OXIESEC PANEL
- Current Dir:
/
/
usr
/
lib
/
python3
/
dist-packages
/
chardet
Server IP: 139.59.38.164
Upload:
Create Dir:
Name
Size
Modified
Perms
📁
..
-
03/17/2025 09:32:20 AM
rwxr-xr-x
📄
__init__.py
1.52 KB
04/12/2017 06:41:25 PM
rw-r--r--
📁
__pycache__
-
10/21/2019 03:49:47 PM
rwxr-xr-x
📄
big5freq.py
30.52 KB
04/11/2017 05:51:33 PM
rw-r--r--
📄
big5prober.py
1.72 KB
04/11/2017 05:51:33 PM
rw-r--r--
📄
chardistribution.py
9.19 KB
04/11/2017 07:52:09 PM
rw-r--r--
📄
charsetgroupprober.py
3.7 KB
04/11/2017 05:51:33 PM
rw-r--r--
📄
charsetprober.py
4.99 KB
06/08/2017 02:21:53 PM
rw-r--r--
📁
cli
-
10/21/2019 03:49:47 PM
rwxr-xr-x
📄
codingstatemachine.py
3.51 KB
04/11/2017 05:51:33 PM
rw-r--r--
📄
compat.py
1.11 KB
06/08/2017 02:32:38 PM
rw-r--r--
📄
cp949prober.py
1.81 KB
04/11/2017 05:51:33 PM
rw-r--r--
📄
enums.py
1.62 KB
04/11/2017 05:51:33 PM
rw-r--r--
📄
escprober.py
3.86 KB
04/11/2017 05:51:33 PM
rw-r--r--
📄
escsm.py
10.26 KB
04/11/2017 05:51:33 PM
rw-r--r--
📄
eucjpprober.py
3.66 KB
04/11/2017 05:51:33 PM
rw-r--r--
📄
euckrfreq.py
13.23 KB
04/11/2017 05:51:33 PM
rw-r--r--
📄
euckrprober.py
1.71 KB
04/11/2017 05:51:33 PM
rw-r--r--
📄
euctwfreq.py
30.88 KB
04/11/2017 08:48:55 PM
rw-r--r--
📄
euctwprober.py
1.71 KB
04/11/2017 05:51:33 PM
rw-r--r--
📄
gb2312freq.py
20.23 KB
04/11/2017 05:51:33 PM
rw-r--r--
📄
gb2312prober.py
1.71 KB
04/11/2017 05:51:33 PM
rw-r--r--
📄
hebrewprober.py
13.51 KB
06/08/2017 02:21:53 PM
rw-r--r--
📄
jisfreq.py
25.17 KB
04/11/2017 05:51:33 PM
rw-r--r--
📄
jpcntx.py
19.18 KB
04/11/2017 05:51:33 PM
rw-r--r--
📄
langbulgarianmodel.py
12.54 KB
06/08/2017 02:32:38 PM
rw-r--r--
📄
langcyrillicmodel.py
17.53 KB
06/08/2017 02:32:38 PM
rw-r--r--
📄
langgreekmodel.py
12.39 KB
06/08/2017 02:32:38 PM
rw-r--r--
📄
langhebrewmodel.py
11.08 KB
06/08/2017 02:32:38 PM
rw-r--r--
📄
langhungarianmodel.py
12.3 KB
06/08/2017 02:32:38 PM
rw-r--r--
📄
langthaimodel.py
11.03 KB
06/08/2017 02:32:38 PM
rw-r--r--
📄
langturkishmodel.py
10.84 KB
06/08/2017 02:32:38 PM
rw-r--r--
📄
latin1prober.py
5.24 KB
06/08/2017 02:21:53 PM
rw-r--r--
📄
mbcharsetprober.py
3.33 KB
04/11/2017 05:51:33 PM
rw-r--r--
📄
mbcsgroupprober.py
1.96 KB
04/11/2017 05:51:33 PM
rw-r--r--
📄
mbcssm.py
24.88 KB
04/11/2017 05:51:33 PM
rw-r--r--
📄
sbcharsetprober.py
5.52 KB
06/08/2017 02:32:38 PM
rw-r--r--
📄
sbcsgroupprober.py
3.46 KB
06/08/2017 02:32:38 PM
rw-r--r--
📄
sjisprober.py
3.69 KB
04/11/2017 05:51:33 PM
rw-r--r--
📄
universaldetector.py
12.19 KB
06/08/2017 02:32:38 PM
rw-r--r--
📄
utf8prober.py
2.7 KB
04/11/2017 05:51:33 PM
rw-r--r--
📄
version.py
242 bytes
06/08/2017 02:32:13 PM
rw-r--r--
Editing: utf8prober.py
Close
######################## 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 .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