OXIESEC PANEL

Name	Size	Modified	Perms
📁 ..	-	05/04/2025 04:37:50 PM	rwxr-xr-x
📄 __init__.py	4.68 KB	08/20/2023 12:12:03 PM	rw-r--r--
📄 __main__.py	123 bytes	08/20/2023 12:12:03 PM	rw-r--r--
📁 __pycache__	-	05/04/2025 04:37:50 PM	rwxr-xr-x
📄 big5freq.py	30.54 KB	08/20/2023 12:12:03 PM	rw-r--r--
📄 big5prober.py	1.72 KB	08/20/2023 12:12:03 PM	rw-r--r--
📄 chardistribution.py	9.8 KB	08/20/2023 12:12:03 PM	rw-r--r--
📄 charsetgroupprober.py	3.82 KB	08/20/2023 12:12:03 PM	rw-r--r--
📄 charsetprober.py	5.29 KB	08/20/2023 12:12:03 PM	rw-r--r--
📁 cli	-	05/04/2025 04:37:50 PM	rwxr-xr-x
📄 codingstatemachine.py	3.64 KB	08/20/2023 12:12:03 PM	rw-r--r--
📄 codingstatemachinedict.py	542 bytes	08/20/2023 12:12:03 PM	rw-r--r--
📄 cp949prober.py	1.82 KB	08/20/2023 12:12:03 PM	rw-r--r--
📄 enums.py	1.64 KB	08/20/2023 12:12:03 PM	rw-r--r--
📄 escprober.py	3.91 KB	08/20/2023 12:12:03 PM	rw-r--r--
📄 escsm.py	11.89 KB	08/20/2023 12:12:03 PM	rw-r--r--
📄 eucjpprober.py	3.84 KB	08/20/2023 12:12:03 PM	rw-r--r--
📄 euckrfreq.py	13.25 KB	08/20/2023 12:12:03 PM	rw-r--r--
📄 euckrprober.py	1.71 KB	08/20/2023 12:12:03 PM	rw-r--r--
📄 euctwfreq.py	36.05 KB	08/20/2023 12:12:03 PM	rw-r--r--
📄 euctwprober.py	1.71 KB	08/20/2023 12:12:03 PM	rw-r--r--
📄 gb2312freq.py	20.25 KB	08/20/2023 12:12:03 PM	rw-r--r--
📄 gb2312prober.py	1.72 KB	08/20/2023 12:12:03 PM	rw-r--r--
📄 hebrewprober.py	14.2 KB	08/20/2023 12:12:03 PM	rw-r--r--
📄 jisfreq.py	25.19 KB	08/20/2023 12:12:03 PM	rw-r--r--
📄 johabfreq.py	41.5 KB	08/20/2023 12:12:03 PM	rw-r--r--
📄 johabprober.py	1.71 KB	08/20/2023 12:12:03 PM	rw-r--r--
📄 jpcntx.py	26.42 KB	08/20/2023 12:12:03 PM	rw-r--r--
📄 langbulgarianmodel.py	102.1 KB	08/20/2023 12:12:03 PM	rw-r--r--
📄 langgreekmodel.py	96.16 KB	08/20/2023 12:12:03 PM	rw-r--r--
📄 langhebrewmodel.py	95.88 KB	08/20/2023 12:12:03 PM	rw-r--r--
📄 langhungarianmodel.py	98.98 KB	08/20/2023 12:12:03 PM	rw-r--r--
📄 langrussianmodel.py	125.02 KB	08/20/2023 12:12:03 PM	rw-r--r--
📄 langthaimodel.py	100.35 KB	08/20/2023 12:12:03 PM	rw-r--r--
📄 langturkishmodel.py	93.13 KB	08/20/2023 12:12:03 PM	rw-r--r--
📄 latin1prober.py	5.25 KB	08/20/2023 12:12:03 PM	rw-r--r--
📄 macromanprober.py	5.93 KB	08/20/2023 12:12:03 PM	rw-r--r--
📄 mbcharsetprober.py	3.63 KB	08/20/2023 12:12:03 PM	rw-r--r--
📄 mbcsgroupprober.py	2.08 KB	08/20/2023 12:12:03 PM	rw-r--r--
📄 mbcssm.py	29.68 KB	08/20/2023 12:12:03 PM	rw-r--r--
📁 metadata	-	05/04/2025 04:37:50 PM	rwxr-xr-x
📄 py.typed	0 bytes	08/20/2023 12:12:03 PM	rw-r--r--
📄 resultdict.py	402 bytes	08/20/2023 12:12:03 PM	rw-r--r--
📄 sbcharsetprober.py	6.25 KB	08/20/2023 12:12:03 PM	rw-r--r--
📄 sbcsgroupprober.py	4.04 KB	08/20/2023 12:12:03 PM	rw-r--r--
📄 sjisprober.py	3.91 KB	08/20/2023 12:12:03 PM	rw-r--r--
📄 universaldetector.py	14.5 KB	08/20/2023 12:12:03 PM	rw-r--r--
📄 utf1632prober.py	8.31 KB	08/20/2023 12:12:03 PM	rw-r--r--
📄 utf8prober.py	2.75 KB	08/20/2023 12:12:03 PM	rw-r--r--
📄 version.py	244 bytes	08/20/2023 12:12:03 PM	rw-r--r--

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 typing import List, Union

from .charsetgroupprober import CharSetGroupProber
from .charsetprober import CharSetProber
from .enums import InputState
from .resultdict import ResultDict
from .universaldetector import UniversalDetector
from .version import VERSION, __version__

__all__ = ["UniversalDetector", "detect", "detect_all", "__version__", "VERSION"]

def detect(
    byte_str: Union[bytes, bytearray], should_rename_legacy: bool = False
) -> ResultDict:
    """
    Detect the encoding of the given byte string.

:param byte_str:     The byte sequence to examine.
    :type byte_str:      ``bytes`` or ``bytearray``
    :param should_rename_legacy:  Should we rename legacy encodings
                                  to their more modern equivalents?
    :type should_rename_legacy:   ``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(should_rename_legacy=should_rename_legacy)
    detector.feed(byte_str)
    return detector.close()

def detect_all(
    byte_str: Union[bytes, bytearray],
    ignore_threshold: bool = False,
    should_rename_legacy: bool = False,
) -> List[ResultDict]:
    """
    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``
    :param should_rename_legacy:  Should we rename legacy encodings
                                  to their more modern equivalents?
    :type should_rename_legacy:   ``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(should_rename_legacy=should_rename_legacy)
    detector.feed(byte_str)
    detector.close()

if detector.input_state == InputState.HIGH_BYTE:
        results: List[ResultDict] = []
        probers: List[CharSetProber] = []
        for prober in detector.charset_probers:
            if isinstance(prober, CharSetGroupProber):
                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
                    )
                # Rename legacy encodings with superset encodings if asked
                if should_rename_legacy:
                    charset_name = detector.LEGACY_MAP.get(
                        charset_name.lower(), 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]