PATH:
usr
/
lib
/
python3.6
/
site-packages
/
pip
/
_vendor
/
chardet
######################## BEGIN LICENSE BLOCK ######################## # The Original Code is Mozilla Communicator client 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 .enums import ProbingState from .charsetprober import CharSetProber class CharSetGroupProber(CharSetProber): def __init__(self, lang_filter=None): super(CharSetGroupProber, self).__init__(lang_filter=lang_filter) self._active_num = 0 self.probers = [] self._best_guess_prober = None def reset(self): super(CharSetGroupProber, self).reset() self._active_num = 0 for prober in self.probers: if prober: prober.reset() prober.active = True self._active_num += 1 self._best_guess_prober = None @property def charset_name(self): if not self._best_guess_prober: self.get_confidence() if not self._best_guess_prober: return None return self._best_guess_prober.charset_name @property def language(self): if not self._best_guess_prober: self.get_confidence() if not self._best_guess_prober: return None return self._best_guess_prober.language def feed(self, byte_str): for prober in self.probers: if not prober: continue if not prober.active: continue state = prober.feed(byte_str) if not state: continue if state == ProbingState.FOUND_IT: self._best_guess_prober = prober return self.state elif state == ProbingState.NOT_ME: prober.active = False self._active_num -= 1 if self._active_num <= 0: self._state = ProbingState.NOT_ME return self.state return self.state def get_confidence(self): state = self.state if state == ProbingState.FOUND_IT: return 0.99 elif state == ProbingState.NOT_ME: return 0.01 best_conf = 0.0 self._best_guess_prober = None for prober in self.probers: if not prober: continue if not prober.active: self.logger.debug('%s not active', prober.charset_name) continue conf = prober.get_confidence() self.logger.debug('%s %s confidence = %s', prober.charset_name, prober.language, conf) if best_conf < conf: best_conf = conf self._best_guess_prober = prober if not self._best_guess_prober: return 0.0 return best_conf
[-] mbcssm.py
[edit]
[-] euckrprober.py
[edit]
[-] charsetprober.py
[edit]
[-] sbcsgroupprober.py
[edit]
[-] utf8prober.py
[edit]
[-] eucjpprober.py
[edit]
[-] codingstatemachine.py
[edit]
[-] gb2312prober.py
[edit]
[-] sjisprober.py
[edit]
[-] escprober.py
[edit]
[-] universaldetector.py
[edit]
[+]
..
[-] gb2312freq.py
[edit]
[-] mbcharsetprober.py
[edit]
[-] big5freq.py
[edit]
[-] euctwprober.py
[edit]
[-] langthaimodel.py
[edit]
[-] langturkishmodel.py
[edit]
[-] sbcharsetprober.py
[edit]
[+]
__pycache__
[-] langgreekmodel.py
[edit]
[-] euctwfreq.py
[edit]
[-] escsm.py
[edit]
[-] euckrfreq.py
[edit]
[-] langbulgarianmodel.py
[edit]
[-] enums.py
[edit]
[-] version.py
[edit]
[-] compat.py
[edit]
[-] big5prober.py
[edit]
[-] cp949prober.py
[edit]
[-] jisfreq.py
[edit]
[-] mbcsgroupprober.py
[edit]
[-] charsetgroupprober.py
[edit]
[-] __init__.py
[edit]
[-] hebrewprober.py
[edit]
[+]
cli
[-] latin1prober.py
[edit]
[-] jpcntx.py
[edit]
[-] langcyrillicmodel.py
[edit]
[-] langhebrewmodel.py
[edit]
[-] chardistribution.py
[edit]
[-] langhungarianmodel.py
[edit]