/usr/lib/python2.7/dist-packages/joblib/_memory_helpers.py is in python-joblib 0.10.3+git55-g660fe5d-1.
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 | try:
# Available in Python 3
from tokenize import open as open_py_source
except ImportError:
# Copied from python3 tokenize
from codecs import lookup, BOM_UTF8
import re
from io import TextIOWrapper, open
cookie_re = re.compile("coding[:=]\s*([-\w.]+)")
def _get_normal_name(orig_enc):
"""Imitates get_normal_name in tokenizer.c."""
# Only care about the first 12 characters.
enc = orig_enc[:12].lower().replace("_", "-")
if enc == "utf-8" or enc.startswith("utf-8-"):
return "utf-8"
if enc in ("latin-1", "iso-8859-1", "iso-latin-1") or \
enc.startswith(("latin-1-", "iso-8859-1-", "iso-latin-1-")):
return "iso-8859-1"
return orig_enc
def _detect_encoding(readline):
"""
The detect_encoding() function is used to detect the encoding that
should be used to decode a Python source file. It requires one
argment, readline, in the same way as the tokenize() generator.
It will call readline a maximum of twice, and return the encoding used
(as a string) and a list of any lines (left as bytes) it has read in.
It detects the encoding from the presence of a utf-8 bom or an encoding
cookie as specified in pep-0263. If both a bom and a cookie are
present, but disagree, a SyntaxError will be raised. If the encoding
cookie is an invalid charset, raise a SyntaxError. Note that if a
utf-8 bom is found, 'utf-8-sig' is returned.
If no encoding is specified, then the default of 'utf-8' will be
returned.
"""
bom_found = False
encoding = None
default = 'utf-8'
def read_or_stop():
try:
return readline()
except StopIteration:
return b''
def find_cookie(line):
try:
line_string = line.decode('ascii')
except UnicodeDecodeError:
return None
matches = cookie_re.findall(line_string)
if not matches:
return None
encoding = _get_normal_name(matches[0])
try:
codec = lookup(encoding)
except LookupError:
# This behaviour mimics the Python interpreter
raise SyntaxError("unknown encoding: " + encoding)
if bom_found:
if codec.name != 'utf-8':
# This behaviour mimics the Python interpreter
raise SyntaxError('encoding problem: utf-8')
encoding += '-sig'
return encoding
first = read_or_stop()
if first.startswith(BOM_UTF8):
bom_found = True
first = first[3:]
default = 'utf-8-sig'
if not first:
return default, []
encoding = find_cookie(first)
if encoding:
return encoding, [first]
second = read_or_stop()
if not second:
return default, [first]
encoding = find_cookie(second)
if encoding:
return encoding, [first, second]
return default, [first, second]
def open_py_source(filename):
"""Open a file in read only mode using the encoding detected by
detect_encoding().
"""
buffer = open(filename, 'rb')
encoding, lines = _detect_encoding(buffer.readline)
buffer.seek(0)
text = TextIOWrapper(buffer, encoding, line_buffering=True)
text.mode = 'r'
return text
|