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
|
|
|
use League\CommonMark\Cursor; |
18
|
|
|
|
19
|
|
|
class LinkParserHelper |
20
|
|
|
{ |
21
|
|
|
/** |
22
|
|
|
* Attempt to parse link destination |
23
|
|
|
* |
24
|
|
|
* @param Cursor $cursor |
25
|
|
|
* |
26
|
|
|
* @return null|string The string, or null if no match |
27
|
|
|
*/ |
28
|
387 |
|
public static function parseLinkDestination(Cursor $cursor) |
29
|
|
|
{ |
30
|
387 |
|
if ($res = $cursor->match(RegexHelper::getInstance()->getLinkDestinationBracesRegex())) { |
31
|
|
|
// Chop off surrounding <..>: |
32
|
12 |
|
return UrlEncoder::unescapeAndEncode( |
33
|
12 |
|
RegexHelper::unescape(substr($res, 1, strlen($res) - 2)) |
34
|
8 |
|
); |
35
|
|
|
} |
36
|
|
|
|
37
|
375 |
|
$oldState = $cursor->saveState(); |
38
|
375 |
|
$openParens = 0; |
39
|
375 |
|
while (($c = $cursor->getCharacter()) !== null) { |
40
|
372 |
|
if ($c === '\\') { |
41
|
21 |
|
$cursor->advanceBy(2); |
42
|
21 |
|
} elseif ($c === '(') { |
43
|
21 |
|
$cursor->advance(); |
44
|
14 |
|
$openParens++; |
45
|
372 |
|
} elseif ($c === ')') { |
46
|
18 |
|
if ($openParens < 1) { |
47
|
18 |
|
break; |
48
|
372 |
|
} |
49
|
117 |
|
|
50
|
114 |
|
$cursor->advance(); |
51
|
|
|
$openParens--; |
52
|
18 |
|
} elseif (preg_match(RegexHelper::REGEX_WHITESPACE_CHAR, $c)) { |
53
|
18 |
|
break; |
54
|
|
|
} else { |
55
|
369 |
|
$cursor->advance(); |
56
|
168 |
|
} |
57
|
|
|
} |
58
|
369 |
|
|
59
|
|
|
$newPos = $cursor->getPosition(); |
60
|
246 |
|
$cursor->restoreState($oldState); |
61
|
|
|
|
62
|
375 |
|
$cursor->advanceBy($newPos - $cursor->getPosition()); |
63
|
375 |
|
|
64
|
|
|
$res = $cursor->getPreviousText(); |
65
|
375 |
|
|
66
|
|
|
return UrlEncoder::unescapeAndEncode( |
67
|
375 |
|
RegexHelper::unescape($res) |
68
|
|
|
); |
69
|
375 |
|
} |
70
|
375 |
|
|
71
|
250 |
|
/** |
72
|
|
|
* @param Cursor $cursor |
73
|
|
|
* |
74
|
|
|
* @return int |
75
|
|
|
*/ |
76
|
|
|
public static function parseLinkLabel(Cursor $cursor) |
77
|
|
|
{ |
78
|
|
|
$escapedChar = RegexHelper::getInstance()->getPartialRegex(RegexHelper::ESCAPED_CHAR); |
79
|
393 |
|
$match = $cursor->match('/^\[(?:[^\\\\\[\]]|' . $escapedChar . '|\\\\)*\]/'); |
80
|
|
|
$length = mb_strlen($match, 'utf-8'); |
81
|
393 |
|
|
82
|
393 |
|
if ($match === null || $length > 1001 || preg_match('/[^\\\\]\\\\\]$/', $match)) { |
83
|
393 |
|
return 0; |
84
|
|
|
} |
85
|
393 |
|
|
86
|
198 |
|
return $length; |
87
|
|
|
} |
88
|
|
|
|
89
|
366 |
|
/** |
90
|
|
|
* Attempt to parse link title (sans quotes) |
91
|
|
|
* |
92
|
|
|
* @param Cursor $cursor |
93
|
|
|
* |
94
|
|
|
* @return null|string The string, or null if no match |
95
|
|
|
*/ |
96
|
|
|
public static function parseLinkTitle(Cursor $cursor) |
97
|
|
|
{ |
98
|
|
|
if ($title = $cursor->match(RegexHelper::getInstance()->getLinkTitleRegex())) { |
99
|
270 |
|
// Chop off quotes from title and unescape |
100
|
|
|
return RegexHelper::unescape(substr($title, 1, strlen($title) - 2)); |
101
|
270 |
|
} |
102
|
|
|
} |
103
|
|
|
} |
104
|
|
|
|