Mercurial Repositories > eric / file comparison
comparison: eric6/ThirdParty/Pygments/pygments/lexers/python.py
eric6/ThirdParty/Pygments/pygments/lexers/python.py
- changeset 6942
- 2602857055c5
- parent 6651
- e8f3b5568b21
- child 7547
- 21b0534faebc
equal
deleted
inserted
replaced
| 6941:f99d60d6b59b | 6942:2602857055c5 |
|---|---|
| 1 # -*- coding: utf-8 -*- | |
| 2 """ | |
| 3 pygments.lexers.python | |
| 4 ~~~~~~~~~~~~~~~~~~~~~~ | |
| 5 | |
| 6 Lexers for Python and related languages. | |
| 7 | |
| 8 :copyright: Copyright 2006-2017 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, include, bygroups, using, \ | |
| 15 default, words, combined, do_insertions | |
| 16 from pygments.util import get_bool_opt, shebang_matches | |
| 17 from pygments.token import Text, Comment, Operator, Keyword, Name, String, \ | |
| 18 Number, Punctuation, Generic, Other, Error | |
| 19 from pygments import unistring as uni | |
| 20 | |
| 21 __all__ = ['PythonLexer', 'PythonConsoleLexer', 'PythonTracebackLexer', | |
| 22 'Python3Lexer', 'Python3TracebackLexer', 'CythonLexer', | |
| 23 'DgLexer', 'NumPyLexer'] | |
| 24 | |
| 25 line_re = re.compile('.*?\n') | |
| 26 | |
| 27 | |
| 28 class PythonLexer(RegexLexer): | |
| 29 """ | |
| 30 For `Python <http://www.python.org>`_ source code. | |
| 31 """ | |
| 32 | |
| 33 name = 'Python' | |
| 34 aliases = ['python', 'py', 'sage'] | |
| 35 filenames = ['*.py', '*.pyw', '*.sc', 'SConstruct', 'SConscript', '*.tac', '*.sage'] | |
| 36 mimetypes = ['text/x-python', 'application/x-python'] | |
| 37 | |
| 38 def innerstring_rules(ttype): | |
| 39 return [ | |
| 40 # the old style '%s' % (...) string formatting | |
| 41 (r'%(\(\w+\))?[-#0 +]*([0-9]+|[*])?(\.([0-9]+|[*]))?' | |
| 42 '[hlL]?[E-GXc-giorsux%]', String.Interpol), | |
| 43 # backslashes, quotes and formatting signs must be parsed one at a time | |
| 44 (r'[^\\\'"%\n]+', ttype), | |
| 45 (r'[\'"\\]', ttype), | |
| 46 # unhandled string formatting sign | |
| 47 (r'%', ttype), | |
| 48 # newlines are an error (use "nl" state) | |
| 49 ] | |
| 50 | |
| 51 tokens = { | |
| 52 'root': [ | |
| 53 (r'\n', Text), | |
| 54 (r'^(\s*)([rRuUbB]{,2})("""(?:.|\n)*?""")', | |
| 55 bygroups(Text, String.Affix, String.Doc)), | |
| 56 (r"^(\s*)([rRuUbB]{,2})('''(?:.|\n)*?''')", | |
| 57 bygroups(Text, String.Affix, String.Doc)), | |
| 58 (r'[^\S\n]+', Text), | |
| 59 (r'\A#!.+$', Comment.Hashbang), | |
| 60 (r'#.*$', Comment.Single), | |
| 61 (r'[]{}:(),;[]', Punctuation), | |
| 62 (r'\\\n', Text), | |
| 63 (r'\\', Text), | |
| 64 (r'(in|is|and|or|not)\b', Operator.Word), | |
| 65 (r'!=|==|<<|>>|[-~+/*%=<>&^|.]', Operator), | |
| 66 include('keywords'), | |
| 67 (r'(def)((?:\s|\\\s)+)', bygroups(Keyword, Text), 'funcname'), | |
| 68 (r'(class)((?:\s|\\\s)+)', bygroups(Keyword, Text), 'classname'), | |
| 69 (r'(from)((?:\s|\\\s)+)', bygroups(Keyword.Namespace, Text), | |
| 70 'fromimport'), | |
| 71 (r'(import)((?:\s|\\\s)+)', bygroups(Keyword.Namespace, Text), | |
| 72 'import'), | |
| 73 include('builtins'), | |
| 74 include('magicfuncs'), | |
| 75 include('magicvars'), | |
| 76 include('backtick'), | |
| 77 ('([rR]|[uUbB][rR]|[rR][uUbB])(""")', | |
| 78 bygroups(String.Affix, String.Double), 'tdqs'), | |
| 79 ("([rR]|[uUbB][rR]|[rR][uUbB])(''')", | |
| 80 bygroups(String.Affix, String.Single), 'tsqs'), | |
| 81 ('([rR]|[uUbB][rR]|[rR][uUbB])(")', | |
| 82 bygroups(String.Affix, String.Double), 'dqs'), | |
| 83 ("([rR]|[uUbB][rR]|[rR][uUbB])(')", | |
| 84 bygroups(String.Affix, String.Single), 'sqs'), | |
| 85 ('([uUbB]?)(""")', bygroups(String.Affix, String.Double), | |
| 86 combined('stringescape', 'tdqs')), | |
| 87 ("([uUbB]?)(''')", bygroups(String.Affix, String.Single), | |
| 88 combined('stringescape', 'tsqs')), | |
| 89 ('([uUbB]?)(")', bygroups(String.Affix, String.Double), | |
| 90 combined('stringescape', 'dqs')), | |
| 91 ("([uUbB]?)(')", bygroups(String.Affix, String.Single), | |
| 92 combined('stringescape', 'sqs')), | |
| 93 include('name'), | |
| 94 include('numbers'), | |
| 95 ], | |
| 96 'keywords': [ | |
| 97 (words(( | |
| 98 'assert', 'break', 'continue', 'del', 'elif', 'else', 'except', | |
| 99 'exec', 'finally', 'for', 'global', 'if', 'lambda', 'pass', | |
| 100 'print', 'raise', 'return', 'try', 'while', 'yield', | |
| 101 'yield from', 'as', 'with'), suffix=r'\b'), | |
| 102 Keyword), | |
| 103 ], | |
| 104 'builtins': [ | |
| 105 (words(( | |
| 106 '__import__', 'abs', 'all', 'any', 'apply', 'basestring', 'bin', | |
| 107 'bool', 'buffer', 'bytearray', 'bytes', 'callable', 'chr', 'classmethod', | |
| 108 'cmp', 'coerce', 'compile', 'complex', 'delattr', 'dict', 'dir', 'divmod', | |
| 109 'enumerate', 'eval', 'execfile', 'exit', 'file', 'filter', 'float', | |
| 110 'frozenset', 'getattr', 'globals', 'hasattr', 'hash', 'hex', 'id', | |
| 111 'input', 'int', 'intern', 'isinstance', 'issubclass', 'iter', 'len', | |
| 112 'list', 'locals', 'long', 'map', 'max', 'min', 'next', 'object', | |
| 113 'oct', 'open', 'ord', 'pow', 'property', 'range', 'raw_input', 'reduce', | |
| 114 'reload', 'repr', 'reversed', 'round', 'set', 'setattr', 'slice', | |
| 115 'sorted', 'staticmethod', 'str', 'sum', 'super', 'tuple', 'type', | |
| 116 'unichr', 'unicode', 'vars', 'xrange', 'zip'), | |
| 117 prefix=r'(?<!\.)', suffix=r'\b'), | |
| 118 Name.Builtin), | |
| 119 (r'(?<!\.)(self|None|Ellipsis|NotImplemented|False|True|cls' | |
| 120 r')\b', Name.Builtin.Pseudo), | |
| 121 (words(( | |
| 122 'ArithmeticError', 'AssertionError', 'AttributeError', | |
| 123 'BaseException', 'DeprecationWarning', 'EOFError', 'EnvironmentError', | |
| 124 'Exception', 'FloatingPointError', 'FutureWarning', 'GeneratorExit', | |
| 125 'IOError', 'ImportError', 'ImportWarning', 'IndentationError', | |
| 126 'IndexError', 'KeyError', 'KeyboardInterrupt', 'LookupError', | |
| 127 'MemoryError', 'ModuleNotFoundError', 'NameError', 'NotImplemented', 'NotImplementedError', | |
| 128 'OSError', 'OverflowError', 'OverflowWarning', 'PendingDeprecationWarning', | |
| 129 'RecursionError', 'ReferenceError', 'RuntimeError', 'RuntimeWarning', 'StandardError', | |
| 130 'StopIteration', 'StopAsyncIteration', 'SyntaxError', 'SyntaxWarning', 'SystemError', | |
| 131 'SystemExit', 'TabError', 'TypeError', 'UnboundLocalError', | |
| 132 'UnicodeDecodeError', 'UnicodeEncodeError', 'UnicodeError', | |
| 133 'UnicodeTranslateError', 'UnicodeWarning', 'UserWarning', | |
| 134 'ValueError', 'VMSError', 'Warning', 'WindowsError', | |
| 135 'ZeroDivisionError'), prefix=r'(?<!\.)', suffix=r'\b'), | |
| 136 Name.Exception), | |
| 137 ], | |
| 138 'magicfuncs': [ | |
| 139 (words(( | |
| 140 '__abs__', '__add__', '__and__', '__call__', '__cmp__', '__coerce__', | |
| 141 '__complex__', '__contains__', '__del__', '__delattr__', '__delete__', | |
| 142 '__delitem__', '__delslice__', '__div__', '__divmod__', '__enter__', | |
| 143 '__eq__', '__exit__', '__float__', '__floordiv__', '__ge__', '__get__', | |
| 144 '__getattr__', '__getattribute__', '__getitem__', '__getslice__', '__gt__', | |
| 145 '__hash__', '__hex__', '__iadd__', '__iand__', '__idiv__', '__ifloordiv__', | |
| 146 '__ilshift__', '__imod__', '__imul__', '__index__', '__init__', | |
| 147 '__instancecheck__', '__int__', '__invert__', '__iop__', '__ior__', | |
| 148 '__ipow__', '__irshift__', '__isub__', '__iter__', '__itruediv__', | |
| 149 '__ixor__', '__le__', '__len__', '__long__', '__lshift__', '__lt__', | |
| 150 '__missing__', '__mod__', '__mul__', '__ne__', '__neg__', '__new__', | |
| 151 '__nonzero__', '__oct__', '__op__', '__or__', '__pos__', '__pow__', | |
| 152 '__radd__', '__rand__', '__rcmp__', '__rdiv__', '__rdivmod__', '__repr__', | |
| 153 '__reversed__', '__rfloordiv__', '__rlshift__', '__rmod__', '__rmul__', | |
| 154 '__rop__', '__ror__', '__rpow__', '__rrshift__', '__rshift__', '__rsub__', | |
| 155 '__rtruediv__', '__rxor__', '__set__', '__setattr__', '__setitem__', | |
| 156 '__setslice__', '__str__', '__sub__', '__subclasscheck__', '__truediv__', | |
| 157 '__unicode__', '__xor__'), suffix=r'\b'), | |
| 158 Name.Function.Magic), | |
| 159 ], | |
| 160 'magicvars': [ | |
| 161 (words(( | |
| 162 '__bases__', '__class__', '__closure__', '__code__', '__defaults__', | |
| 163 '__dict__', '__doc__', '__file__', '__func__', '__globals__', | |
| 164 '__metaclass__', '__module__', '__mro__', '__name__', '__self__', | |
| 165 '__slots__', '__weakref__'), | |
| 166 suffix=r'\b'), | |
| 167 Name.Variable.Magic), | |
| 168 ], | |
| 169 'numbers': [ | |
| 170 (r'(\d+\.\d*|\d*\.\d+)([eE][+-]?[0-9]+)?j?', Number.Float), | |
| 171 (r'\d+[eE][+-]?[0-9]+j?', Number.Float), | |
| 172 (r'0[0-7]+j?', Number.Oct), | |
| 173 (r'0[bB][01]+', Number.Bin), | |
| 174 (r'0[xX][a-fA-F0-9]+', Number.Hex), | |
| 175 (r'\d+L', Number.Integer.Long), | |
| 176 (r'\d+j?', Number.Integer) | |
| 177 ], | |
| 178 'backtick': [ | |
| 179 ('`.*?`', String.Backtick), | |
| 180 ], | |
| 181 'name': [ | |
| 182 (r'@[\w.]+', Name.Decorator), | |
| 183 (r'[a-zA-Z_]\w*', Name), | |
| 184 ], | |
| 185 'funcname': [ | |
| 186 include('magicfuncs'), | |
| 187 (r'[a-zA-Z_]\w*', Name.Function, '#pop'), | |
| 188 default('#pop'), | |
| 189 ], | |
| 190 'classname': [ | |
| 191 (r'[a-zA-Z_]\w*', Name.Class, '#pop') | |
| 192 ], | |
| 193 'import': [ | |
| 194 (r'(?:[ \t]|\\\n)+', Text), | |
| 195 (r'as\b', Keyword.Namespace), | |
| 196 (r',', Operator), | |
| 197 (r'[a-zA-Z_][\w.]*', Name.Namespace), | |
| 198 default('#pop') # all else: go back | |
| 199 ], | |
| 200 'fromimport': [ | |
| 201 (r'(?:[ \t]|\\\n)+', Text), | |
| 202 (r'import\b', Keyword.Namespace, '#pop'), | |
| 203 # if None occurs here, it's "raise x from None", since None can | |
| 204 # never be a module name | |
| 205 (r'None\b', Name.Builtin.Pseudo, '#pop'), | |
| 206 # sadly, in "raise x from y" y will be highlighted as namespace too | |
| 207 (r'[a-zA-Z_.][\w.]*', Name.Namespace), | |
| 208 # anything else here also means "raise x from y" and is therefore | |
| 209 # not an error | |
| 210 default('#pop'), | |
| 211 ], | |
| 212 'stringescape': [ | |
| 213 (r'\\([\\abfnrtv"\']|\n|N\{.*?\}|u[a-fA-F0-9]{4}|' | |
| 214 r'U[a-fA-F0-9]{8}|x[a-fA-F0-9]{2}|[0-7]{1,3})', String.Escape) | |
| 215 ], | |
| 216 'strings-single': innerstring_rules(String.Single), | |
| 217 'strings-double': innerstring_rules(String.Double), | |
| 218 'dqs': [ | |
| 219 (r'"', String.Double, '#pop'), | |
| 220 (r'\\\\|\\"|\\\n', String.Escape), # included here for raw strings | |
| 221 include('strings-double') | |
| 222 ], | |
| 223 'sqs': [ | |
| 224 (r"'", String.Single, '#pop'), | |
| 225 (r"\\\\|\\'|\\\n", String.Escape), # included here for raw strings | |
| 226 include('strings-single') | |
| 227 ], | |
| 228 'tdqs': [ | |
| 229 (r'"""', String.Double, '#pop'), | |
| 230 include('strings-double'), | |
| 231 (r'\n', String.Double) | |
| 232 ], | |
| 233 'tsqs': [ | |
| 234 (r"'''", String.Single, '#pop'), | |
| 235 include('strings-single'), | |
| 236 (r'\n', String.Single) | |
| 237 ], | |
| 238 } | |
| 239 | |
| 240 def analyse_text(text): | |
| 241 return shebang_matches(text, r'pythonw?(2(\.\d)?)?') or \ | |
| 242 'import ' in text[:1000] | |
| 243 | |
| 244 | |
| 245 class Python3Lexer(RegexLexer): | |
| 246 """ | |
| 247 For `Python <http://www.python.org>`_ source code (version 3.0). | |
| 248 | |
| 249 .. versionadded:: 0.10 | |
| 250 """ | |
| 251 | |
| 252 name = 'Python 3' | |
| 253 aliases = ['python3', 'py3'] | |
| 254 filenames = [] # Nothing until Python 3 gets widespread | |
| 255 mimetypes = ['text/x-python3', 'application/x-python3'] | |
| 256 | |
| 257 flags = re.MULTILINE | re.UNICODE | |
| 258 | |
| 259 uni_name = "[%s][%s]*" % (uni.xid_start, uni.xid_continue) | |
| 260 | |
| 261 def innerstring_rules(ttype): | |
| 262 return [ | |
| 263 # the old style '%s' % (...) string formatting (still valid in Py3) | |
| 264 (r'%(\(\w+\))?[-#0 +]*([0-9]+|[*])?(\.([0-9]+|[*]))?' | |
| 265 '[hlL]?[E-GXc-giorsaux%]', String.Interpol), | |
| 266 # the new style '{}'.format(...) string formatting | |
| 267 (r'\{' | |
| 268 r'((\w+)((\.\w+)|(\[[^\]]+\]))*)?' # field name | |
| 269 r'(\![sra])?' # conversion | |
| 270 r'(\:(.?[<>=\^])?[-+ ]?#?0?(\d+)?,?(\.\d+)?[E-GXb-gnosx%]?)?' | |
| 271 r'\}', String.Interpol), | |
| 272 | |
| 273 # backslashes, quotes and formatting signs must be parsed one at a time | |
| 274 (r'[^\\\'"%{\n]+', ttype), | |
| 275 (r'[\'"\\]', ttype), | |
| 276 # unhandled string formatting sign | |
| 277 (r'%|(\{{1,2})', ttype) | |
| 278 # newlines are an error (use "nl" state) | |
| 279 ] | |
| 280 | |
| 281 tokens = PythonLexer.tokens.copy() | |
| 282 tokens['keywords'] = [ | |
| 283 (words(( | |
| 284 'assert', 'async', 'await', 'break', 'continue', 'del', 'elif', | |
| 285 'else', 'except', 'finally', 'for', 'global', 'if', 'lambda', 'pass', | |
| 286 'raise', 'nonlocal', 'return', 'try', 'while', 'yield', 'yield from', | |
| 287 'as', 'with'), suffix=r'\b'), | |
| 288 Keyword), | |
| 289 (words(( | |
| 290 'True', 'False', 'None'), suffix=r'\b'), | |
| 291 Keyword.Constant), | |
| 292 ] | |
| 293 tokens['builtins'] = [ | |
| 294 (words(( | |
| 295 '__import__', 'abs', 'all', 'any', 'bin', 'bool', 'bytearray', 'bytes', | |
| 296 'chr', 'classmethod', 'cmp', 'compile', 'complex', 'delattr', 'dict', | |
| 297 'dir', 'divmod', 'enumerate', 'eval', 'filter', 'float', 'format', | |
| 298 'frozenset', 'getattr', 'globals', 'hasattr', 'hash', 'hex', 'id', | |
| 299 'input', 'int', 'isinstance', 'issubclass', 'iter', 'len', 'list', | |
| 300 'locals', 'map', 'max', 'memoryview', 'min', 'next', 'object', 'oct', | |
| 301 'open', 'ord', 'pow', 'print', 'property', 'range', 'repr', 'reversed', | |
| 302 'round', 'set', 'setattr', 'slice', 'sorted', 'staticmethod', 'str', | |
| 303 'sum', 'super', 'tuple', 'type', 'vars', 'zip'), prefix=r'(?<!\.)', | |
| 304 suffix=r'\b'), | |
| 305 Name.Builtin), | |
| 306 (r'(?<!\.)(self|Ellipsis|NotImplemented|cls)\b', Name.Builtin.Pseudo), | |
| 307 (words(( | |
| 308 'ArithmeticError', 'AssertionError', 'AttributeError', | |
| 309 'BaseException', 'BufferError', 'BytesWarning', 'DeprecationWarning', | |
| 310 'EOFError', 'EnvironmentError', 'Exception', 'FloatingPointError', | |
| 311 'FutureWarning', 'GeneratorExit', 'IOError', 'ImportError', | |
| 312 'ImportWarning', 'IndentationError', 'IndexError', 'KeyError', | |
| 313 'KeyboardInterrupt', 'LookupError', 'MemoryError', 'NameError', | |
| 314 'NotImplementedError', 'OSError', 'OverflowError', | |
| 315 'PendingDeprecationWarning', 'ReferenceError', 'ResourceWarning', | |
| 316 'RuntimeError', 'RuntimeWarning', 'StopIteration', | |
| 317 'SyntaxError', 'SyntaxWarning', 'SystemError', 'SystemExit', 'TabError', | |
| 318 'TypeError', 'UnboundLocalError', 'UnicodeDecodeError', | |
| 319 'UnicodeEncodeError', 'UnicodeError', 'UnicodeTranslateError', | |
| 320 'UnicodeWarning', 'UserWarning', 'ValueError', 'VMSError', 'Warning', | |
| 321 'WindowsError', 'ZeroDivisionError', | |
| 322 # new builtin exceptions from PEP 3151 | |
| 323 'BlockingIOError', 'ChildProcessError', 'ConnectionError', | |
| 324 'BrokenPipeError', 'ConnectionAbortedError', 'ConnectionRefusedError', | |
| 325 'ConnectionResetError', 'FileExistsError', 'FileNotFoundError', | |
| 326 'InterruptedError', 'IsADirectoryError', 'NotADirectoryError', | |
| 327 'PermissionError', 'ProcessLookupError', 'TimeoutError'), | |
| 328 prefix=r'(?<!\.)', suffix=r'\b'), | |
| 329 Name.Exception), | |
| 330 ] | |
| 331 tokens['magicfuncs'] = [ | |
| 332 (words(( | |
| 333 '__abs__', '__add__', '__aenter__', '__aexit__', '__aiter__', '__and__', | |
| 334 '__anext__', '__await__', '__bool__', '__bytes__', '__call__', | |
| 335 '__complex__', '__contains__', '__del__', '__delattr__', '__delete__', | |
| 336 '__delitem__', '__dir__', '__divmod__', '__enter__', '__eq__', '__exit__', | |
| 337 '__float__', '__floordiv__', '__format__', '__ge__', '__get__', | |
| 338 '__getattr__', '__getattribute__', '__getitem__', '__gt__', '__hash__', | |
| 339 '__iadd__', '__iand__', '__ifloordiv__', '__ilshift__', '__imatmul__', | |
| 340 '__imod__', '__import__', '__imul__', '__index__', '__init__', | |
| 341 '__instancecheck__', '__int__', '__invert__', '__ior__', '__ipow__', | |
| 342 '__irshift__', '__isub__', '__iter__', '__itruediv__', '__ixor__', | |
| 343 '__le__', '__len__', '__length_hint__', '__lshift__', '__lt__', | |
| 344 '__matmul__', '__missing__', '__mod__', '__mul__', '__ne__', '__neg__', | |
| 345 '__new__', '__next__', '__or__', '__pos__', '__pow__', '__prepare__', | |
| 346 '__radd__', '__rand__', '__rdivmod__', '__repr__', '__reversed__', | |
| 347 '__rfloordiv__', '__rlshift__', '__rmatmul__', '__rmod__', '__rmul__', | |
| 348 '__ror__', '__round__', '__rpow__', '__rrshift__', '__rshift__', | |
| 349 '__rsub__', '__rtruediv__', '__rxor__', '__set__', '__setattr__', | |
| 350 '__setitem__', '__str__', '__sub__', '__subclasscheck__', '__truediv__', | |
| 351 '__xor__'), suffix=r'\b'), | |
| 352 Name.Function.Magic), | |
| 353 ] | |
| 354 tokens['magicvars'] = [ | |
| 355 (words(( | |
| 356 '__annotations__', '__bases__', '__class__', '__closure__', '__code__', | |
| 357 '__defaults__', '__dict__', '__doc__', '__file__', '__func__', | |
| 358 '__globals__', '__kwdefaults__', '__module__', '__mro__', '__name__', | |
| 359 '__objclass__', '__qualname__', '__self__', '__slots__', '__weakref__'), | |
| 360 suffix=r'\b'), | |
| 361 Name.Variable.Magic), | |
| 362 ] | |
| 363 tokens['numbers'] = [ | |
| 364 (r'(\d(?:_?\d)*\.(?:\d(?:_?\d)*)?|(?:\d(?:_?\d)*)?\.\d(?:_?\d)*)([eE][+-]?\d(?:_?\d)*)?', Number.Float), | |
| 365 (r'\d(?:_?\d)*[eE][+-]?\d(?:_?\d)*j?', Number.Float), | |
| 366 (r'0[oO](?:_?[0-7])+', Number.Oct), | |
| 367 (r'0[bB](?:_?[01])+', Number.Bin), | |
| 368 (r'0[xX](?:_?[a-fA-F0-9])+', Number.Hex), | |
| 369 (r'\d(?:_?\d)*', Number.Integer) | |
| 370 ] | |
| 371 tokens['backtick'] = [] | |
| 372 tokens['name'] = [ | |
| 373 (r'@\w+', Name.Decorator), | |
| 374 (r'@', Operator), # new matrix multiplication operator | |
| 375 (uni_name, Name), | |
| 376 ] | |
| 377 tokens['funcname'] = [ | |
| 378 (uni_name, Name.Function, '#pop') | |
| 379 ] | |
| 380 tokens['classname'] = [ | |
| 381 (uni_name, Name.Class, '#pop') | |
| 382 ] | |
| 383 tokens['import'] = [ | |
| 384 (r'(\s+)(as)(\s+)', bygroups(Text, Keyword, Text)), | |
| 385 (r'\.', Name.Namespace), | |
| 386 (uni_name, Name.Namespace), | |
| 387 (r'(\s*)(,)(\s*)', bygroups(Text, Operator, Text)), | |
| 388 default('#pop') # all else: go back | |
| 389 ] | |
| 390 tokens['fromimport'] = [ | |
| 391 (r'(\s+)(import)\b', bygroups(Text, Keyword), '#pop'), | |
| 392 (r'\.', Name.Namespace), | |
| 393 (uni_name, Name.Namespace), | |
| 394 default('#pop'), | |
| 395 ] | |
| 396 tokens['strings-single'] = innerstring_rules(String.Single) | |
| 397 tokens['strings-double'] = innerstring_rules(String.Double) | |
| 398 | |
| 399 | |
| 400 def analyse_text(text): | |
| 401 return shebang_matches(text, r'pythonw?3(\.\d)?') | |
| 402 | |
| 403 | |
| 404 class PythonConsoleLexer(Lexer): | |
| 405 """ | |
| 406 For Python console output or doctests, such as: | |
| 407 | |
| 408 .. sourcecode:: pycon | |
| 409 | |
| 410 >>> a = 'foo' | |
| 411 >>> print a | |
| 412 foo | |
| 413 >>> 1 / 0 | |
| 414 Traceback (most recent call last): | |
| 415 File "<stdin>", line 1, in <module> | |
| 416 ZeroDivisionError: integer division or modulo by zero | |
| 417 | |
| 418 Additional options: | |
| 419 | |
| 420 `python3` | |
| 421 Use Python 3 lexer for code. Default is ``False``. | |
| 422 | |
| 423 .. versionadded:: 1.0 | |
| 424 """ | |
| 425 name = 'Python console session' | |
| 426 aliases = ['pycon'] | |
| 427 mimetypes = ['text/x-python-doctest'] | |
| 428 | |
| 429 def __init__(self, **options): | |
| 430 self.python3 = get_bool_opt(options, 'python3', False) | |
| 431 Lexer.__init__(self, **options) | |
| 432 | |
| 433 def get_tokens_unprocessed(self, text): | |
| 434 if self.python3: | |
| 435 pylexer = Python3Lexer(**self.options) | |
| 436 tblexer = Python3TracebackLexer(**self.options) | |
| 437 else: | |
| 438 pylexer = PythonLexer(**self.options) | |
| 439 tblexer = PythonTracebackLexer(**self.options) | |
| 440 | |
| 441 curcode = '' | |
| 442 insertions = [] | |
| 443 curtb = '' | |
| 444 tbindex = 0 | |
| 445 tb = 0 | |
| 446 for match in line_re.finditer(text): | |
| 447 line = match.group() | |
| 448 if line.startswith(u'>>> ') or line.startswith(u'... '): | |
| 449 tb = 0 | |
| 450 insertions.append((len(curcode), | |
| 451 [(0, Generic.Prompt, line[:4])])) | |
| 452 curcode += line[4:] | |
| 453 elif line.rstrip() == u'...' and not tb: | |
| 454 # only a new >>> prompt can end an exception block | |
| 455 # otherwise an ellipsis in place of the traceback frames | |
| 456 # will be mishandled | |
| 457 insertions.append((len(curcode), | |
| 458 [(0, Generic.Prompt, u'...')])) | |
| 459 curcode += line[3:] | |
| 460 else: | |
| 461 if curcode: | |
| 462 for item in do_insertions( | |
| 463 insertions, pylexer.get_tokens_unprocessed(curcode)): | |
| 464 yield item | |
| 465 curcode = '' | |
| 466 insertions = [] | |
| 467 if (line.startswith(u'Traceback (most recent call last):') or | |
| 468 re.match(u' File "[^"]+", line \\d+\\n$', line)): | |
| 469 tb = 1 | |
| 470 curtb = line | |
| 471 tbindex = match.start() | |
| 472 elif line == 'KeyboardInterrupt\n': | |
| 473 yield match.start(), Name.Class, line | |
| 474 elif tb: | |
| 475 curtb += line | |
| 476 if not (line.startswith(' ') or line.strip() == u'...'): | |
| 477 tb = 0 | |
| 478 for i, t, v in tblexer.get_tokens_unprocessed(curtb): | |
| 479 yield tbindex+i, t, v | |
| 480 curtb = '' | |
| 481 else: | |
| 482 yield match.start(), Generic.Output, line | |
| 483 if curcode: | |
| 484 for item in do_insertions(insertions, | |
| 485 pylexer.get_tokens_unprocessed(curcode)): | |
| 486 yield item | |
| 487 if curtb: | |
| 488 for i, t, v in tblexer.get_tokens_unprocessed(curtb): | |
| 489 yield tbindex+i, t, v | |
| 490 | |
| 491 | |
| 492 class PythonTracebackLexer(RegexLexer): | |
| 493 """ | |
| 494 For Python tracebacks. | |
| 495 | |
| 496 .. versionadded:: 0.7 | |
| 497 """ | |
| 498 | |
| 499 name = 'Python Traceback' | |
| 500 aliases = ['pytb'] | |
| 501 filenames = ['*.pytb'] | |
| 502 mimetypes = ['text/x-python-traceback'] | |
| 503 | |
| 504 tokens = { | |
| 505 'root': [ | |
| 506 # Cover both (most recent call last) and (innermost last) | |
| 507 # The optional ^C allows us to catch keyboard interrupt signals. | |
| 508 (r'^(\^C)?(Traceback.*\n)', | |
| 509 bygroups(Text, Generic.Traceback), 'intb'), | |
| 510 # SyntaxError starts with this. | |
| 511 (r'^(?= File "[^"]+", line \d+)', Generic.Traceback, 'intb'), | |
| 512 (r'^.*\n', Other), | |
| 513 ], | |
| 514 'intb': [ | |
| 515 (r'^( File )("[^"]+")(, line )(\d+)(, in )(.+)(\n)', | |
| 516 bygroups(Text, Name.Builtin, Text, Number, Text, Name, Text)), | |
| 517 (r'^( File )("[^"]+")(, line )(\d+)(\n)', | |
| 518 bygroups(Text, Name.Builtin, Text, Number, Text)), | |
| 519 (r'^( )(.+)(\n)', | |
| 520 bygroups(Text, using(PythonLexer), Text)), | |
| 521 (r'^([ \t]*)(\.\.\.)(\n)', | |
| 522 bygroups(Text, Comment, Text)), # for doctests... | |
| 523 (r'^([^:]+)(: )(.+)(\n)', | |
| 524 bygroups(Generic.Error, Text, Name, Text), '#pop'), | |
| 525 (r'^([a-zA-Z_]\w*)(:?\n)', | |
| 526 bygroups(Generic.Error, Text), '#pop') | |
| 527 ], | |
| 528 } | |
| 529 | |
| 530 | |
| 531 class Python3TracebackLexer(RegexLexer): | |
| 532 """ | |
| 533 For Python 3.0 tracebacks, with support for chained exceptions. | |
| 534 | |
| 535 .. versionadded:: 1.0 | |
| 536 """ | |
| 537 | |
| 538 name = 'Python 3.0 Traceback' | |
| 539 aliases = ['py3tb'] | |
| 540 filenames = ['*.py3tb'] | |
| 541 mimetypes = ['text/x-python3-traceback'] | |
| 542 | |
| 543 tokens = { | |
| 544 'root': [ | |
| 545 (r'\n', Text), | |
| 546 (r'^Traceback \(most recent call last\):\n', Generic.Traceback, 'intb'), | |
| 547 (r'^During handling of the above exception, another ' | |
| 548 r'exception occurred:\n\n', Generic.Traceback), | |
| 549 (r'^The above exception was the direct cause of the ' | |
| 550 r'following exception:\n\n', Generic.Traceback), | |
| 551 (r'^(?= File "[^"]+", line \d+)', Generic.Traceback, 'intb'), | |
| 552 ], | |
| 553 'intb': [ | |
| 554 (r'^( File )("[^"]+")(, line )(\d+)(, in )(.+)(\n)', | |
| 555 bygroups(Text, Name.Builtin, Text, Number, Text, Name, Text)), | |
| 556 (r'^( File )("[^"]+")(, line )(\d+)(\n)', | |
| 557 bygroups(Text, Name.Builtin, Text, Number, Text)), | |
| 558 (r'^( )(.+)(\n)', | |
| 559 bygroups(Text, using(Python3Lexer), Text)), | |
| 560 (r'^([ \t]*)(\.\.\.)(\n)', | |
| 561 bygroups(Text, Comment, Text)), # for doctests... | |
| 562 (r'^([^:]+)(: )(.+)(\n)', | |
| 563 bygroups(Generic.Error, Text, Name, Text), '#pop'), | |
| 564 (r'^([a-zA-Z_]\w*)(:?\n)', | |
| 565 bygroups(Generic.Error, Text), '#pop') | |
| 566 ], | |
| 567 } | |
| 568 | |
| 569 | |
| 570 class CythonLexer(RegexLexer): | |
| 571 """ | |
| 572 For Pyrex and `Cython <http://cython.org>`_ source code. | |
| 573 | |
| 574 .. versionadded:: 1.1 | |
| 575 """ | |
| 576 | |
| 577 name = 'Cython' | |
| 578 aliases = ['cython', 'pyx', 'pyrex'] | |
| 579 filenames = ['*.pyx', '*.pxd', '*.pxi'] | |
| 580 mimetypes = ['text/x-cython', 'application/x-cython'] | |
| 581 | |
| 582 tokens = { | |
| 583 'root': [ | |
| 584 (r'\n', Text), | |
| 585 (r'^(\s*)("""(?:.|\n)*?""")', bygroups(Text, String.Doc)), | |
| 586 (r"^(\s*)('''(?:.|\n)*?''')", bygroups(Text, String.Doc)), | |
| 587 (r'[^\S\n]+', Text), | |
| 588 (r'#.*$', Comment), | |
| 589 (r'[]{}:(),;[]', Punctuation), | |
| 590 (r'\\\n', Text), | |
| 591 (r'\\', Text), | |
| 592 (r'(in|is|and|or|not)\b', Operator.Word), | |
| 593 (r'(<)([a-zA-Z0-9.?]+)(>)', | |
| 594 bygroups(Punctuation, Keyword.Type, Punctuation)), | |
| 595 (r'!=|==|<<|>>|[-~+/*%=<>&^|.?]', Operator), | |
| 596 (r'(from)(\d+)(<=)(\s+)(<)(\d+)(:)', | |
| 597 bygroups(Keyword, Number.Integer, Operator, Name, Operator, | |
| 598 Name, Punctuation)), | |
| 599 include('keywords'), | |
| 600 (r'(def|property)(\s+)', bygroups(Keyword, Text), 'funcname'), | |
| 601 (r'(cp?def)(\s+)', bygroups(Keyword, Text), 'cdef'), | |
| 602 # (should actually start a block with only cdefs) | |
| 603 (r'(cdef)(:)', bygroups(Keyword, Punctuation)), | |
| 604 (r'(class|struct)(\s+)', bygroups(Keyword, Text), 'classname'), | |
| 605 (r'(from)(\s+)', bygroups(Keyword, Text), 'fromimport'), | |
| 606 (r'(c?import)(\s+)', bygroups(Keyword, Text), 'import'), | |
| 607 include('builtins'), | |
| 608 include('backtick'), | |
| 609 ('(?:[rR]|[uU][rR]|[rR][uU])"""', String, 'tdqs'), | |
| 610 ("(?:[rR]|[uU][rR]|[rR][uU])'''", String, 'tsqs'), | |
| 611 ('(?:[rR]|[uU][rR]|[rR][uU])"', String, 'dqs'), | |
| 612 ("(?:[rR]|[uU][rR]|[rR][uU])'", String, 'sqs'), | |
| 613 ('[uU]?"""', String, combined('stringescape', 'tdqs')), | |
| 614 ("[uU]?'''", String, combined('stringescape', 'tsqs')), | |
| 615 ('[uU]?"', String, combined('stringescape', 'dqs')), | |
| 616 ("[uU]?'", String, combined('stringescape', 'sqs')), | |
| 617 include('name'), | |
| 618 include('numbers'), | |
| 619 ], | |
| 620 'keywords': [ | |
| 621 (words(( | |
| 622 'assert', 'break', 'by', 'continue', 'ctypedef', 'del', 'elif', | |
| 623 'else', 'except', 'except?', 'exec', 'finally', 'for', 'fused', 'gil', | |
| 624 'global', 'if', 'include', 'lambda', 'nogil', 'pass', 'print', | |
| 625 'raise', 'return', 'try', 'while', 'yield', 'as', 'with'), suffix=r'\b'), | |
| 626 Keyword), | |
| 627 (r'(DEF|IF|ELIF|ELSE)\b', Comment.Preproc), | |
| 628 ], | |
| 629 'builtins': [ | |
| 630 (words(( | |
| 631 '__import__', 'abs', 'all', 'any', 'apply', 'basestring', 'bin', | |
| 632 'bool', 'buffer', 'bytearray', 'bytes', 'callable', 'chr', | |
| 633 'classmethod', 'cmp', 'coerce', 'compile', 'complex', 'delattr', | |
| 634 'dict', 'dir', 'divmod', 'enumerate', 'eval', 'execfile', 'exit', | |
| 635 'file', 'filter', 'float', 'frozenset', 'getattr', 'globals', | |
| 636 'hasattr', 'hash', 'hex', 'id', 'input', 'int', 'intern', 'isinstance', | |
| 637 'issubclass', 'iter', 'len', 'list', 'locals', 'long', 'map', 'max', | |
| 638 'min', 'next', 'object', 'oct', 'open', 'ord', 'pow', 'property', | |
| 639 'range', 'raw_input', 'reduce', 'reload', 'repr', 'reversed', | |
| 640 'round', 'set', 'setattr', 'slice', 'sorted', 'staticmethod', | |
| 641 'str', 'sum', 'super', 'tuple', 'type', 'unichr', 'unicode', 'unsigned', | |
| 642 'vars', 'xrange', 'zip'), prefix=r'(?<!\.)', suffix=r'\b'), | |
| 643 Name.Builtin), | |
| 644 (r'(?<!\.)(self|None|Ellipsis|NotImplemented|False|True|NULL' | |
| 645 r')\b', Name.Builtin.Pseudo), | |
| 646 (words(( | |
| 647 'ArithmeticError', 'AssertionError', 'AttributeError', | |
| 648 'BaseException', 'DeprecationWarning', 'EOFError', 'EnvironmentError', | |
| 649 'Exception', 'FloatingPointError', 'FutureWarning', 'GeneratorExit', | |
| 650 'IOError', 'ImportError', 'ImportWarning', 'IndentationError', | |
| 651 'IndexError', 'KeyError', 'KeyboardInterrupt', 'LookupError', | |
| 652 'MemoryError', 'NameError', 'NotImplemented', 'NotImplementedError', | |
| 653 'OSError', 'OverflowError', 'OverflowWarning', | |
| 654 'PendingDeprecationWarning', 'ReferenceError', 'RuntimeError', | |
| 655 'RuntimeWarning', 'StandardError', 'StopIteration', 'SyntaxError', | |
| 656 'SyntaxWarning', 'SystemError', 'SystemExit', 'TabError', | |
| 657 'TypeError', 'UnboundLocalError', 'UnicodeDecodeError', | |
| 658 'UnicodeEncodeError', 'UnicodeError', 'UnicodeTranslateError', | |
| 659 'UnicodeWarning', 'UserWarning', 'ValueError', 'Warning', | |
| 660 'ZeroDivisionError'), prefix=r'(?<!\.)', suffix=r'\b'), | |
| 661 Name.Exception), | |
| 662 ], | |
| 663 'numbers': [ | |
| 664 (r'(\d+\.?\d*|\d*\.\d+)([eE][+-]?[0-9]+)?', Number.Float), | |
| 665 (r'0\d+', Number.Oct), | |
| 666 (r'0[xX][a-fA-F0-9]+', Number.Hex), | |
| 667 (r'\d+L', Number.Integer.Long), | |
| 668 (r'\d+', Number.Integer) | |
| 669 ], | |
| 670 'backtick': [ | |
| 671 ('`.*?`', String.Backtick), | |
| 672 ], | |
| 673 'name': [ | |
| 674 (r'@\w+', Name.Decorator), | |
| 675 (r'[a-zA-Z_]\w*', Name), | |
| 676 ], | |
| 677 'funcname': [ | |
| 678 (r'[a-zA-Z_]\w*', Name.Function, '#pop') | |
| 679 ], | |
| 680 'cdef': [ | |
| 681 (r'(public|readonly|extern|api|inline)\b', Keyword.Reserved), | |
| 682 (r'(struct|enum|union|class)\b', Keyword), | |
| 683 (r'([a-zA-Z_]\w*)(\s*)(?=[(:#=]|$)', | |
| 684 bygroups(Name.Function, Text), '#pop'), | |
| 685 (r'([a-zA-Z_]\w*)(\s*)(,)', | |
| 686 bygroups(Name.Function, Text, Punctuation)), | |
| 687 (r'from\b', Keyword, '#pop'), | |
| 688 (r'as\b', Keyword), | |
| 689 (r':', Punctuation, '#pop'), | |
| 690 (r'(?=["\'])', Text, '#pop'), | |
| 691 (r'[a-zA-Z_]\w*', Keyword.Type), | |
| 692 (r'.', Text), | |
| 693 ], | |
| 694 'classname': [ | |
| 695 (r'[a-zA-Z_]\w*', Name.Class, '#pop') | |
| 696 ], | |
| 697 'import': [ | |
| 698 (r'(\s+)(as)(\s+)', bygroups(Text, Keyword, Text)), | |
| 699 (r'[a-zA-Z_][\w.]*', Name.Namespace), | |
| 700 (r'(\s*)(,)(\s*)', bygroups(Text, Operator, Text)), | |
| 701 default('#pop') # all else: go back | |
| 702 ], | |
| 703 'fromimport': [ | |
| 704 (r'(\s+)(c?import)\b', bygroups(Text, Keyword), '#pop'), | |
| 705 (r'[a-zA-Z_.][\w.]*', Name.Namespace), | |
| 706 # ``cdef foo from "header"``, or ``for foo from 0 < i < 10`` | |
| 707 default('#pop'), | |
| 708 ], | |
| 709 'stringescape': [ | |
| 710 (r'\\([\\abfnrtv"\']|\n|N\{.*?\}|u[a-fA-F0-9]{4}|' | |
| 711 r'U[a-fA-F0-9]{8}|x[a-fA-F0-9]{2}|[0-7]{1,3})', String.Escape) | |
| 712 ], | |
| 713 'strings': [ | |
| 714 (r'%(\([a-zA-Z0-9]+\))?[-#0 +]*([0-9]+|[*])?(\.([0-9]+|[*]))?' | |
| 715 '[hlL]?[E-GXc-giorsux%]', String.Interpol), | |
| 716 (r'[^\\\'"%\n]+', String), | |
| 717 # quotes, percents and backslashes must be parsed one at a time | |
| 718 (r'[\'"\\]', String), | |
| 719 # unhandled string formatting sign | |
| 720 (r'%', String) | |
| 721 # newlines are an error (use "nl" state) | |
| 722 ], | |
| 723 'nl': [ | |
| 724 (r'\n', String) | |
| 725 ], | |
| 726 'dqs': [ | |
| 727 (r'"', String, '#pop'), | |
| 728 (r'\\\\|\\"|\\\n', String.Escape), # included here again for raw strings | |
| 729 include('strings') | |
| 730 ], | |
| 731 'sqs': [ | |
| 732 (r"'", String, '#pop'), | |
| 733 (r"\\\\|\\'|\\\n", String.Escape), # included here again for raw strings | |
| 734 include('strings') | |
| 735 ], | |
| 736 'tdqs': [ | |
| 737 (r'"""', String, '#pop'), | |
| 738 include('strings'), | |
| 739 include('nl') | |
| 740 ], | |
| 741 'tsqs': [ | |
| 742 (r"'''", String, '#pop'), | |
| 743 include('strings'), | |
| 744 include('nl') | |
| 745 ], | |
| 746 } | |
| 747 | |
| 748 | |
| 749 class DgLexer(RegexLexer): | |
| 750 """ | |
| 751 Lexer for `dg <http://pyos.github.com/dg>`_, | |
| 752 a functional and object-oriented programming language | |
| 753 running on the CPython 3 VM. | |
| 754 | |
| 755 .. versionadded:: 1.6 | |
| 756 """ | |
| 757 name = 'dg' | |
| 758 aliases = ['dg'] | |
| 759 filenames = ['*.dg'] | |
| 760 mimetypes = ['text/x-dg'] | |
| 761 | |
| 762 tokens = { | |
| 763 'root': [ | |
| 764 (r'\s+', Text), | |
| 765 (r'#.*?$', Comment.Single), | |
| 766 | |
| 767 (r'(?i)0b[01]+', Number.Bin), | |
| 768 (r'(?i)0o[0-7]+', Number.Oct), | |
| 769 (r'(?i)0x[0-9a-f]+', Number.Hex), | |
| 770 (r'(?i)[+-]?[0-9]+\.[0-9]+(e[+-]?[0-9]+)?j?', Number.Float), | |
| 771 (r'(?i)[+-]?[0-9]+e[+-]?\d+j?', Number.Float), | |
| 772 (r'(?i)[+-]?[0-9]+j?', Number.Integer), | |
| 773 | |
| 774 (r"(?i)(br|r?b?)'''", String, combined('stringescape', 'tsqs', 'string')), | |
| 775 (r'(?i)(br|r?b?)"""', String, combined('stringescape', 'tdqs', 'string')), | |
| 776 (r"(?i)(br|r?b?)'", String, combined('stringescape', 'sqs', 'string')), | |
| 777 (r'(?i)(br|r?b?)"', String, combined('stringescape', 'dqs', 'string')), | |
| 778 | |
| 779 (r"`\w+'*`", Operator), | |
| 780 (r'\b(and|in|is|or|where)\b', Operator.Word), | |
| 781 (r'[!$%&*+\-./:<-@\\^|~;,]+', Operator), | |
| 782 | |
| 783 (words(( | |
| 784 'bool', 'bytearray', 'bytes', 'classmethod', 'complex', 'dict', 'dict\'', | |
| 785 'float', 'frozenset', 'int', 'list', 'list\'', 'memoryview', 'object', | |
| 786 'property', 'range', 'set', 'set\'', 'slice', 'staticmethod', 'str', | |
| 787 'super', 'tuple', 'tuple\'', 'type'), | |
| 788 prefix=r'(?<!\.)', suffix=r'(?![\'\w])'), | |
| 789 Name.Builtin), | |
| 790 (words(( | |
| 791 '__import__', 'abs', 'all', 'any', 'bin', 'bind', 'chr', 'cmp', 'compile', | |
| 792 'complex', 'delattr', 'dir', 'divmod', 'drop', 'dropwhile', 'enumerate', | |
| 793 'eval', 'exhaust', 'filter', 'flip', 'foldl1?', 'format', 'fst', | |
| 794 'getattr', 'globals', 'hasattr', 'hash', 'head', 'hex', 'id', 'init', | |
| 795 'input', 'isinstance', 'issubclass', 'iter', 'iterate', 'last', 'len', | |
| 796 'locals', 'map', 'max', 'min', 'next', 'oct', 'open', 'ord', 'pow', | |
| 797 'print', 'repr', 'reversed', 'round', 'setattr', 'scanl1?', 'snd', | |
| 798 'sorted', 'sum', 'tail', 'take', 'takewhile', 'vars', 'zip'), | |
| 799 prefix=r'(?<!\.)', suffix=r'(?![\'\w])'), | |
| 800 Name.Builtin), | |
| 801 (r"(?<!\.)(self|Ellipsis|NotImplemented|None|True|False)(?!['\w])", | |
| 802 Name.Builtin.Pseudo), | |
| 803 | |
| 804 (r"(?<!\.)[A-Z]\w*(Error|Exception|Warning)'*(?!['\w])", | |
| 805 Name.Exception), | |
| 806 (r"(?<!\.)(Exception|GeneratorExit|KeyboardInterrupt|StopIteration|" | |
| 807 r"SystemExit)(?!['\w])", Name.Exception), | |
| 808 | |
| 809 (r"(?<![\w.])(except|finally|for|if|import|not|otherwise|raise|" | |
| 810 r"subclass|while|with|yield)(?!['\w])", Keyword.Reserved), | |
| 811 | |
| 812 (r"[A-Z_]+'*(?!['\w])", Name), | |
| 813 (r"[A-Z]\w+'*(?!['\w])", Keyword.Type), | |
| 814 (r"\w+'*", Name), | |
| 815 | |
| 816 (r'[()]', Punctuation), | |
| 817 (r'.', Error), | |
| 818 ], | |
| 819 'stringescape': [ | |
| 820 (r'\\([\\abfnrtv"\']|\n|N\{.*?\}|u[a-fA-F0-9]{4}|' | |
| 821 r'U[a-fA-F0-9]{8}|x[a-fA-F0-9]{2}|[0-7]{1,3})', String.Escape) | |
| 822 ], | |
| 823 'string': [ | |
| 824 (r'%(\(\w+\))?[-#0 +]*([0-9]+|[*])?(\.([0-9]+|[*]))?' | |
| 825 '[hlL]?[E-GXc-giorsux%]', String.Interpol), | |
| 826 (r'[^\\\'"%\n]+', String), | |
| 827 # quotes, percents and backslashes must be parsed one at a time | |
| 828 (r'[\'"\\]', String), | |
| 829 # unhandled string formatting sign | |
| 830 (r'%', String), | |
| 831 (r'\n', String) | |
| 832 ], | |
| 833 'dqs': [ | |
| 834 (r'"', String, '#pop') | |
| 835 ], | |
| 836 'sqs': [ | |
| 837 (r"'", String, '#pop') | |
| 838 ], | |
| 839 'tdqs': [ | |
| 840 (r'"""', String, '#pop') | |
| 841 ], | |
| 842 'tsqs': [ | |
| 843 (r"'''", String, '#pop') | |
| 844 ], | |
| 845 } | |
| 846 | |
| 847 | |
| 848 class NumPyLexer(PythonLexer): | |
| 849 """ | |
| 850 A Python lexer recognizing Numerical Python builtins. | |
| 851 | |
| 852 .. versionadded:: 0.10 | |
| 853 """ | |
| 854 | |
| 855 name = 'NumPy' | |
| 856 aliases = ['numpy'] | |
| 857 | |
| 858 # override the mimetypes to not inherit them from python | |
| 859 mimetypes = [] | |
| 860 filenames = [] | |
| 861 | |
| 862 EXTRA_KEYWORDS = set(( | |
| 863 'abs', 'absolute', 'accumulate', 'add', 'alen', 'all', 'allclose', | |
| 864 'alltrue', 'alterdot', 'amax', 'amin', 'angle', 'any', 'append', | |
| 865 'apply_along_axis', 'apply_over_axes', 'arange', 'arccos', 'arccosh', | |
| 866 'arcsin', 'arcsinh', 'arctan', 'arctan2', 'arctanh', 'argmax', 'argmin', | |
| 867 'argsort', 'argwhere', 'around', 'array', 'array2string', 'array_equal', | |
| 868 'array_equiv', 'array_repr', 'array_split', 'array_str', 'arrayrange', | |
| 869 'asanyarray', 'asarray', 'asarray_chkfinite', 'ascontiguousarray', | |
| 870 'asfarray', 'asfortranarray', 'asmatrix', 'asscalar', 'astype', | |
| 871 'atleast_1d', 'atleast_2d', 'atleast_3d', 'average', 'bartlett', | |
| 872 'base_repr', 'beta', 'binary_repr', 'bincount', 'binomial', | |
| 873 'bitwise_and', 'bitwise_not', 'bitwise_or', 'bitwise_xor', 'blackman', | |
| 874 'bmat', 'broadcast', 'byte_bounds', 'bytes', 'byteswap', 'c_', | |
| 875 'can_cast', 'ceil', 'choose', 'clip', 'column_stack', 'common_type', | |
| 876 'compare_chararrays', 'compress', 'concatenate', 'conj', 'conjugate', | |
| 877 'convolve', 'copy', 'corrcoef', 'correlate', 'cos', 'cosh', 'cov', | |
| 878 'cross', 'cumprod', 'cumproduct', 'cumsum', 'delete', 'deprecate', | |
| 879 'diag', 'diagflat', 'diagonal', 'diff', 'digitize', 'disp', 'divide', | |
| 880 'dot', 'dsplit', 'dstack', 'dtype', 'dump', 'dumps', 'ediff1d', 'empty', | |
| 881 'empty_like', 'equal', 'exp', 'expand_dims', 'expm1', 'extract', 'eye', | |
| 882 'fabs', 'fastCopyAndTranspose', 'fft', 'fftfreq', 'fftshift', 'fill', | |
| 883 'finfo', 'fix', 'flat', 'flatnonzero', 'flatten', 'fliplr', 'flipud', | |
| 884 'floor', 'floor_divide', 'fmod', 'frexp', 'fromarrays', 'frombuffer', | |
| 885 'fromfile', 'fromfunction', 'fromiter', 'frompyfunc', 'fromstring', | |
| 886 'generic', 'get_array_wrap', 'get_include', 'get_numarray_include', | |
| 887 'get_numpy_include', 'get_printoptions', 'getbuffer', 'getbufsize', | |
| 888 'geterr', 'geterrcall', 'geterrobj', 'getfield', 'gradient', 'greater', | |
| 889 'greater_equal', 'gumbel', 'hamming', 'hanning', 'histogram', | |
| 890 'histogram2d', 'histogramdd', 'hsplit', 'hstack', 'hypot', 'i0', | |
| 891 'identity', 'ifft', 'imag', 'index_exp', 'indices', 'inf', 'info', | |
| 892 'inner', 'insert', 'int_asbuffer', 'interp', 'intersect1d', | |
| 893 'intersect1d_nu', 'inv', 'invert', 'iscomplex', 'iscomplexobj', | |
| 894 'isfinite', 'isfortran', 'isinf', 'isnan', 'isneginf', 'isposinf', | |
| 895 'isreal', 'isrealobj', 'isscalar', 'issctype', 'issubclass_', | |
| 896 'issubdtype', 'issubsctype', 'item', 'itemset', 'iterable', 'ix_', | |
| 897 'kaiser', 'kron', 'ldexp', 'left_shift', 'less', 'less_equal', 'lexsort', | |
| 898 'linspace', 'load', 'loads', 'loadtxt', 'log', 'log10', 'log1p', 'log2', | |
| 899 'logical_and', 'logical_not', 'logical_or', 'logical_xor', 'logspace', | |
| 900 'lstsq', 'mat', 'matrix', 'max', 'maximum', 'maximum_sctype', | |
| 901 'may_share_memory', 'mean', 'median', 'meshgrid', 'mgrid', 'min', | |
| 902 'minimum', 'mintypecode', 'mod', 'modf', 'msort', 'multiply', 'nan', | |
| 903 'nan_to_num', 'nanargmax', 'nanargmin', 'nanmax', 'nanmin', 'nansum', | |
| 904 'ndenumerate', 'ndim', 'ndindex', 'negative', 'newaxis', 'newbuffer', | |
| 905 'newbyteorder', 'nonzero', 'not_equal', 'obj2sctype', 'ogrid', 'ones', | |
| 906 'ones_like', 'outer', 'permutation', 'piecewise', 'pinv', 'pkgload', | |
| 907 'place', 'poisson', 'poly', 'poly1d', 'polyadd', 'polyder', 'polydiv', | |
| 908 'polyfit', 'polyint', 'polymul', 'polysub', 'polyval', 'power', 'prod', | |
| 909 'product', 'ptp', 'put', 'putmask', 'r_', 'randint', 'random_integers', | |
| 910 'random_sample', 'ranf', 'rank', 'ravel', 'real', 'real_if_close', | |
| 911 'recarray', 'reciprocal', 'reduce', 'remainder', 'repeat', 'require', | |
| 912 'reshape', 'resize', 'restoredot', 'right_shift', 'rint', 'roll', | |
| 913 'rollaxis', 'roots', 'rot90', 'round', 'round_', 'row_stack', 's_', | |
| 914 'sample', 'savetxt', 'sctype2char', 'searchsorted', 'seed', 'select', | |
| 915 'set_numeric_ops', 'set_printoptions', 'set_string_function', | |
| 916 'setbufsize', 'setdiff1d', 'seterr', 'seterrcall', 'seterrobj', | |
| 917 'setfield', 'setflags', 'setmember1d', 'setxor1d', 'shape', | |
| 918 'show_config', 'shuffle', 'sign', 'signbit', 'sin', 'sinc', 'sinh', | |
| 919 'size', 'slice', 'solve', 'sometrue', 'sort', 'sort_complex', 'source', | |
| 920 'split', 'sqrt', 'square', 'squeeze', 'standard_normal', 'std', | |
| 921 'subtract', 'sum', 'svd', 'swapaxes', 'take', 'tan', 'tanh', 'tensordot', | |
| 922 'test', 'tile', 'tofile', 'tolist', 'tostring', 'trace', 'transpose', | |
| 923 'trapz', 'tri', 'tril', 'trim_zeros', 'triu', 'true_divide', 'typeDict', | |
| 924 'typename', 'uniform', 'union1d', 'unique', 'unique1d', 'unravel_index', | |
| 925 'unwrap', 'vander', 'var', 'vdot', 'vectorize', 'view', 'vonmises', | |
| 926 'vsplit', 'vstack', 'weibull', 'where', 'who', 'zeros', 'zeros_like' | |
| 927 )) | |
| 928 | |
| 929 def get_tokens_unprocessed(self, text): | |
| 930 for index, token, value in \ | |
| 931 PythonLexer.get_tokens_unprocessed(self, text): | |
| 932 if token is Name and value in self.EXTRA_KEYWORDS: | |
| 933 yield index, Keyword.Pseudo, value | |
| 934 else: | |
| 935 yield index, token, value | |
| 936 | |
| 937 def analyse_text(text): | |
| 938 return (shebang_matches(text, r'pythonw?(2(\.\d)?)?') or | |
| 939 'import ' in text[:1000]) \ | |
| 940 and ('import numpy' in text or 'from numpy import' in text) |
