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
|
|
|
class UrlEncoder |
18
|
|
|
{ |
19
|
|
|
protected static $dontEncode = [ |
20
|
|
|
'%21' => '!', |
21
|
|
|
'%23' => '#', |
22
|
|
|
'%24' => '$', |
23
|
|
|
'%26' => '&', |
24
|
|
|
'%27' => '\'', |
25
|
|
|
'%28' => '(', |
26
|
|
|
'%29' => ')', |
27
|
|
|
'%2A' => '*', |
28
|
|
|
'%2B' => '+', |
29
|
|
|
'%2C' => ',', |
30
|
|
|
'%2D' => '-', |
31
|
|
|
'%2E' => '.', |
32
|
|
|
'%2F' => '/', |
33
|
|
|
'%3A' => ':', |
34
|
|
|
'%3B' => ';', |
35
|
|
|
'%3D' => '=', |
36
|
|
|
'%3F' => '?', |
37
|
|
|
'%40' => '@', |
38
|
|
|
'%5F' => '_', |
39
|
|
|
'%7E' => '~', |
40
|
|
|
]; |
41
|
|
|
|
42
|
|
|
/** |
43
|
|
|
* @param string $uri |
44
|
|
|
* |
45
|
|
|
* @return string |
46
|
|
|
*/ |
47
|
552 |
|
public static function unescapeAndEncode($uri) |
48
|
|
|
{ |
49
|
552 |
|
$decoded = html_entity_decode($uri); |
50
|
|
|
|
51
|
552 |
|
return self::encode(self::decode($decoded)); |
52
|
|
|
} |
53
|
|
|
|
54
|
|
|
/** |
55
|
|
|
* Decode a percent-encoded URI |
56
|
|
|
* |
57
|
|
|
* @param string $uri |
58
|
|
|
* |
59
|
|
|
* @return string |
60
|
|
|
*/ |
61
|
368 |
|
private static function decode($uri) |
62
|
|
|
{ |
63
|
184 |
|
return preg_replace_callback('/%([0-9a-f]{2})/iu', function($matches) { |
64
|
|
|
// Convert percent-encoded codes to uppercase |
65
|
15 |
|
$upper = strtoupper($matches[0]); |
66
|
|
|
// Keep excluded characters as-is |
67
|
15 |
|
if (array_key_exists($upper, self::$dontEncode)) { |
68
|
6 |
|
return $upper; |
69
|
|
|
} |
70
|
|
|
|
71
|
|
|
// Otherwise, return the character for this codepoint |
72
|
12 |
|
return chr(hexdec($matches[1])); |
73
|
552 |
|
}, $uri); |
74
|
|
|
} |
75
|
|
|
|
76
|
|
|
/** |
77
|
|
|
* Encode a URI, preserving already-encoded and excluded characters |
78
|
|
|
* |
79
|
|
|
* @param string $uri |
80
|
|
|
* |
81
|
|
|
* @return string |
82
|
|
|
*/ |
83
|
|
|
private static function encode($uri) |
84
|
|
|
{ |
85
|
552 |
|
return preg_replace_callback('/(%[0-9a-f]{2})|./iu', function($matches){ |
86
|
|
|
// Keep already-encoded characters as-is |
87
|
543 |
|
if (count($matches) > 1) { |
88
|
6 |
|
return $matches[0]; |
89
|
|
|
} |
90
|
|
|
|
91
|
|
|
// Keep excluded characters as-is |
92
|
543 |
|
if (in_array($matches[0], self::$dontEncode)) { |
93
|
477 |
|
return $matches[0]; |
94
|
|
|
} |
95
|
|
|
|
96
|
|
|
// Otherwise, encode the character |
97
|
483 |
|
return rawurlencode($matches[0]); |
98
|
552 |
|
}, $uri); |
99
|
|
|
} |
100
|
|
|
} |
101
|
|
|
|