^j'dZddlmZddlmZddlmZmZmZm Z m Z m Z ddl m Z ddlmZddlmZmZddlmZmZdd lmZmZdd lmZdd lmZmZgd Zdd Zdej@eefddddddd ddZ!ddej@eefddddddd ddZ"y)u@Universal character encoding detector — 0BSD-licensed rewrite.) annotations)Iterable)_DEFAULT_CHUNK_SIZEDEFAULT_MAX_BYTESMINIMUM_THRESHOLD_resolve_prefer_superset_validate_max_bytes_warn_deprecated_chunk_size) __version__)UniversalDetector) EncodingEraLanguageFilter)apply_compat_namesapply_preferred_superset) DetectionDictDetectionResult) run_pipeline)_validate_encodingnormalize_encodings) rrrrr rr r detect detect_allcd|dk(rddl}|jdSdtd|}t|)aResolve the deprecated ``chardet.equivalences`` submodule on demand. Before the 7.5 split, ``chardet/__init__.py`` imported that module for its own use, which as a side effect made ``chardet.equivalences`` work without an explicit ``import chardet.equivalences``. This package now imports :mod:`chardet.output_names` instead, so the attribute is bound lazily here: importing the shim eagerly would fire its deprecation warning on every ``import chardet``. equivalencesrNzchardet.equivalenceszmodule z has no attribute ) importlib import_module__name__AttributeError)namermsgs R/var/www/html/metafoliadorv2/venv/lib/python3.12/site-packages/chardet/__init__.py __getattr__r!%sA ~ &&'=>> H<1$ :C  FTNcp1252zutf-8)prefer_superset compat_namesinclude_encodingsexclude_encodingsno_match_encodingempty_input_encodingc vt|t|t||}t|d} t|d} t | d} t | d}t |t r|n t |}t|||| | | |}|dj}|d|}|rt||| | |r t|||S) aD Detect the encoding of the given byte string. :param byte_str: The byte sequence to detect encoding for. :param should_rename_legacy: Deprecated alias for *prefer_superset*. :param encoding_era: Restrict candidate encodings to the given era. :param chunk_size: Deprecated -- accepted for backward compatibility but has no effect. :param max_bytes: Maximum number of bytes to examine from *byte_str*. :param prefer_superset: If ``True``, remap subset encodings in the result to their decode-safe Windows/CP superset equivalents (e.g., ISO-8859-1 -> Windows-1252, EUC-KR -> CP949). Recommended when the result will be used to decode: detection examines at most *max_bytes* of input, and only the superset is guaranteed to decode bytes beyond that window. The remap is skipped when the superset cannot decode the examined window itself (the Windows code pages leave a few C1 positions undefined that the ISO subsets map), so the reported name always decodes what was examined. If ``False`` (default), the detected encoding is reported under its own name --- note this only skips the renaming step; it is not a promise of the *smallest* matching encoding, since detection may natively choose a superset that fits the data better. The default will change to ``True`` in chardet 8.0; pass ``False`` explicitly if you depend on subset names. :param compat_names: If ``True`` (default), return encoding names compatible with chardet 5.x/6.x. If ``False``, return raw Python codec names. :param include_encodings: If given, restrict detection to only these encodings (names or aliases). :param exclude_encodings: If given, remove these encodings from the candidate set. :param no_match_encoding: Encoding to return when no candidate survives the pipeline. Defaults to ``"cp1252"``. It is returned as given, at confidence 0.10, and is the one answer that is not checked against the data: it is the caller's sentinel for "nothing fit". :param empty_input_encoding: Encoding to return for empty input. Defaults to ``"utf-8"``. :returns: A dictionary with keys ``"encoding"``, ``"confidence"``, ``"language"``, and ``"mime_type"``. r&r'r(r)) max_bytesr&r'r(r)rNr&r') r r rrr isinstancebytesrto_dictrr)byte_strshould_rename_legacy encoding_era chunk_sizer+r$r%r&r'r(r)includeexcludeno_matchemptydataresultsresultwindows r rr:sj + "./C_UO!"35HIG!"35HIG!"35HIH 35K LE!(E28hD !!""GQZ   !F *9 F  %%  66* Mr"c t|t|t||}t|d} t| d} t | d}t | d}t |t r|n t |}t|||| | ||d}|Dcgc]}|j}}|s |Dcgc]}|dtkDs|}}|r|}|d|}|D]"}|rt||| | |st||$|jd d t}g}|D]/}|d |vs |j|d |j|1|Scc}wcc}w) aYDetect all possible encodings of the given byte string. When *ignore_threshold* is False (the default), results with confidence <= MINIMUM_THRESHOLD (0.20) are filtered out. If all results are below the threshold, the full unfiltered list is returned as a fallback so the caller always receives at least one result. :param byte_str: The byte sequence to detect encoding for. :param ignore_threshold: If ``True``, return all candidate encodings regardless of confidence score. :param should_rename_legacy: Deprecated alias for *prefer_superset*. :param encoding_era: Restrict candidate encodings to the given era. :param chunk_size: Deprecated -- accepted for backward compatibility but has no effect. :param max_bytes: Maximum number of bytes to examine from *byte_str*. :param prefer_superset: If ``True``, remap subset encodings in the results to their decode-safe Windows/CP superset equivalents. If ``False`` (default), skip the renaming --- not a promise of the smallest matching encoding. The default will change to ``True`` in chardet 8.0. See :func:`detect` for details. :param compat_names: If ``True`` (default), return encoding names compatible with chardet 5.x/6.x. If ``False``, return raw Python codec names. :param include_encodings: If given, restrict detection to only these encodings (names or aliases). :param exclude_encodings: If given, remove these encodings from the candidate set. :param no_match_encoding: Encoding to return when no candidate survives the pipeline. Defaults to ``"cp1252"``. :param empty_input_encoding: Encoding to return for empty input. Defaults to ``"utf-8"``. :returns: A list of dictionaries, sorted by descending confidence, one per encoding name. r&r'r(r)T)r+r&r'r(r) full_ranking confidenceNr,c |dS)Nr>)ds r zdetect_all..s Q|_r")keyreverseencoding)r r rrrr-r.rr/rrrsortsetaddappend)r0ignore_thresholdr1r2r3r+r$r%r&r'r(r)r4r5r6r7r8r9rdictsrAfilteredr;seenuniques r rrszb + "./C_UO!"35HIG!"35HIG!"35HIH 35K LE!(E28hD !!"" G#* *QQYY[ *E * $L!,:K(KALL E *9 F *  $6W   q& ) * JJ,dJ;  ED"$F  Z= $ HHQz] # MM!  M1 +LsE&E 8E )rstrreturnobject)r0bytes | bytearrayr1boolr2r r3intr+rUr$rTr%rTr&Iterable[str] | Noner'rVr(rPr)rPrQr)r0rSrJrTr1rTr2r r3rUr+rUr$rTr%rTr&rVr'rVr(rPr)rPrQzlist[DetectionDict])#__doc__ __future__rcollections.abcrchardet._utilsrrrrr r chardet._versionr chardet.detectorr chardet.enumsr rchardet.output_namesrrchardet.pipelinerrchardet.pipeline.orchestratorrchardet.registryrr__all__r!ALLrrr@r"r rdsF"$).5M;6D ."' +)& Q".2.2% 'QQQQ Q  QQQ,Q,QQQQl#!& +)& [".2.2% '[[[[ [  [  [[[,[,[[[[r"