
        'Ä³' => 'i', 'Ã¶' => 'o', 'Å“' => 'o', 'Ã¼' => 'u', 'ÃŸ' => 's', 'Å¿' => 's',
        'Ã€' => 'A', 'Ã' => 'A', 'Ã‚' => 'A', 'Ãƒ' => 'A', 'Ã„' => 'A', 'Ã…' => 'A',
        'Ã†' => 'A', 'Ä€' => 'A', 'Ä„' => 'A', 'Ä‚' => 'A', 'Ã‡' => 'C', 'Ä†' => 'C',
        'ÄŒ' => 'C', 'Äˆ' => 'C', 'ÄŠ' => 'C', 'ÄŽ' => 'D', 'Ä' => 'D', 'Ãˆ' => 'E',
        'Ã‰' => 'E', 'ÃŠ' => 'E', 'Ã‹' => 'E', 'Ä’' => 'E', 'Ä˜' => 'E', 'Äš' => 'E',
        'Ä”' => 'E', 'Ä–' => 'E', 'Äœ' => 'G', 'Äž' => 'G', 'Ä ' => 'G', 'Ä¢' => 'G',
        'Ä¤' => 'H', 'Ä¦' => 'H', 'ÃŒ' => 'I', 'Ã' => 'I', 'ÃŽ' => 'I', 'Ã' => 'I',
        'Äª' => 'I', 'Ä¨' => 'I', 'Ä¬' => 'I', 'Ä®' => 'I', 'Ä°' => 'I', 'Ä´' => 'J',
        'Ä¶' => 'K', 'Ä½' => 'K', 'Ä¹' => 'K', 'Ä»' => 'K', 'Ä¿' => 'K', 'Å' => 'L',
        'Ã‘' => 'N', 'Åƒ' => 'N', 'Å‡' => 'N', 'Å…' => 'N', 'ÅŠ' => 'N', 'Ã’' => 'O',
        'Ã“' => 'O', 'Ã”' => 'O', 'Ã•' => 'O', 'Ã˜' => 'O', 'ÅŒ' => 'O', 'Å' => 'O',
        'ÅŽ' => 'O', 'Å”' => 'R', 'Å˜' => 'R', 'Å–' => 'R', 'Åš' => 'S', 'Åž' => 'S',
        'Åœ' => 'S', 'È˜' => 'S', 'Å ' => 'S', 'Å¤' => 'T', 'Å¢' => 'T', 'Å¦' => 'T',
        'Èš' => 'T', 'Ã™' => 'U', 'Ãš' => 'U', 'Ã›' => 'U', 'Åª' => 'U', 'Å®' => 'U',
        'Å°' => 'U', 'Å¬' => 'U', 'Å¨' => 'U', 'Å²' => 'U', 'Å´' => 'W', 'Å¶' => 'Y',
        'Å¸' => 'Y', 'Ã' => 'Y', 'Å¹' => 'Z', 'Å»' => 'Z', 'Å½' => 'Z', 'Ã ' => 'a',
        'Ã¡' => 'a', 'Ã¢' => 'a', 'Ã£' => 'a', 'Ä' => 'a', 'Ä…' => 'a', 'Äƒ' => 'a',
        'Ã¥' => 'a', 'Ã§' => 'c', 'Ä‡' => 'c', 'Ä' => 'c', 'Ä‰' => 'c', 'Ä‹' => 'c',
        'Ä' => 'd', 'Ä‘' => 'd', 'Ã¨' => 'e', 'Ã©' => 'e', 'Ãª' => 'e', 'Ã«' => 'e',
        'Ä“' => 'e', 'Ä™' => 'e', 'Ä›' => 'e', 'Ä•' => 'e', 'Ä—' => 'e', 'Æ’' => 'f',
        'Ä' => 'g', 'ÄŸ' => 'g', 'Ä¡' => 'g', 'Ä£' => 'g', 'Ä¥' => 'h', 'Ä§' => 'h',
        'Ã¬' => 'i', 'Ã' => 'i', 'Ã®' => 'i', 'Ã¯' => 'i', 'Ä«' => 'i', 'Ä©' => 'i',
        'Ä' => 'i', 'Ä¯' => 'i', 'Ä±' => 'i', 'Äµ' => 'j', 'Ä·' => 'k', 'Ä¸' => 'k',
        'Å‚' => 'l', 'Ä¾' => 'l', 'Äº' => 'l', 'Ä¼' => 'l', 'Å€' => 'l', 'Ã±' => 'n',
        'Å„' => 'n', 'Åˆ' => 'n', 'Å†' => 'n', 'Å‰' => 'n', 'Å‹' => 'n', 'Ã²' => 'o',
        'Ã³' => 'o', 'Ã´' => 'o', 'Ãµ' => 'o', 'Ã¸' => 'o', 'Å' => 'o', 'Å‘' => 'o',
        'Å' => 'o', 'Å•' => 'r', 'Å™' => 'r', 'Å—' => 'r', 'Å›' => 's', 'Å¡' => 's',
        'Å¥' => 't', 'Ã¹' => 'u', 'Ãº' => 'u', 'Ã»' => 'u', 'Å«' => 'u', 'Å¯' => 'u',
        'Å±' => 'u', 'Å' => 'u', 'Å©' => 'u', 'Å³' => 'u', 'Åµ' => 'w', 'Ã¿' => 'y',
        'Ã½' => 'y', 'Å·' => 'y', 'Å¼' => 'z', 'Åº' => 'z', 'Å¾' => 'z', 'Î‘' => 'A',
        'Î†' => 'A', 'á¼ˆ' => 'A', 'á¼‰' => 'A', 'á¼Š' => 'A', 'á¼‹' => 'A', 'á¼Œ' => 'A',
        'á¼' => 'A', 'á¼Ž' => 'A', 'á¼' => 'A', 'á¾ˆ' => 'A', 'á¾‰' => 'A', 'á¾Š' => 'A',
        'á¾‹' => 'A', 'á¾Œ' => 'A', 'á¾' => 'A', 'á¾Ž' => 'A', 'á¾' => 'A', 'á¾¸' => 'A',
        'á¾¹' => 'A', 'á¾º' => 'A', 'á¾¼' => 'A', 'Î’' => 'B', 'Î“' => 'G', 'Î”' => 'D',
        'Î•' => 'E', 'Îˆ' => 'E', 'á¼˜' => 'E', 'á¼™' => 'E', 'á¼š' => 'E', 'á¼›' => 'E',
        'á¼œ' => 'E', 'á¼' => 'E', 'á¿ˆ' => 'E', 'Î–' => 'Z', 'Î—' => 'I', 'Î‰' => 'I',
        'á¼¨' => 'I', 'á¼©' => 'I', 'á¼ª' => 'I', 'á¼«' => 'I', 'á¼¬' => 'I', 'á¼' => 'I',
        'á¼®' => 'I', 'á¼¯' => 'I', 'á¾˜' => 'I', 'á¾™' => 'I', 'á¾š' => 'I', 'á¾›' => 'I',
        'á¾œ' => 'I', 'á¾' => 'I', 'á¾ž' => 'I', 'á¾Ÿ' => 'I', 'á¿Š' => 'I', 'á¿Œ' => 'I',
        'Î˜' => 'T', 'Î™' => 'I', 'ÎŠ' => 'I', 'Îª' => 'I', 'á¼¸' => 'I', 'á¼¹' => 'I',
        'á¼º' => 'I', 'á¼»' => 'I', 'á¼¼' => 'I', 'á¼½' => 'I', 'á¼¾' => 'I', 'á¼¿' => 'I',
        'á¿˜' => 'I', 'á¿™' => 'I', 'á¿š' => 'I', 'Îš' => 'K', 'Î›' => 'L', 'Îœ' => 'M',
        'Î' => 'N', 'Îž' => 'K', 'ÎŸ' => 'O', 'ÎŒ' => 'O', 'á½ˆ' => 'O', 'á½‰' => 'O',
        'á½Š' => 'O', 'á½‹' => 'O', 'á½Œ' => 'O', 'á½' => 'O', 'á¿¸' => 'O', 'Î ' => 'P',
        'Î¡' => 'R', 'á¿¬' => 'R', 'Î£' => 'S', 'Î¤' => 'T', 'Î¥' => 'Y', 'ÎŽ' => 'Y',
        'Î«' => 'Y', 'á½™' => 'Y', 'á½›' => 'Y', 'á½' => 'Y', 'á½Ÿ' => 'Y', 'á¿¨' => 'Y',
        'á¿©' => 'Y', 'á¿ª' => 'Y', 'Î¦' => 'F', 'Î§' => 'X', 'Î¨' => 'P', 'Î©' => 'O',
        'Î' => 'O', 'á½¨' => 'O', 'á½©' => 'O', 'á½ª' => 'O', 'á½«' => 'O', 'á½¬' => 'O',
        'á½' => 'O', 'á½®' => 'O', 'á½¯' => 'O', 'á¾¨' => 'O', 'á¾©' => 'O', 'á¾ª' => 'O',
        'á¾«' => 'O', 'á¾¬' => 'O', 'á¾' => 'O', 'á¾®' => 'O', 'á¾¯' => 'O', 'á¿º' => 'O',
        'á¿¼' => 'O', 'Î±' => 'a', 'Î¬' => 'a', 'á¼€' => 'a', 'á¼' => 'a', 'á¼‚' => 'a',
        'á¼ƒ' => 'a', 'á¼„' => 'a', 'á¼…' => 'a', 'á¼†' => 'a', 'á¼‡' => 'a', 'á¾€' => 'a',
        'á¾' => 'a', 'á¾‚' => 'a', 'á¾ƒ' => 'a', 'á¾„' => 'a', 'á¾…' => 'a', 'á¾†' => 'a',
        'á¾‡' => 'a', 'á½°' => 'a', 'á¾°' => 'a', 'á¾±' => 'a', 'á¾²' => 'a', 'á¾³' => 'a',
        'á¾´' => 'a', 'á¾¶' => 'a', 'á¾·' => 'a', 'Î²' => 'b', 'Î³' => 'g', 'Î´' => 'd',
        'Îµ' => 'e', 'Î' => 'e', 'á¼' => 'e', 'á¼‘' => 'e', 'á¼’' => 'e', 'á¼“' => 'e',
        'á¼”' => 'e', 'á¼•' => 'e', 'á½²' => 'e', 'Î¶' => 'z', 'Î·' => 'i', 'Î®' => 'i',
        'á¼ ' => 'i', 'á¼¡' => 'i', 'á¼¢' => 'i', 'á¼£' => 'i', 'á¼¤' => 'i', 'á¼¥' => 'i',
        'á¼¦' => 'i', 'á¼§' => 'i', 'á¾' => 'i', 'á¾‘' => 'i', 'á¾’' => 'i', 'á¾“' => 'i',
        'á¾”' => 'i', 'á¾•' => 'i', 'á¾–' => 'i', 'á¾—' => 'i', 'á½´' => 'i', 'á¿‚' => 'i',
        'á¿ƒ' => 'i', 'á¿„' => 'i', 'á¿†' => 'i', 'á¿‡' => 'i', 'Î¸' => 't', 'Î¹' => 'i',
        'Î¯' => 'i', 'ÏŠ' => 'i', 'Î' => 'i', 'á¼°' => 'i', 'á¼±' => 'i', 'á¼²' => 'i',
        'á¼³' => 'i', 'á¼´' => 'i', 'á¼µ' => 'i', 'á¼¶' => 'i', 'á¼·' => 'i', 'á½¶' => 'i',
        'á¿' => 'i', 'á¿‘' => 'i', 'á¿’' => 'i', 'á¿–' => 'i', 'á¿—' => 'i', 'Îº' => 'k',
        'Î»' => 'l', 'Î¼' => 'm', 'Î½' => 'n', 'Î¾' => 'k', 'Î¿' => 'o', 'ÏŒ' => 'o',
        'á½€' => 'o', 'á½' => 'o', 'á½‚' => 'o', 'á½ƒ' => 'o', 'á½„' => 'o', 'á½…' => 'o',
        'á½¸' => 'o', 'Ï€' => 'p', 'Ï' => 'r', 'á¿¤' => 'r', 'á¿¥' => 'r', 'Ïƒ' => 's',
        'Ï‚' => 's', 'Ï„' => 't', 'Ï…' => 'y', 'Ï' => 'y', 'Ï‹' => 'y', 'Î°' => 'y',
        'á½' => 'y', 'á½‘' => 'y', 'á½’' => 'y', 'á½“' => 'y', 'á½”' => 'y', 'á½•' => 'y',
        'á½–' => 'y', 'á½—' => 'y', 'á½º' => 'y', 'á¿ ' => 'y', 'á¿¡' => 'y', 'á¿¢' => 'y',
        'á¿¦' => 'y', 'á¿§' => 'y', 'Ï†' => 'f', 'Ï‡' => 'x', 'Ïˆ' => 'p', 'Ï‰' => 'o',
        'ÏŽ' => 'o', 'á½ ' => 'o', 'á½¡' => 'o', 'á½¢' => 'o', 'á½£' => 'o', 'á½¤' => 'o',
        'á½¥' => 'o', 'á½¦' => 'o', 'á½§' => 'o', 'á¾ ' => 'o', 'á¾¡' => 'o', 'á¾¢' => 'o',
        'á¾£' => 'o', 'á¾¤' => 'o', 'á¾¥' => 'o', 'á¾¦' => 'o', 'á¾§' => 'o', 'á½¼' => 'o',
        'á¿²' => 'o', 'á¿³' => 'o', 'á¿´' => 'o', 'á¿¶' => 'o', 'á¿·' => 'o', 'Ð' => 'A',
        'Ð‘' => 'B', 'Ð’' => 'V', 'Ð“' => 'G', 'Ð”' => 'D', 'Ð•' => 'E', 'Ð' => 'E',
        'Ð–' => 'Z', 'Ð—' => 'Z', 'Ð˜' => 'I', 'Ð™' => 'I', 'Ðš' => 'K', 'Ð›' => 'L',
        'Ðœ' => 'M', 'Ð' => 'N', 'Ðž' => 'O', 'ÐŸ' => 'P', 'Ð ' => 'R', 'Ð¡' => 'S',
        'Ð¢' => 'T', 'Ð£' => 'U', 'Ð¤' => 'F', 'Ð¥' => 'K', 'Ð¦' => 'T', 'Ð§' => 'C',
        'Ð¨' => 'S', 'Ð©' => 'S', 'Ð«' => 'Y', 'Ð' => 'E', 'Ð®' => 'Y', 'Ð¯' => 'Y',
        'Ð°' => 'A', 'Ð±' => 'B', 'Ð²' => 'V', 'Ð³' => 'G', 'Ð´' => 'D', 'Ðµ' => 'E',
        'Ñ‘' => 'E', 'Ð¶' => 'Z', 'Ð·' => 'Z', 'Ð¸' => 'I', 'Ð¹' => 'I', 'Ðº' => 'K',
        'Ð»' => 'L', 'Ð¼' => 'M', 'Ð½' => 'N', 'Ð¾' => 'O', 'Ð¿' => 'P', 'Ñ€' => 'R',
        'Ñ' => 'S', 'Ñ‚' => 'T', 'Ñƒ' => 'U', 'Ñ„' => 'F', 'Ñ…' => 'K', 'Ñ†' => 'T',
        'Ñ‡' => 'C', 'Ñˆ' => 'S', 'Ñ‰' => 'S', 'Ñ‹' => 'Y', 'Ñ' => 'E', 'ÑŽ' => 'Y',
        'Ñ' => 'Y', 'Ã°' => 'd', 'Ã' => 'D', 'Ã¾' => 't', 'Ãž' => 'T', 'áƒ' => 'a',
        'áƒ‘' => 'b', 'áƒ’' => 'g', 'áƒ“' => 'd', 'áƒ”' => 'e', 'áƒ•' => 'v', 'áƒ–' => 'z',
        'áƒ—' => 't', 'áƒ˜' => 'i', 'áƒ™' => 'k', 'áƒš' => 'l', 'áƒ›' => 'm', 'áƒœ' => 'n',
        'áƒ' => 'o', 'áƒž' => 'p', 'áƒŸ' => 'z', 'áƒ ' => 'r', 'áƒ¡' => 's', 'áƒ¢' => 't',
        'áƒ£' => 'u', 'áƒ¤' => 'p', 'áƒ¥' => 'k', 'áƒ¦' => 'g', 'áƒ§' => 'q', 'áƒ¨' => 's',
        'áƒ©' => 'c', 'áƒª' => 't', 'áƒ«' => 'd', 'áƒ¬' => 't', 'áƒ' => 'c', 'áƒ®' => 'k',
        'áƒ¯' => 'j', 'áƒ°' => 'h',
    );
    
