chardet/eucjpprober.py

   1 ######################## BEGIN LICENSE BLOCK ########################
   2 # The Original Code is mozilla.org 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 import constants, sys
  29 from constants import eStart, eError, eItsMe
  30 from mbcharsetprober import MultiByteCharSetProber
  31 from codingstatemachine import CodingStateMachine
  32 from chardistribution import EUCJPDistributionAnalysis
  33 from jpcntx import EUCJPContextAnalysis
  34 from mbcssm import EUCJPSMModel
  35
  36 class EUCJPProber(MultiByteCharSetProber):
  37     def __init__(self):
  38         MultiByteCharSetProber.__init__(self)
  39         self._mCodingSM = CodingStateMachine(EUCJPSMModel)
  40         self._mDistributionAnalyzer = EUCJPDistributionAnalysis()
  41         self._mContextAnalyzer = EUCJPContextAnalysis()
  42         self.reset()
  43
  44     def reset(self):
  45         MultiByteCharSetProber.reset(self)
  46         self._mContextAnalyzer.reset()
  47
  48     def get_charset_name(self):
  49         return "EUC-JP"
  50
  51     def feed(self, aBuf):
  52         aLen = len(aBuf)
  53         for i in range(0, aLen):
  54             codingState = self._mCodingSM.next_state(aBuf[i])
  55             if codingState == eError:
  56                 if constants._debug:
  57                     sys.stderr.write(self.get_charset_name() + ' prober hit error at byte ' + str(i) + '\n')
  58                 self._mState = constants.eNotMe
  59                 break
  60             elif codingState == eItsMe:
  61                 self._mState = constants.eFoundIt
  62                 break
  63             elif codingState == eStart:
  64                 charLen = self._mCodingSM.get_current_charlen()
  65                 if i == 0:
  66                     self._mLastChar[1] = aBuf[0]
  67                     self._mContextAnalyzer.feed(self._mLastChar, charLen)
  68                     self._mDistributionAnalyzer.feed(self._mLastChar, charLen)
  69                 else:
  70                     self._mContextAnalyzer.feed(aBuf[i-1:i+1], charLen)
  71                     self._mDistributionAnalyzer.feed(aBuf[i-1:i+1], charLen)
  72
  73         self._mLastChar[0] = aBuf[aLen - 1]
  74
  75         if self.get_state() == constants.eDetecting:
  76             if self._mContextAnalyzer.got_enough_data() and \
  77                    (self.get_confidence() > constants.SHORTCUT_THRESHOLD):
  78                 self._mState = constants.eFoundIt
  79
  80         return self.get_state()
  81
  82     def get_confidence(self):
  83         contxtCf = self._mContextAnalyzer.get_confidence()
  84         distribCf = self._mDistributionAnalyzer.get_confidence()
  85         return max(contxtCf, distribCf)