FM / chardet

/snap/core24/1587/usr/lib/python3/dist-packages/chardet/

/snap/core24/1587/usr/lib/python3/dist-packages/chardet

Name	Size	Mode	Actions
cli/	-	0755	rm
metadata/	-	0755	rm
__pycache__/	-	0755	rm
big5freq.py	31274	0644	edit dl rm
big5prober.py	1763	0644	edit dl rm
chardistribution.py	10032	0644	edit dl rm
charsetgroupprober.py	3915	0644	edit dl rm
charsetprober.py	5420	0644	edit dl rm
codingstatemachine.py	3732	0644	edit dl rm
codingstatemachinedict.py	542	0644	edit dl rm
cp949prober.py	1860	0644	edit dl rm
enums.py	1683	0644	edit dl rm
escprober.py	4006	0644	edit dl rm
escsm.py	12176	0644	edit dl rm
eucjpprober.py	3934	0644	edit dl rm
euckrfreq.py	13566	0644	edit dl rm
euckrprober.py	1753	0644	edit dl rm
euctwfreq.py	36913	0644	edit dl rm
euctwprober.py	1753	0644	edit dl rm
gb2312freq.py	20735	0644	edit dl rm
gb2312prober.py	1759	0644	edit dl rm
hebrewprober.py	14537	0644	edit dl rm
jisfreq.py	25796	0644	edit dl rm
johabfreq.py	42498	0644	edit dl rm
johabprober.py	1752	0644	edit dl rm
jpcntx.py	27055	0644	edit dl rm
langbulgarianmodel.py	104550	0644	edit dl rm
langgreekmodel.py	98472	0644	edit dl rm
langhebrewmodel.py	98184	0644	edit dl rm
langhungarianmodel.py	101351	0644	edit dl rm
langrussianmodel.py	128023	0644	edit dl rm
langthaimodel.py	102762	0644	edit dl rm
langturkishmodel.py	95360	0644	edit dl rm
latin1prober.py	5380	0644	edit dl rm
macromanprober.py	6077	0644	edit dl rm
mbcharsetprober.py	3715	0644	edit dl rm
mbcsgroupprober.py	2131	0644	edit dl rm
mbcssm.py	30391	0644	edit dl rm
py.typed	0	0644	edit dl rm
resultdict.py	402	0644	edit dl rm
sbcharsetprober.py	6400	0644	edit dl rm
sbcsgroupprober.py	4137	0644	edit dl rm
sjisprober.py	4007	0644	edit dl rm
universaldetector.py	14848	0644	edit dl rm
utf8prober.py	2812	0644	edit dl rm
utf1632prober.py	8505	0644	edit dl rm
version.py	244	0644	edit dl rm
__init__.py	4797	0644	edit dl rm
__main__.py	123	0644	edit dl rm

Edit: /snap/core24/1587/usr/lib/python3/dist-packages/chardet/codingstatemachine.py (3732B)

######################## 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 #########################

import logging

from .codingstatemachinedict import CodingStateMachineDict
from .enums import MachineState

class CodingStateMachine:
    """
    A state machine to verify a byte sequence for a particular encoding. For
    each byte the detector receives, it will feed that byte to every active
    state machine available, one byte at a time. The state machine changes its
    state based on its previous state and the byte it receives. There are 3
    states in a state machine that are of interest to an auto-detector:

START state: This is the state to start with, or a legal byte sequence
                 (i.e. a valid code point) for character has been identified.

ME state:  This indicates that the state machine identified a byte sequence
               that is specific to the charset it is designed for and that
               there is no other possible encoding which can contain this byte
               sequence. This will to lead to an immediate positive answer for
               the detector.

ERROR state: This indicates the state machine identified an illegal byte
                 sequence for that encoding. This will lead to an immediate
                 negative answer for this encoding. Detector will exclude this
                 encoding from consideration from here on.
    """

def __init__(self, sm: CodingStateMachineDict) -> None:
        self._model = sm
        self._curr_byte_pos = 0
        self._curr_char_len = 0
        self._curr_state = MachineState.START
        self.active = True
        self.logger = logging.getLogger(__name__)
        self.reset()

def reset(self) -> None:
        self._curr_state = MachineState.START

def next_state(self, c: int) -> int:
        # for each byte we get its class
        # if it is first byte, we also get byte length
        byte_class = self._model["class_table"][c]
        if self._curr_state == MachineState.START:
            self._curr_byte_pos = 0
            self._curr_char_len = self._model["char_len_table"][byte_class]
        # from byte's class and state_table, we get its next state
        curr_state = self._curr_state * self._model["class_factor"] + byte_class
        self._curr_state = self._model["state_table"][curr_state]
        self._curr_byte_pos += 1
        return self._curr_state

def get_current_charlen(self) -> int:
        return self._curr_char_len

def get_coding_state_machine(self) -> str:
        return self._model["name"]

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

cmd: