######################## 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
Name | Type | Size | Permission | Actions |
---|---|---|---|---|
__pycache__ | Folder | 0755 |
|
|
cli | Folder | 0755 |
|
|
__init__.py | File | 1.52 KB | 0644 |
|
big5freq.py | File | 30.52 KB | 0644 |
|
big5prober.py | File | 1.72 KB | 0644 |
|
chardistribution.py | File | 9.19 KB | 0644 |
|
charsetgroupprober.py | File | 3.7 KB | 0644 |
|
charsetprober.py | File | 4.99 KB | 0644 |
|
codingstatemachine.py | File | 3.51 KB | 0644 |
|
compat.py | File | 1.11 KB | 0644 |
|
cp949prober.py | File | 1.81 KB | 0644 |
|
enums.py | File | 1.62 KB | 0644 |
|
escprober.py | File | 3.86 KB | 0644 |
|
escsm.py | File | 10.26 KB | 0644 |
|
eucjpprober.py | File | 3.66 KB | 0644 |
|
euckrfreq.py | File | 13.23 KB | 0644 |
|
euckrprober.py | File | 1.71 KB | 0644 |
|
euctwfreq.py | File | 30.88 KB | 0644 |
|
euctwprober.py | File | 1.71 KB | 0644 |
|
gb2312freq.py | File | 20.23 KB | 0644 |
|
gb2312prober.py | File | 1.71 KB | 0644 |
|
hebrewprober.py | File | 13.51 KB | 0644 |
|
jisfreq.py | File | 25.17 KB | 0644 |
|
jpcntx.py | File | 19.18 KB | 0644 |
|
langbulgarianmodel.py | File | 12.54 KB | 0644 |
|
langcyrillicmodel.py | File | 17.53 KB | 0644 |
|
langgreekmodel.py | File | 12.39 KB | 0644 |
|
langhebrewmodel.py | File | 11.08 KB | 0644 |
|
langhungarianmodel.py | File | 12.3 KB | 0644 |
|
langthaimodel.py | File | 11.03 KB | 0644 |
|
langturkishmodel.py | File | 10.84 KB | 0644 |
|
latin1prober.py | File | 5.24 KB | 0644 |
|
mbcharsetprober.py | File | 3.33 KB | 0644 |
|
mbcsgroupprober.py | File | 1.96 KB | 0644 |
|
mbcssm.py | File | 24.88 KB | 0644 |
|
sbcharsetprober.py | File | 5.52 KB | 0644 |
|
sbcsgroupprober.py | File | 3.46 KB | 0644 |
|
sjisprober.py | File | 3.69 KB | 0644 |
|
universaldetector.py | File | 12.19 KB | 0644 |
|
utf8prober.py | File | 2.7 KB | 0644 |
|
version.py | File | 242 B | 0644 |
|