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 #########################

from . import constants
import sys
import codecs
from .latin1prober import Latin1Prober  # windows-1252
from .mbcsgroupprober import MBCSGroupProber  # multi-byte character sets
from .sbcsgroupprober import SBCSGroupProber  # single-byte character sets
from .escprober import EscCharSetProber  # ISO-2122, etc.
import re

MINIMUM_THRESHOLD = 0.20
ePureAscii = 0
eEscAscii = 1
eHighbyte = 2

class UniversalDetector:
    def __init__(self):
        self._highBitDetector = re.compile(b'[\x80-\xFF]')
        self._escDetector = re.compile(b'(\033|~{)')
        self._mEscCharSetProber = None
        self._mCharSetProbers = []
        self.reset()

def reset(self):
        self.result = {'encoding': None, 'confidence': 0.0}
        self.done = False
        self._mStart = True
        self._mGotData = False
        self._mInputState = ePureAscii
        self._mLastChar = b''
        if self._mEscCharSetProber:
            self._mEscCharSetProber.reset()
        for prober in self._mCharSetProbers:
            prober.reset()

def feed(self, aBuf):
        if self.done:
            return

aLen = len(aBuf)
        if not aLen:
            return

if not self._mGotData:
            # If the data starts with BOM, we know it is UTF
            if aBuf[:3] == codecs.BOM_UTF8:
                # EF BB BF  UTF-8 with BOM
                self.result = {'encoding': "UTF-8-SIG", 'confidence': 1.0}
            elif aBuf[:4] == codecs.BOM_UTF32_LE:
                # FF FE 00 00  UTF-32, little-endian BOM
                self.result = {'encoding': "UTF-32LE", 'confidence': 1.0}
            elif aBuf[:4] == codecs.BOM_UTF32_BE:
                # 00 00 FE FF  UTF-32, big-endian BOM
                self.result = {'encoding': "UTF-32BE", 'confidence': 1.0}
            elif aBuf[:4] == b'\xFE\xFF\x00\x00':
                # FE FF 00 00  UCS-4, unusual octet order BOM (3412)
                self.result = {
                    'encoding': "X-ISO-10646-UCS-4-3412",
                    'confidence': 1.0
                }
            elif aBuf[:4] == b'\x00\x00\xFF\xFE':
                # 00 00 FF FE  UCS-4, unusual octet order BOM (2143)
                self.result = {
                    'encoding': "X-ISO-10646-UCS-4-2143",
                    'confidence': 1.0
                }
            elif aBuf[:2] == codecs.BOM_LE:
                # FF FE  UTF-16, little endian BOM
                self.result = {'encoding': "UTF-16LE", 'confidence': 1.0}
            elif aBuf[:2] == codecs.BOM_BE:
                # FE FF  UTF-16, big endian BOM
                self.result = {'encoding': "UTF-16BE", 'confidence': 1.0}

self._mGotData = True
        if self.result['encoding'] and (self.result['confidence'] > 0.0):
            self.done = True
            return

if self._mInputState == ePureAscii:
            if self._highBitDetector.search(aBuf):
                self._mInputState = eHighbyte
            elif ((self._mInputState == ePureAscii) and
                    self._escDetector.search(self._mLastChar + aBuf)):
                self._mInputState = eEscAscii

self._mLastChar = aBuf[-1:]

if self._mInputState == eEscAscii:
            if not self._mEscCharSetProber:
                self._mEscCharSetProber = EscCharSetProber()
            if self._mEscCharSetProber.feed(aBuf) == constants.eFoundIt:
                self.result = {'encoding': self._mEscCharSetProber.get_charset_name(),
                               'confidence': self._mEscCharSetProber.get_confidence()}
                self.done = True
        elif self._mInputState == eHighbyte:
            if not self._mCharSetProbers:
                self._mCharSetProbers = [MBCSGroupProber(), SBCSGroupProber(),
                                         Latin1Prober()]
            for prober in self._mCharSetProbers:
                if prober.feed(aBuf) == constants.eFoundIt:
                    self.result = {'encoding': prober.get_charset_name(),
                                   'confidence': prober.get_confidence()}
                    self.done = True
                    break

def close(self):
        if self.done:
            return
        if not self._mGotData:
            if constants._debug:
                sys.stderr.write('no data received!\n')
            return
        self.done = True

if self._mInputState == ePureAscii:
            self.result = {'encoding': 'ascii', 'confidence': 1.0}
            return self.result

if self._mInputState == eHighbyte:
            proberConfidence = None
            maxProberConfidence = 0.0
            maxProber = None
            for prober in self._mCharSetProbers:
                if not prober:
                    continue
                proberConfidence = prober.get_confidence()
                if proberConfidence > maxProberConfidence:
                    maxProberConfidence = proberConfidence
                    maxProber = prober
            if maxProber and (maxProberConfidence > MINIMUM_THRESHOLD):
                self.result = {'encoding': maxProber.get_charset_name(),
                               'confidence': maxProber.get_confidence()}
                return self.result

if constants._debug:
            sys.stderr.write('no probers hit minimum threshhold\n')
            for prober in self._mCharSetProbers[0].mProbers:
                if not prober:
                    continue
                sys.stderr.write('%s confidence = %s\n' %
                                 (prober.get_charset_name(),
                                  prober.get_confidence()))