|
1
|
|
|
<?php |
|
2
|
|
|
/** |
|
3
|
|
|
* Highlighter |
|
4
|
|
|
* |
|
5
|
|
|
* Copyright (C) 2016, Some right reserved. |
|
6
|
|
|
* |
|
7
|
|
|
* @author Kacper "Kadet" Donat <[email protected]> |
|
8
|
|
|
* |
|
9
|
|
|
* Contact with author: |
|
10
|
|
|
* Xmpp: [email protected] |
|
11
|
|
|
* E-mail: [email protected] |
|
12
|
|
|
* |
|
13
|
|
|
* From Kadet with love. |
|
14
|
|
|
*/ |
|
15
|
|
|
|
|
16
|
|
|
namespace Kadet\Highlighter\Language; |
|
17
|
|
|
|
|
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\Rule; |
|
25
|
|
|
use Kadet\Highlighter\Parser\Token\ContextualToken; |
|
26
|
|
|
use Kadet\Highlighter\Parser\Token\TerminatorToken; |
|
27
|
|
|
use Kadet\Highlighter\Parser\Token\Token; |
|
28
|
|
|
use Kadet\Highlighter\Parser\TokenFactory; |
|
29
|
|
|
use Kadet\Highlighter\Parser\Validator\Validator; |
|
30
|
|
|
|
|
31
|
|
|
class Python extends GreedyLanguage |
|
32
|
|
|
{ |
|
33
|
|
|
|
|
34
|
|
|
/** |
|
35
|
|
|
* Tokenization rules setup |
|
36
|
|
|
*/ |
|
37
|
|
|
public function setupRules() |
|
38
|
|
|
{ |
|
39
|
|
|
$standard = new Validator(['!string', '!comment']); |
|
40
|
|
|
|
|
41
|
|
|
$this->rules->addMany([ |
|
42
|
|
|
'keyword' => new Rule(new WordMatcher([ |
|
43
|
|
|
'and', 'del', 'from', 'not', 'while', 'as', 'elif', 'global', 'or', 'with', 'assert', 'else', 'if', |
|
44
|
|
|
'pass', 'yield', 'break', 'except', 'import', 'print', 'class', 'exec', 'in', 'raise', 'continue', |
|
45
|
|
|
'finally', 'is', 'return', 'def', 'for', 'lambda', 'try', |
|
46
|
|
|
])), |
|
47
|
|
|
|
|
48
|
|
|
'operator' => new Rule( |
|
49
|
|
|
new RegexMatcher('/([-+%=]=?|!=|\*\*?=?|\/\/?=?|<[<=>]?|>[=>]?|[&|^~])|\b(or|and|not)\b/'), [ |
|
50
|
|
|
'priority' => -1 |
|
51
|
|
|
] |
|
52
|
|
|
), |
|
53
|
|
|
|
|
54
|
|
|
'expression' => new Rule(new RegexMatcher('/\{(\S+)\}/'), [ |
|
55
|
|
|
'context' => ['string'] |
|
56
|
|
|
]), |
|
57
|
|
|
|
|
58
|
|
|
'variable' => [ |
|
59
|
|
|
new Rule(new RegexMatcher('/[^\w.]([a-z_]\w*)\.\w/i')), |
|
60
|
|
|
'property' => new Rule(new RegexMatcher('/(?=(?:\w|\)|\])\s*\.([a-z_]\w*))/i'), [ |
|
61
|
|
|
'priority' => -2, |
|
62
|
|
|
'context' => ['*none', '*expression'] |
|
63
|
|
|
]), |
|
64
|
|
|
], |
|
65
|
|
|
|
|
66
|
|
|
'symbol' => [ |
|
67
|
|
|
new Rule(new RegexMatcher('/import\s+([a-z_][\w.]*)(?:\s*,\s*([a-z_][\w.]*))*/i', [ |
|
68
|
|
|
1 => Token::NAME, |
|
69
|
|
|
2 => Token::NAME, |
|
70
|
|
|
])), |
|
71
|
|
|
'library' => new Rule(new RegexMatcher('/from\s+([a-z_][\w.]*)\s+import/i', [ |
|
72
|
|
|
1 => Token::NAME, |
|
73
|
|
|
])) |
|
74
|
|
|
], |
|
75
|
|
|
|
|
76
|
|
|
