File size: 1,920 Bytes
9c6594c |
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 |
# 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.
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
# Starting with Python 3.7, dicts are guaranteed to be insertion-ordered.
ordered_dict = dict
try:
import cloudpickle as pickle
except ImportError:
import pickle
def tobytes(o):
"""
Encode a unicode or bytes string to bytes.
Parameters
----------
o : str or bytes
Input string.
"""
if isinstance(o, str):
return o.encode('utf8')
else:
return o
def frombytes(o, *, safe=False):
"""
Decode the given bytestring to unicode.
Parameters
----------
o : bytes-like
Input object.
safe : bool, default False
If true, raise on encoding errors.
"""
if safe:
return o.decode('utf8', errors='replace')
else:
return o.decode('utf8')
|