    return str_replace(array_keys($transliteration), array_values($transliteration), $str);
}

Revision: 57886

at June 13, 2012 20:32 by MGHollander

Updated Code

<?php

/**
 * Unaccent a string 
 *
 * An example string like Ã€Ã˜Ä—Ã¿á¾œá½¨Î¶á½…Ð‘ÑŽ will be translated to AOeyIOzoBY. 
 * More complete than :
 *
 *  strtr(
 *      (string)$str,
 *      "Ã€ÃÃ‚ÃƒÃ„Ã…Ã Ã¡Ã¢Ã£Ã¤Ã¥Ã’Ã“Ã”Ã•Ã–Ã˜Ã²Ã³Ã´ÃµÃ¶Ã¸ÃˆÃ‰ÃŠÃ‹Ã¨Ã©ÃªÃ«Ã‡Ã§ÃŒÃÃŽÃÃ¬ÃÃ®Ã¯Ã™ÃšÃ›ÃœÃ¹ÃºÃ»Ã¼Ã¿Ã‘Ã±",
 *      "aaaaaaaaaaaaooooooooooooeeeeeeeecciiiiiiiiuuuuuuuuynn"
 *  );
 *
 * @author http://www.evaisse.net/2008/php-translit-remove-accent-unaccent-21001
 * @param $str input string
 * @param $utf8 if null, function will detect input string encoding
 * @return string input string without accent
 */
public function remove_accents($str, $utf8 = true) {
    $str = (string) $str;
    if (is_null($utf8)) {
        if (!function_exists('mb_detect_encoding')) {
            $utf8 = (strtolower(mb_detect_encoding($str)) == 'utf-8');
        } else {
            $length = strlen($str);
            $utf8 = true;
            
            for ($i = 0; $i < $length; $i++) {
                $c = ord($str[$i]);
                
                if ($c < 0x80) $n = 0; // 0bbbbbbb
                elseif (($c & 0xE0) == 0xC0) $n=1; // 110bbbbb
                elseif (($c & 0xF0) == 0xE0) $n=2; // 1110bbbb
                elseif (($c & 0xF8) == 0xF0) $n=3; // 11110bbb
                elseif (($c & 0xFC) == 0xF8) $n=4; // 111110bb
                elseif (($c & 0xFE) == 0xFC) $n=5; // 1111110b
                else return false; // Does not match any model
                
                for ($j = 0; $j < $n; $j++) { // n bytes matching 10bbbbbb follow ?
                    if ((++$i == $length) || ((ord($str[$i]) & 0xC0) != 0x80)) {
                        $utf8 = false;
                        break;
                    }
                    
                }
            }
        }
        
    }
    
    if (!$utf8) {
        $str = utf8_encode($str);
    }
    
    $transliteration = array(
        'Ä²' => 'I', 'Ã–' => 'O', 'Å’' => 'O', 'Ãœ' => 'U', 'Ã¤' => 'a', 'Ã¦' => 'a',
        'Ä³' => 'i', 'Ã¶' => 'o', 'Å“' => 'o', 'Ã¼' => 'u', 'ÃŸ' => 's', 'Å¿' => 's',
        'Ã€' => 'A', 'Ã' => 'A', 'Ã‚' => 'A', 'Ãƒ' => 'A', 'Ã„' => 'A', 'Ã…' => 'A',
        'Ã†' => 'A', 'Ä€' => 'A', 'Ä„' => 'A', 'Ä‚' => 'A', 'Ã‡' => 'C', 'Ä†' => 'C',
        'ÄŒ' => 'C', 'Äˆ' => 'C', 'ÄŠ' => 'C', 'ÄŽ' => 'D', 'Ä' => 'D', 'Ãˆ' => 'E',
        'Ã‰' => 'E', 'ÃŠ' => 'E', 'Ã‹' => 'E', 'Ä’' => 'E', 'Ä˜' => 'E', 'Äš' => 'E',
        'Ä”' => 'E', 'Ä–' => 'E', 'Äœ' => 'G', 'Äž' => 'G', 'Ä ' => 'G', 'Ä¢' => 'G',
        'Ä¤' => 'H', 'Ä¦' => 'H', 'ÃŒ' => 'I', 'Ã' => 'I', 'ÃŽ' => 'I', 'Ã' => 'I',
        'Äª' => 'I', 'Ä¨' => 'I', 'Ä¬' => 'I', 'Ä®' => 'I', 'Ä°' => 'I', 'Ä´' => 'J',
        'Ä¶' => 'K', 'Ä½' => 'K', 'Ä¹' => 'K', 'Ä»' => 'K', 'Ä¿' => 'K', 'Å' => 'L',
        'Ã‘' => 'N', 'Åƒ' => 'N', 'Å‡' => 'N', 'Å…' => 'N', 'ÅŠ' => 'N', 'Ã’' => 'O',
        'Ã“' => 'O', 'Ã”' => 'O', 'Ã•' => 'O', 'Ã˜' => 'O', 'ÅŒ' => 'O', 'Å' => 'O',
        'ÅŽ' => 'O', 'Å”' => 'R', 'Å˜' => 'R', 'Å–' => 'R', 'Åš' => 'S', 'Åž' => 'S',
        'Åœ' => 'S', 'È˜' => 'S', 'Å ' => 'S', 'Å¤' => 'T', 'Å¢' => 'T', 'Å¦' => 'T',
        'Èš' => 'T', 'Ã™' => 'U', 'Ãš' => 'U', 'Ã›' => 'U', 'Åª' => 'U', 'Å®' => 'U',
        'Å°' => 'U', 'Å¬' => 'U', 'Å¨' => 'U', 'Å²' => 'U', 'Å´' => 'W', 'Å¶' => 'Y',
        'Å¸' => 'Y', 'Ã' => 'Y', 'Å¹' => 'Z', 'Å»' => 'Z', 'Å½' => 'Z', 'Ã ' => 'a',
        'Ã¡' => 'a', 'Ã¢' => 'a', 'Ã£' => 'a', 'Ä' => 'a', 'Ä…' => 'a', 'Äƒ' => 'a',
        'Ã¥' => 'a', 'Ã§' => 'c', 'Ä‡' => 'c', 'Ä' => 'c', 'Ä‰' => 'c', 'Ä‹' => 'c',
        'Ä' => 'd', 'Ä‘' => 'd', 'Ã¨' => 'e', 'Ã©' => 'e', 'Ãª' => 'e', 'Ã«' => 'e',
        'Ä“' => 'e', 'Ä™' => 'e', 'Ä›' => 'e', 'Ä•' => 'e', 'Ä—' => 'e', 'Æ’' => 'f',
        'Ä' => 'g', 'ÄŸ' => 'g', 'Ä¡' => 'g', 'Ä£' => 'g', 'Ä¥' => 'h', 'Ä§' => 'h',
        'Ã¬' => 'i', 'Ã' => 'i', 'Ã®' => 'i', 'Ã¯' => 'i', 'Ä«' => 'i', 'Ä©' => 'i',
        'Ä' => 'i', 'Ä¯' => 'i', 'Ä±' => 'i', 'Äµ' => 'j', 'Ä·' => 'k', 'Ä¸' => 'k',
        'Å‚' => 'l', 'Ä¾' => 'l', 'Äº' => 'l', 'Ä¼' => 'l', 'Å€' => 'l', 'Ã±' => 'n',
        'Å„' => 'n', 'Åˆ' => 'n', 'Å†' => 'n', 'Å‰' => 'n', 'Å‹' => 'n', 'Ã²' => 'o',
        'Ã³' => 'o', 'Ã´' => 'o', 'Ãµ' => 'o', 'Ã¸' => 'o', 'Å' => 'o', 'Å‘' => 'o',
        'Å' => 'o', 'Å•' => 'r', 'Å™' => 'r', 'Å—' => 'r', 'Å›' => 's', 'Å¡' => 's',
        'Å¥' => 't', 'Ã¹' => 'u', 'Ãº' => 'u', 'Ã»' => 'u', 'Å«' => 'u', 'Å¯' => 'u',
        'Å±' => 'u', 'Å' => 'u', 'Å©' => 'u', 'Å³' => 'u', 'Åµ' => 'w', 'Ã¿' => 'y',
        'Ã½' => 'y', 'Å·' => 'y', 'Å¼' => 'z', 'Åº' => 'z', 'Å¾' => 'z', 'Î‘' => 'A',
        'Î†' => 'A', 'á¼ˆ' => 'A', 'á¼‰' => 'A', 'á¼Š' => 'A', 'á¼‹' => 'A', 'á¼Œ' => 'A',
        'á¼' => 'A', 'á¼Ž' => 'A', 'á¼' => 'A', 'á¾ˆ' => 'A', 'á¾‰' => 'A', 'á¾Š' => 'A',
        'á¾‹' => 'A', 'á¾Œ' => 'A', 'á¾' => 'A', 'á¾Ž' => 'A', 'á¾' => 'A', 'á¾¸' => 'A',
        'á¾¹' => 'A', 'á¾º' => 'A', 'á¾¼' => 'A', 'Î’' => 'B', 'Î“' => 'G', 'Î”' => 'D',
        'Î•' => 'E', 'Îˆ' => 'E', 'á¼˜' => 'E', 'á¼™' => 'E', 'á¼š' => 'E', 'á¼›' => 'E',
        'á¼œ' => 'E', 'á¼' => 'E', 'á¿ˆ' => 'E', 'Î–' => 'Z', 'Î—' => 'I', 'Î‰' => 'I',
        'á¼¨' => 'I', 'á¼©' => 'I', 'á¼ª' => 'I', 'á¼«' => 'I', 'á¼¬' => 'I', 'á¼' => 'I',
        'á¼®' => 'I', 'á¼¯' => 'I', 'á¾˜' => 'I', 'á¾™' => 'I', 'á¾š' => 'I', 'á¾›' => 'I',
        'á¾œ' => 'I', 'á¾' => 'I', 'á¾ž' => 'I', 'á¾Ÿ' => 'I', 'á¿Š' => 'I', 'á¿Œ' => 'I',
        'Î˜' => 'T', 'Î™' => 'I', 'ÎŠ' => 'I', 'Îª' => 'I', 'á¼¸' => 'I', 'á¼¹' => 'I',
        'á¼º' => 'I', 'á¼»' => 'I', 'á¼¼' => 'I', 'á¼½' => 'I', 'á¼¾' => 'I', 'á¼¿' => 'I',
        'á¿˜' => 'I', 'á¿™' => 'I', 'á¿š' => 'I', 'Îš' => 'K', 'Î›' => 'L', 'Îœ' => 'M',
        'Î' => 'N', 'Îž' => 'K', 'ÎŸ' => 'O', 'ÎŒ' => 'O', 'á½ˆ' => 'O', 'á½‰' => 'O',
        'á½Š' => 'O', 'á½‹' => 'O', 'á½Œ' => 'O', 'á½' => 'O', 'á¿¸' => 'O', 'Î ' => 'P',
        'Î¡' => 'R', 'á¿¬' => 'R', 'Î£' => 'S', 'Î¤' => 'T', 'Î¥' => 'Y', 'ÎŽ' => 'Y',
        'Î«' => 'Y', 'á½™' => 'Y', 'á½›' => 'Y', 'á½' => 'Y', 'á½Ÿ' => 'Y', 'á¿¨' => 'Y',
        'á¿©' => 'Y', 'á¿ª' => 'Y', 'Î¦' => 'F', 'Î§' => 'X', 'Î¨' => 'P', 'Î©' => 'O',
        'Î' => 'O', 'á½¨' => 'O', 'á½©' => 'O', 'á½ª' => 'O', 'á½«' => 'O', 'á½¬' => 'O',
        'á½' => 'O', 'á½®' => 'O', 'á½¯' => 'O', 'á¾¨' => 'O', 'á¾©' => 'O', 'á¾ª' => 'O',
        'á¾«' => 'O', 'á¾¬' => 'O', 'á¾' => 'O', 'á¾®' => 'O', 'á¾¯' => 'O', 'á¿º' => 'O',
        'á¿¼' => 'O', 'Î±' => 'a', 'Î¬' => 'a', 'á¼€' => 'a', 'á¼' => 'a', 'á¼‚' => 'a',
        'á¼ƒ' => 'a', 'á¼„' => 'a', 'á¼…' => 'a', 'á¼†' => 'a', 'á¼‡' => 'a', 'á¾€' => 'a',
        'á¾' => 'a', 'á¾‚' => 'a', 'á¾ƒ' => 'a', 'á¾„' => 'a', 'á¾…' => 'a', 'á¾†' => 'a',
        'á¾‡' => 'a', 'á½°' => 'a', 'á¾°' => 'a', 'á¾±' => 'a', 'á¾²' => 'a', 'á¾³' => 'a',
        'á¾´' => 'a', 'á¾¶' => 'a', 'á¾·' => 'a', 'Î²' => 'b', 'Î³' => 'g', 'Î´' => 'd',
        'Îµ' => 'e', 'Î' => 'e', 'á¼' => 'e', 'á¼‘' => 'e', 'á¼’' => 'e', 'á¼“' => 'e',
        'á¼”' => 'e', 'á¼•' => 'e', 'á½²' => 'e', 'Î¶' => 'z', 'Î·' => 'i', 'Î®' => 'i',
        'á¼ ' => 'i', 'á¼¡' => 'i', 'á¼¢' => 'i', 'á¼£' => 'i', 'á¼¤' => 'i', 'á¼¥' => 'i',
        'á¼¦' => 'i', 'á¼§' => 'i', 'á¾' => 'i', 'á¾‘' => 'i', 'á¾’' => 'i', 'á¾“' => 'i',
        'á¾”' => 'i', 'á¾•' => 'i', 'á¾–' => 'i', 'á¾—' => 'i', 'á½´' => 'i', 'á¿‚' => 'i',
        'á¿ƒ' => 'i', 'á¿„' => 'i', 'á¿†' => 'i', 'á¿‡' => 'i', 'Î¸' => 't', 'Î¹' => 'i',
        'Î¯' => 'i', 'ÏŠ' => 'i', 'Î' => 'i', 'á¼°' => 'i', 'á¼±' => 'i', 'á¼²' => 'i',
        'á¼³' => 'i', 'á¼´' => 'i', 'á¼µ' => 'i', 'á¼¶' => 'i', 'á¼·' => 'i', 'á½¶' => 'i',
        'á¿' => 'i', 'á¿‘' => 'i', 'á¿’' => 'i', 'á¿–' => 'i', 'á¿—' => 'i', 'Îº' => 'k',
        'Î»' => 'l', 'Î¼' => 'm', 'Î½' => 'n', 'Î¾' => 'k', 'Î¿' => 'o', 'ÏŒ' => 'o',
        'á½€' => 'o', 'á½' => 'o', 'á½‚' => 'o', 'á½ƒ' => 'o', 'á½„' => 'o', 'á½…' => 'o',
        'á½¸' => 'o', 'Ï€' => 'p', 'Ï' => 'r', 'á¿¤' => 'r', 'á¿¥' => 'r', 'Ïƒ' => 's',
        'Ï‚' => 's', 'Ï„' => 't', 'Ï…' => 'y', 'Ï' => 'y', 'Ï‹' => 'y', 'Î°' => 'y',
        'á½' => 'y', 'á½‘' => 'y', 'á½’' => 'y', 'á½“' => 'y', 'á½”' => 'y', 'á½•' => 'y',
        'á½–' => 'y', 'á½—' => 'y', 'á½º' => 'y', 'á¿ ' => 'y', 'á¿¡' => 'y', 'á¿¢' => 'y',
        'á¿¦' => 'y', 'á¿§' => 'y', 'Ï†' => 'f', 'Ï‡' => 'x', 'Ïˆ' => 'p', 'Ï‰' => 'o',
        'ÏŽ' => 'o', 'á½ ' => 'o', 'á½¡' => 'o', 'á½¢' => 'o', 'á½£' => 'o', 'á½¤' => 'o',
        'á½¥' => 'o', 'á½¦' => 'o', 'á½§' => 'o', 'á¾ ' => 'o', 'á¾¡' => 'o', 'á¾¢' => 'o',
        'á¾£' => 'o', 'á¾¤' => 'o', 'á¾¥' => 'o', 'á¾¦' => 'o', 'á¾§' => 'o', 'á½¼' => 'o',
        'á¿²' => 'o', 'á¿³' => 'o', 'á¿´' => 'o', 'á¿¶' => 'o', 'á¿·' => 'o', 'Ð' => 'A',
        'Ð‘' => 'B', 'Ð’' => 'V', 'Ð“' => 'G', 'Ð”' => 'D', 'Ð•' => 'E', 'Ð' => 'E',
        'Ð–' => 'Z', 'Ð—' => 'Z', 'Ð˜' => 'I', 'Ð™' => 'I', 'Ðš' => 'K', 'Ð›' => 'L',
        'Ðœ' => 'M', 'Ð' => 'N', 'Ðž' => 'O', 'ÐŸ' => 'P', 'Ð ' => 'R', 'Ð¡' => 'S',
        'Ð¢' => 'T', 'Ð£' => 'U', 'Ð¤' => 'F', 'Ð¥' => 'K', 'Ð¦' => 'T', 'Ð§' => 'C',
        'Ð¨' => 'S', 'Ð©' => 'S', 'Ð«' => 'Y', 'Ð' => 'E', 'Ð®' => 'Y', 'Ð¯' => 'Y',
        'Ð°' => 'A', 'Ð±' => 'B', 'Ð²' => 'V', 'Ð³' => 'G', 'Ð´' => 'D', 'Ðµ' => 'E',
        'Ñ‘' => 'E', 'Ð¶' => 'Z', 'Ð·' => 'Z', 'Ð¸' => 'I', 'Ð¹' => 'I', 'Ðº' => 'K',
        'Ð»' => 'L', 'Ð¼' => 'M', 'Ð½' => 'N', 'Ð¾' => 'O', 'Ð¿' => 'P', 'Ñ€' => 'R',
        'Ñ' => 'S', 'Ñ‚' => 'T', 'Ñƒ' => 'U', 'Ñ„' => 'F', 'Ñ…' => 'K', 'Ñ†' => 'T',
        'Ñ‡' => 'C', 'Ñˆ' => 'S', 'Ñ‰' => 'S', 'Ñ‹' => 'Y', 'Ñ' => 'E', 'ÑŽ' => 'Y',
        'Ñ' => 'Y', 'Ã°' => 'd', 'Ã' => 'D', 'Ã¾' => 't', 'Ãž' => 'T', 'áƒ' => 'a',
        'áƒ‘' => 'b', 'áƒ’' => 'g', 'áƒ“' => 'd', 'áƒ”' => 'e', 'áƒ•' => 'v', 'áƒ–' => 'z',
        'áƒ—' => 't', 'áƒ˜' => 'i', 'áƒ™' => 'k', 'áƒš' => 'l', 'áƒ›' => 'm', 'áƒœ' => 'n',
        'áƒ' => 'o', 'áƒž' => 'p', 'áƒŸ' => 'z', 'áƒ ' => 'r', 'áƒ¡' => 's', 'áƒ¢' => 't',
        'áƒ£' => 'u', 'áƒ¤' => 'p', 'áƒ¥' => 'k', 'áƒ¦' => 'g', 'áƒ§' => 'q', 'áƒ¨' => 's',
        'áƒ©' => 'c', 'áƒª' => 't', 'áƒ«' => 'd', 'áƒ¬' => 't', 'áƒ' => 'c', 'áƒ®' => 'k',
        'áƒ¯' => 'j', 'áƒ°' => 'h',
    );
    
    return str_replace(array_keys($transliteration), array_values($transliteration), $str);
}

Revision: 57885

at June 13, 2012 20:14 by MGHollander

Updated Code

<?php

/**
 * Unaccent a string. An example string like `Ã€Ã˜Ä—Ã¿á¾œá½¨Î¶á½…Ð‘ÑŽ`
 * will be translated to `AOeyIOzoBY`. More complete than :
 *   strtr( (string)$str,
 *          "Ã€ÃÃ‚ÃƒÃ„Ã…Ã Ã¡Ã¢Ã£Ã¤Ã¥Ã’Ã“Ã”Ã•Ã–Ã˜Ã²Ã³Ã´ÃµÃ¶Ã¸ÃˆÃ‰ÃŠÃ‹Ã¨Ã©ÃªÃ«Ã‡Ã§ÃŒÃÃŽÃÃ¬ÃÃ®Ã¯Ã™ÃšÃ›ÃœÃ¹ÃºÃ»Ã¼Ã¿Ã‘Ã±",
 *          "aaaaaaaaaaaaooooooooooooeeeeeeeecciiiiiiiiuuuuuuuuynn" );
 *
 * @param $str input string
 * @param $utf8 if null, function will detect input string encoding
 * @return string input string without accent
 */
function remove_accents( $str, $utf8=true )
{
    $str = (string)$str;
    if( is_null($utf8) ) {
        if( !function_exists('mb_detect_encoding') ) {
            $utf8 = (strtolower( mb_detect_encoding($str) )=='utf-8');
        } else {
            $length = strlen($str);
            $utf8 = true;
            for ($i=0; $i < $length; $i++) {
                $c = ord($str[$i]);
                if ($c < 0x80) $n = 0; # 0bbbbbbb
                elseif (($c & 0xE0) == 0xC0) $n=1; # 110bbbbb
                elseif (($c & 0xF0) == 0xE0) $n=2; # 1110bbbb
                elseif (($c & 0xF8) == 0xF0) $n=3; # 11110bbb
                elseif (($c & 0xFC) == 0xF8) $n=4; # 111110bb
                elseif (($c & 0xFE) == 0xFC) $n=5; # 1111110b
                else return false; # Does not match any model
                for ($j=0; $j<$n; $j++) { # n bytes matching 10bbbbbb follow ?
                    if ((++$i == $length)
                        || ((ord($str[$i]) & 0xC0) != 0x80)) {
                        $utf8 = false;
                        break;
                    }
                    
                }
            }
        }
        
    }
    
    if(!$utf8)
        $str = utf8_encode($str);

