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: sbcsgroupprober.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 .charsetgroupprober import CharSetGroupProber
from .hebrewprober import HebrewProber
from .langbulgarianmodel import ISO_8859_5_BULGARIAN_MODEL, WINDOWS_1251_BULGARIAN_MODEL
from .langgreekmodel import ISO_8859_7_GREEK_MODEL, WINDOWS_1253_GREEK_MODEL
from .langhebrewmodel import WINDOWS_1255_HEBREW_MODEL

# from .langhungarianmodel import (ISO_8859_2_HUNGARIAN_MODEL,
#                                  WINDOWS_1250_HUNGARIAN_MODEL)
from .langrussianmodel import (
    IBM855_RUSSIAN_MODEL,
    IBM866_RUSSIAN_MODEL,
    ISO_8859_5_RUSSIAN_MODEL,
    KOI8_R_RUSSIAN_MODEL,
    MACCYRILLIC_RUSSIAN_MODEL,
    WINDOWS_1251_RUSSIAN_MODEL,
)
from .langthaimodel import TIS_620_THAI_MODEL
from .langturkishmodel import ISO_8859_9_TURKISH_MODEL
from .sbcharsetprober import SingleByteCharSetProber

class SBCSGroupProber(CharSetGroupProber):
    def __init__(self) -> None:
        super().__init__()
        hebrew_prober = HebrewProber()
        logical_hebrew_prober = SingleByteCharSetProber(
            WINDOWS_1255_HEBREW_MODEL, is_reversed=False, name_prober=hebrew_prober
        )
        # TODO: See if using ISO-8859-8 Hebrew model works better here, since
        #       it's actually the visual one
        visual_hebrew_prober = SingleByteCharSetProber(
            WINDOWS_1255_HEBREW_MODEL, is_reversed=True, name_prober=hebrew_prober
        )
        hebrew_prober.set_model_probers(logical_hebrew_prober, visual_hebrew_prober)
        # TODO: ORDER MATTERS HERE. I changed the order vs what was in master
        #       and several tests failed that did not before. Some thought
        #       should be put into the ordering, and we should consider making
        #       order not matter here, because that is very counter-intuitive.
        self.probers = [
            SingleByteCharSetProber(WINDOWS_1251_RUSSIAN_MODEL),
            SingleByteCharSetProber(KOI8_R_RUSSIAN_MODEL),
            SingleByteCharSetProber(ISO_8859_5_RUSSIAN_MODEL),
            SingleByteCharSetProber(MACCYRILLIC_RUSSIAN_MODEL),
            SingleByteCharSetProber(IBM866_RUSSIAN_MODEL),
            SingleByteCharSetProber(IBM855_RUSSIAN_MODEL),
            SingleByteCharSetProber(ISO_8859_7_GREEK_MODEL),
            SingleByteCharSetProber(WINDOWS_1253_GREEK_MODEL),
            SingleByteCharSetProber(ISO_8859_5_BULGARIAN_MODEL),
            SingleByteCharSetProber(WINDOWS_1251_BULGARIAN_MODEL),
            # TODO: Restore Hungarian encodings (iso-8859-2 and windows-1250)
            #       after we retrain model.
            # SingleByteCharSetProber(ISO_8859_2_HUNGARIAN_MODEL),
            # SingleByteCharSetProber(WINDOWS_1250_HUNGARIAN_MODEL),
            SingleByteCharSetProber(TIS_620_THAI_MODEL),
            SingleByteCharSetProber(ISO_8859_9_TURKISH_MODEL),
            hebrew_prober,
            logical_hebrew_prober,
            visual_hebrew_prober,
        ]
        self.reset()

X7ROOT File Manager

Editing: sbcsgroupprober.py

Upload File

Create Folder