Current Dir: /snap/core22/2955/usr/lib/python3/dist-packages/chardet/
[DIR] cli [ delete | rename ]
[DIR] metadata [ delete | rename ]
[DIR] __pycache__ [ delete | rename ]
[FILE] big5freq.py [ edit | delete | rename ]
[FILE] big5prober.py [ edit | delete | rename ]
[FILE] chardistribution.py [ edit | delete | rename ]
[FILE] charsetgroupprober.py [ edit | delete | rename ]
[FILE] charsetprober.py [ edit | delete | rename ]
[FILE] codingstatemachine.py [ edit | delete | rename ]
[FILE] compat.py [ edit | delete | rename ]
[FILE] cp949prober.py [ edit | delete | rename ]
[FILE] enums.py [ edit | delete | rename ]
[FILE] escprober.py [ edit | delete | rename ]
[FILE] escsm.py [ edit | delete | rename ]
[FILE] eucjpprober.py [ edit | delete | rename ]
[FILE] euckrfreq.py [ edit | delete | rename ]
[FILE] euckrprober.py [ edit | delete | rename ]
[FILE] euctwfreq.py [ edit | delete | rename ]
[FILE] euctwprober.py [ edit | delete | rename ]
[FILE] gb2312freq.py [ edit | delete | rename ]
[FILE] gb2312prober.py [ edit | delete | rename ]
[FILE] hebrewprober.py [ edit | delete | rename ]
[FILE] jisfreq.py [ edit | delete | rename ]
[FILE] jpcntx.py [ edit | delete | rename ]
[FILE] langbulgarianmodel.py [ edit | delete | rename ]
[FILE] langgreekmodel.py [ edit | delete | rename ]
[FILE] langhebrewmodel.py [ edit | delete | rename ]
[FILE] langhungarianmodel.py [ edit | delete | rename ]
[FILE] langrussianmodel.py [ edit | delete | rename ]
[FILE] langthaimodel.py [ edit | delete | rename ]
[FILE] langturkishmodel.py [ edit | delete | rename ]
[FILE] latin1prober.py [ edit | delete | rename ]
[FILE] mbcharsetprober.py [ edit | delete | rename ]
[FILE] mbcsgroupprober.py [ edit | delete | rename ]
[FILE] mbcssm.py [ edit | delete | rename ]
[FILE] sbcharsetprober.py [ edit | delete | rename ]
[FILE] sbcsgroupprober.py [ edit | delete | rename ]
[FILE] sjisprober.py [ edit | delete | rename ]
[FILE] universaldetector.py [ edit | delete | rename ]
[FILE] utf8prober.py [ edit | delete | rename ]
[FILE] version.py [ edit | delete | rename ]
[FILE] __init__.py [ edit | delete | rename ]
Viewing: /snap/core22/2955/usr/lib/python3/dist-packages/chardet/__init__.py
######################## 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]