^j5"dZddlmZddlZddlmZddlmZddlm Z ddl m Z ddl m Z mZmZdd lmZmZdd lmZmZmZmZdd lmZmZmZdd lmZdd lmZm Z GddZ!y)u3UniversalDetector — streaming encoding detection.) annotationsN)Iterable)MappingProxyType)ClassVar)_utils)DEFAULT_MAX_BYTES_resolve_prefer_superset_validate_max_bytes) EncodingEraLanguageFilter)NARROWER_DISPLAY_NAMESPREFERRED_SUPERSETapply_compat_namesapply_preferred_superset) _NONE_RESULT DetectionDictDetectionResult) run_pipeline)_validate_encodingnormalize_encodingsceZdZUdZej ZeeZde d<e jde je fddddddd  dd Zdd Zdd Zdd ZeddZeddZy)UniversalDetectoraStreaming character encoding detector. Implements a feed/close pattern for incremental detection of character encoding from byte streams. Compatible with the chardet 6.x API. All detection is performed by the same pipeline used by :func:`chardet.detect` and :func:`chardet.detect_all`, ensuring consistent results regardless of which API is used. .. note:: This class is **not** thread-safe. Each thread should create its own :class:`UniversalDetector` instance. z$ClassVar[MappingProxyType[str, str]] LEGACY_MAPFTNcp1252zutf-8)prefer_superset compat_namesinclude_encodingsexclude_encodingsno_match_encodingempty_input_encodingc|tjk7rtjdtdt ||}||_||_t|||_ ||_ t|d|_ t|d|_ t| d|_t| d|_t#|_d|_d|_d|_d |_y ) a*Initialize the detector. :param lang_filter: Deprecated -- accepted for backward compatibility but has no effect. A warning is emitted when set to anything other than :attr:`LanguageFilter.ALL`. :param should_rename_legacy: Deprecated alias for *prefer_superset*. :param encoding_era: Restrict candidate encodings to the given era. :param max_bytes: Maximum number of bytes to buffer from :meth:`feed` calls before stopping accumulation. :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). 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:`chardet.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"``. zMlang_filter is not implemented in this version of chardet and will be ignored) stacklevelrrrr FN)r ALLwarningswarnDeprecationWarningr _prefer_superset _compat_namesr _encoding_era _max_bytesr_include_encodings_exclude_encodingsr_no_match_encoding_empty_input_encoding bytearray_buffer_input_truncated_done_closed_result) self lang_filtershould_rename_legacy encoding_era max_bytesrrrrrr s R/var/www/html/metafoliadorv2/venv/lib/python3.12/site-packages/chardet/detector.py__init__zUniversalDetector.__init__3sR .,, , MM&"   3 / !0)I&)#"5 2# #6 2# #5 2# &8 "8& "!{ %  /3 c~|jr d}t||jr |rd|_y|jt |j z }|dkDr|j j|d|t |t|dkDrd|_t |j |jk\rd|_yy)aFeed a chunk of bytes to the detector. Data is accumulated in an internal buffer. Once *max_bytes* have been buffered, :attr:`done` is set to ``True`` and further data is ignored until :meth:`reset` is called. :param byte_str: The next chunk of bytes to examine. :raises ValueError: If called after :meth:`close` without a :meth:`reset`. z+feed() called after close() without reset()TNr) r4 ValueErrorr3r2r+lenr1extendmax)r6byte_strmsg remainings r;feedzUniversalDetector.feed}s <<?CS/ ! ::(,% OOc$,,&77 q= LL  ) 4 5 x=3y!, ,%)D ! t||  /DJ 0r=c >|jsd|_t|j}t||j|j |j |j|j|j|j}|d|_ d|_ |jS)zFinalize detection and return the best result. Runs the full detection pipeline on the buffered data. :returns: A dictionary with keys ``"encoding"``, ``"confidence"``, ``"language"``, and ``"mime_type"``. T)r:input_truncatedrrrr r)r4bytesr1rr*r+r2r,r-r.r/r5r3result)r6dataresultss r;closezUniversalDetector.closes||DL&D"""// $ 5 5"&"9"9"&"9"9"&"9"9%)%?%? G#1:DLDJ{{r=cZt|_d|_d|_d|_d|_y)z2Reset the detector to its initial state for reuse.FN)r0r1r2r3r4r5r6s r;resetzUniversalDetector.resets( { %   r=c|jS)z9Whether detection is complete and no more data is needed.)r3rOs r;donezUniversalDetector.doneszzr=c||j|jj}d}|js|jr |dtvrt |j }|jr#t|||j|j|jr t|||StjS)z"The current best detection result.r=encoding)rr) r5to_dictr(r)r rIr1rr,r-rr)r6dwindows r;rJzUniversalDetector.results << # $$&AF$$""q}8N'Nt||,$$(&*&=&=&*&=&=  !!"1f-H##%%r=)r7r r8boolr9r r:intrrXrrXrIterable[str] | NonerrZrstrr r[returnNone)rCzbytes | bytearrayr\r])r\r)r\r])r\rX)__name__ __module__ __qualname____doc__rMINIMUM_THRESHOLDrrr__annotations__r r$r rr<rFrMrPpropertyrRrJr=r;rrs 008H8J4 '5&8&8%*$/OO* H4!&!2626!)$+H4#H4#H4" H4  H4H4H40H40H4H4"H4 H4T@2&&r=r)"ra __future__rr%collections.abcrtypesrtypingrchardetrchardet._utilsrr r chardet.enumsr r chardet.output_namesr rrrchardet.pipelinerrrchardet.pipeline.orchestratorrchardet.registryrrrrer=r;rqsN9"$" 6 JI6D~&~&r=