Gecko [ www.foryou-vip.com ]

Name	Size	Permission	Date
__pycache__	[ DIR ]	drwxrwxrwx	2020-08-25 15:28
__init__.py	1.26 KB	-rwxrwxrwx	2014-10-07 17:03
big5freq.py	80.66 KB	-rwxrwxrwx	2014-09-17 19:56
big5prober.py	1.64 KB	-rwxrwxrwx	2014-09-17 19:56
chardetect.py	2.45 KB	-rwxrwxrwx	2014-10-07 17:03
chardistribution.py	9.01 KB	-rwxrwxrwx	2014-09-17 19:56
charsetgroupprober.py	3.7 KB	-rwxrwxrwx	2014-09-17 19:56
charsetprober.py	1.86 KB	-rwxrwxrwx	2014-09-17 19:56
codingstatemachine.py	2.26 KB	-rwxrwxrwx	2014-09-17 19:56
compat.py	1.13 KB	-rwxrwxrwx	2014-09-17 19:56
constants.py	1.3 KB	-rwxrwxrwx	2014-09-17 19:56
cp949prober.py	1.74 KB	-rwxrwxrwx	2014-09-17 19:56
escprober.py	3.11 KB	-rwxrwxrwx	2014-09-17 19:56
escsm.py	7.66 KB	-rwxrwxrwx	2014-09-17 19:56
eucjpprober.py	3.59 KB	-rwxrwxrwx	2014-09-17 19:56
euckrfreq.py	44.9 KB	-rwxrwxrwx	2014-09-17 19:56
euckrprober.py	1.64 KB	-rwxrwxrwx	2014-09-17 19:56
euctwfreq.py	34.05 KB	-rwxrwxrwx	2014-09-17 19:56
euctwprober.py	1.64 KB	-rwxrwxrwx	2014-09-17 19:56
gb2312freq.py	35.17 KB	-rwxrwxrwx	2014-09-17 19:56
gb2312prober.py	1.64 KB	-rwxrwxrwx	2014-09-17 19:56
hebrewprober.py	13.05 KB	-rwxrwxrwx	2014-09-17 19:56
jisfreq.py	46.21 KB	-rwxrwxrwx	2014-09-17 19:56
jpcntx.py	18.89 KB	-rwxrwxrwx	2014-10-07 17:03
langbulgarianmodel.py	12.48 KB	-rwxrwxrwx	2014-09-17 19:56
langcyrillicmodel.py	17.31 KB	-rwxrwxrwx	2014-09-17 19:56
langgreekmodel.py	12.33 KB	-rwxrwxrwx	2014-09-17 19:56
langhebrewmodel.py	11.05 KB	-rwxrwxrwx	2014-09-17 19:56
langhungarianmodel.py	12.24 KB	-rwxrwxrwx	2014-09-17 19:56
langthaimodel.py	11.01 KB	-rwxrwxrwx	2014-09-17 19:56
latin1prober.py	5.11 KB	-rwxrwxrwx	2014-10-07 17:03
mbcharsetprober.py	3.19 KB	-rwxrwxrwx	2014-09-17 19:56
mbcsgroupprober.py	1.92 KB	-rwxrwxrwx	2014-09-17 19:56
mbcssm.py	19.13 KB	-rwxrwxrwx	2014-10-07 17:03
sbcharsetprober.py	4.68 KB	-rwxrwxrwx	2014-09-17 19:56
sbcsgroupprober.py	3.21 KB	-rwxrwxrwx	2014-09-17 19:56
sjisprober.py	3.68 KB	-rwxrwxrwx	2014-10-07 17:03
universaldetector.py	6.68 KB	-rwxrwxrwx	2014-09-17 19:56
utf8prober.py	2.59 KB	-rwxrwxrwx	2014-09-17 19:56

Rename

######################## 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
#
# 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
from .compat import wrap_ord

SAMPLE_SIZE = 64
SB_ENOUGH_REL_THRESHOLD = 1024
POSITIVE_SHORTCUT_THRESHOLD = 0.95
NEGATIVE_SHORTCUT_THRESHOLD = 0.05
SYMBOL_CAT_ORDER = 250
NUMBER_OF_SEQ_CAT = 4
POSITIVE_CAT = NUMBER_OF_SEQ_CAT - 1
#NEGATIVE_CAT = 0

class SingleByteCharSetProber(CharSetProber):
    def __init__(self, model, reversed=False, nameProber=None):
        CharSetProber.__init__(self)
        self._mModel = model
        # TRUE if we need to reverse every pair in the model lookup
        self._mReversed = reversed
        # Optional auxiliary prober for name decision
        self._mNameProber = nameProber
        self.reset()

def reset(self):
        CharSetProber.reset(self)
        # char order of last character
        self._mLastOrder = 255
        self._mSeqCounters = [0] * NUMBER_OF_SEQ_CAT
        self._mTotalSeqs = 0
        self._mTotalChar = 0
        # characters that fall in our sampling range
        self._mFreqChar = 0

def get_charset_name(self):
        if self._mNameProber:
            return self._mNameProber.get_charset_name()
        else:
            return self._mModel['charsetName']

def feed(self, aBuf):
        if not self._mModel['keepEnglishLetter']:
            aBuf = self.filter_without_english_letters(aBuf)
        aLen = len(aBuf)
        if not aLen:
            return self.get_state()
        for c in aBuf:
            order = self._mModel['charToOrderMap'][wrap_ord(c)]
            if order < SYMBOL_CAT_ORDER:
                self._mTotalChar += 1
            if order < SAMPLE_SIZE:
                self._mFreqChar += 1
                if self._mLastOrder < SAMPLE_SIZE:
                    self._mTotalSeqs += 1
                    if not self._mReversed:
                        i = (self._mLastOrder * SAMPLE_SIZE) + order
                        model = self._mModel['precedenceMatrix'][i]
                    else:  # reverse the order of the letters in the lookup
                        i = (order * SAMPLE_SIZE) + self._mLastOrder
                        model = self._mModel['precedenceMatrix'][i]
                    self._mSeqCounters[model] += 1
            self._mLastOrder = order

if self.get_state() == constants.eDetecting:
            if self._mTotalSeqs > SB_ENOUGH_REL_THRESHOLD:
                cf = self.get_confidence()
                if cf > POSITIVE_SHORTCUT_THRESHOLD:
                    if constants._debug:
                        sys.stderr.write('%s confidence = %s, we have a'
                                         'winner\n' %
                                         (self._mModel['charsetName'], cf))
                    self._mState = constants.eFoundIt
                elif cf < NEGATIVE_SHORTCUT_THRESHOLD:
                    if constants._debug:
                        sys.stderr.write('%s confidence = %s, below negative'
                                         'shortcut threshhold %s\n' %
                                         (self._mModel['charsetName'], cf,
                                          NEGATIVE_SHORTCUT_THRESHOLD))
                    self._mState = constants.eNotMe

return self.get_state()

def get_confidence(self):
        r = 0.01
        if self._mTotalSeqs > 0:
            r = ((1.0 * self._mSeqCounters[POSITIVE_CAT]) / self._mTotalSeqs
                 / self._mModel['mTypicalPositiveRatio'])
            r = r * self._mFreqChar / self._mTotalChar
            if r >= 1.0:
                r = 0.99
        return r