Bump plexapi from 4.15.16 to 4.16.0 (#2439)

* Bump plexapi from 4.15.16 to 4.16.0

Bumps [plexapi](https://github.com/pkkid/python-plexapi) from 4.15.16 to 4.16.0.
- [Release notes](https://github.com/pkkid/python-plexapi/releases)
- [Commits](https://github.com/pkkid/python-plexapi/compare/4.15.16...4.16.0)

---
updated-dependencies:
- dependency-name: plexapi
  dependency-type: direct:production
  update-type: version-update:semver-minor
...

Signed-off-by: dependabot[bot] <support@github.com>

* Update plexapi==4.16.0

---------

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: JonnyWong16 <9099342+JonnyWong16@users.noreply.github.com>

[skip ci]
This commit is contained in:
dependabot[bot] 2024-11-19 10:00:37 -08:00 committed by GitHub
commit 0836fb902c
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
20 changed files with 287 additions and 49 deletions

View file

@ -159,6 +159,8 @@ def from_bytes(
results: CharsetMatches = CharsetMatches()
early_stop_results: CharsetMatches = CharsetMatches()
sig_encoding, sig_payload = identify_sig_or_bom(sequences)
if sig_encoding is not None:
@ -221,16 +223,20 @@ def from_bytes(
try:
if is_too_large_sequence and is_multi_byte_decoder is False:
str(
sequences[: int(50e4)]
if strip_sig_or_bom is False
else sequences[len(sig_payload) : int(50e4)],
(
sequences[: int(50e4)]
if strip_sig_or_bom is False
else sequences[len(sig_payload) : int(50e4)]
),
encoding=encoding_iana,
)
else:
decoded_payload = str(
sequences
if strip_sig_or_bom is False
else sequences[len(sig_payload) :],
(
sequences
if strip_sig_or_bom is False
else sequences[len(sig_payload) :]
),
encoding=encoding_iana,
)
except (UnicodeDecodeError, LookupError) as e:
@ -367,7 +373,13 @@ def from_bytes(
and not lazy_str_hard_failure
):
fallback_entry = CharsetMatch(
sequences, encoding_iana, threshold, False, [], decoded_payload
sequences,
encoding_iana,
threshold,
False,
[],
decoded_payload,
preemptive_declaration=specified_encoding,
)
if encoding_iana == specified_encoding:
fallback_specified = fallback_entry
@ -421,28 +433,58 @@ def from_bytes(
),
)
results.append(
CharsetMatch(
sequences,
encoding_iana,
mean_mess_ratio,
bom_or_sig_available,
cd_ratios_merged,
decoded_payload,
)
current_match = CharsetMatch(
sequences,
encoding_iana,
mean_mess_ratio,
bom_or_sig_available,
cd_ratios_merged,
(
decoded_payload
if (
is_too_large_sequence is False
or encoding_iana in [specified_encoding, "ascii", "utf_8"]
)
else None
),
preemptive_declaration=specified_encoding,
)
results.append(current_match)
if (
encoding_iana in [specified_encoding, "ascii", "utf_8"]
and mean_mess_ratio < 0.1
):
# If md says nothing to worry about, then... stop immediately!
if mean_mess_ratio == 0.0:
logger.debug(
"Encoding detection: %s is most likely the one.",
current_match.encoding,
)
if explain:
logger.removeHandler(explain_handler)
logger.setLevel(previous_logger_level)
return CharsetMatches([current_match])
early_stop_results.append(current_match)
if (
len(early_stop_results)
and (specified_encoding is None or specified_encoding in tested)
and "ascii" in tested
and "utf_8" in tested
):
probable_result: CharsetMatch = early_stop_results.best() # type: ignore[assignment]
logger.debug(
"Encoding detection: %s is most likely the one.", encoding_iana
"Encoding detection: %s is most likely the one.",
probable_result.encoding,
)
if explain:
logger.removeHandler(explain_handler)
logger.setLevel(previous_logger_level)
return CharsetMatches([results[encoding_iana]])
return CharsetMatches([probable_result])
if encoding_iana == sig_encoding:
logger.debug(

View file

@ -109,6 +109,14 @@ def cli_detect(argv: Optional[List[str]] = None) -> int:
dest="force",
help="Replace file without asking if you are sure, use this flag with caution.",
)
parser.add_argument(
"-i",
"--no-preemptive",
action="store_true",
default=False,
dest="no_preemptive",
help="Disable looking at a charset declaration to hint the detector.",
)
parser.add_argument(
"-t",
"--threshold",
@ -133,21 +141,35 @@ def cli_detect(argv: Optional[List[str]] = None) -> int:
args = parser.parse_args(argv)
if args.replace is True and args.normalize is False:
if args.files:
for my_file in args.files:
my_file.close()
print("Use --replace in addition of --normalize only.", file=sys.stderr)
return 1
if args.force is True and args.replace is False:
if args.files:
for my_file in args.files:
my_file.close()
print("Use --force in addition of --replace only.", file=sys.stderr)
return 1
if args.threshold < 0.0 or args.threshold > 1.0:
if args.files:
for my_file in args.files:
my_file.close()
print("--threshold VALUE should be between 0. AND 1.", file=sys.stderr)
return 1
x_ = []
for my_file in args.files:
matches = from_fp(my_file, threshold=args.threshold, explain=args.verbose)
matches = from_fp(
my_file,
threshold=args.threshold,
explain=args.verbose,
preemptive_behaviour=args.no_preemptive is False,
)
best_guess = matches.best()
@ -155,9 +177,11 @@ def cli_detect(argv: Optional[List[str]] = None) -> int:
print(
'Unable to identify originating encoding for "{}". {}'.format(
my_file.name,
"Maybe try increasing maximum amount of chaos."
if args.threshold < 1.0
else "",
(
"Maybe try increasing maximum amount of chaos."
if args.threshold < 1.0
else ""
),
),
file=sys.stderr,
)
@ -258,8 +282,8 @@ def cli_detect(argv: Optional[List[str]] = None) -> int:
try:
x_[0].unicode_path = join(dir_path, ".".join(o_))
with open(x_[0].unicode_path, "w", encoding="utf-8") as fp:
fp.write(str(best_guess))
with open(x_[0].unicode_path, "wb") as fp:
fp.write(best_guess.output())
except IOError as e:
print(str(e), file=sys.stderr)
if my_file.closed is False:

View file

@ -544,6 +544,8 @@ COMMON_SAFE_ASCII_CHARACTERS: Set[str] = {
"|",
'"',
"-",
"(",
")",
}

View file

@ -1,13 +1,24 @@
from typing import Any, Dict, Optional, Union
from __future__ import annotations
from typing import TYPE_CHECKING, Any, Optional
from warnings import warn
from .api import from_bytes
from .constant import CHARDET_CORRESPONDENCE
# TODO: remove this check when dropping Python 3.7 support
if TYPE_CHECKING:
from typing_extensions import TypedDict
class ResultDict(TypedDict):
encoding: Optional[str]
language: str
confidence: Optional[float]
def detect(
byte_str: bytes, should_rename_legacy: bool = False, **kwargs: Any
) -> Dict[str, Optional[Union[str, float]]]:
) -> ResultDict:
"""
chardet legacy method
Detect the encoding of the given byte string. It should be mostly backward-compatible.