    $transliteration = array(
    'Ä²' => 'I', 'Ã–' => 'O','Å’' => 'O','Ãœ' => 'U','Ã¤' => 'a','Ã¦' => 'a',
    'Ä³' => 'i','Ã¶' => 'o','Å“' => 'o','Ã¼' => 'u','ÃŸ' => 's','Å¿' => 's',
    'Ã€' => 'A','Ã' => 'A','Ã‚' => 'A','Ãƒ' => 'A','Ã„' => 'A','Ã…' => 'A',
    'Ã†' => 'A','Ä€' => 'A','Ä„' => 'A','Ä‚' => 'A','Ã‡' => 'C','Ä†' => 'C',
    'ÄŒ' => 'C','Äˆ' => 'C','ÄŠ' => 'C','ÄŽ' => 'D','Ä' => 'D','Ãˆ' => 'E',
    'Ã‰' => 'E','ÃŠ' => 'E','Ã‹' => 'E','Ä’' => 'E','Ä˜' => 'E','Äš' => 'E',
    'Ä”' => 'E','Ä–' => 'E','Äœ' => 'G','Äž' => 'G','Ä ' => 'G','Ä¢' => 'G',
    'Ä¤' => 'H','Ä¦' => 'H','ÃŒ' => 'I','Ã' => 'I','ÃŽ' => 'I','Ã' => 'I',
    'Äª' => 'I','Ä¨' => 'I','Ä¬' => 'I','Ä®' => 'I','Ä°' => 'I','Ä´' => 'J',
    'Ä¶' => 'K','Ä½' => 'K','Ä¹' => 'K','Ä»' => 'K','Ä¿' => 'K','Å' => 'L',
    'Ã‘' => 'N','Åƒ' => 'N','Å‡' => 'N','Å…' => 'N','ÅŠ' => 'N','Ã’' => 'O',
    'Ã“' => 'O','Ã”' => 'O','Ã•' => 'O','Ã˜' => 'O','ÅŒ' => 'O','Å' => 'O',
    'ÅŽ' => 'O','Å”' => 'R','Å˜' => 'R','Å–' => 'R','Åš' => 'S','Åž' => 'S',
    'Åœ' => 'S','È˜' => 'S','Å ' => 'S','Å¤' => 'T','Å¢' => 'T','Å¦' => 'T',
    'Èš' => 'T','Ã™' => 'U','Ãš' => 'U','Ã›' => 'U','Åª' => 'U','Å®' => 'U',
    'Å°' => 'U','Å¬' => 'U','Å¨' => 'U','Å²' => 'U','Å´' => 'W','Å¶' => 'Y',
    'Å¸' => 'Y','Ã' => 'Y','Å¹' => 'Z','Å»' => 'Z','Å½' => 'Z','Ã ' => 'a',
    'Ã¡' => 'a','Ã¢' => 'a','Ã£' => 'a','Ä' => 'a','Ä…' => 'a','Äƒ' => 'a',
    'Ã¥' => 'a','Ã§' => 'c','Ä‡' => 'c','Ä' => 'c','Ä‰' => 'c','Ä‹' => 'c',
    'Ä' => 'd','Ä‘' => 'd','Ã¨' => 'e','Ã©' => 'e','Ãª' => 'e','Ã«' => 'e',
    'Ä“' => 'e','Ä™' => 'e','Ä›' => 'e','Ä•' => 'e','Ä—' => 'e','Æ’' => 'f',
    'Ä' => 'g','ÄŸ' => 'g','Ä¡' => 'g','Ä£' => 'g','Ä¥' => 'h','Ä§' => 'h',
    'Ã¬' => 'i','Ã' => 'i','Ã®' => 'i','Ã¯' => 'i','Ä«' => 'i','Ä©' => 'i',
    'Ä' => 'i','Ä¯' => 'i','Ä±' => 'i','Äµ' => 'j','Ä·' => 'k','Ä¸' => 'k',
    'Å‚' => 'l','Ä¾' => 'l','Äº' => 'l','Ä¼' => 'l','Å€' => 'l','Ã±' => 'n',
    'Å„' => 'n','Åˆ' => 'n','Å†' => 'n','Å‰' => 'n','Å‹' => 'n','Ã²' => 'o',
    'Ã³' => 'o','Ã´' => 'o','Ãµ' => 'o','Ã¸' => 'o','Å' => 'o','Å‘' => 'o',
    'Å' => 'o','Å•' => 'r','Å™' => 'r','Å—' => 'r','Å›' => 's','Å¡' => 's',
    'Å¥' => 't','Ã¹' => 'u','Ãº' => 'u','Ã»' => 'u','Å«' => 'u','Å¯' => 'u',
    'Å±' => 'u','Å' => 'u','Å©' => 'u','Å³' => 'u','Åµ' => 'w','Ã¿' => 'y',
    'Ã½' => 'y','Å·' => 'y','Å¼' => 'z','Åº' => 'z','Å¾' => 'z','Î‘' => 'A',
    'Î†' => 'A','á¼ˆ' => 'A','á¼‰' => 'A','á¼Š' => 'A','á¼‹' => 'A','á¼Œ' => 'A',
    'á¼' => 'A','á¼Ž' => 'A','á¼' => 'A','á¾ˆ' => 'A','á¾‰' => 'A','á¾Š' => 'A',
    'á¾‹' => 'A','á¾Œ' => 'A','á¾' => 'A','á¾Ž' => 'A','á¾' => 'A','á¾¸' => 'A',
    'á¾¹' => 'A','á¾º' => 'A','á¾¼' => 'A','Î’' => 'B','Î“' => 'G','Î”' => 'D',
    'Î•' => 'E','Îˆ' => 'E','á¼˜' => 'E','á¼™' => 'E','á¼š' => 'E','á¼›' => 'E',
    'á¼œ' => 'E','á¼' => 'E','á¿ˆ' => 'E','Î–' => 'Z','Î—' => 'I','Î‰' => 'I',
    'á¼¨' => 'I','á¼©' => 'I','á¼ª' => 'I','á¼«' => 'I','á¼¬' => 'I','á¼' => 'I',
    'á¼®' => 'I','á¼¯' => 'I','á¾˜' => 'I','á¾™' => 'I','á¾š' => 'I','á¾›' => 'I',
    'á¾œ' => 'I','á¾' => 'I','á¾ž' => 'I','á¾Ÿ' => 'I','á¿Š' => 'I','á¿Œ' => 'I',
    'Î˜' => 'T','Î™' => 'I','ÎŠ' => 'I','Îª' => 'I','á¼¸' => 'I','á¼¹' => 'I',
    'á¼º' => 'I','á¼»' => 'I','á¼¼' => 'I','á¼½' => 'I','á¼¾' => 'I','á¼¿' => 'I',
    'á¿˜' => 'I','á¿™' => 'I','á¿š' => 'I','Îš' => 'K','Î›' => 'L','Îœ' => 'M',
    'Î' => 'N','Îž' => 'K','ÎŸ' => 'O','ÎŒ' => 'O','á½ˆ' => 'O','á½‰' => 'O',
    'á½Š' => 'O','á½‹' => 'O','á½Œ' => 'O','á½' => 'O','á¿¸' => 'O','Î ' => 'P',
    'Î¡' => 'R','á¿¬' => 'R','Î£' => 'S','Î¤' => 'T','Î¥' => 'Y','ÎŽ' => 'Y',
    'Î«' => 'Y','á½™' => 'Y','á½›' => 'Y','á½' => 'Y','á½Ÿ' => 'Y','á¿¨' => 'Y',
    'á¿©' => 'Y','á¿ª' => 'Y','Î¦' => 'F','Î§' => 'X','Î¨' => 'P','Î©' => 'O',
    'Î' => 'O','á½¨' => 'O','á½©' => 'O','á½ª' => 'O','á½«' => 'O','á½¬' => 'O',
    'á½' => 'O','á½®' => 'O','á½¯' => 'O','á¾¨' => 'O','á¾©' => 'O','á¾ª' => 'O',
    'á¾«' => 'O','á¾¬' => 'O','á¾' => 'O','á¾®' => 'O','á¾¯' => 'O','á¿º' => 'O',
    'á¿¼' => 'O','Î±' => 'a','Î¬' => 'a','á¼€' => 'a','á¼' => 'a','á¼‚' => 'a',
    'á¼ƒ' => 'a','á¼„' => 'a','á¼…' => 'a','á¼†' => 'a','á¼‡' => 'a','á¾€' => 'a',
    'á¾' => 'a','á¾‚' => 'a','á¾ƒ' => 'a','á¾„' => 'a','á¾…' => 'a','á¾†' => 'a',
    'á¾‡' => 'a','á½°' => 'a','á¾°' => 'a','á¾±' => 'a','á¾²' => 'a','á¾³' => 'a',
    'á¾´' => 'a','á¾¶' => 'a','á¾·' => 'a','Î²' => 'b','Î³' => 'g','Î´' => 'd',
    'Îµ' => 'e','Î' => 'e','á¼' => 'e','á¼‘' => 'e','á¼’' => 'e','á¼“' => 'e',
    'á¼”' => 'e','á¼•' => 'e','á½²' => 'e','Î¶' => 'z','Î·' => 'i','Î®' => 'i',
    'á¼ ' => 'i','á¼¡' => 'i','á¼¢' => 'i','á¼£' => 'i','á¼¤' => 'i','á¼¥' => 'i',
    'á¼¦' => 'i','á¼§' => 'i','á¾' => 'i','á¾‘' => 'i','á¾’' => 'i','á¾“' => 'i',
    'á¾”' => 'i','á¾•' => 'i','á¾–' => 'i','á¾—' => 'i','á½´' => 'i','á¿‚' => 'i',
    'á¿ƒ' => 'i','á¿„' => 'i','á¿†' => 'i','á¿‡' => 'i','Î¸' => 't','Î¹' => 'i',
    'Î¯' => 'i','ÏŠ' => 'i','Î' => 'i','á¼°' => 'i','á¼±' => 'i','á¼²' => 'i',
    'á¼³' => 'i','á¼´' => 'i','á¼µ' => 'i','á¼¶' => 'i','á¼·' => 'i','á½¶' => 'i',
    'á¿' => 'i','á¿‘' => 'i','á¿’' => 'i','á¿–' => 'i','á¿—' => 'i','Îº' => 'k',
    'Î»' => 'l','Î¼' => 'm','Î½' => 'n','Î¾' => 'k','Î¿' => 'o','ÏŒ' => 'o',
    'á½€' => 'o','á½' => 'o','á½‚' => 'o','á½ƒ' => 'o','á½„' => 'o','á½…' => 'o',
    'á½¸' => 'o','Ï€' => 'p','Ï' => 'r','á¿¤' => 'r','á¿¥' => 'r','Ïƒ' => 's',
    'Ï‚' => 's','Ï„' => 't','Ï…' => 'y','Ï' => 'y','Ï‹' => 'y','Î°' => 'y',
    'á½' => 'y','á½‘' => 'y','á½’' => 'y','á½“' => 'y','á½”' => 'y','á½•' => 'y',
    'á½–' => 'y','á½—' => 'y','á½º' => 'y','á¿ ' => 'y','á¿¡' => 'y','á¿¢' => 'y',
    'á¿¦' => 'y','á¿§' => 'y','Ï†' => 'f','Ï‡' => 'x','Ïˆ' => 'p','Ï‰' => 'o',
    'ÏŽ' => 'o','á½ ' => 'o','á½¡' => 'o','á½¢' => 'o','á½£' => 'o','á½¤' => 'o',
    'á½¥' => 'o','á½¦' => 'o','á½§' => 'o','á¾ ' => 'o','á¾¡' => 'o','á¾¢' => 'o',
    'á¾£' => 'o','á¾¤' => 'o','á¾¥' => 'o','á¾¦' => 'o','á¾§' => 'o','á½¼' => 'o',
    'á¿²' => 'o','á¿³' => 'o','á¿´' => 'o','á¿¶' => 'o','á¿·' => 'o','Ð' => 'A',
    'Ð‘' => 'B','Ð’' => 'V','Ð“' => 'G','Ð”' => 'D','Ð•' => 'E','Ð' => 'E',
    'Ð–' => 'Z','Ð—' => 'Z','Ð˜' => 'I','Ð™' => 'I','Ðš' => 'K','Ð›' => 'L',
    'Ðœ' => 'M','Ð' => 'N','Ðž' => 'O','ÐŸ' => 'P','Ð ' => 'R','Ð¡' => 'S',
    'Ð¢' => 'T','Ð£' => 'U','Ð¤' => 'F','Ð¥' => 'K','Ð¦' => 'T','Ð§' => 'C',
    'Ð¨' => 'S','Ð©' => 'S','Ð«' => 'Y','Ð' => 'E','Ð®' => 'Y','Ð¯' => 'Y',
    'Ð°' => 'A','Ð±' => 'B','Ð²' => 'V','Ð³' => 'G','Ð´' => 'D','Ðµ' => 'E',
    'Ñ‘' => 'E','Ð¶' => 'Z','Ð·' => 'Z','Ð¸' => 'I','Ð¹' => 'I','Ðº' => 'K',
    'Ð»' => 'L','Ð¼' => 'M','Ð½' => 'N','Ð¾' => 'O','Ð¿' => 'P','Ñ€' => 'R',
    'Ñ' => 'S','Ñ‚' => 'T','Ñƒ' => 'U','Ñ„' => 'F','Ñ…' => 'K','Ñ†' => 'T',
    'Ñ‡' => 'C','Ñˆ' => 'S','Ñ‰' => 'S','Ñ‹' => 'Y','Ñ' => 'E','ÑŽ' => 'Y',
    'Ñ' => 'Y','Ã°' => 'd','Ã' => 'D','Ã¾' => 't','Ãž' => 'T','áƒ' => 'a',
    'áƒ‘' => 'b','áƒ’' => 'g','áƒ“' => 'd','áƒ”' => 'e','áƒ•' => 'v','áƒ–' => 'z',
    'áƒ—' => 't','áƒ˜' => 'i','áƒ™' => 'k','áƒš' => 'l','áƒ›' => 'm','áƒœ' => 'n',
    'áƒ' => 'o','áƒž' => 'p','áƒŸ' => 'z','áƒ ' => 'r','áƒ¡' => 's','áƒ¢' => 't',
    'áƒ£' => 'u','áƒ¤' => 'p','áƒ¥' => 'k','áƒ¦' => 'g','áƒ§' => 'q','áƒ¨' => 's',
    'áƒ©' => 'c','áƒª' => 't','áƒ«' => 'd','áƒ¬' => 't','áƒ' => 'c','áƒ®' => 'k',
    'áƒ¯' => 'j','áƒ°' => 'h'
    );
    $str = str_replace( array_keys( $transliteration ),
                        array_values( $transliteration ),
                        $str);
    return $str;
}

