|
1
|
|
|
<?php |
|
2
|
|
|
|
|
3
|
|
|
/* |
|
4
|
|
|
* This file is part of the league/commonmark package. |
|
5
|
|
|
* |
|
6
|
|
|
* (c) Colin O'Dell <[email protected]> |
|
7
|
|
|
* |
|
8
|
|
|
* Original code based on the CommonMark JS reference parser (https://bitly.com/commonmark-js) |
|
9
|
|
|
* - (c) John MacFarlane |
|
10
|
|
|
* |
|
11
|
|
|
* For the full copyright and license information, please view the LICENSE |
|
12
|
|
|
* file that was distributed with this source code. |
|
13
|
|
|
*/ |
|
14
|
|
|
|
|
15
|
|
|
namespace League\CommonMark\Util; |
|
16
|
|
|
|
|
17
|
|
|
final class Html5EntityDecoder |
|
18
|
|
|
{ |
|
19
|
69 |
|
public static function decode(string $entity): string |
|
20
|
|
|
{ |
|
21
|
69 |
|
if (\substr($entity, -1) !== ';') { |
|
22
|
3 |
|
return $entity; |
|
23
|
|
|
} |
|
24
|
|
|
|
|
25
|
69 |
|
if (\substr($entity, 0, 2) === '&#') { |
|
26
|
30 |
|
if (\strtolower(\substr($entity, 2, 1)) === 'x') { |
|
27
|
3 |
|
return self::fromHex(\substr($entity, 3, -1)); |
|
28
|
|
|
} |
|
29
|
|
|
|
|
30
|
27 |
|
return self::fromDecimal(\substr($entity, 2, -1)); |
|
31
|
|
|
} |
|
32
|
|
|
|
|
33
|
51 |
|
return \html_entity_decode($entity, \ENT_QUOTES | \ENT_HTML5, 'UTF-8'); |
|
34
|
|
|
} |
|
35
|
|
|
|
|
36
|
|
|
/** |
|
37
|
|
|
* @param mixed $number |
|
38
|
|
|
* |
|
39
|
|
|
* @return string |
|
40
|
|
|
*/ |
|
41
|
30 |
|
private static function fromDecimal($number): string |
|
42
|
|
|
{ |
|
43
|
|
|
// Only convert code points within planes 0-2, excluding NULL |
|
44
|
30 |
|
if (empty($number) || $number > 0x2FFFF) { |
|
45
|
3 |
|
return self::fromHex('fffd'); |
|
46
|
|
|
} |
|
47
|
|
|
|
|
48
|
30 |
|
$entity = '&#' . $number . ';'; |
|
49
|
|
|
|
|
50
|
30 |
|
$converted = \mb_decode_numericentity($entity, [0x0, 0x2FFFF, 0, 0xFFFF], 'UTF-8'); |
|
51
|
|
|
|
|
52
|
30 |
|
if ($converted === $entity) { |
|
53
|
|
|
return self::fromHex('fffd'); |
|
54
|
|
|
} |
|
55
|
|
|
|
|
56
|
30 |
|
return $converted; |
|
57
|
|
|
} |
|
58
|
|
|
|
|
59
|
6 |
|
private static function fromHex(string $hexChars): string |
|
60
|
|
|
{ |
|
61
|
6 |
|
return self::fromDecimal(\hexdec($hexChars)); |
|
62
|
|
|
} |
|
63
|
|
|
} |
|
64
|
|
|
|
thephpleague /
commonmark
