|
1
|
|
|
<?php |
|
2
|
|
|
|
|
3
|
|
|
/** |
|
4
|
|
|
* Highlighter |
|
5
|
|
|
* |
|
6
|
|
|
* Copyright (C) 2016, Some right reserved. |
|
7
|
|
|
* |
|
8
|
|
|
* @author Kacper "Kadet" Donat <[email protected]> |
|
9
|
|
|
* |
|
10
|
|
|
* Contact with author: |
|
11
|
|
|
* Xmpp: [email protected] |
|
12
|
|
|
* E-mail: [email protected] |
|
13
|
|
|
* |
|
14
|
|
|
* From Kadet with love. |
|
15
|
|
|
*/ |
|
16
|
|
|
|
|
17
|
|
|
namespace Kadet\Highlighter\Language; |
|
18
|
|
|
|
|
19
|
|
|
use Kadet\Highlighter\Matcher\CommentMatcher; |
|
20
|
|
|
use Kadet\Highlighter\Matcher\RegexMatcher; |
|
21
|
|
|
use Kadet\Highlighter\Matcher\SubStringMatcher; |
|
22
|
|
|
use Kadet\Highlighter\Matcher\WordMatcher; |
|
23
|
|
|
use Kadet\Highlighter\Parser\CloseRule; |
|
24
|
|
|
use Kadet\Highlighter\Parser\OpenRule; |
|
25
|
|
|
use Kadet\Highlighter\Parser\Rule; |
|
26
|
|
|
use Kadet\Highlighter\Parser\Token\ContextualToken; |
|
27
|
|
|
use Kadet\Highlighter\Parser\Token\LanguageToken; |
|
28
|
|
|
use Kadet\Highlighter\Parser\Token\Token; |
|
29
|
|
|
use Kadet\Highlighter\Parser\TokenFactory; |
|
30
|
|
|
use Kadet\Highlighter\Parser\Validator\Validator; |
|
31
|
|
|
|
|
32
|
|
|
class Perl extends GreedyLanguage |
|
33
|
|
|
{ |
|
34
|
|
|
|
|
35
|
|
|
/** |
|
36
|
|
|
* Tokenization rules definition |
|
37
|
|
|
*/ |
|
38
|
|
|
public function setupRules() |
|
39
|
|
|
{ |
|
40
|
|
|
$identifier = '\w+'; |
|
41
|
|
|
$number = '[+-]?(?=\d|\.\d)\d*(\.\d*)?([Ee]([+-]?\d+))?'; |
|
42
|
|
|
|
|
43
|
|
|
$this->rules->addMany([ |
|
44
|
|
|
'string' => CommonFeatures::strings(['single' => '\'', 'double' => '"'], [ |
|
45
|
|
|
'context' => ['!keyword', '!comment', '!string', '!language', '!number'], |
|
46
|
|
|
]), |
|
47
|
|
|
|
|
48
|
|
|
'comment' => new Rule(new CommentMatcher(['#'])), |
|
49
|
|
|
|
|
50
|
|
|
'keyword' => new Rule(new WordMatcher([ |
|
51
|
|
|
'case', 'continue', 'do', 'else', 'elsif', 'for', 'foreach', |
|
52
|
|
|
'if', 'last', 'my', 'next', 'our', 'redo', 'reset', 'then', |
|
53
|
|
|
'unless', 'until', 'while', 'use', 'print', 'new', 'BEGIN', |
|
54
|
|
|
'sub', 'CHECK', 'INIT', 'END', 'return', 'exit' |
|
55
|
|
|
])), |
|
56
|
|
|
|
|
57
|
|
|
'operator.escape' => new Rule(new RegexMatcher('/(\\\.)/'), [ |
|
58
|
|
|
'context' => ['string'] |
|
59
|
|
|
]), |
|
60
|
|
|
|
|
61
|
|
|
'string.nowdoc' => new Rule( |
|
62
|
|
|
new RegexMatcher('/<<\s*\'(\w+)\';(?P<string>.*?)\R\1/sm', [ |
|
63
|
|
|
'string' => Token::NAME, |
|
64
|
|
|
0 => 'keyword.nowdoc' |
|
65
|
|
|
]), |
|
66
|
|
|
['context' => ['!comment']] |
|
67
|
|
|
), |
|
68
|
|
|
|
|
69
|
|
|
'language.shell' => new Rule(new SubStringMatcher('`'), [ |
|
70
|
|
|
'context' => ['!operator.escape', '!comment', '!string', '!keyword.nowdoc'], |
|
71
|
|
|
'factory' => new TokenFactory(ContextualToken::class), |
|
72