Revision: 57884

at June 13, 2012 20:10 by MGHollander

Updated Code

/**
 * Unaccent a string. An example string like Ã€Ã˜Ä—Ã¿á¾œá½¨Î¶á½…Ð‘ÑŽ
 * will be translated to AOeyIOzoBY. 
 *
 * More complete than:
 *   strtr( (string)$str,
 *          "Ã€ÃÃ‚ÃƒÃ„Ã…Ã Ã¡Ã¢Ã£Ã¤Ã¥Ã’Ã“Ã”Ã•Ã–Ã˜Ã²Ã³Ã´ÃµÃ¶Ã¸ÃˆÃ‰ÃŠÃ‹Ã¨Ã©ÃªÃ«Ã‡Ã§ÃŒÃÃŽÃÃ¬ÃÃ®Ã¯Ã™ÃšÃ›ÃœÃ¹ÃºÃ»Ã¼Ã¿Ã‘Ã±",
 *          "aaaaaaaaaaaaooooooooooooeeeeeeeecciiiiiiiiuuuuuuuuynn" );
 *
 * @param $str input string
 * @param $utf8 if null, function will detect input string encoding
 * @author http://www.evaisse.net/2008/php-translit-remove-accent-unaccent-21001
 * @return string input string without accent
 */
function removeAccents($str, $utf8 = true) {
    $str = (string)$str;
    if (is_null($utf8)) {
        if (!function_exists('mb_detect_encoding')) {
            $utf8 = (strtolower(mb_detect_encoding($str))=='utf-8');
        } else {
            $length = strlen($str);
            $utf8 = true;
            for ($i = 0; $i < $length; $i++) {
                $c = ord($str[$i]);
                if ($c < 0x80) $n = 0; # 0bbbbbbb
                elseif (($c & 0xE0) == 0xC0) $n = 1; # 110bbbbb
                elseif (($c & 0xF0) == 0xE0) $n = 2; # 1110bbbb
                elseif (($c & 0xF8) == 0xF0) $n = 3; # 11110bbb
                elseif (($c & 0xFC) == 0xF8) $n = 4; # 111110bb
                elseif (($c & 0xFE) == 0xFC) $n = 5; # 1111110b
                else return false; # Does not match any model
                for ($j = 0; $j < $n; $j++) { # n bytes matching 10bbbbbb follow ?
                    if ((++$i == $length) || ((ord($str[$i]) & 0xC0) != 0x80)) {
                        $utf8 = false;
                        break;
                    }

                }
            }
        }

    }

    if (!$utf8) {
        $str = utf8_encode($str);
    }
    
    $transliteration = array(
        '?' => 'I', 'Ã–' => 'O','Å’' => 'O','Ãœ' => 'U','Ã¤' => 'a','Ã¦' => 'a',
        '?' => 'i','Ã¶' => 'o','Å“' => 'o','Ã¼' => 'u','ÃŸ' => 's','?' => 's',
        'Ã€' => 'A','Ã' => 'A','Ã‚' => 'A','Ãƒ' => 'A','Ã„' => 'A','Ã…' => 'A',
        'Ã†' => 'A','A' => 'A','A' => 'A','A' => 'A','Ã‡' => 'C','C' => 'C',
        'C' => 'C','C' => 'C','C' => 'C','D' => 'D','Ã' => 'D','Ãˆ' => 'E',
        'Ã‰' => 'E','ÃŠ' => 'E','Ã‹' => 'E','E' => 'E','E' => 'E','E' => 'E',
        'E' => 'E','E' => 'E','G' => 'G','G' => 'G','G' => 'G','G' => 'G',
        'H' => 'H','H' => 'H','ÃŒ' => 'I','Ã' => 'I','ÃŽ' => 'I','Ã' => 'I',
        'I' => 'I','I' => 'I','I' => 'I','I' => 'I','I' => 'I','J' => 'J',
        'K' => 'K','L' => 'K','L' => 'K','L' => 'K','?' => 'K','L' => 'L',
        'Ã‘' => 'N','N' => 'N','N' => 'N','N' => 'N','?' => 'N','Ã’' => 'O',
        'Ã“' => 'O','Ã”' => 'O','Ã•' => 'O','Ã˜' => 'O','O' => 'O','O' => 'O',
        'O' => 'O','R' => 'R','R' => 'R','R' => 'R','S' => 'S','S' => 'S',
        'S' => 'S','?' => 'S','Å ' => 'S','T' => 'T','T' => 'T','T' => 'T',
        '?' => 'T','Ã™' => 'U','Ãš' => 'U','Ã›' => 'U','U' => 'U','U' => 'U',
        'U' => 'U','U' => 'U','U' => 'U','U' => 'U','W' => 'W','Y' => 'Y',
        'Å¸' => 'Y','Ã' => 'Y','Z' => 'Z','Z' => 'Z','Å½' => 'Z','Ã ' => 'a',
        'Ã¡' => 'a','Ã¢' => 'a','Ã£' => 'a','a' => 'a','a' => 'a','a' => 'a',
        'Ã¥' => 'a','Ã§' => 'c','c' => 'c','c' => 'c','c' => 'c','c' => 'c',
        'd' => 'd','d' => 'd','Ã¨' => 'e','Ã©' => 'e','Ãª' => 'e','Ã«' => 'e',
        'e' => 'e','e' => 'e','e' => 'e','e' => 'e','e' => 'e','Æ’' => 'f',
        'g' => 'g','g' => 'g','g' => 'g','g' => 'g','h' => 'h','h' => 'h',
        'Ã¬' => 'i','Ã' => 'i','Ã®' => 'i','Ã¯' => 'i','i' => 'i','i' => 'i',
        'i' => 'i','i' => 'i','i' => 'i','j' => 'j','k' => 'k','?' => 'k',
        'l' => 'l','l' => 'l','l' => 'l','l' => 'l','?' => 'l','Ã±' => 'n',
        'n' => 'n','n' => 'n','n' => 'n','?' => 'n','?' => 'n','Ã²' => 'o',
        'Ã³' => 'o','Ã´' => 'o','Ãµ' => 'o','Ã¸' => 'o','o' => 'o','o' => 'o',
        'o' => 'o','r' => 'r','r' => 'r','r' => 'r','s' => 's','Å¡' => 's',
        't' => 't','Ã¹' => 'u','Ãº' => 'u','Ã»' => 'u','u' => 'u','u' => 'u',
        'u' => 'u','u' => 'u','u' => 'u','u' => 'u','w' => 'w','Ã¿' => 'y',
        'Ã½' => 'y','y' => 'y','z' => 'z','z' => 'z','Å¾' => 'z','?' => 'A',
        '?' => 'A','?' => 'A','?' => 'A','?' => 'A','?' => 'A','?' => 'A',
        '?' => 'A','?' => 'A','?' => 'A','?' => 'A','?' => 'A','?' => 'A',
        '?' => 'A','?' => 'A','?' => 'A','?' => 'A','?' => 'A','?' => 'A',
        '?' => 'A','?' => 'A','?' => 'A','?' => 'B','G' => 'G','?' => 'D',
        '?' => 'E','?' => 'E','?' => 'E','?' => 'E','?' => 'E','?' => 'E',
        '?' => 'E','?' => 'E','?' => 'E','?' => 'Z','?' => 'I','?' => 'I',
        '?' => 'I','?' => 'I','?' => 'I','?' => 'I','?' => 'I','?' => 'I',
        '?' => 'I','?' => 'I','?' => 'I','?' => 'I','?' => 'I','?' => 'I',
        '?' => 'I','?' => 'I','?' => 'I','?' => 'I','?' => 'I','?' => 'I',
        'T' => 'T','?' => 'I','?' => 'I','?' => 'I','?' => 'I','?' => 'I',
        '?' => 'I','?' => 'I','?' => 'I','?' => 'I','?' => 'I','?' => 'I',
        '?' => 'I','?' => 'I','?' => 'I','?' => 'K','?' => 'L','?' => 'M',
        '?' => 'N','?' => 'K','?' => 'O','?' => 'O','?' => 'O','?' => 'O',
        '?' => 'O','?' => 'O','?' => 'O','?' => 'O','?' => 'O','?' => 'P',
        '?' => 'R','?' => 'R','S' => 'S','?' => 'T','?' => 'Y','?' => 'Y',
        '?' => 'Y','?' => 'Y','?' => 'Y','?' => 'Y','?' => 'Y','?' => 'Y',
        '?' => 'Y','?' => 'Y','F' => 'F','?' => 'X','?' => 'P','O' => 'O',
        '?' => 'O','?' => 'O','?' => 'O','?' => 'O','?' => 'O','?' => 'O',
        '?' => 'O','?' => 'O','?' => 'O','?' => 'O','?' => 'O','?' => 'O',
        '?' => 'O','?' => 'O','?' => 'O','?' => 'O','?' => 'O','?' => 'O',
        '?' => 'O','a' => 'a','?' => 'a','?' => 'a','?' => 'a','?' => 'a',
        '?' => 'a','?' => 'a','?' => 'a','?' => 'a','?' => 'a','?' => 'a',
        '?' => 'a','?' => 'a','?' => 'a','?' => 'a','?' => 'a','?' => 'a',
        '?' => 'a','?' => 'a','?' => 'a','?' => 'a','?' => 'a','?' => 'a',
        '?' => 'a','?' => 'a','?' => 'a','ÃŸ' => 'b','?' => 'g','d' => 'd',
        'e' => 'e','?' => 'e','?' => 'e','?' => 'e','?' => 'e','?' => 'e',
        '?' => 'e','?' => 'e','?' => 'e','?' => 'z','?' => 'i','?' => 'i',
        '?' => 'i','?' => 'i','?' => 'i','?' => 'i','?' => 'i','?' => 'i',
        '?' => 'i','?' => 'i','?' => 'i','?' => 'i','?' => 'i','?' => 'i',
        '?' => 'i','?' => 'i','?' => 'i','?' => 'i','?' => 'i','?' => 'i',
        '?' => 'i','?' => 'i','?' => 'i','?' => 'i','?' => 't','?' => 'i',
        '?' => 'i','?' => 'i','?' => 'i','?' => 'i','?' => 'i','?' => 'i',
        '?' => 'i','?' => 'i','?' => 'i','?' => 'i','?' => 'i','?' => 'i',
        '?' => 'i','?' => 'i','?' => 'i','?' => 'i','?' => 'i','?' => 'k',
        '?' => 'l','Âµ' => 'm','?' => 'n','?' => 'k','?' => 'o','?' => 'o',
        '?' => 'o','?' => 'o','?' => 'o','?' => 'o','?' => 'o','?' => 'o',
        '?' => 'o','p' => 'p','?' => 'r','?' => 'r','?' => 'r','s' => 's',
        '?' => 's','t' => 't','?' => 'y','?' => 'y','?' => 'y','?' => 'y',
        '?' => 'y','?' => 'y','?' => 'y','?' => 'y','?' => 'y','?' => 'y',
        '?' => 'y','?' => 'y','?' => 'y','?' => 'y','?' => 'y','?' => 'y',
        '?' => 'y','?' => 'y','f' => 'f','?' => 'x','?' => 'p','?' => 'o',
        '?' => 'o','?' => 'o','?' => 'o','?' => 'o','?' => 'o','?' => 'o',
        '?' => 'o','?' => 'o','?' => 'o','?' => 'o','?' => 'o','?' => 'o',
        '?' => 'o','?' => 'o','?' => 'o','?' => 'o','?' => 'o','?' => 'o',
        '?' => 'o','?' => 'o','?' => 'o','?' => 'o','?' => 'o','?' => 'A',
        '?' => 'B','?' => 'V','?' => 'G','?' => 'D','?' => 'E','?' => 'E',
        '?' => 'Z','?' => 'Z','?' => 'I','?' => 'I','?' => 'K','?' => 'L',
        '?' => 'M','?' => 'N','?' => 'O','?' => 'P','?' => 'R','?' => 'S',
        '?' => 'T','?' => 'U','?' => 'F','?' => 'K','?' => 'T','?' => 'C',
        '?' => 'S','?' => 'S','?' => 'Y','?' => 'E','?' => 'Y','?' => 'Y',
        '?' => 'A','?' => 'B','?' => 'V','?' => 'G','?' => 'D','?' => 'E',
        '?' => 'E','?' => 'Z','?' => 'Z','?' => 'I','?' => 'I','?' => 'K',
        '?' => 'L','?' => 'M','?' => 'N','?' => 'O','?' => 'P','?' => 'R',
        '?' => 'S','?' => 'T','?' => 'U','?' => 'F','?' => 'K','?' => 'T',
        '?' => 'C','?' => 'S','?' => 'S','?' => 'Y','?' => 'E','?' => 'Y',
        '?' => 'Y','Ã°' => 'd','Ã' => 'D','Ã¾' => 't','Ãž' => 'T','?' => 'a',
        '?' => 'b','?' => 'g','?' => 'd','?' => 'e','?' => 'v','?' => 'z',
        '?' => 't','?' => 'i','?' => 'k','?' => 'l','?' => 'm','?' => 'n',
        '?' => 'o','?' => 'p','?' => 'z','?' => 'r','?' => 's','?' => 't',
        '?' => 'u','?' => 'p','?' => 'k','?' => 'g','?' => 'q','?' => 's',
        '?' => 'c','?' => 't','?' => 'd','?' => 't','?' => 'c','?' => 'k',
        '?' => 'j','?' => 'h',
    );
    
    $str = str_replace(array_keys( $transliteration ), array_values( $transliteration ), $str);
    
    return $str;
}

Revision: 57883

at June 13, 2012 20:08 by MGHollander

Updated Code

/**
 * Unaccent the input string string. An example string like Ã€Ã˜eÃ¿??????
 * will be translated to AOeyIOzoBY. 
 *
 * More complete than:
 *   strtr( (string)$str,
 *          "Ã€ÃÃ‚ÃƒÃ„Ã…Ã Ã¡Ã¢Ã£Ã¤Ã¥Ã’Ã“Ã”Ã•Ã–Ã˜Ã²Ã³Ã´ÃµÃ¶Ã¸ÃˆÃ‰ÃŠÃ‹Ã¨Ã©ÃªÃ«Ã‡Ã§ÃŒÃÃŽÃÃ¬ÃÃ®Ã¯Ã™ÃšÃ›ÃœÃ¹ÃºÃ»Ã¼Ã¿Ã‘Ã±",
 *          "aaaaaaaaaaaaooooooooooooeeeeeeeecciiiiiiiiuuuuuuuuynn" );
 *
 * @param $str input string
 * @param $utf8 if null, function will detect input string encoding
 * @author http://www.evaisse.net/2008/php-translit-remove-accent-unaccent-21001
 * @return string input string without accent
 */
function removeAccents($str, $utf8 = true) {
    $str = (string)$str;
    if (is_null($utf8)) {
        if (!function_exists('mb_detect_encoding')) {
            $utf8 = (strtolower(mb_detect_encoding($str))=='utf-8');
        } else {
            $length = strlen($str);
            $utf8 = true;
            for ($i = 0; $i < $length; $i++) {
                $c = ord($str[$i]);
                if ($c < 0x80) $n = 0; # 0bbbbbbb
                elseif (($c & 0xE0) == 0xC0) $n = 1; # 110bbbbb
                elseif (($c & 0xF0) == 0xE0) $n = 2; # 1110bbbb
                elseif (($c & 0xF8) == 0xF0) $n = 3; # 11110bbb
                elseif (($c & 0xFC) == 0xF8) $n = 4; # 111110bb
                elseif (($c & 0xFE) == 0xFC) $n = 5; # 1111110b
                else return false; # Does not match any model
                for ($j = 0; $j < $n; $j++) { # n bytes matching 10bbbbbb follow ?
                    if ((++$i == $length) || ((ord($str[$i]) & 0xC0) != 0x80)) {
                        $utf8 = false;
                        break;
                    }

                }
            }
        }

    }

    if (!$utf8) {
        $str = utf8_encode($str);
    }
    
    $transliteration = array(
        '?' => 'I', 'Ã–' => 'O','Å’' => 'O','Ãœ' => 'U','Ã¤' => 'a','Ã¦' => 'a',
        '?' => 'i','Ã¶' => 'o','Å“' => 'o','Ã¼' => 'u','ÃŸ' => 's','?' => 's',
        'Ã€' => 'A','Ã' => 'A','Ã‚' => 'A','Ãƒ' => 'A','Ã„' => 'A','Ã…' => 'A',
        'Ã†' => 'A','A' => 'A','A' => 'A','A' => 'A','Ã‡' => 'C','C' => 'C',
        'C' => 'C','C' => 'C','C' => 'C','D' => 'D','Ã' => 'D','Ãˆ' => 'E',
        'Ã‰' => 'E','ÃŠ' => 'E','Ã‹' => 'E','E' => 'E','E' => 'E','E' => 'E',
        'E' => 'E','E' => 'E','G' => 'G','G' => 'G','G' => 'G','G' => 'G',
        'H' => 'H','H' => 'H','ÃŒ' => 'I','Ã' => 'I','ÃŽ' => 'I','Ã' => 'I',
        'I' => 'I','I' => 'I','I' => 'I','I' => 'I','I' => 'I','J' => 'J',
        'K' => 'K','L' => 'K','L' => 'K','L' => 'K','?' => 'K','L' => 'L',
        'Ã‘' => 'N','N' => 'N','N' => 'N','N' => 'N','?' => 'N','Ã’' => 'O',
        'Ã“' => 'O','Ã”' => 'O','Ã•' => 'O','Ã˜' => 'O','O' => 'O','O' => 'O',
        'O' => 'O','R' => 'R','R' => 'R','R' => 'R','S' => 'S','S' => 'S',
        'S' => 'S','?' => 'S','Å ' => 'S','T' => 'T','T' => 'T','T' => 'T',
        '?' => 'T','Ã™' => 'U','Ãš' => 'U','Ã›' => 'U','U' => 'U','U' => 'U',
        'U' => 'U','U' => 'U','U' => 'U','U' => 'U','W' => 'W','Y' => 'Y',
        'Å¸' => 'Y','Ã' => 'Y','Z' => 'Z','Z' => 'Z','Å½' => 'Z','Ã ' => 'a',
        'Ã¡' => 'a','Ã¢' => 'a','Ã£' => 'a','a' => 'a','a' => 'a','a' => 'a',
        'Ã¥' => 'a','Ã§' => 'c','c' => 'c','c' => 'c','c' => 'c','c' => 'c',
        'd' => 'd','d' => 'd','Ã¨' => 'e','Ã©' => 'e','Ãª' => 'e','Ã«' => 'e',
        'e' => 'e','e' => 'e','e' => 'e','e' => 'e','e' => 'e','Æ’' => 'f',
        'g' => 'g','g' => 'g','g' => 'g','g' => 'g','h' => 'h','h' => 'h',
        'Ã¬' => 'i','Ã' => 'i','Ã®' => 'i','Ã¯' => 'i','i' => 'i','i' => 'i',
        'i' => 'i','i' => 'i','i' => 'i','j' => 'j','k' => 'k','?' => 'k',
        'l' => 'l','l' => 'l','l' => 'l','l' => 'l','?' => 'l','Ã±' => 'n',
        'n' => 'n','n' => 'n','n' => 'n','?' => 'n','?' => 'n','Ã²' => 'o',
        'Ã³' => 'o','Ã´' => 'o','Ãµ' => 'o','Ã¸' => 'o','o' => 'o','o' => 'o',
        'o' => 'o','r' => 'r','r' => 'r','r' => 'r','s' => 's','Å¡' => 's',
        't' => 't','Ã¹' => 'u','Ãº' => 'u','Ã»' => 'u','u' => 'u','u' => 'u',
        'u' => 'u','u' => 'u','u' => 'u','u' => 'u','w' => 'w','Ã¿' => 'y',
        'Ã½' => 'y','y' => 'y','z' => 'z','z' => 'z','Å¾' => 'z','?' => 'A',
        '?' => 'A','?' => 'A','?' => 'A','?' => 'A','?' => 'A','?' => 'A',
        '?' => 'A','?' => 'A','?' => 'A','?' => 'A','?' => 'A','?' => 'A',
        '?' => 'A','?' => 'A','?' => 'A','?' => 'A','?' => 'A','?' => 'A',
        '?' => 'A','?' => 'A','?' => 'A','?' => 'B','G' => 'G','?' => 'D',
        '?' => 'E','?' => 'E','?' => 'E','?' => 'E','?' => 'E','?' => 'E',
        '?' => 'E','?' => 'E','?' => 'E','?' => 'Z','?' => 'I','?' => 'I',
        '?' => 'I','?' => 'I','?' => 'I','?' => 'I','?' => 'I','?' => 'I',
        '?' => 'I','?' => 'I','?' => 'I','?' => 'I','?' => 'I','?' => 'I',
        '?' => 'I','?' => 'I','?' => 'I','?' => 'I','?' => 'I','?' => 'I',
        'T' => 'T','?' => 'I','?' => 'I','?' => 'I','?' => 'I','?' => 'I',
        '?' => 'I','?' => 'I','?' => 'I','?' => 'I','?' => 'I','?' => 'I',
        '?' => 'I','?' => 'I','?' => 'I','?' => 'K','?' => 'L','?' => 'M',
        '?' => 'N','?' => 'K','?' => 'O','?' => 'O','?' => 'O','?' => 'O',
        '?' => 'O','?' => 'O','?' => 'O','?' => 'O','?' => 'O','?' => 'P',
        '?' => 'R','?' => 'R','S' => 'S','?' => 'T','?' => 'Y','?' => 'Y',
        '?' => 'Y','?' => 'Y','?' => 'Y','?' => 'Y','?' => 'Y','?' => 'Y',
        '?' => 'Y','?' => 'Y','F' => 'F','?' => 'X','?' => 'P','O' => 'O',
        '?' => 'O','?' => 'O','?' => 'O','?' => 'O','?' => 'O','?' => 'O',
        '?' => 'O','?' => 'O','?' => 'O','?' => 'O','?' => 'O','?' => 'O',
        '?' => 'O','?' => 'O','?' => 'O','?' => 'O','?' => 'O','?' => 'O',
        '?' => 'O','a' => 'a','?' => 'a','?' => 'a','?' => 'a','?' => 'a',
        '?' => 'a','?' => 'a','?' => 'a','?' => 'a','?' => 'a','?' => 'a',
        '?' => 'a','?' => 'a','?' => 'a','?' => 'a','?' => 'a','?' => 'a',
        '?' => 'a','?' => 'a','?' => 'a','?' => 'a','?' => 'a','?' => 'a',
        '?' => 'a','?' => 'a','?' => 'a','ÃŸ' => 'b','?' => 'g','d' => 'd',
        'e' => 'e','?' => 'e','?' => 'e','?' => 'e','?' => 'e','?' => 'e',
        '?' => 'e','?' => 'e','?' => 'e','?' => 'z','?' => 'i','?' => 'i',
        '?' => 'i','?' => 'i','?' => 'i','?' => 'i','?' => 'i','?' => 'i',
        '?' => 'i','?' => 'i','?' => 'i','?' => 'i','?' => 'i','?' => 'i',
        '?' => 'i','?' => 'i','?' => 'i','?' => 'i','?' => 'i','?' => 'i',
        '?' => 'i','?' => 'i','?' => 'i','?' => 'i','?' => 't','?' => 'i',
        '?' => 'i','?' => 'i','?' => 'i','?' => 'i','?' => 'i','?' => 'i',
        '?' => 'i','?' => 'i','?' => 'i','?' => 'i','?' => 'i','?' => 'i',
        '?' => 'i','?' => 'i','?' => 'i','?' => 'i','?' => 'i','?' => 'k',
        '?' => 'l','Âµ' => 'm','?' => 'n','?' => 'k','?' => 'o','?' => 'o',
        '?' => 'o','?' => 'o','?' => 'o','?' => 'o','?' => 'o','?' => 'o',
        '?' => 'o','p' => 'p','?' => 'r','?' => 'r','?' => 'r','s' => 's',
        '?' => 's','t' => 't','?' => 'y','?' => 'y','?' => 'y','?' => 'y',
        '?' => 'y','?' => 'y','?' => 'y','?' => 'y','?' => 'y','?' => 'y',
        '?' => 'y','?' => 'y','?' => 'y','?' => 'y','?' => 'y','?' => 'y',
        '?' => 'y','?' => 'y','f' => 'f','?' => 'x','?' => 'p','?' => 'o',
        '?' => 'o','?' => 'o','?' => 'o','?' => 'o','?' => 'o','?' => 'o',
        '?' => 'o','?' => 'o','?' => 'o','?' => 'o','?' => 'o','?' => 'o',
        '?' => 'o','?' => 'o','?' => 'o','?' => 'o','?' => 'o','?' => 'o',
        '?' => 'o','?' => 'o','?' => 'o','?' => 'o','?' => 'o','?' => 'A',
        '?' => 'B','?' => 'V','?' => 'G','?' => 'D','?' => 'E','?' => 'E',
        '?' => 'Z','?' => 'Z','?' => 'I','?' => 'I','?' => 'K','?' => 'L',
        '?' => 'M','?' => 'N','?' => 'O','?' => 'P','?' => 'R','?' => 'S',
        '?' => 'T','?' => 'U','?' => 'F','?' => 'K','?' => 'T','?' => 'C',
        '?' => 'S','?' => 'S','?' => 'Y','?' => 'E','?' => 'Y','?' => 'Y',
        '?' => 'A','?' => 'B','?' => 'V','?' => 'G','?' => 'D','?' => 'E',
        '?' => 'E','?' => 'Z','?' => 'Z','?' => 'I','?' => 'I','?' => 'K',
        '?' => 'L','?' => 'M','?' => 'N','?' => 'O','?' => 'P','?' => 'R',
        '?' => 'S','?' => 'T','?' => 'U','?' => 'F','?' => 'K','?' => 'T',
        '?' => 'C','?' => 'S','?' => 'S','?' => 'Y','?' => 'E','?' => 'Y',
        '?' => 'Y','Ã°' => 'd','Ã' => 'D','Ã¾' => 't','Ãž' => 'T','?' => 'a',
        '?' => 'b','?' => 'g','?' => 'd','?' => 'e','?' => 'v','?' => 'z',
        '?' => 't','?' => 'i','?' => 'k','?' => 'l','?' => 'm','?' => 'n',
        '?' => 'o','?' => 'p','?' => 'z','?' => 'r','?' => 's','?' => 't',
        '?' => 'u','?' => 'p','?' => 'k','?' => 'g','?' => 'q','?' => 's',
        '?' => 'c','?' => 't','?' => 'd','?' => 't','?' => 'c','?' => 'k',
        '?' => 'j','?' => 'h',
    );
    
    $str = str_replace(array_keys( $transliteration ), array_values( $transliteration ), $str);
    
    return $str;
}

Revision: 57882

at June 13, 2012 20:07 by MGHollander

Updated Code

/**
 * Unaccent the input string string. An example string like `Ãƒï¿½Ãƒï¿½eÃƒÂ¿??????`
 * will be translated to `AOeyIOzoBY`. More complete than :
 *   strtr( (string)$str,
 *          "Ãƒï¿½Ãƒï¿½Ãƒï¿½Ãƒï¿½Ãƒï¿½Ãƒï¿½ÃƒÂ ÃƒÂ¡ÃƒÂ¢ÃƒÂ£ÃƒÂ¤ÃƒÂ¥Ãƒï¿½Ãƒï¿½Ãƒï¿½Ãƒï¿½Ãƒï¿½Ãƒï¿½ÃƒÂ²ÃƒÂ³ÃƒÂ´ÃƒÂµÃƒÂ¶ÃƒÂ¸Ãƒï¿½Ãƒï¿½Ãƒï¿½Ãƒï¿½ÃƒÂ¨ÃƒÂ©ÃƒÂªÃƒÂ«Ãƒï¿½ÃƒÂ§Ãƒï¿½Ãƒï¿½Ãƒï¿½Ãƒï¿½ÃƒÂ¬ÃƒÂÃƒÂ®ÃƒÂ¯Ãƒï¿½Ãƒï¿½Ãƒï¿½Ãƒï¿½ÃƒÂ¹ÃƒÂºÃƒÂ»ÃƒÂ¼ÃƒÂ¿Ãƒï¿½ÃƒÂ±",
 *          "aaaaaaaaaaaaooooooooooooeeeeeeeecciiiiiiiiuuuuuuuuynn" );
 *
 * @param $str input string
 * @param $utf8 if null, function will detect input string encoding
 * @author http://www.evaisse.net/2008/php-translit-remove-accent-unaccent-21001
 * @return string input string without accent
 */
function removeAccents($str, $utf8 = true) {
    $str = (string)$str;
    if (is_null($utf8)) {
        if (!function_exists('mb_detect_encoding')) {
            $utf8 = (strtolower(mb_detect_encoding($str))=='utf-8');
        } else {
            $length = strlen($str);
            $utf8 = true;
            for ($i = 0; $i < $length; $i++) {
                $c = ord($str[$i]);
                if ($c < 0x80) $n = 0; # 0bbbbbbb
                elseif (($c & 0xE0) == 0xC0) $n = 1; # 110bbbbb
                elseif (($c & 0xF0) == 0xE0) $n = 2; # 1110bbbb
                elseif (($c & 0xF8) == 0xF0) $n = 3; # 11110bbb
                elseif (($c & 0xFC) == 0xF8) $n = 4; # 111110bb
                elseif (($c & 0xFE) == 0xFC) $n = 5; # 1111110b
                else return false; # Does not match any model
                for ($j = 0; $j < $n; $j++) { # n bytes matching 10bbbbbb follow ?
                    if ((++$i == $length) || ((ord($str[$i]) & 0xC0) != 0x80)) {
                        $utf8 = false;
                        break;
                    }

                }
            }
        }

    }

    if (!$utf8) {
        $str = utf8_encode($str);
    }
    
    $transliteration = array(
        '?' => 'I', 'Ãƒï¿½' => 'O','Ã…ï¿½' => 'O','Ãƒï¿½' => 'U','ÃƒÂ¤' => 'a','ÃƒÂ¦' => 'a',
        '?' => 'i','ÃƒÂ¶' => 'o','Ã…ï¿½' => 'o','ÃƒÂ¼' => 'u','Ãƒï¿½' => 's','?' => 's',
        'Ãƒï¿½' => 'A','Ãƒï¿½' => 'A','Ãƒï¿½' => 'A','Ãƒï¿½' => 'A','Ãƒï¿½' => 'A','Ãƒï¿½' => 'A',
        'Ãƒï¿½' => 'A','A' => 'A','A' => 'A','A' => 'A','Ãƒï¿½' => 'C','C' => 'C',
        'C' => 'C','C' => 'C','C' => 'C','D' => 'D','Ãƒï¿½' => 'D','Ãƒï¿½' => 'E',
        'Ãƒï¿½' => 'E','Ãƒï¿½' => 'E','Ãƒï¿½' => 'E','E' => 'E','E' => 'E','E' => 'E',
        'E' => 'E','E' => 'E','G' => 'G','G' => 'G','G' => 'G','G' => 'G',
        'H' => 'H','H' => 'H','Ãƒï¿½' => 'I','Ãƒï¿½' => 'I','Ãƒï¿½' => 'I','Ãƒï¿½' => 'I',
        'I' => 'I','I' => 'I','I' => 'I','I' => 'I','I' => 'I','J' => 'J',
        'K' => 'K','L' => 'K','L' => 'K','L' => 'K','?' => 'K','L' => 'L',
        'Ãƒï¿½' => 'N','N' => 'N','N' => 'N','N' => 'N','?' => 'N','Ãƒï¿½' => 'O',
        'Ãƒï¿½' => 'O','Ãƒï¿½' => 'O','Ãƒï¿½' => 'O','Ãƒï¿½' => 'O','O' => 'O','O' => 'O',
        'O' => 'O','R' => 'R','R' => 'R','R' => 'R','S' => 'S','S' => 'S',
        'S' => 'S','?' => 'S','Ã…Â ' => 'S','T' => 'T','T' => 'T','T' => 'T',
        '?' => 'T','Ãƒï¿½' => 'U','Ãƒï¿½' => 'U','Ãƒï¿½' => 'U','U' => 'U','U' => 'U',
        'U' => 'U','U' => 'U','U' => 'U','U' => 'U','W' => 'W','Y' => 'Y',
        'Ã…Â¸' => 'Y','Ãƒï¿½' => 'Y','Z' => 'Z','Z' => 'Z','Ã…Â½' => 'Z','ÃƒÂ ' => 'a',
        'ÃƒÂ¡' => 'a','ÃƒÂ¢' => 'a','ÃƒÂ£' => 'a','a' => 'a','a' => 'a','a' => 'a',
        'ÃƒÂ¥' => 'a','ÃƒÂ§' => 'c','c' => 'c','c' => 'c','c' => 'c','c' => 'c',
        'd' => 'd','d' => 'd','ÃƒÂ¨' => 'e','ÃƒÂ©' => 'e','ÃƒÂª' => 'e','ÃƒÂ«' => 'e',
        'e' => 'e','e' => 'e','e' => 'e','e' => 'e','e' => 'e','Ã†ï¿½' => 'f',
        'g' => 'g','g' => 'g','g' => 'g','g' => 'g','h' => 'h','h' => 'h',
        'ÃƒÂ¬' => 'i','ÃƒÂ' => 'i','ÃƒÂ®' => 'i','ÃƒÂ¯' => 'i','i' => 'i','i' => 'i',
        'i' => 'i','i' => 'i','i' => 'i','j' => 'j','k' => 'k','?' => 'k',
        'l' => 'l','l' => 'l','l' => 'l','l' => 'l','?' => 'l','ÃƒÂ±' => 'n',
        'n' => 'n','n' => 'n','n' => 'n','?' => 'n','?' => 'n','ÃƒÂ²' => 'o',
        'ÃƒÂ³' => 'o','ÃƒÂ´' => 'o','ÃƒÂµ' => 'o','ÃƒÂ¸' => 'o','o' => 'o','o' => 'o',
        'o' => 'o','r' => 'r','r' => 'r','r' => 'r','s' => 's','Ã…Â¡' => 's',
        't' => 't','ÃƒÂ¹' => 'u','ÃƒÂº' => 'u','ÃƒÂ»' => 'u','u' => 'u','u' => 'u',
        'u' => 'u','u' => 'u','u' => 'u','u' => 'u','w' => 'w','ÃƒÂ¿' => 'y',
        'ÃƒÂ½' => 'y','y' => 'y','z' => 'z','z' => 'z','Ã…Â¾' => 'z','?' => 'A',
        '?' => 'A','?' => 'A','?' => 'A','?' => 'A','?' => 'A','?' => 'A',
        '?' => 'A','?' => 'A','?' => 'A','?' => 'A','?' => 'A','?' => 'A',
        '?' => 'A','?' => 'A','?' => 'A','?' => 'A','?' => 'A','?' => 'A',
        '?' => 'A','?' => 'A','?' => 'A','?' => 'B','G' => 'G','?' => 'D',
        '?' => 'E','?' => 'E','?' => 'E','?' => 'E','?' => 'E','?' => 'E',
        '?' => 'E','?' => 'E','?' => 'E','?' => 'Z','?' => 'I','?' => 'I',
        '?' => 'I','?' => 'I','?' => 'I','?' => 'I','?' => 'I','?' => 'I',
        '?' => 'I','?' => 'I','?' => 'I','?' => 'I','?' => 'I','?' => 'I',
        '?' => 'I','?' => 'I','?' => 'I','?' => 'I','?' => 'I','?' => 'I',
        'T' => 'T','?' => 'I','?' => 'I','?' => 'I','?' => 'I','?' => 'I',
        '?' => 'I','?' => 'I','?' => 'I','?' => 'I','?' => 'I','?' => 'I',
        '?' => 'I','?' => 'I','?' => 'I','?' => 'K','?' => 'L','?' => 'M',
        '?' => 'N','?' => 'K','?' => 'O','?' => 'O','?' => 'O','?' => 'O',
        '?' => 'O','?' => 'O','?' => 'O','?' => 'O','?' => 'O','?' => 'P',
        '?' => 'R','?' => 'R','S' => 'S','?' => 'T','?' => 'Y','?' => 'Y',
        '?' => 'Y','?' => 'Y','?' => 'Y','?' => 'Y','?' => 'Y','?' => 'Y',
        '?' => 'Y','?' => 'Y','F' => 'F','?' => 'X','?' => 'P','O' => 'O',
        '?' => 'O','?' => 'O','?' => 'O','?' => 'O','?' => 'O','?' => 'O',
        '?' => 'O','?' => 'O','?' => 'O','?' => 'O','?' => 'O','?' => 'O',
        '?' => 'O','?' => 'O','?' => 'O','?' => 'O','?' => 'O','?' => 'O',
        '?' => 'O','a' => 'a','?' => 'a','?' => 'a','?' => 'a','?' => 'a',
        '?' => 'a','?' => 'a','?' => 'a','?' => 'a','?' => 'a','?' => 'a',
        '?' => 'a','?' => 'a','?' => 'a','?' => 'a','?' => 'a','?' => 'a',
        '?' => 'a','?' => 'a','?' => 'a','?' => 'a','?' => 'a','?' => 'a',
        '?' => 'a','?' => 'a','?' => 'a','Ãƒï¿½' => 'b','?' => 'g','d' => 'd',
        'e' => 'e','?' => 'e','?' => 'e','?' => 'e','?' => 'e','?' => 'e',
        '?' => 'e','?' => 'e','?' => 'e','?' => 'z','?' => 'i','?' => 'i',
        '?' => 'i','?' => 'i','?' => 'i','?' => 'i','?' => 'i','?' => 'i',
        '?' => 'i','?' => 'i','?' => 'i','?' => 'i','?' => 'i','?' => 'i',
        '?' => 'i','?' => 'i','?' => 'i','?' => 'i','?' => 'i','?' => 'i',
        '?' => 'i','?' => 'i','?' => 'i','?' => 'i','?' => 't','?' => 'i',
        '?' => 'i','?' => 'i','?' => 'i','?' => 'i','?' => 'i','?' => 'i',
        '?' => 'i','?' => 'i','?' => 'i','?' => 'i','?' => 'i','?' => 'i',
        '?' => 'i','?' => 'i','?' => 'i','?' => 'i','?' => 'i','?' => 'k',
        '?' => 'l','Ã‚Âµ' => 'm','?' => 'n','?' => 'k','?' => 'o','?' => 'o',
        '?' => 'o','?' => 'o','?' => 'o','?' => 'o','?' => 'o','?' => 'o',
        '?' => 'o','p' => 'p','?' => 'r','?' => 'r','?' => 'r','s' => 's',
        '?' => 's','t' => 't','?' => 'y','?' => 'y','?' => 'y','?' => 'y',
        '?' => 'y','?' => 'y','?' => 'y','?' => 'y','?' => 'y','?' => 'y',
        '?' => 'y','?' => 'y','?' => 'y','?' => 'y','?' => 'y','?' => 'y',
        '?' => 'y','?' => 'y','f' => 'f','?' => 'x','?' => 'p','?' => 'o',
        '?' => 'o','?' => 'o','?' => 'o','?' => 'o','?' => 'o','?' => 'o',
        '?' => 'o','?' => 'o','?' => 'o','?' => 'o','?' => 'o','?' => 'o',
        '?' => 'o','?' => 'o','?' => 'o','?' => 'o','?' => 'o','?' => 'o',
        '?' => 'o','?' => 'o','?' => 'o','?' => 'o','?' => 'o','?' => 'A',
        '?' => 'B','?' => 'V','?' => 'G','?' => 'D','?' => 'E','?' => 'E',
        '?' => 'Z','?' => 'Z','?' => 'I','?' => 'I','?' => 'K','?' => 'L',
        '?' => 'M','?' => 'N','?' => 'O','?' => 'P','?' => 'R','?' => 'S',
        '?' => 'T','?' => 'U','?' => 'F','?' => 'K','?' => 'T','?' => 'C',
        '?' => 'S','?' => 'S','?' => 'Y','?' => 'E','?' => 'Y','?' => 'Y',
        '?' => 'A','?' => 'B','?' => 'V','?' => 'G','?' => 'D','?' => 'E',
        '?' => 'E','?' => 'Z','?' => 'Z','?' => 'I','?' => 'I','?' => 'K',
        '?' => 'L','?' => 'M','?' => 'N','?' => 'O','?' => 'P','?' => 'R',
        '?' => 'S','?' => 'T','?' => 'U','?' => 'F','?' => 'K','?' => 'T',
        '?' => 'C','?' => 'S','?' => 'S','?' => 'Y','?' => 'E','?' => 'Y',
        '?' => 'Y','ÃƒÂ°' => 'd','Ãƒï¿½' => 'D','ÃƒÂ¾' => 't','Ãƒï¿½' => 'T','?' => 'a',
        '?' => 'b','?' => 'g','?' => 'd','?' => 'e','?' => 'v','?' => 'z',
        '?' => 't','?' => 'i','?' => 'k','?' => 'l','?' => 'm','?' => 'n',
        '?' => 'o','?' => 'p','?' => 'z','?' => 'r','?' => 's','?' => 't',
        '?' => 'u','?' => 'p','?' => 'k','?' => 'g','?' => 'q','?' => 's',
        '?' => 'c','?' => 't','?' => 'd','?' => 't','?' => 'c','?' => 'k',
        '?' => 'j','?' => 'h',
    );
    
