RegexHelper::matchAll()   B
last analyzed

Complexity

Conditions 6
Paths 10

Size

Total Lines 21

Duplication

Lines 0
Ratio 0 %

Code Coverage

Tests 11
CRAP Score 6

Importance

Changes 0
Metric Value
dl 0
loc 21
ccs 11
cts 11
cp 1
rs 8.9617
c 0
b 0
f 0
cc 6
nc 10
nop 3
crap 6
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\Block\Element\HtmlBlock;
18
19
/**
20
 * Provides regular expressions and utilities for parsing Markdown
21
 */
22
final class RegexHelper
23
{
24
    // Partial regular expressions (wrap with `/` on each side before use)
25
    public const PARTIAL_ENTITY = '&(?:#x[a-f0-9]{1,6}|#[0-9]{1,7}|[a-z][a-z0-9]{1,31});';
26
    public const PARTIAL_ESCAPABLE = '[!"#$%&\'()*+,.\/:;<=>[email protected][\\\\\]^_`{|}~-]';
27
    public const PARTIAL_ESCAPED_CHAR = '\\\\' . self::PARTIAL_ESCAPABLE;
28
    public const PARTIAL_IN_DOUBLE_QUOTES = '"(' . self::PARTIAL_ESCAPED_CHAR . '|[^"\x00])*"';
29
    public const PARTIAL_IN_SINGLE_QUOTES = '\'(' . self::PARTIAL_ESCAPED_CHAR . '|[^\'\x00])*\'';
30
    public const PARTIAL_IN_PARENS = '\\((' . self::PARTIAL_ESCAPED_CHAR . '|[^)\x00])*\\)';
31
    public const PARTIAL_REG_CHAR = '[^\\\\()\x00-\x20]';
32
    public const PARTIAL_IN_PARENS_NOSP = '\((' . self::PARTIAL_REG_CHAR . '|' . self::PARTIAL_ESCAPED_CHAR . '|\\\\)*\)';
33
    public const PARTIAL_TAGNAME = '[A-Za-z][A-Za-z0-9-]*';
34
    public const PARTIAL_BLOCKTAGNAME = '(?:address|article|aside|base|basefont|blockquote|body|caption|center|col|colgroup|dd|details|dialog|dir|div|dl|dt|fieldset|figcaption|figure|footer|form|frame|frameset|h1|head|header|hr|html|iframe|legend|li|link|main|menu|menuitem|nav|noframes|ol|optgroup|option|p|param|section|source|title|summary|table|tbody|td|tfoot|th|thead|title|tr|track|ul)';
35
    public const PARTIAL_ATTRIBUTENAME = '[a-zA-Z_:][a-zA-Z0-9:._-]*';
36
    public const PARTIAL_UNQUOTEDVALUE = '[^"\'=<>`\x00-\x20]+';
37
    public const PARTIAL_SINGLEQUOTEDVALUE = '\'[^\']*\'';
38
    public const PARTIAL_DOUBLEQUOTEDVALUE = '"[^"]*"';
39
    public const PARTIAL_ATTRIBUTEVALUE = '(?:' . self::PARTIAL_UNQUOTEDVALUE . '|' . self::PARTIAL_SINGLEQUOTEDVALUE . '|' . self::PARTIAL_DOUBLEQUOTEDVALUE . ')';
40
    public const PARTIAL_ATTRIBUTEVALUESPEC = '(?:' . '\s*=' . '\s*' . self::PARTIAL_ATTRIBUTEVALUE . ')';
41
    public const PARTIAL_ATTRIBUTE = '(?:' . '\s+' . self::PARTIAL_ATTRIBUTENAME . self::PARTIAL_ATTRIBUTEVALUESPEC . '?)';
42
    public const PARTIAL_OPENTAG = '<' . self::PARTIAL_TAGNAME . self::PARTIAL_ATTRIBUTE . '*' . '\s*\/?>';
43
    public const PARTIAL_CLOSETAG = '<\/' . self::PARTIAL_TAGNAME . '\s*[>]';
44
    public const PARTIAL_OPENBLOCKTAG = '<' . self::PARTIAL_BLOCKTAGNAME . self::PARTIAL_ATTRIBUTE . '*' . '\s*\/?>';
45
    public const PARTIAL_CLOSEBLOCKTAG = '<\/' . self::PARTIAL_BLOCKTAGNAME . '\s*[>]';
46
    public const PARTIAL_HTMLCOMMENT = '<!---->|<!--(?:-?[^>-])(?:-?[^-])*-->';
47
    public const PARTIAL_PROCESSINGINSTRUCTION = '[<][?].*?[?][>]';
48
    public const PARTIAL_DECLARATION = '<![A-Z]+' . '\s+[^>]*>';
49
    public const PARTIAL_CDATA = '<!\[CDATA\[[\s\S]*?]\]>';
50
    public const PARTIAL_HTMLTAG = '(?:' . self::PARTIAL_OPENTAG . '|' . self::PARTIAL_CLOSETAG . '|' . self::PARTIAL_HTMLCOMMENT . '|' .
51
        self::PARTIAL_PROCESSINGINSTRUCTION . '|' . self::PARTIAL_DECLARATION . '|' . self::PARTIAL_CDATA . ')';
