File Manager

X7ROOT File Manager

Current Path: /opt/alt/python313/lib/python3.13/site-packages/pip/_vendor/chardet

opt / alt / python313 / lib / python3.13 / site-packages / pip / _vendor / chardet /

ðŸ“ ..
ðŸ“„ __init__.py(4.68 KB)
ðŸ“ __pycache__
ðŸ“„ big5freq.py(30.54 KB)
ðŸ“„ big5prober.py(1.72 KB)
ðŸ“„ chardistribution.py(9.8 KB)
ðŸ“„ charsetgroupprober.py(3.82 KB)
ðŸ“„ charsetprober.py(5.29 KB)
ðŸ“ cli
ðŸ“„ codingstatemachine.py(3.64 KB)
ðŸ“„ codingstatemachinedict.py(542 B)
ðŸ“„ cp949prober.py(1.82 KB)
ðŸ“„ enums.py(1.64 KB)
ðŸ“„ escprober.py(3.91 KB)
ðŸ“„ escsm.py(11.89 KB)
ðŸ“„ eucjpprober.py(3.84 KB)
ðŸ“„ euckrfreq.py(13.25 KB)
ðŸ“„ euckrprober.py(1.71 KB)
ðŸ“„ euctwfreq.py(36.05 KB)
ðŸ“„ euctwprober.py(1.71 KB)
ðŸ“„ gb2312freq.py(20.25 KB)
ðŸ“„ gb2312prober.py(1.72 KB)
ðŸ“„ hebrewprober.py(14.2 KB)
ðŸ“„ jisfreq.py(25.19 KB)
ðŸ“„ johabfreq.py(41.5 KB)
ðŸ“„ johabprober.py(1.71 KB)
ðŸ“„ jpcntx.py(26.42 KB)
ðŸ“„ langbulgarianmodel.py(102.11 KB)
ðŸ“„ langgreekmodel.py(96.18 KB)
ðŸ“„ langhebrewmodel.py(95.89 KB)
ðŸ“„ langhungarianmodel.py(98.99 KB)
ðŸ“„ langrussianmodel.py(125.03 KB)
ðŸ“„ langthaimodel.py(100.37 KB)
ðŸ“„ langturkishmodel.py(93.14 KB)
ðŸ“„ latin1prober.py(5.25 KB)
ðŸ“„ macromanprober.py(5.93 KB)
ðŸ“„ mbcharsetprober.py(3.63 KB)
ðŸ“„ mbcsgroupprober.py(2.08 KB)
ðŸ“„ mbcssm.py(29.68 KB)
ðŸ“ metadata
ðŸ“„ py.typed(0 B)
ðŸ“„ resultdict.py(402 B)
ðŸ“„ sbcharsetprober.py(6.25 KB)
ðŸ“„ sbcsgroupprober.py(4.04 KB)
ðŸ“„ sjisprober.py(3.91 KB)
ðŸ“„ universaldetector.py(14.5 KB)
ðŸ“„ utf1632prober.py(8.31 KB)
ðŸ“„ utf8prober.py(2.75 KB)
ðŸ“„ version.py(244 B)

Editing: sbcharsetprober.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
#
# 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 typing import Dict, List, NamedTuple, Optional, Union

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

class SingleByteCharSetModel(NamedTuple):
    charset_name: str
    language: str
    char_to_order_map: Dict[int, int]
    language_model: Dict[int, Dict[int, int]]
    typical_positive_ratio: float
    keep_ascii_letters: bool
    alphabet: str

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: SingleByteCharSetModel,
        is_reversed: bool = False,
        name_prober: Optional[CharSetProber] = None,
    ) -> None:
        super().__init__()
        self._model = model
        # TRUE if we need to reverse every pair in the model lookup
        self._reversed = is_reversed
        # Optional auxiliary prober for name decision
        self._name_prober = name_prober
        self._last_order = 255
        self._seq_counters: List[int] = []
        self._total_seqs = 0
        self._total_char = 0
        self._control_char = 0
        self._freq_char = 0
        self.reset()

def reset(self) -> None:
        super().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
        self._control_char = 0
        # characters that fall in our sampling range
        self._freq_char = 0

@property
    def charset_name(self) -> Optional[str]:
        if self._name_prober:
            return self._name_prober.charset_name
        return self._model.charset_name

@property
    def language(self) -> Optional[str]:
        if self._name_prober:
            return self._name_prober.language
        return self._model.language

def feed(self, byte_str: Union[bytes, bytearray]) -> ProbingState:
        # TODO: Make filter_international_words keep things in self.alphabet
        if not self._model.keep_ascii_letters:
            byte_str = self.filter_international_words(byte_str)
        else:
            byte_str = self.remove_xml_tags(byte_str)
        if not byte_str:
            return self.state
        char_to_order_map = self._model.char_to_order_map
        language_model = self._model.language_model
        for char in byte_str:
            order = char_to_order_map.get(char, CharacterCategory.UNDEFINED)
            # 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:
                        lm_cat = language_model[self._last_order][order]
                    else:
                        lm_cat = language_model[order][self._last_order]
                    self._seq_counters[lm_cat] += 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 threshold %s",
                        charset_name,
                        confidence,
                        self.NEGATIVE_SHORTCUT_THRESHOLD,
                    )
                    self._state = ProbingState.NOT_ME

return self.state

def get_confidence(self) -> float:
        r = 0.01
        if self._total_seqs > 0:
            r = (
                (
                    self._seq_counters[SequenceLikelihood.POSITIVE]
                    + 0.25 * self._seq_counters[SequenceLikelihood.LIKELY]
                )
                / self._total_seqs
                / self._model.typical_positive_ratio
            )
            # The more control characters (proportionnaly to the size
            # of the text), the less confident we become in the current
            # charset.
            r = r * (self._total_char - self._control_char) / self._total_char
            r = r * self._freq_char / self._total_char
            if r >= 1.0:
                r = 0.99
        return r

X7ROOT File Manager

Editing: sbcharsetprober.py

Upload File

Create Folder