Mercurial Repositories > eric / file comparison
comparison: ThirdParty/Pygments/pygments/lexers/haskell.py
ThirdParty/Pygments/pygments/lexers/haskell.py
- changeset 4172
- 4f20dba37ab6
- child 4697
- c2e9bf425554
equal
deleted
inserted
replaced
| 4170:8bc578136279 | 4172:4f20dba37ab6 |
|---|---|
| 1 # -*- coding: utf-8 -*- | |
| 2 """ | |
| 3 pygments.lexers.haskell | |
| 4 ~~~~~~~~~~~~~~~~~~~~~~~ | |
| 5 | |
| 6 Lexers for Haskell and related languages. | |
| 7 | |
| 8 :copyright: Copyright 2006-2014 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, do_insertions, \ | |
| 15 default, include | |
| 16 from pygments.token import Text, Comment, Operator, Keyword, Name, String, \ | |
| 17 Number, Punctuation, Generic | |
| 18 from pygments import unistring as uni | |
| 19 | |
| 20 __all__ = ['HaskellLexer', 'IdrisLexer', 'AgdaLexer', 'CryptolLexer', | |
| 21 'LiterateHaskellLexer', 'LiterateIdrisLexer', 'LiterateAgdaLexer', | |
| 22 'LiterateCryptolLexer', 'KokaLexer'] | |
| 23 | |
| 24 | |
| 25 line_re = re.compile('.*?\n') | |
| 26 | |
| 27 | |
| 28 class HaskellLexer(RegexLexer): | |
| 29 """ | |
| 30 A Haskell lexer based on the lexemes defined in the Haskell 98 Report. | |
| 31 | |
| 32 .. versionadded:: 0.8 | |
| 33 """ | |
| 34 name = 'Haskell' | |
| 35 aliases = ['haskell', 'hs'] | |
| 36 filenames = ['*.hs'] | |
| 37 mimetypes = ['text/x-haskell'] | |
| 38 | |
| 39 flags = re.MULTILINE | re.UNICODE | |
| 40 | |
| 41 reserved = ('case', 'class', 'data', 'default', 'deriving', 'do', 'else', | |
| 42 'if', 'in', 'infix[lr]?', 'instance', | |
| 43 'let', 'newtype', 'of', 'then', 'type', 'where', '_') | |
| 44 ascii = ('NUL', 'SOH', '[SE]TX', 'EOT', 'ENQ', 'ACK', | |
| 45 'BEL', 'BS', 'HT', 'LF', 'VT', 'FF', 'CR', 'S[OI]', 'DLE', | |
| 46 'DC[1-4]', 'NAK', 'SYN', 'ETB', 'CAN', | |
| 47 'EM', 'SUB', 'ESC', '[FGRU]S', 'SP', 'DEL') | |
| 48 | |
| 49 tokens = { | |
| 50 'root': [ | |
| 51 # Whitespace: | |
| 52 (r'\s+', Text), | |
| 53 # (r'--\s*|.*$', Comment.Doc), | |
| 54 (r'--(?![!#$%&*+./<=>?@^|_~:\\]).*?$', Comment.Single), | |
| 55 (r'\{-', Comment.Multiline, 'comment'), | |
| 56 # Lexemes: | |
| 57 # Identifiers | |
| 58 (r'\bimport\b', Keyword.Reserved, 'import'), | |
| 59 (r'\bmodule\b', Keyword.Reserved, 'module'), | |
| 60 (r'\berror\b', Name.Exception), | |
| 61 (r'\b(%s)(?!\')\b' % '|'.join(reserved), Keyword.Reserved), | |
| 62 (r"'[^\\]'", String.Char), # this has to come before the TH quote | |
| 63 (r'^[_' + uni.Ll + r'][\w\']*', Name.Function), | |
| 64 (r"'?[_" + uni.Ll + r"][\w']*", Name), | |
| 65 (r"('')?[" + uni.Lu + r"][\w\']*", Keyword.Type), | |
| 66 # Operators | |
| 67 (r'\\(?![:!#$%&*+.\\/<=>?@^|~-]+)', Name.Function), # lambda operator | |
| 68 (r'(<-|::|->|=>|=)(?![:!#$%&*+.\\/<=>?@^|~-]+)', Operator.Word), # specials | |
| 69 (r':[:!#$%&*+.\\/<=>?@^|~-]*', Keyword.Type), # Constructor operators | |
| 70 (r'[:!#$%&*+.\\/<=>?@^|~-]+', Operator), # Other operators | |
| 71 # Numbers | |
| 72 (r'\d+[eE][+-]?\d+', Number.Float), | |
| 73 (r'\d+\.\d+([eE][+-]?\d+)?', Number.Float), | |
| 74 (r'0[oO][0-7]+', Number.Oct), | |
| 75 (r'0[xX][\da-fA-F]+', Number.Hex), | |
| 76 (r'\d+', Number.Integer), | |
| 77 # Character/String Literals | |
| 78 (r"'", String.Char, 'character'), | |
| 79 (r'"', String, 'string'), | |
| 80 # Special | |
| 81 (r'\[\]', Keyword.Type), | |
| 82 (r'\(\)', Name.Builtin), | |
| 83 (r'[][(),;`{}]', Punctuation), | |
| 84 ], | |
| 85 'import': [ | |
| 86 # Import statements | |
| 87 (r'\s+', Text), | |
| 88 (r'"', String, 'string'), | |
| 89 # after "funclist" state | |
| 90 (r'\)', Punctuation, '#pop'), | |
| 91 (r'qualified\b', Keyword), | |
| 92 # import X as Y | |
| 93 (r'([' + uni.Lu + r'][\w.]*)(\s+)(as)(\s+)([' + uni.Lu + r'][\w.]*)', | |
| 94 bygroups(Name.Namespace, Text, Keyword, Text, Name), '#pop'), | |
| 95 # import X hiding (functions) | |
| 96 (r'([' + uni.Lu + r'][\w.]*)(\s+)(hiding)(\s+)(\()', | |
| 97 bygroups(Name.Namespace, Text, Keyword, Text, Punctuation), 'funclist'), | |
| 98 # import X (functions) | |
| 99 (r'([' + uni.Lu + r'][\w.]*)(\s+)(\()', | |
| 100 bygroups(Name.Namespace, Text, Punctuation), 'funclist'), | |
| 101 # import X | |
| 102 (r'[\w.]+', Name.Namespace, '#pop'), | |
| 103 ], | |
| 104 'module': [ | |
| 105 (r'\s+', Text), | |
| 106 (r'([' + uni.Lu + r'][\w.]*)(\s+)(\()', | |
| 107 bygroups(Name.Namespace, Text, Punctuation), 'funclist'), | |
| 108 (r'[' + uni.Lu + r'][\w.]*', Name.Namespace, '#pop'), | |
| 109 ], | |
| 110 'funclist': [ | |
| 111 (r'\s+', Text), | |
| 112 (r'[' + uni.Lu + r']\w*', Keyword.Type), | |
| 113 (r'(_[\w\']+|[' + uni.Ll + r'][\w\']*)', Name.Function), | |
| 114 (r'--(?![!#$%&*+./<=>?@^|_~:\\]).*?$', Comment.Single), | |
| 115 (r'\{-', Comment.Multiline, 'comment'), | |
| 116 (r',', Punctuation), | |
| 117 (r'[:!#$%&*+.\\/<=>?@^|~-]+', Operator), | |
| 118 # (HACK, but it makes sense to push two instances, believe me) | |
| 119 (r'\(', Punctuation, ('funclist', 'funclist')), | |
| 120 (r'\)', Punctuation, '#pop:2'), | |
| 121 ], | |
| 122 # NOTE: the next four states are shared in the AgdaLexer; make sure | |
| 123 # any change is compatible with Agda as well or copy over and change | |
| 124 'comment': [ | |
| 125 # Multiline Comments | |
| 126 (r'[^-{}]+', Comment.Multiline), | |
| 127 (r'\{-', Comment.Multiline, '#push'), | |
| 128 (r'-\}', Comment.Multiline, '#pop'), | |
| 129 (r'[-{}]', Comment.Multiline), | |
| 130 ], | |
| 131 'character': [ | |
| 132 # Allows multi-chars, incorrectly. | |
| 133 (r"[^\\']'", String.Char, '#pop'), | |
| 134 (r"\\", String.Escape, 'escape'), | |
| 135 ("'", String.Char, '#pop'), | |
| 136 ], | |
| 137 'string': [ | |
| 138 (r'[^\\"]+', String), | |
| 139 (r"\\", String.Escape, 'escape'), | |
| 140 ('"', String, '#pop'), | |
| 141 ], | |
| 142 'escape': [ | |
| 143 (r'[abfnrtv"\'&\\]', String.Escape, '#pop'), | |
| 144 (r'\^[][' + uni.Lu + r'@^_]', String.Escape, '#pop'), | |
| 145 ('|'.join(ascii), String.Escape, '#pop'), | |
| 146 (r'o[0-7]+', String.Escape, '#pop'), | |
| 147 (r'x[\da-fA-F]+', String.Escape, '#pop'), | |
| 148 (r'\d+', String.Escape, '#pop'), | |
| 149 (r'\s+\\', String.Escape, '#pop'), | |
| 150 ], | |
| 151 } | |
| 152 | |
| 153 | |
| 154 class IdrisLexer(RegexLexer): | |
| 155 """ | |
| 156 A lexer for the dependently typed programming language Idris. | |
| 157 | |
| 158 Based on the Haskell and Agda Lexer. | |
| 159 | |
| 160 .. versionadded:: 2.0 | |
| 161 """ | |
| 162 name = 'Idris' | |
| 163 aliases = ['idris', 'idr'] | |
| 164 filenames = ['*.idr'] | |
| 165 mimetypes = ['text/x-idris'] | |
| 166 | |
| 167 reserved = ('case', 'class', 'data', 'default', 'using', 'do', 'else', | |
| 168 'if', 'in', 'infix[lr]?', 'instance', 'rewrite', 'auto', | |
| 169 'namespace', 'codata', 'mutual', 'private', 'public', 'abstract', | |
| 170 'total', 'partial', | |
| 171 'let', 'proof', 'of', 'then', 'static', 'where', '_', 'with', | |
| 172 'pattern', 'term', 'syntax', 'prefix', | |
| 173 'postulate', 'parameters', 'record', 'dsl', 'impossible', 'implicit', | |
| 174 'tactics', 'intros', 'intro', 'compute', 'refine', 'exact', 'trivial') | |
| 175 | |
| 176 ascii = ('NUL', 'SOH', '[SE]TX', 'EOT', 'ENQ', 'ACK', | |
| 177 'BEL', 'BS', 'HT', 'LF', 'VT', 'FF', 'CR', 'S[OI]', 'DLE', | |
| 178 'DC[1-4]', 'NAK', 'SYN', 'ETB', 'CAN', | |
| 179 'EM', 'SUB', 'ESC', '[FGRU]S', 'SP', 'DEL') | |
| 180 | |
| 181 directives = ('lib', 'link', 'flag', 'include', 'hide', 'freeze', 'access', | |
| 182 'default', 'logging', 'dynamic', 'name', 'error_handlers', 'language') | |
| 183 | |
| 184 tokens = { | |
| 185 'root': [ | |
| 186 # Comments | |
| 187 (r'^(\s*)(%%%s)' % '|'.join(directives), | |
| 188 bygroups(Text, Keyword.Reserved)), | |
| 189 (r'(\s*)(--(?![!#$%&*+./<=>?@^|_~:\\]).*?)$', bygroups(Text, Comment.Single)), | |
| 190 (r'(\s*)(\|{3}.*?)$', bygroups(Text, Comment.Single)), | |
| 191 (r'(\s*)(\{-)', bygroups(Text, Comment.Multiline), 'comment'), | |
| 192 # Declaration | |
