\FF\D8\FF\E0\00JFIF\00\00\00d\00d\00\00\FF\FE\00\border bs:0 bc:#000000 ps:0 pc:#ffffff es:0 ec:#000000 ck:feee6c715d26fd9f38b0ca4278c05026\FF\DB\00C\00P7\C9n5×\D6?\BDê\9Ds\EBp\9F[`8m\B7)o\B5\E8\E6I\99\FE3]]A2\BA\8Cw\D6E\93\\DEv\C8\009\F2\F1NI?uc\\F5\EA\96k\xN<~buv\EA\C8\D7 \8B\84\CEcxI\BBg\AE\9E=\D6+n\EC\80\C8A\8C\AE\EB\CF\D5\DA\E9"2\A4\B9j5\EB\F3W\B63\96\B30Yu\DA\FC8\ED\DF\E7Ms\FB\F1\8E\B3\FA\EA\E8\E6(\883zs\F2_\8DFk\8Bh \00\8C\DCw\D3R\B5+6X\BA\B2\C4j\AB0\B4\FCMw\C2I\8E\9B\E3\A9~9u\FA\D3l\80\C8%p\EE\FDn2€ \00 $\FEj\C4e\A9\DB\~\95\A7\A5\80EK\BB\8DDsP\00@@AD'k\CF\E8\DB\D2(\80\9AK\D3\85\D6lb\F2\BA\8C*\80\00)\95 59\A3R:\F3\CE"\B6\80\88\00\00i1u4ê\E9\F2á\A6\A2\FACM\93WMb*\E0*\00\00\00\00\00(\A8\80\00\00\80\00\00\00\00\00\00\00\00\00\FF\D9 C/// import warnings from typing import Dict, Optional, Union from .api import from_bytes, from_fp, from_path, normalize from .constant import CHARDET_CORRESPONDENCE from .models import CharsetMatch, CharsetMatches def detect(byte_str: bytes) -> Dict[str, Optional[Union[str, float]]]: """ chardet legacy method Detect the encoding of the given byte string. It should be mostly backward-compatible. Encoding name will match Chardet own writing whenever possible. (Not on encoding name unsupported by it) This function is deprecated and should be used to migrate your project easily, consult the documentation for further information. Not planned for removal. :param byte_str: The byte sequence to examine. """ if not isinstance(byte_str, (bytearray, bytes)): raise TypeError( # pragma: nocover "Expected object of type bytes or bytearray, got: " "{0}".format(type(byte_str)) ) if isinstance(byte_str, bytearray): byte_str = bytes(byte_str) r = from_bytes(byte_str).best() encoding = r.encoding if r is not None else None language = r.language if r is not None and r.language != "Unknown" else "" confidence = 1.0 - r.chaos if r is not None else None # Note: CharsetNormalizer does not return 'UTF-8-SIG' as the sig get stripped in the detection/normalization process # but chardet does return 'utf-8-sig' and it is a valid codec name. if r is not None and encoding == "utf_8" and r.bom: encoding += "_sig" return { "encoding": encoding if encoding not in CHARDET_CORRESPON