SWAMPy

✎ CARVE FLESH

EDITING: __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.

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]

CANCEL

Name	Type	Size	Modified	Actions
↩ ..	DIR	—	—
📁 __pycache__/	DIR	—	2023-11-13 20:19
📁 cli/	DIR	—	2023-11-13 20:19
📁 metadata/	DIR	—	2023-11-13 20:19
📄 __init__.py	PY	3.2 KB	2022-03-25 13:25	EDIT
📄 big5freq.py	PY	30.5 KB	2022-03-25 13:25	EDIT
📄 big5prober.py	PY	1.7 KB	2022-03-25 13:25	EDIT
📄 chardistribution.py	PY	9.2 KB	2022-03-25 13:25	EDIT
📄 charsetgroupprober.py	PY	3.7 KB	2022-03-25 13:25	EDIT
📄 charsetprober.py	PY	5 KB	2022-03-25 13:25	EDIT
📄 codingstatemachine.py	PY	3.5 KB	2022-03-25 13:25	EDIT
📄 compat.py	PY	1.2 KB	2022-03-25 13:25	EDIT
📄 cp949prober.py	PY	1.8 KB	2022-03-25 13:25	EDIT
📄 enums.py	PY	1.6 KB	2022-03-25 13:25	EDIT
📄 escprober.py	PY	3.9 KB	2022-03-25 13:25	EDIT
📄 escsm.py	PY	10.3 KB	2022-03-25 13:25	EDIT
📄 eucjpprober.py	PY	3.7 KB	2022-03-25 13:25	EDIT
📄 euckrfreq.py	PY	13.2 KB	2022-03-25 13:25	EDIT
📄 euckrprober.py	PY	1.7 KB	2022-03-25 13:25	EDIT
📄 euctwfreq.py	PY	30.9 KB	2022-03-25 13:25	EDIT
📄 euctwprober.py	PY	1.7 KB	2022-03-25 13:25	EDIT
📄 gb2312freq.py	PY	20.2 KB	2022-03-25 13:25	EDIT
📄 gb2312prober.py	PY	1.7 KB	2022-03-25 13:25	EDIT
📄 hebrewprober.py	PY	13.5 KB	2022-03-25 13:25	EDIT
📄 jisfreq.py	PY	25.2 KB	2022-03-25 13:25	EDIT
📄 jpcntx.py	PY	19.2 KB	2022-03-25 13:25	EDIT
📄 langbulgarianmodel.py	PY	103.2 KB	2022-03-25 13:25	EDIT
📄 langgreekmodel.py	PY	97.2 KB	2022-03-25 13:25	EDIT
📄 langhebrewmodel.py	PY	96.4 KB	2022-03-25 13:25	EDIT
📄 langhungarianmodel.py	PY	100.1 KB	2022-03-25 13:25	EDIT
📄 langrussianmodel.py	PY	128.1 KB	2022-03-25 13:25	EDIT
📄 langthaimodel.py	PY	100.9 KB	2022-03-25 13:25	EDIT
📄 langturkishmodel.py	PY	93.7 KB	2022-03-25 13:25	EDIT
📄 latin1prober.py	PY	5.2 KB	2022-03-25 13:25	EDIT
📄 mbcharsetprober.py	PY	3.3 KB	2022-03-25 13:25	EDIT
📄 mbcsgroupprober.py	PY	2 KB	2022-03-25 13:25	EDIT
📄 mbcssm.py	PY	24.9 KB	2022-03-25 13:25	EDIT
📄 sbcharsetprober.py	PY	6 KB	2022-03-25 13:25	EDIT
📄 sbcsgroupprober.py	PY	4.2 KB	2022-03-25 13:25	EDIT
📄 sjisprober.py	PY	3.7 KB	2022-03-25 13:25	EDIT
📄 universaldetector.py	PY	12.2 KB	2022-03-25 13:25	EDIT
📄 utf8prober.py	PY	2.7 KB	2022-03-25 13:25	EDIT
📄 version.py	PY	242 B	2022-03-25 13:25	EDIT