67bfcbdd0b
This avoids the need to duplicate our dependency list in multiple places and allows us to take advantage of tox's dependency management infrastructure, to ensure we always get the latest and greatest version of a package allowed by upper-constraints. While here, we also bump the other pre-commit hooks and update hints to accommodate typed fixtures. Change-Id: I4020374b45c8ead4b3b65651389c1e903a1de7bd Signed-off-by: Stephen Finucane <sfinucan@redhat.com>
140 lines
4.4 KiB
Python
140 lines
4.4 KiB
Python
# Copyright 2014 Red Hat, Inc.
|
|
# All Rights Reserved.
|
|
#
|
|
# Licensed 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
|
|
from typing import Any
|
|
|
|
import debtcollector.removals # type: ignore
|
|
|
|
|
|
def safe_decode(
|
|
text: str | bytes,
|
|
incoming: str | None = None,
|
|
errors: str = 'strict',
|
|
) -> str:
|
|
"""Decodes incoming text/bytes string using `incoming` if they're not
|
|
already unicode.
|
|
|
|
:param incoming: Text's current encoding
|
|
:param errors: Errors handling policy. See here for valid
|
|
values http://docs.python.org/2/library/codecs.html
|
|
:returns: text or a unicode `incoming` encoded
|
|
representation of it.
|
|
:raises TypeError: If text is not an instance of str
|
|
"""
|
|
if not isinstance(text, str | bytes):
|
|
raise TypeError(f"{type(text)} can't be decoded")
|
|
|
|
if isinstance(text, str):
|
|
return text
|
|
|
|
if not incoming:
|
|
incoming = (
|
|
getattr(sys.stdin, 'encoding', None) or sys.getdefaultencoding()
|
|
)
|
|
|
|
try:
|
|
return text.decode(incoming, errors)
|
|
except UnicodeDecodeError:
|
|
# Note(flaper87) If we get here, it means that
|
|
# sys.stdin.encoding / sys.getdefaultencoding
|
|
# didn't return a suitable encoding to decode
|
|
# text. This happens mostly when global LANG
|
|
# var is not set correctly and there's no
|
|
# default encoding. In this case, most likely
|
|
# python will use ASCII or ANSI encoders as
|
|
# default encodings but they won't be capable
|
|
# of decoding non-ASCII characters.
|
|
#
|
|
# Also, UTF-8 is being used since it's an ASCII
|
|
# extension.
|
|
return text.decode('utf-8', errors)
|
|
|
|
|
|
def safe_encode(
|
|
text: str | bytes,
|
|
incoming: str | None = None,
|
|
encoding: str = 'utf-8',
|
|
errors: str = 'strict',
|
|
) -> bytes:
|
|
"""Encodes incoming text/bytes string using `encoding`.
|
|
|
|
If incoming is not specified, text is expected to be encoded with
|
|
current python's default encoding. (`sys.getdefaultencoding`)
|
|
|
|
:param incoming: Text's current encoding
|
|
:param encoding: Expected encoding for text (Default UTF-8)
|
|
:param errors: Errors handling policy. See here for valid
|
|
values http://docs.python.org/2/library/codecs.html
|
|
:returns: text or a bytestring `encoding` encoded
|
|
representation of it.
|
|
:raises TypeError: If text is not an instance of str
|
|
|
|
See also to_utf8() function which is simpler and don't depend on
|
|
the locale encoding.
|
|
"""
|
|
if not isinstance(text, str | bytes):
|
|
raise TypeError(f"{type(text)} can't be encoded")
|
|
|
|
if not incoming:
|
|
incoming = (
|
|
getattr(sys.stdin, 'encoding', None) or sys.getdefaultencoding()
|
|
)
|
|
|
|
# Avoid case issues in comparisons
|
|
if hasattr(incoming, 'lower'):
|
|
incoming = incoming.lower()
|
|
if hasattr(encoding, 'lower'):
|
|
encoding = encoding.lower()
|
|
|
|
if isinstance(text, str):
|
|
return text.encode(encoding, errors)
|
|
elif text and encoding != incoming:
|
|
# Decode text before encoding it with `encoding`
|
|
text = safe_decode(text, incoming, errors)
|
|
return text.encode(encoding, errors)
|
|
else:
|
|
return text
|
|
|
|
|
|
def to_utf8(text: str | bytes) -> bytes:
|
|
"""Encode Unicode to UTF-8, return bytes unchanged.
|
|
|
|
Raise TypeError if text is not a bytes string or a Unicode string.
|
|
|
|
.. versionadded:: 3.5
|
|
"""
|
|
if isinstance(text, bytes):
|
|
return text
|
|
elif isinstance(text, str):
|
|
return text.encode('utf-8')
|
|
else:
|
|
raise TypeError(
|
|
f"bytes or Unicode expected, got {type(text).__name__}"
|
|
)
|
|
|
|
|
|
@debtcollector.removals.remove(
|
|
message='Use str(exc) instead', category=DeprecationWarning
|
|
)
|
|
def exception_to_unicode(exc: Any) -> str:
|
|
"""Get the message of an exception as a Unicode string.
|
|
|
|
On Python 3, the exception message is always a Unicode string.
|
|
|
|
.. versionadded:: 1.6
|
|
"""
|
|
return str(exc)
|