Skip to content

Instantly share code, notes, and snippets.

@evaisse
Created August 18, 2009 07:43
Show Gist options
  • Save evaisse/169594 to your computer and use it in GitHub Desktop.
Save evaisse/169594 to your computer and use it in GitHub Desktop.
php function to remove accent from the input string string. An example string like `ÀØėÿᾜὨζὅБю` * will be translated to `AOeyIOzoBY`
<?php # -*- coding: utf-8 -*-
// function remove_accents()
/**
* Unaccent the input string string. An example string like `ÀØėÿᾜὨζὅБю`
* will be translated to `AOeyIOzoBY`. More complete than :
* strtr( (string)$str,
* "ÀÁÂÃÄÅàáâãäåÒÓÔÕÖØòóôõöøÈÉÊËèéêëÇçÌÍÎÏìíîïÙÚÛÜùúûüÿÑñ",
* "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(
'IJ' => 'I', 'Ö' => 'O','Œ' => 'O','Ü' => 'U','ä' => 'a','æ' => 'a',
'ij' => 'i','ö' => 'o','œ' => 'o','ü' => 'u','ß' => 's','ſ' => 's',
'À' => 'A','Á' => 'A','Â' => 'A','Ã' => 'A','Ä' => 'A','Å' => 'A',
'Æ' => 'A','Ā' => 'A','Ą' => 'A','Ă' => 'A','Ç' => 'C','Ć' => 'C',
'Č' => 'C','Ĉ' => 'C','Ċ' => 'C','Ď' => 'D','Đ' => 'D','È' => 'E',
'É' => 'E','Ê' => 'E','Ë' => 'E','Ē' => 'E','Ę' => 'E','Ě' => 'E',
'Ĕ' => 'E','Ė' => 'E','Ĝ' => 'G','Ğ' => 'G','Ġ' => 'G','Ģ' => 'G',
'Ĥ' => 'H','Ħ' => 'H','Ì' => 'I','Í' => 'I','Î' => 'I','Ï' => 'I',
'Ī' => 'I','Ĩ' => 'I','Ĭ' => 'I','Į' => 'I','İ' => 'I','Ĵ' => 'J',
'Ķ' => 'K','Ľ' => 'K','Ĺ' => 'K','Ļ' => 'K','Ŀ' => 'K','Ł' => 'L',
'Ñ' => 'N','Ń' => 'N','Ň' => 'N','Ņ' => 'N','Ŋ' => 'N','Ò' => 'O',
'Ó' => 'O','Ô' => 'O','Õ' => 'O','Ø' => 'O','Ō' => 'O','Ő' => 'O',
'Ŏ' => 'O','Ŕ' => 'R','Ř' => 'R','Ŗ' => 'R','Ś' => 'S','Ş' => 'S',
'Ŝ' => 'S','Ș' => 'S','Š' => 'S','Ť' => 'T','Ţ' => 'T','Ŧ' => 'T',
'Ț' => 'T','Ù' => 'U','Ú' => 'U','Û' => 'U','Ū' => 'U','Ů' => 'U',
'Ű' => 'U','Ŭ' => 'U','Ũ' => 'U','Ų' => 'U','Ŵ' => 'W','Ŷ' => 'Y',
'Ÿ' => 'Y','Ý' => 'Y','Ź' => 'Z','Ż' => 'Z','Ž' => 'Z','à' => 'a',
'á' => 'a','â' => 'a','ã' => 'a','ā' => 'a','ą' => 'a','ă' => 'a',
'å' => 'a','ç' => 'c','ć' => 'c','č' => 'c','ĉ' => 'c','ċ' => 'c',
'ď' => 'd','đ' => 'd','è' => 'e','é' => 'e','ê' => 'e','ë' => 'e',
'ē' => 'e','ę' => 'e','ě' => 'e','ĕ' => 'e','ė' => 'e','ƒ' => 'f',
'ĝ' => 'g','ğ' => 'g','ġ' => 'g','ģ' => 'g','ĥ' => 'h','ħ' => 'h',
'ì' => 'i','í' => 'i','î' => 'i','ï' => 'i','ī' => 'i','ĩ' => 'i',
'ĭ' => 'i','į' => 'i','ı' => 'i','ĵ' => 'j','ķ' => 'k','ĸ' => 'k',