|
|
|
]), |
|
73
|
|
|
|
|
74
|
|
|
'variable.scalar' => new Rule(new RegexMatcher("/(\\\$$identifier)/")), |
|
75
|
|
|
'variable.array' => new Rule(new RegexMatcher("/(\\@$identifier)/")), |
|
76
|
|
|
'variable.hash' => new Rule(new RegexMatcher("/(\\%$identifier)/")), |
|
77
|
|
|
|
|
78
|
|
|
'variable.property' => new Rule(new RegexMatcher("/\\\$$identifier{($identifier)}/")), |
|
79
|
|
|
|
|
80
|
|
|
// Stupidly named var? Perl one, for sure. |
|
81
|
|
|
'variable.special' => new Rule(new RegexMatcher('/([$@%][^\s\w]+[\w]*)/')), |
|
82
|
|
|
|
|
83
|
|
|
'operator' => [ |
|
84
|
|
|
new Rule(new RegexMatcher('/(-[rwxoRWXOezsfdlpSbctugkTBMAC])/')), |
|
85
|
|
|
new Rule(new WordMatcher([ |
|
86
|
|
|
'not', 'and', 'or', 'xor', 'goto', 'last', 'next', 'redo', 'dump', |
|
87
|
|
|
'eq', 'ne', 'cmp', 'not', 'and', 'or', 'xor' |
|
88
|
|
|
], ['atomic' => true])), |
|
89
|
|
|
], |
|
90
|
|
|
|
|
91
|
|
|
'call' => new Rule(new RegexMatcher('/([a-z]\w+)(?:\s*\(|\s+[$%@"\'`{])/i')), |
|
92
|
|
|
|
|
93
|
|
|
'number' => [ |
|
94
|
|
|
new Rule(new RegexMatcher("/(\\b|\"|')$number\\1/", [ |
|
95
|
|
|
0 => Token::NAME |
|
96
|
|
|
]), ['priority' => 5]), |
|
97
|
|
|
], |
|
98
|
|
|
|
|
99
|
|
|
'string.regex' => [ |
|
100
|
|
|
new OpenRule(new RegexMatcher('#~\s*[ms]?(/).*?/#m'), [ |
|
101
|
|
|
'context' => Validator::everywhere() |
|
102
|
|
|
]), |
|
103
|
|
|
new OpenRule(new RegexMatcher('#~\s*(s/).*?/#m')), |
|
104
|
|
|
|
|
105
|
|
|
new Rule(new RegexMatcher('#(?=\/.*?(/[gimuy]{0,5}))#m'), [ |
|
106
|
|
|
'priority' => 1, |
|
107
|
|
|
'factory' => new TokenFactory(ContextualToken::class), |
|
108
|
|
|
'context' => ['!operator.escape', 'string.regex'] |
|
109
|
|
|
]) |
|
110
|
|
|
], |
|
111
|
|
|
|
|
112
|
|
|
'symbol.iterator' => [ |
|
113
|
|
|
new Rule(new RegexMatcher('#(<\w+>)#s')) |
|
114
|
|
|
] |
|
115
|
|
|
]); |
|
116
|
|
|
} |
|
117
|
|
|
|
|
118
|
|
|
/** |
|
119
|
|
|
* Unique language identifier, for example 'php' |
|
120
|
|
|
* |
|
121
|
|
|
* @return string |
|
122
|
|
|
*/ |
|
123
|
|
|
public function getIdentifier() |
|
124
|
|
|
{ |
|
125
|
|
|
return 'perl'; |
|
126
|
|
|
} |
|
127
|
|
|
|
|
128
|
|
|
public function getEnds($embedded = false) |
|
129
|
|
|
{ |
|
130
|
|
|
return [ |
|
131
|
|
|
parent::getEnds($embedded), |
|
132
|
|
|
new CloseRule(new SubStringMatcher('__END__'), [ |
|
133
|
|
|
'factory' => new TokenFactory(LanguageToken::class), |
|
134
|
|
|
'language' => $this |
|
135
|
|
|
]) |
|
136
|
|
|
]; |
|
137
|
|
|
} |
|
138
|
|
|
|
|
139
|
|
|
public static function getMetadata() |
|
140
|
|
|
{ |
|
141
|
|
|
return [ |
|
142
|
|
|
'name' => ['perl'], |
|
143
|
|
|
'mime' => ['text/x-perl', 'application/x-perl'], |
|
144
|
|
|
'extension' => ['*.pl', '*.pm', '*.t'] |
|
145
|
|
|
]; |
|
146
|
|
|
} |
|
147
|
|
|
} |
|
148
|
|
|
|
kadet1090 /
KeyLighter
