OLD | NEW |
(Empty) | |
| 1 ######################## BEGIN LICENSE BLOCK ######################## |
| 2 # The Original Code is Mozilla Communicator client code. |
| 3 # |
| 4 # The Initial Developer of the Original Code is |
| 5 # Netscape Communications Corporation. |
| 6 # Portions created by the Initial Developer are Copyright (C) 1998 |
| 7 # the Initial Developer. All Rights Reserved. |
| 8 # |
| 9 # Contributor(s): |
| 10 # Mark Pilgrim - port to Python |
| 11 # |
| 12 # This library is free software; you can redistribute it and/or |
| 13 # modify it under the terms of the GNU Lesser General Public |
| 14 # License as published by the Free Software Foundation; either |
| 15 # version 2.1 of the License, or (at your option) any later version. |
| 16 # |
| 17 # This library is distributed in the hope that it will be useful, |
| 18 # but WITHOUT ANY WARRANTY; without even the implied warranty of |
| 19 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU |
| 20 # Lesser General Public License for more details. |
| 21 # |
| 22 # You should have received a copy of the GNU Lesser General Public |
| 23 # License along with this library; if not, write to the Free Software |
| 24 # Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA |
| 25 # 02110-1301 USA |
| 26 ######################### END LICENSE BLOCK ######################### |
| 27 |
| 28 from . import constants |
| 29 import sys |
| 30 from .charsetprober import CharSetProber |
| 31 |
| 32 |
| 33 class CharSetGroupProber(CharSetProber): |
| 34 def __init__(self): |
| 35 CharSetProber.__init__(self) |
| 36 self._mActiveNum = 0 |
| 37 self._mProbers = [] |
| 38 self._mBestGuessProber = None |
| 39 |
| 40 def reset(self): |
| 41 CharSetProber.reset(self) |
| 42 self._mActiveNum = 0 |
| 43 for prober in self._mProbers: |
| 44 if prober: |
| 45 prober.reset() |
| 46 prober.active = True |
| 47 self._mActiveNum += 1 |
| 48 self._mBestGuessProber = None |
| 49 |
| 50 def get_charset_name(self): |
| 51 if not self._mBestGuessProber: |
| 52 self.get_confidence() |
| 53 if not self._mBestGuessProber: |
| 54 return None |
| 55 # self._mBestGuessProber = self._mProbers[0] |
| 56 return self._mBestGuessProber.get_charset_name() |
| 57 |
| 58 def feed(self, aBuf): |
| 59 for prober in self._mProbers: |
| 60 if not prober: |
| 61 continue |
| 62 if not prober.active: |
| 63 continue |
| 64 st = prober.feed(aBuf) |
| 65 if not st: |
| 66 continue |
| 67 if st == constants.eFoundIt: |
| 68 self._mBestGuessProber = prober |
| 69 return self.get_state() |
| 70 elif st == constants.eNotMe: |
| 71 prober.active = False |
| 72 self._mActiveNum -= 1 |
| 73 if self._mActiveNum <= 0: |
| 74 self._mState = constants.eNotMe |
| 75 return self.get_state() |
| 76 return self.get_state() |
| 77 |
| 78 def get_confidence(self): |
| 79 st = self.get_state() |
| 80 if st == constants.eFoundIt: |
| 81 return 0.99 |
| 82 elif st == constants.eNotMe: |
| 83 return 0.01 |
| 84 bestConf = 0.0 |
| 85 self._mBestGuessProber = None |
| 86 for prober in self._mProbers: |
| 87 if not prober: |
| 88 continue |
| 89 if not prober.active: |
| 90 if constants._debug: |
| 91 sys.stderr.write(prober.get_charset_name() |
| 92 + ' not active\n') |
| 93 continue |
| 94 cf = prober.get_confidence() |
| 95 if constants._debug: |
| 96 sys.stderr.write('%s confidence = %s\n' % |
| 97 (prober.get_charset_name(), cf)) |
| 98 if bestConf < cf: |
| 99 bestConf = cf |
| 100 self._mBestGuessProber = prober |
| 101 if not self._mBestGuessProber: |
| 102 return 0.0 |
| 103 return bestConf |
| 104 # else: |
| 105 # self._mBestGuessProber = self._mProbers[0] |
| 106 # return self._mBestGuessProber.get_confidence() |
OLD | NEW |