1
|
|
|
<?php |
2
|
|
|
|
3
|
|
|
/* |
4
|
|
|
* This file is part of the league/commonmark package. |
5
|
|
|
* |
6
|
|
|
* (c) Colin O'Dell <[email protected]> |
7
|
|
|
* |
8
|
|
|
* For the full copyright and license information, please view the LICENSE |
9
|
|
|
* file that was distributed with this source code. |
10
|
|
|
*/ |
11
|
|
|
|
12
|
|
|
namespace League\CommonMark\Extension\Autolink; |
13
|
|
|
|
14
|
|
|
use League\CommonMark\Event\DocumentParsedEvent; |
15
|
|
|
use League\CommonMark\Inline\Element\Link; |
16
|
|
|
use League\CommonMark\Inline\Element\Text; |
17
|
|
|
|
18
|
|
|
final class UrlAutolinkProcessor |
19
|
|
|
{ |
20
|
|
|
// RegEx adapted from https://github.com/symfony/symfony/blob/4.2/src/Symfony/Component/Validator/Constraints/UrlValidator.php |
21
|
|
|
const REGEX = '~ |
22
|
|
|
(?<=^|[ \\t\\n\\x0b\\x0c\\x0d*_\\~\\(]) # Can only come at the beginning of a line, after whitespace, or certain delimiting characters |
23
|
|
|
( |
24
|
|
|
# Must start with a supported scheme + auth, or "www" |
25
|
|
|
(?: |
26
|
|
|
(?:%s):// # protocol |
27
|
|
|
(?:([\.\pL\pN-]+:)?([\.\pL\pN-]+)@)? # basic auth |
28
|
|
|
|www\.) |
29
|
|
|
(?: |
30
|
|
|
(?:[\pL\pN\pS\-\.])+(?:\.?(?:[\pL\pN]|xn\-\-[\pL\pN-]+)+\.?) # a domain name |
31
|
|
|
| # or |
32
|
|
|
\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3} # an IP address |
33
|
|
|
| # or |
34
|
|
|
\[ |
35
|
|
|
(?:(?:(?:(?:(?:(?:(?:[0-9a-f]{1,4})):){6})(?:(?:(?:(?:(?:[0-9a-f]{1,4})):(?:(?:[0-9a-f]{1,4})))|(?:(?:(?:(?:(?:25[0-5]|(?:[1-9]|1[0-9]|2[0-4])?[0-9]))\.){3}(?:(?:25[0-5]|(?:[1-9]|1[0-9]|2[0-4])?[0-9])))))))|(?:(?:::(?:(?:(?:[0-9a-f]{1,4})):){5})(?:(?:(?:(?:(?:[0-9a-f]{1,4})):(?:(?:[0-9a-f]{1,4})))|(?:(?:(?:(?:(?:25[0-5]|(?:[1-9]|1[0-9]|2[0-4])?[0-9]))\.){3}(?:(?:25[0-5]|(?:[1-9]|1[0-9]|2[0-4])?[0-9])))))))|(?:(?:(?:(?:(?:[0-9a-f]{1,4})))?::(?:(?:(?:[0-9a-f]{1,4})):){4})(?:(?:(?:(?:(?:[0-9a-f]{1,4})):(?:(?:[0-9a-f]{1,4})))|(?:(?:(?:(?:(?:25[0-5]|(?:[1-9]|1[0-9]|2[0-4])?[0-9]))\.){3}(?:(?:25[0-5]|(?:[1-9]|1[0-9]|2[0-4])?[0-9])))))))|(?:(?:(?:(?:(?:(?:[0-9a-f]{1,4})):){0,1}(?:(?:[0-9a-f]{1,4})))?::(?:(?:(?:[0-9a-f]{1,4})):){3})(?:(?:(?:(?:(?:[0-9a-f]{1,4})):(?:(?:[0-9a-f]{1,4})))|(?:(?:(?:(?:(?:25[0-5]|(?:[1-9]|1[0-9]|2[0-4])?[0-9]))\.){3}(?:(?:25[0-5]|(?:[1-9]|1[0-9]|2[0-4])?[0-9])))))))|(?:(?:(?:(?:(?:(?:[0-9a-f]{1,4})):){0,2}(?:(?:[0-9a-f]{1,4})))?::(?:(?:(?:[0-9a-f]{1,4})):){2})(?:(?:(?:(?:(?:[0-9a-f]{1,4})):(?:(?:[0-9a-f]{1,4})))|(?:(?:(?:(?:(?:25[0-5]|(?:[1-9]|1[0-9]|2[0-4])?