52
    public const PARTIAL_HTMLBLOCKOPEN = '<(?:' . self::PARTIAL_BLOCKTAGNAME . '(?:[\s\/>]|$)' . '|' .
53
        '\/' . self::PARTIAL_BLOCKTAGNAME . '(?:[\s>]|$)' . '|' . '[?!])';
54
    public const PARTIAL_LINK_TITLE = '^(?:"(' . self::PARTIAL_ESCAPED_CHAR . '|[^"\x00])*"' .
55
        '|' . '\'(' . self::PARTIAL_ESCAPED_CHAR . '|[^\'\x00])*\'' .
56
        '|' . '\((' . self::PARTIAL_ESCAPED_CHAR . '|[^()\x00])*\))';
57
58
    public const REGEX_PUNCTUATION = '/^[\x{2000}-\x{206F}\x{2E00}-\x{2E7F}\p{Pc}\p{Pd}\p{Pe}\p{Pf}\p{Pi}\p{Po}\p{Ps}\\\\\'!"#\$%&\(\)\*\+,\-\.\\/:;<=>\[email protected]\[\]\^_`\{\|\}~]/u';
59
    public const REGEX_UNSAFE_PROTOCOL = '/^javascript:|vbscript:|file:|data:/i';
60
    public const REGEX_SAFE_DATA_PROTOCOL = '/^data:image\/(?:png|gif|jpeg|webp)/i';
61
    public const REGEX_NON_SPACE = '/[^ \t\f\v\r\n]/';
62
63
    public const REGEX_WHITESPACE_CHAR = '/^[ \t\n\x0b\x0c\x0d]/';
64
    public const REGEX_WHITESPACE = '/[ \t\n\x0b\x0c\x0d]+/';
65
    public const REGEX_UNICODE_WHITESPACE_CHAR = '/^\pZ|\s/u';
66
    public const REGEX_THEMATIC_BREAK = '/^(?:(?:\*[ \t]*){3,}|(?:_[ \t]*){3,}|(?:-[ \t]*){3,})[ \t]*$/';
67
    public const REGEX_LINK_DESTINATION_BRACES = '/^(?:<(?:[^<>\\n\\\\\\x00]|\\\\.)*>)/';
68
69
    /**
70
     * @param string $character
71
     *
72
     * @return bool
73
     */
74 114
    public static function isEscapable(string $character): bool
75
    {
76 114
        return \preg_match('/' . self::PARTIAL_ESCAPABLE . '/', $character) === 1;
77
    }
78
79
    /**
80
     * Attempt to match a regex in string s at offset offset
81
     *
82
     * @param string $regex
83
     * @param string $string
84
     * @param int    $offset
85
     *
86
     * @return int|null Index of match, or null
87
     */
88 1899
    public static function matchAt(string $regex, string $string, int $offset = 0): ?int
89
    {
90 1899
        $matches = [];
91 1899
        $string = \mb_substr($string, $offset, null, 'utf-8');
92 1899
        if (!\preg_match($regex, $string, $matches, \PREG_OFFSET_CAPTURE)) {
93 1839
            return null;
94
        }
95
96
        // PREG_OFFSET_CAPTURE always returns the byte offset, not the char offset, which is annoying
97 297
        $charPos = \mb_strlen(\mb_strcut($string, 0, $matches[0][1], 'utf-8'), 'utf-8');
98
99 297
        return $offset + $charPos;
100
    }
101
102
    /**
103
     * Functional wrapper around preg_match_all
104
     *
105
     * @param string $pattern
106
     * @param string $subject
107
     * @param int    $offset
108
     *
109
     * @return array|null
110
     */
111 2001
    public static function matchAll(string $pattern, string $subject, int $offset = 0): ?array
112
    {
113 2001
        if ($offset !== 0) {
114 420
            $subject = \substr($subject, $offset);
115
        }
116
117 2001
        \preg_match_all($pattern, $subject, $matches, \PREG_PATTERN_ORDER);
118
119 2001
        $fullMatches = \reset($matches);
120 2001
        if (empty($fullMatches)) {
121 1956
            return null;
122
        }
123
124 303
        if (\count($fullMatches) === 1) {
125 303
            foreach ($matches as &$match) {
126 303
                $match = \reset($match);
127
            }
128
        }
129
130 303
        return $matches ?: null;
131
    }
132
133
    /**