'ł' => 'l','ľ' => 'l','ĺ' => 'l','ļ' => 'l','ŀ' => 'l','ñ' => 'n',
'ń' => 'n','ň' => 'n','ņ' => 'n','ʼn' => 'n','ŋ' => 'n','ò' => 'o',
'ó' => 'o','ô' => 'o','õ' => 'o','ø' => 'o','ō' => 'o','ő' => 'o',
'ŏ' => 'o','ŕ' => 'r','ř' => 'r','ŗ' => 'r','ś' => 's','š' => 's',
'ť' => 't','ù' => 'u','ú' => 'u','û' => 'u','ū' => 'u','ů' => 'u',
'ű' => 'u','ŭ' => 'u','ũ' => 'u','ų' => 'u','ŵ' => 'w','ÿ' => 'y',
'ý' => 'y','ŷ' => 'y','ż' => 'z','ź' => 'z','ž' => 'z','Α' => 'A',
'Ά' => 'A','Ἀ' => 'A','Ἁ' => 'A','Ἂ' => 'A','Ἃ' => 'A','Ἄ' => 'A',
'Ἅ' => 'A','Ἆ' => 'A','Ἇ' => 'A','ᾈ' => 'A','ᾉ' => 'A','ᾊ' => 'A',
'ᾋ' => 'A','ᾌ' => 'A','ᾍ' => 'A','ᾎ' => 'A','ᾏ' => 'A','Ᾰ' => 'A',
'Ᾱ' => 'A','Ὰ' => 'A','ᾼ' => 'A','Β' => 'B','Γ' => 'G','Δ' => 'D',
'Ε' => 'E','Έ' => 'E','Ἐ' => 'E','Ἑ' => 'E','Ἒ' => 'E','Ἓ' => 'E',
'Ἔ' => 'E','Ἕ' => 'E','Ὲ' => 'E','Ζ' => 'Z','Η' => 'I','Ή' => 'I',
'Ἠ' => 'I','Ἡ' => 'I','Ἢ' => 'I','Ἣ' => 'I','Ἤ' => 'I','Ἥ' => 'I',
'Ἦ' => 'I','Ἧ' => 'I','ᾘ' => 'I','ᾙ' => 'I','ᾚ' => 'I','ᾛ' => 'I',
'ᾜ' => 'I','ᾝ' => 'I','ᾞ' => 'I','ᾟ' => 'I','Ὴ' => 'I','ῌ' => 'I',
'Θ' => 'T','Ι' => 'I','Ί' => 'I','Ϊ' => 'I','Ἰ' => 'I','Ἱ' => 'I',
'Ἲ' => 'I','Ἳ' => 'I','Ἴ' => 'I','Ἵ' => 'I','Ἶ' => 'I','Ἷ' => 'I',
'Ῐ' => 'I','Ῑ' => 'I','Ὶ' => 'I','Κ' => 'K','Λ' => 'L','Μ' => 'M',
'Ν' => 'N','Ξ' => 'K','Ο' => 'O','Ό' => 'O','Ὀ' => 'O','Ὁ' => 'O',
'Ὂ' => 'O','Ὃ' => 'O','Ὄ' => 'O','Ὅ' => 'O','Ὸ' => 'O','Π' => 'P',
'Ρ' => 'R','Ῥ' => 'R','Σ' => 'S','Τ' => 'T','Υ' => 'Y','Ύ' => 'Y',
'Ϋ' => 'Y','Ὑ' => 'Y','Ὓ' => 'Y','Ὕ' => 'Y','Ὗ' => 'Y','Ῠ' => 'Y',
'Ῡ' => 'Y','Ὺ' => 'Y','Φ' => 'F','Χ' => 'X','Ψ' => 'P','Ω' => 'O',
'Ώ' => 'O','Ὠ' => 'O','Ὡ' => 'O','Ὢ' => 'O','Ὣ' => 'O','Ὤ' => 'O',
'Ὥ' => 'O','Ὦ' => 'O','Ὧ' => 'O','ᾨ' => 'O','ᾩ' => 'O','ᾪ' => 'O',
'ᾫ' => 'O','ᾬ' => 'O','ᾭ' => 'O','ᾮ' => 'O','ᾯ' => 'O','Ὼ' => 'O',
'ῼ' => 'O','α' => 'a','ά' => 'a','ἀ' => 'a','ἁ' => 'a','ἂ' => 'a',
'ἃ' => 'a','ἄ' => 'a','ἅ' => 'a','ἆ' => 'a','ἇ' => 'a','ᾀ' => 'a',
'ᾁ' => 'a','ᾂ' => 'a','ᾃ' => 'a','ᾄ' => 'a','ᾅ' => 'a','ᾆ' => 'a',
'ᾇ' => 'a','ὰ' => 'a','ᾰ' => 'a','ᾱ' => 'a','ᾲ' => 'a','ᾳ' => 'a',
'ᾴ' => 'a','ᾶ' => 'a','ᾷ' => 'a','β' => 'b','γ' => 'g','δ' => 'd',
'ε' => 'e','έ' => 'e','ἐ' => 'e','ἑ' => 'e','ἒ' => 'e','ἓ' => 'e',
'ἔ' => 'e','ἕ' => 'e','ὲ' => 'e','ζ' => 'z','η' => 'i','ή' => 'i',
'ἠ' => 'i','ἡ' => 'i','ἢ' => 'i','ἣ' => 'i','ἤ' => 'i','ἥ' => 'i',
'ἦ' => 'i','ἧ' => 'i','ᾐ' => 'i','ᾑ' => 'i','ᾒ' => 'i','ᾓ' => 'i',
'ᾔ' => 'i','ᾕ' => 'i','ᾖ' => 'i','ᾗ' => 'i','ὴ' => 'i','ῂ' => 'i',
'ῃ' => 'i','ῄ' => 'i','ῆ' => 'i','ῇ' => 'i','θ' => 't','ι' => 'i',
'ί' => 'i','ϊ' => 'i','ΐ' => 'i','ἰ' => 'i','ἱ' => 'i','ἲ' => 'i',
'ἳ' => 'i','ἴ' => 'i','ἵ' => 'i','ἶ' => 'i','ἷ' => 'i','ὶ' => 'i',
'ῐ' => 'i','ῑ' => 'i','ῒ' => 'i','ῖ' => 'i','ῗ' => 'i','κ' => 'k',
'λ' => 'l','μ' => 'm','ν' => 'n','ξ' => 'k','ο' => 'o','ό' => 'o',
'ὀ' => 'o','ὁ' => 'o','ὂ' => 'o','ὃ' => 'o','ὄ' => 'o','ὅ' => 'o',
'ὸ' => 'o','π' => 'p','ρ' => 'r','ῤ' => 'r','ῥ' => 'r','σ' => 's',
'ς' => 's','τ' => 't','υ' => 'y','ύ' => 'y','ϋ' => 'y','ΰ' => 'y',
'ὐ' => 'y','ὑ' => 'y','ὒ' => 'y','ὓ' => 'y','ὔ' => 'y','ὕ' => 'y',
'ὖ' => 'y','ὗ' => 'y','ὺ' => 'y','ῠ' => 'y','ῡ' => 'y','ῢ' => 'y',
'ῦ' => 'y','ῧ' => 'y','φ' => 'f','χ' => 'x','ψ' => 'p','ω' => 'o',
'ώ' => 'o','ὠ' => 'o','ὡ' => 'o','ὢ' => 'o','ὣ' => 'o','ὤ' => 'o',
'ὥ' => 'o','ὦ' => 'o','ὧ' => 'o','ᾠ' => 'o','ᾡ' => 'o','ᾢ' => 'o',
'ᾣ' => 'o','ᾤ' => 'o','ᾥ' => 'o','ᾦ' => 'o','ᾧ' => 'o','ὼ' => 'o',
'ῲ' => 'o','ῳ' => 'o','ῴ' => 'o','ῶ' => 'o','ῷ' => 'o','А' => 'A',
'Б' => 'B','В' => 'V','Г' => 'G','Д' => 'D','Е' => 'E','Ё' => 'E',
'Ж' => 'Z','З' => 'Z','И' => 'I','Й' => 'I','К' => 'K','Л' => 'L',
'М' => 'M','Н' => 'N','О' => 'O','П' => 'P','Р' => 'R','С' => 'S',
'Т' => 'T','У' => 'U','Ф' => 'F','Х' => 'K','Ц' => 'T','Ч' => 'C',
'Ш' => 'S','Щ' => 'S','Ы' => 'Y','Э' => 'E','Ю' => 'Y','Я' => 'Y',
'а' => 'A','б' => 'B','в' => 'V','г' => 'G','д' => 'D','е' => 'E',
'ё' => 'E','ж' => 'Z','з' => 'Z','и' => 'I','й' => 'I','к' => 'K',
'л' => 'L','м' => 'M','н' => 'N','о' => 'O','п' => 'P','р' => 'R',
'с' => 'S','т' => 'T','у' => 'U','ф' => 'F','х' => 'K','ц' => 'T',
'ч' => 'C','ш' => 'S','щ' => 'S','ы' => 'Y','э' => 'E','ю' => 'Y',
'я' => 'Y','ð' => 'd','Ð' => 'D','þ' => 't','Þ' => 'T','ა' => 'a',
'ბ' => 'b','გ' => 'g','დ' => 'd','ე' => 'e','ვ' => 'v','ზ' => 'z',
'თ' => 't','ი' => 'i','კ' => 'k','ლ' => 'l','მ' => 'm','ნ' => 'n',
'ო' => 'o','პ' => 'p','ჟ' => 'z','რ' => 'r','ს' => 's','ტ' => 't',
'უ' => 'u','ფ' => 'p','ქ' => 'k','ღ' => 'g','ყ' => 'q','შ' => 's',
'ჩ' => 'c','ც' => 't','ძ' => 'd','წ' => 't','ჭ' => 'c','ხ' => 'k',
'ჯ' => 'j','ჰ' => 'h'
);
$str = str_replace( array_keys( $transliteration ),
array_values( $transliteration ),
$str);
return $str;
}
//- remove_accents()
@TeddyBear06
Copy link

Thank you !

Copy link

ghost commented Mar 8, 2015

Great function!

However, on lines 19 and 20 it seems odd to check if a function doesn't exist, and if so, call it. That can't work, or am I missing something?

@ludofleury
Copy link

@ghost is right there is a typo there.

  • mb_detect_encoding should be called with the strict argument otherwise false positive will incur.
  • str_replace can be replaced with strtr strtr($string, $transliteration) (didn't benchmark that tho).
  • safer version would be using chr() instead of writing the characters.

From wordpress (they must have face quite some issue):

        if (!preg_match('/[\x80-\xff]/', $string)) {
            return $string;
        }

        $chars = [
            // Decompositions for Latin-1 Supplement
            chr(194).chr(170) => 'a', chr(194).chr(186) => 'o',
            chr(195).chr(128) => 'A', chr(195).chr(129) => 'A',
            chr(195).chr(130) => 'A', chr(195).chr(131) => 'A',
            chr(195).chr(132) => 'A', chr(195).chr(133) => 'A',
            chr(195).chr(134) => 'AE',chr(195).chr(135) => 'C',
            chr(195).chr(136) => 'E', chr(195).chr(137) => 'E',
            chr(195).chr(138) => 'E', chr(195).chr(139) => 'E',
            chr(195).chr(140) => 'I', chr(195).chr(141) => 'I',
            chr(195).chr(142) => 'I', chr(195).chr(143) => 'I',
            chr(195).chr(144) => 'D', chr(195).chr(145) => 'N',
            chr(195).chr(146) => 'O', chr(195).chr(147) => 'O',
            chr(195).chr(148) => 'O', chr(195).chr(149) => 'O',
            chr(195).chr(150) => 'O', chr(195).chr(153) => 'U',
            chr(195).chr(154) => 'U', chr(195).chr(155) => 'U',
            chr(195).chr(156) => 'U', chr(195).chr(157) => 'Y',
            chr(195).chr(158) => 'TH',chr(195).chr(159) => 's',
            chr(195).chr(160) => 'a', chr(195).chr(161) => 'a',
            chr(195).chr(162) => 'a', chr(195).chr(163) => 'a',
            chr(195).chr(164) => 'a', chr(195).chr(165) => 'a',
            chr(195).chr(166) => 'ae',chr(195).chr(167) => 'c',
            chr(195).chr(168) => 'e', chr(195).chr(169) => 'e',
            chr(195).chr(170) => 'e', chr(195).chr(171) => 'e',
            chr(195).chr(172) => 'i', chr(195).chr(173) => 'i',
            chr(195).chr(174) => 'i', chr(195).chr(175) => 'i',
            chr(195).chr(176) => 'd', chr(195).chr(177) => 'n',
            chr(195).chr(178) => 'o', chr(195).chr(179) => 'o',
            chr(195).chr(180) => 'o', chr(195).chr(181) => 'o',
            chr(195).chr(182) => 'o', chr(195).chr(184) => 'o',
            chr(195).chr(185) => 'u', chr(195).chr(186) => 'u',
            chr(195).chr(187) => 'u', chr(195).chr(188) => 'u',
            chr(195).chr(189) => 'y', chr(195).chr(190) => 'th',
            chr(195).chr(191) => 'y', chr(195).chr(152) => 'O',
            // Decompositions for Latin Extended-A
            chr(196).chr(128) => 'A', chr(196).chr(129) => 'a',
            chr(196).chr(130) => 'A', chr(196).chr(131) => 'a',
            chr(196).chr(132) => 'A', chr(196).chr(133) => 'a',
            chr(196).chr(134) => 'C', chr(196).chr(135) => 'c',
            chr(196).chr(136) => 'C', chr(196).chr(137) => 'c',
