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
|
# -*- coding: utf-8 -*-
"""
pygments.util
~~~~~~~~~~~~~
Utility functions.
:copyright: 2006-2007 by Georg Brandl.
:license: BSD, see LICENSE for more details.
"""
import re
split_path_re = re.compile(r'[/\\ ]')
doctype_lookup_re = re.compile(r'''(?smx)
(<\?.*?\?>)?\s*
<!DOCTYPE\s+(
[a-zA-Z_][a-zA-Z0-9]*\s+
[a-zA-Z_][a-zA-Z0-9]*\s+
"[^"]*")
[^>]*>
''')
tag_re = re.compile(r'<(.+?)(\s.*?)?>.*?</.+?>(?uism)')
class ClassNotFound(ValueError):
"""
If one of the get_*_by_* functions didn't find a matching class.
"""
class OptionError(Exception):
pass
def get_choice_opt(options, optname, allowed, default=None):
string = options.get(optname, default)
if string not in allowed:
raise OptionError('Value for option %s must be one of %s' %
(optname, ', '.join(map(str, allowed))))
return string
def get_bool_opt(options, optname, default=None):
string = options.get(optname, default)
if isinstance(string, bool):
return string
elif isinstance(string, int):
return bool(string)
elif not isinstance(string, basestring):
raise OptionError('Invalid type %r for option %s; use '
'1/0, yes/no, true/false, on/off' % (
string, optname))
elif string.lower() in ('1', 'yes', 'true', 'on'):
return True
elif string.lower() in ('0', 'no', 'false', 'off'):
return False
else:
raise OptionError('Invalid value %r for option %s; use '
'1/0, yes/no, true/false, on/off' % (
string, optname))
def get_int_opt(options, optname, default=None):
string = options.get(optname, default)
try:
return int(string)
except TypeError:
raise OptionError('Invalid type %r for option %s; you '
'must give an integer value' % (
string, optname))
except ValueError:
raise OptionError('Invalid value %r for option %s; you '
'must give an integer value' % (
string, optname))
def get_list_opt(options, optname, default=None):
val = options.get(optname, default)
if isinstance(val, basestring):
return val.split()
elif isinstance(val, (list, tuple)):
return list(val)
else:
raise OptionError('Invalid type %r for option %s; you '
'must give a list value' % (
val, optname))
def docstring_headline(obj):
if not obj.__doc__:
return ''
res = []
for line in obj.__doc__.strip().splitlines():
if line.strip():
res.append(" " + line.strip())
else:
break
return ''.join(res).lstrip()
def make_analysator(f):
"""
Return a static text analysation function that
returns float values.
"""
def text_analyse(text):
rv = f(text)
if not rv:
return 0.0
return min(1.0, max(0.0, float(rv)))
text_analyse.__doc__ = f.__doc__
return staticmethod(text_analyse)
def shebang_matches(text, regex):
"""
Check if the given regular expression matches the last part of the
shebang if one exists.
>>> from pygments.util import shebang_matches
>>> shebang_matches('#!/usr/bin/env python', r'python(2\.\d)?')
True
>>> shebang_matches('#!/usr/bin/python2.4', r'python(2\.\d)?')
True
>>> shebang_matches('#!/usr/bin/python-ruby', r'python(2\.\d)?')
False
>>> shebang_matches('#!/usr/bin/python/ruby', r'python(2\.\d)?')
False
>>> shebang_matches('#!/usr/bin/startsomethingwith python',
... r'python(2\.\d)?')
True
It also checks for common windows executable file extensions::
>>> shebang_matches('#!C:\\Python2.4\\Python.exe', r'python(2\.\d)?')
True
Parameters (``'-f'`` or ``'--foo'`` are ignored so ``'perl'`` does
the same as ``'perl -e'``)
Note that this method automatically searches the whole string (eg:
the regular expression is wrapped in ``'^$'``)
"""
index = text.find('\n')
if index >= 0:
first_line = text[:index].lower()
else:
first_line = text.lower()
if first_line.startswith('#!'):
try:
found = [x for x in split_path_re.split(first_line[2:].strip())
if x and not x.startswith('-')][-1]
except IndexError:
return False
regex = re.compile('^%s(\.(exe|cmd|bat|bin))?$' % regex, re.IGNORECASE)
if regex.search(found) is not None:
return True
return False
def doctype_matches(text, regex):
"""
Check if the doctype matches a regular expression (if present).
Note that this method only checks the first part of a DOCTYPE.
eg: 'html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"'
"""
m = doctype_lookup_re.match(text)
if m is None:
return False
doctype = m.group(2)
return re.compile(regex).match(doctype.strip()) is not None
def html_doctype_matches(text):
"""
Check if the file looks like it has a html doctype.
"""
return doctype_matches(text, r'html\s+PUBLIC\s+"-//W3C//DTD X?HTML.*')
_looks_like_xml_cache = {}
def looks_like_xml(text):
"""
Check if a doctype exists or if we have some tags.
"""
key = hash(text)
try:
return _looks_like_xml_cache[key]
except KeyError:
m = doctype_lookup_re.match(text)
if m is not None:
return True
rv = tag_re.search(text[:1000]) is not None
_looks_like_xml_cache[key] = rv
return rv
|
