pygmentize 0.0.1

Sign up to get free protection for your applications and to get access to all the features.
Files changed (101) hide show
  1. data/LICENSE +19 -0
  2. data/lib/pygments.rb +23 -0
  3. data/pygmentize.gemspec +11 -0
  4. data/test/pygments.rb +19 -0
  5. data/vendor/pygmentize.py +7 -0
  6. data/vendor/pygments/AUTHORS +73 -0
  7. data/vendor/pygments/LICENSE +25 -0
  8. data/vendor/pygments/__init__.py +91 -0
  9. data/vendor/pygments/__init__.pyc +0 -0
  10. data/vendor/pygments/cmdline.py +430 -0
  11. data/vendor/pygments/cmdline.pyc +0 -0
  12. data/vendor/pygments/console.py +74 -0
  13. data/vendor/pygments/console.pyc +0 -0
  14. data/vendor/pygments/filter.py +74 -0
  15. data/vendor/pygments/filter.pyc +0 -0
  16. data/vendor/pygments/filters/__init__.py +357 -0
  17. data/vendor/pygments/filters/__init__.pyc +0 -0
  18. data/vendor/pygments/formatter.py +92 -0
  19. data/vendor/pygments/formatter.pyc +0 -0
  20. data/vendor/pygments/formatters/__init__.py +68 -0
  21. data/vendor/pygments/formatters/__init__.pyc +0 -0
  22. data/vendor/pygments/formatters/_mapping.py +92 -0
  23. data/vendor/pygments/formatters/_mapping.pyc +0 -0
  24. data/vendor/pygments/formatters/bbcode.py +109 -0
  25. data/vendor/pygments/formatters/bbcode.pyc +0 -0
  26. data/vendor/pygments/formatters/html.py +723 -0
  27. data/vendor/pygments/formatters/html.pyc +0 -0
  28. data/vendor/pygments/formatters/img.py +553 -0
  29. data/vendor/pygments/formatters/img.pyc +0 -0
  30. data/vendor/pygments/formatters/latex.py +354 -0
  31. data/vendor/pygments/formatters/latex.pyc +0 -0
  32. data/vendor/pygments/formatters/other.py +117 -0
  33. data/vendor/pygments/formatters/other.pyc +0 -0
  34. data/vendor/pygments/formatters/rtf.py +136 -0
  35. data/vendor/pygments/formatters/rtf.pyc +0 -0
  36. data/vendor/pygments/formatters/svg.py +154 -0
  37. data/vendor/pygments/formatters/svg.pyc +0 -0
  38. data/vendor/pygments/formatters/terminal.py +109 -0
  39. data/vendor/pygments/formatters/terminal.pyc +0 -0
  40. data/vendor/pygments/formatters/terminal256.py +219 -0
  41. data/vendor/pygments/formatters/terminal256.pyc +0 -0
  42. data/vendor/pygments/lexer.py +660 -0
  43. data/vendor/pygments/lexer.pyc +0 -0
  44. data/vendor/pygments/lexers/__init__.py +226 -0
  45. data/vendor/pygments/lexers/__init__.pyc +0 -0
  46. data/vendor/pygments/lexers/_asybuiltins.py +1645 -0
  47. data/vendor/pygments/lexers/_clbuiltins.py +232 -0
  48. data/vendor/pygments/lexers/_luabuiltins.py +256 -0
  49. data/vendor/pygments/lexers/_mapping.py +234 -0
  50. data/vendor/pygments/lexers/_mapping.pyc +0 -0
  51. data/vendor/pygments/lexers/_phpbuiltins.py +3389 -0
  52. data/vendor/pygments/lexers/_vimbuiltins.py +3 -0
  53. data/vendor/pygments/lexers/agile.py +1485 -0
  54. data/vendor/pygments/lexers/agile.pyc +0 -0
  55. data/vendor/pygments/lexers/asm.py +353 -0
  56. data/vendor/pygments/lexers/compiled.py +2365 -0
  57. data/vendor/pygments/lexers/dotnet.py +355 -0
  58. data/vendor/pygments/lexers/functional.py +756 -0
  59. data/vendor/pygments/lexers/functional.pyc +0 -0
  60. data/vendor/pygments/lexers/math.py +461 -0
  61. data/vendor/pygments/lexers/other.py +2297 -0
  62. data/vendor/pygments/lexers/parsers.py +695 -0
  63. data/vendor/pygments/lexers/special.py +100 -0
  64. data/vendor/pygments/lexers/special.pyc +0 -0
  65. data/vendor/pygments/lexers/templates.py +1387 -0
  66. data/vendor/pygments/lexers/text.py +1586 -0
  67. data/vendor/pygments/lexers/web.py +1619 -0
  68. data/vendor/pygments/lexers/web.pyc +0 -0
  69. data/vendor/pygments/plugin.py +74 -0
  70. data/vendor/pygments/plugin.pyc +0 -0
  71. data/vendor/pygments/scanner.py +104 -0
  72. data/vendor/pygments/style.py +117 -0
  73. data/vendor/pygments/style.pyc +0 -0
  74. data/vendor/pygments/styles/__init__.py +68 -0
  75. data/vendor/pygments/styles/__init__.pyc +0 -0
  76. data/vendor/pygments/styles/autumn.py +65 -0
  77. data/vendor/pygments/styles/borland.py +51 -0
  78. data/vendor/pygments/styles/bw.py +49 -0
  79. data/vendor/pygments/styles/colorful.py +81 -0
  80. data/vendor/pygments/styles/default.py +73 -0
  81. data/vendor/pygments/styles/default.pyc +0 -0
  82. data/vendor/pygments/styles/emacs.py +72 -0
  83. data/vendor/pygments/styles/friendly.py +72 -0
  84. data/vendor/pygments/styles/fruity.py +43 -0
  85. data/vendor/pygments/styles/manni.py +75 -0
  86. data/vendor/pygments/styles/monokai.py +106 -0
  87. data/vendor/pygments/styles/murphy.py +80 -0
  88. data/vendor/pygments/styles/native.py +65 -0
  89. data/vendor/pygments/styles/pastie.py +75 -0
  90. data/vendor/pygments/styles/perldoc.py +69 -0
  91. data/vendor/pygments/styles/tango.py +141 -0
  92. data/vendor/pygments/styles/trac.py +63 -0
  93. data/vendor/pygments/styles/vim.py +63 -0
  94. data/vendor/pygments/styles/vs.py +38 -0
  95. data/vendor/pygments/token.py +198 -0
  96. data/vendor/pygments/token.pyc +0 -0
  97. data/vendor/pygments/unistring.py +130 -0
  98. data/vendor/pygments/unistring.pyc +0 -0
  99. data/vendor/pygments/util.py +226 -0
  100. data/vendor/pygments/util.pyc +0 -0
  101. metadata +166 -0
@@ -0,0 +1,355 @@
1
+ # -*- coding: utf-8 -*-
2
+ """
3
+ pygments.lexers.dotnet
4
+ ~~~~~~~~~~~~~~~~~~~~~~
5
+
6
+ Lexers for .net languages.
7
+
8
+ :copyright: Copyright 2006-2010 by the Pygments team, see AUTHORS.
9
+ :license: BSD, see LICENSE for details.
10
+ """
11
+ import re
12
+
13
+ from pygments.lexer import RegexLexer, DelegatingLexer, bygroups, using, this
14
+ from pygments.token import Punctuation, \
15
+ Text, Comment, Operator, Keyword, Name, String, Number, Literal, Other
16
+ from pygments.util import get_choice_opt
17
+ from pygments import unistring as uni
18
+
19
+ from pygments.lexers.web import XmlLexer
20
+
21
+ __all__ = ['CSharpLexer', 'BooLexer', 'VbNetLexer', 'CSharpAspxLexer',
22
+ 'VbNetAspxLexer']
23
+
24
+
25
+ def _escape(st):
26
+ return st.replace(u'\\', ur'\\').replace(u'-', ur'\-').\
27
+ replace(u'[', ur'\[').replace(u']', ur'\]')
28
+
29
+ class CSharpLexer(RegexLexer):
30
+ """
31
+ For `C# <http://msdn2.microsoft.com/en-us/vcsharp/default.aspx>`_
32
+ source code.
33
+
34
+ Additional options accepted:
35
+
36
+ `unicodelevel`
37
+ Determines which Unicode characters this lexer allows for identifiers.
38
+ The possible values are:
39
+
40
+ * ``none`` -- only the ASCII letters and numbers are allowed. This
41
+ is the fastest selection.
42
+ * ``basic`` -- all Unicode characters from the specification except
43
+ category ``Lo`` are allowed.
44
+ * ``full`` -- all Unicode characters as specified in the C# specs
45
+ are allowed. Note that this means a considerable slowdown since the
46
+ ``Lo`` category has more than 40,000 characters in it!
47
+
48
+ The default value is ``basic``.
49
+
50
+ *New in Pygments 0.8.*
51
+ """
52
+
53
+ name = 'C#'
54
+ aliases = ['csharp', 'c#']
55
+ filenames = ['*.cs']
56
+ mimetypes = ['text/x-csharp'] # inferred
57
+
58
+ flags = re.MULTILINE | re.DOTALL | re.UNICODE
59
+
60
+ # for the range of allowed unicode characters in identifiers,
61
+ # see http://www.ecma-international.org/publications/files/ECMA-ST/Ecma-334.pdf
62
+
63
+ levels = {
64
+ 'none': '@?[_a-zA-Z][a-zA-Z0-9_]*',
65
+ 'basic': ('@?[_' + uni.Lu + uni.Ll + uni.Lt + uni.Lm + uni.Nl + ']' +
66
+ '[' + uni.Lu + uni.Ll + uni.Lt + uni.Lm + uni.Nl +
67
+ uni.Nd + uni.Pc + uni.Cf + uni.Mn + uni.Mc + ']*'),
68
+ 'full': ('@?(?:_|[^' +
69
+ _escape(uni.allexcept('Lu', 'Ll', 'Lt', 'Lm', 'Lo', 'Nl')) + '])'
70
+ + '[^' + _escape(uni.allexcept('Lu', 'Ll', 'Lt', 'Lm', 'Lo',
71
+ 'Nl', 'Nd', 'Pc', 'Cf', 'Mn',
72
+ 'Mc')) + ']*'),
73
+ }
74
+
75
+ tokens = {}
76
+ token_variants = True
77
+
78
+ for levelname, cs_ident in levels.items():
79
+ tokens[levelname] = {
80
+ 'root': [
81
+ # method names
82
+ (r'^([ \t]*(?:' + cs_ident + r'(?:\[\])?\s+)+?)' # return type
83
+ r'(' + cs_ident + ')' # method name
84
+ r'(\s*)(\()', # signature start
85
+ bygroups(using(this), Name.Function, Text, Punctuation)),
86
+ (r'^\s*\[.*?\]', Name.Attribute),
87
+ (r'[^\S\n]+', Text),
88
+ (r'\\\n', Text), # line continuation
89
+ (r'//.*?\n', Comment.Single),
90
+ (r'/[*](.|\n)*?[*]/', Comment.Multiline),
91
+ (r'\n', Text),
92
+ (r'[~!%^&*()+=|\[\]:;,.<>/?-]', Punctuation),
93
+ (r'[{}]', Punctuation),
94
+ (r'@"(\\\\|\\"|[^"])*"', String),
95
+ (r'"(\\\\|\\"|[^"\n])*["\n]', String),
96
+ (r"'\\.'|'[^\\]'", String.Char),
97
+ (r"[0-9](\.[0-9]*)?([eE][+-][0-9]+)?"
98
+ r"[flFLdD]?|0[xX][0-9a-fA-F]+[Ll]?", Number),
99
+ (r'#[ \t]*(if|endif|else|elif|define|undef|'
100
+ r'line|error|warning|region|endregion|pragma)\b.*?\n',
101
+ Comment.Preproc),
102
+ (r'\b(extern)(\s+)(alias)\b', bygroups(Keyword, Text,
103
+ Keyword)),
104
+ (r'(abstract|as|base|break|case|catch|'
105
+ r'checked|const|continue|default|delegate|'
106
+ r'do|else|enum|event|explicit|extern|false|finally|'
107
+ r'fixed|for|foreach|goto|if|implicit|in|interface|'
108
+ r'internal|is|lock|new|null|operator|'
109
+ r'out|override|params|private|protected|public|readonly|'
110
+ r'ref|return|sealed|sizeof|stackalloc|static|'
111
+ r'switch|this|throw|true|try|typeof|'
112
+ r'unchecked|unsafe|virtual|void|while|'
113
+ r'get|set|new|partial|yield|add|remove|value)\b', Keyword),
114
+ (r'(global)(::)', bygroups(Keyword, Punctuation)),
115
+ (r'(bool|byte|char|decimal|double|float|int|long|object|sbyte|'
116
+ r'short|string|uint|ulong|ushort)\b\??', Keyword.Type),
117
+ (r'(class|struct)(\s+)', bygroups(Keyword, Text), 'class'),
118
+ (r'(namespace|using)(\s+)', bygroups(Keyword, Text), 'namespace'),
119
+ (cs_ident, Name),
120
+ ],
121
+ 'class': [
122
+ (cs_ident, Name.Class, '#pop')
123
+ ],
124
+ 'namespace': [
125
+ (r'(?=\()', Text, '#pop'), # using (resource)
126
+ ('(' + cs_ident + r'|\.)+', Name.Namespace, '#pop')
127
+ ]
128
+ }
129
+
130
+ def __init__(self, **options):
131
+ level = get_choice_opt(options, 'unicodelevel', self.tokens.keys(), 'basic')
132
+ if level not in self._all_tokens:
133
+ # compile the regexes now
134
+ self._tokens = self.__class__.process_tokendef(level)
135
+ else:
136
+ self._tokens = self._all_tokens[level]
137
+
138
+ RegexLexer.__init__(self, **options)
139
+
140
+
141
+ class BooLexer(RegexLexer):
142
+ """
143
+ For `Boo <http://boo.codehaus.org/>`_ source code.
144
+ """
145
+
146
+ name = 'Boo'
147
+ aliases = ['boo']
148
+ filenames = ['*.boo']
149
+ mimetypes = ['text/x-boo']
150
+
151
+ tokens = {
152
+ 'root': [
153
+ (r'\s+', Text),
154
+ (r'(#|//).*$', Comment.Single),
155
+ (r'/[*]', Comment.Multiline, 'comment'),
156
+ (r'[]{}:(),.;[]', Punctuation),
157
+ (r'\\\n', Text),
158
+ (r'\\', Text),
159
+ (r'(in|is|and|or|not)\b', Operator.Word),
160
+ (r'/(\\\\|\\/|[^/\s])/', String.Regex),
161
+ (r'@/(\\\\|\\/|[^/])*/', String.Regex),
162
+ (r'=~|!=|==|<<|>>|[-+/*%=<>&^|]', Operator),
163
+ (r'(as|abstract|callable|constructor|destructor|do|import|'
164
+ r'enum|event|final|get|interface|internal|of|override|'
165
+ r'partial|private|protected|public|return|set|static|'
166
+ r'struct|transient|virtual|yield|super|and|break|cast|'
167
+ r'continue|elif|else|ensure|except|for|given|goto|if|in|'
168
+ r'is|isa|not|or|otherwise|pass|raise|ref|try|unless|when|'
169
+ r'while|from|as)\b', Keyword),
170
+ (r'def(?=\s+\(.*?\))', Keyword),
171
+ (r'(def)(\s+)', bygroups(Keyword, Text), 'funcname'),
172
+ (r'(class)(\s+)', bygroups(Keyword, Text), 'classname'),
173
+ (r'(namespace)(\s+)', bygroups(Keyword, Text), 'namespace'),
174
+ (r'(?<!\.)(true|false|null|self|__eval__|__switch__|array|'
175
+ r'assert|checked|enumerate|filter|getter|len|lock|map|'
176
+ r'matrix|max|min|normalArrayIndexing|print|property|range|'
177
+ r'rawArrayIndexing|required|typeof|unchecked|using|'
178
+ r'yieldAll|zip)\b', Name.Builtin),
179
+ ('"""(\\\\|\\"|.*?)"""', String.Double),
180
+ ('"(\\\\|\\"|[^"]*?)"', String.Double),
181
+ ("'(\\\\|\\'|[^']*?)'", String.Single),
182
+ ('[a-zA-Z_][a-zA-Z0-9_]*', Name),
183
+ (r'(\d+\.\d*|\d*\.\d+)([fF][+-]?[0-9]+)?', Number.Float),
184
+ (r'[0-9][0-9\.]*(m|ms|d|h|s)', Number),
185
+ (r'0\d+', Number.Oct),
186
+ (r'0x[a-fA-F0-9]+', Number.Hex),
187
+ (r'\d+L', Number.Integer.Long),
188
+ (r'\d+', Number.Integer),
189
+ ],
190
+ 'comment': [
191
+ ('/[*]', Comment.Multiline, '#push'),
192
+ ('[*]/', Comment.Multiline, '#pop'),
193
+ ('[^/*]', Comment.Multiline),
194
+ ('[*/]', Comment.Multiline)
195
+ ],
196
+ 'funcname': [
197
+ ('[a-zA-Z_][a-zA-Z0-9_]*', Name.Function, '#pop')
198
+ ],
199
+ 'classname': [
200
+ ('[a-zA-Z_][a-zA-Z0-9_]*', Name.Class, '#pop')
201
+ ],
202
+ 'namespace': [
203
+ ('[a-zA-Z_][a-zA-Z0-9_.]*', Name.Namespace, '#pop')
204
+ ]
205
+ }
206
+
207
+
208
+ class VbNetLexer(RegexLexer):
209
+ """
210
+ For
211
+ `Visual Basic.NET <http://msdn2.microsoft.com/en-us/vbasic/default.aspx>`_
212
+ source code.
213
+ """
214
+
215
+ name = 'VB.net'
216
+ aliases = ['vb.net', 'vbnet']
217
+ filenames = ['*.vb', '*.bas']
218
+ mimetypes = ['text/x-vbnet', 'text/x-vba'] # (?)
219
+
220
+ flags = re.MULTILINE | re.IGNORECASE
221
+ tokens = {
222
+ 'root': [
223
+ (r'^\s*<.*?>', Name.Attribute),
224
+ (r'\s+', Text),
225
+ (r'\n', Text),
226
+ (r'rem\b.*?\n', Comment),
227
+ (r"'.*?\n", Comment),
228
+ (r'#If\s.*?\sThen|#ElseIf\s.*?\sThen|#End\s+If|#Const|'
229
+ r'#ExternalSource.*?\n|#End\s+ExternalSource|'
230
+ r'#Region.*?\n|#End\s+Region|#ExternalChecksum',
231
+ Comment.Preproc),
232
+ (r'[\(\){}!#,.:]', Punctuation),
233
+ (r'Option\s+(Strict|Explicit|Compare)\s+'
234
+ r'(On|Off|Binary|Text)', Keyword.Declaration),
235
+ (r'(?<!\.)(AddHandler|Alias|'
236
+ r'ByRef|ByVal|Call|Case|Catch|CBool|CByte|CChar|CDate|'
237
+ r'CDec|CDbl|CInt|CLng|CObj|Const|Continue|CSByte|CShort|'
238
+ r'CSng|CStr|CType|CUInt|CULng|CUShort|Declare|'
239
+ r'Default|Delegate|Dim|DirectCast|Do|Each|Else|ElseIf|'
240
+ r'End|EndIf|Enum|Erase|Error|Event|Exit|False|Finally|For|'
241
+ r'Friend|Function|Get|Global|GoSub|GoTo|Handles|If|'
242
+ r'Implements|Imports|Inherits|Interface|'
243
+ r'Let|Lib|Loop|Me|Module|MustInherit|'
244
+ r'MustOverride|MyBase|MyClass|Namespace|Narrowing|New|Next|'
245
+ r'Not|Nothing|NotInheritable|NotOverridable|Of|On|'
246
+ r'Operator|Option|Optional|Overloads|Overridable|'
247
+ r'Overrides|ParamArray|Partial|Private|Property|Protected|'
248
+ r'Public|RaiseEvent|ReadOnly|ReDim|RemoveHandler|Resume|'
249
+ r'Return|Select|Set|Shadows|Shared|Single|'
250
+ r'Static|Step|Stop|Structure|Sub|SyncLock|Then|'
251
+ r'Throw|To|True|Try|TryCast|Wend|'
252
+ r'Using|When|While|Widening|With|WithEvents|'
253
+ r'WriteOnly)\b', Keyword),
254
+ (r'(?<!\.)(Function|Sub|Property)(\s+)',
255
+ bygroups(Keyword, Text), 'funcname'),
256
+ (r'(?<!\.)(Class|Structure|Enum)(\s+)',
257
+ bygroups(Keyword, Text), 'classname'),
258
+ (r'(?<!\.)(Namespace|Imports)(\s+)',
259
+ bygroups(Keyword, Text), 'namespace'),
260
+ (r'(?<!\.)(Boolean|Byte|Char|Date|Decimal|Double|Integer|Long|'
261
+ r'Object|SByte|Short|Single|String|Variant|UInteger|ULong|'
262
+ r'UShort)\b', Keyword.Type),
263
+ (r'(?<!\.)(AddressOf|And|AndAlso|As|GetType|In|Is|IsNot|Like|Mod|'
264
+ r'Or|OrElse|TypeOf|Xor)\b', Operator.Word),
265
+ (r'&=|[*]=|/=|\\=|\^=|\+=|-=|<<=|>>=|<<|>>|:=|'
266
+ r'<=|>=|<>|[-&*/\\^+=<>]',
267
+ Operator),
268
+ ('"', String, 'string'),
269
+ ('[a-zA-Z_][a-zA-Z0-9_]*[%&@!#$]?', Name),
270
+ ('#.*?#', Literal.Date),
271
+ (r'(\d+\.\d*|\d*\.\d+)([fF][+-]?[0-9]+)?', Number.Float),
272
+ (r'\d+([SILDFR]|US|UI|UL)?', Number.Integer),
273
+ (r'&H[0-9a-f]+([SILDFR]|US|UI|UL)?', Number.Integer),
274
+ (r'&O[0-7]+([SILDFR]|US|UI|UL)?', Number.Integer),
275
+ (r'_\n', Text), # Line continuation
276
+ ],
277
+ 'string': [
278
+ (r'""', String),
279
+ (r'"C?', String, '#pop'),
280
+ (r'[^"]+', String),
281
+ ],
282
+ 'funcname': [
283
+ (r'[a-z_][a-z0-9_]*', Name.Function, '#pop')
284
+ ],
285
+ 'classname': [
286
+ (r'[a-z_][a-z0-9_]*', Name.Class, '#pop')
287
+ ],
288
+ 'namespace': [
289
+ (r'[a-z_][a-z0-9_.]*', Name.Namespace, '#pop')
290
+ ],
291
+ }
292
+
293
+ class GenericAspxLexer(RegexLexer):
294
+ """
295
+ Lexer for ASP.NET pages.
296
+ """
297
+
298
+ name = 'aspx-gen'
299
+ filenames = []
300
+ mimetypes = []
301
+
302
+ flags = re.DOTALL
303
+
304
+ tokens = {
305
+ 'root': [
306
+ (r'(<%[@=#]?)(.*?)(%>)', bygroups(Name.Tag, Other, Name.Tag)),
307
+ (r'(<script.*?>)(.*?)(</script>)', bygroups(using(XmlLexer),
308
+ Other,
309
+ using(XmlLexer))),
310
+ (r'(.+?)(?=<)', using(XmlLexer)),
311
+ (r'.+', using(XmlLexer)),
312
+ ],
313
+ }
314
+
315
+ #TODO support multiple languages within the same source file
316
+ class CSharpAspxLexer(DelegatingLexer):
317
+ """
318
+ Lexer for highligting C# within ASP.NET pages.
319
+ """
320
+
321
+ name = 'aspx-cs'
322
+ aliases = ['aspx-cs']
323
+ filenames = ['*.aspx', '*.asax', '*.ascx', '*.ashx', '*.asmx', '*.axd']
324
+ mimetypes = []
325
+
326
+ def __init__(self, **options):
327
+ super(CSharpAspxLexer, self).__init__(CSharpLexer,GenericAspxLexer,
328
+ **options)
329
+
330
+ def analyse_text(text):
331
+ if re.search(r'Page\s*Language="C#"', text, re.I) is not None:
332
+ return 0.2
333
+ elif re.search(r'script[^>]+language=["\']C#', text, re.I) is not None:
334
+ return 0.15
335
+ return 0.001 # TODO really only for when filename matched...
336
+
337
+ class VbNetAspxLexer(DelegatingLexer):
338
+ """
339
+ Lexer for highligting Visual Basic.net within ASP.NET pages.
340
+ """
341
+
342
+ name = 'aspx-vb'
343
+ aliases = ['aspx-vb']
344
+ filenames = ['*.aspx', '*.asax', '*.ascx', '*.ashx', '*.asmx', '*.axd']
345
+ mimetypes = []
346
+
347
+ def __init__(self, **options):
348
+ super(VbNetAspxLexer, self).__init__(VbNetLexer,GenericAspxLexer,
349
+ **options)
350
+
351
+ def analyse_text(text):
352
+ if re.search(r'Page\s*Language="Vb"', text, re.I) is not None:
353
+ return 0.2
354
+ elif re.search(r'script[^>]+language=["\']vb', text, re.I) is not None:
355
+ return 0.15
@@ -0,0 +1,756 @@
1
+ # -*- coding: utf-8 -*-
2
+ """
3
+ pygments.lexers.functional
4
+ ~~~~~~~~~~~~~~~~~~~~~~~~~~
5
+
6
+ Lexers for functional languages.
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 Lexer, RegexLexer, bygroups, include, do_insertions
15
+ from pygments.token import Text, Comment, Operator, Keyword, Name, \
16
+ String, Number, Punctuation, Literal, Generic
17
+
18
+
19
+ __all__ = ['SchemeLexer', 'CommonLispLexer', 'HaskellLexer', 'LiterateHaskellLexer',
20
+ 'OcamlLexer', 'ErlangLexer', 'ErlangShellLexer']
21
+
22
+
23
+ class SchemeLexer(RegexLexer):
24
+ """
25
+ A Scheme lexer, parsing a stream and outputting the tokens
26
+ needed to highlight scheme code.
27
+ This lexer could be most probably easily subclassed to parse
28
+ other LISP-Dialects like Common Lisp, Emacs Lisp or AutoLisp.
29
+
30
+ This parser is checked with pastes from the LISP pastebin
31
+ at http://paste.lisp.org/ to cover as much syntax as possible.
32
+
33
+ It supports the full Scheme syntax as defined in R5RS.
34
+
35
+ *New in Pygments 0.6.*
36
+ """
37
+ name = 'Scheme'
38
+ aliases = ['scheme', 'scm']
39
+ filenames = ['*.scm']
40
+ mimetypes = ['text/x-scheme', 'application/x-scheme']
41
+
42
+ # list of known keywords and builtins taken form vim 6.4 scheme.vim
43
+ # syntax file.
44
+ keywords = [
45
+ 'lambda', 'define', 'if', 'else', 'cond', 'and', 'or', 'case', 'let',
46
+ 'let*', 'letrec', 'begin', 'do', 'delay', 'set!', '=>', 'quote',
47
+ 'quasiquote', 'unquote', 'unquote-splicing', 'define-syntax',
48
+ 'let-syntax', 'letrec-syntax', 'syntax-rules'
49
+ ]
50
+ builtins = [
51
+ '*', '+', '-', '/', '<', '<=', '=', '>', '>=', 'abs', 'acos', 'angle',
52
+ 'append', 'apply', 'asin', 'assoc', 'assq', 'assv', 'atan',
53
+ 'boolean?', 'caaaar', 'caaadr', 'caaar', 'caadar', 'caaddr', 'caadr',
54
+ 'caar', 'cadaar', 'cadadr', 'cadar', 'caddar', 'cadddr', 'caddr',
55
+ 'cadr', 'call-with-current-continuation', 'call-with-input-file',
56
+ 'call-with-output-file', 'call-with-values', 'call/cc', 'car',
57
+ 'cdaaar', 'cdaadr', 'cdaar', 'cdadar', 'cdaddr', 'cdadr', 'cdar',
58
+ 'cddaar', 'cddadr', 'cddar', 'cdddar', 'cddddr', 'cdddr', 'cddr',
59
+ 'cdr', 'ceiling', 'char->integer', 'char-alphabetic?', 'char-ci<=?',
60
+ 'char-ci<?', 'char-ci=?', 'char-ci>=?', 'char-ci>?', 'char-downcase',
61
+ 'char-lower-case?', 'char-numeric?', 'char-ready?', 'char-upcase',
62
+ 'char-upper-case?', 'char-whitespace?', 'char<=?', 'char<?', 'char=?',
63
+ 'char>=?', 'char>?', 'char?', 'close-input-port', 'close-output-port',
64
+ 'complex?', 'cons', 'cos', 'current-input-port', 'current-output-port',
65
+ 'denominator', 'display', 'dynamic-wind', 'eof-object?', 'eq?',
66
+ 'equal?', 'eqv?', 'eval', 'even?', 'exact->inexact', 'exact?', 'exp',
67
+ 'expt', 'floor', 'for-each', 'force', 'gcd', 'imag-part',
68
+ 'inexact->exact', 'inexact?', 'input-port?', 'integer->char',
69
+ 'integer?', 'interaction-environment', 'lcm', 'length', 'list',
70
+ 'list->string', 'list->vector', 'list-ref', 'list-tail', 'list?',
71
+ 'load', 'log', 'magnitude', 'make-polar', 'make-rectangular',
72
+ 'make-string', 'make-vector', 'map', 'max', 'member', 'memq', 'memv',
73
+ 'min', 'modulo', 'negative?', 'newline', 'not', 'null-environment',
74
+ 'null?', 'number->string', 'number?', 'numerator', 'odd?',
75
+ 'open-input-file', 'open-output-file', 'output-port?', 'pair?',
76
+ 'peek-char', 'port?', 'positive?', 'procedure?', 'quotient',
77
+ 'rational?', 'rationalize', 'read', 'read-char', 'real-part', 'real?',
78
+ 'remainder', 'reverse', 'round', 'scheme-report-environment',
79
+ 'set-car!', 'set-cdr!', 'sin', 'sqrt', 'string', 'string->list',
80
+ 'string->number', 'string->symbol', 'string-append', 'string-ci<=?',
81
+ 'string-ci<?', 'string-ci=?', 'string-ci>=?', 'string-ci>?',
82
+ 'string-copy', 'string-fill!', 'string-length', 'string-ref',
83
+ 'string-set!', 'string<=?', 'string<?', 'string=?', 'string>=?',
84
+ 'string>?', 'string?', 'substring', 'symbol->string', 'symbol?',
85
+ 'tan', 'transcript-off', 'transcript-on', 'truncate', 'values',
86
+ 'vector', 'vector->list', 'vector-fill!', 'vector-length',
87
+ 'vector-ref', 'vector-set!', 'vector?', 'with-input-from-file',
88
+ 'with-output-to-file', 'write', 'write-char', 'zero?'
89
+ ]
90
+
91
+ # valid names for identifiers
92
+ # well, names can only not consist fully of numbers
93
+ # but this should be good enough for now
94
+ valid_name = r'[a-zA-Z0-9!$%&*+,/:<=>?@^_~|-]+'
95
+
96
+ tokens = {
97
+ 'root' : [
98
+ # the comments - always starting with semicolon
99
+ # and going to the end of the line
100
+ (r';.*$', Comment.Single),
101
+
102
+ # whitespaces - usually not relevant
103
+ (r'\s+', Text),
104
+
105
+ # numbers
106
+ (r'-?\d+\.\d+', Number.Float),
107
+ (r'-?\d+', Number.Integer),
108
+ # support for uncommon kinds of numbers -
109
+ # have to figure out what the characters mean
110
+ #(r'(#e|#i|#b|#o|#d|#x)[\d.]+', Number),
111
+
112
+ # strings, symbols and characters
113
+ (r'"(\\\\|\\"|[^"])*"', String),
114
+ (r"'" + valid_name, String.Symbol),
115
+ (r"#\\([()/'\".'_!§$%& ?=+-]{1}|[a-zA-Z0-9]+)", String.Char),
116
+
117
+ # constants
118
+ (r'(#t|#f)', Name.Constant),
119
+
120
+ # special operators
121
+ (r"('|#|`|,@|,|\.)", Operator),
122
+
123
+ # highlight the keywords
124
+ ('(%s)' % '|'.join([
125
+ re.escape(entry) + ' ' for entry in keywords]),
126
+ Keyword
127
+ ),
128
+
129
+ # first variable in a quoted string like
130
+ # '(this is syntactic sugar)
131
+ (r"(?<='\()" + valid_name, Name.Variable),
132
+ (r"(?<=#\()" + valid_name, Name.Variable),
133
+
134
+ # highlight the builtins
135
+ ("(?<=\()(%s)" % '|'.join([
136
+ re.escape(entry) + ' ' for entry in builtins]),
137
+ Name.Builtin
138
+ ),
139
+
140
+ # the remaining functions
141
+ (r'(?<=\()' + valid_name, Name.Function),
142
+ # find the remaining variables
143
+ (valid_name, Name.Variable),
144
+
145
+ # the famous parentheses!
146
+ (r'(\(|\))', Punctuation),
147
+ ],
148
+ }
149
+
150
+
151
+ class CommonLispLexer(RegexLexer):
152
+ """
153
+ A Common Lisp lexer.
154
+
155
+ *New in Pygments 0.9.*
156
+ """
157
+ name = 'Common Lisp'
158
+ aliases = ['common-lisp', 'cl']
159
+ filenames = ['*.cl', '*.lisp', '*.el'] # use for Elisp too
160
+ mimetypes = ['text/x-common-lisp']
161
+
162
+ flags = re.IGNORECASE | re.MULTILINE
163
+
164
+ ### couple of useful regexes
165
+
166
+ # characters that are not macro-characters and can be used to begin a symbol
167
+ nonmacro = r'\\.|[a-zA-Z0-9!$%&*+-/<=>?@\[\]^_{}~]'
168
+ constituent = nonmacro + '|[#.:]'
169
+ terminated = r'(?=[ "()\'\n,;`])' # whitespace or terminating macro characters
170
+
171
+ ### symbol token, reverse-engineered from hyperspec
172
+ # Take a deep breath...
173
+ symbol = r'(\|[^|]+\||(?:%s)(?:%s)*)' % (nonmacro, constituent)
174
+
175
+ def __init__(self, **options):
176
+ from pygments.lexers._clbuiltins import BUILTIN_FUNCTIONS, \
177
+ SPECIAL_FORMS, MACROS, LAMBDA_LIST_KEYWORDS, DECLARATIONS, \
178
+ BUILTIN_TYPES, BUILTIN_CLASSES
179
+ self.builtin_function = BUILTIN_FUNCTIONS
180
+ self.special_forms = SPECIAL_FORMS
181
+ self.macros = MACROS
182
+ self.lambda_list_keywords = LAMBDA_LIST_KEYWORDS
183
+ self.declarations = DECLARATIONS
184
+ self.builtin_types = BUILTIN_TYPES
185
+ self.builtin_classes = BUILTIN_CLASSES
186
+ RegexLexer.__init__(self, **options)
187
+
188
+ def get_tokens_unprocessed(self, text):
189
+ stack = ['root']
190
+ for index, token, value in RegexLexer.get_tokens_unprocessed(self, text, stack):
191
+ if token is Name.Variable:
192
+ if value in self.builtin_function:
193
+ yield index, Name.Builtin, value
194
+ continue
195
+ if value in self.special_forms:
196
+ yield index, Keyword, value
197
+ continue
198
+ if value in self.macros:
199
+ yield index, Name.Builtin, value
200
+ continue
201
+ if value in self.lambda_list_keywords:
202
+ yield index, Keyword, value
203
+ continue
204
+ if value in self.declarations:
205
+ yield index, Keyword, value
206
+ continue
207
+ if value in self.builtin_types:
208
+ yield index, Keyword.Type, value
209
+ continue
210
+ if value in self.builtin_classes:
211
+ yield index, Name.Class, value
212
+ continue
213
+ yield index, token, value
214
+
215
+ tokens = {
216
+ 'root' : [
217
+ ('', Text, 'body'),
218
+ ],
219
+ 'multiline-comment' : [
220
+ (r'#\|', Comment.Multiline, '#push'), # (cf. Hyperspec 2.4.8.19)
221
+ (r'\|#', Comment.Multiline, '#pop'),
222
+ (r'[^|#]+', Comment.Multiline),
223
+ (r'[|#]', Comment.Multiline),
224
+ ],
225
+ 'commented-form' : [
226
+ (r'\(', Comment.Preproc, '#push'),
227
+ (r'\)', Comment.Preproc, '#pop'),
228
+ (r'[^()]+', Comment.Preproc),
229
+ ],
230
+ 'body' : [
231
+ # whitespace
232
+ (r'\s+', Text),
233
+
234
+ # single-line comment
235
+ (r';.*$', Comment.Single),
236
+
237
+ # multi-line comment
238
+ (r'#\|', Comment.Multiline, 'multiline-comment'),
239
+
240
+ # encoding comment (?)
241
+ (r'#\d*Y.*$', Comment.Special),
242
+
243
+ # strings and characters
244
+ (r'"(\\.|[^"\\])*"', String),
245
+ # quoting
246
+ (r":" + symbol, String.Symbol),
247
+ (r"'" + symbol, String.Symbol),
248
+ (r"'", Operator),
249
+ (r"`", Operator),
250
+
251
+ # decimal numbers
252
+ (r'[-+]?\d+\.?' + terminated, Number.Integer),
253
+ (r'[-+]?\d+/\d+' + terminated, Number),
254
+ (r'[-+]?(\d*\.\d+([defls][-+]?\d+)?|\d+(\.\d*)?[defls][-+]?\d+)' \
255
+ + terminated, Number.Float),
256
+
257
+ # sharpsign strings and characters
258
+ (r"#\\." + terminated, String.Char),
259
+ (r"#\\" + symbol, String.Char),
260
+
261
+ # vector
262
+ (r'#\(', Operator, 'body'),
263
+
264
+ # bitstring
265
+ (r'#\d*\*[01]*', Literal.Other),
266
+
267
+ # uninterned symbol
268
+ (r'#:' + symbol, String.Symbol),
269
+
270
+ # read-time and load-time evaluation
271
+ (r'#[.,]', Operator),
272
+
273
+ # function shorthand
274
+ (r'#\'', Name.Function),
275
+
276
+ # binary rational
277
+ (r'#[bB][+-]?[01]+(/[01]+)?', Number),
278
+
279
+ # octal rational
280
+ (r'#[oO][+-]?[0-7]+(/[0-7]+)?', Number.Oct),
281
+
282
+ # hex rational
283
+ (r'#[xX][+-]?[0-9a-fA-F]+(/[0-9a-fA-F]+)?', Number.Hex),
284
+
285
+ # radix rational
286
+ (r'#\d+[rR][+-]?[0-9a-zA-Z]+(/[0-9a-zA-Z]+)?', Number),
287
+
288
+ # complex
289
+ (r'(#[cC])(\()', bygroups(Number, Punctuation), 'body'),
290
+
291
+ # array
292
+ (r'(#\d+[aA])(\()', bygroups(Literal.Other, Punctuation), 'body'),
293
+
294
+ # structure
295
+ (r'(#[sS])(\()', bygroups(Literal.Other, Punctuation), 'body'),
296
+
297
+ # path
298
+ (r'#[pP]?"(\\.|[^"])*"', Literal.Other),
299
+
300
+ # reference
301
+ (r'#\d+=', Operator),
302
+ (r'#\d+#', Operator),
303
+
304
+ # read-time comment
305
+ (r'#+nil' + terminated + '\s*\(', Comment.Preproc, 'commented-form'),
306
+
307
+ # read-time conditional
308
+ (r'#[+-]', Operator),
309
+
310
+ # special operators that should have been parsed already
311
+ (r'(,@|,|\.)', Operator),
312
+
313
+ # special constants
314
+ (r'(t|nil)' + terminated, Name.Constant),
315
+
316
+ # functions and variables
317
+ (r'\*' + symbol + '\*', Name.Variable.Global),
318
+ (symbol, Name.Variable),
319
+
320
+ # parentheses
321
+ (r'\(', Punctuation, 'body'),
322
+ (r'\)', Punctuation, '#pop'),
323
+ ],
324
+ }
325
+
326
+
327
+ class HaskellLexer(RegexLexer):
328
+ """
329
+ A Haskell lexer based on the lexemes defined in the Haskell 98 Report.
330
+
331
+ *New in Pygments 0.8.*
332
+ """
333
+ name = 'Haskell'
334
+ aliases = ['haskell', 'hs']
335
+ filenames = ['*.hs']
336
+ mimetypes = ['text/x-haskell']
337
+
338
+ reserved = ['case','class','data','default','deriving','do','else',
339
+ 'if','in','infix[lr]?','instance',
340
+ 'let','newtype','of','then','type','where','_']
341
+ ascii = ['NUL','SOH','[SE]TX','EOT','ENQ','ACK',
342
+ 'BEL','BS','HT','LF','VT','FF','CR','S[OI]','DLE',
343
+ 'DC[1-4]','NAK','SYN','ETB','CAN',
344
+ 'EM','SUB','ESC','[FGRU]S','SP','DEL']
345
+
346
+ tokens = {
347
+ 'root': [
348
+ # Whitespace:
349
+ (r'\s+', Text),
350
+ #(r'--\s*|.*$', Comment.Doc),
351
+ (r'--(?![!#$%&*+./<=>?@\^|_~]).*?$', Comment.Single),
352
+ (r'{-', Comment.Multiline, 'comment'),
353
+ # Lexemes:
354
+ # Identifiers
355
+ (r'\bimport\b', Keyword.Reserved, 'import'),
356
+ (r'\bmodule\b', Keyword.Reserved, 'module'),
357
+ (r'\berror\b', Name.Exception),
358
+ (r'\b(%s)(?!\')\b' % '|'.join(reserved), Keyword.Reserved),
359
+ (r'^[_a-z][\w\']*', Name.Function),
360
+ (r'[_a-z][\w\']*', Name),
361
+ (r'[A-Z][\w\']*', Keyword.Type),
362
+ # Operators
363
+ (r'\\(?![:!#$%&*+.\\/<=>?@^|~-]+)', Name.Function), # lambda operator
364
+ (r'(<-|::|->|=>|=)(?![:!#$%&*+.\\/<=>?@^|~-]+)', Operator.Word), # specials
365
+ (r':[:!#$%&*+.\\/<=>?@^|~-]*', Keyword.Type), # Constructor operators
366
+ (r'[:!#$%&*+.\\/<=>?@^|~-]+', Operator), # Other operators
367
+ # Numbers
368
+ (r'\d+[eE][+-]?\d+', Number.Float),
369
+ (r'\d+\.\d+([eE][+-]?\d+)?', Number.Float),
370
+ (r'0[oO][0-7]+', Number.Oct),
371
+ (r'0[xX][\da-fA-F]+', Number.Hex),
372
+ (r'\d+', Number.Integer),
373
+ # Character/String Literals
374
+ (r"'", String.Char, 'character'),
375
+ (r'"', String, 'string'),
376
+ # Special
377
+ (r'\[\]', Keyword.Type),
378
+ (r'\(\)', Name.Builtin),
379
+ (r'[][(),;`{}]', Punctuation),
380
+ ],
381
+ 'import': [
382
+ # Import statements
383
+ (r'\s+', Text),
384
+ # after "funclist" state
385
+ (r'\)', Punctuation, '#pop'),
386
+ (r'qualified\b', Keyword),
387
+ # import X as Y
388
+ (r'([A-Z][a-zA-Z0-9_.]*)(\s+)(as)(\s+)([A-Z][a-zA-Z0-9_.]*)',
389
+ bygroups(Name.Namespace, Text, Keyword, Text, Name), '#pop'),
390
+ # import X hiding (functions)
391
+ (r'([A-Z][a-zA-Z0-9_.]*)(\s+)(hiding)(\s+)(\()',
392
+ bygroups(Name.Namespace, Text, Keyword, Text, Punctuation), 'funclist'),
393
+ # import X (functions)
394
+ (r'([A-Z][a-zA-Z0-9_.]*)(\s+)(\()',
395
+ bygroups(Name.Namespace, Text, Punctuation), 'funclist'),
396
+ # import X
397
+ (r'[a-zA-Z0-9_.]+', Name.Namespace, '#pop'),
398
+ ],
399
+ 'module': [
400
+ (r'\s+', Text),
401
+ (r'([A-Z][a-zA-Z0-9_.]*)(\s+)(\()',
402
+ bygroups(Name.Namespace, Text, Punctuation), 'funclist'),
403
+ (r'[A-Z][a-zA-Z0-9_.]*', Name.Namespace, '#pop'),
404
+ ],
405
+ 'funclist': [
406
+ (r'\s+', Text),
407
+ (r'[A-Z][a-zA-Z0-9_]*', Keyword.Type),
408
+ (r'[_a-z][\w\']+', Name.Function),
409
+ (r'--.*$', Comment.Single),
410
+ (r'{-', Comment.Multiline, 'comment'),
411
+ (r',', Punctuation),
412
+ (r'[:!#$%&*+.\\/<=>?@^|~-]+', Operator),
413
+ # (HACK, but it makes sense to push two instances, believe me)
414
+ (r'\(', Punctuation, ('funclist', 'funclist')),
415
+ (r'\)', Punctuation, '#pop:2'),
416
+ ],
417
+ 'comment': [
418
+ # Multiline Comments
419
+ (r'[^-{}]+', Comment.Multiline),
420
+ (r'{-', Comment.Multiline, '#push'),
421
+ (r'-}', Comment.Multiline, '#pop'),
422
+ (r'[-{}]', Comment.Multiline),
423
+ ],
424
+ 'character': [
425
+ # Allows multi-chars, incorrectly.
426
+ (r"[^\\']", String.Char),
427
+ (r"\\", String.Escape, 'escape'),
428
+ ("'", String.Char, '#pop'),
429
+ ],
430
+ 'string': [
431
+ (r'[^\\"]+', String),
432
+ (r"\\", String.Escape, 'escape'),
433
+ ('"', String, '#pop'),
434
+ ],
435
+ 'escape': [
436
+ (r'[abfnrtv"\'&\\]', String.Escape, '#pop'),
437
+ (r'\^[][A-Z@\^_]', String.Escape, '#pop'),
438
+ ('|'.join(ascii), String.Escape, '#pop'),
439
+ (r'o[0-7]+', String.Escape, '#pop'),
440
+ (r'x[\da-fA-F]+', String.Escape, '#pop'),
441
+ (r'\d+', String.Escape, '#pop'),
442
+ (r'\s+\\', String.Escape, '#pop'),
443
+ ],
444
+ }
445
+
446
+
447
+ line_re = re.compile('.*?\n')
448
+ bird_re = re.compile(r'(>[ \t]*)(.*\n)')
449
+
450
+ class LiterateHaskellLexer(Lexer):
451
+ """
452
+ For Literate Haskell (Bird-style or LaTeX) source.
453
+
454
+ Additional options accepted:
455
+
456
+ `litstyle`
457
+ If given, must be ``"bird"`` or ``"latex"``. If not given, the style
458
+ is autodetected: if the first non-whitespace character in the source
459
+ is a backslash or percent character, LaTeX is assumed, else Bird.
460
+
461
+ *New in Pygments 0.9.*
462
+ """
463
+ name = 'Literate Haskell'
464
+ aliases = ['lhs', 'literate-haskell']
465
+ filenames = ['*.lhs']
466
+ mimetypes = ['text/x-literate-haskell']
467
+
468
+ def get_tokens_unprocessed(self, text):
469
+ hslexer = HaskellLexer(**self.options)
470
+
471
+ style = self.options.get('litstyle')
472
+ if style is None:
473
+ style = (text.lstrip()[0:1] in '%\\') and 'latex' or 'bird'
474
+
475
+ code = ''
476
+ insertions = []
477
+ if style == 'bird':
478
+ # bird-style
479
+ for match in line_re.finditer(text):
480
+ line = match.group()
481
+ m = bird_re.match(line)
482
+ if m:
483
+ insertions.append((len(code),
484
+ [(0, Comment.Special, m.group(1))]))
485
+ code += m.group(2)
486
+ else:
487
+ insertions.append((len(code), [(0, Text, line)]))
488
+ else:
489
+ # latex-style
490
+ from pygments.lexers.text import TexLexer
491
+ lxlexer = TexLexer(**self.options)
492
+
493
+ codelines = 0
494
+ latex = ''
495
+ for match in line_re.finditer(text):
496
+ line = match.group()
497
+ if codelines:
498
+ if line.lstrip().startswith('\\end{code}'):
499
+ codelines = 0
500
+ latex += line
501
+ else:
502
+ code += line
503
+ elif line.lstrip().startswith('\\begin{code}'):
504
+ codelines = 1
505
+ latex += line
506
+ insertions.append((len(code),
507
+ list(lxlexer.get_tokens_unprocessed(latex))))
508
+ latex = ''
509
+ else:
510
+ latex += line
511
+ insertions.append((len(code),
512
+ list(lxlexer.get_tokens_unprocessed(latex))))
513
+ for item in do_insertions(insertions, hslexer.get_tokens_unprocessed(code)):
514
+ yield item
515
+
516
+
517
+ class OcamlLexer(RegexLexer):
518
+ """
519
+ For the OCaml language.
520
+
521
+ *New in Pygments 0.7.*
522
+ """
523
+
524
+ name = 'OCaml'
525
+ aliases = ['ocaml']
526
+ filenames = ['*.ml', '*.mli', '*.mll', '*.mly']
527
+ mimetypes = ['text/x-ocaml']
528
+
529
+ keywords = [
530
+ 'as', 'assert', 'begin', 'class', 'constraint', 'do', 'done',
531
+ 'downto', 'else', 'end', 'exception', 'external', 'false',
532
+ 'for', 'fun', 'function', 'functor', 'if', 'in', 'include',
533
+ 'inherit', 'initializer', 'lazy', 'let', 'match', 'method',
534
+ 'module', 'mutable', 'new', 'object', 'of', 'open', 'private',
535
+ 'raise', 'rec', 'sig', 'struct', 'then', 'to', 'true', 'try',
536
+ 'type', 'val', 'virtual', 'when', 'while', 'with'
537
+ ]
538
+ keyopts = [
539
+ '!=','#','&','&&','\(','\)','\*','\+',',','-',
540
+ '-\.','->','\.','\.\.',':','::',':=',':>',';',';;','<',
541
+ '<-','=','>','>]','>}','\?','\?\?','\[','\[<','\[>','\[\|',
542
+ ']','_','`','{','{<','\|','\|]','}','~'
543
+ ]
544
+
545
+ operators = r'[!$%&*+\./:<=>?@^|~-]'
546
+ word_operators = ['and', 'asr', 'land', 'lor', 'lsl', 'lxor', 'mod', 'or']
547
+ prefix_syms = r'[!?~]'
548
+ infix_syms = r'[=<>@^|&+\*/$%-]'
549
+ primitives = ['unit', 'int', 'float', 'bool', 'string', 'char', 'list', 'array']
550
+
551
+ tokens = {
552
+ 'escape-sequence': [
553
+ (r'\\[\"\'ntbr]', String.Escape),
554
+ (r'\\[0-9]{3}', String.Escape),
555
+ (r'\\x[0-9a-fA-F]{2}', String.Escape),
556
+ ],
557
+ 'root': [
558
+ (r'\s+', Text),
559
+ (r'false|true|\(\)|\[\]', Name.Builtin.Pseudo),
560
+ (r'\b([A-Z][A-Za-z0-9_\']*)(?=\s*\.)',
561
+ Name.Namespace, 'dotted'),
562
+ (r'\b([A-Z][A-Za-z0-9_\']*)', Name.Class),
563
+ (r'\(\*', Comment, 'comment'),
564
+ (r'\b(%s)\b' % '|'.join(keywords), Keyword),
565
+ (r'(%s)' % '|'.join(keyopts), Operator),
566
+ (r'(%s|%s)?%s' % (infix_syms, prefix_syms, operators), Operator),
567
+ (r'\b(%s)\b' % '|'.join(word_operators), Operator.Word),
568
+ (r'\b(%s)\b' % '|'.join(primitives), Keyword.Type),
569
+
570
+ (r"[^\W\d][\w']*", Name),
571
+
572
+ (r'\d[\d_]*', Number.Integer),
573
+ (r'0[xX][\da-fA-F][\da-fA-F_]*', Number.Hex),
574
+ (r'0[oO][0-7][0-7_]*', Number.Oct),
575
+ (r'0[bB][01][01_]*', Number.Binary),
576
+ (r'-?\d[\d_]*(.[\d_]*)?([eE][+\-]?\d[\d_]*)', Number.Float),
577
+
578
+ (r"'(?:(\\[\\\"'ntbr ])|(\\[0-9]{3})|(\\x[0-9a-fA-F]{2}))'",
579
+ String.Char),
580
+ (r"'.'", String.Char),
581
+ (r"'", Keyword), # a stray quote is another syntax element
582
+
583
+ (r'"', String.Double, 'string'),
584
+
585
+ (r'[~?][a-z][\w\']*:', Name.Variable),
586
+ ],
587
+ 'comment': [
588
+ (r'[^(*)]+', Comment),
589
+ (r'\(\*', Comment, '#push'),
590
+ (r'\*\)', Comment, '#pop'),
591
+ (r'[(*)]', Comment),
592
+ ],
593
+ 'string': [
594
+ (r'[^\\"]+', String.Double),
595
+ include('escape-sequence'),
596
+ (r'\\\n', String.Double),
597
+ (r'"', String.Double, '#pop'),
598
+ ],
599
+ 'dotted': [
600
+ (r'\s+', Text),
601
+ (r'\.', Punctuation),
602
+ (r'[A-Z][A-Za-z0-9_\']*(?=\s*\.)', Name.Namespace),
603
+ (r'[A-Z][A-Za-z0-9_\']*', Name.Class, '#pop'),
604
+ (r'[a-z][a-z0-9_\']*', Name, '#pop'),
605
+ ],
606
+ }
607
+
608
+
609
+ class ErlangLexer(RegexLexer):
610
+ """
611
+ For the Erlang functional programming language.
612
+
613
+ Blame Jeremy Thurgood (http://jerith.za.net/).
614
+
615
+ *New in Pygments 0.9.*
616
+ """
617
+
618
+ name = 'Erlang'
619
+ aliases = ['erlang']
620
+ filenames = ['*.erl', '*.hrl']
621
+ mimetypes = ['text/x-erlang']
622
+
623
+ keywords = [
624
+ 'after', 'begin', 'case', 'catch', 'cond', 'end', 'fun', 'if',
625
+ 'let', 'of', 'query', 'receive', 'try', 'when',
626
+ ]
627
+
628
+ builtins = [ # See erlang(3) man page
629
+ 'abs', 'append_element', 'apply', 'atom_to_list', 'binary_to_list',
630
+ 'bitstring_to_list', 'binary_to_term', 'bit_size', 'bump_reductions',
631
+ 'byte_size', 'cancel_timer', 'check_process_code', 'delete_module',
632
+ 'demonitor', 'disconnect_node', 'display', 'element', 'erase', 'exit',
633
+ 'float', 'float_to_list', 'fun_info', 'fun_to_list',
634
+ 'function_exported', 'garbage_collect', 'get', 'get_keys',
635
+ 'group_leader', 'hash', 'hd', 'integer_to_list', 'iolist_to_binary',
636
+ 'iolist_size', 'is_atom', 'is_binary', 'is_bitstring', 'is_boolean',
637
+ 'is_builtin', 'is_float', 'is_function', 'is_integer', 'is_list',
638
+ 'is_number', 'is_pid', 'is_port', 'is_process_alive', 'is_record',
639
+ 'is_reference', 'is_tuple', 'length', 'link', 'list_to_atom',
640
+ 'list_to_binary', 'list_to_bitstring', 'list_to_existing_atom',
641
+ 'list_to_float', 'list_to_integer', 'list_to_pid', 'list_to_tuple',
642
+ 'load_module', 'localtime_to_universaltime', 'make_tuple', 'md5',
643
+ 'md5_final', 'md5_update', 'memory', 'module_loaded', 'monitor',
644
+ 'monitor_node', 'node', 'nodes', 'open_port', 'phash', 'phash2',
645
+ 'pid_to_list', 'port_close', 'port_command', 'port_connect',
646
+ 'port_control', 'port_call', 'port_info', 'port_to_list',
647
+ 'process_display', 'process_flag', 'process_info', 'purge_module',
648
+ 'put', 'read_timer', 'ref_to_list', 'register', 'resume_process',
649
+ 'round', 'send', 'send_after', 'send_nosuspend', 'set_cookie',
650
+ 'setelement', 'size', 'spawn', 'spawn_link', 'spawn_monitor',
651
+ 'spawn_opt', 'split_binary', 'start_timer', 'statistics',
652
+ 'suspend_process', 'system_flag', 'system_info', 'system_monitor',
653
+ 'system_profile', 'term_to_binary', 'tl', 'trace', 'trace_delivered',
654
+ 'trace_info', 'trace_pattern', 'trunc', 'tuple_size', 'tuple_to_list',
655
+ 'universaltime_to_localtime', 'unlink', 'unregister', 'whereis'
656
+ ]
657
+
658
+ operators = r'(\+|-|\*|/|<|>|=|==|/=|=:=|=/=|=<|>=|\+\+|--|<-|!)'
659
+ word_operators = [
660
+ 'and', 'andalso', 'band', 'bnot', 'bor', 'bsl', 'bsr', 'bxor',
661
+ 'div', 'not', 'or', 'orelse', 'rem', 'xor'
662
+ ]
663
+
664
+ atom_re = r"(?:[a-z][a-zA-Z0-9_]*|'[^\n']*[^\\]')"
665
+
666
+ variable_re = r'(?:[A-Z_][a-zA-Z0-9_]*)'
667
+
668
+ escape_re = r'(?:\\(?:[bdefnrstv\'"\\/]|[0-7][0-7]?[0-7]?|\^[a-zA-Z]))'
669
+
670
+ macro_re = r'(?:'+variable_re+r'|'+atom_re+r')'
671
+
672
+ base_re = r'(?:[2-9]|[12][0-9]|3[0-6])'
673
+
674
+ tokens = {
675
+ 'root': [
676
+ (r'\s+', Text),
677
+ (r'%.*\n', Comment),
678
+ ('(' + '|'.join(keywords) + r')\b', Keyword),
679
+ ('(' + '|'.join(builtins) + r')\b', Name.Builtin),
680
+ ('(' + '|'.join(word_operators) + r')\b', Operator.Word),
681
+ (r'^-', Punctuation, 'directive'),
682
+ (operators, Operator),
683
+ (r'"', String, 'string'),
684
+ (r'<<', Name.Label),
685
+ (r'>>', Name.Label),
686
+ (r'('+atom_re+')(:)', bygroups(Name.Namespace, Punctuation)),
687
+ (r'^('+atom_re+r')(\s*)(\()', bygroups(Name.Function, Text, Punctuation)),
688
+ (r'[+-]?'+base_re+r'#[0-9a-zA-Z]+', Number.Integer),
689
+ (r'[+-]?\d+', Number.Integer),
690
+ (r'[+-]?\d+.\d+', Number.Float),
691
+ (r'[][:_@\".{}()|;,]', Punctuation),
692
+ (variable_re, Name.Variable),
693
+ (atom_re, Name),
694
+ (r'\?'+macro_re, Name.Constant),
695
+ (r'\$(?:'+escape_re+r'|\\[ %]|[^\\])', String.Char),
696
+ (r'#'+atom_re+r'(:?\.'+atom_re+r')?', Name.Label),
697
+ ],
698
+ 'string': [
699
+ (escape_re, String.Escape),
700
+ (r'"', String, '#pop'),
701
+ (r'~[0-9.*]*[~#+bBcdefginpPswWxX]', String.Interpol),
702
+ (r'[^"\\~]+', String),
703
+ (r'~', String),
704
+ ],
705
+ 'directive': [
706
+ (r'(define)(\s*)(\()('+macro_re+r')',
707
+ bygroups(Name.Entity, Text, Punctuation, Name.Constant), '#pop'),
708
+ (r'(record)(\s*)(\()('+macro_re+r')',
709
+ bygroups(Name.Entity, Text, Punctuation, Name.Label), '#pop'),
710
+ (atom_re, Name.Entity, '#pop'),
711
+ ],
712
+ }
713
+
714
+
715
+ class ErlangShellLexer(Lexer):
716
+ """
717
+ Shell sessions in erl (for Erlang code).
718
+
719
+ *New in Pygments 1.1.*
720
+ """
721
+ name = 'Erlang erl session'
722
+ aliases = ['erl']
723
+ filenames = ['*.erl-sh']
724
+ mimetypes = ['text/x-erl-shellsession']
725
+
726
+ _prompt_re = re.compile(r'\d+>(?=\s|\Z)')
727
+
728
+ def get_tokens_unprocessed(self, text):
729
+ erlexer = ErlangLexer(**self.options)
730
+
731
+ curcode = ''
732
+ insertions = []
733
+ for match in line_re.finditer(text):
734
+ line = match.group()
735
+ m = self._prompt_re.match(line)
736
+ if m is not None:
737
+ end = m.end()
738
+ insertions.append((len(curcode),
739
+ [(0, Generic.Prompt, line[:end])]))
740
+ curcode += line[end:]
741
+ else:
742
+ if curcode:
743
+ for item in do_insertions(insertions,
744
+ erlexer.get_tokens_unprocessed(curcode)):
745
+ yield item
746
+ curcode = ''
747
+ insertions = []
748
+ if line.startswith('*'):
749
+ yield match.start(), Generic.Traceback, line
750
+ else:
751
+ yield match.start(), Generic.Output, line
752
+ if curcode:
753
+ for item in do_insertions(insertions,
754
+ erlexer.get_tokens_unprocessed(curcode)):
755
+ yield item
756
+