View file

@ -236,7 +236,7 @@ class SuspiciousRange(MessDetectorPlugin):
@property
def ratio(self) -> float:
if self._character_count <= 24:
if self._character_count <= 13:
return 0.0
ratio_of_suspicious_range_usage: float = (
@ -260,6 +260,7 @@ class SuperWeirdWordPlugin(MessDetectorPlugin):
self._buffer: str = ""
self._buffer_accent_count: int = 0
self._buffer_glyph_count: int = 0
def eligible(self, character: str) -> bool:
return True
@ -279,6 +280,14 @@ class SuperWeirdWordPlugin(MessDetectorPlugin):
and is_thai(character) is False
):
self._foreign_long_watch = True
if (
is_cjk(character)
or is_hangul(character)
or is_katakana(character)
or is_hiragana(character)
or is_thai(character)
):
self._buffer_glyph_count += 1
return
if not self._buffer:
return
@ -291,17 +300,20 @@ class SuperWeirdWordPlugin(MessDetectorPlugin):
self._character_count += buffer_length
if buffer_length >= 4:
if self._buffer_accent_count / buffer_length > 0.34:
if self._buffer_accent_count / buffer_length >= 0.5:
self._is_current_word_bad = True
# Word/Buffer ending with an upper case accentuated letter are so rare,
# that we will consider them all as suspicious. Same weight as foreign_long suspicious.
if (
elif (
is_accentuated(self._buffer[-1])
and self._buffer[-1].isupper()
and all(_.isupper() for _ in self._buffer) is False
):
self._foreign_long_count += 1
self._is_current_word_bad = True
elif self._buffer_glyph_count == 1:
self._is_current_word_bad = True
self._foreign_long_count += 1
if buffer_length >= 24 and self._foreign_long_watch:
camel_case_dst = [
i
@ -325,6 +337,7 @@ class SuperWeirdWordPlugin(MessDetectorPlugin):
self._foreign_long_watch = False
self._buffer = ""
self._buffer_accent_count = 0
self._buffer_glyph_count = 0
elif (
character not in {"<", ">", "-", "=", "~", "|", "_"}
and character.isdigit() is False

View file

@ -1,9 +1,10 @@
from encodings.aliases import aliases
from hashlib import sha256
from json import dumps
from re import sub
from typing import Any, Dict, Iterator, List, Optional, Tuple, Union
from .constant import TOO_BIG_SEQUENCE
from .constant import RE_POSSIBLE_ENCODING_INDICATION, TOO_BIG_SEQUENCE
from .utils import iana_name, is_multi_byte_encoding, unicode_range
@ -16,6 +17,7 @@ class CharsetMatch:
has_sig_or_bom: bool,
languages: "CoherenceMatches",
decoded_payload: Optional[str] = None,
preemptive_declaration: Optional[str] = None,
):
self._payload: bytes = payload
@ -33,13 +35,13 @@ class CharsetMatch:
self._string: Optional[str] = decoded_payload
self._preemptive_declaration: Optional[str] = preemptive_declaration
def __eq__(self, other: object) -> bool:
if not isinstance(other, CharsetMatch):
raise TypeError(
"__eq__ cannot be invoked on {} and {}.".format(
str(other.__class__), str(self.__class__)
)
)
if isinstance(other, str):
return iana_name(other) == self.encoding
return False
return self.encoding == other.encoding and self.fingerprint == other.fingerprint
def __lt__(self, other: object) -> bool:
@ -210,7 +212,24 @@ class CharsetMatch:
"""
if self._output_encoding is None or self._output_encoding != encoding:
self._output_encoding = encoding
self._output_payload = str(self).encode(encoding, "replace")
decoded_string = str(self)
if (
self._preemptive_declaration is not None
and self._preemptive_declaration.lower()
not in ["utf-8", "utf8", "utf_8"]
):
patched_header = sub(
RE_POSSIBLE_ENCODING_INDICATION,
lambda m: m.string[m.span()[0] : m.span()[1]].replace(
m.groups()[0], iana_name(self._output_encoding) # type: ignore[arg-type]
),
decoded_string[:8192],
1,
)
decoded_string = patched_header + decoded_string[8192:]
self._output_payload = decoded_string.encode(encoding, "replace")
return self._output_payload # type: ignore
@ -266,7 +285,7 @@ class CharsetMatches:
)
)
# We should disable the submatch factoring when the input file is too heavy (conserve RAM usage)
if len(item.raw) <= TOO_BIG_SEQUENCE:
if len(item.raw) < TOO_BIG_SEQUENCE:
for match in self._results:
if match.fingerprint == item.fingerprint and match.chaos == item.chaos:
match.add_submatch(item)

View file

@ -2,5 +2,5 @@
Expose version
"""
__version__ = "3.3.2"
__version__ = "3.4.0"
VERSION = __version__.split(".")