xref: /webtrees/app/Encodings/UTF16BE.php (revision d11be7027e34e3121be11cc025421873364403f9)
1<?php
2
3/**
4 * webtrees: online genealogy
5 * Copyright (C) 2023 webtrees development team
6 * This program is free software: you can redistribute it and/or modify
7 * it under the terms of the GNU General Public License as published by
8 * the Free Software Foundation, either version 3 of the License, or
9 * (at your option) any later version.
10 * This program is distributed in the hope that it will be useful,
11 * but WITHOUT ANY WARRANTY; without even the implied warranty of
12 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
13 * GNU General Public License for more details.
14 * You should have received a copy of the GNU General Public License
15 * along with this program. If not, see <https://www.gnu.org/licenses/>.
16 */
17
18declare(strict_types=1);
19
20namespace Fisharebest\Webtrees\Encodings;
21
22use function chr;
23use function intdiv;
24use function ord;
25
26/**
27 * Convert between UTF-16BE and UTF-8.
28 */
29class UTF16BE extends AbstractUTF16Encoding
30{
31    public const NAME = 'UTF-16BE';
32
33    public const BYTE_ORDER_MARK       = "\xFE\xFF";
34    public const REPLACEMENT_CHARACTER = "\xFF\xFD";
35
36    /**
37     * Convert two bytes to a code-point, taking care of byte-order.
38     *
39     * @param string $character
40     *
41     * @return int
42     */
43    protected function characterToCodePoint(string $character): int
44    {
45        return 256 * ord($character[0]) + ord($character[1]);
46    }
47
48    /**
49     * Convert a code-point to two bytes, taking care of byte-order.
50     *
51     * @param int $code_point
52     *
53     * @return string
54     */
55    protected function codePointToCharacter(int $code_point): string
56    {
57        if ($code_point >= 0xD800 && $code_point <= 0xDFFF) {
58            return self::REPLACEMENT_CHARACTER;
59        }
60
61        return chr(intdiv($code_point, 256)) . chr($code_point % 256);
62    }
63}
64