CharsetUtils.php

<?php

namespace ArturDoruch\StringUtil;

/**
 * Character sets utilities.
 *
 * @author Artur Doruch <arturdoruch@interia.pl>
 */
class CharsetUtils
{
    /**
     * Checks whether a string has UTF-8 encoding type.
     *
     * @param string $string
     *
     * @return bool
     */
    public static function isUtf8(string $string): bool
    {
        return preg_match('//u', $string); //(bool) mb_detect_encoding($string, 'UTF-8', $strict = true);
    }

    /**
     * Removes characters not available in the UTF-8 encoding type.
     * Code taken from https://webcollab.sourceforge.io/unicode.html
     *
     * @param string $string
     *
     * @return string
     */
    public static function cleanupUtf8(string $string): string
    {
        return preg_replace(
            '/[\x00-\x08\x10\x0B\x0C\x0E-\x19\x7F]'.
            '|[\x00-\x7F][\x80-\xBF]+'.
            '|([\xC0\xC1]|[\xF0-\xFF])[\x80-\xBF]*'.
            '|[\xC2-\xDF]((?![\x80-\xBF])|[\x80-\xBF]{2,})'.
            '|[\xE0-\xEF](([\x80-\xBF](?![\x80-\xBF]))|(?![\x80-\xBF]{2})|[\x80-\xBF]{3,})/S',
            '', $string);
    }

    /**
     * Decodes hexadecimal code points of the UTF-8 charset escaped with "\u", like "\uXXXX".
     * The code points of the characters not available in the UTF-8 charset are removed.
     * Code taken from https://stackoverflow.com/a/2934602
     *
     * @param string $string
     * @param string $encoding Encoding type of the $string. E.g: UTF-16BE.
     *
     * @return string
     */
    public static function decodeHexCodePoints(string $string, string $encoding = 'UCS-2BE'): string
    {
        return preg_replace_callback('/\\\u([0-9a-fA-F]{4,6})/', function ($matches) use ($encoding) {
            if (strlen($matches[1]) > 4) {
                return '';
            }

            return mb_convert_encoding(pack('H*', $matches[1]), 'UTF-8', $encoding);
        }, $string);
    }

    /**
     * @param string $string
     *
     * @return string
     */
    public static function decodeNonBreakingSpaces($string): string
    {
        $string = str_replace('&nbsp;', ' ', $string);

        if (null === $str = preg_replace('/\x{00A0}/u', ' ', $string)) {
            return $string;
        }

        return $str;
    }

    /**
     * Removes accents (diacritic marks) from a string, by converting them to their
     * corresponding non-accented ASCII characters.
     *
     * @param string $string
     *
     * @return string
     */
    public static function removeAccents(string $string): string
    {
        return strtr($string, self::ACCENTED_CHARACTERS);
    }

    const ACCENTED_CHARACTERS = [
        'À' => 'A',
        'Á' => 'A',
        'Â' => 'A',
        'Ã' => 'A',
        'Ä' => 'Ae',
        'Æ' => 'Ae',
        'Å' => 'Aa',
        'æ' => 'a',
        'Ç' => 'C',
        'È' => 'E',
        'É' => 'E',
        'Ê' => 'E',
        'Ë' => 'E',
        'Ì' => 'I',
        'Í' => 'I',
        'Î' => 'I',
        'Ï' => 'I',
        'Ñ' => 'N',
        'Ò' => 'O',
        'Ó' => 'O',
        'Ô' => 'O',
        'Õ' => 'O',
        'Ö' => 'Oe',
        'Ù' => 'U',
        'Ú' => 'U',
        'Û' => 'U',
        'Ü' => 'Ue',
        'Ý' => 'Y',
        'ß' => 'ss',
        'à' => 'a',
        'á' => 'a',
        'â' => 'a',
        'ã' => 'a',
        'ä' => 'ae',
        'å' => 'aa',
        'ç' => 'c',
        'è' => 'e',
        'é' => 'e',
        'ê' => 'e',
        'ë' => 'e',
        'ì' => 'i',
        'í' => 'i',
        'î' => 'i',
        'ï' => 'i',
        'ñ' => 'n',
        'ò' => 'o',
        'ó' => 'o',
        'ô' => 'o',
        'õ' => 'o',
        'ö' => 'oe',
        'ù' => 'u',
        'ú' => 'u',
        'û' => 'u',
        'ü' => 'ue',
        'ý' => 'y',
        'ÿ' => 'y',
        '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',
        'Ø' => 'O',
        'ø' => 'o',
        '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',
    ];
}