Current Path: > > opt > alt > python313 > lib > python3.13 > site-packages > pip > _vendor > chardet
Operation : Linux host59.registrar-servers.com 4.18.0-513.18.1.lve.2.el8.x86_64 #1 SMP Sat Mar 30 15:36:11 UTC 2024 x86_64 Software : Apache Server IP : 198.54.126.42 | Your IP: 216.73.216.8 Domains : 1034 Domain(s) Permission : [ 0755 ]
Name | Type | Size | Last Modified | Actions |
---|---|---|---|---|
__pycache__ | Directory | - | - | |
cli | Directory | - | - | |
metadata | Directory | - | - | |
__init__.py | File | 4797 bytes | December 01 2024 12:47:36. | |
big5freq.py | File | 31274 bytes | December 01 2024 12:47:36. | |
big5prober.py | File | 1763 bytes | December 01 2024 12:47:36. | |
chardistribution.py | File | 10032 bytes | December 01 2024 12:47:36. | |
charsetgroupprober.py | File | 3915 bytes | December 01 2024 12:47:36. | |
charsetprober.py | File | 5420 bytes | December 01 2024 12:47:36. | |
codingstatemachine.py | File | 3732 bytes | December 01 2024 12:47:36. | |
codingstatemachinedict.py | File | 542 bytes | December 01 2024 12:47:36. | |
cp949prober.py | File | 1860 bytes | December 01 2024 12:47:36. | |
enums.py | File | 1683 bytes | December 01 2024 12:47:36. | |
escprober.py | File | 4006 bytes | December 01 2024 12:47:36. | |
escsm.py | File | 12176 bytes | December 01 2024 12:47:36. | |
eucjpprober.py | File | 3934 bytes | December 01 2024 12:47:36. | |
euckrfreq.py | File | 13566 bytes | December 01 2024 12:47:36. | |
euckrprober.py | File | 1753 bytes | December 01 2024 12:47:36. | |
euctwfreq.py | File | 36913 bytes | December 01 2024 12:47:36. | |
euctwprober.py | File | 1753 bytes | December 01 2024 12:47:36. | |
gb2312freq.py | File | 20735 bytes | December 01 2024 12:47:36. | |
gb2312prober.py | File | 1759 bytes | December 01 2024 12:47:36. | |
hebrewprober.py | File | 14537 bytes | December 01 2024 12:47:36. | |
jisfreq.py | File | 25796 bytes | December 01 2024 12:47:36. | |
johabfreq.py | File | 42498 bytes | December 01 2024 12:47:36. | |
johabprober.py | File | 1752 bytes | December 01 2024 12:47:36. | |
jpcntx.py | File | 27055 bytes | December 01 2024 12:47:36. | |
langbulgarianmodel.py | File | 104562 bytes | December 01 2024 12:47:36. | |
langgreekmodel.py | File | 98484 bytes | December 01 2024 12:47:36. | |
langhebrewmodel.py | File | 98196 bytes | December 01 2024 12:47:36. | |
langhungarianmodel.py | File | 101363 bytes | December 01 2024 12:47:36. | |
langrussianmodel.py | File | 128035 bytes | December 01 2024 12:47:36. | |
langthaimodel.py | File | 102774 bytes | December 01 2024 12:47:36. | |
langturkishmodel.py | File | 95372 bytes | December 01 2024 12:47:36. | |
latin1prober.py | File | 5380 bytes | December 01 2024 12:47:36. | |
macromanprober.py | File | 6077 bytes | December 01 2024 12:47:36. | |
mbcharsetprober.py | File | 3715 bytes | December 01 2024 12:47:36. | |
mbcsgroupprober.py | File | 2131 bytes | December 01 2024 12:47:36. | |
mbcssm.py | File | 30391 bytes | December 01 2024 12:47:36. | |
py.typed | File | 0 bytes | December 01 2024 12:47:36. | |
resultdict.py | File | 402 bytes | December 01 2024 12:47:36. | |
sbcharsetprober.py | File | 6400 bytes | December 01 2024 12:47:36. | |
sbcsgroupprober.py | File | 4137 bytes | December 01 2024 12:47:36. | |
sjisprober.py | File | 4007 bytes | December 01 2024 12:47:36. | |
universaldetector.py | File | 14848 bytes | December 01 2024 12:47:36. | |
utf1632prober.py | File | 8505 bytes | December 01 2024 12:47:36. | |
utf8prober.py | File | 2812 bytes | December 01 2024 12:47:36. | |
version.py | File | 244 bytes | December 01 2024 12:47:36. |
######################## 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"]
SILENT KILLER Tool