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
229
230
231
232
233
234
|
# -*- coding: utf-8 -*-
"""
sphinx.highlighting
~~~~~~~~~~~~~~~~~~~
Highlight code blocks using Pygments.
:copyright: Copyright 2007-2013 by the Sphinx team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
import sys
import re
import textwrap
try:
import parser
except ImportError:
# parser is not available on Jython
parser = None
from sphinx.util.pycompat import htmlescape
from sphinx.util.texescape import tex_hl_escape_map_new
from sphinx.ext import doctest
try:
import pygments
from pygments import highlight
from pygments.lexers import PythonLexer, PythonConsoleLexer, CLexer, \
TextLexer, RstLexer
from pygments.lexers import get_lexer_by_name, guess_lexer
from pygments.formatters import HtmlFormatter, LatexFormatter
from pygments.filters import ErrorToken
from pygments.styles import get_style_by_name
from pygments.util import ClassNotFound
from sphinx.pygments_styles import SphinxStyle, NoneStyle
except ImportError:
pygments = None
lexers = None
HtmlFormatter = LatexFormatter = None
else:
lexers = dict(
none = TextLexer(),
python = PythonLexer(),
pycon = PythonConsoleLexer(),
pycon3 = PythonConsoleLexer(python3=True),
rest = RstLexer(),
c = CLexer(),
)
for _lexer in lexers.values():
_lexer.add_filter('raiseonerror')
escape_hl_chars = {ord(u'\\'): u'\\PYGZbs{}',
ord(u'{'): u'\\PYGZob{}',
ord(u'}'): u'\\PYGZcb{}'}
# used if Pygments is not available
_LATEX_STYLES = r'''
\newcommand\PYGZbs{\char`\\}
\newcommand\PYGZob{\char`\{}
\newcommand\PYGZcb{\char`\}}
'''
parsing_exceptions = (SyntaxError, UnicodeEncodeError)
if sys.version_info < (2, 5):
# Python <= 2.4 raises MemoryError when parsing an
# invalid encoding cookie
parsing_exceptions += MemoryError,
class PygmentsBridge(object):
# Set these attributes if you want to have different Pygments formatters
# than the default ones.
html_formatter = HtmlFormatter
latex_formatter = LatexFormatter
def __init__(self, dest='html', stylename='sphinx',
trim_doctest_flags=False):
self.dest = dest
if not pygments:
return
if stylename is None or stylename == 'sphinx':
style = SphinxStyle
elif stylename == 'none':
style = NoneStyle
elif '.' in stylename:
module, stylename = stylename.rsplit('.', 1)
style = getattr(__import__(module, None, None, ['__name__']),
stylename)
else:
style = get_style_by_name(stylename)
self.trim_doctest_flags = trim_doctest_flags
self.formatter_args = {'style' : style}
if dest == 'html':
self.formatter = self.html_formatter
else:
self.formatter = self.latex_formatter
self.formatter_args['commandprefix'] = 'PYG'
def get_formatter(self, **kwargs):
kwargs.update(self.formatter_args)
return self.formatter(**kwargs)
def unhighlighted(self, source):
if self.dest == 'html':
return '<pre>' + htmlescape(source) + '</pre>\n'
else:
# first, escape highlighting characters like Pygments does
source = source.translate(escape_hl_chars)
# then, escape all characters nonrepresentable in LaTeX
source = source.translate(tex_hl_escape_map_new)
return '\\begin{Verbatim}[commandchars=\\\\\\{\\}]\n' + \
source + '\\end{Verbatim}\n'
def try_parse(self, src):
# Make sure it ends in a newline
src += '\n'
# Ignore consistent indentation.
if src.lstrip('\n').startswith(' '):
src = textwrap.dedent(src)
# Replace "..." by a mark which is also a valid python expression
# (Note, the highlighter gets the original source, this is only done
# to allow "..." in code and still highlight it as Python code.)
mark = "__highlighting__ellipsis__"
src = src.replace("...", mark)
# lines beginning with "..." are probably placeholders for suite
src = re.sub(r"(?m)^(\s*)" + mark + "(.)", r"\1"+ mark + r"# \2", src)
# if we're using 2.5, use the with statement
if sys.version_info >= (2, 5):
src = 'from __future__ import with_statement\n' + src
if sys.version_info < (3, 0) and isinstance(src, unicode):
# Non-ASCII chars will only occur in string literals
# and comments. If we wanted to give them to the parser
# correctly, we'd have to find out the correct source
# encoding. Since it may not even be given in a snippet,
# just replace all non-ASCII characters.
src = src.encode('ascii', 'replace')
if (3, 0) <= sys.version_info < (3, 2):
# Python 3.1 can't process '\r' as linesep.
# `parser.suite("print('hello')\r\n")` cause error.
if '\r\n' in src:
src = src.replace('\r\n', '\n')
if parser is None:
return True
try:
parser.suite(src)
except parsing_exceptions:
return False
else:
return True
def highlight_block(self, source, lang, warn=None, force=False, **kwargs):
if not isinstance(source, unicode):
source = source.decode()
if not pygments:
return self.unhighlighted(source)
# find out which lexer to use
if lang in ('py', 'python'):
if source.startswith('>>>'):
# interactive session
lexer = lexers['pycon']
elif not force:
# maybe Python -- try parsing it
if self.try_parse(source):
lexer = lexers['python']
else:
return self.unhighlighted(source)
else:
lexer = lexers['python']
elif lang in ('python3', 'py3') and source.startswith('>>>'):
# for py3, recognize interactive sessions, but do not try parsing...
lexer = lexers['pycon3']
elif lang == 'guess':
try:
lexer = guess_lexer(source)
except Exception:
return self.unhighlighted(source)
else:
if lang in lexers:
lexer = lexers[lang]
else:
try:
lexer = lexers[lang] = get_lexer_by_name(lang)
except ClassNotFound:
if warn:
warn('Pygments lexer name %r is not known' % lang)
return self.unhighlighted(source)
else:
raise
else:
lexer.add_filter('raiseonerror')
# trim doctest options if wanted
if isinstance(lexer, PythonConsoleLexer) and self.trim_doctest_flags:
source = doctest.blankline_re.sub('', source)
source = doctest.doctestopt_re.sub('', source)
# highlight via Pygments
try:
formatter = self.get_formatter(**kwargs)
hlsource = highlight(source, lexer, formatter)
if self.dest == 'html':
return hlsource
else:
if not isinstance(hlsource, unicode): # Py2 / Pygments < 1.6
hlsource = hlsource.decode()
return hlsource.translate(tex_hl_escape_map_new)
except ErrorToken:
# this is most probably not the selected language,
# so let it pass unhighlighted
return self.unhighlighted(source)
def get_stylesheet(self):
if not pygments:
if self.dest == 'latex':
return _LATEX_STYLES
# no HTML styles needed
return ''
formatter = self.get_formatter()
if self.dest == 'html':
return formatter.get_style_defs('.highlight')
else:
return formatter.get_style_defs()
|
