encoded_file.py
1.99 KB
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
"""
Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
See https://llvm.org/LICENSE.txt for license information.
SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
Prepares language bindings for LLDB build process. Run with --help
to see a description of the supported command line arguments.
"""
# Python modules:
import io
# Third party modules
import six
def _encoded_read(old_read, encoding):
def impl(size):
result = old_read(size)
# If this is Python 2 then we need to convert the resulting `unicode` back
# into a `str` before returning
if six.PY2:
result = result.encode(encoding)
return result
return impl
def _encoded_write(old_write, encoding):
def impl(s):
# If we were asked to write a `str` (in Py2) or a `bytes` (in Py3) decode it
# as unicode before attempting to write.
if isinstance(s, six.binary_type):
s = s.decode(encoding, "replace")
# Filter unreadable characters, Python 3 is stricter than python 2 about them.
import re
s = re.sub(r'[^\x00-\x7f]',r' ',s)
return old_write(s)
return impl
'''
Create a Text I/O file object that can be written to with either unicode strings or byte strings
under Python 2 and Python 3, and automatically encodes and decodes as necessary to return the
native string type for the current Python version
'''
def open(
file,
encoding,
mode='r',
buffering=-1,
errors=None,
newline=None,
closefd=True):
wrapped_file = io.open(
file,
mode=mode,
buffering=buffering,
encoding=encoding,
errors=errors,
newline=newline,
closefd=closefd)
new_read = _encoded_read(getattr(wrapped_file, 'read'), encoding)
new_write = _encoded_write(getattr(wrapped_file, 'write'), encoding)
setattr(wrapped_file, 'read', new_read)
setattr(wrapped_file, 'write', new_write)
return wrapped_file