WordPress.org

Make WordPress Core

Opened 13 months ago

Last modified 13 months ago

#44906 new enhancement

Include greek accent characters on "remove_accents" function

Reported by: papazetis Owned by:
Milestone: Awaiting Review Priority: normal
Severity: minor Version: 4.9.8
Component: Formatting Keywords: has-patch dev-feedback
Focuses: Cc:
PR Number:

Description

Hi,

I extended the "remove_accents" function to support greek accents.
If you wish you can add it in core.

I have just added greek characters after:

elseif ( 'el' == $locale ) {

Thanks

<?php
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 ( 'de_DE' == $locale || 'de_DE_formal' == $locale || 'de_CH' == $locale || 'de_CH_informal' == $locale ) {
            $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';
        } elseif ( 'el' == $locale ) {
            $chars[ 'Ά' ] = 'Α';
            $chars[ 'ά' ] = 'α';
            $chars[ 'Έ' ] = 'Ε';
            $chars[ 'έ' ] = 'α';
            $chars[ 'Ί' ] = 'Ι';
            $chars[ 'ί' ] = 'ι';
            $chars[ 'ΐ' ] = 'ϊ';
            $chars[ 'Ύ' ] = 'Υ';
            $chars[ 'ύ' ] = 'υ';
            $chars[ 'ΰ' ] = 'ϋ';
            $chars[ 'Ή' ] = 'Η';
            $chars[ 'ή' ] = 'η';
            $chars[ 'Ό' ] = 'Ο';
            $chars[ 'ό' ] = 'ο';
            $chars[ 'Ώ' ] = 'Ω';
            $chars[ 'ώ' ] = 'ω';
        }

        $string = strtr($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;

}

Attachments (2)

44906.patch (981 bytes) - added by mukesh27 13 months ago.
Try this patch.
44906.2.patch (981 bytes) - added by mukesh27 13 months ago.
updated patch.

Download all attachments as: .zip

Change History (6)

#1 in reply to: ↑ description @papazetis
13 months ago

Wrong character.
Just replace:

$chars[ 'έ' ] = 'α';

with

$chars[ 'έ' ] = 'ε';

Replying to papazetis:

Hi,

I extended the "remove_accents" function to support greek accents.
If you wish you can add it in core.

I have just added greek characters after:

elseif ( 'el' == $locale ) {

Thanks

<?php
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 ( 'de_DE' == $locale || 'de_DE_formal' == $locale || 'de_CH' == $locale || 'de_CH_informal' == $locale ) {
            $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';
        } elseif ( 'el' == $locale ) {
            $chars[ 'Ά' ] = 'Α';
            $chars[ 'ά' ] = 'α';
            $chars[ 'Έ' ] = 'Ε';
            $chars[ 'έ' ] = 'α';
            $chars[ 'Ί' ] = 'Ι';
            $chars[ 'ί' ] = 'ι';
            $chars[ 'ΐ' ] = 'ϊ';
            $chars[ 'Ύ' ] = 'Υ';
            $chars[ 'ύ' ] = 'υ';
            $chars[ 'ΰ' ] = 'ϋ';
            $chars[ 'Ή' ] = 'Η';
            $chars[ 'ή' ] = 'η';
            $chars[ 'Ό' ] = 'Ο';
            $chars[ 'ό' ] = 'ο';
            $chars[ 'Ώ' ] = 'Ω';
            $chars[ 'ώ' ] = 'ω';
        }

        $string = strtr($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;

}

@mukesh27
13 months ago

Try this patch.

#2 follow-up: @mukesh27
13 months ago

  • Keywords has-patch dev-feedback added
  • Severity changed from normal to minor

#3 in reply to: ↑ 2 @papazetis
13 months ago

Replying to mukesh27:

I added a wrong character before. So please change this line (1736)

$chars[ 'έ' ] = 'α';

with that

$chars[ 'έ' ] = 'ε';
Last edited 13 months ago by papazetis (previous) (diff)

@mukesh27
13 months ago

updated patch.

Note: See TracTickets for help on using tickets.