ÿØÿà JFIF ÿÛ „ ( %"1"%)+...383,7(-.-
![]() Server : Apache/2.4.6 (CentOS) OpenSSL/1.0.2k-fips PHP/7.4.20 System : Linux st2.domain.com 3.10.0-1127.10.1.el7.x86_64 #1 SMP Wed Jun 3 14:28:03 UTC 2020 x86_64 User : apache ( 48) PHP Version : 7.4.20 Disable Function : NONE Directory : /proc/self/root/usr/share/mysqlsh/oci_sdk/oci/_vendor/chardet/ |
# coding: utf-8 # Modified Work: Copyright (c) 2018, 2020, Oracle and/or its affiliates. All rights reserved. # Original Work: Copyright (c) 2018 Character Encoding Detector contributors. https://github.com/chardet from .charsetprober import CharSetProber from .enums import ProbingState, MachineState from .codingstatemachine import CodingStateMachine from .mbcssm import UTF8_SM_MODEL class UTF8Prober(CharSetProber): ONE_CHAR_PROB = 0.5 def __init__(self): super(UTF8Prober, self).__init__() self.coding_sm = CodingStateMachine(UTF8_SM_MODEL) self._num_mb_chars = None self.reset() def reset(self): super(UTF8Prober, self).reset() self.coding_sm.reset() self._num_mb_chars = 0 @property def charset_name(self): return "utf-8" @property def language(self): return "" def feed(self, byte_str): for c in byte_str: coding_state = self.coding_sm.next_state(c) if coding_state == MachineState.ERROR: self._state = ProbingState.NOT_ME break elif coding_state == MachineState.ITS_ME: self._state = ProbingState.FOUND_IT break elif coding_state == MachineState.START: if self.coding_sm.get_current_charlen() >= 2: self._num_mb_chars += 1 if self.state == ProbingState.DETECTING: if self.get_confidence() > self.SHORTCUT_THRESHOLD: self._state = ProbingState.FOUND_IT return self.state def get_confidence(self): unlike = 0.99 if self._num_mb_chars < 6: unlike *= self.ONE_CHAR_PROB ** self._num_mb_chars return 1.0 - unlike else: return unlike