######################## 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 .universaldetector import UniversalDetector from .enums import InputState 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('Expected object of type bytes or bytearray, got: ' '{}'.format(type(byte_str))) else: byte_str = bytearray(byte_str) detector = UniversalDetector() detector.feed(byte_str) return detector.close() def detect_all(byte_str): """ Detect all the possible encodings 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('Expected object of type bytes or bytearray, got: ' '{}'.format(type(byte_str))) else: byte_str = bytearray(byte_str) detector = UniversalDetector() detector.feed(byte_str) detector.close() if detector._input_state == InputState.HIGH_BYTE: results = [] for prober in detector._charset_probers: if prober.get_confidence() > detector.MINIMUM_THRESHOLD: charset_name = prober.charset_name lower_charset_name = prober.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'): if 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]
Name | Type | Size | Permission | Actions |
---|---|---|---|---|
__pycache__ | Folder | 0755 |
|
|
cli | Folder | 0755 |
|
|
metadata | Folder | 0755 |
|
|
__init__.py | File | 3.19 KB | 0644 |
|
big5freq.py | File | 30.52 KB | 0644 |
|
big5prober.py | File | 1.72 KB | 0644 |
|
chardistribution.py | File | 9.19 KB | 0644 |
|
charsetgroupprober.py | File | 3.75 KB | 0644 |
|
charsetprober.py | File | 4.99 KB | 0644 |
|
codingstatemachine.py | File | 3.51 KB | 0644 |
|
compat.py | File | 1.17 KB | 0644 |
|
cp949prober.py | File | 1.81 KB | 0644 |
|
enums.py | File | 1.62 KB | 0644 |
|
escprober.py | File | 3.86 KB | 0644 |
|
escsm.py | File | 10.26 KB | 0644 |
|
eucjpprober.py | File | 3.66 KB | 0644 |
|
euckrfreq.py | File | 13.23 KB | 0644 |
|
euckrprober.py | File | 1.71 KB | 0644 |
|
euctwfreq.py | File | 30.88 KB | 0644 |
|
euctwprober.py | File | 1.71 KB | 0644 |
|
gb2312freq.py | File | 20.23 KB | 0644 |
|
gb2312prober.py | File | 1.71 KB | 0644 |
|
hebrewprober.py | File | 13.51 KB | 0644 |
|
jisfreq.py | File | 25.17 KB | 0644 |
|
jpcntx.py | File | 19.18 KB | 0644 |
|
langbulgarianmodel.py | File | 103.21 KB | 0644 |
|
langgreekmodel.py | File | 97.23 KB | 0644 |
|
langhebrewmodel.py | File | 96.45 KB | 0644 |
|
langhungarianmodel.py | File | 100.08 KB | 0644 |
|
langrussianmodel.py | File | 128.09 KB | 0644 |
|
langthaimodel.py | File | 100.88 KB | 0644 |
|
langturkishmodel.py | File | 93.69 KB | 0644 |
|
latin1prober.py | File | 5.24 KB | 0644 |
|
mbcharsetprober.py | File | 3.33 KB | 0644 |
|
mbcsgroupprober.py | File | 1.96 KB | 0644 |
|
mbcssm.py | File | 24.88 KB | 0644 |
|
sbcharsetprober.py | File | 5.99 KB | 0644 |
|
sbcsgroupprober.py | File | 4.21 KB | 0644 |
|
sjisprober.py | File | 3.69 KB | 0644 |
|
universaldetector.py | File | 12.21 KB | 0644 |
|
utf8prober.py | File | 2.7 KB | 0644 |
|
version.py | File | 242 B | 0644 |
|