mirror of
https://github.com/Tautulli/Tautulli.git
synced 2025-07-16 02:02:58 -07:00
Bump requests from 2.26.0 to 2.27.0 (#1602)
* Bump requests from 2.26.0 to 2.27.0 Bumps [requests](https://github.com/psf/requests) from 2.26.0 to 2.27.0. - [Release notes](https://github.com/psf/requests/releases) - [Changelog](https://github.com/psf/requests/blob/main/HISTORY.md) - [Commits](https://github.com/psf/requests/compare/v2.26.0...v2.27.0) --- updated-dependencies: - dependency-name: requests dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> * Update requests==2.27.0 Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: JonnyWong16 <9099342+JonnyWong16@users.noreply.github.com>
This commit is contained in:
dependabot[bot]
GitHub
parent
2c7a3934cb
commit
bb5ebe0fa5
11 changed files with 156 additions and 83 deletions
|
|
@ -68,20 +68,21 @@ def from_bytes(
|
|||
)
|
||||
|
||||
if explain:
|
||||
previous_logger_level = logger.level # type: int
|
||||
logger.addHandler(explain_handler)
|
||||
logger.setLevel(logging.DEBUG)
|
||||
|
||||
length = len(sequences) # type: int
|
||||
|
||||
if length == 0:
|
||||
logger.warning(
|
||||
"Given content is empty, stopping the process very early, returning empty utf_8 str match"
|
||||
)
|
||||
logger.warning("Encoding detection on empty bytes, assuming utf_8 intention.")
|
||||
if explain:
|
||||
logger.removeHandler(explain_handler)
|
||||
logger.setLevel(previous_logger_level or logging.WARNING)
|
||||
return CharsetMatches([CharsetMatch(sequences, "utf_8", 0.0, False, [], "")])
|
||||
|
||||
if cp_isolation is not None:
|
||||
logger.warning(
|
||||
logger.debug(
|
||||
"cp_isolation is set. use this flag for debugging purpose. "
|
||||
"limited list of encoding allowed : %s.",
|
||||
", ".join(cp_isolation),
|
||||
|
|
@ -91,7 +92,7 @@ def from_bytes(
|
|||
cp_isolation = []
|
||||
|
||||
if cp_exclusion is not None:
|
||||
logger.warning(
|
||||
logger.debug(
|
||||
"cp_exclusion is set. use this flag for debugging purpose. "
|
||||
"limited list of encoding excluded : %s.",
|
||||
", ".join(cp_exclusion),
|
||||
|
|
@ -101,7 +102,7 @@ def from_bytes(
|
|||
cp_exclusion = []
|
||||
|
||||
if length <= (chunk_size * steps):
|
||||
logger.warning(
|
||||
logger.debug(
|
||||
"override steps (%i) and chunk_size (%i) as content does not fit (%i byte(s) given) parameters.",
|
||||
steps,
|
||||
chunk_size,
|
||||
|
|
@ -187,7 +188,7 @@ def from_bytes(
|
|||
) # type: bool
|
||||
|
||||
if encoding_iana in {"utf_16", "utf_32"} and not bom_or_sig_available:
|
||||
logger.info(
|
||||
logger.debug(
|
||||
"Encoding %s wont be tested as-is because it require a BOM. Will try some sub-encoder LE/BE.",
|
||||
encoding_iana,
|
||||
)
|
||||
|
|
@ -218,7 +219,7 @@ def from_bytes(
|
|||
)
|
||||
except (UnicodeDecodeError, LookupError) as e:
|
||||
if not isinstance(e, LookupError):
|
||||
logger.warning(
|
||||
logger.debug(
|
||||
"Code page %s does not fit given bytes sequence at ALL. %s",
|
||||
encoding_iana,
|
||||
str(e),
|
||||
|
|
@ -234,7 +235,7 @@ def from_bytes(
|
|||
break
|
||||
|
||||
if similar_soft_failure_test:
|
||||
logger.warning(
|
||||
logger.debug(
|
||||
"%s is deemed too similar to code page %s and was consider unsuited already. Continuing!",
|
||||
encoding_iana,
|
||||
encoding_soft_failed,
|
||||
|
|
@ -254,7 +255,7 @@ def from_bytes(
|
|||
) # type: bool
|
||||
|
||||
if multi_byte_bonus:
|
||||
logger.info(
|
||||
logger.debug(
|
||||
"Code page %s is a multi byte encoding table and it appear that at least one character "
|
||||
"was encoded using n-bytes.",
|
||||
encoding_iana,
|
||||
|
|
@ -264,6 +265,7 @@ def from_bytes(
|
|||
|
||||
max_chunk_gave_up = max(max_chunk_gave_up, 2)
|
||||
early_stop_count = 0 # type: int
|
||||
lazy_str_hard_failure = False
|
||||
|
||||
md_chunks = [] # type: List[str]
|
||||
md_ratios = []
|
||||
|
|
@ -283,12 +285,13 @@ def from_bytes(
|
|||
errors="ignore" if is_multi_byte_decoder else "strict",
|
||||
) # type: str
|
||||
except UnicodeDecodeError as e: # Lazy str loading may have missed something there
|
||||
logger.warning(
|
||||
logger.debug(
|
||||
"LazyStr Loading: After MD chunk decode, code page %s does not fit given bytes sequence at ALL. %s",
|
||||
encoding_iana,
|
||||
str(e),
|
||||
)
|
||||
early_stop_count = max_chunk_gave_up
|
||||
lazy_str_hard_failure = True
|
||||
break
|
||||
|
||||
# multi-byte bad cutting detector and adjustment
|
||||
|
|
@ -324,12 +327,30 @@ def from_bytes(
|
|||
):
|
||||
break
|
||||
|
||||
# We might want to check the sequence again with the whole content
|
||||
# Only if initial MD tests passes
|
||||
if (
|
||||
not lazy_str_hard_failure
|
||||
and is_too_large_sequence
|
||||
and not is_multi_byte_decoder
|
||||
):
|
||||
try:
|
||||
sequences[int(50e3) :].decode(encoding_iana, errors="strict")
|
||||
except UnicodeDecodeError as e:
|
||||
logger.debug(
|
||||
"LazyStr Loading: After final lookup, code page %s does not fit given bytes sequence at ALL. %s",
|
||||
encoding_iana,
|
||||
str(e),
|
||||
)
|
||||
tested_but_hard_failure.append(encoding_iana)
|
||||
continue
|
||||
|
||||
mean_mess_ratio = (
|
||||
sum(md_ratios) / len(md_ratios) if md_ratios else 0.0
|
||||
) # type: float
|
||||
if mean_mess_ratio >= threshold or early_stop_count >= max_chunk_gave_up:
|
||||
tested_but_soft_failure.append(encoding_iana)
|
||||
logger.warning(
|
||||
logger.info(
|
||||
"%s was excluded because of initial chaos probing. Gave up %i time(s). "
|
||||
"Computed mean chaos is %f %%.",
|
||||
encoding_iana,
|
||||
|
|
@ -337,7 +358,10 @@ def from_bytes(
|
|||
round(mean_mess_ratio * 100, ndigits=3),
|
||||
)
