Gecko [ gtgates.com ]

Name	Size	Permission	Date
cli	[ DIR ]	drwxr-xr-x	2024-02-12 23:52
__init__.py	1.52 KB	-rw-r--r--	2017-04-12 18:41
__init__.pyc	970 B	-rw-r--r--	2022-04-21 14:07
__init__.pyo	970 B	-rw-r--r--	2022-04-21 14:07
big5freq.py	30.52 KB	-rw-r--r--	2017-04-11 17:51
big5freq.pyc	53.41 KB	-rw-r--r--	2022-04-21 14:07
big5freq.pyo	53.41 KB	-rw-r--r--	2022-04-21 14:07
big5prober.py	1.72 KB	-rw-r--r--	2017-04-11 17:51
big5prober.pyc	1.27 KB	-rw-r--r--	2022-04-21 14:07
big5prober.pyo	1.27 KB	-rw-r--r--	2022-04-21 14:07
chardistribution.py	9.19 KB	-rw-r--r--	2017-04-11 19:52
chardistribution.pyc	7.36 KB	-rw-r--r--	2022-04-21 14:07
chardistribution.pyo	7.36 KB	-rw-r--r--	2022-04-21 14:07
charsetgroupprober.py	3.7 KB	-rw-r--r--	2017-04-11 17:51
charsetgroupprober.pyc	2.71 KB	-rw-r--r--	2022-04-21 14:07
charsetgroupprober.pyo	2.71 KB	-rw-r--r--	2022-04-21 14:07
charsetprober.py	4.99 KB	-rw-r--r--	2017-06-08 14:21
charsetprober.pyc	3.92 KB	-rw-r--r--	2022-04-21 14:07
charsetprober.pyo	3.92 KB	-rw-r--r--	2022-04-21 14:07
codingstatemachine.py	3.51 KB	-rw-r--r--	2017-04-11 17:51
codingstatemachine.pyc	3.19 KB	-rw-r--r--	2022-04-21 14:07
codingstatemachine.pyo	3.19 KB	-rw-r--r--	2022-04-21 14:07
compat.py	1.11 KB	-rw-r--r--	2017-06-08 14:32
compat.pyc	392 B	-rw-r--r--	2022-04-21 14:07
compat.pyo	392 B	-rw-r--r--	2022-04-21 14:07
cp949prober.py	1.81 KB	-rw-r--r--	2017-04-11 17:51
cp949prober.pyc	1.27 KB	-rw-r--r--	2022-04-21 14:07
cp949prober.pyo	1.27 KB	-rw-r--r--	2022-04-21 14:07
enums.py	1.62 KB	-rw-r--r--	2017-04-11 17:51
enums.pyc	2.96 KB	-rw-r--r--	2022-04-21 14:07
enums.pyo	2.96 KB	-rw-r--r--	2022-04-21 14:07
escprober.py	3.86 KB	-rw-r--r--	2017-04-11 17:51
escprober.pyc	3.06 KB	-rw-r--r--	2022-04-21 14:07
escprober.pyo	3.06 KB	-rw-r--r--	2022-04-21 14:07
escsm.py	10.26 KB	-rw-r--r--	2017-04-11 17:51
escsm.pyc	7.82 KB	-rw-r--r--	2022-04-21 14:07
escsm.pyo	7.82 KB	-rw-r--r--	2022-04-21 14:07
eucjpprober.py	3.66 KB	-rw-r--r--	2017-04-11 17:51
eucjpprober.pyc	2.88 KB	-rw-r--r--	2022-04-21 14:07
eucjpprober.pyo	2.88 KB	-rw-r--r--	2022-04-21 14:07
euckrfreq.py	13.23 KB	-rw-r--r--	2017-04-11 17:51
euckrfreq.pyc	23.51 KB	-rw-r--r--	2022-04-21 14:07
euckrfreq.pyo	23.51 KB	-rw-r--r--	2022-04-21 14:07
euckrprober.py	1.71 KB	-rw-r--r--	2017-04-11 17:51
euckrprober.pyc	1.28 KB	-rw-r--r--	2022-04-21 14:07
euckrprober.pyo	1.28 KB	-rw-r--r--	2022-04-21 14:07
euctwfreq.py	30.88 KB	-rw-r--r--	2017-04-11 20:48
euctwfreq.pyc	53.42 KB	-rw-r--r--	2022-04-21 14:07
euctwfreq.pyo	53.42 KB	-rw-r--r--	2022-04-21 14:07
euctwprober.py	1.71 KB	-rw-r--r--	2017-04-11 17:51
euctwprober.pyc	1.28 KB	-rw-r--r--	2022-04-21 14:07
euctwprober.pyo	1.28 KB	-rw-r--r--	2022-04-21 14:07
gb2312freq.py	20.23 KB	-rw-r--r--	2017-04-11 17:51
gb2312freq.pyc	37.44 KB	-rw-r--r--	2022-04-21 14:07
gb2312freq.pyo	37.44 KB	-rw-r--r--	2022-04-21 14:07
gb2312prober.py	1.71 KB	-rw-r--r--	2017-04-11 17:51
gb2312prober.pyc	1.28 KB	-rw-r--r--	2022-04-21 14:07
gb2312prober.pyo	1.28 KB	-rw-r--r--	2022-04-21 14:07
hebrewprober.py	13.51 KB	-rw-r--r--	2017-06-08 14:21
hebrewprober.pyc	3.6 KB	-rw-r--r--	2022-04-21 14:07
hebrewprober.pyo	3.6 KB	-rw-r--r--	2022-04-21 14:07
jisfreq.py	25.17 KB	-rw-r--r--	2017-04-11 17:51
jisfreq.pyc	43.44 KB	-rw-r--r--	2022-04-21 14:07
jisfreq.pyo	43.44 KB	-rw-r--r--	2022-04-21 14:07
jpcntx.py	19.18 KB	-rw-r--r--	2017-04-11 17:51
jpcntx.pyc	24.57 KB	-rw-r--r--	2022-04-21 14:07
jpcntx.pyo	24.57 KB	-rw-r--r--	2022-04-21 14:07
langbulgarianmodel.py	12.54 KB	-rw-r--r--	2017-06-08 14:32
langbulgarianmodel.pyc	24.37 KB	-rw-r--r--	2022-04-21 14:07
langbulgarianmodel.pyo	24.37 KB	-rw-r--r--	2022-04-21 14:07
langcyrillicmodel.py	17.53 KB	-rw-r--r--	2017-06-08 14:32
langcyrillicmodel.pyc	29.95 KB	-rw-r--r--	2022-04-21 14:07
langcyrillicmodel.pyo	29.95 KB	-rw-r--r--	2022-04-21 14:07
langgreekmodel.py	12.39 KB	-rw-r--r--	2017-06-08 14:32
langgreekmodel.pyc	24.05 KB	-rw-r--r--	2022-04-21 14:07
langgreekmodel.pyo	24.05 KB	-rw-r--r--	2022-04-21 14:07
langhebrewmodel.py	11.08 KB	-rw-r--r--	2017-06-08 14:32
langhebrewmodel.pyc	22.89 KB	-rw-r--r--	2022-04-21 14:07
langhebrewmodel.pyo	22.89 KB	-rw-r--r--	2022-04-21 14:07
langhungarianmodel.py	12.3 KB	-rw-r--r--	2017-06-08 14:32
langhungarianmodel.pyc	24.34 KB	-rw-r--r--	2022-04-21 14:07
langhungarianmodel.pyo	24.34 KB	-rw-r--r--	2022-04-21 14:07
langthaimodel.py	11.03 KB	-rw-r--r--	2017-06-08 14:32
langthaimodel.pyc	22.87 KB	-rw-r--r--	2022-04-21 14:07
langthaimodel.pyo	22.87 KB	-rw-r--r--	2022-04-21 14:07
langturkishmodel.py	10.84 KB	-rw-r--r--	2017-06-08 14:32
langturkishmodel.pyc	22.88 KB	-rw-r--r--	2022-04-21 14:07
langturkishmodel.pyo	22.88 KB	-rw-r--r--	2022-04-21 14:07
latin1prober.py	5.24 KB	-rw-r--r--	2017-06-08 14:21
latin1prober.pyc	3.56 KB	-rw-r--r--	2022-04-21 14:07
latin1prober.pyo	3.56 KB	-rw-r--r--	2022-04-21 14:07
mbcharsetprober.py	3.33 KB	-rw-r--r--	2017-04-11 17:51
mbcharsetprober.pyc	2.64 KB	-rw-r--r--	2022-04-21 14:07
mbcharsetprober.pyo	2.64 KB	-rw-r--r--	2022-04-21 14:07
mbcsgroupprober.py	1.96 KB	-rw-r--r--	2017-04-11 17:51
mbcsgroupprober.pyc	1.27 KB	-rw-r--r--	2022-04-21 14:07
mbcsgroupprober.pyo	1.27 KB	-rw-r--r--	2022-04-21 14:07
mbcssm.py	24.88 KB	-rw-r--r--	2017-04-11 17:51
mbcssm.pyc	18.66 KB	-rw-r--r--	2022-04-21 14:07
mbcssm.pyo	18.66 KB	-rw-r--r--	2022-04-21 14:07
sbcharsetprober.py	5.52 KB	-rw-r--r--	2017-06-08 14:32
sbcharsetprober.pyc	3.49 KB	-rw-r--r--	2022-04-21 14:07
sbcharsetprober.pyo	3.49 KB	-rw-r--r--	2022-04-21 14:07
sbcsgroupprober.py	3.46 KB	-rw-r--r--	2017-06-08 14:32
sbcsgroupprober.pyc	1.85 KB	-rw-r--r--	2022-04-21 14:07
sbcsgroupprober.pyo	1.85 KB	-rw-r--r--	2022-04-21 14:07
sjisprober.py	3.69 KB	-rw-r--r--	2017-04-11 17:51
sjisprober.pyc	2.9 KB	-rw-r--r--	2022-04-21 14:07
sjisprober.pyo	2.9 KB	-rw-r--r--	2022-04-21 14:07
universaldetector.py	12.19 KB	-rw-r--r--	2017-06-08 14:32
universaldetector.pyc	6.88 KB	-rw-r--r--	2022-04-21 14:07
universaldetector.pyo	6.88 KB	-rw-r--r--	2022-04-21 14:07
utf8prober.py	2.7 KB	-rw-r--r--	2017-04-11 17:51
utf8prober.pyc	2.36 KB	-rw-r--r--	2022-04-21 14:07
utf8prober.pyo	2.36 KB	-rw-r--r--	2022-04-21 14:07
version.py	242 B	-rw-r--r--	2017-06-08 14:32
version.pyc	419 B	-rw-r--r--	2022-04-21 14:07
version.pyo	419 B	-rw-r--r--	2022-04-21 14:07

