1 # -*- coding: utf-8 -*- |
|
2 """ |
|
3 pygments.lexers.python |
|
4 ~~~~~~~~~~~~~~~~~~~~~~ |
|
5 |
|
6 Lexers for Python and related languages. |
|
7 |
|
8 :copyright: Copyright 2006-2021 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 'Python2Lexer', 'Python2TracebackLexer', |
|
23 'CythonLexer', '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 (version 3.x). |
|
31 |
|
32 .. versionadded:: 0.10 |
|
33 |
|
34 .. versionchanged:: 2.5 |
|
35 This is now the default ``PythonLexer``. It is still available as the |
|
36 alias ``Python3Lexer``. |
|
37 """ |
|
38 |
|
39 name = 'Python' |
|
40 aliases = ['python', 'py', 'sage', 'python3', 'py3'] |
|
41 filenames = [ |
|
42 '*.py', |
|
43 '*.pyw', |
|
44 # Jython |
|
45 '*.jy', |
|
46 # Sage |
|
47 '*.sage', |
|
48 # SCons |
|
49 '*.sc', |
|
50 'SConstruct', |
|
51 'SConscript', |
|
52 # Skylark/Starlark (used by Bazel, Buck, and Pants) |
|
53 '*.bzl', |
|
54 'BUCK', |
|
55 'BUILD', |
|
56 'BUILD.bazel', |
|
57 'WORKSPACE', |
|
58 # Twisted Application infrastructure |
|
59 '*.tac', |
|
60 ] |
|
61 mimetypes = ['text/x-python', 'application/x-python', |
|
62 'text/x-python3', 'application/x-python3'] |
|
63 |
|
64 flags = re.MULTILINE | re.UNICODE |
|
65 |
|
66 uni_name = "[%s][%s]*" % (uni.xid_start, uni.xid_continue) |
|
67 |
|
68 def innerstring_rules(ttype): |
|
69 return [ |
|
70 # the old style '%s' % (...) string formatting (still valid in Py3) |
|
71 (r'%(\(\w+\))?[-#0 +]*([0-9]+|[*])?(\.([0-9]+|[*]))?' |
|
72 '[hlL]?[E-GXc-giorsaux%]', String.Interpol), |
|
73 # the new style '{}'.format(...) string formatting |
|
74 (r'\{' |
|
75 r'((\w+)((\.\w+)|(\[[^\]]+\]))*)?' # field name |
|
76 r'(\![sra])?' # conversion |
|
77 r'(\:(.?[<>=\^])?[-+ ]?#?0?(\d+)?,?(\.\d+)?[E-GXb-gnosx%]?)?' |
|
78 r'\}', String.Interpol), |
|
79 |
|
80 # backslashes, quotes and formatting signs must be parsed one at a time |
|
81 (r'[^\\\'"%{\n]+', ttype), |
|
82 (r'[\'"\\]', ttype), |
|
83 # unhandled string formatting sign |
|
84 (r'%|(\{{1,2})', ttype) |
|
85 # newlines are an error (use "nl" state) |
|
86 ] |
|
87 |
|
88 def fstring_rules(ttype): |
|
89 return [ |
|
90 # Assuming that a '}' is the closing brace after format specifier. |
|
91 # Sadly, this means that we won't detect syntax error. But it's |
|
92 # more important to parse correct syntax correctly, than to |
|
93 # highlight invalid syntax. |
|
94 (r'\}', String.Interpol), |
|
95 (r'\{', String.Interpol, 'expr-inside-fstring'), |
|
96 # backslashes, quotes and formatting signs must be parsed one at a time |
|
97 (r'[^\\\'"{}\n]+', ttype), |
|
98 (r'[\'"\\]', ttype), |
|
99 # newlines are an error (use "nl" state) |
|
100 ] |
|
101 |
|
102 tokens = { |
|
103 'root': [ |
|
104 (r'\n', Text), |
|
105 (r'^(\s*)([rRuUbB]{,2})("""(?:.|\n)*?""")', |
|
106 bygroups(Text, String.Affix, String.Doc)), |
|
107 (r"^(\s*)([rRuUbB]{,2})('''(?:.|\n)*?''')", |
|
108 bygroups(Text, String.Affix, String.Doc)), |
|
109 (r'\A#!.+$', Comment.Hashbang), |
|
110 (r'#.*$', Comment.Single), |
|
111 (r'\\\n', Text), |
|
112 (r'\\', Text), |
|
113 include('keywords'), |
|
114 (r'(def)((?:\s|\\\s)+)', bygroups(Keyword, Text), 'funcname'), |
|
115 (r'(class)((?:\s|\\\s)+)', bygroups(Keyword, Text), 'classname'), |
|
116 (r'(from)((?:\s|\\\s)+)', bygroups(Keyword.Namespace, Text), |
|
117 'fromimport'), |
|
118 (r'(import)((?:\s|\\\s)+)', bygroups(Keyword.Namespace, Text), |
|
119 'import'), |
|
120 include('expr'), |
|
121 ], |
|
122 'expr': [ |
|
123 # raw f-strings |
|
124 ('(?i)(rf|fr)(""")', |
|
125 bygroups(String.Affix, String.Double), 'tdqf'), |
|
126 ("(?i)(rf|fr)(''')", |
|
127 bygroups(String.Affix, String.Single), 'tsqf'), |
|
128 ('(?i)(rf|fr)(")', |
|
129 bygroups(String.Affix, String.Double), 'dqf'), |
|
130 ("(?i)(rf|fr)(')", |
|
131 bygroups(String.Affix, String.Single), 'sqf'), |
|
132 # non-raw f-strings |
|
133 ('([fF])(""")', bygroups(String.Affix, String.Double), |
|
134 combined('fstringescape', 'tdqf')), |
|
135 ("([fF])(''')", bygroups(String.Affix, String.Single), |
|
136 combined('fstringescape', 'tsqf')), |
|
137 ('([fF])(")', bygroups(String.Affix, String.Double), |
|
138 combined('fstringescape', 'dqf')), |
|
139 ("([fF])(')", bygroups(String.Affix, String.Single), |
|
140 combined('fstringescape', 'sqf')), |
|
141 # raw strings |
|
142 ('(?i)(rb|br|r)(""")', |
|
143 bygroups(String.Affix, String.Double), 'tdqs'), |
|
144 ("(?i)(rb|br|r)(''')", |
|
145 bygroups(String.Affix, String.Single), 'tsqs'), |
|
146 ('(?i)(rb|br|r)(")', |
|
147 bygroups(String.Affix, String.Double), 'dqs'), |
|
148 ("(?i)(rb|br|r)(')", |
|
149 bygroups(String.Affix, String.Single), 'sqs'), |
|
150 # non-raw strings |
|
151 ('([uUbB]?)(""")', bygroups(String.Affix, String.Double), |
|
152 combined('stringescape', 'tdqs')), |
|
153 ("([uUbB]?)(''')", bygroups(String.Affix, String.Single), |
|
154 combined('stringescape', 'tsqs')), |
|
155 ('([uUbB]?)(")', bygroups(String.Affix, String.Double), |
|
156 combined('stringescape', 'dqs')), |
|
157 ("([uUbB]?)(')", bygroups(String.Affix, String.Single), |
|
158 combined('stringescape', 'sqs')), |
|
159 (r'[^\S\n]+', Text), |
|
160 (r'!=|==|<<|>>|:=|[-~+/*%=<>&^|.]', Operator), |
|
161 (r'[]{}:(),;[]', Punctuation), |
|
162 (r'(in|is|and|or|not)\b', Operator.Word), |
|
163 include('expr-keywords'), |
|
164 include('builtins'), |
|
165 include('magicfuncs'), |
|
166 include('magicvars'), |
|
167 include('name'), |
|
168 include('numbers'), |
|
169 ], |
|
170 'expr-inside-fstring': [ |
|
171 (r'[{([]', Punctuation, 'expr-inside-fstring-inner'), |
|
172 # without format specifier |
|
173 (r'(=\s*)?' # debug (https://bugs.python.org/issue36817) |
|
174 r'(\![sraf])?' # conversion |
|
175 r'\}', String.Interpol, '#pop'), |
|
176 # with format specifier |
|
177 # we'll catch the remaining '}' in the outer scope |
|
178 (r'(=\s*)?' # debug (https://bugs.python.org/issue36817) |
|
179 r'(\![sraf])?' # conversion |
|
180 r':', String.Interpol, '#pop'), |
|
181 (r'\s+', Text), # allow new lines |
|
182 include('expr'), |
|
183 ], |
|
184 'expr-inside-fstring-inner': [ |
|
185 (r'[{([]', Punctuation, 'expr-inside-fstring-inner'), |
|
186 (r'[])}]', Punctuation, '#pop'), |
|
187 (r'\s+', Text), # allow new lines |
|
188 include('expr'), |
|
189 ], |
|
190 'expr-keywords': [ |
|
191 # Based on https://docs.python.org/3/reference/expressions.html |
|
192 (words(( |
|
193 'async for', 'await', 'else', 'for', 'if', 'lambda', |
|
194 'yield', 'yield from'), suffix=r'\b'), |
|
195 Keyword), |
|
196 (words(('True', 'False', 'None'), suffix=r'\b'), Keyword.Constant), |
|
197 ], |
|
198 'keywords': [ |
|
199 (words(( |
|
200 'assert', 'async', 'await', 'break', 'continue', 'del', 'elif', |
|
201 'else', 'except', 'finally', 'for', 'global', 'if', 'lambda', |
|
202 'pass', 'raise', 'nonlocal', 'return', 'try', 'while', 'yield', |
|
203 'yield from', 'as', 'with'), suffix=r'\b'), |
|
204 Keyword), |
|
205 (words(('True', 'False', 'None'), suffix=r'\b'), Keyword.Constant), |
|
206 ], |
|
207 'builtins': [ |
|
208 (words(( |
|
209 '__import__', 'abs', 'all', 'any', 'bin', 'bool', 'bytearray', |
|
210 'bytes', 'chr', 'classmethod', 'compile', 'complex', |
|
211 'delattr', 'dict', 'dir', 'divmod', 'enumerate', 'eval', 'filter', |
|
212 'float', 'format', 'frozenset', 'getattr', 'globals', 'hasattr', |
|
213 'hash', 'hex', 'id', 'input', 'int', 'isinstance', 'issubclass', |
|
214 'iter', 'len', 'list', 'locals', 'map', 'max', 'memoryview', |
|
215 'min', 'next', 'object', 'oct', 'open', 'ord', 'pow', 'print', |
|
216 'property', 'range', 'repr', 'reversed', 'round', 'set', 'setattr', |
|
217 'slice', 'sorted', 'staticmethod', 'str', 'sum', 'super', 'tuple', |
|
218 'type', 'vars', 'zip'), prefix=r'(?<!\.)', suffix=r'\b'), |
|
219 Name.Builtin), |
|
220 (r'(?<!\.)(self|Ellipsis|NotImplemented|cls)\b', Name.Builtin.Pseudo), |
|
221 (words(( |
|
222 'ArithmeticError', 'AssertionError', 'AttributeError', |
|
223 'BaseException', 'BufferError', 'BytesWarning', 'DeprecationWarning', |
|
224 'EOFError', 'EnvironmentError', 'Exception', 'FloatingPointError', |
|
225 'FutureWarning', 'GeneratorExit', 'IOError', 'ImportError', |
|
226 'ImportWarning', 'IndentationError', 'IndexError', 'KeyError', |
|
227 'KeyboardInterrupt', 'LookupError', 'MemoryError', 'NameError', |
|
228 'NotImplementedError', 'OSError', 'OverflowError', |
|
229 'PendingDeprecationWarning', 'ReferenceError', 'ResourceWarning', |
|
230 'RuntimeError', 'RuntimeWarning', 'StopIteration', |
|
231 'SyntaxError', 'SyntaxWarning', 'SystemError', 'SystemExit', |
|
232 'TabError', 'TypeError', 'UnboundLocalError', 'UnicodeDecodeError', |
|
233 'UnicodeEncodeError', 'UnicodeError', 'UnicodeTranslateError', |
|
234 'UnicodeWarning', 'UserWarning', 'ValueError', 'VMSError', |
|
235 'Warning', 'WindowsError', 'ZeroDivisionError', |
|
236 # new builtin exceptions from PEP 3151 |
|
237 'BlockingIOError', 'ChildProcessError', 'ConnectionError', |
|
238 'BrokenPipeError', 'ConnectionAbortedError', 'ConnectionRefusedError', |
|
239 'ConnectionResetError', 'FileExistsError', 'FileNotFoundError', |
|
240 'InterruptedError', 'IsADirectoryError', 'NotADirectoryError', |
|
241 'PermissionError', 'ProcessLookupError', 'TimeoutError', |
|
242 # others new in Python 3 |
|
243 'StopAsyncIteration', 'ModuleNotFoundError', 'RecursionError'), |
|
244 prefix=r'(?<!\.)', suffix=r'\b'), |
|
245 Name.Exception), |
|
246 ], |
|
247 'magicfuncs': [ |
|
248 (words(( |
|
249 '__abs__', '__add__', '__aenter__', '__aexit__', '__aiter__', |
|
250 '__and__', '__anext__', '__await__', '__bool__', '__bytes__', |
|
251 '__call__', '__complex__', '__contains__', '__del__', '__delattr__', |
|
252 '__delete__', '__delitem__', '__dir__', '__divmod__', '__enter__', |
|
253 '__eq__', '__exit__', '__float__', '__floordiv__', '__format__', |
|
254 '__ge__', '__get__', '__getattr__', '__getattribute__', |
|
255 '__getitem__', '__gt__', '__hash__', '__iadd__', '__iand__', |
|
256 '__ifloordiv__', '__ilshift__', '__imatmul__', '__imod__', |
|
257 '__imul__', '__index__', '__init__', '__instancecheck__', |
|
258 '__int__', '__invert__', '__ior__', '__ipow__', '__irshift__', |
|
259 '__isub__', '__iter__', '__itruediv__', '__ixor__', '__le__', |
|
260 '__len__', '__length_hint__', '__lshift__', '__lt__', '__matmul__', |
|
261 '__missing__', '__mod__', '__mul__', '__ne__', '__neg__', |
|
262 '__new__', '__next__', '__or__', '__pos__', '__pow__', |
|
263 '__prepare__', '__radd__', '__rand__', '__rdivmod__', '__repr__', |
|
264 '__reversed__', '__rfloordiv__', '__rlshift__', '__rmatmul__', |
|
265 '__rmod__', '__rmul__', '__ror__', '__round__', '__rpow__', |
|
266 '__rrshift__', '__rshift__', '__rsub__', '__rtruediv__', |
|
267 '__rxor__', '__set__', '__setattr__', '__setitem__', '__str__', |
|
268 '__sub__', '__subclasscheck__', '__truediv__', |
|
269 '__xor__'), suffix=r'\b'), |
|
270 Name.Function.Magic), |
|
271 ], |
|
272 'magicvars': [ |
|
273 (words(( |
|
274 '__annotations__', '__bases__', '__class__', '__closure__', |
|
275 '__code__', '__defaults__', '__dict__', '__doc__', '__file__', |
|
276 '__func__', '__globals__', '__kwdefaults__', '__module__', |
|
277 '__mro__', '__name__', '__objclass__', '__qualname__', |
|
278 '__self__', '__slots__', '__weakref__'), suffix=r'\b'), |
|
279 Name.Variable.Magic), |
|
280 ], |
|
281 'numbers': [ |
|
282 (r'(\d(?:_?\d)*\.(?:\d(?:_?\d)*)?|(?:\d(?:_?\d)*)?\.\d(?:_?\d)*)' |
|
283 r'([eE][+-]?\d(?:_?\d)*)?', Number.Float), |
|
284 (r'\d(?:_?\d)*[eE][+-]?\d(?:_?\d)*j?', Number.Float), |
|
285 (r'0[oO](?:_?[0-7])+', Number.Oct), |
|
286 (r'0[bB](?:_?[01])+', Number.Bin), |
|
287 (r'0[xX](?:_?[a-fA-F0-9])+', Number.Hex), |
|
288 (r'\d(?:_?\d)*', Number.Integer), |
|
289 ], |
|
290 'name': [ |
|
291 (r'@' + uni_name, Name.Decorator), |
|
292 (r'@', Operator), # new matrix multiplication operator |
|
293 (uni_name, Name), |
|
294 ], |
|
295 'funcname': [ |
|
296 include('magicfuncs'), |
|
297 (uni_name, Name.Function, '#pop'), |
|
298 default('#pop'), |
|
299 ], |
|
300 'classname': [ |
|
301 (uni_name, Name.Class, '#pop'), |
|
302 ], |
|
303 'import': [ |
|
304 (r'(\s+)(as)(\s+)', bygroups(Text, Keyword, Text)), |
|
305 (r'\.', Name.Namespace), |
|
306 (uni_name, Name.Namespace), |
|
307 (r'(\s*)(,)(\s*)', bygroups(Text, Operator, Text)), |
|
308 default('#pop') # all else: go back |
|
309 ], |
|
310 'fromimport': [ |
|
311 (r'(\s+)(import)\b', bygroups(Text, Keyword.Namespace), '#pop'), |
|
312 (r'\.', Name.Namespace), |
|
313 # if None occurs here, it's "raise x from None", since None can |
|
314 # never be a module name |
|
315 (r'None\b', Name.Builtin.Pseudo, '#pop'), |
|
316 (uni_name, Name.Namespace), |
|
317 default('#pop'), |
|
318 ], |
|
319 'fstringescape': [ |
|
320 (r'\{\{', String.Escape), |
|
321 (r'\}\}', String.Escape), |
|
322 include('stringescape'), |
|
323 ], |
|
324 'stringescape': [ |
|
325 (r'\\([\\abfnrtv"\']|\n|N\{.*?\}|u[a-fA-F0-9]{4}|' |
|
326 r'U[a-fA-F0-9]{8}|x[a-fA-F0-9]{2}|[0-7]{1,3})', String.Escape) |
|
327 ], |
|
328 'fstrings-single': fstring_rules(String.Single), |
|
329 'fstrings-double': fstring_rules(String.Double), |
|
330 'strings-single': innerstring_rules(String.Single), |
|
331 'strings-double': innerstring_rules(String.Double), |
|
332 'dqf': [ |
|
333 (r'"', String.Double, '#pop'), |
|
334 (r'\\\\|\\"|\\\n', String.Escape), # included here for raw strings |
|
335 include('fstrings-double') |
|
336 ], |
|
337 'sqf': [ |
|
338 (r"'", String.Single, '#pop'), |
|
339 (r"\\\\|\\'|\\\n", String.Escape), # included here for raw strings |
|
340 include('fstrings-single') |
|
341 ], |
|
342 'dqs': [ |
|
343 (r'"', String.Double, '#pop'), |
|
344 (r'\\\\|\\"|\\\n', String.Escape), # included here for raw strings |
|
345 include('strings-double') |
|
346 ], |
|
347 'sqs': [ |
|
348 (r"'", String.Single, '#pop'), |
|
349 (r"\\\\|\\'|\\\n", String.Escape), # included here for raw strings |
|
350 include('strings-single') |
|
351 ], |
|
352 'tdqf': [ |
|
353 (r'"""', String.Double, '#pop'), |
|
354 include('fstrings-double'), |
|
355 (r'\n', String.Double) |
|
356 ], |
|
357 'tsqf': [ |
|
358 (r"'''", String.Single, '#pop'), |
|
359 include('fstrings-single'), |
|
360 (r'\n', String.Single) |
|
361 ], |
|
362 'tdqs': [ |
|
363 (r'"""', String.Double, '#pop'), |
|
364 include('strings-double'), |
|
365 (r'\n', String.Double) |
|
366 ], |
|
367 'tsqs': [ |
|
368 (r"'''", String.Single, '#pop'), |
|
369 include('strings-single'), |
|
370 (r'\n', String.Single) |
|
371 ], |
|
372 } |
|
373 |
|
374 def analyse_text(text): |
|
375 return shebang_matches(text, r'pythonw?(3(\.\d)?)?') |
|
376 |
|
377 |
|
378 Python3Lexer = PythonLexer |
|
379 |
|
380 |
|
381 class Python2Lexer(RegexLexer): |
|
382 """ |
|
383 For `Python 2.x <http://www.python.org>`_ source code. |
|
384 |
|
385 .. versionchanged:: 2.5 |
|
386 This class has been renamed from ``PythonLexer``. ``PythonLexer`` now |
|
387 refers to the Python 3 variant. File name patterns like ``*.py`` have |
|
388 been moved to Python 3 as well. |
|
389 """ |
|
390 |
|
391 name = 'Python 2.x' |
|
392 aliases = ['python2', 'py2'] |
|
393 filenames = [] # now taken over by PythonLexer (3.x) |
|
394 mimetypes = ['text/x-python2', 'application/x-python2'] |
|
395 |
|
396 def innerstring_rules(ttype): |
|
397 return [ |
|
398 # the old style '%s' % (...) string formatting |
|
399 (r'%(\(\w+\))?[-#0 +]*([0-9]+|[*])?(\.([0-9]+|[*]))?' |
|
400 '[hlL]?[E-GXc-giorsux%]', String.Interpol), |
|
401 # backslashes, quotes and formatting signs must be parsed one at a time |
|
402 (r'[^\\\'"%\n]+', ttype), |
|
403 (r'[\'"\\]', ttype), |
|
404 # unhandled string formatting sign |
|
405 (r'%', ttype), |
|
406 # newlines are an error (use "nl" state) |
|
407 ] |
|
408 |
|
409 tokens = { |
|
410 'root': [ |
|
411 (r'\n', Text), |
|
412 (r'^(\s*)([rRuUbB]{,2})("""(?:.|\n)*?""")', |
|
413 bygroups(Text, String.Affix, String.Doc)), |
|
414 (r"^(\s*)([rRuUbB]{,2})('''(?:.|\n)*?''')", |
|
415 bygroups(Text, String.Affix, String.Doc)), |
|
416 (r'[^\S\n]+', Text), |
|
417 (r'\A#!.+$', Comment.Hashbang), |
|
418 (r'#.*$', Comment.Single), |
|
419 (r'[]{}:(),;[]', Punctuation), |
|
420 (r'\\\n', Text), |
|
421 (r'\\', Text), |
|
422 (r'(in|is|and|or|not)\b', Operator.Word), |
|
423 (r'!=|==|<<|>>|[-~+/*%=<>&^|.]', Operator), |
|
424 include('keywords'), |
|
425 (r'(def)((?:\s|\\\s)+)', bygroups(Keyword, Text), 'funcname'), |
|
426 (r'(class)((?:\s|\\\s)+)', bygroups(Keyword, Text), 'classname'), |
|
427 (r'(from)((?:\s|\\\s)+)', bygroups(Keyword.Namespace, Text), |
|
428 'fromimport'), |
|
429 (r'(import)((?:\s|\\\s)+)', bygroups(Keyword.Namespace, Text), |
|
430 'import'), |
|
431 include('builtins'), |
|
432 include('magicfuncs'), |
|
433 include('magicvars'), |
|
434 include('backtick'), |
|
435 ('([rR]|[uUbB][rR]|[rR][uUbB])(""")', |
|
436 bygroups(String.Affix, String.Double), 'tdqs'), |
|
437 ("([rR]|[uUbB][rR]|[rR][uUbB])(''')", |
|
438 bygroups(String.Affix, String.Single), 'tsqs'), |
|
439 ('([rR]|[uUbB][rR]|[rR][uUbB])(")', |
|
440 bygroups(String.Affix, String.Double), 'dqs'), |
|
441 ("([rR]|[uUbB][rR]|[rR][uUbB])(')", |
|
442 bygroups(String.Affix, String.Single), 'sqs'), |
|
443 ('([uUbB]?)(""")', bygroups(String.Affix, String.Double), |
|
444 combined('stringescape', 'tdqs')), |
|
445 ("([uUbB]?)(''')", bygroups(String.Affix, String.Single), |
|
446 combined('stringescape', 'tsqs')), |
|
447 ('([uUbB]?)(")', bygroups(String.Affix, String.Double), |
|
448 combined('stringescape', 'dqs')), |
|
449 ("([uUbB]?)(')", bygroups(String.Affix, String.Single), |
|
450 combined('stringescape', 'sqs')), |
|
451 include('name'), |
|
452 include('numbers'), |
|
453 ], |
|
454 'keywords': [ |
|
455 (words(( |
|
456 'assert', 'break', 'continue', 'del', 'elif', 'else', 'except', |
|
457 'exec', 'finally', 'for', 'global', 'if', 'lambda', 'pass', |
|
458 'print', 'raise', 'return', 'try', 'while', 'yield', |
|
459 'yield from', 'as', 'with'), suffix=r'\b'), |
|
460 Keyword), |
|
461 ], |
|
462 'builtins': [ |
|
463 (words(( |
|
464 '__import__', 'abs', 'all', 'any', 'apply', 'basestring', 'bin', |
|
465 'bool', 'buffer', 'bytearray', 'bytes', 'callable', 'chr', 'classmethod', |
|
466 'cmp', 'coerce', 'compile', 'complex', 'delattr', 'dict', 'dir', 'divmod', |
|
467 'enumerate', 'eval', 'execfile', 'exit', 'file', 'filter', 'float', |
|
468 'frozenset', 'getattr', 'globals', 'hasattr', 'hash', 'hex', 'id', |
|
469 'input', 'int', 'intern', 'isinstance', 'issubclass', 'iter', 'len', |
|
470 'list', 'locals', 'long', 'map', 'max', 'min', 'next', 'object', |
|
471 'oct', 'open', 'ord', 'pow', 'property', 'range', 'raw_input', 'reduce', |
|
472 'reload', 'repr', 'reversed', 'round', 'set', 'setattr', 'slice', |
|
473 'sorted', 'staticmethod', 'str', 'sum', 'super', 'tuple', 'type', |
|
474 'unichr', 'unicode', 'vars', 'xrange', 'zip'), |
|
475 prefix=r'(?<!\.)', suffix=r'\b'), |
|
476 Name.Builtin), |
|
477 (r'(?<!\.)(self|None|Ellipsis|NotImplemented|False|True|cls' |
|
478 r')\b', Name.Builtin.Pseudo), |
|
479 (words(( |
|
480 'ArithmeticError', 'AssertionError', 'AttributeError', |
|
481 'BaseException', 'DeprecationWarning', 'EOFError', 'EnvironmentError', |
|
482 'Exception', 'FloatingPointError', 'FutureWarning', 'GeneratorExit', |
|
483 'IOError', 'ImportError', 'ImportWarning', 'IndentationError', |
|
484 'IndexError', 'KeyError', 'KeyboardInterrupt', 'LookupError', |
|
485 'MemoryError', 'NameError', |
|
486 'NotImplementedError', 'OSError', 'OverflowError', 'OverflowWarning', |
|
487 'PendingDeprecationWarning', 'ReferenceError', |
|
488 'RuntimeError', 'RuntimeWarning', 'StandardError', 'StopIteration', |
|
489 'SyntaxError', 'SyntaxWarning', 'SystemError', 'SystemExit', |
|
490 'TabError', 'TypeError', 'UnboundLocalError', 'UnicodeDecodeError', |
|
491 'UnicodeEncodeError', 'UnicodeError', 'UnicodeTranslateError', |
|
492 'UnicodeWarning', 'UserWarning', 'ValueError', 'VMSError', 'Warning', |
|
493 'WindowsError', 'ZeroDivisionError'), prefix=r'(?<!\.)', suffix=r'\b'), |
|
494 Name.Exception), |
|
495 ], |
|
496 'magicfuncs': [ |
|
497 (words(( |
|
498 '__abs__', '__add__', '__and__', '__call__', '__cmp__', '__coerce__', |
|
499 '__complex__', '__contains__', '__del__', '__delattr__', '__delete__', |
|
500 '__delitem__', '__delslice__', '__div__', '__divmod__', '__enter__', |
|
501 '__eq__', '__exit__', '__float__', '__floordiv__', '__ge__', '__get__', |
|
502 '__getattr__', '__getattribute__', '__getitem__', '__getslice__', '__gt__', |
|
503 '__hash__', '__hex__', '__iadd__', '__iand__', '__idiv__', '__ifloordiv__', |
|
504 '__ilshift__', '__imod__', '__imul__', '__index__', '__init__', |
|
505 '__instancecheck__', '__int__', '__invert__', '__iop__', '__ior__', |
|
506 '__ipow__', '__irshift__', '__isub__', '__iter__', '__itruediv__', |
|
507 '__ixor__', '__le__', '__len__', '__long__', '__lshift__', '__lt__', |
|
508 '__missing__', '__mod__', '__mul__', '__ne__', '__neg__', '__new__', |
|
509 '__nonzero__', '__oct__', '__op__', '__or__', '__pos__', '__pow__', |
|
510 '__radd__', '__rand__', '__rcmp__', '__rdiv__', '__rdivmod__', '__repr__', |
|
511 '__reversed__', '__rfloordiv__', '__rlshift__', '__rmod__', '__rmul__', |
|
512 '__rop__', '__ror__', '__rpow__', '__rrshift__', '__rshift__', '__rsub__', |
|
513 '__rtruediv__', '__rxor__', '__set__', '__setattr__', '__setitem__', |
|
514 '__setslice__', '__str__', '__sub__', '__subclasscheck__', '__truediv__', |
|
515 '__unicode__', '__xor__'), suffix=r'\b'), |
|
516 Name.Function.Magic), |
|
517 ], |
|
518 'magicvars': [ |
|
519 (words(( |
|
520 '__bases__', '__class__', '__closure__', '__code__', '__defaults__', |
|
521 '__dict__', '__doc__', '__file__', '__func__', '__globals__', |
|
522 '__metaclass__', '__module__', '__mro__', '__name__', '__self__', |
|
523 '__slots__', '__weakref__'), |
|
524 suffix=r'\b'), |
|
525 Name.Variable.Magic), |
|
526 ], |
|
527 'numbers': [ |
|
528 (r'(\d+\.\d*|\d*\.\d+)([eE][+-]?[0-9]+)?j?', Number.Float), |
|
529 (r'\d+[eE][+-]?[0-9]+j?', Number.Float), |
|
530 (r'0[0-7]+j?', Number.Oct), |
|
531 (r'0[bB][01]+', Number.Bin), |
|
532 (r'0[xX][a-fA-F0-9]+', Number.Hex), |
|
533 (r'\d+L', Number.Integer.Long), |
|
534 (r'\d+j?', Number.Integer) |
|
535 ], |
|
536 'backtick': [ |
|
537 ('`.*?`', String.Backtick), |
|
538 ], |
|
539 'name': [ |
|
540 (r'@[\w.]+', Name.Decorator), |
|
541 (r'[a-zA-Z_]\w*', Name), |
|
542 ], |
|
543 'funcname': [ |
|
544 include('magicfuncs'), |
|
545 (r'[a-zA-Z_]\w*', Name.Function, '#pop'), |
|
546 default('#pop'), |
|
547 ], |
|
548 'classname': [ |
|
549 (r'[a-zA-Z_]\w*', Name.Class, '#pop') |
|
550 ], |
|
551 'import': [ |
|
552 (r'(?:[ \t]|\\\n)+', Text), |
|
553 (r'as\b', Keyword.Namespace), |
|
554 (r',', Operator), |
|
555 (r'[a-zA-Z_][\w.]*', Name.Namespace), |
|
556 default('#pop') # all else: go back |
|
557 ], |
|
558 'fromimport': [ |
|
559 (r'(?:[ \t]|\\\n)+', Text), |
|
560 (r'import\b', Keyword.Namespace, '#pop'), |
|
561 # if None occurs here, it's "raise x from None", since None can |
|
562 # never be a module name |
|
563 (r'None\b', Name.Builtin.Pseudo, '#pop'), |
|
564 # sadly, in "raise x from y" y will be highlighted as namespace too |
|
565 (r'[a-zA-Z_.][\w.]*', Name.Namespace), |
|
566 # anything else here also means "raise x from y" and is therefore |
|
567 # not an error |
|
568 default('#pop'), |
|
569 ], |
|
570 'stringescape': [ |
|
571 (r'\\([\\abfnrtv"\']|\n|N\{.*?\}|u[a-fA-F0-9]{4}|' |
|
572 r'U[a-fA-F0-9]{8}|x[a-fA-F0-9]{2}|[0-7]{1,3})', String.Escape) |
|
573 ], |
|
574 'strings-single': innerstring_rules(String.Single), |
|
575 'strings-double': innerstring_rules(String.Double), |
|
576 'dqs': [ |
|
577 (r'"', String.Double, '#pop'), |
|
578 (r'\\\\|\\"|\\\n', String.Escape), # included here for raw strings |
|
579 include('strings-double') |
|
580 ], |
|
581 'sqs': [ |
|
582 (r"'", String.Single, '#pop'), |
|
583 (r"\\\\|\\'|\\\n", String.Escape), # included here for raw strings |
|
584 include('strings-single') |
|
585 ], |
|
586 'tdqs': [ |
|
587 (r'"""', String.Double, '#pop'), |
|
588 include('strings-double'), |
|
589 (r'\n', String.Double) |
|
590 ], |
|
591 'tsqs': [ |
|
592 (r"'''", String.Single, '#pop'), |
|
593 include('strings-single'), |
|
594 (r'\n', String.Single) |
|
595 ], |
|
596 } |
|
597 |
|
598 def analyse_text(text): |
|
599 return shebang_matches(text, r'pythonw?2(\.\d)?') or \ |
|
600 'import ' in text[:1000] |
|
601 |
|
602 |
|
603 class PythonConsoleLexer(Lexer): |
|
604 """ |
|
605 For Python console output or doctests, such as: |
|
606 |
|
607 .. sourcecode:: pycon |
|
608 |
|
609 >>> a = 'foo' |
|
610 >>> print a |
|
611 foo |
|
612 >>> 1 / 0 |
|
613 Traceback (most recent call last): |
|
614 File "<stdin>", line 1, in <module> |
|
615 ZeroDivisionError: integer division or modulo by zero |
|
616 |
|
617 Additional options: |
|
618 |
|
619 `python3` |
|
620 Use Python 3 lexer for code. Default is ``True``. |
|
621 |
|
622 .. versionadded:: 1.0 |
|
623 .. versionchanged:: 2.5 |
|
624 Now defaults to ``True``. |
|
625 """ |
|
626 name = 'Python console session' |
|
627 aliases = ['pycon'] |
|
628 mimetypes = ['text/x-python-doctest'] |
|
629 |
|
630 def __init__(self, **options): |
|
631 self.python3 = get_bool_opt(options, 'python3', True) |
|
632 Lexer.__init__(self, **options) |
|
633 |
|
634 def get_tokens_unprocessed(self, text): |
|
635 if self.python3: |
|
636 pylexer = PythonLexer(**self.options) |
|
637 tblexer = PythonTracebackLexer(**self.options) |
|
638 else: |
|
639 pylexer = Python2Lexer(**self.options) |
|
640 tblexer = Python2TracebackLexer(**self.options) |
|
641 |
|
642 curcode = '' |
|
643 insertions = [] |
|
644 curtb = '' |
|
645 tbindex = 0 |
|
646 tb = 0 |
|
647 for match in line_re.finditer(text): |
|
648 line = match.group() |
|
649 if line.startswith('>>> ') or line.startswith('... '): |
|
650 tb = 0 |
|
651 insertions.append((len(curcode), |
|
652 [(0, Generic.Prompt, line[:4])])) |
|
653 curcode += line[4:] |
|
654 elif line.rstrip() == '...' and not tb: |
|
655 # only a new >>> prompt can end an exception block |
|
656 # otherwise an ellipsis in place of the traceback frames |
|
657 # will be mishandled |
|
658 insertions.append((len(curcode), |
|
659 [(0, Generic.Prompt, '...')])) |
|
660 curcode += line[3:] |
|
661 else: |
|
662 if curcode: |
|
663 yield from do_insertions( |
|
664 insertions, pylexer.get_tokens_unprocessed(curcode)) |
|
665 curcode = '' |
|
666 insertions = [] |
|
667 if (line.startswith('Traceback (most recent call last):') or |
|
668 re.match(' File "[^"]+", line \\d+\\n$', line)): |
|
669 tb = 1 |
|
670 curtb = line |
|
671 tbindex = match.start() |
|
672 elif line == 'KeyboardInterrupt\n': |
|
673 yield match.start(), Name.Class, line |
|
674 elif tb: |
|
675 curtb += line |
|
676 if not (line.startswith(' ') or line.strip() == '...'): |
|
677 tb = 0 |
|
678 for i, t, v in tblexer.get_tokens_unprocessed(curtb): |
|
679 yield tbindex+i, t, v |
|
680 curtb = '' |
|
681 else: |
|
682 yield match.start(), Generic.Output, line |
|
683 if curcode: |
|
684 yield from do_insertions(insertions, |
|
685 pylexer.get_tokens_unprocessed(curcode)) |
|
686 if curtb: |
|
687 for i, t, v in tblexer.get_tokens_unprocessed(curtb): |
|
688 yield tbindex+i, t, v |
|
689 |
|
690 |
|
691 class PythonTracebackLexer(RegexLexer): |
|
692 """ |
|
693 For Python 3.x tracebacks, with support for chained exceptions. |
|
694 |
|
695 .. versionadded:: 1.0 |
|
696 |
|
697 .. versionchanged:: 2.5 |
|
698 This is now the default ``PythonTracebackLexer``. It is still available |
|
699 as the alias ``Python3TracebackLexer``. |
|
700 """ |
|
701 |
|
702 name = 'Python Traceback' |
|
703 aliases = ['pytb', 'py3tb'] |
|
704 filenames = ['*.pytb', '*.py3tb'] |
|
705 mimetypes = ['text/x-python-traceback', 'text/x-python3-traceback'] |
|
706 |
|
707 tokens = { |
|
708 'root': [ |
|
709 (r'\n', Text), |
|
710 (r'^Traceback \(most recent call last\):\n', Generic.Traceback, 'intb'), |
|
711 (r'^During handling of the above exception, another ' |
|
712 r'exception occurred:\n\n', Generic.Traceback), |
|
713 (r'^The above exception was the direct cause of the ' |
|
714 r'following exception:\n\n', Generic.Traceback), |
|
715 (r'^(?= File "[^"]+", line \d+)', Generic.Traceback, 'intb'), |
|
716 (r'^.*\n', Other), |
|
717 ], |
|
718 'intb': [ |
|
719 (r'^( File )("[^"]+")(, line )(\d+)(, in )(.+)(\n)', |
|
720 bygroups(Text, Name.Builtin, Text, Number, Text, Name, Text)), |
|
721 (r'^( File )("[^"]+")(, line )(\d+)(\n)', |
|
722 bygroups(Text, Name.Builtin, Text, Number, Text)), |
|
723 (r'^( )(.+)(\n)', |
|
724 bygroups(Text, using(PythonLexer), Text)), |
|
725 (r'^([ \t]*)(\.\.\.)(\n)', |
|
726 bygroups(Text, Comment, Text)), # for doctests... |
|
727 (r'^([^:]+)(: )(.+)(\n)', |
|
728 bygroups(Generic.Error, Text, Name, Text), '#pop'), |
|
729 (r'^([a-zA-Z_][\w.]*)(:?\n)', |
|
730 bygroups(Generic.Error, Text), '#pop') |
|
731 ], |
|
732 } |
|
733 |
|
734 |
|
735 Python3TracebackLexer = PythonTracebackLexer |
|
736 |
|
737 |
|
738 class Python2TracebackLexer(RegexLexer): |
|
739 """ |
|
740 For Python tracebacks. |
|
741 |
|
742 .. versionadded:: 0.7 |
|
743 |
|
744 .. versionchanged:: 2.5 |
|
745 This class has been renamed from ``PythonTracebackLexer``. |
|
746 ``PythonTracebackLexer`` now refers to the Python 3 variant. |
|
747 """ |
|
748 |
|
749 name = 'Python 2.x Traceback' |
|
750 aliases = ['py2tb'] |
|
751 filenames = ['*.py2tb'] |
|
752 mimetypes = ['text/x-python2-traceback'] |
|
753 |
|
754 tokens = { |
|
755 'root': [ |
|
756 # Cover both (most recent call last) and (innermost last) |
|
757 # The optional ^C allows us to catch keyboard interrupt signals. |
|
758 (r'^(\^C)?(Traceback.*\n)', |
|
759 bygroups(Text, Generic.Traceback), 'intb'), |
|
760 # SyntaxError starts with this. |
|
761 (r'^(?= File "[^"]+", line \d+)', Generic.Traceback, 'intb'), |
|
762 (r'^.*\n', Other), |
|
763 ], |
|
764 'intb': [ |
|
765 (r'^( File )("[^"]+")(, line )(\d+)(, in )(.+)(\n)', |
|
766 bygroups(Text, Name.Builtin, Text, Number, Text, Name, Text)), |
|
767 (r'^( File )("[^"]+")(, line )(\d+)(\n)', |
|
768 bygroups(Text, Name.Builtin, Text, Number, Text)), |
|
769 (r'^( )(.+)(\n)', |
|
770 bygroups(Text, using(Python2Lexer), Text)), |
|
771 (r'^([ \t]*)(\.\.\.)(\n)', |
|
772 bygroups(Text, Comment, Text)), # for doctests... |
|
773 (r'^([^:]+)(: )(.+)(\n)', |
|
774 bygroups(Generic.Error, Text, Name, Text), '#pop'), |
|
775 (r'^([a-zA-Z_]\w*)(:?\n)', |
|
776 bygroups(Generic.Error, Text), '#pop') |
|
777 ], |
|
778 } |
|
779 |
|
780 |
|
781 class CythonLexer(RegexLexer): |
|
782 """ |
|
783 For Pyrex and `Cython <http://cython.org>`_ source code. |
|
784 |
|
785 .. versionadded:: 1.1 |
|
786 """ |
|
787 |
|
788 name = 'Cython' |
|
789 aliases = ['cython', 'pyx', 'pyrex'] |
|
790 filenames = ['*.pyx', '*.pxd', '*.pxi'] |
|
791 mimetypes = ['text/x-cython', 'application/x-cython'] |
|
792 |
|
793 tokens = { |
|
794 'root': [ |
|
795 (r'\n', Text), |
|
796 (r'^(\s*)("""(?:.|\n)*?""")', bygroups(Text, String.Doc)), |
|
797 (r"^(\s*)('''(?:.|\n)*?''')", bygroups(Text, String.Doc)), |
|
798 (r'[^\S\n]+', Text), |
|
799 (r'#.*$', Comment), |
|
800 (r'[]{}:(),;[]', Punctuation), |
|
801 (r'\\\n', Text), |
|
802 (r'\\', Text), |
|
803 (r'(in|is|and|or|not)\b', Operator.Word), |
|
804 (r'(<)([a-zA-Z0-9.?]+)(>)', |
|
805 bygroups(Punctuation, Keyword.Type, Punctuation)), |
|
806 (r'!=|==|<<|>>|[-~+/*%=<>&^|.?]', Operator), |
|
807 (r'(from)(\d+)(<=)(\s+)(<)(\d+)(:)', |
|
808 bygroups(Keyword, Number.Integer, Operator, Name, Operator, |
|
809 Name, Punctuation)), |
|
810 include('keywords'), |
|
811 (r'(def|property)(\s+)', bygroups(Keyword, Text), 'funcname'), |
|
812 (r'(cp?def)(\s+)', bygroups(Keyword, Text), 'cdef'), |
|
813 # (should actually start a block with only cdefs) |
|
814 (r'(cdef)(:)', bygroups(Keyword, Punctuation)), |
|
815 (r'(class|struct)(\s+)', bygroups(Keyword, Text), 'classname'), |
|
816 (r'(from)(\s+)', bygroups(Keyword, Text), 'fromimport'), |
|
817 (r'(c?import)(\s+)', bygroups(Keyword, Text), 'import'), |
|
818 include('builtins'), |
|
819 include('backtick'), |
|
820 ('(?:[rR]|[uU][rR]|[rR][uU])"""', String, 'tdqs'), |
|
821 ("(?:[rR]|[uU][rR]|[rR][uU])'''", String, 'tsqs'), |
|
822 ('(?:[rR]|[uU][rR]|[rR][uU])"', String, 'dqs'), |
|
823 ("(?:[rR]|[uU][rR]|[rR][uU])'", String, 'sqs'), |
|
824 ('[uU]?"""', String, combined('stringescape', 'tdqs')), |
|
825 ("[uU]?'''", String, combined('stringescape', 'tsqs')), |
|
826 ('[uU]?"', String, combined('stringescape', 'dqs')), |
|
827 ("[uU]?'", String, combined('stringescape', 'sqs')), |
|
828 include('name'), |
|
829 include('numbers'), |
|
830 ], |
|
831 'keywords': [ |
|
832 (words(( |
|
833 'assert', 'async', 'await', 'break', 'by', 'continue', 'ctypedef', 'del', 'elif', |
|
834 'else', 'except', 'except?', 'exec', 'finally', 'for', 'fused', 'gil', |
|
835 'global', 'if', 'include', 'lambda', 'nogil', 'pass', 'print', |
|
836 'raise', 'return', 'try', 'while', 'yield', 'as', 'with'), suffix=r'\b'), |
|
837 Keyword), |
|
838 (r'(DEF|IF|ELIF|ELSE)\b', Comment.Preproc), |
|
839 ], |
|
840 'builtins': [ |
|
841 (words(( |
|
842 '__import__', 'abs', 'all', 'any', 'apply', 'basestring', 'bin', |
|
843 'bool', 'buffer', 'bytearray', 'bytes', 'callable', 'chr', |
|
844 'classmethod', 'cmp', 'coerce', 'compile', 'complex', 'delattr', |
|
845 'dict', 'dir', 'divmod', 'enumerate', 'eval', 'execfile', 'exit', |
|
846 'file', 'filter', 'float', 'frozenset', 'getattr', 'globals', |
|
847 'hasattr', 'hash', 'hex', 'id', 'input', 'int', 'intern', 'isinstance', |
|
848 'issubclass', 'iter', 'len', 'list', 'locals', 'long', 'map', 'max', |
|
849 'min', 'next', 'object', 'oct', 'open', 'ord', 'pow', 'property', |
|
850 'range', 'raw_input', 'reduce', 'reload', 'repr', 'reversed', |
|
851 'round', 'set', 'setattr', 'slice', 'sorted', 'staticmethod', |
|
852 'str', 'sum', 'super', 'tuple', 'type', 'unichr', 'unicode', 'unsigned', |
|
853 'vars', 'xrange', 'zip'), prefix=r'(?<!\.)', suffix=r'\b'), |
|
854 Name.Builtin), |
|
855 (r'(?<!\.)(self|None|Ellipsis|NotImplemented|False|True|NULL' |
|
856 r')\b', Name.Builtin.Pseudo), |
|
857 (words(( |
|
858 'ArithmeticError', 'AssertionError', 'AttributeError', |
|
859 'BaseException', 'DeprecationWarning', 'EOFError', 'EnvironmentError', |
|
860 'Exception', 'FloatingPointError', 'FutureWarning', 'GeneratorExit', |
|
861 'IOError', 'ImportError', 'ImportWarning', 'IndentationError', |
|
862 'IndexError', 'KeyError', 'KeyboardInterrupt', 'LookupError', |
|
863 'MemoryError', 'NameError', 'NotImplemented', 'NotImplementedError', |
|
864 'OSError', 'OverflowError', 'OverflowWarning', |
|
865 'PendingDeprecationWarning', 'ReferenceError', 'RuntimeError', |
|
866 'RuntimeWarning', 'StandardError', 'StopIteration', 'SyntaxError', |
|
867 'SyntaxWarning', 'SystemError', 'SystemExit', 'TabError', |
|
868 'TypeError', 'UnboundLocalError', 'UnicodeDecodeError', |
|
869 'UnicodeEncodeError', 'UnicodeError', 'UnicodeTranslateError', |
|
870 'UnicodeWarning', 'UserWarning', 'ValueError', 'Warning', |
|
871 'ZeroDivisionError'), prefix=r'(?<!\.)', suffix=r'\b'), |
|
872 Name.Exception), |
|
873 ], |
|
874 'numbers': [ |
|
875 (r'(\d+\.?\d*|\d*\.\d+)([eE][+-]?[0-9]+)?', Number.Float), |
|
876 (r'0\d+', Number.Oct), |
|
877 (r'0[xX][a-fA-F0-9]+', Number.Hex), |
|
878 (r'\d+L', Number.Integer.Long), |
|
879 (r'\d+', Number.Integer) |
|
880 ], |
|
881 'backtick': [ |
|
882 ('`.*?`', String.Backtick), |
|
883 ], |
|
884 'name': [ |
|
885 (r'@\w+', Name.Decorator), |
|
886 (r'[a-zA-Z_]\w*', Name), |
|
887 ], |
|
888 'funcname': [ |
|
889 (r'[a-zA-Z_]\w*', Name.Function, '#pop') |
|
890 ], |
|
891 'cdef': [ |
|
892 (r'(public|readonly|extern|api|inline)\b', Keyword.Reserved), |
|
893 (r'(struct|enum|union|class)\b', Keyword), |
|
894 (r'([a-zA-Z_]\w*)(\s*)(?=[(:#=]|$)', |
|
895 bygroups(Name.Function, Text), '#pop'), |
|
896 (r'([a-zA-Z_]\w*)(\s*)(,)', |
|
897 bygroups(Name.Function, Text, Punctuation)), |
|
898 (r'from\b', Keyword, '#pop'), |
|
899 (r'as\b', Keyword), |
|
900 (r':', Punctuation, '#pop'), |
|
901 (r'(?=["\'])', Text, '#pop'), |
|
902 (r'[a-zA-Z_]\w*', Keyword.Type), |
|
903 (r'.', Text), |
|
904 ], |
|
905 'classname': [ |
|
906 (r'[a-zA-Z_]\w*', Name.Class, '#pop') |
|
907 ], |
|
908 'import': [ |
|
909 (r'(\s+)(as)(\s+)', bygroups(Text, Keyword, Text)), |
|
910 (r'[a-zA-Z_][\w.]*', Name.Namespace), |
|
911 (r'(\s*)(,)(\s*)', bygroups(Text, Operator, Text)), |
|
912 default('#pop') # all else: go back |
|
913 ], |
|
914 'fromimport': [ |
|
915 (r'(\s+)(c?import)\b', bygroups(Text, Keyword), '#pop'), |
|
916 (r'[a-zA-Z_.][\w.]*', Name.Namespace), |
|
917 # ``cdef foo from "header"``, or ``for foo from 0 < i < 10`` |
|
918 default('#pop'), |
|
919 ], |
|
920 'stringescape': [ |
|
921 (r'\\([\\abfnrtv"\']|\n|N\{.*?\}|u[a-fA-F0-9]{4}|' |
|
922 r'U[a-fA-F0-9]{8}|x[a-fA-F0-9]{2}|[0-7]{1,3})', String.Escape) |
|
923 ], |
|
924 'strings': [ |
|
925 (r'%(\([a-zA-Z0-9]+\))?[-#0 +]*([0-9]+|[*])?(\.([0-9]+|[*]))?' |
|
926 '[hlL]?[E-GXc-giorsux%]', String.Interpol), |
|
927 (r'[^\\\'"%\n]+', String), |
|
928 # quotes, percents and backslashes must be parsed one at a time |
|
929 (r'[\'"\\]', String), |
|
930 # unhandled string formatting sign |
|
931 (r'%', String) |
|
932 # newlines are an error (use "nl" state) |
|
933 ], |
|
934 'nl': [ |
|
935 (r'\n', String) |
|
936 ], |
|
937 'dqs': [ |
|
938 (r'"', String, '#pop'), |
|
939 (r'\\\\|\\"|\\\n', String.Escape), # included here again for raw strings |
|
940 include('strings') |
|
941 ], |
|
942 'sqs': [ |
|
943 (r"'", String, '#pop'), |
|
944 (r"\\\\|\\'|\\\n", String.Escape), # included here again for raw strings |
|
945 include('strings') |
|
946 ], |
|
947 'tdqs': [ |
|
948 (r'"""', String, '#pop'), |
|
949 include('strings'), |
|
950 include('nl') |
|
951 ], |
|
952 'tsqs': [ |
|
953 (r"'''", String, '#pop'), |
|
954 include('strings'), |
|
955 include('nl') |
|
956 ], |
|
957 } |
|
958 |
|
959 |
|
960 class DgLexer(RegexLexer): |
|
961 """ |
|
962 Lexer for `dg <http://pyos.github.com/dg>`_, |
|
963 a functional and object-oriented programming language |
|
964 running on the CPython 3 VM. |
|
965 |
|
966 .. versionadded:: 1.6 |
|
967 """ |
|
968 name = 'dg' |
|
969 aliases = ['dg'] |
|
970 filenames = ['*.dg'] |
|
971 mimetypes = ['text/x-dg'] |
|
972 |
|
973 tokens = { |
|
974 'root': [ |
|
975 (r'\s+', Text), |
|
976 (r'#.*?$', Comment.Single), |
|
977 |
|
978 (r'(?i)0b[01]+', Number.Bin), |
|
979 (r'(?i)0o[0-7]+', Number.Oct), |
|
980 (r'(?i)0x[0-9a-f]+', Number.Hex), |
|
981 (r'(?i)[+-]?[0-9]+\.[0-9]+(e[+-]?[0-9]+)?j?', Number.Float), |
|
982 (r'(?i)[+-]?[0-9]+e[+-]?\d+j?', Number.Float), |
|
983 (r'(?i)[+-]?[0-9]+j?', Number.Integer), |
|
984 |
|
985 (r"(?i)(br|r?b?)'''", String, combined('stringescape', 'tsqs', 'string')), |
|
986 (r'(?i)(br|r?b?)"""', String, combined('stringescape', 'tdqs', 'string')), |
|
987 (r"(?i)(br|r?b?)'", String, combined('stringescape', 'sqs', 'string')), |
|
988 (r'(?i)(br|r?b?)"', String, combined('stringescape', 'dqs', 'string')), |
|
989 |
|
990 (r"`\w+'*`", Operator), |
|
991 (r'\b(and|in|is|or|where)\b', Operator.Word), |
|
992 (r'[!$%&*+\-./:<-@\\^|~;,]+', Operator), |
|
993 |
|
994 (words(( |
|
995 'bool', 'bytearray', 'bytes', 'classmethod', 'complex', 'dict', 'dict\'', |
|
996 'float', 'frozenset', 'int', 'list', 'list\'', 'memoryview', 'object', |
|
997 'property', 'range', 'set', 'set\'', 'slice', 'staticmethod', 'str', |
|
998 'super', 'tuple', 'tuple\'', 'type'), |
|
999 prefix=r'(?<!\.)', suffix=r'(?![\'\w])'), |
|
1000 Name.Builtin), |
|
1001 (words(( |
|
1002 '__import__', 'abs', 'all', 'any', 'bin', 'bind', 'chr', 'cmp', 'compile', |
|
1003 'complex', 'delattr', 'dir', 'divmod', 'drop', 'dropwhile', 'enumerate', |
|
1004 'eval', 'exhaust', 'filter', 'flip', 'foldl1?', 'format', 'fst', |
|
1005 'getattr', 'globals', 'hasattr', 'hash', 'head', 'hex', 'id', 'init', |
|
1006 'input', 'isinstance', 'issubclass', 'iter', 'iterate', 'last', 'len', |
|
1007 'locals', 'map', 'max', 'min', 'next', 'oct', 'open', 'ord', 'pow', |
|
1008 'print', 'repr', 'reversed', 'round', 'setattr', 'scanl1?', 'snd', |
|
1009 'sorted', 'sum', 'tail', 'take', 'takewhile', 'vars', 'zip'), |
|
1010 prefix=r'(?<!\.)', suffix=r'(?![\'\w])'), |
|
1011 Name.Builtin), |
|
1012 (r"(?<!\.)(self|Ellipsis|NotImplemented|None|True|False)(?!['\w])", |
|
1013 Name.Builtin.Pseudo), |
|
1014 |
|
1015 (r"(?<!\.)[A-Z]\w*(Error|Exception|Warning)'*(?!['\w])", |
|
1016 Name.Exception), |
|
1017 (r"(?<!\.)(Exception|GeneratorExit|KeyboardInterrupt|StopIteration|" |
|
1018 r"SystemExit)(?!['\w])", Name.Exception), |
|
1019 |
|
1020 (r"(?<![\w.])(except|finally|for|if|import|not|otherwise|raise|" |
|
1021 r"subclass|while|with|yield)(?!['\w])", Keyword.Reserved), |
|
1022 |
|
1023 (r"[A-Z_]+'*(?!['\w])", Name), |
|
1024 (r"[A-Z]\w+'*(?!['\w])", Keyword.Type), |
|
1025 (r"\w+'*", Name), |
|
1026 |
|
1027 (r'[()]', Punctuation), |
|
1028 (r'.', Error), |
|
1029 ], |
|
1030 'stringescape': [ |
|
1031 (r'\\([\\abfnrtv"\']|\n|N\{.*?\}|u[a-fA-F0-9]{4}|' |
|
1032 r'U[a-fA-F0-9]{8}|x[a-fA-F0-9]{2}|[0-7]{1,3})', String.Escape) |
|
1033 ], |
|
1034 'string': [ |
|
1035 (r'%(\(\w+\))?[-#0 +]*([0-9]+|[*])?(\.([0-9]+|[*]))?' |
|
1036 '[hlL]?[E-GXc-giorsux%]', String.Interpol), |
|
1037 (r'[^\\\'"%\n]+', String), |
|
1038 # quotes, percents and backslashes must be parsed one at a time |
|
1039 (r'[\'"\\]', String), |
|
1040 # unhandled string formatting sign |
|
1041 (r'%', String), |
|
1042 (r'\n', String) |
|
1043 ], |
|
1044 'dqs': [ |
|
1045 (r'"', String, '#pop') |
|
1046 ], |
|
1047 'sqs': [ |
|
1048 (r"'", String, '#pop') |
|
1049 ], |
|
1050 'tdqs': [ |
|
1051 (r'"""', String, '#pop') |
|
1052 ], |
|
1053 'tsqs': [ |
|
1054 (r"'''", String, '#pop') |
|
1055 ], |
|
1056 } |
|
1057 |
|
1058 |
|
1059 class NumPyLexer(PythonLexer): |
|
1060 """ |
|
1061 A Python lexer recognizing Numerical Python builtins. |
|
1062 |
|
1063 .. versionadded:: 0.10 |
|
1064 """ |
|
1065 |
|
1066 name = 'NumPy' |
|
1067 aliases = ['numpy'] |
|
1068 |
|
1069 # override the mimetypes to not inherit them from python |
|
1070 mimetypes = [] |
|
1071 filenames = [] |
|
1072 |
|
1073 EXTRA_KEYWORDS = { |
|
1074 'abs', 'absolute', 'accumulate', 'add', 'alen', 'all', 'allclose', |
|
1075 'alltrue', 'alterdot', 'amax', 'amin', 'angle', 'any', 'append', |
|
1076 'apply_along_axis', 'apply_over_axes', 'arange', 'arccos', 'arccosh', |
|
1077 'arcsin', 'arcsinh', 'arctan', 'arctan2', 'arctanh', 'argmax', 'argmin', |
|
1078 'argsort', 'argwhere', 'around', 'array', 'array2string', 'array_equal', |
|
1079 'array_equiv', 'array_repr', 'array_split', 'array_str', 'arrayrange', |
|
1080 'asanyarray', 'asarray', 'asarray_chkfinite', 'ascontiguousarray', |
|
1081 'asfarray', 'asfortranarray', 'asmatrix', 'asscalar', 'astype', |
|
1082 'atleast_1d', 'atleast_2d', 'atleast_3d', 'average', 'bartlett', |
|
1083 'base_repr', 'beta', 'binary_repr', 'bincount', 'binomial', |
|
1084 'bitwise_and', 'bitwise_not', 'bitwise_or', 'bitwise_xor', 'blackman', |
|
1085 'bmat', 'broadcast', 'byte_bounds', 'bytes', 'byteswap', 'c_', |
|
1086 'can_cast', 'ceil', 'choose', 'clip', 'column_stack', 'common_type', |
|
1087 'compare_chararrays', 'compress', 'concatenate', 'conj', 'conjugate', |
|
1088 'convolve', 'copy', 'corrcoef', 'correlate', 'cos', 'cosh', 'cov', |
|
1089 'cross', 'cumprod', 'cumproduct', 'cumsum', 'delete', 'deprecate', |
|
1090 'diag', 'diagflat', 'diagonal', 'diff', 'digitize', 'disp', 'divide', |
|
1091 'dot', 'dsplit', 'dstack', 'dtype', 'dump', 'dumps', 'ediff1d', 'empty', |
|
1092 'empty_like', 'equal', 'exp', 'expand_dims', 'expm1', 'extract', 'eye', |
|
1093 'fabs', 'fastCopyAndTranspose', 'fft', 'fftfreq', 'fftshift', 'fill', |
|
1094 'finfo', 'fix', 'flat', 'flatnonzero', 'flatten', 'fliplr', 'flipud', |
|
1095 'floor', 'floor_divide', 'fmod', 'frexp', 'fromarrays', 'frombuffer', |
|
1096 'fromfile', 'fromfunction', 'fromiter', 'frompyfunc', 'fromstring', |
|
1097 'generic', 'get_array_wrap', 'get_include', 'get_numarray_include', |
|
1098 'get_numpy_include', 'get_printoptions', 'getbuffer', 'getbufsize', |
|
1099 'geterr', 'geterrcall', 'geterrobj', 'getfield', 'gradient', 'greater', |
|
1100 'greater_equal', 'gumbel', 'hamming', 'hanning', 'histogram', |
|
1101 'histogram2d', 'histogramdd', 'hsplit', 'hstack', 'hypot', 'i0', |
|
1102 'identity', 'ifft', 'imag', 'index_exp', 'indices', 'inf', 'info', |
|
1103 'inner', 'insert', 'int_asbuffer', 'interp', 'intersect1d', |
|
1104 'intersect1d_nu', 'inv', 'invert', 'iscomplex', 'iscomplexobj', |
|
1105 'isfinite', 'isfortran', 'isinf', 'isnan', 'isneginf', 'isposinf', |
|
1106 'isreal', 'isrealobj', 'isscalar', 'issctype', 'issubclass_', |
|
1107 'issubdtype', 'issubsctype', 'item', 'itemset', 'iterable', 'ix_', |
|
1108 'kaiser', 'kron', 'ldexp', 'left_shift', 'less', 'less_equal', 'lexsort', |
|
1109 'linspace', 'load', 'loads', 'loadtxt', 'log', 'log10', 'log1p', 'log2', |
|
1110 'logical_and', 'logical_not', 'logical_or', 'logical_xor', 'logspace', |
|
1111 'lstsq', 'mat', 'matrix', 'max', 'maximum', 'maximum_sctype', |
|
1112 'may_share_memory', 'mean', 'median', 'meshgrid', 'mgrid', 'min', |
|
1113 'minimum', 'mintypecode', 'mod', 'modf', 'msort', 'multiply', 'nan', |
|
1114 'nan_to_num', 'nanargmax', 'nanargmin', 'nanmax', 'nanmin', 'nansum', |
|
1115 'ndenumerate', 'ndim', 'ndindex', 'negative', 'newaxis', 'newbuffer', |
|
1116 'newbyteorder', 'nonzero', 'not_equal', 'obj2sctype', 'ogrid', 'ones', |
|
1117 'ones_like', 'outer', 'permutation', 'piecewise', 'pinv', 'pkgload', |
|
1118 'place', 'poisson', 'poly', 'poly1d', 'polyadd', 'polyder', 'polydiv', |
|
1119 'polyfit', 'polyint', 'polymul', 'polysub', 'polyval', 'power', 'prod', |
|
1120 'product', 'ptp', 'put', 'putmask', 'r_', 'randint', 'random_integers', |
|
1121 'random_sample', 'ranf', 'rank', 'ravel', 'real', 'real_if_close', |
|
1122 'recarray', 'reciprocal', 'reduce', 'remainder', 'repeat', 'require', |
|
1123 'reshape', 'resize', 'restoredot', 'right_shift', 'rint', 'roll', |
|
1124 'rollaxis', 'roots', 'rot90', 'round', 'round_', 'row_stack', 's_', |
|
1125 'sample', 'savetxt', 'sctype2char', 'searchsorted', 'seed', 'select', |
|
1126 'set_numeric_ops', 'set_printoptions', 'set_string_function', |
|
1127 'setbufsize', 'setdiff1d', 'seterr', 'seterrcall', 'seterrobj', |
|
1128 'setfield', 'setflags', 'setmember1d', 'setxor1d', 'shape', |
|
1129 'show_config', 'shuffle', 'sign', 'signbit', 'sin', 'sinc', 'sinh', |
|
1130 'size', 'slice', 'solve', 'sometrue', 'sort', 'sort_complex', 'source', |
|
1131 'split', 'sqrt', 'square', 'squeeze', 'standard_normal', 'std', |
|
1132 'subtract', 'sum', 'svd', 'swapaxes', 'take', 'tan', 'tanh', 'tensordot', |
|
1133 'test', 'tile', 'tofile', 'tolist', 'tostring', 'trace', 'transpose', |
|
1134 'trapz', 'tri', 'tril', 'trim_zeros', 'triu', 'true_divide', 'typeDict', |
|
1135 'typename', 'uniform', 'union1d', 'unique', 'unique1d', 'unravel_index', |
|
1136 'unwrap', 'vander', 'var', 'vdot', 'vectorize', 'view', 'vonmises', |
|
1137 'vsplit', 'vstack', 'weibull', 'where', 'who', 'zeros', 'zeros_like' |
|
1138 } |
|
1139 |
|
1140 def get_tokens_unprocessed(self, text): |
|
1141 for index, token, value in \ |
|
1142 PythonLexer.get_tokens_unprocessed(self, text): |
|
1143 if token is Name and value in self.EXTRA_KEYWORDS: |
|
1144 yield index, Keyword.Pseudo, value |
|
1145 else: |
|
1146 yield index, token, value |
|
1147 |
|
1148 def analyse_text(text): |
|
1149 return (shebang_matches(text, r'pythonw?(3(\.\d)?)?') or |
|
1150 'import ' in text[:1000]) \ |
|
1151 and ('import numpy' in text or 'from numpy import' in text) |
|