U
|
L ±d¦ ã @ sh d dl mZmZ ddlmZ ddlmZ ddlmZm Z m
|
Z
|
ddl m Z m Z mZmZ G dd deZd S )
|
é )ÚOptionalÚUnioné )Ú CharSetProber)ÚCodingStateMachine)ÚLanguageFilterÚ MachineStateÚ ProbingState)Ú HZ_SM_MODELÚISO2022CN_SM_MODELÚISO2022JP_SM_MODELÚISO2022KR_SM_MODELc s e Zd ZdZejfedd fdd Zdd fdd Zee e
|
dd d
|
Z ee e
|
dd d Z e dd dZeeef edddZ ZS )ÚEscCharSetProberz¼
|
This CharSetProber uses a "code scheme" approach for detecting encodings,
|
whereby easily recognizable escape or shift sequences are relied on to
|
identify these encodings.
|
N)Ú lang_filterÚreturnc s t j|d g | _| jtj@ r@| j tt¡ | j tt ¡ | jtj
|
@ r\| j tt ¡ | jtj @ rx| j tt ¡ d| _d | _d | _tj| _| ¡ d S )N)r r )ÚsuperÚ__init__Ú coding_smr r ÚCHINESE_SIMPLIFIEDÚappendr r
|
r ÚJAPANESEr ÚKOREANr Úactive_sm_countÚ_detected_charsetÚ_detected_languager Ú DETECTINGÚ_stateÚreset)Úselfr ©Ú __class__© úHd:\z\workplace\vscode\pyvenv\venv\Lib\site-packages\chardet/escprober.pyr 0 s zEscCharSetProber.__init__)r c s@ t ¡ | jD ]}d|_| ¡ qt| j| _d | _d | _d S )NT)r r r ÚactiveÚlenr r r )r r r r! r" r @ s
|
|
|
zEscCharSetProber.resetc C s | j S ©N©r ©r r! r! r" Ú charset_nameI s z EscCharSetProber.charset_namec C s | j S r% )r r' r! r! r" ÚlanguageM s zEscCharSetProber.languagec C s | j r
|
dS dS )Ng®Gáz®ï?g r& r' r! r! r" Úget_confidenceQ s z EscCharSetProber.get_confidence)Úbyte_strr c C s |D ]}| j D ]}|jsq| |¡}|tjkrdd|_| jd8 _| jdkrtj| _| j S q|tj
|
krtj | _| ¡ | _ |j| _| j S qq| j S )NFr r )r r# Ú
|
next_stater ÚERRORr r ÚNOT_MEr ÚstateÚITS_MEÚFOUND_ITÚget_coding_state_machiner r) r )r r+ Úcr Ú coding_stater! r! r" ÚfeedT s"
|
|
|
|
|
|
zEscCharSetProber.feed)Ú__name__Ú
|
__module__Ú __qualname__Ú__doc__r ÚNONEr r Úpropertyr Ústrr( r) Úfloatr* r ÚbytesÚ bytearrayr r5 Ú __classcell__r! r! r r" r ) s r N)Útypingr r Ú charsetproberr Úcodingstatemachiner Úenumsr r r Úescsmr
|
r r r r r! r! r! r" Ú<module> s
|
|
