o j@sdZddlmZddlZddlmZddlmZddlm Z ddl m Z ddl m Z mZmZdd lmZmZdd lmZmZmZdd lmZmZmZdd lmZdd lmZmZGdddZ dS)u3UniversalDetector — streaming encoding detection.) annotationsN)Iterable)MappingProxyType)ClassVar)_utils)DEFAULT_MAX_BYTES_resolve_prefer_superset_validate_max_bytes) EncodingEraLanguageFilter)PREFERRED_SUPERSETapply_compat_namesapply_preferred_superset) _NONE_RESULT DetectionDictDetectionResult) run_pipeline)_validate_encodingnormalize_encodingsc@seZdZUdZejZeeZde d<e j de j e fddddddd d+ddZd,d d!Zd-d#d$Zd.d%d&Zed/d'd(Zed-d)d*ZdS)0UniversalDetectoraStreaming character encoding detector. Implements a feed/close pattern for incremental detection of character encoding from byte streams. Compatible with the chardet 6.x API. All detection is performed by the same pipeline used by :func:`chardet.detect` and :func:`chardet.detect_all`, ensuring consistent results regardless of which API is used. .. note:: This class is **not** thread-safe. Each thread should create its own :class:`UniversalDetector` instance. z$ClassVar[MappingProxyType[str, str]] LEGACY_MAPFTNcp1252zutf-8)prefer_superset compat_namesinclude_encodingsexclude_encodingsno_match_encodingempty_input_encoding lang_filterr should_rename_legacybool encoding_erar max_bytesintrrrIterable[str] | NonerrstrrreturnNonec Cs|tjkr tjdtddt||}||_||_t|||_ ||_ t |d|_ t |d|_ t| d|_t| d|_t|_d|_d|_d |_d S) a3Initialize 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 ISO subset encodings to their Windows/CP superset equivalents (e.g., ISO-8859-1 -> Windows-1252). :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) stacklevelrrrrFN)r ALLwarningswarnDeprecationWarningr_prefer_superset _compat_namesr _encoding_era _max_bytesr_include_encodings_exclude_encodingsr_no_match_encoding_empty_input_encoding bytearray_buffer_done_closed_result) selfrrr!r"rrrrrrr<V/var/www/html/fyndo/pharma/fyndo/venv/lib/python3.10/site-packages/chardet/detector.py__init__2s< & zUniversalDetector.__init__byte_strbytes | bytearraycCsf|jr d}t||jrdS|jt|j}|dkr$|j|d|t|j|jkr1d|_dSdS)aFeed a chunk of bytes to the detector. Data is accumulated in an internal buffer. Once *max_bytes* have been buffered, :attr:`done` is set to ``True`` and further data is ignored until :meth:`reset` is called. :param byte_str: The next chunk of bytes to examine. :raises ValueError: If called after :meth:`close` without a :meth:`reset`. z+feed() called after close() without reset()NrT)r9 ValueErrorr8r1lenr7extend)r;r?msg remainingr<r<r=feedxs  zUniversalDetector.feedrc CsN|js$d|_t|j}t||j|j|j|j|j|j d}|d|_ d|_ |j S)zFinalize detection and return the best result. Runs the full detection pipeline on the buffered data. :returns: A dictionary with keys ``"encoding"``, ``"confidence"``, and ``"language"``. T)r"rrrrr) r9bytesr7rr0r1r2r3r4r5r:r8result)r;dataresultsr<r<r=closes  zUniversalDetector.closecCst|_d|_d|_d|_dS)z2Reset the detector to its initial state for reuse.FN)r6r7r8r9r:r;r<r<r=resets zUniversalDetector.resetcCs|jS)z9Whether detection is complete and no more data is needed.)r8rLr<r<r=doneszUniversalDetector.donecCs<|jdur|j}|jrt||jrt||StS)z"The current best detection result.N)r:to_dictr.rr/r r)r;dr<r<r=rHs  zUniversalDetector.result)rr rr r!r r"r#rr rr rr$rr$rr%rr%r&r')r?r@r&r')r&r)r&r')r&r )__name__ __module__ __qualname____doc__rMINIMUM_THRESHOLDrr r__annotations__r r*r rr>rFrKrMpropertyrNrHr<r<r<r=rs2   F   r)!rT __future__rr+collections.abcrtypesrtypingrchardetrchardet._utilsrrr chardet.enumsr r chardet.equivalencesr r rchardet.pipelinerrrchardet.pipeline.orchestratorrchardet.registryrrrr<r<r<r=s