OXIESEC PANEL
- Current Dir:
/
/
var
/
www
/
reader
/
hps
/
faces
/
faces
/
lib
/
python3.10
/
site-packages
/
pip
/
_vendor
/
chardet
Server IP: 139.59.38.164
Upload:
Create Dir:
Name
Size
Modified
Perms
📁
..
-
10/26/2024 01:28:40 PM
rwxr-xr-x
📄
__init__.py
3.62 KB
10/26/2024 01:28:31 PM
rw-r--r--
📁
__pycache__
-
10/26/2024 01:29:39 PM
rwxr-xr-x
📄
big5freq.py
30.54 KB
10/26/2024 01:28:30 PM
rw-r--r--
📄
big5prober.py
1.7 KB
10/26/2024 01:28:30 PM
rw-r--r--
📄
chardistribution.py
9.38 KB
10/26/2024 01:28:30 PM
rw-r--r--
📄
charsetgroupprober.py
3.73 KB
10/26/2024 01:28:30 PM
rw-r--r--
📄
charsetprober.py
4.69 KB
10/26/2024 01:28:30 PM
rw-r--r--
📁
cli
-
10/26/2024 01:30:12 PM
rwxr-xr-x
📄
codingstatemachine.py
3.48 KB
10/26/2024 01:28:30 PM
rw-r--r--
📄
cp949prober.py
1.79 KB
10/26/2024 01:28:30 PM
rw-r--r--
📄
enums.py
1.58 KB
10/26/2024 01:28:30 PM
rw-r--r--
📄
escprober.py
3.77 KB
10/26/2024 01:28:30 PM
rw-r--r--
📄
escsm.py
11.74 KB
10/26/2024 01:28:30 PM
rw-r--r--
📄
eucjpprober.py
3.59 KB
10/26/2024 01:28:30 PM
rw-r--r--
📄
euckrfreq.py
13.25 KB
10/26/2024 01:28:30 PM
rw-r--r--
📄
euckrprober.py
1.69 KB
10/26/2024 01:28:30 PM
rw-r--r--
📄
euctwfreq.py
36.05 KB
10/26/2024 01:28:30 PM
rw-r--r--
📄
euctwprober.py
1.69 KB
10/26/2024 01:28:30 PM
rw-r--r--
📄
gb2312freq.py
20.25 KB
10/26/2024 01:28:30 PM
rw-r--r--
📄
gb2312prober.py
1.7 KB
10/26/2024 01:28:30 PM
rw-r--r--
📄
hebrewprober.py
13.59 KB
10/26/2024 01:28:30 PM
rw-r--r--
📄
jisfreq.py
25.19 KB
10/26/2024 01:28:30 PM
rw-r--r--
📄
johabfreq.py
41.5 KB
10/26/2024 01:28:30 PM
rw-r--r--
📄
johabprober.py
1.69 KB
10/26/2024 01:28:30 PM
rw-r--r--
📄
jpcntx.py
26.17 KB
10/26/2024 01:28:30 PM
rw-r--r--
📄
langbulgarianmodel.py
102.11 KB
10/26/2024 01:28:31 PM
rw-r--r--
📄
langgreekmodel.py
96.18 KB
10/26/2024 01:28:31 PM
rw-r--r--
📄
langhebrewmodel.py
95.89 KB
10/26/2024 01:28:31 PM
rw-r--r--
📄
langhungarianmodel.py
98.99 KB
10/26/2024 01:28:31 PM
rw-r--r--
📄
langrussianmodel.py
125.03 KB
10/26/2024 01:28:31 PM
rw-r--r--
📄
langthaimodel.py
100.37 KB
10/26/2024 01:28:31 PM
rw-r--r--
📄
langturkishmodel.py
93.14 KB
10/26/2024 01:28:31 PM
rw-r--r--
📄
latin1prober.py
5.14 KB
10/26/2024 01:28:31 PM
rw-r--r--
📄
mbcharsetprober.py
3.29 KB
10/26/2024 01:28:31 PM
rw-r--r--
📄
mbcsgroupprober.py
2.01 KB
10/26/2024 01:28:31 PM
rw-r--r--
📄
mbcssm.py
29.36 KB
10/26/2024 01:28:31 PM
rw-r--r--
📁
metadata
-
10/26/2024 01:30:12 PM
rwxr-xr-x
📄
sbcharsetprober.py
6.05 KB
10/26/2024 01:28:31 PM
rw-r--r--
📄
sbcsgroupprober.py
4.03 KB
10/26/2024 01:28:31 PM
rw-r--r--
📄
sjisprober.py
3.66 KB
10/26/2024 01:28:31 PM
rw-r--r--
📄
universaldetector.py
12.98 KB
10/26/2024 01:28:31 PM
rw-r--r--
📄
utf1632prober.py
8.09 KB
10/26/2024 01:28:31 PM
rw-r--r--
📄
utf8prober.py
2.65 KB
10/26/2024 01:28:31 PM
rw-r--r--
📄
version.py
242 bytes
10/26/2024 01:28:31 PM
rw-r--r--
Editing: __init__.py
Close
######################## BEGIN LICENSE BLOCK ######################## # 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 .enums import InputState from .universaldetector import UniversalDetector from .version import VERSION, __version__ __all__ = ["UniversalDetector", "detect", "detect_all", "__version__", "VERSION"] def detect(byte_str): """ Detect the encoding of the given byte string. :param byte_str: The byte sequence to examine. :type byte_str: ``bytes`` or ``bytearray`` """ if not isinstance(byte_str, bytearray): if not isinstance(byte_str, bytes): raise TypeError( f"Expected object of type bytes or bytearray, got: {type(byte_str)}" ) byte_str = bytearray(byte_str) detector = UniversalDetector() detector.feed(byte_str) return detector.close() def detect_all(byte_str, ignore_threshold=False): """ Detect all the possible encodings of the given byte string. :param byte_str: The byte sequence to examine. :type byte_str: ``bytes`` or ``bytearray`` :param ignore_threshold: Include encodings that are below ``UniversalDetector.MINIMUM_THRESHOLD`` in results. :type ignore_threshold: ``bool`` """ if not isinstance(byte_str, bytearray): if not isinstance(byte_str, bytes): raise TypeError( f"Expected object of type bytes or bytearray, got: {type(byte_str)}" ) byte_str = bytearray(byte_str) detector = UniversalDetector() detector.feed(byte_str) detector.close() if detector.input_state == InputState.HIGH_BYTE: results = [] probers = [] for prober in detector.charset_probers: if hasattr(prober, "probers"): probers.extend(p for p in prober.probers) else: probers.append(prober) for prober in probers: if ignore_threshold or prober.get_confidence() > detector.MINIMUM_THRESHOLD: charset_name = prober.charset_name or "" lower_charset_name = charset_name.lower() # Use Windows encoding name instead of ISO-8859 if we saw any # extra Windows-specific bytes if lower_charset_name.startswith("iso-8859") and detector.has_win_bytes: charset_name = detector.ISO_WIN_MAP.get( lower_charset_name, charset_name ) results.append( { "encoding": charset_name, "confidence": prober.get_confidence(), "language": prober.language, } ) if len(results) > 0: return sorted(results, key=lambda result: -result["confidence"]) return [detector.result]