/usr/lib/python3/dist-packages/pygments/util.py is in python3-pygments 1.6+dfsg-1ubuntu1.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 | # -*- coding: utf-8 -*-
"""
pygments.util
~~~~~~~~~~~~~
Utility functions.
:copyright: Copyright 2006-2013 by the Pygments team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
import re
import sys
import codecs
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, normcase=False):
string = options.get(optname, default)
if normcase:
string = string.lower()
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, str):
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, str):
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):
try:
rv = f(text)
except Exception:
return 0.0
if not rv:
return 0.0
try:
return min(1.0, max(0.0, float(rv)))
except (ValueError, TypeError):
return 0.0
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
# Python narrow build compatibility
def _surrogatepair(c):
return (0xd7c0 + (c >> 10), (0xdc00 + (c & 0x3ff)))
def unirange(a, b):
"""
Returns a regular expression string to match the given non-BMP range.
"""
if b < a:
raise ValueError("Bad character range")
if a < 0x10000 or b < 0x10000:
raise ValueError("unirange is only defined for non-BMP ranges")
if sys.maxunicode > 0xffff:
# wide build
return '[%s-%s]' % (chr(a), chr(b))
else:
# narrow build stores surrogates, and the 're' module handles them
# (incorrectly) as characters. Since there is still ordering among
# these characters, expand the range to one that it understands. Some
# background in http://bugs.python.org/issue3665 and
# http://bugs.python.org/issue12749
#
# Additionally, the lower constants are using unichr rather than
# literals because jython [which uses the wide path] can't load this
# file if they are literals.
ah, al = _surrogatepair(a)
bh, bl = _surrogatepair(b)
if ah == bh:
return '(?:%s[%s-%s])' % (chr(ah), chr(al), chr(bl))
else:
buf = []
buf.append('%s[%s-%s]' %
(chr(ah), chr(al),
ah == bh and chr(bl) or chr(0xdfff)))
if ah - bh > 1:
buf.append('[%s-%s][%s-%s]' %
chr(ah+1), chr(bh-1), chr(0xdc00), chr(0xdfff))
if ah != bh:
buf.append('%s[%s-%s]' %
(chr(bh), chr(0xdc00), chr(bl)))
return '(?:' + '|'.join(buf) + ')'
# Python 2/3 compatibility
if sys.version_info < (3,0):
b = bytes = str
u_prefix = 'u'
import io, io
BytesIO = io.StringIO
StringIO = io.StringIO
uni_open = codecs.open
else:
import builtins
bytes = builtins.bytes
u_prefix = ''
def b(s):
if isinstance(s, str):
return bytes(list(map(ord, s)))
elif isinstance(s, bytes):
return s
else:
raise TypeError("Invalid argument %r for b()" % (s,))
import io
BytesIO = io.BytesIO
StringIO = io.StringIO
uni_open = builtins.open
|