134
     * Replace backslash escapes with literal characters
135
     *
136
     * @param string $string
137
     *
138
     * @return string
139
     */
140 525
    public static function unescape(string $string): string
141
    {
142 525
        $allEscapedChar = '/\\\\(' . self::PARTIAL_ESCAPABLE . ')/';
143
144 525
        /** @var string $escaped */
145
        $escaped = \preg_replace($allEscapedChar, '$1', $string);
146 24
147 525
        /** @var string $replaced */
148
        $replaced = \preg_replace_callback('/' . self::PARTIAL_ENTITY . '/i', function ($e) {
149 525
            return Html5EntityDecoder::decode($e[0]);
150
        }, $escaped);
151
152
        return $replaced;
153
    }
154
155
    /**
156
     * @param int $type HTML block type
157
     *
158
     * @return string
159 318
     *
160
     * @internal
161 212
     */
162 106
    public static function getHtmlBlockOpenRegex(int $type): string
163 285
    {
164 98
        switch ($type) {
165 267
            case HtmlBlock::TYPE_1_CODE_CONTAINER:
166 91
                return '/^<(?:script|pre|style)(?:\s|>|$)/i';
167 252
            case HtmlBlock::TYPE_2_COMMENT:
168 88
                return '/^<!--/';
169 249
            case HtmlBlock::TYPE_3:
170 85
                return '/^<[?]/';
171 246
            case HtmlBlock::TYPE_4:
172 82
                return '/^<![A-Z]/';
173 240
            case HtmlBlock::TYPE_5_CDATA:
174 54
                return '/^<!\[CDATA\[/';
175 159
            case HtmlBlock::TYPE_6_BLOCK_ELEMENT:
176
                return '%^<[/]?(?:address|article|aside|base|basefont|blockquote|body|caption|center|col|colgroup|dd|details|dialog|dir|div|dl|dt|fieldset|figcaption|figure|footer|form|frame|frameset|h[123456]|head|header|hr|html|iframe|legend|li|link|main|menu|menuitem|nav|noframes|ol|optgroup|option|p|param|section|source|title|summary|table|tbody|td|tfoot|th|thead|title|tr|track|ul)(?:\s|[/]?[>]|$)%i';
177
            case HtmlBlock::TYPE_7_MISC_ELEMENT:
178 3
                return '/^(?:' . self::PARTIAL_OPENTAG . '|' . self::PARTIAL_CLOSETAG . ')\\s*$/i';
179
        }
180
181
        throw new \InvalidArgumentException('Invalid HTML block type');
182
    }
183
184
    /**
185
     * @param int $type HTML block type
186
     *
187
     * @return string
188 63
     *
189
     * @internal
190 42
     */
191 21
    public static function getHtmlBlockCloseRegex(int $type): string
192 30
    {
193 11
        switch ($type) {
194 15
            case HtmlBlock::TYPE_1_CODE_CONTAINER:
195 6
                return '%<\/(?:script|pre|style)>%i';
196 3
            case HtmlBlock::TYPE_2_COMMENT:
197 5
                return '/-->/';
198 3
            case HtmlBlock::TYPE_3:
199 4
                return '/\?>/';
200 3
            case HtmlBlock::TYPE_4:
201
                return '/>/';
202
            case HtmlBlock::TYPE_5_CDATA:
203 9
                return '/\]\]>/';
204
        }
205
206
        throw new \InvalidArgumentException('Invalid HTML block type');
207
    }
208
209
    /**
210
     * @param string $url
211 24
     *
212
     * @return bool
213 24
     */
214
    public static function isLinkPotentiallyUnsafe(string $url): bool
215
    {
216
        return \preg_match(self::REGEX_UNSAFE_PROTOCOL, $url) !== 0 && \preg_match(self::REGEX_SAFE_DATA_PROTOCOL, $url) === 0;
217
    }
218
}
219