bazarr/libs/chardet/__init__.py

116 lines
4.7 KiB
Python
Raw Normal View History

######################## 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 #########################
2023-06-23 04:03:23 +00:00
from typing import List, Union
from .charsetgroupprober import CharSetGroupProber
from .charsetprober import CharSetProber
from .enums import InputState
2023-06-23 04:03:23 +00:00
from .resultdict import ResultDict
2022-11-07 18:06:49 +00:00
from .universaldetector import UniversalDetector
from .version import VERSION, __version__
2022-11-07 18:06:49 +00:00
__all__ = ["UniversalDetector", "detect", "detect_all", "__version__", "VERSION"]
2023-06-23 04:03:23 +00:00
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``
2023-06-23 04:03:23 +00:00
: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):
2022-11-07 18:06:49 +00:00
raise TypeError(
f"Expected object of type bytes or bytearray, got: {type(byte_str)}"
)
byte_str = bytearray(byte_str)
2023-06-23 04:03:23 +00:00
detector = UniversalDetector(should_rename_legacy=should_rename_legacy)
detector.feed(byte_str)
return detector.close()
2023-06-23 04:03:23 +00:00
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.
2022-11-07 18:06:49 +00:00
: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``
2023-06-23 04:03:23 +00:00
: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):
2022-11-07 18:06:49 +00:00
raise TypeError(
f"Expected object of type bytes or bytearray, got: {type(byte_str)}"
)
byte_str = bytearray(byte_str)
2023-06-23 04:03:23 +00:00
detector = UniversalDetector(should_rename_legacy=should_rename_legacy)
detector.feed(byte_str)
detector.close()
2022-11-07 18:06:49 +00:00
if detector.input_state == InputState.HIGH_BYTE:
2023-06-23 04:03:23 +00:00
results: List[ResultDict] = []
probers: List[CharSetProber] = []
2022-11-07 18:06:49 +00:00
for prober in detector.charset_probers:
2023-06-23 04:03:23 +00:00
if isinstance(prober, CharSetGroupProber):
2022-11-07 18:06:49 +00:00
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
2022-11-07 18:06:49 +00:00
if lower_charset_name.startswith("iso-8859") and detector.has_win_bytes:
charset_name = detector.ISO_WIN_MAP.get(
lower_charset_name, charset_name
)
2023-06-23 04:03:23 +00:00
# Rename legacy encodings with superset encodings if asked
if should_rename_legacy:
charset_name = detector.LEGACY_MAP.get(
charset_name.lower(), charset_name
)
2022-11-07 18:06:49 +00:00
results.append(
{
"encoding": charset_name,
"confidence": prober.get_confidence(),
"language": prober.language,
}
)
if len(results) > 0:
2022-11-07 18:06:49 +00:00
return sorted(results, key=lambda result: -result["confidence"])
return [detector.result]