yf_utf8_clean class

    public function _do($text = '', $params = [])
    {
        if ( ! strlen($text)) {
            return '';
        }
        $text = utf8_strip_ascii_ctrl($text);
        if ((SEARCH_COUNTRY == 'ua' || $params['country'] == 'ua') && preg_match('/[а-яА-Я]/', $text)) {
            $text = $this->_utf8_bad_for_rus_clean($text);
        } else {
            $text = $this->_utf8_strip_non_ascii($text);
        }
        if ($params['simple_chars']) {
            $allowed_symbols = implode('', array_keys($this->UTF8_LOWER_ACCENTS)) . implode('', array_keys($this->UTF8_UPPER_ACCENTS));
            if ((SEARCH_COUNTRY == 'ua' || $params['country'] == 'ua')) {
                $allowed_symbols .= 'а-яА-Я';
            }
            $text = preg_replace('/[^a-z0-9' . $allowed_symbols . ' ]/', '', $text);
        }
        return $text;
    }

    public function _init()
    {
        // TODO: check and enable: require_php_lib('yf_utf8_funcs') and set $this->fss_exists = function_exists('fss_prep_replace')
        return false;
    }

    public function _unaccent($str = '')
    {
        if ( ! common()->is_utf8($str)) {
            $str = mb_convert_encoding($str, 'UTF-8', 'ISO-8859-1');
        }
        if ($this->fss_exists && ! ($GLOBALS['force_strtr'] ?? null)) {
            if ( ! isset($GLOBALS['fss']['unaccent'])) {
                $s = array_merge($this->UTF8_UPPER_ACCENTS, $this->UTF8_LOWER_ACCENTS);
                $GLOBALS['fss']['unaccent'] = fss_prep_replace($s);
            }
            $str = fss_exec_replace(($GLOBALS['fss']['unaccent'] ?? null), $str);

            return $str;
        }
        $str = strtr($str, $this->UTF8_UPPER_ACCENTS);
        $str = strtr($str, $this->UTF8_LOWER_ACCENTS);
        return $str;
    }

    public function _unaccent_test2($string = '')
    {
        $transliteration = [
            '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', 'IJ' => 'IJ', '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', 'Ö' => 'Oe', 'Ø' => 'O',
            'Ō' => 'O', 'Ő' => 'O', 'Ŏ' => 'O', 'Œ' => 'OE', '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', 'Ü' => 'Ue',
            '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', 'ä' => 'ae', 'ā' => 'a', 'ą' => 'a',
            'ă' => 'a', 'å' => 'a', 'æ' => 'ae', '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',
            'ij' => 'ij', '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', 'ö' => 'oe',
            'ø' => 'o', 'ō' => 'o', 'ő' => 'o', 'ŏ' => 'o', 'œ' => 'oe',
            'ŕ' => 'r', 'ř' => 'r', 'ŗ' => 'r', 'ś' => 's', 'š' => 's',
            'ť' => 't', 'ù' => 'u', 'ú' => 'u', 'û' => 'u', 'ü' => 'ue',
            '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', 'ß' => 'ss', 'ſ' => 'ss',
        ];
        $string = strtr($string, $transliteration);
        return $string;
    }

    public function _unaccent_test3($text = '')
    {
        static $search;
        if ( ! $search) {
            $search = [];
            // Get the HTML entities table into an array
            $trans = [
                '"' => '"',
                '&' => '&',
                '\'' => ''',
                '<' => '<',
                '>' => '>',
            ];
            // Go through the entity mappings one-by-one
            foreach ((array) $trans as $literal => $entity) {
                // Make sure we don't process any other characters
                // such as fractions, quotes etc:
                if (ord($literal) >= 192) {
                    // Get the accented form of the letter
                    // Get e.g. 'E' from the string '&Eacute'
                    $search[mb_convert_encoding($literal, 'UTF-8', 'ISO-8859-1')] = $entity[1];
                }
            }
        }
        return strtr($text, $search);
    }

    public function _utf8_bad_for_rus_clean($str)
    {
        $UTF8_BAD =
            '([\x00-\x7F]' .						  // ASCII (including control chars)
            '|[\xC2-\xDF][\x80-\xBF]' .			  // non-overlong 2-byte
            '|\xE0[\xA0-\xBF][\x80-\xBF]' .		  // excluding overlongs
            '|[\xE1-\xEC\xEE\xEF][\x80-\xBF]{2}' . // straight 3-byte
            '|\xED[\x80-\x9F][\x80-\xBF]' .		  // excluding surrogates
            '|\xF0[\x90-\xBF][\x80-\xBF]{2}' .	  // planes 1-3
            '|[\xF1-\xF3][\x80-\xBF]{3}' .		  // planes 4-15
            '|\xF4[\x80-\x8F][\x80-\xBF]{2}' .	  // plane 16
            '|(.{1}))';							  // invalid byte
        ob_start();
        while (preg_match('/' . $UTF8_BAD . '/S', $str, $matches)) {
            if ( ! isset($matches[2])) {
                echo $matches[0];
            }
            $str = substr($str, strlen($matches[0]));
        }
        $result = ob_get_clean();
        return $result;
    }

    public function _utf8_strip_non_ascii($str)
    {
        ob_start();
        while (preg_match('/^([\x00-\x7F]+)|([^\x00-\x7F]+)/S', $str, $matches)) {
            if ( ! isset($matches[2])) {
                echo $matches[0];
            } else {
                // Leave accented symbols untouched
                if (isset($this->UTF8_LOWER_ACCENTS[$matches[0]]) || isset($this->UTF8_UPPER_ACCENTS[$matches[0]])) {
                    echo $matches[0];
                }
            }
            $str = substr($str, strlen($matches[0]));
        }
        $result = ob_get_clean();
        return $result;
    }