|
||||
# Preparing those fallbacks in case we got nothing.
|
||||
if encoding_iana in ["ascii", "utf_8", specified_encoding]:
|
||||
if (
|
||||
encoding_iana in ["ascii", "utf_8", specified_encoding]
|
||||
and not lazy_str_hard_failure
|
||||
):
|
||||
fallback_entry = CharsetMatch(
|
||||
sequences, encoding_iana, threshold, False, [], decoded_payload
|
||||
)
|
||||
|
|
@ -361,7 +385,7 @@ def from_bytes(
|
|||
target_languages = mb_encoding_languages(encoding_iana)
|
||||
|
||||
if target_languages:
|
||||
logger.info(
|
||||
logger.debug(
|
||||
"{} should target any language(s) of {}".format(
|
||||
encoding_iana, str(target_languages)
|
||||
)
|
||||
|
|
@ -369,12 +393,15 @@ def from_bytes(
|
|||
|
||||
cd_ratios = []
|
||||
|
||||
for chunk in md_chunks:
|
||||
chunk_languages = coherence_ratio(
|
||||
chunk, 0.1, ",".join(target_languages) if target_languages else None
|
||||
)
|
||||
# We shall skip the CD when its about ASCII
|
||||
# Most of the time its not relevant to run "language-detection" on it.
|
||||
if encoding_iana != "ascii":
|
||||
for chunk in md_chunks:
|
||||
chunk_languages = coherence_ratio(
|
||||
chunk, 0.1, ",".join(target_languages) if target_languages else None
|
||||
)
|
||||
|
||||
cd_ratios.append(chunk_languages)
|
||||
cd_ratios.append(chunk_languages)
|
||||
|
||||
cd_ratios_merged = merge_coherence_ratios(cd_ratios)
|
||||
|
||||
|
|
@ -385,20 +412,6 @@ def from_bytes(
|
|||
)
|
||||
)
|
||||
|
||||
# We might want to check the sequence again with the whole content
|
||||
# Only if initial MD/CD tests passes
|
||||
if is_too_large_sequence and not is_multi_byte_decoder:
|
||||
try:
|
||||
sequences[int(50e3) :].decode(encoding_iana, errors="strict")
|
||||
except UnicodeDecodeError as e:
|
||||
logger.warning(
|
||||
"LazyStr Loading: After final lookup, code page %s does not fit given bytes sequence at ALL. %s",
|
||||
encoding_iana,
|
||||
str(e),
|
||||
)
|
||||
tested_but_hard_failure.append(encoding_iana)
|
||||
continue
|
||||
|
||||
results.append(
|
||||
CharsetMatch(
|
||||
sequences,
|
||||
|
|
@ -419,6 +432,7 @@ def from_bytes(
|
|||
)
|
||||
if explain:
|
||||
logger.removeHandler(explain_handler)
|
||||
logger.setLevel(previous_logger_level)
|
||||
return CharsetMatches([results[encoding_iana]])
|
||||
|
||||
if encoding_iana == sig_encoding:
|
||||
|
|
@ -428,16 +442,17 @@ def from_bytes(
|
|||
)
|
||||
if explain:
|
||||
logger.removeHandler(explain_handler)
|
||||
logger.setLevel(previous_logger_level)
|
||||
return CharsetMatches([results[encoding_iana]])
|
||||
|
||||
if len(results) == 0:
|
||||
if fallback_u8 or fallback_ascii or fallback_specified:
|
||||
logger.warning(
|
||||
logger.debug(
|
||||
"Nothing got out of the detection process. Using ASCII/UTF-8/Specified fallback."
|
||||
)
|
||||
|
||||
if fallback_specified:
|
||||
logger.warning(
|
||||
logger.debug(
|
||||
"%s will be used as a fallback match", fallback_specified.encoding
|
||||
)
|
||||
results.append(fallback_specified)
|
||||
|
|
@ -458,6 +473,7 @@ def from_bytes(
|
|||
|
||||
if explain:
|
||||
logger.removeHandler(explain_handler)
|
||||
logger.setLevel(previous_logger_level)
|
||||
|
||||
return results
|
||||
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue