utils.py
137 lines
| 4.1 KiB
| text/x-python
|
PythonLexer
/ vcsserver / utils.py
r0 | # RhodeCode VCSServer provides access to different vcs backends via network. | |||
r850 | # Copyright (C) 2014-2020 RhodeCode GmbH | |||
r0 | # | |||
# This program 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 3 of the License, or | ||||
# (at your option) any later version. | ||||
# | ||||
# This program 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 this program; if not, write to the Free Software Foundation, | ||||
# Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA | ||||
r381 | import logging | |||
r483 | import hashlib | |||
r381 | ||||
log = logging.getLogger(__name__) | ||||
r0 | ||||
r180 | def safe_int(val, default=None): | |||
""" | ||||
Returns int() of val if val is not convertable to int use default | ||||
instead | ||||
r0 | ||||
r180 | :param val: | |||
:param default: | ||||
""" | ||||
try: | ||||
val = int(val) | ||||
except (ValueError, TypeError): | ||||
val = default | ||||
return val | ||||
r1046 | def safe_str(str_, to_encoding=None) -> str: | |||
r0 | """ | |||
safe str function. Does few trick to turn unicode_ into string | ||||
r1046 | :param str_: str to encode | |||
r825 | :param to_encoding: encode to this type UTF8 default | |||
r0 | :rtype: str | |||
:returns: str object | ||||
""" | ||||
r1046 | if isinstance(str_, str): | |||
return str_ | ||||
# if it's bytes cast to str | ||||
if not isinstance(str_, bytes): | ||||
return str(str_) | ||||
r825 | to_encoding = to_encoding or ['utf8'] | |||
r0 | if not isinstance(to_encoding, (list, tuple)): | |||
to_encoding = [to_encoding] | ||||
for enc in to_encoding: | ||||
try: | ||||
r1046 | return str(str_, enc) | |||
except UnicodeDecodeError: | ||||
r0 | pass | |||
r1046 | return str(str_, to_encoding[0], 'replace') | |||
r825 | ||||
r1046 | def safe_bytes(str_, from_encoding=None) -> bytes: | |||
r825 | """ | |||
r1046 | safe bytes function. Does few trick to turn str_ into bytes string: | |||
r825 | ||||
:param str_: string to decode | ||||
:param from_encoding: encode from this type UTF8 default | ||||
:rtype: unicode | ||||
:returns: unicode object | ||||
""" | ||||
r1046 | if isinstance(str_, bytes): | |||
r825 | return str_ | |||
r1046 | if not isinstance(str_, str): | |||
raise ValueError('safe_bytes cannot convert other types than str: got: {}'.format(type(str_))) | ||||
from_encoding = from_encoding or ['utf8'] | ||||
r825 | if not isinstance(from_encoding, (list, tuple)): | |||
from_encoding = [from_encoding] | ||||
for enc in from_encoding: | ||||
try: | ||||
r1046 | return str_.encode(enc) | |||
r825 | except UnicodeDecodeError: | |||
pass | ||||
r1048 | return str_.encode(from_encoding[0], 'replace') | |||
def ascii_bytes(str_, allow_bytes=False) -> bytes: | ||||
""" | ||||
Simple conversion from str to bytes, with assumption that str_ is pure ASCII. | ||||
Fails with UnicodeError on invalid input. | ||||
This should be used where encoding and "safe" ambiguity should be avoided. | ||||
Where strings already have been encoded in other ways but still are unicode | ||||
string - for example to hex, base64, json, urlencoding, or are known to be | ||||
identifiers. | ||||
""" | ||||
if allow_bytes and isinstance(str_, bytes): | ||||
return str_ | ||||
if not isinstance(str_, str): | ||||
raise ValueError('ascii_bytes cannot convert other types than str: got: {}'.format(type(str_))) | ||||
return str_.encode('ascii') | ||||
def ascii_str(str_): | ||||
""" | ||||
Simple conversion from bytes to str, with assumption that str_ is pure ASCII. | ||||
Fails with UnicodeError on invalid input. | ||||
This should be used where encoding and "safe" ambiguity should be avoided. | ||||
Where strings are encoded but also in other ways are known to be ASCII, and | ||||
where a unicode string is wanted without caring about encoding. For example | ||||
to hex, base64, urlencoding, or are known to be identifiers. | ||||
""" | ||||
if not isinstance(str_, bytes): | ||||
raise ValueError('ascii_str cannot convert other types than bytes: got: {}'.format(type(str_))) | ||||
return str_.decode('ascii') | ||||
r407 | ||||
class AttributeDict(dict): | ||||
def __getattr__(self, attr): | ||||
return self.get(attr, None) | ||||
__setattr__ = dict.__setitem__ | ||||
__delattr__ = dict.__delitem__ | ||||
r483 | ||||
def sha1(val): | ||||
return hashlib.sha1(val).hexdigest() | ||||