1
0
mirror of https://github.com/moparisthebest/SickRage synced 2024-12-13 11:32:20 -05:00
SickRage/sickbeard/encodingKludge.py

105 lines
3.2 KiB
Python
Raw Normal View History

# Author: Nic Wolfe <nic@wolfeden.ca>
# URL: http://code.google.com/p/sickbeard/
#
2014-05-23 08:37:22 -04:00
# This file is part of SickRage.
#
2014-05-23 08:37:22 -04:00
# SickRage 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.
#
2014-05-23 08:37:22 -04:00
# SickRage 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
2014-05-23 08:37:22 -04:00
# along with SickRage. If not, see <http://www.gnu.org/licenses/>.
import os
import traceback
import re
import sickbeard
import six
import chardet
import unicodedata
from string import ascii_letters, digits
from sickbeard import logger
def toSafeString(original):
valid_chars = "-_.() %s%s" % (ascii_letters, digits)
cleaned_filename = unicodedata.normalize('NFKD', _toUnicode(original)).encode('ASCII', 'ignore')
valid_string = ''.join(c for c in cleaned_filename if c in valid_chars)
return ' '.join(valid_string.split())
def simplifyString(original):
string = stripAccents(original.lower())
string = toSafeString(' '.join(re.split('\W+', string)))
split = re.split('\W+|_', string.lower())
return _toUnicode(' '.join(split))
def _toUnicode(x):
if isinstance(x, unicode):
return x
else:
try:
return six.text_type(x)
except:
try:
if chardet.detect(x).get('encoding') == 'utf-8':
return x.decode('utf-8')
if isinstance(x, str):
try:
return x.decode(sickbeard.SYS_ENCODING)
except UnicodeDecodeError:
raise
return x
except:
return x
def ss(x):
u_x = _toUnicode(x)
try:
u_x_encoded = u_x.encode(sickbeard.SYS_ENCODING, 'xmlcharrefreplace')
except:
try:
u_x_encoded = u_x.encode(sickbeard.SYS_ENCODING)
except:
try:
u_x_encoded = u_x.encode(sickbeard.SYS_ENCODING, 'replace')
except:
try:
u_x_encoded = u_x.encode('utf-8', 'replace')
except:
2014-12-13 14:19:13 -05:00
try:
u_x_encoded = str(x)
except:
u_x_encoded = x
return u_x_encoded
def fixListEncodings(x):
if not isinstance(x, (list, tuple)):
return x
else:
return filter(lambda x: x != None, map(_toUnicode, x))
2014-05-14 12:18:54 -04:00
def ek(func, *args, **kwargs):
if os.name == 'nt':
2014-05-14 12:18:54 -04:00
result = func(*args, **kwargs)
else:
result = func(*[ss(x) if isinstance(x, (str, unicode)) else x for x in args], **kwargs)
if isinstance(result, (list, tuple)):
return fixListEncodings(result)
elif isinstance(result, str):
return _toUnicode(result)
else:
2014-05-14 12:18:54 -04:00
return result
def stripAccents(s):
return ''.join((c for c in unicodedata.normalize('NFD', _toUnicode(s)) if unicodedata.category(c) != 'Mn'))