Gecko [ betsfootball.net ]

Name	Size	Permission	Date
__pycache__	[ DIR ]	drwxr-xr-x	2023-07-12 09:40
cli	[ DIR ]	drwxr-xr-x	2023-07-12 09:40
metadata	[ DIR ]	drwxr-xr-x	2023-07-12 09:40
__init__.py	4.68 KB	-rw-r--r--	2022-12-26 14:42
big5freq.py	30.54 KB	-rw-r--r--	2022-12-26 14:42
big5prober.py	1.72 KB	-rw-r--r--	2022-12-26 14:42
chardistribution.py	9.8 KB	-rw-r--r--	2022-12-26 14:42
charsetgroupprober.py	3.82 KB	-rw-r--r--	2022-12-26 14:42
charsetprober.py	5.29 KB	-rw-r--r--	2022-12-26 14:42
codingstatemachine.py	3.64 KB	-rw-r--r--	2022-12-26 14:42
codingstatemachinedict.py	542 B	-rw-r--r--	2022-12-26 14:42
cp949prober.py	1.82 KB	-rw-r--r--	2022-12-26 14:42
enums.py	1.64 KB	-rw-r--r--	2022-12-26 14:42
escprober.py	3.91 KB	-rw-r--r--	2022-12-26 14:42
escsm.py	11.89 KB	-rw-r--r--	2022-12-26 14:42
eucjpprober.py	3.84 KB	-rw-r--r--	2022-12-26 14:42
euckrfreq.py	13.25 KB	-rw-r--r--	2022-12-26 14:42
euckrprober.py	1.71 KB	-rw-r--r--	2022-12-26 14:42
euctwfreq.py	36.05 KB	-rw-r--r--	2022-12-26 14:42
euctwprober.py	1.71 KB	-rw-r--r--	2022-12-26 14:42
gb2312freq.py	20.25 KB	-rw-r--r--	2022-12-26 14:42
gb2312prober.py	1.72 KB	-rw-r--r--	2022-12-26 14:42
hebrewprober.py	14.2 KB	-rw-r--r--	2022-12-26 14:42
jisfreq.py	25.19 KB	-rw-r--r--	2022-12-26 14:42
johabfreq.py	41.5 KB	-rw-r--r--	2022-12-26 14:42
johabprober.py	1.71 KB	-rw-r--r--	2022-12-26 14:42
jpcntx.py	26.42 KB	-rw-r--r--	2022-12-26 14:42
langbulgarianmodel.py	102.1 KB	-rw-r--r--	2022-12-26 14:42
langgreekmodel.py	96.16 KB	-rw-r--r--	2022-12-26 14:42
langhebrewmodel.py	95.88 KB	-rw-r--r--	2022-12-26 14:42
langhungarianmodel.py	98.98 KB	-rw-r--r--	2022-12-26 14:42
langrussianmodel.py	125.02 KB	-rw-r--r--	2022-12-26 14:42
langthaimodel.py	100.35 KB	-rw-r--r--	2022-12-26 14:42
langturkishmodel.py	93.13 KB	-rw-r--r--	2022-12-26 14:42
latin1prober.py	5.25 KB	-rw-r--r--	2022-12-26 14:42
macromanprober.py	5.93 KB	-rw-r--r--	2022-12-26 14:42
mbcharsetprober.py	3.63 KB	-rw-r--r--	2022-12-26 14:42
mbcsgroupprober.py	2.08 KB	-rw-r--r--	2022-12-26 14:42
mbcssm.py	29.68 KB	-rw-r--r--	2022-12-26 14:42
py.typed	0 B	-rw-r--r--	2022-12-26 14:42
resultdict.py	402 B	-rw-r--r--	2022-12-26 14:42
sbcharsetprober.py	6.25 KB	-rw-r--r--	2022-12-26 14:42
sbcsgroupprober.py	4.04 KB	-rw-r--r--	2022-12-26 14:42
sjisprober.py	3.91 KB	-rw-r--r--	2022-12-26 14:42
universaldetector.py	14.5 KB	-rw-r--r--	2022-12-26 14:42
utf1632prober.py	8.31 KB	-rw-r--r--	2022-12-26 14:42
utf8prober.py	2.75 KB	-rw-r--r--	2022-12-26 14:42
version.py	244 B	-rw-r--r--	2022-12-26 14:42

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 .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()