aboutsummaryrefslogtreecommitdiffstats
path: root/libbe/util/encoding.py
blob: 712a3fa3b03c7acf8f7b04d281cd7516c6c92f00 (plain) (blame)
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
# Copyright (C) 2008-2012 Chris Ball <cjb@laptop.org>
#                         Gianluca Montecchi <gian@grys.it>
#                         Niall Douglas (s_sourceforge@nedprod.com) <spam@spamtrap.com>
#                         W. Trevor King <wking@tremily.us>
#
# This file is part of Bugs Everywhere.
#
# Bugs Everywhere is free software: you can redistribute it and/or modify it
# under the terms of the GNU General Public License as published by the Free
# Software Foundation, either version 2 of the License, or (at your option) any
# later version.
#
# Bugs Everywhere is distributed in the hope that it will be useful, but
# WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
# FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
# more details.
#
# You should have received a copy of the GNU General Public License along with
# Bugs Everywhere.  If not, see <http://www.gnu.org/licenses/>.

"""
Support input/output/filesystem encodings (e.g. UTF-8).
"""

import codecs
import locale
import os
import sys
import types

import libbe
if libbe.TESTING == True:
    import doctest


ENCODING = os.environ.get('BE_ENCODING', None)
"override get_encoding() output"
INPUT_ENCODING = os.environ.get('BE_INPUT_ENCODING', None)
"override get_input_encoding() output"
OUTPUT_ENCODING = os.environ.get('BE_OUTPUT_ENCODING', None)
"override get_output_encoding() output"

def get_encoding():
    """
    Guess a useful input/output/filesystem encoding...  Maybe we need
    seperate encodings for input/output and filesystem?  Hmm...
    """
    if ENCODING != None:
        return ENCODING
    encoding = locale.getpreferredencoding() or sys.getdefaultencoding()
    return encoding

def get_input_encoding():
    if INPUT_ENCODING != None:
        return INPUT_ENCODING
    return sys.__stdin__.encoding or get_encoding()

def get_output_encoding():
    if OUTPUT_ENCODING != None:
        return OUTPUT_ENCODING
    return sys.__stdout__.encoding or get_encoding()

def get_text_file_encoding():
    """Return the encoding that should be used for file contents
    """
    return get_encoding()

def get_argv_encoding():
    return get_encoding()

def known_encoding(encoding):
    """
    >>> known_encoding("highly-unlikely-encoding")
    False
    >>> known_encoding(get_encoding())
    True
    """
    try:
        codecs.lookup(encoding)
        return True
    except LookupError:
        return False

def get_file_contents(path, mode='r', encoding=None, decode=False):
    if decode == True:
        if encoding == None:
            encoding = get_text_file_encoding()
        f = codecs.open(path, mode, encoding)
    else:
        f = open(path, mode)
    contents = f.read()
    f.close()
    return contents

def set_file_contents(path, contents, mode='w', encoding=None):
    if type(contents) == types.UnicodeType:
        if encoding == None:
            encoding = get_text_file_encoding()
        f = codecs.open(path, mode, encoding)
    else:
        f = open(path, mode)
    f.write(contents)
    f.close()

if libbe.TESTING == True:
    suite = doctest.DocTestSuite()