[0-9]))\.){3}(?:(?:25[0-5]|(?:[1-9]|1[0-9]|2[0-4])?[0-9])))))))|(?:(?:(?:(?:(?:(?:[0-9a-f]{1,4})):){0,3}(?:(?:[0-9a-f]{1,4})))?::(?:(?:[0-9a-f]{1,4})):)(?:(?:(?:(?:(?:[0-9a-f]{1,4})):(?:(?:[0-9a-f]{1,4})))|(?:(?:(?:(?:(?:25[0-5]|(?:[1-9]|1[0-9]|2[0-4])?[0-9]))\.){3}(?:(?:25[0-5]|(?:[1-9]|1[0-9]|2[0-4])?[0-9])))))))|(?:(?:(?:(?:(?:(?:[0-9a-f]{1,4})):){0,4}(?:(?:[0-9a-f]{1,4})))?::)(?:(?:(?:(?:(?:[0-9a-f]{1,4})):(?:(?:[0-9a-f]{1,4})))|(?:(?:(?:(?:(?:25[0-5]|(?:[1-9]|1[0-9]|2[0-4])?[0-9]))\.){3}(?:(?:25[0-5]|(?:[1-9]|1[0-9]|2[0-4])?[0-9])))))))|(?:(?:(?:(?:(?:(?:[0-9a-f]{1,4})):){0,5}(?:(?:[0-9a-f]{1,4})))?::)(?:(?:[0-9a-f]{1,4})))|(?:(?:(?:(?:(?:(?:[0-9a-f]{1,4})):){0,6}(?:(?:[0-9a-f]{1,4})))?::)))) |
36
|
|
|
\] # an IPv6 address |
37
|
|
|
) |
38
|
|
|
(?::[0-9]+)? # a port (optional) |
39
|
|
|
(?:/ (?:[\pL\pN\-._\~!$&\'()*+,;=:@]|%%[0-9A-Fa-f]{2})* )* # a path |
40
|
|
|
(?:\? (?:[\pL\pN\-._\~!$&\'()*+,;=:@/?]|%%[0-9A-Fa-f]{2})* )? # a query (optional) |
41
|
|
|
(?:\# (?:[\pL\pN\-._\~!$&\'()*+,;=:@/?]|%%[0-9A-Fa-f]{2})* )? # a fragment (optional) |
42
|
|
|
)~ixu'; |
43
|
|
|
|
44
|
|
|
private $finalRegex; |
45
|
|
|
|
46
|
177 |
|
public function __construct(array $allowedProtocols = ['http', 'https', 'ftp']) |
47
|
|
|
{ |
48
|
177 |
|
$this->finalRegex = \sprintf(self::REGEX, \implode('|', $allowedProtocols)); |
49
|
177 |
|
} |
50
|
|
|
|
51
|
|
|
/** |
52
|
|
|
* @param DocumentParsedEvent $e |
53
|
|
|
* |
54
|
|
|
* @return void |
55
|
|
|
*/ |
56
|
177 |
|
public function __invoke(DocumentParsedEvent $e) |
57
|
|
|
{ |
58
|
177 |
|
$walker = $e->getDocument()->walker(); |
59
|
|
|
|
60
|
177 |
|
while ($event = $walker->next()) { |
61
|
177 |
|
$node = $event->getNode(); |
62
|
177 |
|
if ($node instanceof Text && !($node->parent() instanceof Link)) { |
63
|
162 |
|
self::processAutolinks($node, $this->finalRegex); |
64
|
|
|
} |
65
|
|
|
} |
66
|
177 |
|
} |
67
|
|
|
|
68
|
162 |
|
private static function processAutolinks(Text $node, $regex) |
69
|
|
|
{ |
70
|
162 |
|
$contents = \preg_split($regex, $node->getContent(), -1, PREG_SPLIT_DELIM_CAPTURE); |
71
|
|
|
|
72
|
162 |
|
if ($contents === false || \count($contents) === 1) { |
73
|
75 |
|
return; |
74
|
|
|
} |
75
|
|
|
|
76
|
87 |
|
$leftovers = ''; |
77
|
87 |
|
foreach ($contents as $i => $content) { |
78
|
|
|
// Even-indexed elements are things before/after the URLs |
79
|
87 |
|
if ($i % 2 === 0) { |
80
|
|
|
// Insert any left-over characters here as well |
81
|
87 |
|
$text = $leftovers . $content; |
