3jm<dZddlmZddlZddlmZmZddlmZdZ ejdejZ ejdejZ ejd ejZejd ejZdd Zdd Zdd Zy)z]+encoding\s*=\s*['"]([^'"]+)['"]s,]+charset\s*=\s*['"]?\s*([^\s'">;]+)s6]+content\s*=\s*['"][^'"]*charset=([^\s'">;]+)s&^[ \t\f]*#.*?coding[:=][ \t]*([-\w.]+)cjd|ddvrydj|jdddd}tj|}|r[ |j dj dj }t|}|t||rt|tdd Sy#ttf$rYywxYw) aBCheck the first two lines of *data* for a PEP 263 encoding declaration. PEP 263 declarations (e.g. ``# -*- coding: utf-8 -*-``) are only valid on line 1 or line 2 of a Python source file. :param data: The raw byte data to scan. :returns: A :class:`DetectionResult` with confidence 0.95, or ``None``. #N asciiz text/x-pythonencoding confidencelanguage mime_type) joinsplit _PEP263_REsearchgroupdecodestripUnicodeDecodeError ValueErrorr_validate_bytesrr)datafirst_two_linesmatchraw_namers D/DATA/.local/lib/python3.12/site-packages/chardet/pipeline/markup.py_detect_pep263r"s 4:jjE1!5bq!9:O   o .E  {{1~,,W5;;=H#8,  OD($C"!3)   #J/  s.B B21B2c|sy|dt}tttfD]}|j |}|s |j dj dj}t|}|Tt||sa|turdnd}t|td|cSt|S#ttf$rYwxYw)aScan the first bytes of *data* for a charset declaration. Checks for: 1. ```` 2. ```` 3. ```` 4. PEP 263 ``# -*- coding: ... -*-`` (first two lines only) :param data: The raw byte data to scan. :returns: A :class:`DetectionResult` with confidence 0.95, or ``None``. Nr r ztext/xmlz text/htmlr) _SCAN_LIMIT_XML_ENCODING_RE_HTML5_CHARSET_RE_HTML4_CONTENT_TYPE_RErrrrrrrrrrr")rheadpatternrr rrs r!detect_markup_charsetr*:s    D$&79OPt$   ;;q>009??A'x0H#h(G*15E*EJ; &%7!' Q" $ ' 3  s.B,,B>=B>cj |dtj|y#tttf$rYywxYw)zCheck that *data* can be decoded under *encoding* without errors. Only validates the first ``_SCAN_LIMIT`` bytes to avoid decoding a full 200 kB input just to verify a charset declaration found in the header. NFT)r$rr LookupErrorr)rrs r!rr`s< \k!!(+   Z 8s 22)rbytesreturnzDetectionResult | None)rr-rstrr.bool)__doc__ __future__rrechardet.pipelinerrchardet.registryrr$compile IGNORECASEr%r&r' MULTILINErr"r*rr!r;sB" F, 2::6 BJJ8"--$BBMM RZZBBLL Q ># L r: