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
|
# -*- coding: utf-8 -*-
"""
pygments.lexers.julia
~~~~~~~~~~~~~~~~~~~~~
Lexers for the Julia language.
:copyright: Copyright 2006-2015 by the Pygments team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
import re
from pygments.lexer import Lexer, RegexLexer, bygroups, combined, \
do_insertions, words
from pygments.token import Text, Comment, Operator, Keyword, Name, String, \
Number, Punctuation, Generic
from pygments.util import shebang_matches, unirange
__all__ = ['JuliaLexer', 'JuliaConsoleLexer']
line_re = re.compile('.*?\n')
class JuliaLexer(RegexLexer):
"""
For `Julia <http://julialang.org/>`_ source code.
.. versionadded:: 1.6
"""
name = 'Julia'
aliases = ['julia', 'jl']
filenames = ['*.jl']
mimetypes = ['text/x-julia', 'application/x-julia']
flags = re.MULTILINE | re.UNICODE
builtins = (
'exit', 'whos', 'edit', 'load', 'is', 'isa', 'isequal', 'typeof', 'tuple',
'ntuple', 'uid', 'hash', 'finalizer', 'convert', 'promote', 'subtype',
'typemin', 'typemax', 'realmin', 'realmax', 'sizeof', 'eps', 'promote_type',
'method_exists', 'applicable', 'invoke', 'dlopen', 'dlsym', 'system',
'error', 'throw', 'assert', 'new', 'Inf', 'Nan', 'pi', 'im',
)
keywords = (
'begin', 'while', 'for', 'in', 'return', 'break', 'continue',
'macro', 'quote', 'let', 'if', 'elseif', 'else', 'try', 'catch', 'end',
'bitstype', 'ccall', 'do', 'using', 'module', 'import', 'export',
'importall', 'baremodule', 'immutable',
)
types = (
'Bool', 'Int', 'Int8', 'Int16', 'Int32', 'Int64', 'Uint', 'Uint8', 'Uint16',
'Uint32', 'Uint64', 'Float32', 'Float64', 'Complex64', 'Complex128', 'Any',
'Nothing', 'None',
)
tokens = {
'root': [
(r'\n', Text),
(r'[^\S\n]+', Text),
(r'#=', Comment.Multiline, "blockcomment"),
(r'#.*$', Comment),
(r'[\[\]{}:(),;@]', Punctuation),
(r'\\\n', Text),
(r'\\', Text),
# keywords
(r'(local|global|const)\b', Keyword.Declaration),
(words(keywords, suffix=r'\b'), Keyword),
(words(types, suffix=r'\b'), Keyword.Type),
# functions
(r'(function)((?:\s|\\\s)+)',
bygroups(Keyword, Name.Function), 'funcname'),
# types
(r'(type|typealias|abstract|immutable)((?:\s|\\\s)+)',
bygroups(Keyword, Name.Class), 'typename'),
# operators
(r'==|!=|<=|>=|->|&&|\|\||::|<:|[-~+/*%=<>&^|.?!$]', Operator),
(r'\.\*|\.\^|\.\\|\.\/|\\', Operator),
# builtins
(words(builtins, suffix=r'\b'), Name.Builtin),
# backticks
(r'`(?s).*?`', String.Backtick),
# chars
(r"'(\\.|\\[0-7]{1,3}|\\x[a-fA-F0-9]{1,3}|\\u[a-fA-F0-9]{1,4}|"
r"\\U[a-fA-F0-9]{1,6}|[^\\\'\n])'", String.Char),
# try to match trailing transpose
(r'(?<=[.\w)\]])\'+', Operator),
# strings
(r'(?:[IL])"', String, 'string'),
(r'[E]?"', String, combined('stringescape', 'string')),
# names
(r'@[\w.]+', Name.Decorator),
(u'(?:[a-zA-Z_\u00A1-\uffff]|%s)(?:[a-zA-Z_0-9\u00A1-\uffff]|%s)*!*' %
((unirange(0x10000, 0x10ffff),)*2), Name),
# numbers
(r'(\d+(_\d+)+\.\d*|\d*\.\d+(_\d+)+)([eEf][+-]?[0-9]+)?', Number.Float),
(r'(\d+\.\d*|\d*\.\d+)([eEf][+-]?[0-9]+)?', Number.Float),
(r'\d+(_\d+)+[eEf][+-]?[0-9]+', Number.Float),
(r'\d+[eEf][+-]?[0-9]+', Number.Float),
(r'0b[01]+(_[01]+)+', Number.Bin),
(r'0b[01]+', Number.Bin),
(r'0o[0-7]+(_[0-7]+)+', Number.Oct),
(r'0o[0-7]+', Number.Oct),
(r'0x[a-fA-F0-9]+(_[a-fA-F0-9]+)+', Number.Hex),
(r'0x[a-fA-F0-9]+', Number.Hex),
(r'\d+(_\d+)+', Number.Integer),
(r'\d+', Number.Integer)
],
'funcname': [
('[a-zA-Z_]\w*', Name.Function, '#pop'),
('\([^\s\w{]{1,2}\)', Operator, '#pop'),
('[^\s\w{]{1,2}', Operator, '#pop'),
],
'typename': [
('[a-zA-Z_]\w*', Name.Class, '#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),
],
"blockcomment": [
(r'[^=#]', Comment.Multiline),
(r'#=', Comment.Multiline, '#push'),
(r'=#', Comment.Multiline, '#pop'),
(r'[=#]', Comment.Multiline),
],
'string': [
(r'"', String, '#pop'),
(r'\\\\|\\"|\\\n', String.Escape), # included here for raw strings
# Interpolation is defined as "$" followed by the shortest full
# expression, which is something we can't parse.
# Include the most common cases here: $word, and $(paren'd expr).
(r'\$[a-zA-Z_]+', String.Interpol),
(r'\$\(', String.Interpol, 'in-intp'),
# @printf and @sprintf formats
(r'%[-#0 +]*([0-9]+|[*])?(\.([0-9]+|[*]))?[hlL]?[E-GXc-giorsux%]',
String.Interpol),
(r'[^$%"\\]+', String),
# unhandled special signs
(r'[$%"\\]', String),
],
'in-intp': [
(r'[^()]+', String.Interpol),
(r'\(', String.Interpol, '#push'),
(r'\)', String.Interpol, '#pop'),
]
}
def analyse_text(text):
return shebang_matches(text, r'julia')
class JuliaConsoleLexer(Lexer):
"""
For Julia console sessions. Modeled after MatlabSessionLexer.
.. versionadded:: 1.6
"""
name = 'Julia console'
aliases = ['jlcon']
def get_tokens_unprocessed(self, text):
jllexer = JuliaLexer(**self.options)
curcode = ''
insertions = []
for match in line_re.finditer(text):
line = match.group()
if line.startswith('julia>'):
insertions.append((len(curcode),
[(0, Generic.Prompt, line[:6])]))
curcode += line[6:]
elif line.startswith(' '):
idx = len(curcode)
# without is showing error on same line as before...?
line = "\n" + line
token = (0, Generic.Traceback, line)
insertions.append((idx, [token]))
else:
if curcode:
for item in do_insertions(
insertions, jllexer.get_tokens_unprocessed(curcode)):
yield item
curcode = ''
insertions = []
yield match.start(), Generic.Output, line
if curcode: # or item:
for item in do_insertions(
insertions, jllexer.get_tokens_unprocessed(curcode)):
yield item
|