| 193 (r'^(\s*)([^\s(){}]+)(\s*)(:)(\s*)', | |
| 194 bygroups(Text, Name.Function, Text, Operator.Word, Text)), | |
| 195 # Identifiers | |
| 196 (r'\b(%s)(?!\')\b' % '|'.join(reserved), Keyword.Reserved), | |
| 197 (r'(import|module)(\s+)', bygroups(Keyword.Reserved, Text), 'module'), | |
| 198 (r"('')?[A-Z][\w\']*", Keyword.Type), | |
| 199 (r'[a-z][\w\']*', Text), | |
| 200 # Special Symbols | |
| 201 (r'(<-|::|->|=>|=)', Operator.Word), # specials | |
| 202 (r'([(){}\[\]:!#$%&*+.\\/<=>?@^|~-]+)', Operator.Word), # specials | |
| 203 # Numbers | |
| 204 (r'\d+[eE][+-]?\d+', Number.Float), | |
| 205 (r'\d+\.\d+([eE][+-]?\d+)?', Number.Float), | |
| 206 (r'0[xX][\da-fA-F]+', Number.Hex), | |
| 207 (r'\d+', Number.Integer), | |
| 208 # Strings | |
| 209 (r"'", String.Char, 'character'), | |
| 210 (r'"', String, 'string'), | |
| 211 (r'[^\s(){}]+', Text), | |
| 212 (r'\s+?', Text), # Whitespace | |
| 213 ], | |
| 214 'module': [ | |
| 215 (r'\s+', Text), | |
| 216 (r'([A-Z][\w.]*)(\s+)(\()', | |
| 217 bygroups(Name.Namespace, Text, Punctuation), 'funclist'), | |
| 218 (r'[A-Z][\w.]*', Name.Namespace, '#pop'), | |
| 219 ], | |
| 220 'funclist': [ | |
| 221 (r'\s+', Text), | |
| 222 (r'[A-Z]\w*', Keyword.Type), | |
| 223 (r'(_[\w\']+|[a-z][\w\']*)', Name.Function), | |
| 224 (r'--.*$', Comment.Single), | |
| 225 (r'\{-', Comment.Multiline, 'comment'), | |
| 226 (r',', Punctuation), | |
| 227 (r'[:!#$%&*+.\\/<=>?@^|~-]+', Operator), | |
| 228 # (HACK, but it makes sense to push two instances, believe me) | |
| 229 (r'\(', Punctuation, ('funclist', 'funclist')), | |
| 230 (r'\)', Punctuation, '#pop:2'), | |
| 231 ], | |
| 232 # NOTE: the next four states are shared in the AgdaLexer; make sure | |
| 233 # any change is compatible with Agda as well or copy over and change | |
| 234 'comment': [ | |
| 235 # Multiline Comments | |
| 236 (r'[^-{}]+', Comment.Multiline), | |
| 237 (r'\{-', Comment.Multiline, '#push'), | |
| 238 (r'-\}', Comment.Multiline, '#pop'), | |
| 239 (r'[-{}]', Comment.Multiline), | |
| 240 ], | |
| 241 'character': [ | |
| 242 # Allows multi-chars, incorrectly. | |
| 243 (r"[^\\']", String.Char), | |
| 244 (r"\\", String.Escape, 'escape'), | |
| 245 ("'", String.Char, '#pop'), | |
| 246 ], | |
| 247 'string': [ | |
| 248 (r'[^\\"]+', String), | |
| 249 (r"\\", String.Escape, 'escape'), | |
| 250 ('"', String, '#pop'), | |
| 251 ], | |
| 252 'escape': [ | |
| 253 (r'[abfnrtv"\'&\\]', String.Escape, '#pop'), | |
| 254 (r'\^[][A-Z@^_]', String.Escape, '#pop'), | |
| 255 ('|'.join(ascii), String.Escape, '#pop'), | |
| 256 (r'o[0-7]+', String.Escape, '#pop'), | |
| 257 (r'x[\da-fA-F]+', String.Escape, '#pop'), | |
| 258 (r'\d+', String.Escape, '#pop'), | |
| 259 (r'\s+\\', String.Escape, '#pop') | |
| 260 ], | |
| 261 } | |
| 262 | |
| 263 | |
| 264 class AgdaLexer(RegexLexer): | |
| 265 """ | |
| 266 For the `Agda <http://wiki.portal.chalmers.se/agda/pmwiki.php>`_ | |
| 267 dependently typed functional programming language and proof assistant. | |
| 268 | |
| 269 .. versionadded:: 2.0 | |
| 270 """ | |
| 271 | |
| 272 name = 'Agda' | |
| 273 aliases = ['agda'] | |
| 274 filenames = ['*.agda'] | |
| 275 mimetypes = ['text/x-agda'] | |
| 276 | |
| 277 reserved = ['abstract', 'codata', 'coinductive', 'constructor', 'data', | |
| 278 'field', 'forall', 'hiding', 'in', 'inductive', 'infix', | |
| 279 'infixl', 'infixr', 'instance', 'let', 'mutual', 'open', | |
| 280 'pattern', 'postulate', 'primitive', 'private', | |
| 281 'quote', 'quoteGoal', 'quoteTerm', | |
| 282 'record', 'renaming', 'rewrite', 'syntax', 'tactic', | |
| 283 'unquote', 'unquoteDecl', 'using', 'where', 'with'] | |
| 284 | |
| 285 tokens = { | |
| 286 'root': [ | |
| 287 # Declaration | |
| 288 (r'^(\s*)([^\s(){}]+)(\s*)(:)(\s*)', | |
| 289 bygroups(Text, Name.Function, Text, Operator.Word, Text)), | |
| 290 # Comments | |
| 291 (r'--(?![!#$%&*+./<=>?@^|_~:\\]).*?$', Comment.Single), | |
| 292 (r'\{-', Comment.Multiline, 'comment'), | |
| 293 # Holes | |
| 294 (r'\{!', Comment.Directive, 'hole'), | |
| 295 # Lexemes: | |
| 296 # Identifiers | |
| 297 (r'\b(%s)(?!\')\b' % '|'.join(reserved), Keyword.Reserved), | |
| 298 (r'(import|module)(\s+)', bygroups(Keyword.Reserved, Text), 'module'), | |
| 299 (r'\b(Set|Prop)\b', Keyword.Type), | |
| 300 # Special Symbols | |
| 301 (r'(\(|\)|\{|\})', Operator), | |
| 302 (u'(\\.{1,3}|\\||\u039B|\u2200|\u2192|:|=|->)', Operator.Word), | |
| 303 # Numbers | |
| 304 (r'\d+[eE][+-]?\d+', Number.Float), | |
| 305 (r'\d+\.\d+([eE][+-]?\d+)?', Number.Float), | |
| 306 (r'0[xX][\da-fA-F]+', Number.Hex), | |
| 307 (r'\d+', Number.Integer), | |
| 308 # Strings | |
| 309 (r"'", String.Char, 'character'), | |
| 310 (r'"', String, 'string'), | |
| 311 (r'[^\s(){}]+', Text), | |
| 312 (r'\s+?', Text), # Whitespace | |
| 313 ], | |
| 314 'hole': [ | |
| 315 # Holes | |
| 316 (r'[^!{}]+', Comment.Directive), | |
| 317 (r'\{!', Comment.Directive, '#push'), | |
| 318 (r'!\}', Comment.Directive, '#pop'), | |
| 319 (r'[!{}]', Comment.Directive), | |
| 320 ], | |
| 321 'module': [ | |
| 322 (r'\{-', Comment.Multiline, 'comment'), | |
| 323 (r'[a-zA-Z][\w.]*', Name, '#pop'), | |
| 324 (r'[^a-zA-Z]+', Text) | |
| 325 ], | |
| 326 'comment': HaskellLexer.tokens['comment'], | |
| 327 'character': HaskellLexer.tokens['character'], | |
| 328 'string': HaskellLexer.tokens['string'], | |
| 329 'escape': HaskellLexer.tokens['escape'] | |
| 330 } | |
| 331 | |
| 332 | |
| 333 class CryptolLexer(RegexLexer): | |
| 334 """ | |
| 335 FIXME: A Cryptol2 lexer based on the lexemes defined in the Haskell 98 Report. | |
| 336 | |
| 337 .. versionadded:: 2.0 | |
| 338 """ | |
| 339 name = 'Cryptol' | |
| 340 aliases = ['cryptol', 'cry'] | |
| 341 filenames = ['*.cry'] | |
| 342 mimetypes = ['text/x-cryptol'] | |
| 343 | |
| 344 reserved = ('Arith', 'Bit', 'Cmp', 'False', 'Inf', 'True', 'else', | |
| 345 'export', 'extern', 'fin', 'if', 'import', 'inf', 'lg2', | |
| 346 'max', 'min', 'module', 'newtype', 'pragma', 'property', | |
| 347 'then', 'type', 'where', 'width') | |
| 348 ascii = ('NUL', 'SOH', '[SE]TX', 'EOT', 'ENQ', 'ACK', | |
| 349 'BEL', 'BS', 'HT', 'LF', 'VT', 'FF', 'CR', 'S[OI]', 'DLE', | |
| 350 'DC[1-4]', 'NAK', 'SYN', 'ETB', 'CAN', | |
| 351 'EM', 'SUB', 'ESC', '[FGRU]S', 'SP', 'DEL') | |
| 352 | |
| 353 tokens = { | |
| 354 'root': [ | |
| 355 # Whitespace: | |
| 356 (r'\s+', Text), | |
| 357 # (r'--\s*|.*$', Comment.Doc), | |
| 358 (r'//.*$', Comment.Single), | |
| 359 (r'/\*', Comment.Multiline, 'comment'), | |
| 360 # Lexemes: | |
| 361 # Identifiers | |
| 362 (r'\bimport\b', Keyword.Reserved, 'import'), | |
| 363 (r'\bmodule\b', Keyword.Reserved, 'module'), | |
| 364 (r'\berror\b', Name.Exception), | |
| 365 (r'\b(%s)(?!\')\b' % '|'.join(reserved), Keyword.Reserved), | |
| 366 (r'^[_a-z][\w\']*', Name.Function), | |
| 367 (r"'?[_a-z][\w']*", Name), | |
| 368 (r"('')?[A-Z][\w\']*", Keyword.Type), | |
| 369 # Operators | |
| 370 (r'\\(?![:!#$%&*+.\\/<=>?@^|~-]+)', Name.Function), # lambda operator | |
| 371 (r'(<-|::|->|=>|=)(?![:!#$%&*+.\\/<=>?@^|~-]+)', Operator.Word), # specials | |
| 372 (r':[:!#$%&*+.\\/<=>?@^|~-]*', Keyword.Type), # Constructor operators | |
| 373 (r'[:!#$%&*+.\\/<=>?@^|~-]+', Operator), # Other operators | |
| 374 # Numbers | |
| 375 (r'\d+[eE][+-]?\d+', Number.Float), | |
| 376 (r'\d+\.\d+([eE][+-]?\d+)?', Number.Float), | |
| 377 (r'0[oO][0-7]+', Number.Oct), | |
| 378 (r'0[xX][\da-fA-F]+', Number.Hex), | |
| 379 (r'\d+', Number.Integer), | |
| 380 # Character/String Literals | |
| 381 (r"'", String.Char, 'character'), | |
| 382 (r'"', String, 'string'), | |
| 383 # Special | |
| 384 (r'\[\]', Keyword.Type), | |
| 385 (r'\(\)', Name.Builtin), | |
| 386 (r'[][(),;`{}]', Punctuation), | |
| 387 ], | |
| 388 'import': [ | |
| 389 # Import statements | |
| 390 (r'\s+', Text), | |
| 391 (r'"', String, 'string'), | |
| 392 # after "funclist" state | |
| 393 (r'\)', Punctuation, '#pop'), | |
| 394 (r'qualified\b', Keyword), | |
| 395 # import X as Y | |
| 396 (r'([A-Z][\w.]*)(\s+)(as)(\s+)([A-Z][\w.]*)', | |
| 397 bygroups(Name.Namespace, Text, Keyword, Text, Name), '#pop'), | |
| 398 # import X hiding (functions) | |
| 399 (r'([A-Z][\w.]*)(\s+)(hiding)(\s+)(\()', | |
| 400 bygroups(Name.Namespace, Text, Keyword, Text, Punctuation), 'funclist'), | |
| 401 # import X (functions) | |
| 402 (r'([A-Z][\w.]*)(\s+)(\()', | |
| 403 bygroups(Name.Namespace, Text, Punctuation), 'funclist'), | |
| 404 # import X | |
| 405 (r'[\w.]+', Name.Namespace, '#pop'), | |
| 406 ], | |
| 407 'module': [ | |
| 408 (r'\s+', Text), | |
| 409 (r'([A-Z][\w.]*)(\s+)(\()', | |
| 410 bygroups(Name.Namespace, Text, Punctuation), 'funclist'), | |
| 411 (r'[A-Z][\w.]*', Name.Namespace, '#pop'), | |
| 412 ], | |
| 413 'funclist': [ | |
| 414 (r'\s+', Text), | |
| 415 (r'[A-Z]\w*', Keyword.Type), | |
| 416 (r'(_[\w\']+|[a-z][\w\']*)', Name.Function), | |
| 417 # TODO: these don't match the comments in docs, remove. | |
| 418 #(r'--(?![!#$%&*+./<=>?@^|_~:\\]).*?$', Comment.Single), | |
| 419 #(r'{-', Comment.Multiline, 'comment'), | |
| 420 (r',', Punctuation), | |
| 421 (r'[:!#$%&*+.\\/<=>?@^|~-]+', Operator), | |
| 422 # (HACK, but it makes sense to push two instances, believe me) | |
| 423 (r'\(', Punctuation, ('funclist', 'funclist')), | |
| 424 (r'\)', Punctuation, '#pop:2'), | |
| 425 ], | |
| 426 'comment': [ | |
| 427 # Multiline Comments | |
| 428 (r'[^/*]+', Comment.Multiline), | |
| 429 (r'/\*', Comment.Multiline, '#push'), | |
| 430 (r'\*/', Comment.Multiline, '#pop'), | |
| 431 (r'[*/]', Comment.Multiline), | |
| 432 ], | |
| 433 'character': [ | |
| 434 # Allows multi-chars, incorrectly. | |
| 435 (r"[^\\']'", String.Char, '#pop'), | |
| 436 (r"\\", String.Escape, 'escape'), | |
| 437 ("'", String.Char, '#pop'), | |
| 438 ], | |
| 439 'string': [ | |
| 440 (r'[^\\"]+', String), | |
| 441 (r"\\", String.Escape, 'escape'), | |
| 442 ('"', String, '#pop'), | |
| 443 ], | |
| 444 'escape': [ | |
| 445 (r'[abfnrtv"\'&\\]', String.Escape, '#pop'), | |
| 446 (r'\^[][A-Z@^_]', String.Escape, '#pop'), | |
| 447 ('|'.join(ascii), String.Escape, '#pop'), | |
| 448 (r'o[0-7]+', String.Escape, '#pop'), | |
| 449 (r'x[\da-fA-F]+', String.Escape, '#pop'), | |
| 450 (r'\d+', String.Escape, '#pop'), | |
| 451 (r'\s+\\', String.Escape, '#pop'), | |
| 452 ], | |
| 453 } | |
| 454 | |
| 455 EXTRA_KEYWORDS = set(('join', 'split', 'reverse', 'transpose', 'width', | |
| 456 'length', 'tail', '<<', '>>', '<<<', '>>>', 'const', | |
| 457 'reg', 'par', 'seq', 'ASSERT', 'undefined', 'error', | |
| 458 'trace')) | |
| 459 | |
| 460 def get_tokens_unprocessed(self, text): | |
| 461 stack = ['root'] | |
| 462 for index, token, value in \ | |
| 463 RegexLexer.get_tokens_unprocessed(self, text, stack): | |
| 464 if token is Name and value in self.EXTRA_KEYWORDS: | |
| 465 yield index, Name.Builtin, value | |
| 466 else: | |
| 467 yield index, token, value | |
| 468 | |
| 469 | |
| 470 class LiterateLexer(Lexer): | |
| 471 """ | |
| 472 Base class for lexers of literate file formats based on LaTeX or Bird-style | |
| 473 (prefixing each code line with ">"). | |
| 474 | |
| 475 Additional options accepted: | |
| 476 | |
| 477 `litstyle` | |
| 478 If given, must be ``"bird"`` or ``"latex"``. If not given, the style | |
| 479 is autodetected: if the first non-whitespace character in the source | |
| 480 is a backslash or percent character, LaTeX is assumed, else Bird. | |
| 481 """ | |
| 482 | |
| 483 bird_re = re.compile(r'(>[ \t]*)(.*\n)') | |
| 484 | |
| 485 def __init__(self, baselexer, **options): | |
| 486 self.baselexer = baselexer | |
| 487 Lexer.__init__(self, **options) | |
| 488 | |
| 489 def get_tokens_unprocessed(self, text): | |
| 490 style = self.options.get('litstyle') | |
| 491 if style is None: | |
| 492 style = (text.lstrip()[0:1] in '%\\') and 'latex' or 'bird' | |
| 493 | |
| 494 code = '' | |
| 495 insertions = [] | |
| 496 if style == 'bird': | |
| 497 # bird-style | |
| 498 for match in line_re.finditer(text): | |
| 499 line = match.group() | |
| 500 m = self.bird_re.match(line) | |
| 501 if m: | |
| 502 insertions.append((len(code), | |
| 503 [(0, Comment.Special, m.group(1))])) | |
| 504 code += m.group(2) | |
| 505 else: | |
| 506 insertions.append((len(code), [(0, Text, line)])) | |
| 507 else: | |
| 508 # latex-style | |
| 509 from pygments.lexers.markup import TexLexer | |
| 510 lxlexer = TexLexer(**self.options) | |
| 511 codelines = 0 | |
| 512 latex = '' | |
| 513 for match in line_re.finditer(text): | |
| 514 line = match.group() | |
| 515 if codelines: | |
| 516 if line.lstrip().startswith('\\end{code}'): | |
| 517 codelines = 0 | |
| 518 latex += line | |
| 519 else: | |
| 520 code += line | |
| 521 elif line.lstrip().startswith('\\begin{code}'): | |
| 522 codelines = 1 | |
| 523 latex += line | |
| 524 insertions.append((len(code), | |
| 525 list(lxlexer.get_tokens_unprocessed(latex)))) | |
| 526 latex = '' | |
| 527 else: | |
| 528 latex += line | |
| 529 insertions.append((len(code), | |
| 530 list(lxlexer.get_tokens_unprocessed(latex)))) | |
| 531 for item in do_insertions(insertions, self.baselexer.get_tokens_unprocessed(code)): | |
| 532 yield item | |
| 533 | |
| 534 | |
| 535 class LiterateHaskellLexer(LiterateLexer): | |
| 536 """ | |
| 537 For Literate Haskell (Bird-style or LaTeX) source. | |
| 538 | |
| 539 Additional options accepted: | |
| 540 | |
| 541 `litstyle` | |
| 542 If given, must be ``"bird"`` or ``"latex"``. If not given, the style | |
| 543 is autodetected: if the first non-whitespace character in the source | |
| 544 is a backslash or percent character, LaTeX is assumed, else Bird. | |
| 545 | |
| 546 .. versionadded:: 0.9 | |
| 547 """ | |
| 548 name = 'Literate Haskell' | |
| 549 aliases = ['lhs', 'literate-haskell', 'lhaskell'] | |
| 550 filenames = ['*.lhs'] | |
| 551 mimetypes = ['text/x-literate-haskell'] | |
| 552 | |
| 553 def __init__(self, **options): | |
| 554 hslexer = HaskellLexer(**options) | |
| 555 LiterateLexer.__init__(self, hslexer, **options) | |
| 556 | |
| 557 | |
| 558 class LiterateIdrisLexer(LiterateLexer): | |
| 559 """ | |
| 560 For Literate Idris (Bird-style or LaTeX) source. | |
| 561 | |
| 562 Additional options accepted: | |
| 563 | |
| 564 `litstyle` | |
| 565 If given, must be ``"bird"`` or ``"latex"``. If not given, the style | |
| 566 is autodetected: if the first non-whitespace character in the source | |
| 567 is a backslash or percent character, LaTeX is assumed, else Bird. | |
| 568 | |
| 569 .. versionadded:: 2.0 | |
| 570 """ | |
| 571 name = 'Literate Idris' | |
| 572 aliases = ['lidr', 'literate-idris', 'lidris'] | |
| 573 filenames = ['*.lidr'] | |
| 574 mimetypes = ['text/x-literate-idris'] | |
| 575 | |
| 576 def __init__(self, **options): | |
| 577 hslexer = IdrisLexer(**options) | |
| 578 LiterateLexer.__init__(self, hslexer, **options) | |
| 579 | |
| 580 | |
| 581 class LiterateAgdaLexer(LiterateLexer): | |
| 582 """ | |
| 583 For Literate Agda source. | |
| 584 | |
| 585 Additional options accepted: | |
| 586 | |
| 587 `litstyle` | |
| 588 If given, must be ``"bird"`` or ``"latex"``. If not given, the style | |
| 589 is autodetected: if the first non-whitespace character in the source | |
| 590 is a backslash or percent character, LaTeX is assumed, else Bird. | |
| 591 | |
| 592 .. versionadded:: 2.0 | |
| 593 """ | |
| 594 name = 'Literate Agda' | |
| 595 aliases = ['lagda', 'literate-agda'] | |
| 596 filenames = ['*.lagda'] | |
| 597 mimetypes = ['text/x-literate-agda'] | |
| 598 | |
| 599 def __init__(self, **options): | |
| 600 agdalexer = AgdaLexer(**options) | |
| 601 LiterateLexer.__init__(self, agdalexer, litstyle='latex', **options) | |
| 602 | |
| 603 | |
| 604 class LiterateCryptolLexer(LiterateLexer): | |
| 605 """ | |
| 606 For Literate Cryptol (Bird-style or LaTeX) source. | |
| 607 | |
| 608 Additional options accepted: | |
| 609 | |
| 610 `litstyle` | |
| 611 If given, must be ``"bird"`` or ``"latex"``. If not given, the style | |
| 612 is autodetected: if the first non-whitespace character in the source | |
| 613 is a backslash or percent character, LaTeX is assumed, else Bird. | |
| 614 | |
| 615 .. versionadded:: 2.0 | |
| 616 """ | |
| 617 name = 'Literate Cryptol' | |
| 618 aliases = ['lcry', 'literate-cryptol', 'lcryptol'] | |
| 619 filenames = ['*.lcry'] | |
| 620 mimetypes = ['text/x-literate-cryptol'] | |
| 621 | |
| 622 def __init__(self, **options): | |
| 623 crylexer = CryptolLexer(**options) | |
| 624 LiterateLexer.__init__(self, crylexer, **options) | |
| 625 | |
| 626 | |
| 627 class KokaLexer(RegexLexer): | |
| 628 """ | |
| 629 Lexer for the `Koka <http://koka.codeplex.com>`_ | |
| 630 language. | |
| 631 | |
| 632 .. versionadded:: 1.6 | |
| 633 """ | |
| 634 | |
| 635 name = 'Koka' | |
| 636 aliases = ['koka'] | |
| 637 filenames = ['*.kk', '*.kki'] | |
| 638 mimetypes = ['text/x-koka'] | |
| 639 | |
| 640 keywords = [ | |
| 641 'infix', 'infixr', 'infixl', | |
| 642 'type', 'cotype', 'rectype', 'alias', | |
| 643 'struct', 'con', | |
| 644 'fun', 'function', 'val', 'var', | |
| 645 'external', | |
| 646 'if', 'then', 'else', 'elif', 'return', 'match', | |
| 647 'private', 'public', 'private', | |
| 648 'module', 'import', 'as', | |
| 649 'include', 'inline', | |
| 650 'rec', | |
| 651 'try', 'yield', 'enum', | |
| 652 'interface', 'instance', | |
| 653 ] | |
| 654 | |
| 655 # keywords that are followed by a type | |
| 656 typeStartKeywords = [ | |
| 657 'type', 'cotype', 'rectype', 'alias', 'struct', 'enum', | |
| 658 ] | |
| 659 | |
| 660 # keywords valid in a type | |
| 661 typekeywords = [ | |
| 662 'forall', 'exists', 'some', 'with', | |
| 663 ] | |
| 664 | |
| 665 # builtin names and special names | |
| 666 builtin = [ | |
| 667 'for', 'while', 'repeat', | |
| 668 'foreach', 'foreach-indexed', | |
| 669 'error', 'catch', 'finally', | |
| 670 'cs', 'js', 'file', 'ref', 'assigned', | |
| 671 ] | |
| 672 | |
| 673 # symbols that can be in an operator | |
| 674 symbols = r'[$%&*+@!/\\^~=.:\-?|<>]+' | |
| 675 | |
| 676 # symbol boundary: an operator keyword should not be followed by any of these | |
| 677 sboundary = '(?!'+symbols+')' | |
| 678 | |
| 679 # name boundary: a keyword should not be followed by any of these | |
| 680 boundary = '(?![\w/])' | |
| 681 | |
| 682 # koka token abstractions | |
| 683 tokenType = Name.Attribute | |
| 684 tokenTypeDef = Name.Class | |
| 685 tokenConstructor = Generic.Emph | |
| 686 | |
| 687 # main lexer | |
| 688 tokens = { | |
| 689 'root': [ | |
| 690 include('whitespace'), | |
| 691 | |
| 692 # go into type mode | |
| 693 (r'::?' + sboundary, tokenType, 'type'), | |
| 694 (r'(alias)(\s+)([a-z]\w*)?', bygroups(Keyword, Text, tokenTypeDef), | |
| 695 'alias-type'), | |
| 696 (r'(struct)(\s+)([a-z]\w*)?', bygroups(Keyword, Text, tokenTypeDef), | |
| 697 'struct-type'), | |
| 698 ((r'(%s)' % '|'.join(typeStartKeywords)) + | |
| 699 r'(\s+)([a-z]\w*)?', bygroups(Keyword, Text, tokenTypeDef), | |
| 700 'type'), | |
| 701 | |
| 702 # special sequences of tokens (we use ?: for non-capturing group as | |
| 703 # required by 'bygroups') | |
| 704 (r'(module)(\s+)(interface\s+)?((?:[a-z]\w*/)*[a-z]\w*)', | |
| 705 bygroups(Keyword, Text, Keyword, Name.Namespace)), | |
| 706 (r'(import)(\s+)((?:[a-z]\w*/)*[a-z]\w*)' | |
| 707 r'(?:(\s*)(=)(\s*)((?:qualified\s*)?)' | |
| 708 r'((?:[a-z]\w*/)*[a-z]\w*))?', | |
| 709 bygroups(Keyword, Text, Name.Namespace, Text, Keyword, Text, | |
| 710 Keyword, Name.Namespace)), | |
| 711 | |
| 712 (r'(^(?:(?:public|private)\s*)?(?:function|fun|val))' | |
| 713 r'(\s+)([a-z]\w*|\((?:' + symbols + r'|/)\))', | |
| 714 bygroups(Keyword, Text, Name.Function)), | |
| 715 (r'(^(?:(?:public|private)\s*)?external)(\s+)(inline\s+)?' | |
| 716 r'([a-z]\w*|\((?:' + symbols + r'|/)\))', | |
| 717 bygroups(Keyword, Text, Keyword, Name.Function)), | |
| 718 | |
| 719 # keywords | |
| 720 (r'(%s)' % '|'.join(typekeywords) + boundary, Keyword.Type), | |
| 721 (r'(%s)' % '|'.join(keywords) + boundary, Keyword), | |
| 722 (r'(%s)' % '|'.join(builtin) + boundary, Keyword.Pseudo), | |
| 723 (r'::?|:=|\->|[=.]' + sboundary, Keyword), | |
| 724 | |
| 725 # names | |
| 726 (r'((?:[a-z]\w*/)*)([A-Z]\w*)', | |
| 727 bygroups(Name.Namespace, tokenConstructor)), | |
| 728 (r'((?:[a-z]\w*/)*)([a-z]\w*)', bygroups(Name.Namespace, Name)), | |
| 729 (r'((?:[a-z]\w*/)*)(\((?:' + symbols + r'|/)\))', | |
| 730 bygroups(Name.Namespace, Name)), | |
| 731 (r'_\w*', Name.Variable), | |
| 732 | |
| 733 # literal string | |
| 734 (r'@"', String.Double, 'litstring'), | |
| 735 | |
| 736 # operators | |
| 737 (symbols + "|/(?![*/])", Operator), | |
| 738 (r'`', Operator), | |
| 739 (r'[{}()\[\];,]', Punctuation), | |
| 740 | |
| 741 # literals. No check for literal characters with len > 1 | |
| 742 (r'[0-9]+\.[0-9]+([eE][\-+]?[0-9]+)?', Number.Float), | |
| 743 (r'0[xX][0-9a-fA-F]+', Number.Hex), | |
| 744 (r'[0-9]+', Number.Integer), | |
| 745 | |
| 746 (r"'", String.Char, 'char'), | |
| 747 (r'"', String.Double, 'string'), | |
| 748 ], | |
| 749 | |
| 750 # type started by alias | |
| 751 'alias-type': [ | |
| 752 (r'=', Keyword), | |
| 753 include('type') | |
| 754 ], | |
| 755 | |
| 756 # type started by struct | |
| 757 'struct-type': [ | |
| 758 (r'(?=\((?!,*\)))', Punctuation, '#pop'), | |
| 759 include('type') | |
| 760 ], | |
| 761 | |
| 762 # type started by colon | |
| 763 'type': [ | |
| 764 (r'[(\[<]', tokenType, 'type-nested'), | |
| 765 include('type-content') | |
| 766 ], | |
| 767 | |
| 768 # type nested in brackets: can contain parameters, comma etc. | |
| 769 'type-nested': [ | |
| 770 (r'[)\]>]', tokenType, '#pop'), | |
| 771 (r'[(\[<]', tokenType, 'type-nested'), | |
| 772 (r',', tokenType), | |
| 773 (r'([a-z]\w*)(\s*)(:)(?!:)', | |
| 774 bygroups(Name, Text, tokenType)), # parameter name | |
| 775 include('type-content') | |
| 776 ], | |
| 777 | |
| 778 # shared contents of a type | |
| 779 'type-content': [ | |
| 780 include('whitespace'), | |
| 781 | |
| 782 # keywords | |
| 783 (r'(%s)' % '|'.join(typekeywords) + boundary, Keyword), | |
| 784 (r'(?=((%s)' % '|'.join(keywords) + boundary + '))', | |
| 785 Keyword, '#pop'), # need to match because names overlap... | |
| 786 | |
| 787 # kinds | |
| 788 (r'[EPHVX]' + boundary, tokenType), | |
| 789 | |
| 790 # type names | |
| 791 (r'[a-z][0-9]*(?![\w/])', tokenType), | |
| 792 (r'_\w*', tokenType.Variable), # Generic.Emph | |
| 793 (r'((?:[a-z]\w*/)*)([A-Z]\w*)', | |
| 794 bygroups(Name.Namespace, tokenType)), | |
| 795 (r'((?:[a-z]\w*/)*)([a-z]\w+)', | |
| 796 bygroups(Name.Namespace, tokenType)), | |
| 797 | |
| 798 # type keyword operators | |
| 799 (r'::|->|[.:|]', tokenType), | |
| 800 | |
| 801 # catchall | |
| 802 default('#pop') | |
| 803 ], | |
| 804 | |
| 805 # comments and literals | |
| 806 'whitespace': [ | |
| 807 (r'\n\s*#.*$', Comment.Preproc), | |
| 808 (r'\s+', Text), | |
| 809 (r'/\*', Comment.Multiline, 'comment'), | |
| 810 (r'//.*$', Comment.Single) | |
| 811 ], | |
| 812 'comment': [ | |
| 813 (r'[^/*]+', Comment.Multiline), | |
| 814 (r'/\*', Comment.Multiline, '#push'), | |
| 815 (r'\*/', Comment.Multiline, '#pop'), | |
| 816 (r'[*/]', Comment.Multiline), | |
| 817 ], | |
| 818 'litstring': [ | |
| 819 (r'[^"]+', String.Double), | |
| 820 (r'""', String.Escape), | |
| 821 (r'"', String.Double, '#pop'), | |
| 822 ], | |
| 823 'string': [ | |
| 824 (r'[^\\"\n]+', String.Double), | |
| 825 include('escape-sequence'), | |
| 826 (r'["\n]', String.Double, '#pop'), | |
| 827 ], | |
| 828 'char': [ | |
| 829 (r'[^\\\'\n]+', String.Char), | |
| 830 include('escape-sequence'), | |
| 831 (r'[\'\n]', String.Char, '#pop'), | |
| 832 ], | |
| 833 'escape-sequence': [ | |
| 834 (r'\\[nrt\\"\']', String.Escape), | |
| 835 (r'\\x[0-9a-fA-F]{2}', String.Escape), | |
| 836 (r'\\u[0-9a-fA-F]{4}', String.Escape), | |
| 837 # Yes, \U literals are 6 hex digits. | |
| 838 (r'\\U[0-9a-fA-F]{6}', String.Escape) | |
| 839 ] | |
| 840 } |
