pygmentize 0.0.1
Sign up to get free protection for your applications and to get access to all the features.
- data/LICENSE +19 -0
- data/lib/pygments.rb +23 -0
- data/pygmentize.gemspec +11 -0
- data/test/pygments.rb +19 -0
- data/vendor/pygmentize.py +7 -0
- data/vendor/pygments/AUTHORS +73 -0
- data/vendor/pygments/LICENSE +25 -0
- data/vendor/pygments/__init__.py +91 -0
- data/vendor/pygments/__init__.pyc +0 -0
- data/vendor/pygments/cmdline.py +430 -0
- data/vendor/pygments/cmdline.pyc +0 -0
- data/vendor/pygments/console.py +74 -0
- data/vendor/pygments/console.pyc +0 -0
- data/vendor/pygments/filter.py +74 -0
- data/vendor/pygments/filter.pyc +0 -0
- data/vendor/pygments/filters/__init__.py +357 -0
- data/vendor/pygments/filters/__init__.pyc +0 -0
- data/vendor/pygments/formatter.py +92 -0
- data/vendor/pygments/formatter.pyc +0 -0
- data/vendor/pygments/formatters/__init__.py +68 -0
- data/vendor/pygments/formatters/__init__.pyc +0 -0
- data/vendor/pygments/formatters/_mapping.py +92 -0
- data/vendor/pygments/formatters/_mapping.pyc +0 -0
- data/vendor/pygments/formatters/bbcode.py +109 -0
- data/vendor/pygments/formatters/bbcode.pyc +0 -0
- data/vendor/pygments/formatters/html.py +723 -0
- data/vendor/pygments/formatters/html.pyc +0 -0
- data/vendor/pygments/formatters/img.py +553 -0
- data/vendor/pygments/formatters/img.pyc +0 -0
- data/vendor/pygments/formatters/latex.py +354 -0
- data/vendor/pygments/formatters/latex.pyc +0 -0
- data/vendor/pygments/formatters/other.py +117 -0
- data/vendor/pygments/formatters/other.pyc +0 -0
- data/vendor/pygments/formatters/rtf.py +136 -0
- data/vendor/pygments/formatters/rtf.pyc +0 -0
- data/vendor/pygments/formatters/svg.py +154 -0
- data/vendor/pygments/formatters/svg.pyc +0 -0
- data/vendor/pygments/formatters/terminal.py +109 -0
- data/vendor/pygments/formatters/terminal.pyc +0 -0
- data/vendor/pygments/formatters/terminal256.py +219 -0
- data/vendor/pygments/formatters/terminal256.pyc +0 -0
- data/vendor/pygments/lexer.py +660 -0
- data/vendor/pygments/lexer.pyc +0 -0
- data/vendor/pygments/lexers/__init__.py +226 -0
- data/vendor/pygments/lexers/__init__.pyc +0 -0
- data/vendor/pygments/lexers/_asybuiltins.py +1645 -0
- data/vendor/pygments/lexers/_clbuiltins.py +232 -0
- data/vendor/pygments/lexers/_luabuiltins.py +256 -0
- data/vendor/pygments/lexers/_mapping.py +234 -0
- data/vendor/pygments/lexers/_mapping.pyc +0 -0
- data/vendor/pygments/lexers/_phpbuiltins.py +3389 -0
- data/vendor/pygments/lexers/_vimbuiltins.py +3 -0
- data/vendor/pygments/lexers/agile.py +1485 -0
- data/vendor/pygments/lexers/agile.pyc +0 -0
- data/vendor/pygments/lexers/asm.py +353 -0
- data/vendor/pygments/lexers/compiled.py +2365 -0
- data/vendor/pygments/lexers/dotnet.py +355 -0
- data/vendor/pygments/lexers/functional.py +756 -0
- data/vendor/pygments/lexers/functional.pyc +0 -0
- data/vendor/pygments/lexers/math.py +461 -0
- data/vendor/pygments/lexers/other.py +2297 -0
- data/vendor/pygments/lexers/parsers.py +695 -0
- data/vendor/pygments/lexers/special.py +100 -0
- data/vendor/pygments/lexers/special.pyc +0 -0
- data/vendor/pygments/lexers/templates.py +1387 -0
- data/vendor/pygments/lexers/text.py +1586 -0
- data/vendor/pygments/lexers/web.py +1619 -0
- data/vendor/pygments/lexers/web.pyc +0 -0
- data/vendor/pygments/plugin.py +74 -0
- data/vendor/pygments/plugin.pyc +0 -0
- data/vendor/pygments/scanner.py +104 -0
- data/vendor/pygments/style.py +117 -0
- data/vendor/pygments/style.pyc +0 -0
- data/vendor/pygments/styles/__init__.py +68 -0
- data/vendor/pygments/styles/__init__.pyc +0 -0
- data/vendor/pygments/styles/autumn.py +65 -0
- data/vendor/pygments/styles/borland.py +51 -0
- data/vendor/pygments/styles/bw.py +49 -0
- data/vendor/pygments/styles/colorful.py +81 -0
- data/vendor/pygments/styles/default.py +73 -0
- data/vendor/pygments/styles/default.pyc +0 -0
- data/vendor/pygments/styles/emacs.py +72 -0
- data/vendor/pygments/styles/friendly.py +72 -0
- data/vendor/pygments/styles/fruity.py +43 -0
- data/vendor/pygments/styles/manni.py +75 -0
- data/vendor/pygments/styles/monokai.py +106 -0
- data/vendor/pygments/styles/murphy.py +80 -0
- data/vendor/pygments/styles/native.py +65 -0
- data/vendor/pygments/styles/pastie.py +75 -0
- data/vendor/pygments/styles/perldoc.py +69 -0
- data/vendor/pygments/styles/tango.py +141 -0
- data/vendor/pygments/styles/trac.py +63 -0
- data/vendor/pygments/styles/vim.py +63 -0
- data/vendor/pygments/styles/vs.py +38 -0
- data/vendor/pygments/token.py +198 -0
- data/vendor/pygments/token.pyc +0 -0
- data/vendor/pygments/unistring.py +130 -0
- data/vendor/pygments/unistring.pyc +0 -0
- data/vendor/pygments/util.py +226 -0
- data/vendor/pygments/util.pyc +0 -0
- metadata +166 -0
@@ -0,0 +1,695 @@
|
|
1
|
+
# -*- coding: utf-8 -*-
|
2
|
+
"""
|
3
|
+
pygments.lexers.parsers
|
4
|
+
~~~~~~~~~~~~~~~~~~~~~~~
|
5
|
+
|
6
|
+
Lexers for parser generators.
|
7
|
+
|
8
|
+
:copyright: Copyright 2006-2010 by the Pygments team, see AUTHORS.
|
9
|
+
:license: BSD, see LICENSE for details.
|
10
|
+
"""
|
11
|
+
|
12
|
+
import re
|
13
|
+
|
14
|
+
from pygments.lexer import RegexLexer, DelegatingLexer, \
|
15
|
+
include, bygroups, using
|
16
|
+
from pygments.token import Punctuation, Other, Text, Comment, Operator, \
|
17
|
+
Keyword, Name, String, Number, Whitespace
|
18
|
+
from pygments.lexers.compiled import JavaLexer, CLexer, CppLexer, \
|
19
|
+
ObjectiveCLexer, DLexer
|
20
|
+
from pygments.lexers.dotnet import CSharpLexer
|
21
|
+
from pygments.lexers.agile import RubyLexer, PythonLexer, PerlLexer
|
22
|
+
from pygments.lexers.web import ActionScriptLexer
|
23
|
+
|
24
|
+
|
25
|
+
__all__ = ['RagelLexer', 'RagelEmbeddedLexer', 'RagelCLexer', 'RagelDLexer',
|
26
|
+
'RagelCppLexer', 'RagelObjectiveCLexer', 'RagelRubyLexer',
|
27
|
+
'RagelJavaLexer', 'AntlrLexer', 'AntlrPythonLexer',
|
28
|
+
'AntlrPerlLexer', 'AntlrRubyLexer', 'AntlrCppLexer',
|
29
|
+
#'AntlrCLexer',
|
30
|
+
'AntlrCSharpLexer', 'AntlrObjectiveCLexer',
|
31
|
+
'AntlrJavaLexer', "AntlrActionScriptLexer"]
|
32
|
+
|
33
|
+
|
34
|
+
class RagelLexer(RegexLexer):
|
35
|
+
"""
|
36
|
+
A pure `Ragel <http://www.complang.org/ragel/>`_ lexer. Use this for
|
37
|
+
fragments of Ragel. For ``.rl`` files, use RagelEmbeddedLexer instead
|
38
|
+
(or one of the language-specific subclasses).
|
39
|
+
|
40
|
+
*New in Pygments 1.1.*
|
41
|
+
"""
|
42
|
+
|
43
|
+
name = 'Ragel'
|
44
|
+
aliases = ['ragel']
|
45
|
+
filenames = []
|
46
|
+
|
47
|
+
tokens = {
|
48
|
+
'whitespace': [
|
49
|
+
(r'\s+', Whitespace)
|
50
|
+
],
|
51
|
+
'comments': [
|
52
|
+
(r'\#.*$', Comment),
|
53
|
+
],
|
54
|
+
'keywords': [
|
55
|
+
(r'(access|action|alphtype)\b', Keyword),
|
56
|
+
(r'(getkey|write|machine|include)\b', Keyword),
|
57
|
+
(r'(any|ascii|extend|alpha|digit|alnum|lower|upper)\b', Keyword),
|
58
|
+
(r'(xdigit|cntrl|graph|print|punct|space|zlen|empty)\b', Keyword)
|
59
|
+
],
|
60
|
+
'numbers': [
|
61
|
+
(r'0x[0-9A-Fa-f]+', Number.Hex),
|
62
|
+
(r'[+-]?[0-9]+', Number.Integer),
|
63
|
+
],
|
64
|
+
'literals': [
|
65
|
+
(r'"(\\\\|\\"|[^"])*"', String), # double quote string
|
66
|
+
(r"'(\\\\|\\'|[^'])*'", String), # single quote string
|
67
|
+
(r'\[(\\\\|\\\]|[^\]])*\]', String), # square bracket literals
|
68
|
+
(r'/(?!\*)(\\\\|\\/|[^/])*/', String.Regex), # regular expressions
|
69
|
+
],
|
70
|
+
'identifiers': [
|
71
|
+
(r'[a-zA-Z_][a-zA-Z_0-9]*', Name.Variable),
|
72
|
+
],
|
73
|
+
'operators': [
|
74
|
+
(r',', Operator), # Join
|
75
|
+
(r'\||&|-|--', Operator), # Union, Intersection and Subtraction
|
76
|
+
(r'\.|<:|:>|:>>', Operator), # Concatention
|
77
|
+
(r':', Operator), # Label
|
78
|
+
(r'->', Operator), # Epsilon Transition
|
79
|
+
(r'(>|\$|%|<|@|<>)(/|eof\b)', Operator), # EOF Actions
|
80
|
+
(r'(>|\$|%|<|@|<>)(!|err\b)', Operator), # Global Error Actions
|
81
|
+
(r'(>|\$|%|<|@|<>)(\^|lerr\b)', Operator), # Local Error Actions
|
82
|
+
(r'(>|\$|%|<|@|<>)(~|to\b)', Operator), # To-State Actions
|
83
|
+
(r'(>|\$|%|<|@|<>)(\*|from\b)', Operator), # From-State Actions
|
84
|
+
(r'>|@|\$|%', Operator), # Transition Actions and Priorities
