|
1
|
|
|
<?php |
|
2
|
|
|
|
|
3
|
|
|
/** |
|
4
|
|
|
* webtrees: online genealogy |
|
5
|
|
|
* Copyright (C) 2021 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
|
|
|
|
|
18
|
|
|
declare(strict_types=1); |
|
19
|
|
|
|
|
20
|
|
|
namespace Fisharebest\Webtrees\Encodings; |
|
21
|
|
|
|
|
22
|
|
|
use function chr; |
|
23
|
|
|
use function intdiv; |
|
24
|
|
|
use function ord; |
|
25
|
|
|
use function str_split; |
|
26
|
|
|
|
|
27
|
|
|
/** |
|
28
|
|
|
* Convert between UTF-16BE and UTF-8. |
|
29
|
|
|
*/ |
|
30
|
|
|
class UTF16BE extends AbstractUTF16Encoding |
|
31
|
|
|
{ |
|
32
|
|
|
public const NAME = 'UTF-16BE'; |
|
33
|
|
|
|
|
34
|
|
|
public const BYTE_ORDER_MARK = "\xFE\xFF"; |
|
35
|
|
|
public const REPLACEMENT_CHARACTER = "\xFF\xFD"; |
|
36
|
|
|
|
|
37
|
|
|
/** |
|
38
|
|
|
* Convert two bytes to a code-point, taking care of byte-order. |
|
39
|
|
|
* |
|
40
|
|
|
* @param string $character |
|
41
|
|
|
* |
|
42
|
|
|
* @return int |
|
43
|
|
|
*/ |
|
44
|
|
|
protected function characterToCodePoint(string $character): int |
|
45
|
|
|
{ |
|
46
|
|
|
return 256 * ord($character[0]) + ord($character[1]); |
|
47
|
|
|
} |
|
48
|
|
|
|
|
49
|
|
|
/** |
|
50
|
|
|
* Convert a code-point to two bytes, taking care of byte-order. |
|
51
|
|
|
* |
|
52
|
|
|
* @param int $code_point |
|
53
|
|
|
* |
|
54
|
|
|
* @return string |
|
55
|
|
|
*/ |
|
56
|
|
|
protected function codePointToCharacter(int $code_point): string |
|
57
|
|
|
{ |
|
58
|
|
|
if ($code_point >= 0xD800 && $code_point <= 0xDFFF) { |
|
59
|
|
|
return self::REPLACEMENT_CHARACTER; |
|
60
|
|
|
} |
|
61
|
|
|
|
|
62
|
|
|
return chr(intdiv($code_point, 256)) . chr($code_point % 256); |
|
63
|
|
|
} |
|
64
|
|
|
} |
|
65
|
|
|
|