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 .charsetprober import CharSetProber
from .enums import CharacterCategory, ProbingState, SequenceLikelihood

class SingleByteCharSetProber(CharSetProber):
    SAMPLE_SIZE = 64
    SB_ENOUGH_REL_THRESHOLD = 1024  #  0.25 * SAMPLE_SIZE^2
    POSITIVE_SHORTCUT_THRESHOLD = 0.95
    NEGATIVE_SHORTCUT_THRESHOLD = 0.05

def __init__(self, model, reversed=False, name_prober=None):
        super(SingleByteCharSetProber, self).__init__()
        self._model = model
        # TRUE if we need to reverse every pair in the model lookup
        self._reversed = reversed
        # Optional auxiliary prober for name decision
        self._name_prober = name_prober
        self._last_order = None
        self._seq_counters = None
        self._total_seqs = None
        self._total_char = None
        self._freq_char = None
        self.reset()

def reset(self):
        super(SingleByteCharSetProber, self).reset()
        # char order of last character
        self._last_order = 255
        self._seq_counters = [0] * SequenceLikelihood.get_num_categories()
        self._total_seqs = 0
        self._total_char = 0
        # characters that fall in our sampling range
        self._freq_char = 0

@property
    def charset_name(self):
        if self._name_prober:
            return self._name_prober.charset_name
        else:
            return self._model['charset_name']

@property
    def language(self):
        if self._name_prober:
            return self._name_prober.language
        else:
            return self._model.get('language')

def feed(self, byte_str):
        if not self._model['keep_english_letter']:
            byte_str = self.filter_international_words(byte_str)
        if not byte_str:
            return self.state
        char_to_order_map = self._model['char_to_order_map']
        for i, c in enumerate(byte_str):
            # XXX: Order is in range 1-64, so one would think we want 0-63 here,
            #      but that leads to 27 more test failures than before.
            order = char_to_order_map[c]
            # XXX: This was SYMBOL_CAT_ORDER before, with a value of 250, but
            #      CharacterCategory.SYMBOL is actually 253, so we use CONTROL
            #      to make it closer to the original intent. The only difference
            #      is whether or not we count digits and control characters for
            #      _total_char purposes.
            if order < CharacterCategory.CONTROL:
                self._total_char += 1
            if order < self.SAMPLE_SIZE:
                self._freq_char += 1
                if self._last_order < self.SAMPLE_SIZE:
                    self._total_seqs += 1
                    if not self._reversed:
                        i = (self._last_order * self.SAMPLE_SIZE) + order
                        model = self._model['precedence_matrix'][i]
                    else:  # reverse the order of the letters in the lookup
                        i = (order * self.SAMPLE_SIZE) + self._last_order
                        model = self._model['precedence_matrix'][i]
                    self._seq_counters[model] += 1
            self._last_order = order

charset_name = self._model['charset_name']
        if self.state == ProbingState.DETECTING:
            if self._total_seqs > self.SB_ENOUGH_REL_THRESHOLD:
                confidence = self.get_confidence()
                if confidence > self.POSITIVE_SHORTCUT_THRESHOLD:
                    self.logger.debug('%s confidence = %s, we have a winner',
                                      charset_name, confidence)
                    self._state = ProbingState.FOUND_IT
                elif confidence < self.NEGATIVE_SHORTCUT_THRESHOLD:
                    self.logger.debug('%s confidence = %s, below negative '
                                      'shortcut threshhold %s', charset_name,
                                      confidence,
                                      self.NEGATIVE_SHORTCUT_THRESHOLD)
                    self._state = ProbingState.NOT_ME

return self.state

def get_confidence(self):
        r = 0.01
        if self._total_seqs > 0:
            r = ((1.0 * self._seq_counters[SequenceLikelihood.POSITIVE]) /
                 self._total_seqs / self._model['typical_positive_ratio'])
            r = r * self._freq_char / self._total_char
            if r >= 1.0:
                r = 0.99
        return r