예제 #1
0
class EUCJPProber(MultiByteCharSetProber):
    def __init__(self):
        MultiByteCharSetProber.__init__(self)
        self._mCodingSM = CodingStateMachine(EUCJPSMModel)
        self._mDistributionAnalyzer = EUCJPDistributionAnalysis()
        self._mContextAnalyzer = EUCJPContextAnalysis()
        self.reset()

    def reset(self):
        MultiByteCharSetProber.reset(self)
        self._mContextAnalyzer.reset()

    def get_charset_name(self):
        return "EUC-JP"

    def feed(self, aBuf):
        aLen = len(aBuf)
        for i in range(0, aLen):
            codingState = self._mCodingSM.next_state(aBuf[i])
            if codingState == eError:
                if constants._debug:
                    sys.stderr.write(self.get_charset_name() +
                                     ' prober hit error at byte ' + str(i) +
                                     '\n')
                self._mState = constants.eNotMe
                break
            elif codingState == eItsMe:
                self._mState = constants.eFoundIt
                break
            elif codingState == eStart:
                charLen = self._mCodingSM.get_current_charlen()
                if i == 0:
                    self._mLastChar[1] = aBuf[0]
                    self._mContextAnalyzer.feed(self._mLastChar, charLen)
                    self._mDistributionAnalyzer.feed(self._mLastChar, charLen)
                else:
                    self._mContextAnalyzer.feed(aBuf[i - 1:i + 1], charLen)
                    self._mDistributionAnalyzer.feed(aBuf[i - 1:i + 1],
                                                     charLen)

        self._mLastChar[0] = aBuf[aLen - 1]

        if self.get_state() == constants.eDetecting:
            if self._mContextAnalyzer.got_enough_data() and \
                   (self.get_confidence() > constants.SHORTCUT_THRESHOLD):
                self._mState = constants.eFoundIt

        return self.get_state()

    def get_confidence(self):
        contxtCf = self._mContextAnalyzer.get_confidence()
        distribCf = self._mDistributionAnalyzer.get_confidence()
        return max(contxtCf, distribCf)
예제 #2
0
class EUCJPProber(MultiByteCharSetProber):
    def __init__(self):
        MultiByteCharSetProber.__init__(self)
        self._mCodingSM = CodingStateMachine(EUCJPSMModel)
        self._mDistributionAnalyzer = EUCJPDistributionAnalysis()
        self._mContextAnalyzer = EUCJPContextAnalysis()
        self.reset()

    def reset(self):
        MultiByteCharSetProber.reset(self)
        self._mContextAnalyzer.reset()

    def get_charset_name(self):
        return "EUC-JP"

    def feed(self, aBuf):
        aLen = len(aBuf)
        for i in range(0, aLen):
            codingState = self._mCodingSM.next_state(aBuf[i])
            if codingState == eError:
                if constants._debug:
                    sys.stderr.write(self.get_charset_name() + ' prober hit error at byte ' + str(i) + '\n')
                self._mState = constants.eNotMe
                break
            elif codingState == eItsMe:
                self._mState = constants.eFoundIt
                break
            elif codingState == eStart:
                charLen = self._mCodingSM.get_current_charlen()
                if i == 0:
                    self._mLastChar[1] = aBuf[0]
                    self._mContextAnalyzer.feed(self._mLastChar, charLen)
                    self._mDistributionAnalyzer.feed(self._mLastChar, charLen)
                else:
                    self._mContextAnalyzer.feed(aBuf[i-1:i+1], charLen)
                    self._mDistributionAnalyzer.feed(aBuf[i-1:i+1], charLen)

        self._mLastChar[0] = aBuf[aLen - 1]

        if self.get_state() == constants.eDetecting:
            if self._mContextAnalyzer.got_enough_data() and \
                   (self.get_confidence() > constants.SHORTCUT_THRESHOLD):
                self._mState = constants.eFoundIt

        return self.get_state()

    def get_confidence(self):
        contxtCf = self._mContextAnalyzer.get_confidence()
        distribCf = self._mDistributionAnalyzer.get_confidence()
        return max(contxtCf, distribCf)
예제 #3
0
 def __init__(self):
     MultiByteCharSetProber.__init__(self)
     self._mCodingSM = CodingStateMachine(EUCJPSMModel)
     self._mDistributionAnalyzer = EUCJPDistributionAnalysis()
     self._mContextAnalyzer = EUCJPContextAnalysis()
     self.reset()
예제 #4
0
 def __init__(self):
     MultiByteCharSetProber.__init__(self)
     self._mCodingSM = CodingStateMachine(EUCJPSMModel)
     self._mDistributionAnalyzer = EUCJPDistributionAnalysis()
     self._mContextAnalyzer = EUCJPContextAnalysis()
     self.reset()