'keyword.escape' => new Rule(new RegexMatcher('/(\\\(?:.|[0-7]{3}|x\x{2}))/'), [ |
|
77
|
|
|
'context' => Validator::everywhere() |
|
78
|
|
|
]), |
|
79
|
|
|
|
|
80
|
|
|
'comment' => new Rule(new CommentMatcher(['#'])), |
|
81
|
|
|
'constant.special' => [ |
|
82
|
|
|
new Rule(new WordMatcher(['True', 'False', 'NotImplemented', 'Ellipsis'], [ |
|
83
|
|
|
'case-sensitivity' => true |
|
84
|
|
|
])), |
|
85
|
|
|
new Rule(new RegexMatcher('/\b(__\w+__)\b/')) |
|
86
|
|
|
], |
|
87
|
|
|
'call' => new Rule(new RegexMatcher('/([a-z_]\w*)\s*\(/i'), ['priority' => 2]), |
|
88
|
|
|
|
|
89
|
|
|
'meta.newline' => new CloseRule(new RegexMatcher('/()\r?\n/'), [ |
|
90
|
|
|
'factory' => new TokenFactory(TerminatorToken::class), |
|
91
|
|
|
'context' => ['!keyword.escape', 'string.single-line'], |
|
92
|
|
|
'closes' => ['string.single-line.double', 'string.single-line.single'] |
|
93
|
|
|
]), |
|
94
|
|
|
|
|
95
|
|
|
'number' => new Rule( |
|
96
|
|
|
new RegexMatcher('/(-?(?:0[bo])?(?:(?:\d|0x[\da-f])[\da-f]*\.?\d*|\.\d+)(?:e[+-]?\d+)?j?)\b/') |
|
97
|
|
|
), |
|
98
|
|
|
|
|
99
|
|
|
'string' => [ |
|
100
|
|
|
'single-line' => [ |
|
101
|
|
|
'double' => new Rule(new RegexMatcher('/(?:^|[^"])(")(?=[^"]|$)/'), [ |
|
102
|
|
|
'factory' => new TokenFactory(ContextualToken::class), |
|
103
|
|
|
'context' => $standard, |
|
104
|
|
|
]), |
|
105
|
|
|
'single' => new Rule(new RegexMatcher('/(?:^|[^\'])(\')(?=[^\']|$)/'), [ |
|
106
|
|
|
'factory' => new TokenFactory(ContextualToken::class), |
|
107
|
|
|
'context' => $standard, |
|
108
|
|
|
]), |
|
109
|
|
|
], |
|
110
|
|
|
'multi-line' => [ |
|
111
|
|
|
'double' => new Rule(new SubStringMatcher('"""'), [ |
|
112
|
|
|
'factory' => new TokenFactory(ContextualToken::class), |
|
113
|
|
|
'context' => $standard, |
|
114
|
|
|
'priority' => 2, |
|
115
|
|
|
]), |
|
116
|
|
|
'single' => new Rule(new SubStringMatcher('\'\'\''), [ |
|
117
|
|
|
'factory' => new TokenFactory(ContextualToken::class), |
|
118
|
|
|
'context' => $standard, |
|
119
|
|
|
'priority' => 2, |
|
120
|
|
|
]), |
|
121
|
|
|
] |
|
122
|
|
|
], |
|
123
|
|
|
|
|
124
|
|
|
'symbol.function' => new Rule(new RegexMatcher('/def\s+([a-z_]\w+)\s*\(/i')), |
|
125
|
|
|
'symbol.class' => new Rule(new RegexMatcher('/class\s+([a-z_]\w+)/i')), |
|
126
|
|
|
]); |
|
127
|
|
|
} |
|
128
|
|
|
|
|
129
|
|
|
/** |
|
130
|
|
|
* Unique language identifier, for example 'php' |
|
131
|
|
|
* |
|
132
|
|
|
* @return string |
|
133
|
|
|
*/ |
|
134
|
|
|
public function getIdentifier() |
|
135
|
|
|
{ |
|
136
|
|
|
return 'python'; |
|
137
|
|
|
} |
|
138
|
|
|
} |
|
139
|
|
|
|
kadet1090 /
KeyLighter