    $str = str_replace(array_keys( $transliteration ), array_values( $transliteration ), $str);
    
    return $str;
}

Revision: 57881

at June 13, 2012 19:58 by MGHollander

Initial Code

/**
 * Unaccent the input string string. An example string like `Ã€Ã˜eÃ¿??????`
 * will be translated to `AOeyIOzoBY`. More complete than :
 *   strtr( (string)$str,
 *          "Ã€ÃÃ‚ÃƒÃ„Ã…Ã Ã¡Ã¢Ã£Ã¤Ã¥Ã’Ã“Ã”Ã•Ã–Ã˜Ã²Ã³Ã´ÃµÃ¶Ã¸ÃˆÃ‰ÃŠÃ‹Ã¨Ã©ÃªÃ«Ã‡Ã§ÃŒÃÃŽÃÃ¬ÃÃ®Ã¯Ã™ÃšÃ›ÃœÃ¹ÃºÃ»Ã¼Ã¿Ã‘Ã±",
 *          "aaaaaaaaaaaaooooooooooooeeeeeeeecciiiiiiiiuuuuuuuuynn" );
 *
 * @param $str input string
 * @param $utf8 if null, function will detect input string encoding
 * @author http://www.evaisse.net/2008/php-translit-remove-accent-unaccent-21001
 * @return string input string without accent
 */
function removeAccents($str, $utf8 = true) {
    $str = (string)$str;
    if (is_null($utf8)) {
        if (!function_exists('mb_detect_encoding')) {
            $utf8 = (strtolower(mb_detect_encoding($str))=='utf-8');
        } else {
            $length = strlen($str);
            $utf8 = true;
            for ($i = 0; $i < $length; $i++) {
                $c = ord($str[$i]);
                if ($c < 0x80) $n = 0; # 0bbbbbbb
                elseif (($c & 0xE0) == 0xC0) $n = 1; # 110bbbbb
                elseif (($c & 0xF0) == 0xE0) $n = 2; # 1110bbbb
                elseif (($c & 0xF8) == 0xF0) $n = 3; # 11110bbb
                elseif (($c & 0xFC) == 0xF8) $n = 4; # 111110bb
                elseif (($c & 0xFE) == 0xFC) $n = 5; # 1111110b
                else return false; # Does not match any model
                for ($j = 0; $j < $n; $j++) { # n bytes matching 10bbbbbb follow ?
                    if ((++$i == $length) || ((ord($str[$i]) & 0xC0) != 0x80)) {
                        $utf8 = false;
                        break;
                    }

                }
            }
        }

    }

    if (!$utf8) {
        $str = utf8_encode($str);
    }
    
    $transliteration = array(
        '?' => 'I', 'Ã–' => 'O','Å’' => 'O','Ãœ' => 'U','Ã¤' => 'a','Ã¦' => 'a',
        '?' => 'i','Ã¶' => 'o','Å“' => 'o','Ã¼' => 'u','ÃŸ' => 's','?' => 's',
        'Ã€' => 'A','Ã' => 'A','Ã‚' => 'A','Ãƒ' => 'A','Ã„' => 'A','Ã…' => 'A',
        'Ã†' => 'A','A' => 'A','A' => 'A','A' => 'A','Ã‡' => 'C','C' => 'C',
        'C' => 'C','C' => 'C','C' => 'C','D' => 'D','Ã' => 'D','Ãˆ' => 'E',
        'Ã‰' => 'E','ÃŠ' => 'E','Ã‹' => 'E','E' => 'E','E' => 'E','E' => 'E',
        'E' => 'E','E' => 'E','G' => 'G','G' => 'G','G' => 'G','G' => 'G',
        'H' => 'H','H' => 'H','ÃŒ' => 'I','Ã' => 'I','ÃŽ' => 'I','Ã' => 'I',
        'I' => 'I','I' => 'I','I' => 'I','I' => 'I','I' => 'I','J' => 'J',
        'K' => 'K','L' => 'K','L' => 'K','L' => 'K','?' => 'K','L' => 'L',
        'Ã‘' => 'N','N' => 'N','N' => 'N','N' => 'N','?' => 'N','Ã’' => 'O',
        'Ã“' => 'O','Ã”' => 'O','Ã•' => 'O','Ã˜' => 'O','O' => 'O','O' => 'O',
        'O' => 'O','R' => 'R','R' => 'R','R' => 'R','S' => 'S','S' => 'S',
        'S' => 'S','?' => 'S','Å ' => 'S','T' => 'T','T' => 'T','T' => 'T',
        '?' => 'T','Ã™' => 'U','Ãš' => 'U','Ã›' => 'U','U' => 'U','U' => 'U',
        'U' => 'U','U' => 'U','U' => 'U','U' => 'U','W' => 'W','Y' => 'Y',
        'Å¸' => 'Y','Ã' => 'Y','Z' => 'Z','Z' => 'Z','Å½' => 'Z','Ã ' => 'a',
        'Ã¡' => 'a','Ã¢' => 'a','Ã£' => 'a','a' => 'a','a' => 'a','a' => 'a',
        'Ã¥' => 'a','Ã§' => 'c','c' => 'c','c' => 'c','c' => 'c','c' => 'c',
        'd' => 'd','d' => 'd','Ã¨' => 'e','Ã©' => 'e','Ãª' => 'e','Ã«' => 'e',
        'e' => 'e','e' => 'e','e' => 'e','e' => 'e','e' => 'e','Æ’' => 'f',
        'g' => 'g','g' => 'g','g' => 'g','g' => 'g','h' => 'h','h' => 'h',
        'Ã¬' => 'i','Ã' => 'i','Ã®' => 'i','Ã¯' => 'i','i' => 'i','i' => 'i',
        'i' => 'i','i' => 'i','i' => 'i','j' => 'j','k' => 'k','?' => 'k',
        'l' => 'l','l' => 'l','l' => 'l','l' => 'l','?' => 'l','Ã±' => 'n',
        'n' => 'n','n' => 'n','n' => 'n','?' => 'n','?' => 'n','Ã²' => 'o',
        'Ã³' => 'o','Ã´' => 'o','Ãµ' => 'o','Ã¸' => 'o','o' => 'o','o' => 'o',
        'o' => 'o','r' => 'r','r' => 'r','r' => 'r','s' => 's','Å¡' => 's',
        't' => 't','Ã¹' => 'u','Ãº' => 'u','Ã»' => 'u','u' => 'u','u' => 'u',
        'u' => 'u','u' => 'u','u' => 'u','u' => 'u','w' => 'w','Ã¿' => 'y',
        'Ã½' => 'y','y' => 'y','z' => 'z','z' => 'z','Å¾' => 'z','?' => 'A',
        '?' => 'A','?' => 'A','?' => 'A','?' => 'A','?' => 'A','?' => 'A',
        '?' => 'A','?' => 'A','?' => 'A','?' => 'A','?' => 'A','?' => 'A',
        '?' => 'A','?' => 'A','?' => 'A','?' => 'A','?' => 'A','?' => 'A',
        '?' => 'A','?' => 'A','?' => 'A','?' => 'B','G' => 'G','?' => 'D',
        '?' => 'E','?' => 'E','?' => 'E','?' => 'E','?' => 'E','?' => 'E',
        '?' => 'E','?' => 'E','?' => 'E','?' => 'Z','?' => 'I','?' => 'I',
        '?' => 'I','?' => 'I','?' => 'I','?' => 'I','?' => 'I','?' => 'I',
        '?' => 'I','?' => 'I','?' => 'I','?' => 'I','?' => 'I','?' => 'I',
        '?' => 'I','?' => 'I','?' => 'I','?' => 'I','?' => 'I','?' => 'I',
        'T' => 'T','?' => 'I','?' => 'I','?' => 'I','?' => 'I','?' => 'I',
        '?' => 'I','?' => 'I','?' => 'I','?' => 'I','?' => 'I','?' => 'I',
        '?' => 'I','?' => 'I','?' => 'I','?' => 'K','?' => 'L','?' => 'M',
        '?' => 'N','?' => 'K','?' => 'O','?' => 'O','?' => 'O','?' => 'O',
        '?' => 'O','?' => 'O','?' => 'O','?' => 'O','?' => 'O','?' => 'P',
        '?' => 'R','?' => 'R','S' => 'S','?' => 'T','?' => 'Y','?' => 'Y',
        '?' => 'Y','?' => 'Y','?' => 'Y','?' => 'Y','?' => 'Y','?' => 'Y',
        '?' => 'Y','?' => 'Y','F' => 'F','?' => 'X','?' => 'P','O' => 'O',
        '?' => 'O','?' => 'O','?' => 'O','?' => 'O','?' => 'O','?' => 'O',
        '?' => 'O','?' => 'O','?' => 'O','?' => 'O','?' => 'O','?' => 'O',
        '?' => 'O','?' => 'O','?' => 'O','?' => 'O','?' => 'O','?' => 'O',
        '?' => 'O','a' => 'a','?' => 'a','?' => 'a','?' => 'a','?' => 'a',
        '?' => 'a','?' => 'a','?' => 'a','?' => 'a','?' => 'a','?' => 'a',
        '?' => 'a','?' => 'a','?' => 'a','?' => 'a','?' => 'a','?' => 'a',
        '?' => 'a','?' => 'a','?' => 'a','?' => 'a','?' => 'a','?' => 'a',
        '?' => 'a','?' => 'a','?' => 'a','ÃŸ' => 'b','?' => 'g','d' => 'd',
        'e' => 'e','?' => 'e','?' => 'e','?' => 'e','?' => 'e','?' => 'e',
        '?' => 'e','?' => 'e','?' => 'e','?' => 'z','?' => 'i','?' => 'i',
        '?' => 'i','?' => 'i','?' => 'i','?' => 'i','?' => 'i','?' => 'i',
        '?' => 'i','?' => 'i','?' => 'i','?' => 'i','?' => 'i','?' => 'i',
        '?' => 'i','?' => 'i','?' => 'i','?' => 'i','?' => 'i','?' => 'i',
        '?' => 'i','?' => 'i','?' => 'i','?' => 'i','?' => 't','?' => 'i',
        '?' => 'i','?' => 'i','?' => 'i','?' => 'i','?' => 'i','?' => 'i',
        '?' => 'i','?' => 'i','?' => 'i','?' => 'i','?' => 'i','?' => 'i',
        '?' => 'i','?' => 'i','?' => 'i','?' => 'i','?' => 'i','?' => 'k',
        '?' => 'l','Âµ' => 'm','?' => 'n','?' => 'k','?' => 'o','?' => 'o',
        '?' => 'o','?' => 'o','?' => 'o','?' => 'o','?' => 'o','?' => 'o',
        '?' => 'o','p' => 'p','?' => 'r','?' => 'r','?' => 'r','s' => 's',
        '?' => 's','t' => 't','?' => 'y','?' => 'y','?' => 'y','?' => 'y',
        '?' => 'y','?' => 'y','?' => 'y','?' => 'y','?' => 'y','?' => 'y',
        '?' => 'y','?' => 'y','?' => 'y','?' => 'y','?' => 'y','?' => 'y',
        '?' => 'y','?' => 'y','f' => 'f','?' => 'x','?' => 'p','?' => 'o',
        '?' => 'o','?' => 'o','?' => 'o','?' => 'o','?' => 'o','?' => 'o',
        '?' => 'o','?' => 'o','?' => 'o','?' => 'o','?' => 'o','?' => 'o',
        '?' => 'o','?' => 'o','?' => 'o','?' => 'o','?' => 'o','?' => 'o',
        '?' => 'o','?' => 'o','?' => 'o','?' => 'o','?' => 'o','?' => 'A',
        '?' => 'B','?' => 'V','?' => 'G','?' => 'D','?' => 'E','?' => 'E',
        '?' => 'Z','?' => 'Z','?' => 'I','?' => 'I','?' => 'K','?' => 'L',
        '?' => 'M','?' => 'N','?' => 'O','?' => 'P','?' => 'R','?' => 'S',
        '?' => 'T','?' => 'U','?' => 'F','?' => 'K','?' => 'T','?' => 'C',
        '?' => 'S','?' => 'S','?' => 'Y','?' => 'E','?' => 'Y','?' => 'Y',
        '?' => 'A','?' => 'B','?' => 'V','?' => 'G','?' => 'D','?' => 'E',
        '?' => 'E','?' => 'Z','?' => 'Z','?' => 'I','?' => 'I','?' => 'K',
        '?' => 'L','?' => 'M','?' => 'N','?' => 'O','?' => 'P','?' => 'R',
        '?' => 'S','?' => 'T','?' => 'U','?' => 'F','?' => 'K','?' => 'T',
        '?' => 'C','?' => 'S','?' => 'S','?' => 'Y','?' => 'E','?' => 'Y',
        '?' => 'Y','Ã°' => 'd','Ã' => 'D','Ã¾' => 't','Ãž' => 'T','?' => 'a',
        '?' => 'b','?' => 'g','?' => 'd','?' => 'e','?' => 'v','?' => 'z',
        '?' => 't','?' => 'i','?' => 'k','?' => 'l','?' => 'm','?' => 'n',
        '?' => 'o','?' => 'p','?' => 'z','?' => 'r','?' => 's','?' => 't',
        '?' => 'u','?' => 'p','?' => 'k','?' => 'g','?' => 'q','?' => 's',
        '?' => 'c','?' => 't','?' => 'd','?' => 't','?' => 'c','?' => 'k',
        '?' => 'j','?' => 'h',
    );
    
    $str = str_replace(array_keys( $transliteration ), array_values( $transliteration ), $str);
    
    return $str;
}

Initial URL

Initial Description

Unaccent a string.

 An example string like Ã€Ã˜Ä—Ã¿á¾œá½¨Î¶á½…Ð‘ÑŽ will be translated to AOeyIOzoBY.

Initial Title

Unaccent a string

Initial Tags

Initial Language

PHP

Choose a language for easy browsing: