PHP convert accented characters to ascii. Convert UTF8 to ASCII. PHP function to convert national chars into their latin equivalents. For example, convert “Biên Thùy” to “Bien Thuy” or “Höhle” to Hohle. This is usefull function when you want to have friendly url…
So, this is PHP function to replaces special characters in a string with their “non-special” counterpart.
function bienthuy_to_latin($string) {
$needtobt = array(
'À'=>'A', 'Á'=>'A', 'Â'=>'A', 'Ã'=>'A', 'Ä'=>'A', 'Å'=>'A', 'Ă'=>'A', 'Ā'=>'A', 'Ą'=>'A', 'Æ'=>'A', 'Ǽ'=>'A',
'à'=>'a', 'á'=>'a', 'â'=>'a', 'ã'=>'a', 'ä'=>'a', 'å'=>'a', 'ă'=>'a', 'ā'=>'a', 'ą'=>'a', 'æ'=>'a', 'ǽ'=>'a',
'Þ'=>'B', 'þ'=>'b', 'ß'=>'Ss',
'Ç'=>'C', 'Č'=>'C', 'Ć'=>'C', 'Ĉ'=>'C', 'Ċ'=>'C',
'ç'=>'c', 'č'=>'c', 'ć'=>'c', 'ĉ'=>'c', 'ċ'=>'c',
'Đ'=>'Dj', 'Ď'=>'D', 'Đ'=>'D',
'đ'=>'dj', 'ď'=>'d',
'È'=>'E', 'É'=>'E', 'Ê'=>'E', 'Ë'=>'E', 'Ĕ'=>'E', 'Ē'=>'E', 'Ę'=>'E', 'Ė'=>'E',
'è'=>'e', 'é'=>'e', 'ê'=>'e', 'ë'=>'e', 'ĕ'=>'e', 'ē'=>'e', 'ę'=>'e', 'ė'=>'e',
'Ĝ'=>'G', 'Ğ'=>'G', 'Ġ'=>'G', 'Ģ'=>'G',
'ĝ'=>'g', 'ğ'=>'g', 'ġ'=>'g', 'ģ'=>'g',
'Ĥ'=>'H', 'Ħ'=>'H',
'ĥ'=>'h', 'ħ'=>'h',
'Ì'=>'I', 'Í'=>'I', 'Î'=>'I', 'Ï'=>'I', 'İ'=>'I', 'Ĩ'=>'I', 'Ī'=>'I', 'Ĭ'=>'I', 'Į'=>'I',
'ì'=>'i', 'í'=>'i', 'î'=>'i', 'ï'=>'i', 'į'=>'i', 'ĩ'=>'i', 'ī'=>'i', 'ĭ'=>'i', 'ı'=>'i',
'Ĵ'=>'J',
'ĵ'=>'j',
'Ķ'=>'K',
'ķ'=>'k', 'ĸ'=>'k',
'Ĺ'=>'L', 'Ļ'=>'L', 'Ľ'=>'L', 'Ŀ'=>'L', 'Ł'=>'L',
'ĺ'=>'l', 'ļ'=>'l', 'ľ'=>'l', 'ŀ'=>'l', 'ł'=>'l',
'Ñ'=>'N', 'Ń'=>'N', 'Ň'=>'N', 'Ņ'=>'N', 'Ŋ'=>'N',
'ñ'=>'n', 'ń'=>'n', 'ň'=>'n', 'ņ'=>'n', 'ŋ'=>'n', 'ʼn'=>'n',
'Ò'=>'O', 'Ó'=>'O', 'Ô'=>'O', 'Õ'=>'O', 'Ö'=>'O', 'Ø'=>'O', 'Ō'=>'O', 'Ŏ'=>'O', 'Ő'=>'O', 'Œ'=>'O',
'ò'=>'o', 'ó'=>'o', 'ô'=>'o', 'õ'=>'o', 'ö'=>'o', 'ø'=>'o', 'ō'=>'o', 'ŏ'=>'o', 'ő'=>'o', 'œ'=>'o', 'ð'=>'o',
'Ŕ'=>'R', 'Ř'=>'R',
'ŕ'=>'r', 'ř'=>'r', 'ŗ'=>'r',
'Š'=>'S', 'Ŝ'=>'S', 'Ś'=>'S', 'Ş'=>'S',
'š'=>'s', 'ŝ'=>'s', 'ś'=>'s', 'ş'=>'s',
'Ŧ'=>'T', 'Ţ'=>'T', 'Ť'=>'T',
'ŧ'=>'t', 'ţ'=>'t', 'ť'=>'t',
'Ù'=>'U', 'Ú'=>'U', 'Û'=>'U', 'Ü'=>'U', 'Ũ'=>'U', 'Ū'=>'U', 'Ŭ'=>'U', 'Ů'=>'U', 'Ű'=>'U', 'Ų'=>'U',
'ù'=>'u', 'ú'=>'u', 'û'=>'u', 'ü'=>'u', 'ũ'=>'u', 'ū'=>'u', 'ŭ'=>'u', 'ů'=>'u', 'ű'=>'u', 'ų'=>'u',
'Ŵ'=>'W', 'Ẁ'=>'W', 'Ẃ'=>'W', 'Ẅ'=>'W',
'ŵ'=>'w', 'ẁ'=>'w', 'ẃ'=>'w', 'ẅ'=>'w',
'Ý'=>'Y', 'Ÿ'=>'Y', 'Ŷ'=>'Y',
'ý'=>'y', 'ÿ'=>'y', 'ŷ'=>'y',
'Ž'=>'Z', 'Ź'=>'Z', 'Ż'=>'Z', 'Ž'=>'Z',
'ž'=>'z', 'ź'=>'z', 'ż'=>'z', 'ž'=>'z',
'“'=>'"', '”'=>'"', '‘'=>"'", '’'=>"'", '•'=>'-', '…'=>'...', '—'=>'-', '–'=>'-', '¿'=>'?', '¡'=>'!', '°'=>' degrees ',
'¼'=>' 1/4 ', '½'=>' 1/2 ', '¾'=>' 3/4 ', '⅓'=>' 1/3 ', '⅔'=>' 2/3 ', '⅛'=>' 1/8 ', '⅜'=>' 3/8 ', '⅝'=>' 5/8 ', '⅞'=>' 7/8 ',
'÷'=>' divided by ', '×'=>' times ', '±'=>' plus-minus ', '√'=>' square root ', '∞'=>' infinity ',
'≈'=>' almost equal to ', '≠'=>' not equal to ', '≡'=>' identical to ', '≤'=>' less than or equal to ', '≥'=>' greater than or equal to ',
'←'=>' left ', '→'=>' right ', '↑'=>' up ', '↓'=>' down ', '↔'=>' left and right ', '↕'=>' up and down ',
'℅'=>' care of ', '℮' => ' estimated ',
'Ω'=>' ohm ',
'♀'=>' female ', '♂'=>' male ',
'©'=>' Copyright ', '®'=>' Registered ', '™' =>' Trademark ',
);
$string = strtr($string, $needtobt);
$string = preg_replace("/[^\x9\xA\xD\x20-\x7F]/u", "", $string);
return $string;
}
This PHP file must be saved in UTF-8 encoding.
An other version using UTF-8 code for JavaScript as below:
function nonAccentVietnamese(str) {
str = str.toLowerCase();
str = str.replace(/à|á|ạ|ả|ã|â|ầ|ấ|ậ|ẩ|ẫ|ă|ằ|ắ|ặ|ẳ|ẵ/g, "a");
str = str.replace(/è|é|ẹ|ẻ|ẽ|ê|ề|ế|ệ|ể|ễ/g, "e");
str = str.replace(/ì|í|ị|ỉ|ĩ/g, "i");
str = str.replace(/ò|ó|ọ|ỏ|õ|ô|ồ|ố|ộ|ổ|ỗ|ơ|ờ|ớ|ợ|ở|ỡ/g, "o");
str = str.replace(/ù|ú|ụ|ủ|ũ|ư|ừ|ứ|ự|ử|ữ/g, "u");
str = str.replace(/ỳ|ý|ỵ|ỷ|ỹ/g, "y");
str = str.replace(/đ/g, "d");
str = str.replace(/\u0300|\u0301|\u0303|\u0309|\u0323/g, ""); // Huyền sắc hỏi ngã nặng
str = str.replace(/\u02C6|\u0306|\u031B/g, ""); // Â, Ê, Ă, Ơ, Ư
return str;
}
Remove vietnamese accent javascript / Bỏ dấu tiếng Việt
function stringToSlug(str) {
// remove accents
var from = "àáãảạăằắẳẵặâầấẩẫậèéẻẽẹêềếểễệđùúủũụưừứửữựòóỏõọôồốổỗộơờớởỡợìíỉĩịäëïîöüûñç",
to = "aaaaaaaaaaaaaaaaaeeeeeeeeeeeduuuuuuuuuuuoooooooooooooooooiiiiiaeiiouunc";
for (var i=0, l=from.length ; i < l ; i++) {
str = str.replace(RegExp(from[i], "gi"), to[i]);
}
str = str.toLowerCase()
.trim()
.replace(/[^a-z0-9\-]/g, '-')
.replace(/-+/g, '-');
return str;
}
Actually, removing accents should be processed on server side to make sure your content is rendered properly before display to user.
The function above will also replace all Vietnamese accented characters with non-accented characters.
The PHP convert accented characters to ascii function above also use to remove Vietnamese accent in URL.
WordPress core also include a function called remove_accents. It’s located inside this file: wp-includes/formatting.php
You can use it as follow:
function remove_accents( $string ) {
if ( ! preg_match( '/[\x80-\xff]/', $string ) ) {
return $string;
}
if ( seems_utf8( $string ) ) {
$chars = array(
// Decompositions for Latin-1 Supplement.
'ª' => 'a',
'º' => 'o',
'À' => 'A',
'Á' => 'A',
'Â' => 'A',
'Ã' => 'A',
'Ä' => 'A',
'Å' => 'A',
'Æ' => 'AE',
'Ç' => 'C',
'È' => 'E',
'É' => 'E',
'Ê' => 'E',
'Ë' => 'E',
'Ì' => 'I',
'Í' => 'I',
'Î' => 'I',
'Ï' => 'I',
'Ð' => 'D',
'Ñ' => 'N',
'Ò' => 'O',
'Ó' => 'O',
'Ô' => 'O',
'Õ' => 'O',
'Ö' => 'O',
'Ù' => 'U',
'Ú' => 'U',
'Û' => 'U',
'Ü' => 'U',
'Ý' => 'Y',
'Þ' => 'TH',
'ß' => 's',
'à' => 'a',
'á' => 'a',
'â' => 'a',
'ã' => 'a',
'ä' => 'a',
'å' => 'a',
'æ' => 'ae',
'ç' => 'c',
'è' => 'e',
'é' => 'e',
'ê' => 'e',
'ë' => 'e',
'ì' => 'i',
'í' => 'i',
'î' => 'i',
'ï' => 'i',
'ð' => 'd',
'ñ' => 'n',
'ò' => 'o',
'ó' => 'o',
'ô' => 'o',
'õ' => 'o',
'ö' => 'o',
'ø' => 'o',
'ù' => 'u',
'ú' => 'u',
'û' => 'u',
'ü' => 'u',
'ý' => 'y',
'þ' => 'th',
'ÿ' => 'y',
'Ø' => 'O',
// Decompositions for Latin Extended-A.
'Ā' => 'A',
'ā' => 'a',
'Ă' => 'A',
'ă' => 'a',
'Ą' => 'A',
'ą' => 'a',
'Ć' => 'C',
'ć' => 'c',
'Ĉ' => 'C',
'ĉ' => 'c',
'Ċ' => 'C',
'ċ' => 'c',
'Č' => 'C',
'č' => 'c',
'Ď' => 'D',
'ď' => 'd',
'Đ' => 'D',
'đ' => 'd',
'Ē' => 'E',
'ē' => 'e',
'Ĕ' => 'E',
'ĕ' => 'e',
'Ė' => 'E',
'ė' => 'e',
'Ę' => 'E',
'ę' => 'e',
'Ě' => 'E',
'ě' => 'e',
'Ĝ' => 'G',
'ĝ' => 'g',
'Ğ' => 'G',
'ğ' => 'g',
'Ġ' => 'G',
'ġ' => 'g',
'Ģ' => 'G',
'ģ' => 'g',
'Ĥ' => 'H',
'ĥ' => 'h',
'Ħ' => 'H',
'ħ' => 'h',
'Ĩ' => 'I',
'ĩ' => 'i',
'Ī' => 'I',
'ī' => 'i',
'Ĭ' => 'I',
'ĭ' => 'i',
'Į' => 'I',
'į' => 'i',
'İ' => 'I',
'ı' => 'i',
'IJ' => 'IJ',
'ij' => 'ij',
'Ĵ' => 'J',
'ĵ' => 'j',
'Ķ' => 'K',
'ķ' => 'k',
'ĸ' => 'k',
'Ĺ' => 'L',
'ĺ' => 'l',
'Ļ' => 'L',
'ļ' => 'l',
'Ľ' => 'L',
'ľ' => 'l',
'Ŀ' => 'L',
'ŀ' => 'l',
'Ł' => 'L',
'ł' => 'l',
'Ń' => 'N',
'ń' => 'n',
'Ņ' => 'N',
'ņ' => 'n',
'Ň' => 'N',
'ň' => 'n',
'ʼn' => 'n',
'Ŋ' => 'N',
'ŋ' => 'n',
'Ō' => 'O',
'ō' => 'o',
'Ŏ' => 'O',
'ŏ' => 'o',
'Ő' => 'O',
'ő' => 'o',
'Œ' => 'OE',
'œ' => 'oe',
'Ŕ' => 'R',
'ŕ' => 'r',
'Ŗ' => 'R',
'ŗ' => 'r',
'Ř' => 'R',
'ř' => 'r',
'Ś' => 'S',
'ś' => 's',
'Ŝ' => 'S',
'ŝ' => 's',
'Ş' => 'S',
'ş' => 's',
'Š' => 'S',
'š' => 's',
'Ţ' => 'T',
'ţ' => 't',
'Ť' => 'T',
'ť' => 't',
'Ŧ' => 'T',
'ŧ' => 't',
'Ũ' => 'U',
'ũ' => 'u',
'Ū' => 'U',
'ū' => 'u',
'Ŭ' => 'U',
'ŭ' => 'u',
'Ů' => 'U',
'ů' => 'u',
'Ű' => 'U',
'ű' => 'u',
'Ų' => 'U',
'ų' => 'u',
'Ŵ' => 'W',
'ŵ' => 'w',
'Ŷ' => 'Y',
'ŷ' => 'y',
'Ÿ' => 'Y',
'Ź' => 'Z',
'ź' => 'z',
'Ż' => 'Z',
'ż' => 'z',
'Ž' => 'Z',
'ž' => 'z',
'ſ' => 's',
// Decompositions for Latin Extended-B.
'Ș' => 'S',
'ș' => 's',
'Ț' => 'T',
'ț' => 't',
// Euro sign.
'€' => 'E',
// GBP (Pound) sign.
'£' => '',
// Vowels with diacritic (Vietnamese).
// Unmarked.
'Ơ' => 'O',
'ơ' => 'o',
'Ư' => 'U',
'ư' => 'u',
// Grave accent.
'Ầ' => 'A',
'ầ' => 'a',
'Ằ' => 'A',
'ằ' => 'a',
'Ề' => 'E',
'ề' => 'e',
'Ồ' => 'O',
'ồ' => 'o',
'Ờ' => 'O',
'ờ' => 'o',
'Ừ' => 'U',
'ừ' => 'u',
'Ỳ' => 'Y',
'ỳ' => 'y',
// Hook.
'Ả' => 'A',
'ả' => 'a',
'Ẩ' => 'A',
'ẩ' => 'a',
'Ẳ' => 'A',
'ẳ' => 'a',
'Ẻ' => 'E',
'ẻ' => 'e',
'Ể' => 'E',
'ể' => 'e',
'Ỉ' => 'I',
'ỉ' => 'i',
'Ỏ' => 'O',
'ỏ' => 'o',
'Ổ' => 'O',
'ổ' => 'o',
'Ở' => 'O',
'ở' => 'o',
'Ủ' => 'U',
'ủ' => 'u',
'Ử' => 'U',
'ử' => 'u',
'Ỷ' => 'Y',
'ỷ' => 'y',
// Tilde.
'Ẫ' => 'A',
'ẫ' => 'a',
'Ẵ' => 'A',
'ẵ' => 'a',
'Ẽ' => 'E',
'ẽ' => 'e',
'Ễ' => 'E',
'ễ' => 'e',
'Ỗ' => 'O',
'ỗ' => 'o',
'Ỡ' => 'O',
'ỡ' => 'o',
'Ữ' => 'U',
'ữ' => 'u',
'Ỹ' => 'Y',
'ỹ' => 'y',
// Acute accent.
'Ấ' => 'A',
'ấ' => 'a',
'Ắ' => 'A',
'ắ' => 'a',
'Ế' => 'E',
'ế' => 'e',
'Ố' => 'O',
'ố' => 'o',
'Ớ' => 'O',
'ớ' => 'o',
'Ứ' => 'U',
'ứ' => 'u',
// Dot below.
'Ạ' => 'A',
'ạ' => 'a',
'Ậ' => 'A',
'ậ' => 'a',
'Ặ' => 'A',
'ặ' => 'a',
'Ẹ' => 'E',
'ẹ' => 'e',
'Ệ' => 'E',
'ệ' => 'e',
'Ị' => 'I',
'ị' => 'i',
'Ọ' => 'O',
'ọ' => 'o',
'Ộ' => 'O',
'ộ' => 'o',
'Ợ' => 'O',
'ợ' => 'o',
'Ụ' => 'U',
'ụ' => 'u',
'Ự' => 'U',
'ự' => 'u',
'Ỵ' => 'Y',
'ỵ' => 'y',
// Vowels with diacritic (Chinese, Hanyu Pinyin).
'ɑ' => 'a',
// Macron.
'Ǖ' => 'U',
'ǖ' => 'u',
// Acute accent.
'Ǘ' => 'U',
'ǘ' => 'u',
// Caron.
'Ǎ' => 'A',
'ǎ' => 'a',
'Ǐ' => 'I',
'ǐ' => 'i',
'Ǒ' => 'O',
'ǒ' => 'o',
'Ǔ' => 'U',
'ǔ' => 'u',
'Ǚ' => 'U',
'ǚ' => 'u',
// Grave accent.
'Ǜ' => 'U',
'ǜ' => 'u',
);
// Used for locale-specific rules.
$locale = get_locale();
if ( in_array( $locale, array( 'de_DE', 'de_DE_formal', 'de_CH', 'de_CH_informal' ), true ) ) {
$chars['Ä'] = 'Ae';
$chars['ä'] = 'ae';
$chars['Ö'] = 'Oe';
$chars['ö'] = 'oe';
$chars['Ü'] = 'Ue';
$chars['ü'] = 'ue';
$chars['ß'] = 'ss';
} elseif ( 'da_DK' === $locale ) {
$chars['Æ'] = 'Ae';
$chars['æ'] = 'ae';
$chars['Ø'] = 'Oe';
$chars['ø'] = 'oe';
$chars['Å'] = 'Aa';
$chars['å'] = 'aa';
} elseif ( 'ca' === $locale ) {
$chars['l·l'] = 'll';
} elseif ( 'sr_RS' === $locale || 'bs_BA' === $locale ) {
$chars['Đ'] = 'DJ';
$chars['đ'] = 'dj';
}
$string = strtr( $string, $chars );
} else {
$chars = array();
// Assume ISO-8859-1 if not UTF-8.
$chars['in'] = "\x80\x83\x8a\x8e\x9a\x9e"
. "\x9f\xa2\xa5\xb5\xc0\xc1\xc2"
. "\xc3\xc4\xc5\xc7\xc8\xc9\xca"
. "\xcb\xcc\xcd\xce\xcf\xd1\xd2"
. "\xd3\xd4\xd5\xd6\xd8\xd9\xda"
. "\xdb\xdc\xdd\xe0\xe1\xe2\xe3"
. "\xe4\xe5\xe7\xe8\xe9\xea\xeb"
. "\xec\xed\xee\xef\xf1\xf2\xf3"
. "\xf4\xf5\xf6\xf8\xf9\xfa\xfb"
. "\xfc\xfd\xff";
$chars['out'] = 'EfSZszYcYuAAAAAACEEEEIIIINOOOOOOUUUUYaaaaaaceeeeiiiinoooooouuuuyy';
$string = strtr( $string, $chars['in'], $chars['out'] );
$double_chars = array();
$double_chars['in'] = array( "\x8c", "\x9c", "\xc6", "\xd0", "\xde", "\xdf", "\xe6", "\xf0", "\xfe" );
$double_chars['out'] = array( 'OE', 'oe', 'AE', 'DH', 'TH', 'ss', 'ae', 'dh', 'th' );
$string = str_replace( $double_chars['in'], $double_chars['out'], $string );
}
return $string;
}
Example Converting standard Vietnamese Characters to non-accent ones:
$bienthuy = "Chào mừng các bạn ghé thăm website của Biên Thùy. Chúc các bạn vui vẻ"; echo bienthuy_to_latin ($bienthuy);
Result:
Chao mung cac ban ghe tham website cua Bien Thuy. Chuc cac ban vui ve