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 28import sys 29from . import constants 30from .mbcharsetprober import MultiByteCharSetProber 31from .codingstatemachine import CodingStateMachine 32from .chardistribution import EUCJPDistributionAnalysis 33from .jpcntx import EUCJPContextAnalysis 34from .mbcssm import EUCJPSMModel 35 36 37class EUCJPProber(MultiByteCharSetProber): 38 def __init__(self): 39 MultiByteCharSetProber.__init__(self) 40 self._mCodingSM = CodingStateMachine(EUCJPSMModel) 41 self._mDistributionAnalyzer = EUCJPDistributionAnalysis() 42 self._mContextAnalyzer = EUCJPContextAnalysis() 43 self.reset() 44 45 def reset(self): 46 MultiByteCharSetProber.reset(self) 47 self._mContextAnalyzer.reset() 48 49 def get_charset_name(self): 50 return "EUC-JP" 51 52 def feed(self, aBuf): 53 aLen = len(aBuf) 54 for i in range(0, aLen): 55 # PY3K: aBuf is a byte array, so aBuf[i] is an int, not a byte 56 codingState = self._mCodingSM.next_state(aBuf[i]) 57 if codingState == constants.eError: 58 if constants._debug: 59 sys.stderr.write(self.get_charset_name() 60 + ' prober hit error at byte ' + str(i) 61 + '\n') 62 self._mState = constants.eNotMe 63 break 64 elif codingState == constants.eItsMe: 65 self._mState = constants.eFoundIt 66 break 67 elif codingState == constants.eStart: 68 charLen = self._mCodingSM.get_current_charlen() 69 if i == 0: 70 self._mLastChar[1] = aBuf[0] 71 self._mContextAnalyzer.feed(self._mLastChar, charLen) 72 self._mDistributionAnalyzer.feed(self._mLastChar, charLen) 73 else: 74 self._mContextAnalyzer.feed(aBuf[i - 1:i + 1], charLen) 75 self._mDistributionAnalyzer.feed(aBuf[i - 1:i + 1], 76 charLen) 77 78 self._mLastChar[0] = aBuf[aLen - 1] 79 80 if self.get_state() == constants.eDetecting: 81 if (self._mContextAnalyzer.got_enough_data() and 82 (self.get_confidence() > constants.SHORTCUT_THRESHOLD)): 83 self._mState = constants.eFoundIt 84 85 return self.get_state() 86 87 def get_confidence(self): 88 contxtCf = self._mContextAnalyzer.get_confidence() 89 distribCf = self._mDistributionAnalyzer.get_confidence() 90 return max(contxtCf, distribCf) 91