82
|
87 |
|
if ($text !== '') { |
83
|
51 |
|
$node->insertBefore(new Text($leftovers . $content)); |
84
|
|
|
} |
85
|
|
|
|
86
|
87 |
|
$leftovers = ''; |
87
|
87 |
|
continue; |
88
|
|
|
} |
89
|
|
|
|
90
|
87 |
|
$leftovers = ''; |
91
|
|
|
|
92
|
|
|
// Does the URL end with punctuation that should be stripped? |
93
|
87 |
|
if (\preg_match('/(.+)([?!.,:*_~]+)$/', $content, $matches)) { |
94
|
|
|
// Add the punctuation later |
95
|
24 |
|
$content = $matches[1]; |
96
|
24 |
|
$leftovers = $matches[2]; |
97
|
|
|
} |
98
|
|
|
|
99
|
|
|
// Does the URL end with something that looks like an entity reference? |
100
|
87 |
|
if (\preg_match('/(.+)(&[A-Za-z0-9]+;)$/', $content, $matches)) { |
101
|
6 |
|
$content = $matches[1]; |
102
|
6 |
|
$leftovers = $matches[2] . $leftovers; |
103
|
|
|
} |
104
|
|
|
|
105
|
|
|
// Does the URL need its closing paren chopped off? |
106
|
87 |
|
if (\substr($content, -1) === ')' && self::hasMoreCloserParensThanOpeners($content)) { |
107
|
12 |
|
$content = \substr($content, 0, -1); |
108
|
12 |
|
$leftovers = ')' . $leftovers; |
109
|
|
|
} |
110
|
|
|
|
111
|
87 |
|
self::addLink($node, $content); |
112
|
|
|
} |
113
|
|
|
|
114
|
87 |
|
$node->detach(); |
115
|
87 |
|
} |
116
|
|
|
|
117
|
87 |
|
private static function addLink(Text $node, $url) |
118
|
|
|
{ |
119
|
|
|
// Auto-prefix 'http://' onto 'www' URLs |
120
|
87 |
|
if (\substr($url, 0, 4) === 'www.') { |
121
|
48 |
|
$node->insertBefore(new Link('http://' . $url, $url)); |
122
|
|
|
|
123
|
48 |
|
return; |
124
|
|
|
} |
125
|
|
|
|
126
|
39 |
|
$node->insertBefore(new Link($url, $url)); |
127
|
39 |
|
} |
128
|
|
|
|
129
|
|
|
/** |
130
|
|
|
* @param string $content |
131
|
|
|
* |
132
|
|
|
* @return bool |
133
|
|
|
*/ |
134
|
15 |
|
private static function hasMoreCloserParensThanOpeners($content) |
135
|
|
|
{ |
136
|
|
|
// Scan the entire autolink for the total number of parentheses. |
137
|
|
|
// If there is a greater number of closing parentheses than opening ones, |
138
|
|
|
// we don’t consider the last character part of the autolink, in order to |
139
|
|
|
// facilitate including an autolink inside a parenthesis. |
140
|
15 |
|
\preg_match_all('/[()]/', $content, $matches); |
141
|
|
|
|
142
|
15 |
|
$charCount = ['(' => 0, ')' => 0]; |
143
|
15 |
|
foreach ($matches[0] as $char) { |
144
|
15 |
|
$charCount[$char]++; |
145
|
|
|
} |
146
|
|
|
|
147
|
15 |
|
return $charCount[')'] > $charCount['(']; |
148
|
|
|
} |
149
|
|
|
} |
150
|
|
|
|