Current Path: > > opt > alt > python37 > lib > > python3.7 > 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 | - | - | |
__init__.py | File | 1559 bytes | June 08 2017 14:29:16. | |
big5freq.py | File | 31254 bytes | June 08 2017 14:29:16. | |
big5prober.py | File | 1757 bytes | June 08 2017 14:29:16. | |
chardistribution.py | File | 9411 bytes | June 08 2017 14:29:16. | |
charsetgroupprober.py | File | 3787 bytes | June 08 2017 14:29:16. | |
charsetprober.py | File | 5110 bytes | June 08 2017 14:29:16. | |
codingstatemachine.py | File | 3590 bytes | June 08 2017 14:29:16. | |
compat.py | File | 1134 bytes | June 08 2017 14:29:16. | |
cp949prober.py | File | 1855 bytes | June 08 2017 14:29:16. | |
enums.py | File | 1661 bytes | June 08 2017 14:29:16. | |
escprober.py | File | 3950 bytes | June 08 2017 14:29:16. | |
escsm.py | File | 10510 bytes | June 08 2017 14:29:16. | |
eucjpprober.py | File | 3749 bytes | June 08 2017 14:29:16. | |
euckrfreq.py | File | 13546 bytes | June 08 2017 14:29:16. | |
euckrprober.py | File | 1748 bytes | June 08 2017 14:29:16. | |
euctwfreq.py | File | 31621 bytes | June 08 2017 14:29:16. | |
euctwprober.py | File | 1747 bytes | June 08 2017 14:29:16. | |
gb2312freq.py | File | 20715 bytes | June 08 2017 14:29:16. | |
gb2312prober.py | File | 1754 bytes | June 08 2017 14:29:16. | |
hebrewprober.py | File | 13838 bytes | June 08 2017 14:29:16. | |
jisfreq.py | File | 25777 bytes | June 08 2017 14:29:16. | |
jpcntx.py | File | 19643 bytes | June 08 2017 14:29:16. | |
langbulgarianmodel.py | File | 12839 bytes | June 08 2017 14:29:16. | |
langcyrillicmodel.py | File | 17948 bytes | June 08 2017 14:29:16. | |
langgreekmodel.py | File | 12688 bytes | June 08 2017 14:29:16. | |
langhebrewmodel.py | File | 11345 bytes | June 08 2017 14:29:16. | |
langhungarianmodel.py | File | 12592 bytes | June 08 2017 14:29:16. | |
langthaimodel.py | File | 11290 bytes | June 08 2017 14:29:16. | |
langturkishmodel.py | File | 11102 bytes | June 08 2017 14:29:16. | |
latin1prober.py | File | 5370 bytes | June 08 2017 14:29:16. | |
mbcharsetprober.py | File | 3413 bytes | June 08 2017 14:29:16. | |
mbcsgroupprober.py | File | 2012 bytes | June 08 2017 14:29:16. | |
mbcssm.py | File | 25481 bytes | June 08 2017 14:29:16. | |
sbcharsetprober.py | File | 5657 bytes | June 08 2017 14:29:16. | |
sbcsgroupprober.py | File | 3546 bytes | June 08 2017 14:29:16. | |
sjisprober.py | File | 3774 bytes | June 08 2017 14:29:16. | |
universaldetector.py | File | 12485 bytes | June 08 2017 14:29:16. | |
utf8prober.py | File | 2766 bytes | June 08 2017 14:29:16. | |
version.py | File | 242 bytes | June 08 2017 14:29:16. |
######################## 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 .charsetprober import CharSetProber from .codingstatemachine import CodingStateMachine from .enums import LanguageFilter, ProbingState, MachineState 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=None): super(EscCharSetProber, self).__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 = None self._detected_charset = None self._detected_language = None self._state = None self.reset() def reset(self): super(EscCharSetProber, self).reset() for coding_sm in self.coding_sm: if not coding_sm: continue 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): return self._detected_charset @property def language(self): return self._detected_language def get_confidence(self): if self._detected_charset: return 0.99 else: return 0.00 def feed(self, byte_str): for c in byte_str: for coding_sm in self.coding_sm: if not coding_sm or 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
SILENT KILLER Tool