ok
Direktori : /lib/python3.6/site-packages/chardet/__pycache__/ |
Current File : //lib/python3.6/site-packages/chardet/__pycache__/universaldetector.cpython-36.pyc |
3 `9Y�0 � @ s� d Z ddlZddlZddlZddlmZ ddlmZmZm Z ddl mZ ddlm Z ddlmZ dd lmZ G d d� de�ZdS )a Module containing the UniversalDetector detector class, which is the primary class a user of ``chardet`` should use. :author: Mark Pilgrim (initial port to Python) :author: Shy Shalom (original C code) :author: Dan Blanchard (major refactoring for 3.0) :author: Ian Cordasco � N� )�CharSetGroupProber)� InputState�LanguageFilter�ProbingState)�EscCharSetProber)�Latin1Prober)�MBCSGroupProber)�SBCSGroupProberc @ sn e Zd ZdZdZejd�Zejd�Zejd�Z dddd d ddd d�Z ejfdd�Z dd� Zdd� Zdd� ZdS )�UniversalDetectoraq The ``UniversalDetector`` class underlies the ``chardet.detect`` function and coordinates all of the different charset probers. To get a ``dict`` containing an encoding and its confidence, you can simply run: .. code:: u = UniversalDetector() u.feed(some_bytes) u.close() detected = u.result g�������?s [�-�]s (|~{)s [�-�]zWindows-1252zWindows-1250zWindows-1251zWindows-1256zWindows-1253zWindows-1255zWindows-1254zWindows-1257)z iso-8859-1z iso-8859-2z iso-8859-5z iso-8859-6z iso-8859-7z iso-8859-8z iso-8859-9ziso-8859-13c C sN d | _ g | _d | _d | _d | _d | _d | _|| _tj t �| _d | _| j � d S )N)�_esc_charset_prober�_charset_probers�result�done� _got_data�_input_state� _last_char�lang_filter�loggingZ getLogger�__name__�logger�_has_win_bytes�reset)�selfr � r �'/usr/lib/python3.6/universaldetector.py�__init__Q s zUniversalDetector.__init__c C sZ dddd�| _ d| _d| _d| _tj| _d| _| jr>| jj � x| j D ]}|j � qFW dS )z� Reset the UniversalDetector and all of its probers back to their initial states. This is called by ``__init__``, so you only need to call this directly in between analyses of different documents. Ng )�encoding� confidence�languageF� )r r r r r � PURE_ASCIIr r r r r )r �proberr r r r ^ s zUniversalDetector.resetc C s> | j r dS t|�sdS t|t�s(t|�}| js�|jtj�rJdddd�| _nv|jtj tj f�rldddd�| _nT|jd�r�dddd�| _n:|jd �r�d ddd�| _n |jtjtjf�r�dddd�| _d| _| jd dk r�d| _ dS | j tjk�r.| jj|��rtj| _ n*| j tjk�r.| jj| j| ��r.tj| _ |dd� | _| j tjk�r�| j�s^t| j�| _| jj|�tjk�r:| jj| jj� | jjd�| _d| _ n�| j tjk�r:| j�s�t | j�g| _| jt!j"@ �r�| jj#t$� � | jj#t%� � x@| jD ]6}|j|�tjk�r�|j|j� |jd�| _d| _ P �q�W | j&j|��r:d| _'dS )a� Takes a chunk of a document and feeds it through all of the relevant charset probers. After calling ``feed``, you can check the value of the ``done`` attribute to see if you need to continue feeding the ``UniversalDetector`` more data, or if it has made a prediction (in the ``result`` attribute). .. note:: You should always call ``close`` when you're done feeding in your document if ``done`` is not already ``True``. Nz UTF-8-SIGg �?� )r r r zUTF-32s �� zX-ISO-10646-UCS-4-3412s ��zX-ISO-10646-UCS-4-2143zUTF-16Tr r ���)(r �len� isinstance� bytearrayr � startswith�codecs�BOM_UTF8r �BOM_UTF32_LE�BOM_UTF32_BE�BOM_LE�BOM_BEr r r! �HIGH_BYTE_DETECTOR�search� HIGH_BYTE�ESC_DETECTORr Z ESC_ASCIIr r r �feedr ZFOUND_IT�charset_name�get_confidencer r r r ZNON_CJK�appendr r �WIN_BYTE_DETECTORr )r Zbyte_strr"