Current Path: > > opt > cloudlinux > venv > lib64 > python3.11 > > site-packages > chardet
Operation : Linux premium131.web-hosting.com 4.18.0-553.44.1.lve.el8.x86_64 #1 SMP Thu Mar 13 14:29:12 UTC 2025 x86_64 Software : Apache Server IP : 162.0.232.56 | Your IP: 216.73.216.111 Domains : 1034 Domain(s) Permission : [ 0755 ]
Name | Type | Size | Last Modified | Actions |
---|---|---|---|---|
__pycache__ | Directory | - | - | |
cli | Directory | - | - | |
metadata | Directory | - | - | |
__init__.py | File | 4797 bytes | April 17 2025 13:10:59. | |
__main__.py | File | 123 bytes | April 17 2025 13:10:59. | |
big5freq.py | File | 31274 bytes | April 17 2025 13:10:59. | |
big5prober.py | File | 1763 bytes | April 17 2025 13:10:59. | |
chardistribution.py | File | 10032 bytes | April 17 2025 13:10:59. | |
charsetgroupprober.py | File | 3915 bytes | April 17 2025 13:10:59. | |
charsetprober.py | File | 5420 bytes | April 17 2025 13:10:59. | |
codingstatemachine.py | File | 3732 bytes | April 17 2025 13:10:59. | |
codingstatemachinedict.py | File | 542 bytes | April 17 2025 13:10:59. | |
cp949prober.py | File | 1860 bytes | April 17 2025 13:10:59. | |
enums.py | File | 1683 bytes | April 17 2025 13:10:59. | |
escprober.py | File | 4006 bytes | April 17 2025 13:10:59. | |
escsm.py | File | 12176 bytes | April 17 2025 13:10:59. | |
eucjpprober.py | File | 3934 bytes | April 17 2025 13:10:59. | |
euckrfreq.py | File | 13566 bytes | April 17 2025 13:10:59. | |
euckrprober.py | File | 1753 bytes | April 17 2025 13:10:59. | |
euctwfreq.py | File | 36913 bytes | April 17 2025 13:10:59. | |
euctwprober.py | File | 1753 bytes | April 17 2025 13:10:59. | |
gb2312freq.py | File | 20735 bytes | April 17 2025 13:10:59. | |
gb2312prober.py | File | 1759 bytes | April 17 2025 13:10:59. | |
hebrewprober.py | File | 14537 bytes | April 17 2025 13:10:59. | |
jisfreq.py | File | 25796 bytes | April 17 2025 13:10:59. | |
johabfreq.py | File | 42498 bytes | April 17 2025 13:10:59. | |
johabprober.py | File | 1752 bytes | April 17 2025 13:10:59. | |
jpcntx.py | File | 27055 bytes | April 17 2025 13:10:59. | |
langbulgarianmodel.py | File | 104550 bytes | April 17 2025 13:10:59. | |
langgreekmodel.py | File | 98472 bytes | April 17 2025 13:10:59. | |
langhebrewmodel.py | File | 98184 bytes | April 17 2025 13:10:59. | |
langhungarianmodel.py | File | 101351 bytes | April 17 2025 13:10:59. | |
langrussianmodel.py | File | 128023 bytes | April 17 2025 13:10:59. | |
langthaimodel.py | File | 102762 bytes | April 17 2025 13:10:59. | |
langturkishmodel.py | File | 95360 bytes | April 17 2025 13:10:59. | |
latin1prober.py | File | 5380 bytes | April 17 2025 13:10:59. | |
macromanprober.py | File | 6077 bytes | April 17 2025 13:10:59. | |
mbcharsetprober.py | File | 3715 bytes | April 17 2025 13:10:59. | |
mbcsgroupprober.py | File | 2131 bytes | April 17 2025 13:10:59. | |
mbcssm.py | File | 30391 bytes | April 17 2025 13:10:59. | |
py.typed | File | 0 bytes | April 17 2025 13:10:59. | |
resultdict.py | File | 402 bytes | April 17 2025 13:10:59. | |
sbcharsetprober.py | File | 6400 bytes | April 17 2025 13:10:59. | |
sbcsgroupprober.py | File | 4137 bytes | April 17 2025 13:10:59. | |
sjisprober.py | File | 4007 bytes | April 17 2025 13:10:59. | |
universaldetector.py | File | 14848 bytes | April 17 2025 13:10:59. | |
utf1632prober.py | File | 8505 bytes | April 17 2025 13:10:59. | |
utf8prober.py | File | 2812 bytes | April 17 2025 13:10:59. | |
version.py | File | 244 bytes | April 17 2025 13:10:59. |
######################## 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 Union from .chardistribution import SJISDistributionAnalysis from .codingstatemachine import CodingStateMachine from .enums import MachineState, ProbingState from .jpcntx import SJISContextAnalysis from .mbcharsetprober import MultiByteCharSetProber from .mbcssm import SJIS_SM_MODEL class SJISProber(MultiByteCharSetProber): def __init__(self) -> None: super().__init__() self.coding_sm = CodingStateMachine(SJIS_SM_MODEL) self.distribution_analyzer = SJISDistributionAnalysis() self.context_analyzer = SJISContextAnalysis() self.reset() def reset(self) -> None: super().reset() self.context_analyzer.reset() @property def charset_name(self) -> str: return self.context_analyzer.charset_name @property def language(self) -> str: return "Japanese" def feed(self, byte_str: Union[bytes, bytearray]) -> ProbingState: assert self.coding_sm is not None assert self.distribution_analyzer is not None for i, byte in enumerate(byte_str): coding_state = self.coding_sm.next_state(byte) if coding_state == MachineState.ERROR: self.logger.debug( "%s %s prober hit error at byte %s", self.charset_name, self.language, i, ) self._state = ProbingState.NOT_ME break if coding_state == MachineState.ITS_ME: self._state = ProbingState.FOUND_IT break if coding_state == MachineState.START: char_len = self.coding_sm.get_current_charlen() if i == 0: self._last_char[1] = byte self.context_analyzer.feed( self._last_char[2 - char_len :], char_len ) self.distribution_analyzer.feed(self._last_char, char_len) else: self.context_analyzer.feed( byte_str[i + 1 - char_len : i + 3 - char_len], char_len ) self.distribution_analyzer.feed(byte_str[i - 1 : i + 1], char_len) self._last_char[0] = byte_str[-1] if self.state == ProbingState.DETECTING: if self.context_analyzer.got_enough_data() and ( self.get_confidence() > self.SHORTCUT_THRESHOLD ): self._state = ProbingState.FOUND_IT return self.state def get_confidence(self) -> float: assert self.distribution_analyzer is not None context_conf = self.context_analyzer.get_confidence() distrib_conf = self.distribution_analyzer.get_confidence() return max(context_conf, distrib_conf)
SILENT KILLER Tool