OXIESEC PANEL

Name	Size	Modified	Perms
📁 ..	-	10/02/2024 07:52:55 PM	rwxr-xr-x
📄 __init__.py	1.26 KB	10/07/2014 03:03:24 PM	rw-r--r--
📁 __pycache__	-	10/02/2024 07:52:55 PM	rwxr-xr-x
📄 big5freq.py	80.66 KB	09/17/2014 05:56:49 PM	rw-r--r--
📄 big5prober.py	1.64 KB	09/17/2014 05:56:49 PM	rw-r--r--
📄 chardetect.py	2.45 KB	10/07/2014 03:03:14 PM	rw-r--r--
📄 chardistribution.py	9.01 KB	09/17/2014 05:56:49 PM	rw-r--r--
📄 charsetgroupprober.py	3.7 KB	09/17/2014 05:56:49 PM	rw-r--r--
📄 charsetprober.py	1.86 KB	09/17/2014 05:56:49 PM	rw-r--r--
📄 codingstatemachine.py	2.26 KB	09/17/2014 05:56:49 PM	rw-r--r--
📄 compat.py	1.13 KB	09/17/2014 05:56:49 PM	rw-r--r--
📄 constants.py	1.3 KB	09/17/2014 05:56:49 PM	rw-r--r--
📄 cp949prober.py	1.74 KB	09/17/2014 05:56:49 PM	rw-r--r--
📄 escprober.py	3.11 KB	09/17/2014 05:56:49 PM	rw-r--r--
📄 escsm.py	7.66 KB	09/17/2014 05:56:49 PM	rw-r--r--
📄 eucjpprober.py	3.59 KB	09/17/2014 05:56:49 PM	rw-r--r--
📄 euckrfreq.py	44.9 KB	09/17/2014 05:56:49 PM	rw-r--r--
📄 euckrprober.py	1.64 KB	09/17/2014 05:56:49 PM	rw-r--r--
📄 euctwfreq.py	34.05 KB	09/17/2014 05:56:49 PM	rw-r--r--
📄 euctwprober.py	1.64 KB	09/17/2014 05:56:49 PM	rw-r--r--
📄 gb2312freq.py	35.17 KB	09/17/2014 05:56:49 PM	rw-r--r--
📄 gb2312prober.py	1.64 KB	09/17/2014 05:56:49 PM	rw-r--r--
📄 hebrewprober.py	13.05 KB	09/17/2014 05:56:49 PM	rw-r--r--
📄 jisfreq.py	46.21 KB	09/17/2014 05:56:49 PM	rw-r--r--
📄 jpcntx.py	18.89 KB	10/07/2014 03:03:14 PM	rw-r--r--
📄 langbulgarianmodel.py	12.48 KB	09/17/2014 05:56:49 PM	rw-r--r--
📄 langcyrillicmodel.py	17.31 KB	09/17/2014 05:56:49 PM	rw-r--r--
📄 langgreekmodel.py	12.33 KB	09/17/2014 05:56:49 PM	rw-r--r--
📄 langhebrewmodel.py	11.05 KB	09/17/2014 05:56:49 PM	rw-r--r--
📄 langhungarianmodel.py	12.24 KB	09/17/2014 05:56:49 PM	rw-r--r--
📄 langthaimodel.py	11.01 KB	09/17/2014 05:56:49 PM	rw-r--r--
📄 latin1prober.py	5.11 KB	10/07/2014 03:03:14 PM	rw-r--r--
📄 mbcharsetprober.py	3.19 KB	09/17/2014 05:56:49 PM	rw-r--r--
📄 mbcsgroupprober.py	1.92 KB	09/17/2014 05:56:49 PM	rw-r--r--
📄 mbcssm.py	19.13 KB	10/07/2014 03:03:14 PM	rw-r--r--
📄 sbcharsetprober.py	4.68 KB	09/17/2014 05:56:49 PM	rw-r--r--
📄 sbcsgroupprober.py	3.21 KB	09/17/2014 05:56:49 PM	rw-r--r--
📄 sjisprober.py	3.68 KB	10/07/2014 03:03:14 PM	rw-r--r--
📄 universaldetector.py	6.68 KB	09/17/2014 05:56:49 PM	rw-r--r--
📄 utf8prober.py	2.59 KB	09/17/2014 05:56:49 PM	rw-r--r--

Editing: mbcharsetprober.py

######################## BEGIN LICENSE BLOCK ########################
# The Original Code is Mozilla Universal charset detector code.
#
# The Initial Developer of the Original Code is
# Netscape Communications Corporation.
# Portions created by the Initial Developer are Copyright (C) 2001
# the Initial Developer. All Rights Reserved.
#
# Contributor(s):
#   Mark Pilgrim - port to Python
#   Shy Shalom - original C code
#   Proofpoint, Inc.
#
# 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 #########################

import sys
from . import constants
from .charsetprober import CharSetProber

class MultiByteCharSetProber(CharSetProber):
    def __init__(self):
        CharSetProber.__init__(self)
        self._mDistributionAnalyzer = None
        self._mCodingSM = None
        self._mLastChar = [0, 0]

def reset(self):
        CharSetProber.reset(self)
        if self._mCodingSM:
            self._mCodingSM.reset()
        if self._mDistributionAnalyzer:
            self._mDistributionAnalyzer.reset()
        self._mLastChar = [0, 0]

def get_charset_name(self):
        pass

def feed(self, aBuf):
        aLen = len(aBuf)
        for i in range(0, aLen):
            codingState = self._mCodingSM.next_state(aBuf[i])
            if codingState == constants.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 == constants.eItsMe:
                self._mState = constants.eFoundIt
                break
            elif codingState == constants.eStart:
                charLen = self._mCodingSM.get_current_charlen()
                if i == 0:
                    self._mLastChar[1] = aBuf[0]
                    self._mDistributionAnalyzer.feed(self._mLastChar, charLen)
                else:
                    self._mDistributionAnalyzer.feed(aBuf[i - 1:i + 1],
                                                     charLen)

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

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

return self.get_state()

def get_confidence(self):
        return self._mDistributionAnalyzer.get_confidence()