|
85
|
+
(r'\*|\?|\+|{[0-9]*,[0-9]*}', Operator), # Repetition
|
86
|
+
(r'!|\^', Operator), # Negation
|
87
|
+
(r'\(|\)', Operator), # Grouping
|
88
|
+
],
|
89
|
+
'root': [
|
90
|
+
include('literals'),
|
91
|
+
include('whitespace'),
|
92
|
+
include('comments'),
|
93
|
+
include('keywords'),
|
94
|
+
include('numbers'),
|
95
|
+
include('identifiers'),
|
96
|
+
include('operators'),
|
97
|
+
(r'{', Punctuation, 'host'),
|
98
|
+
(r'=', Operator),
|
99
|
+
(r';', Punctuation),
|
100
|
+
],
|
101
|
+
'host': [
|
102
|
+
(r'(' + r'|'.join(( # keep host code in largest possible chunks
|
103
|
+
r'[^{}\'"/#]+', # exclude unsafe characters
|
104
|
+
r'[^\\][\\][{}]', # allow escaped { or }
|
105
|
+
|
106
|
+
# strings and comments may safely contain unsafe characters
|
107
|
+
r'"(\\\\|\\"|[^"])*"', # double quote string
|
108
|
+
r"'(\\\\|\\'|[^'])*'", # single quote string
|
109
|
+
r'//.*$\n?', # single line comment
|
110
|
+
r'/\*(.|\n)*?\*/', # multi-line javadoc-style comment
|
111
|
+
r'\#.*$\n?', # ruby comment
|
112
|
+
|
113
|
+
# regular expression: There's no reason for it to start
|
114
|
+
# with a * and this stops confusion with comments.
|
115
|
+
r'/(?!\*)(\\\\|\\/|[^/])*/',
|
116
|
+
|
117
|
+
# / is safe now that we've handled regex and javadoc comments
|
118
|
+
r'/',
|
119
|
+
)) + r')+', Other),
|
120
|
+
|
121
|
+
(r'{', Punctuation, '#push'),
|
122
|
+
(r'}', Punctuation, '#pop'),
|
123
|
+
],
|
124
|
+
}
|
125
|
+
|
126
|
+
|
127
|
+
class RagelEmbeddedLexer(RegexLexer):
|
128
|
+
"""
|
129
|
+
A lexer for `Ragel`_ embedded in a host language file.
|
130
|
+
|
131
|
+
This will only highlight Ragel statements. If you want host language
|
132
|
+
highlighting then call the language-specific Ragel lexer.
|
133
|
+
|
134
|
+
*New in Pygments 1.1.*
|
135
|
+
"""
|
136
|
+
|
137
|
+
name = 'Embedded Ragel'
|
138
|
+
aliases = ['ragel-em']
|
139
|
+
filenames = ['*.rl']
|
140
|
+
|
141
|
+
tokens = {
|
142
|
+
'root': [
|
143
|
+
(r'(' + r'|'.join(( # keep host code in largest possible chunks
|
144
|
+
r'[^%\'"/#]+', # exclude unsafe characters
|
145
|
+
r'%(?=[^%]|$)', # a single % sign is okay, just not 2 of them
|
146
|
+
|
147
|
+
# strings and comments may safely contain unsafe characters
|
148
|
+
r'"(\\\\|\\"|[^"])*"', # double quote string
|
149
|
+
r"'(\\\\|\\'|[^'])*'", # single quote string
|
150
|
+
r'/\*(.|\n)*?\*/', # multi-line javadoc-style comment
|
151
|
+
r'//.*$\n?', # single line comment
|
152
|
+
r'\#.*$\n?', # ruby/ragel comment
|
153
|
+
r'/(?!\*)(\\\\|\\/|[^/])*/', # regular expression
|
154
|
+
|
155
|
+
# / is safe now that we've handled regex and javadoc comments
|
156
|
+
r'/',
|
157
|
+
)) + r')+', Other),
|
158
|
+
|
159
|
+
# Single Line FSM.
|
160
|
+
# Please don't put a quoted newline in a single line FSM.
|
161
|
+
# That's just mean. It will break this.
|
162
|
+
(r'(%%)(?![{%])(.*)($|;)(\n?)', bygroups(Punctuation,
|
163
|
+
using(RagelLexer),
|
164
|
+
Punctuation, Text)),
|
165
|
+
|
166
|
+
# Multi Line FSM.
|
167
|
+
(r'(%%%%|%%){', Punctuation, 'multi-line-fsm'),
|
168
|
+
],
|
169
|
+
'multi-line-fsm': [
|
170
|
+
(r'(' + r'|'.join(( # keep ragel code in largest possible chunks.
|
171
|
+
r'(' + r'|'.join((
|
172
|
+
r'[^}\'"\[/#]', # exclude unsafe characters
|
173
|
+
r'}(?=[^%]|$)', # } is okay as long as it's not followed by %
|
174
|
+
r'}%(?=[^%]|$)', # ...well, one %'s okay, just not two...
|
175
|
+
r'[^\\][\\][{}]', # ...and } is okay if it's escaped
|
176
|
+
|
177
|
+
# allow / if it's preceded with one of these symbols
|
178
|
+
# (ragel EOF actions)
|
179
|
+
r'(>|\$|%|<|@|<>)/',
|
180
|
+
|
181
|
+
# specifically allow regex followed immediately by *
|
182
|
+
# so it doesn't get mistaken for a comment
|
183
|
+
r'/(?!\*)(\\\\|\\/|[^/])*/\*',
|
184
|
+
|
185
|
+
# allow / as long as it's not followed by another / or by a *
|
186
|
+
r'/(?=[^/\*]|$)',
|
187
|
+
|
188
|
+
# We want to match as many of these as we can in one block.
|
189
|
+
# Not sure if we need the + sign here,
|
190
|
+
# does it help performance?
|
191
|
+
)) + r')+',
|
192
|
+
|
193
|
+
# strings and comments may safely contain unsafe characters
|
194
|
+
r'"(\\\\|\\"|[^"])*"', # double quote string
|
195
|
+
r"'(\\\\|\\'|[^'])*'", # single quote string
|
196
|
+
r"\[(\\\\|\\\]|[^\]])*\]", # square bracket literal
|
197
|
+
r'/\*(.|\n)*?\*/', # multi-line javadoc-style comment
|
198
|
+
r'//.*$\n?', # single line comment
|
199
|
+
r'\#.*$\n?', # ruby/ragel comment
|
200
|
+
)) + r')+', using(RagelLexer)),
|
201
|
+
|
202
|
+
(r'}%%', Punctuation, '#pop'),
|
203
|
+
]
|
204
|
+
}
|
205
|
+
|
206
|
+
def analyse_text(text):
|
207
|
+
return '@LANG: indep' in text or 0.1
|
208
|
+
|
209
|
+
|
210
|
+
class RagelRubyLexer(DelegatingLexer):
|
211
|
+
"""
|
212
|
+
A lexer for `Ragel`_ in a Ruby host file.
|
213
|
+
|
214
|
+
*New in Pygments 1.1.*
|
215
|
+
"""
|
216
|
+
|
217
|
+
name = 'Ragel in Ruby Host'
|
218
|
+
aliases = ['ragel-ruby', 'ragel-rb']
|
219
|
+
filenames = ['*.rl']
|
220
|
+
|
221
|
+
def __init__(self, **options):
|
222
|
+
super(RagelRubyLexer, self).__init__(RubyLexer, RagelEmbeddedLexer,
|
223
|
+
**options)
|
224
|
+
|
225
|
+
def analyse_text(text):
|
226
|
+
return '@LANG: ruby' in text
|
227
|
+
|
228
|
+
|
229
|
+
class RagelCLexer(DelegatingLexer):
|
230
|
+
"""
|
231
|
+
A lexer for `Ragel`_ in a C host file.
|
232
|
+
|
233
|
+
*New in Pygments 1.1.*
|
234
|
+
"""
|
235
|
+
|
236
|
+
name = 'Ragel in C Host'
|
237
|
+
aliases = ['ragel-c']
|
238
|
+
filenames = ['*.rl']
|
239
|
+
|
240
|
+
def __init__(self, **options):
|
241
|
+
super(RagelCLexer, self).__init__(CLexer, RagelEmbeddedLexer,
|
242
|
+
**options)
|
243
|
+
|
244
|
+
def analyse_text(text):
|
245
|
+
return '@LANG: c' in text
|
246
|
+
|
247
|
+
|
248
|
+
class RagelDLexer(DelegatingLexer):
|
249
|
+
"""
|
250
|
+
A lexer for `Ragel`_ in a D host file.
|
251
|
+
|
252
|
+
*New in Pygments 1.1.*
|
253
|
+
"""
|
254
|
+
|
255
|
+
name = 'Ragel in D Host'
|
256
|
+
aliases = ['ragel-d']
|
257
|
+
filenames = ['*.rl']
|
258
|
+
|
259
|
+
def __init__(self, **options):
|
260
|
+
super(RagelDLexer, self).__init__(DLexer, RagelEmbeddedLexer, **options)
|
261
|
+
|
262
|
+
def analyse_text(text):
|
263
|
+
return '@LANG: d' in text
|
264
|
+
|
265
|
+
|
266
|
+
class RagelCppLexer(DelegatingLexer):
|
267
|
+
"""
|
268
|
+
A lexer for `Ragel`_ in a CPP host file.
|
269
|
+
|
270
|
+
*New in Pygments 1.1.*
|
271
|
+
"""
|
272
|
+
|
273
|
+
name = 'Ragel in CPP Host'
|
274
|
+
aliases = ['ragel-cpp']
|
275
|
+
filenames = ['*.rl']
|
276
|
+
|
277
|
+
def __init__(self, **options):
|
278
|
+
super(RagelCppLexer, self).__init__(CppLexer, RagelEmbeddedLexer, **options)
|
279
|
+
|
280
|
+
def analyse_text(text):
|
281
|
+
return '@LANG: c++' in text
|
282
|
+
|
283
|
+
|
284
|
+
class RagelObjectiveCLexer(DelegatingLexer):
|
285
|
+
"""
|
286
|
+
A lexer for `Ragel`_ in an Objective C host file.
|
287
|
+
|
288
|
+
*New in Pygments 1.1.*
|
289
|
+
"""
|
290
|
+
|
291
|
+
name = 'Ragel in Objective C Host'
|
292
|
+
aliases = ['ragel-objc']
|
293
|
+
filenames = ['*.rl']
|
294
|
+
|
295
|
+
def __init__(self, **options):
|
296
|
+
super(RagelObjectiveCLexer, self).__init__(ObjectiveCLexer,
|
297
|
+
RagelEmbeddedLexer,
|
298
|
+
**options)
|
299
|
+
|
300
|
+
def analyse_text(text):
|
301
|
+
return '@LANG: objc' in text
|
302
|
+
|
303
|
+
|
304
|
+
class RagelJavaLexer(DelegatingLexer):
|
305
|
+
"""
|
306
|
+
A lexer for `Ragel`_ in a Java host file.
|
307
|
+
|
308
|
+
*New in Pygments 1.1.*
|
309
|
+
"""
|
310
|
+
|
311
|
+
name = 'Ragel in Java Host'
|
312
|
+
aliases = ['ragel-java']
|
313
|
+
filenames = ['*.rl']
|
314
|
+
|
315
|
+
def __init__(self, **options):
|
316
|
+
super(RagelJavaLexer, self).__init__(JavaLexer, RagelEmbeddedLexer,
|
317
|
+
**options)
|
318
|
+
|
319
|
+
def analyse_text(text):
|
320
|
+
return '@LANG: java' in text
|
321
|
+
|
322
|
+
|
323
|
+
class AntlrLexer(RegexLexer):
|
324
|
+
"""
|
325
|
+
Generic `ANTLR`_ Lexer.
|
326
|
+
Should not be called directly, instead
|
327
|
+
use DelegatingLexer for your target language.
|
328
|
+
|
329
|
+
*New in Pygments 1.1.*
|
330
|
+
|
331
|
+
.. _ANTLR: http://www.antlr.org/
|
332
|
+
"""
|
333
|
+
|
334
|
+
name = 'ANTLR'
|
335
|
+
aliases = ['antlr']
|
336
|
+
filenames = []
|
337
|
+
|
338
|
+
_id = r'[A-Za-z][A-Za-z_0-9]*'
|
339
|
+
_TOKEN_REF = r'[A-Z][A-Za-z_0-9]*'
|
340
|
+
_RULE_REF = r'[a-z][A-Za-z_0-9]*'
|
341
|
+
_STRING_LITERAL = r'\'(?:\\\\|\\\'|[^\']*)\''
|
342
|
+
_INT = r'[0-9]+'
|
343
|
+
|
344
|
+
tokens = {
|
345
|
+
'whitespace': [
|
346
|
+
(r'\s+', Whitespace),
|
347
|
+
],
|
348
|
+
'comments': [
|
349
|
+
(r'//.*$', Comment),
|
350
|
+
(r'/\*(.|\n)*?\*/', Comment),
|
351
|
+
],
|
352
|
+
'root': [
|
353
|
+
include('whitespace'),
|
354
|
+
include('comments'),
|
355
|
+
|
356
|
+
(r'(lexer|parser|tree)?(\s*)(grammar\b)(\s*)(' + _id + ')(;)',
|
357
|
+
bygroups(Keyword, Whitespace, Keyword, Whitespace, Name.Class,
|
358
|
+
Punctuation)),
|
359
|
+
# optionsSpec
|
360
|
+
(r'options\b', Keyword, 'options'),
|
361
|
+
# tokensSpec
|
362
|
+
(r'tokens\b', Keyword, 'tokens'),
|
363
|
+
# attrScope
|
364
|
+
(r'(scope)(\s*)(' + _id + ')(\s*)({)',
|
365
|
+
bygroups(Keyword, Whitespace, Name.Variable, Whitespace,
|
366
|
+
Punctuation), 'action'),
|
367
|
+
# exception
|
368
|
+
(r'(catch|finally)\b', Keyword, 'exception'),
|
369
|
+
# action
|
370
|
+
(r'(@' + _id + ')(\s*)(::)?(\s*)(' + _id + ')(\s*)({)',
|
371
|
+
bygroups(Name.Label, Whitespace, Punctuation, Whitespace,
|
372
|
+
Name.Label, Whitespace, Punctuation), 'action'),
|
373
|
+
# rule
|
374
|
+
(r'((?:protected|private|public|fragment)\b)?(\s*)(' + _id + ')(!)?', \
|
375
|
+
bygroups(Keyword, Whitespace, Name.Label, Punctuation),
|
376
|
+
('rule-alts', 'rule-prelims')),
|
377
|
+
],
|
378
|
+
'exception': [
|
379
|
+
(r'\n', Whitespace, '#pop'),
|
380
|
+
(r'\s', Whitespace),
|
381
|
+
include('comments'),
|
382
|
+
|
383
|
+
(r'\[', Punctuation, 'nested-arg-action'),
|
384
|
+
(r'\{', Punctuation, 'action'),
|
385
|
+
],
|
386
|
+
'rule-prelims': [
|
387
|
+
include('whitespace'),
|
388
|
+
include('comments'),
|
389
|
+
|
390
|
+
(r'returns\b', Keyword),
|
391
|
+
(r'\[', Punctuation, 'nested-arg-action'),
|
392
|
+
(r'\{', Punctuation, 'action'),
|
393
|
+
# throwsSpec
|
394
|
+
(r'(throws)(\s+)(' + _id + ')',
|
395
|
+
bygroups(Keyword, Whitespace, Name.Label)),
|
396
|
+
(r'(?:(,)(\s*)(' + _id + '))+',
|
397
|
+
bygroups(Punctuation, Whitespace, Name.Label)), # Additional throws
|
398
|
+
# optionsSpec
|
399
|
+
(r'options\b', Keyword, 'options'),
|
400
|
+
# ruleScopeSpec - scope followed by target language code or name of action
|
401
|
+
# TODO finish implementing other possibilities for scope
|
402
|
+
# L173 ANTLRv3.g from ANTLR book
|
403
|
+
(r'(scope)(\s+)({)', bygroups(Keyword, Whitespace, Punctuation),
|
404
|
+
'action'),
|
405
|
+
(r'(scope)(\s+)(' + _id + ')(\s*)(;)',
|
406
|
+
bygroups(Keyword, Whitespace, Name.Label, Whitespace, Punctuation)),
|
407
|
+
# ruleAction
|
408
|
+
(r'(@' + _id + ')(\s*)({)',
|
409
|
+
bygroups(Name.Label, Whitespace, Punctuation), 'action'),
|
410
|
+
# finished prelims, go to rule alts!
|
411
|
+
(r':', Punctuation, '#pop')
|
412
|
+
],
|
413
|
+
'rule-alts': [
|
414
|
+
include('whitespace'),
|
415
|
+
include('comments'),
|
416
|
+
|
417
|
+
# These might need to go in a separate 'block' state triggered by (
|
418
|
+
(r'options\b', Keyword, 'options'),
|
419
|
+
(r':', Punctuation),
|
420
|
+
|
421
|
+
# literals
|
422
|
+
(r"'(\\\\|\\'|[^'])*'", String),
|
423
|
+
(r'"(\\\\|\\"|[^"])*"', String),
|
424
|
+
(r'<<([^>]|>[^>])>>', String),
|
425
|
+
# identifiers
|
426
|
+
# Tokens start with capital letter.
|
427
|
+
(r'\$?[A-Z_][A-Za-z_0-9]*', Name.Constant),
|
428
|
+
# Rules start with small letter.
|
429
|
+
(r'\$?[a-z_][A-Za-z_0-9]*', Name.Variable),
|
430
|
+
# operators
|
431
|
+
(r'(\+|\||->|=>|=|\(|\)|\.\.|\.|\?|\*|\^|!|\#|~)', Operator),
|
432
|
+
(r',', Punctuation),
|
433
|
+
(r'\[', Punctuation, 'nested-arg-action'),
|
434
|
+
(r'\{', Punctuation, 'action'),
|
435
|
+
(r';', Punctuation, '#pop')
|
436
|
+
],
|
437
|
+
'tokens': [
|
438
|
+
include('whitespace'),
|
439
|
+
include('comments'),
|
440
|
+
(r'{', Punctuation),
|
441
|
+
(r'(' + _TOKEN_REF + r')(\s*)(=)?(\s*)(' + _STRING_LITERAL
|
442
|
+
+ ')?(\s*)(;)',
|
443
|
+
bygroups(Name.Label, Whitespace, Punctuation, Whitespace,
|
444
|
+
String, Whitespace, Punctuation)),
|
445
|
+
(r'}', Punctuation, '#pop'),
|
446
|
+
],
|
447
|
+
'options': [
|
448
|
+
include('whitespace'),
|
449
|
+
include('comments'),
|
450
|
+
(r'{', Punctuation),
|
451
|
+
(r'(' + _id + r')(\s*)(=)(\s*)(' +
|
452
|
+
'|'.join((_id, _STRING_LITERAL, _INT, '\*'))+ ')(\s*)(;)',
|
453
|
+
bygroups(Name.Variable, Whitespace, Punctuation, Whitespace,
|
454
|
+
Text, Whitespace, Punctuation)),
|
455
|
+
(r'}', Punctuation, '#pop'),
|
456
|
+
],
|
457
|
+
'action': [
|
458
|
+
(r'(' + r'|'.join(( # keep host code in largest possible chunks
|
459
|
+
r'[^\${}\'"/\\]+', # exclude unsafe characters
|
460
|
+
|
461
|
+
# strings and comments may safely contain unsafe characters
|
462
|
+
r'"(\\\\|\\"|[^"])*"', # double quote string
|
463
|
+
r"'(\\\\|\\'|[^'])*'", # single quote string
|
464
|
+
r'//.*$\n?', # single line comment
|
465
|
+
r'/\*(.|\n)*?\*/', # multi-line javadoc-style comment
|
466
|
+
|
467
|
+
# regular expression: There's no reason for it to start
|
468
|
+
# with a * and this stops confusion with comments.
|
469
|
+
r'/(?!\*)(\\\\|\\/|[^/])*/',
|
470
|
+
|
471
|
+
# backslashes are okay, as long as we are not backslashing a %
|
472
|
+
r'\\(?!%)',
|
473
|
+
|
474
|
+
# Now that we've handled regex and javadoc comments
|
475
|
+
# it's safe to let / through.
|
476
|
+
r'/',
|
477
|
+
)) + r')+', Other),
|
478
|
+
(r'(\\)(%)', bygroups(Punctuation, Other)),
|
479
|
+
(r'(\$[a-zA-Z]+)(\.?)(text|value)?',
|
480
|
+
bygroups(Name.Variable, Punctuation, Name.Property)),
|
481
|
+
(r'{', Punctuation, '#push'),
|
482
|
+
(r'}', Punctuation, '#pop'),
|
483
|
+
],
|
484
|
+
'nested-arg-action': [
|
485
|
+
(r'(' + r'|'.join(( # keep host code in largest possible chunks.
|
486
|
+
r'[^\$\[\]\'"/]+', # exclude unsafe characters
|
487
|
+
|
488
|
+
# strings and comments may safely contain unsafe characters
|
489
|
+
r'"(\\\\|\\"|[^"])*"', # double quote string
|
490
|
+
r"'(\\\\|\\'|[^'])*'", # single quote string
|
491
|
+
r'//.*$\n?', # single line comment
|
492
|
+
r'/\*(.|\n)*?\*/', # multi-line javadoc-style comment
|
493
|
+
|
494
|
+
# regular expression: There's no reason for it to start
|
495
|
+
# with a * and this stops confusion with comments.
|
496
|
+
r'/(?!\*)(\\\\|\\/|[^/])*/',
|
497
|
+
|
498
|
+
# Now that we've handled regex and javadoc comments
|
499
|
+
# it's safe to let / through.
|
500
|
+
r'/',
|
501
|
+
)) + r')+', Other),
|
502
|
+
|
503
|
+
|
504
|
+
(r'\[', Punctuation, '#push'),
|
505
|
+
(r'\]', Punctuation, '#pop'),
|
506
|
+
(r'(\$[a-zA-Z]+)(\.?)(text|value)?',
|
507
|
+
bygroups(Name.Variable, Punctuation, Name.Property)),
|
508
|
+
(r'(\\\\|\\\]|\\\[|[^\[\]])+', Other),
|
509
|
+
]
|
510
|
+
}
|
511
|
+
|
512
|
+
def analyse_text(text):
|
513
|
+
return re.search(r'^\s*grammar\s+[a-zA-Z0-9]+\s*;', text, re.M)
|
514
|
+
|
515
|
+
# http://www.antlr.org/wiki/display/ANTLR3/Code+Generation+Targets
|
516
|
+
|
517
|
+
# TH: I'm not aware of any language features of C++ that will cause
|
518
|
+
# incorrect lexing of C files. Antlr doesn't appear to make a distinction,
|
519
|
+
# so just assume they're C++. No idea how to make Objective C work in the
|
520
|
+
# future.
|
521
|
+
|
522
|
+
#class AntlrCLexer(DelegatingLexer):
|
523
|
+
# """
|
524
|
+
# ANTLR with C Target
|
525
|
+
#
|
526
|
+
# *New in Pygments 1.1*
|
527
|
+
# """
|
528
|
+
#
|
529
|
+
# name = 'ANTLR With C Target'
|
530
|
+
# aliases = ['antlr-c']
|
531
|
+
# filenames = ['*.G', '*.g']
|
532
|
+
#
|
533
|
+
# def __init__(self, **options):
|
534
|
+
# super(AntlrCLexer, self).__init__(CLexer, AntlrLexer, **options)
|
535
|
+
#
|
536
|
+
# def analyse_text(text):
|
537
|
+
# return re.match(r'^\s*language\s*=\s*C\s*;', text)
|
538
|
+
|
539
|
+
class AntlrCppLexer(DelegatingLexer):
|
540
|
+
"""
|
541
|
+
`ANTLR`_ with CPP Target
|
542
|
+
|
543
|
+
*New in Pygments 1.1.*
|
544
|
+
"""
|
545
|
+
|
546
|
+
name = 'ANTLR With CPP Target'
|
547
|
+
aliases = ['antlr-cpp']
|
548
|
+
filenames = ['*.G', '*.g']
|
549
|
+
|
550
|
+
def __init__(self, **options):
|
551
|
+
super(AntlrCppLexer, self).__init__(CppLexer, AntlrLexer, **options)
|
552
|
+
|
553
|
+
def analyse_text(text):
|
554
|
+
return AntlrLexer.analyse_text(text) and \
|
555
|
+
re.search(r'^\s*language\s*=\s*C\s*;', text, re.M)
|
556
|
+
|
557
|
+
|
558
|
+
class AntlrObjectiveCLexer(DelegatingLexer):
|
559
|
+
"""
|
560
|
+
`ANTLR`_ with Objective-C Target
|
561
|
+
|
562
|
+
*New in Pygments 1.1.*
|
563
|
+
"""
|
564
|
+
|
565
|
+
name = 'ANTLR With ObjectiveC Target'
|
566
|
+
aliases = ['antlr-objc']
|
567
|
+
filenames = ['*.G', '*.g']
|
568
|
+
|
569
|
+
def __init__(self, **options):
|
570
|
+
super(AntlrObjectiveCLexer, self).__init__(ObjectiveCLexer,
|
571
|
+
AntlrLexer, **options)
|
572
|
+
|
573
|
+
def analyse_text(text):
|
574
|
+
return AntlrLexer.analyse_text(text) and \
|
575
|
+
re.search(r'^\s*language\s*=\s*ObjC\s*;', text)
|
576
|
+
|
577
|
+
|
578
|
+
class AntlrCSharpLexer(DelegatingLexer):
|
579
|
+
"""
|
580
|
+
`ANTLR`_ with C# Target
|
581
|
+
|
582
|
+
*New in Pygments 1.1.*
|
583
|
+
"""
|
584
|
+
|
585
|
+
name = 'ANTLR With C# Target'
|
586
|
+
aliases = ['antlr-csharp', 'antlr-c#']
|
587
|
+
filenames = ['*.G', '*.g']
|
588
|
+
|
589
|
+
def __init__(self, **options):
|
590
|
+
super(AntlrCSharpLexer, self).__init__(CSharpLexer, AntlrLexer,
|
591
|
+
**options)
|
592
|
+
|
593
|
+
def analyse_text(text):
|
594
|
+
return AntlrLexer.analyse_text(text) and \
|
595
|
+
re.search(r'^\s*language\s*=\s*CSharp2\s*;', text, re.M)
|
596
|
+
|
597
|
+
|
598
|
+
class AntlrPythonLexer(DelegatingLexer):
|
599
|
+
"""
|
600
|
+
`ANTLR`_ with Python Target
|
601
|
+
|
602
|
+
*New in Pygments 1.1.*
|
603
|
+
"""
|
604
|
+
|
605
|
+
name = 'ANTLR With Python Target'
|
606
|
+
aliases = ['antlr-python']
|
607
|
+
filenames = ['*.G', '*.g']
|
608
|
+
|
609
|
+
def __init__(self, **options):
|
610
|
+
super(AntlrPythonLexer, self).__init__(PythonLexer, AntlrLexer,
|
611
|
+
**options)
|
612
|
+
|
613
|
+
def analyse_text(text):
|
614
|
+
return AntlrLexer.analyse_text(text) and \
|
615
|
+
re.search(r'^\s*language\s*=\s*Python\s*;', text, re.M)
|
616
|
+
|
617
|
+
|
618
|
+
class AntlrJavaLexer(DelegatingLexer):
|
619
|
+
"""
|
620
|
+
`ANTLR`_ with Java Target
|
621
|
+
|
622
|
+
*New in Pygments 1.1*
|
623
|
+
"""
|
624
|
+
|
625
|
+
name = 'ANTLR With Java Target'
|
626
|
+
aliases = ['antlr-java']
|
627
|
+
filenames = ['*.G', '*.g']
|
628
|
+
|
629
|
+
def __init__(self, **options):
|
630
|
+
super(AntlrJavaLexer, self).__init__(JavaLexer, AntlrLexer,
|
631
|
+
**options)
|
632
|
+
|
633
|
+
def analyse_text(text):
|
634
|
+
# Antlr language is Java by default
|
635
|
+
return AntlrLexer.analyse_text(text) and 0.9
|
636
|
+
|
637
|
+
|
638
|
+
class AntlrRubyLexer(DelegatingLexer):
|
639
|
+
"""
|
640
|
+
`ANTLR`_ with Ruby Target
|
641
|
+
|
642
|
+
*New in Pygments 1.1.*
|
643
|
+
"""
|
644
|
+
|
645
|
+
name = 'ANTLR With Ruby Target'
|
646
|
+
aliases = ['antlr-ruby', 'antlr-rb']
|
647
|
+
filenames = ['*.G', '*.g']
|
648
|
+
|
649
|
+
def __init__(self, **options):
|
650
|
+
super(AntlrRubyLexer, self).__init__(RubyLexer, AntlrLexer,
|
651
|
+
**options)
|
652
|
+
|
653
|
+
def analyse_text(text):
|
654
|
+
return AntlrLexer.analyse_text(text) and \
|
655
|
+
re.search(r'^\s*language\s*=\s*Ruby\s*;', text, re.M)
|
656
|
+
|
657
|
+
|
658
|
+
class AntlrPerlLexer(DelegatingLexer):
|
659
|
+
"""
|
660
|
+
`ANTLR`_ with Perl Target
|
661
|
+
|
662
|
+
*New in Pygments 1.1.*
|
663
|
+
"""
|
664
|
+
|
665
|
+
name = 'ANTLR With Perl Target'
|
666
|
+
aliases = ['antlr-perl']
|
667
|
+
filenames = ['*.G', '*.g']
|
668
|
+
|
669
|
+
def __init__(self, **options):
|
670
|
+
super(AntlrPerlLexer, self).__init__(PerlLexer, AntlrLexer,
|
671
|
+
**options)
|
672
|
+
|
673
|
+
def analyse_text(text):
|
674
|
+
return AntlrLexer.analyse_text(text) and \
|
675
|
+
re.search(r'^\s*language\s*=\s*Perl5\s*;', text, re.M)
|
676
|
+
|
677
|
+
|
678
|
+
class AntlrActionScriptLexer(DelegatingLexer):
|
679
|
+
"""
|
680
|
+
`ANTLR`_ with ActionScript Target
|
681
|
+
|
682
|
+
*New in Pygments 1.1.*
|
683
|
+
"""
|
684
|
+
|
685
|
+
name = 'ANTLR With ActionScript Target'
|
686
|
+
aliases = ['antlr-as', 'antlr-actionscript']
|
687
|
+
filenames = ['*.G', '*.g']
|
688
|
+
|
689
|
+
def __init__(self, **options):
|
690
|
+
super(AntlrActionScriptLexer, self).__init__(ActionScriptLexer,
|
691
|
+
AntlrLexer, **options)
|
692
|
+
|
693
|
+
def analyse_text(text):
|
694
|
+
return AntlrLexer.analyse_text(text) and \
|
695
|
+
re.search(r'^\s*language\s*=\s*ActionScript\s*;', text, re.M)
|