1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
|
# -*- coding: utf-8 -*-
"""
pygments.lexers.python (as CustomLexer)
~~~~~~~~~~~~~~~~~~~~~~
For test_cmdline.py
"""
import re
from pygments.lexer import Lexer, RegexLexer, include, bygroups, using, \
default, words, combined, do_insertions
from pygments.util import get_bool_opt, shebang_matches
from pygments.token import Text, Comment, Operator, Keyword, Name, String, \
Number, Punctuation, Generic, Other, Error
from pygments import unistring as uni
line_re = re.compile('.*?\n')
class CustomLexer(RegexLexer):
"""
For `Python <http://www.python.org>`_ source code.
"""
name = 'Python'
aliases = ['python', 'py', 'sage']
filenames = ['*.py', '*.pyw', '*.sc', 'SConstruct', 'SConscript', '*.tac', '*.sage']
mimetypes = ['text/x-python', 'application/x-python']
def innerstring_rules(ttype):
return [
# the old style '%s' % (...) string formatting
(r'%(\(\w+\))?[-#0 +]*([0-9]+|[*])?(\.([0-9]+|[*]))?'
'[hlL]?[diouxXeEfFgGcrs%]', String.Interpol),
# backslashes, quotes and formatting signs must be parsed one at a time
(r'[^\\\'"%\n]+', ttype),
(r'[\'"\\]', ttype),
# unhandled string formatting sign
(r'%', ttype),
# newlines are an error (use "nl" state)
]
tokens = {
'root': [
(r'\n', Text),
(r'^(\s*)([rRuU]{,2}"""(?:.|\n)*?""")', bygroups(Text, String.Doc)),
(r"^(\s*)([rRuU]{,2}'''(?:.|\n)*?''')", bygroups(Text, String.Doc)),
(r'[^\S\n]+', Text),
(r'\A#!.+$', Comment.Hashbang),
(r'#.*$', Comment.Single),
(r'[]{}:(),;[]', Punctuation),
(r'\\\n', Text),
(r'\\', Text),
(r'(in|is|and|or|not)\b', Operator.Word),
(r'!=|==|<<|>>|[-~+/*%=<>&^|.]', Operator),
include('keywords'),
(r'(def)((?:\s|\\\s)+)', bygroups(Keyword, Text), 'funcname'),
(r'(class)((?:\s|\\\s)+)', bygroups(Keyword, Text), 'classname'),
(r'(from)((?:\s|\\\s)+)', bygroups(Keyword.Namespace, Text),
'fromimport'),
(r'(import)((?:\s|\\\s)+)', bygroups(Keyword.Namespace, Text),
'import'),
include('builtins'),
include('magicfuncs'),
include('magicvars'),
include('backtick'),
('(?:[rR]|[uU][rR]|[rR][uU])"""', String.Double, 'tdqs'),
("(?:[rR]|[uU][rR]|[rR][uU])'''", String.Single, 'tsqs'),
('(?:[rR]|[uU][rR]|[rR][uU])"', String.Double, 'dqs'),
("(?:[rR]|[uU][rR]|[rR][uU])'", String.Single, 'sqs'),
('[uU]?"""', String.Double, combined('stringescape', 'tdqs')),
("[uU]?'''", String.Single, combined('stringescape', 'tsqs')),
('[uU]?"', String.Double, combined('stringescape', 'dqs')),
("[uU]?'", String.Single, combined('stringescape', 'sqs')),
include('name'),
include('numbers'),
],
'keywords': [
(words((
'assert', 'break', 'continue', 'del', 'elif', 'else', 'except',
'exec', 'finally', 'for', 'global', 'if', 'lambda', 'pass',
'print', 'raise', 'return', 'try', 'while', 'yield',
'yield from', 'as', 'with'), suffix=r'\b'),
Keyword),
],
'builtins': [
(words((
'__import__', 'abs', 'all', 'any', 'apply', 'basestring', 'bin',
'bool', 'buffer', 'bytearray', 'bytes', 'callable', 'chr', 'classmethod',
'cmp', 'coerce', 'compile', 'complex', 'delattr', 'dict', 'dir', 'divmod',
'enumerate', 'eval', 'execfile', 'exit', 'file', 'filter', 'float',
'frozenset', 'getattr', 'globals', 'hasattr', 'hash', 'hex', 'id',
'input', 'int', 'intern', 'isinstance', 'issubclass', 'iter', 'len',
'list', 'locals', 'long', 'map', 'max', 'min', 'next', 'object',
'oct', 'open', 'ord', 'pow', 'property', 'range', 'raw_input', 'reduce',
'reload', 'repr', 'reversed', 'round', 'set', 'setattr', 'slice',
'sorted', 'staticmethod', 'str', 'sum', 'super', 'tuple', 'type',
'unichr', 'unicode', 'vars', 'xrange', 'zip'),
prefix=r'(?<!\.)', suffix=r'\b'),
Name.Builtin),
(r'(?<!\.)(self|None|Ellipsis|NotImplemented|False|True'
r')\b', Name.Builtin.Pseudo),
(words((
'ArithmeticError', 'AssertionError', 'AttributeError',
'BaseException', 'DeprecationWarning', 'EOFError', 'EnvironmentError',
'Exception', 'FloatingPointError', 'FutureWarning', 'GeneratorExit',
'IOError', 'ImportError', 'ImportWarning', 'IndentationError',
'IndexError', 'KeyError', 'KeyboardInterrupt', 'LookupError',
'MemoryError', 'NameError', 'NotImplemented', 'NotImplementedError',
'OSError', 'OverflowError', 'OverflowWarning', 'PendingDeprecationWarning',
'ReferenceError', 'RuntimeError', 'RuntimeWarning', 'StandardError',
'StopIteration', 'SyntaxError', 'SyntaxWarning', 'SystemError',
'SystemExit', 'TabError', 'TypeError', 'UnboundLocalError',
'UnicodeDecodeError', 'UnicodeEncodeError', 'UnicodeError',
'UnicodeTranslateError', 'UnicodeWarning', 'UserWarning',
'ValueError', 'VMSError', 'Warning', 'WindowsError',
'ZeroDivisionError'), prefix=r'(?<!\.)', suffix=r'\b'),
Name.Exception),
],
'magicfuncs': [
(words((
'__abs__', '__add__', '__and__', '__call__', '__cmp__', '__coerce__',
'__complex__', '__contains__', '__del__', '__delattr__', '__delete__',
'__delitem__', '__delslice__', '__div__', '__divmod__', '__enter__',
'__eq__', '__exit__', '__float__', '__floordiv__', '__ge__', '__get__',
'__getattr__', '__getattribute__', '__getitem__', '__getslice__', '__gt__',
'__hash__', '__hex__', '__iadd__', '__iand__', '__idiv__', '__ifloordiv__',
'__ilshift__', '__imod__', '__imul__', '__index__', '__init__',
'__instancecheck__', '__int__', '__invert__', '__iop__', '__ior__',
'__ipow__', '__irshift__', '__isub__', '__iter__', '__itruediv__',
'__ixor__', '__le__', '__len__', '__long__', '__lshift__', '__lt__',
'__missing__', '__mod__', '__mul__', '__ne__', '__neg__', '__new__',
'__nonzero__', '__oct__', '__op__', '__or__', '__pos__', '__pow__',
'__radd__', '__rand__', '__rcmp__', '__rdiv__', '__rdivmod__', '__repr__',
'__reversed__', '__rfloordiv__', '__rlshift__', '__rmod__', '__rmul__',
'__rop__', '__ror__', '__rpow__', '__rrshift__', '__rshift__', '__rsub__',
'__rtruediv__', '__rxor__', '__set__', '__setattr__', '__setitem__',
'__setslice__', '__str__', '__sub__', '__subclasscheck__', '__truediv__',
'__unicode__', '__xor__'), suffix=r'\b'),
Name.Function.Magic),
],
'magicvars': [
(words((
'__bases__', '__class__', '__closure__', '__code__', '__defaults__',
'__dict__', '__doc__', '__file__', '__func__', '__globals__',
'__metaclass__', '__module__', '__mro__', '__name__', '__self__',
'__slots__', '__weakref__'),
suffix=r'\b'),
Name.Variable.Magic),
],
'numbers': [
(r'(\d+\.\d*|\d*\.\d+)([eE][+-]?[0-9]+)?j?', Number.Float),
(r'\d+[eE][+-]?[0-9]+j?', Number.Float),
(r'0[0-7]+j?', Number.Oct),
(r'0[bB][01]+', Number.Bin),
(r'0[xX][a-fA-F0-9]+', Number.Hex),
(r'\d+L', Number.Integer.Long),
(r'\d+j?', Number.Integer)
],
'backtick': [
('`.*?`', String.Backtick),
],
'name': [
(r'@[\w.]+', Name.Decorator),
('[a-zA-Z_]\w*', Name),
],
'funcname': [
include('magicfuncs'),
('[a-zA-Z_]\w*', Name.Function, '#pop'),
default('#pop'),
],
'classname': [
('[a-zA-Z_]\w*', Name.Class, '#pop')
],
'import': [
(r'(?:[ \t]|\\\n)+', Text),
(r'as\b', Keyword.Namespace),
(r',', Operator),
(r'[a-zA-Z_][\w.]*', Name.Namespace),
default('#pop') # all else: go back
],
'fromimport': [
(r'(?:[ \t]|\\\n)+', Text),
(r'import\b', Keyword.Namespace, '#pop'),
# if None occurs here, it's "raise x from None", since None can
# never be a module name
(r'None\b', Name.Builtin.Pseudo, '#pop'),
# sadly, in "raise x from y" y will be highlighted as namespace too
(r'[a-zA-Z_.][\w.]*', Name.Namespace),
# anything else here also means "raise x from y" and is therefore
# not an error
default('#pop'),
],
'stringescape': [
(r'\\([\\abfnrtv"\']|\n|N\{.*?\}|u[a-fA-F0-9]{4}|'
r'U[a-fA-F0-9]{8}|x[a-fA-F0-9]{2}|[0-7]{1,3})', String.Escape)
],
'strings-single': innerstring_rules(String.Single),
'strings-double': innerstring_rules(String.Double),
'dqs': [
(r'"', String.Double, '#pop'),
(r'\\\\|\\"|\\\n', String.Escape), # included here for raw strings
include('strings-double')
],
'sqs': [
(r"'", String.Single, '#pop'),
(r"\\\\|\\'|\\\n", String.Escape), # included here for raw strings
include('strings-single')
],
'tdqs': [
(r'"""', String.Double, '#pop'),
include('strings-double'),
(r'\n', String.Double)
],
'tsqs': [
(r"'''", String.Single, '#pop'),
include('strings-single'),
(r'\n', String.Single)
],
}
def analyse_text(text):
return shebang_matches(text, r'pythonw?(2(\.\d)?)?') or \
'import ' in text[:1000]
class LexerWrapper(CustomLexer):
name="PythonLexerWrapper"
|