            chr(196).chr(138) => 'C', chr(196).chr(139) => 'c',
            chr(196).chr(140) => 'C', chr(196).chr(141) => 'c',
            chr(196).chr(142) => 'D', chr(196).chr(143) => 'd',
            chr(196).chr(144) => 'D', chr(196).chr(145) => 'd',
            chr(196).chr(146) => 'E', chr(196).chr(147) => 'e',
            chr(196).chr(148) => 'E', chr(196).chr(149) => 'e',
            chr(196).chr(150) => 'E', chr(196).chr(151) => 'e',
            chr(196).chr(152) => 'E', chr(196).chr(153) => 'e',
            chr(196).chr(154) => 'E', chr(196).chr(155) => 'e',
            chr(196).chr(156) => 'G', chr(196).chr(157) => 'g',
            chr(196).chr(158) => 'G', chr(196).chr(159) => 'g',
            chr(196).chr(160) => 'G', chr(196).chr(161) => 'g',
            chr(196).chr(162) => 'G', chr(196).chr(163) => 'g',
            chr(196).chr(164) => 'H', chr(196).chr(165) => 'h',
            chr(196).chr(166) => 'H', chr(196).chr(167) => 'h',
            chr(196).chr(168) => 'I', chr(196).chr(169) => 'i',
            chr(196).chr(170) => 'I', chr(196).chr(171) => 'i',
            chr(196).chr(172) => 'I', chr(196).chr(173) => 'i',
            chr(196).chr(174) => 'I', chr(196).chr(175) => 'i',
            chr(196).chr(176) => 'I', chr(196).chr(177) => 'i',
            chr(196).chr(178) => 'IJ',chr(196).chr(179) => 'ij',
            chr(196).chr(180) => 'J', chr(196).chr(181) => 'j',
            chr(196).chr(182) => 'K', chr(196).chr(183) => 'k',
            chr(196).chr(184) => 'k', chr(196).chr(185) => 'L',
            chr(196).chr(186) => 'l', chr(196).chr(187) => 'L',
            chr(196).chr(188) => 'l', chr(196).chr(189) => 'L',
            chr(196).chr(190) => 'l', chr(196).chr(191) => 'L',
            chr(197).chr(128) => 'l', chr(197).chr(129) => 'L',
            chr(197).chr(130) => 'l', chr(197).chr(131) => 'N',
            chr(197).chr(132) => 'n', chr(197).chr(133) => 'N',
            chr(197).chr(134) => 'n', chr(197).chr(135) => 'N',
            chr(197).chr(136) => 'n', chr(197).chr(137) => 'N',
            chr(197).chr(138) => 'n', chr(197).chr(139) => 'N',
            chr(197).chr(140) => 'O', chr(197).chr(141) => 'o',
            chr(197).chr(142) => 'O', chr(197).chr(143) => 'o',
            chr(197).chr(144) => 'O', chr(197).chr(145) => 'o',
            chr(197).chr(146) => 'OE',chr(197).chr(147) => 'oe',
            chr(197).chr(148) => 'R',chr(197).chr(149) => 'r',
            chr(197).chr(150) => 'R',chr(197).chr(151) => 'r',
            chr(197).chr(152) => 'R',chr(197).chr(153) => 'r',
            chr(197).chr(154) => 'S',chr(197).chr(155) => 's',
            chr(197).chr(156) => 'S',chr(197).chr(157) => 's',
            chr(197).chr(158) => 'S',chr(197).chr(159) => 's',
            chr(197).chr(160) => 'S', chr(197).chr(161) => 's',
            chr(197).chr(162) => 'T', chr(197).chr(163) => 't',
            chr(197).chr(164) => 'T', chr(197).chr(165) => 't',
            chr(197).chr(166) => 'T', chr(197).chr(167) => 't',
            chr(197).chr(168) => 'U', chr(197).chr(169) => 'u',
            chr(197).chr(170) => 'U', chr(197).chr(171) => 'u',
            chr(197).chr(172) => 'U', chr(197).chr(173) => 'u',
            chr(197).chr(174) => 'U', chr(197).chr(175) => 'u',
            chr(197).chr(176) => 'U', chr(197).chr(177) => 'u',
            chr(197).chr(178) => 'U', chr(197).chr(179) => 'u',
            chr(197).chr(180) => 'W', chr(197).chr(181) => 'w',
            chr(197).chr(182) => 'Y', chr(197).chr(183) => 'y',
            chr(197).chr(184) => 'Y', chr(197).chr(185) => 'Z',
            chr(197).chr(186) => 'z', chr(197).chr(187) => 'Z',
            chr(197).chr(188) => 'z', chr(197).chr(189) => 'Z',
            chr(197).chr(190) => 'z', chr(197).chr(191) => 's',
            // Decompositions for Latin Extended-B
            chr(200).chr(152) => 'S', chr(200).chr(153) => 's',
            chr(200).chr(154) => 'T', chr(200).chr(155) => 't',
            // Euro Sign
            chr(226).chr(130).chr(172) => 'E',
            // GBP (Pound) Sign
            chr(194).chr(163) => '',
            // Vowels with diacritic (Vietnamese)
            // unmarked
            chr(198).chr(160) => 'O', chr(198).chr(161) => 'o',
            chr(198).chr(175) => 'U', chr(198).chr(176) => 'u',
            // grave accent
            chr(225).chr(186).chr(166) => 'A', chr(225).chr(186).chr(167) => 'a',
            chr(225).chr(186).chr(176) => 'A', chr(225).chr(186).chr(177) => 'a',
            chr(225).chr(187).chr(128) => 'E', chr(225).chr(187).chr(129) => 'e',
            chr(225).chr(187).chr(146) => 'O', chr(225).chr(187).chr(147) => 'o',
            chr(225).chr(187).chr(156) => 'O', chr(225).chr(187).chr(157) => 'o',
            chr(225).chr(187).chr(170) => 'U', chr(225).chr(187).chr(171) => 'u',
            chr(225).chr(187).chr(178) => 'Y', chr(225).chr(187).chr(179) => 'y',
            // hook
            chr(225).chr(186).chr(162) => 'A', chr(225).chr(186).chr(163) => 'a',
            chr(225).chr(186).chr(168) => 'A', chr(225).chr(186).chr(169) => 'a',
            chr(225).chr(186).chr(178) => 'A', chr(225).chr(186).chr(179) => 'a',
            chr(225).chr(186).chr(186) => 'E', chr(225).chr(186).chr(187) => 'e',
            chr(225).chr(187).chr(130) => 'E', chr(225).chr(187).chr(131) => 'e',
            chr(225).chr(187).chr(136) => 'I', chr(225).chr(187).chr(137) => 'i',
            chr(225).chr(187).chr(142) => 'O', chr(225).chr(187).chr(143) => 'o',
            chr(225).chr(187).chr(148) => 'O', chr(225).chr(187).chr(149) => 'o',
            chr(225).chr(187).chr(158) => 'O', chr(225).chr(187).chr(159) => 'o',
            chr(225).chr(187).chr(166) => 'U', chr(225).chr(187).chr(167) => 'u',
            chr(225).chr(187).chr(172) => 'U', chr(225).chr(187).chr(173) => 'u',
            chr(225).chr(187).chr(182) => 'Y', chr(225).chr(187).chr(183) => 'y',
            // tilde
            chr(225).chr(186).chr(170) => 'A', chr(225).chr(186).chr(171) => 'a',
            chr(225).chr(186).chr(180) => 'A', chr(225).chr(186).chr(181) => 'a',
            chr(225).chr(186).chr(188) => 'E', chr(225).chr(186).chr(189) => 'e',
            chr(225).chr(187).chr(132) => 'E', chr(225).chr(187).chr(133) => 'e',
            chr(225).chr(187).chr(150) => 'O', chr(225).chr(187).chr(151) => 'o',
            chr(225).chr(187).chr(160) => 'O', chr(225).chr(187).chr(161) => 'o',
            chr(225).chr(187).chr(174) => 'U', chr(225).chr(187).chr(175) => 'u',
            chr(225).chr(187).chr(184) => 'Y', chr(225).chr(187).chr(185) => 'y',
            // acute accent
            chr(225).chr(186).chr(164) => 'A', chr(225).chr(186).chr(165) => 'a',
            chr(225).chr(186).chr(174) => 'A', chr(225).chr(186).chr(175) => 'a',
            chr(225).chr(186).chr(190) => 'E', chr(225).chr(186).chr(191) => 'e',
            chr(225).chr(187).chr(144) => 'O', chr(225).chr(187).chr(145) => 'o',
            chr(225).chr(187).chr(154) => 'O', chr(225).chr(187).chr(155) => 'o',
            chr(225).chr(187).chr(168) => 'U', chr(225).chr(187).chr(169) => 'u',
            // dot below
            chr(225).chr(186).chr(160) => 'A', chr(225).chr(186).chr(161) => 'a',
            chr(225).chr(186).chr(172) => 'A', chr(225).chr(186).chr(173) => 'a',
            chr(225).chr(186).chr(182) => 'A', chr(225).chr(186).chr(183) => 'a',
            chr(225).chr(186).chr(184) => 'E', chr(225).chr(186).chr(185) => 'e',
            chr(225).chr(187).chr(134) => 'E', chr(225).chr(187).chr(135) => 'e',
            chr(225).chr(187).chr(138) => 'I', chr(225).chr(187).chr(139) => 'i',
            chr(225).chr(187).chr(140) => 'O', chr(225).chr(187).chr(141) => 'o',
            chr(225).chr(187).chr(152) => 'O', chr(225).chr(187).chr(153) => 'o',
            chr(225).chr(187).chr(162) => 'O', chr(225).chr(187).chr(163) => 'o',
            chr(225).chr(187).chr(164) => 'U', chr(225).chr(187).chr(165) => 'u',
            chr(225).chr(187).chr(176) => 'U', chr(225).chr(187).chr(177) => 'u',
            chr(225).chr(187).chr(180) => 'Y', chr(225).chr(187).chr(181) => 'y',
            // Vowels with diacritic (Chinese, Hanyu Pinyin)
            chr(201).chr(145) => 'a',
            // macron
            chr(199).chr(149) => 'U', chr(199).chr(150) => 'u',
            // acute accent
            chr(199).chr(151) => 'U', chr(199).chr(152) => 'u',
            // caron
            chr(199).chr(141) => 'A', chr(199).chr(142) => 'a',
            chr(199).chr(143) => 'I', chr(199).chr(144) => 'i',
            chr(199).chr(145) => 'O', chr(199).chr(146) => 'o',
            chr(199).chr(147) => 'U', chr(199).chr(148) => 'u',
            chr(199).chr(153) => 'U', chr(199).chr(154) => 'u',
            // grave accent
            chr(199).chr(155) => 'U', chr(199).chr(156) => 'u',
        ];


        $string = strtr($string, $chars);

@stegrams
Copy link

@ludofleury I just noticed that your version didn't work for Greek characters

e.g Γεια σου κόσμε is expected to come out as Geia soy kosme

That functionality would be helpful for a search engine implementation.

@mnsuccess
Copy link

thanks !! great function

@thattejada
Copy link

I found this function in this blog http://jike.in/?qa=456827/string-how-to-replace-special-characters-with-the-ones-theyre-based-on-in-php

It seems that do what it needs to do with accents

function Unaccent($string)
{
    return preg_replace('~&([a-z]{1,2})(acute|cedil|circ|grave|lig|orn|ring|slash|th|tilde|uml);~i', '$1', htmlentities($string, ENT_QUOTES, 'UTF-8'));
}

@FrantataCZ
Copy link

thx

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment