Decodes input and encodes output
Currently novaclient doesn't handle properly incoming and outgoing encode / decode process. As a solution for this, this patch implements a decoding process for all data incoming from the user side and decodes everything going out of the client, i.e: http requests, prints, etc. This patch introduces a new module (strutils.py) taken from oslo-incubator in order to use 2 of the functions present in it: About safe_(decode|encode): Both functions try to encode / decode the incoming text using the stdin encoding, fallback to python's default encoding if that returns None or to UTF-8 as the last option. In both functions only basestring objects are accepted and they both raise TypeError if an object of another type is passed. About the general novaclient changes: In order to better support non-ASCII characters, it is a good practice to use unicode interanlly and encode everything that has to go out. This patch aims to do that and introduces this behaviour in the client. Testing: A good test (besides using tox) is to use nova client with and without setting any locale (export LANG=). Fixes bug: 1061156 Change-Id: I20b75e42b0c3dac89f1048faa1127253a64f86c7changes/84/23084/6
parent
39b6e00eed
commit
47e6bc25ae
@ -0,0 +1,133 @@
|
||||
# vim: tabstop=4 shiftwidth=4 softtabstop=4
|
||||
|
||||
# Copyright 2011 OpenStack LLC.
|
||||
# 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.
|
||||
|
||||
"""
|
||||
System-level utilities and helper functions.
|
||||
"""
|
||||
|
||||
import logging
|
||||
import sys
|
||||
|
||||
LOG = logging.getLogger(__name__)
|
||||
|
||||
|
||||
def int_from_bool_as_string(subject):
|
||||
"""
|
||||
Interpret a string as a boolean and return either 1 or 0.
|
||||
|
||||
Any string value in:
|
||||
|
||||
('True', 'true', 'On', 'on', '1')
|
||||
|
||||
is interpreted as a boolean True.
|
||||
|
||||
Useful for JSON-decoded stuff and config file parsing
|
||||
"""
|
||||
return bool_from_string(subject) and 1 or 0
|
||||
|
||||
|
||||
def bool_from_string(subject):
|
||||
"""
|
||||
Interpret a string as a boolean.
|
||||
|
||||
Any string value in:
|
||||
|
||||
('True', 'true', 'On', 'on', 'Yes', 'yes', '1')
|
||||
|
||||
is interpreted as a boolean True.
|
||||
|
||||
Useful for JSON-decoded stuff and config file parsing
|
||||
"""
|
||||
if isinstance(subject, bool):
|
||||
return subject
|
||||
if isinstance(subject, basestring):
|
||||
if subject.strip().lower() in ('true', 'on', 'yes', '1'):
|
||||
return True
|
||||
return False
|
||||
|
||||
|
||||
def safe_decode(text, incoming=None, errors='strict'):
|
||||
"""
|
||||
Decodes incoming str 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 isntance of basestring
|
||||
"""
|
||||
if not isinstance(text, basestring):
|
||||
raise TypeError("%s can't be decoded" % type(text))
|
||||
|
||||
if isinstance(text, unicode):
|
||||
return text
|
||||
|
||||
if not incoming:
|
||||
incoming = (sys.stdin.encoding 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, incoming=None,
|
||||
encoding='utf-8', errors='strict'):
|
||||
"""
|
||||
Encodes incoming str/unicode 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 isntance of basestring
|
||||
"""
|
||||
if not isinstance(text, basestring):
|
||||
raise TypeError("%s can't be encoded" % type(text))
|
||||
|
||||
if not incoming:
|
||||
incoming = (sys.stdin.encoding or
|
||||
sys.getdefaultencoding())
|
||||
|
||||
if isinstance(text, unicode):
|
||||
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)
|
||||
|
||||
return text
|
@ -1,7 +1,7 @@
|
||||
[DEFAULT]
|
||||
|
||||
# The list of modules to copy from openstack-common
|
||||
modules=setup,timeutils
|
||||
modules=setup,timeutils,strutils
|
||||
|
||||
# The base module to hold the copy of openstack.common
|
||||
base=novaclient
|
||||
|
Loading…
Reference in New Issue