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.org code.
#
# The Initial Developer of the Original Code is
# Netscape Communications Corporation.
# Portions created by the Initial Developer are Copyright (C) 1998
# the Initial Developer. All Rights Reserved.
#
# Contributor(s):
#   Mark Pilgrim - port to Python
#
# 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 Optional, Union

from .charsetprober import CharSetProber
from .codingstatemachine import CodingStateMachine
from .enums import LanguageFilter, MachineState, ProbingState
from .escsm import (
    HZ_SM_MODEL,
    ISO2022CN_SM_MODEL,
    ISO2022JP_SM_MODEL,
    ISO2022KR_SM_MODEL,
)

class EscCharSetProber(CharSetProber):
    """
    This CharSetProber uses a "code scheme" approach for detecting encodings,
    whereby easily recognizable escape or shift sequences are relied on to
    identify these encodings.
    """

def __init__(self, lang_filter: LanguageFilter = LanguageFilter.NONE) -> None:
        super().__init__(lang_filter=lang_filter)
        self.coding_sm = []
        if self.lang_filter & LanguageFilter.CHINESE_SIMPLIFIED:
            self.coding_sm.append(CodingStateMachine(HZ_SM_MODEL))
            self.coding_sm.append(CodingStateMachine(ISO2022CN_SM_MODEL))
        if self.lang_filter & LanguageFilter.JAPANESE:
            self.coding_sm.append(CodingStateMachine(ISO2022JP_SM_MODEL))
        if self.lang_filter & LanguageFilter.KOREAN:
            self.coding_sm.append(CodingStateMachine(ISO2022KR_SM_MODEL))
        self.active_sm_count = 0
        self._detected_charset: Optional[str] = None
        self._detected_language: Optional[str] = None
        self._state = ProbingState.DETECTING
        self.reset()

def reset(self) -> None:
        super().reset()
        for coding_sm in self.coding_sm:
            coding_sm.active = True
            coding_sm.reset()
        self.active_sm_count = len(self.coding_sm)
        self._detected_charset = None
        self._detected_language = None

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

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

def get_confidence(self) -> float:
        return 0.99 if self._detected_charset else 0.00

def feed(self, byte_str: Union[bytes, bytearray]) -> ProbingState:
        for c in byte_str:
            for coding_sm in self.coding_sm:
                if not coding_sm.active:
                    continue
                coding_state = coding_sm.next_state(c)
                if coding_state == MachineState.ERROR:
                    coding_sm.active = False
                    self.active_sm_count -= 1
                    if self.active_sm_count <= 0:
                        self._state = ProbingState.NOT_ME
                        return self.state
                elif coding_state == MachineState.ITS_ME:
                    self._state = ProbingState.FOUND_IT
                    self._detected_charset = coding_sm.get_coding_state_machine()
                    self._detected_language = coding_sm.language
                    return self.state

return self.state