summaryrefslogtreecommitdiffstats
path: root/src/arrow/python/pyarrow/compat.pxi
blob: a5db5741b81e099d3caccd9792c1cf1952ff7993 (plain)
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
# Licensed to the Apache Software Foundation (ASF) under one
# or more contributor license agreements.  See the NOTICE file
# distributed with this work for additional information
# regarding copyright ownership.  The ASF licenses this file
# to you under the Apache License, Version 2.0 (the
# "License"); you may not use this file except in compliance
# with the License.  You may obtain a copy of the License at
#
#   http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing,
# software distributed under the License is distributed on an
# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
# KIND, either express or implied.  See the License for the
# specific language governing permissions and limitations
# under the License.

import sys


def encode_file_path(path):
    if isinstance(path, str):
        # POSIX systems can handle utf-8. UTF8 is converted to utf16-le in
        # libarrow
        encoded_path = path.encode('utf-8')
    else:
        encoded_path = path

    # Windows file system requires utf-16le for file names; Arrow C++ libraries
    # will convert utf8 to utf16
    return encoded_path


if sys.version_info >= (3, 7):
    # Starting with Python 3.7, dicts are guaranteed to be insertion-ordered.
    ordered_dict = dict
else:
    import collections
    ordered_dict = collections.OrderedDict


try:
    import pickle5 as builtin_pickle
except ImportError:
    import pickle as builtin_pickle


try:
    import cloudpickle as pickle
except ImportError:
    pickle = builtin_pickle


def tobytes(o):
    if isinstance(o, str):
        return o.encode('utf8')
    else:
        return o


def frombytes(o, *, safe=False):
    if safe:
        return o.decode('utf8', errors='replace')
    else:
        return o.decode('utf8')