mirror of
https://github.com/SickGear/SickGear.git
synced 2024-12-01 00:43:37 +00:00
0d9fbc1ad7
This version of SickBeard uses both TVDB and TVRage to search and gather it's series data from allowing you to now have access to and download shows that you couldn't before because of being locked into only what TheTVDB had to offer. Also this edition is based off the code we used in our XEM editon so it does come with scene numbering support as well as all the other features our XEM edition has to offer. Please before using this with your existing database (sickbeard.db) please make a backup copy of it and delete any other database files such as cache.db and failed.db if present, we HIGHLY recommend starting out with no database files at all to make this a fresh start but the choice is at your own risk! Enjoy!
76 lines
2.6 KiB
Python
76 lines
2.6 KiB
Python
######################## BEGIN LICENSE BLOCK ########################
|
|
# The Original Code is mozilla.org code.
|
|
#
|
|
# The Initial Developer of the Original Code is
|
|
# Netscape Communications Corporation.
|
|
# Portions created by the Initial Developer are Copyright (C) 1998
|
|
# the Initial Developer. All Rights Reserved.
|
|
#
|
|
# Contributor(s):
|
|
# Mark Pilgrim - port to Python
|
|
#
|
|
# This library is free software; you can redistribute it and/or
|
|
# modify it under the terms of the GNU Lesser General Public
|
|
# License as published by the Free Software Foundation; either
|
|
# version 2.1 of the License, or (at your option) any later version.
|
|
#
|
|
# This library 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
|
|
# Lesser General Public License for more details.
|
|
#
|
|
# You should have received a copy of the GNU Lesser General Public
|
|
# License along with this library; if not, write to the Free Software
|
|
# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
|
|
# 02110-1301 USA
|
|
######################### END LICENSE BLOCK #########################
|
|
|
|
from . import constants
|
|
from .charsetprober import CharSetProber
|
|
from .codingstatemachine import CodingStateMachine
|
|
from .mbcssm import UTF8SMModel
|
|
|
|
ONE_CHAR_PROB = 0.5
|
|
|
|
|
|
class UTF8Prober(CharSetProber):
|
|
def __init__(self):
|
|
CharSetProber.__init__(self)
|
|
self._mCodingSM = CodingStateMachine(UTF8SMModel)
|
|
self.reset()
|
|
|
|
def reset(self):
|
|
CharSetProber.reset(self)
|
|
self._mCodingSM.reset()
|
|
self._mNumOfMBChar = 0
|
|
|
|
def get_charset_name(self):
|
|
return "utf-8"
|
|
|
|
def feed(self, aBuf):
|
|
for c in aBuf:
|
|
codingState = self._mCodingSM.next_state(c)
|
|
if codingState == constants.eError:
|
|
self._mState = constants.eNotMe
|
|
break
|
|
elif codingState == constants.eItsMe:
|
|
self._mState = constants.eFoundIt
|
|
break
|
|
elif codingState == constants.eStart:
|
|
if self._mCodingSM.get_current_charlen() >= 2:
|
|
self._mNumOfMBChar += 1
|
|
|
|
if self.get_state() == constants.eDetecting:
|
|
if self.get_confidence() > constants.SHORTCUT_THRESHOLD:
|
|
self._mState = constants.eFoundIt
|
|
|
|
return self.get_state()
|
|
|
|
def get_confidence(self):
|
|
unlike = 0.99
|
|
if self._mNumOfMBChar < 6:
|
|
for i in range(0, self._mNumOfMBChar):
|
|
unlike = unlike * ONE_CHAR_PROB
|
|
return 1.0 - unlike
|
|
else:
|
|
return unlike
|