관리-도구
편집 파일: cd.cpython-37.pyc
B �bD+ � @ s� d dl Z d dlmZ d dlmZmZ d dlmZ d dlm Z m Z m Z m Z ddl mZ ddlmZmZmZmZ dd lmZ dd lmZ dd lmZmZmZm Z m Z e e e d �d d�Z e e e d�dd�Z e� e e e d �dd��Z!e� e e e d �dd��Z"eed�e e e#e#f d�dd��Z$d,e e e#e e d�d d �Z%e e e e&d �d d �Z'e e e d!�d"d#�Z(e e ed$�d%d&�Z)ed'd�d-e e&e e ed)�d*d+��Z*dS ).� N)�IncrementalDecoder)�Counter� OrderedDict)� lru_cache)�Dict�List�Optional�Tuple� )� FREQUENCIES)�KO_NAMES�LANGUAGE_SUPPORTED_COUNT�TOO_SMALL_SEQUENCE�ZH_NAMES)� is_suspiciously_successive_range)�CoherenceMatches)�is_accentuated�is_latin�is_multi_byte_encoding�is_unicode_range_secondary� unicode_range)� iana_name�returnc s� t | �rtd��t�d�| ��j}|dd�}i �d� xltdd�D ]^}|�t|g��}|r@t |�}|dkrjq@t |�d kr@|�kr�d�|< �| d 7 < � d 7 � q@W t � �fd d ��D ��S ) zF Return associated unicode ranges in a single byte code page. z.Function not supported on multi-byte code pagez encodings.{}�ignore)�errorsr �@ � NFr c s g | ]}�| � d kr|�qS )g333333�?� )�.0�character_range)�character_count� seen_rangesr �F/opt/alt/python37/lib/python3.7/site-packages/charset_normalizer/cd.py� <listcomp>2 s z*encoding_unicode_range.<locals>.<listcomp>) r �IOError� importlib� import_module�formatr �range�decode�bytesr r �sorted)r �decoder�p�i�chunkr r )r r! r" �encoding_unicode_range s( r0 )� primary_ranger c C sD g }x:t �� D ].\}}x$|D ] }t|�| kr |�|� P q W qW |S )z> Return inferred languages used with a unicode range. )r �itemsr �append)r1 � languages�language� characters� characterr r r" �unicode_range_languages9 s r8 c C s> t | �}d}x|D ]}d|kr|}P qW |dkr6dgS t|�S )z� Single-byte encoding language association. Some code page are heavily linked to particular language(s). This function does the correspondence. NZLatinz Latin Based)r0 r8 )r Zunicode_rangesr1 Zspecified_ranger r r" �encoding_languagesH s r9 c C sb | � d�s&| � d�s&| � d�s&| dkr,dgS | � d�s>| tkrFddgS | � d �sX| tkr^d gS g S ) z� Multi-byte encoding language association. Some code page are heavily linked to particular language(s). This function does the correspondence. Zshift_� iso2022_jpZeuc_j�cp932ZJapaneseZgbZChinesezClassical Chinese� iso2022_krZKorean)� startswithr r )r r r r" �mb_encoding_languages\ s r> )�maxsize)r5 r c C sF d}d}x4t | D ](}|s&t|�r&d}|rt|�dkrd}qW ||fS )zg Determine main aspects from a supported language if it contains accents and if is pure Latin. FT)r r r )r5 �target_have_accents�target_pure_latinr7 r r r" �get_target_featuresq s rB F)r6 �ignore_non_latinr c s� g }t dd� � D ��}xxt�� D ]l\}}t|�\}}|rB|dkrBq |dkrP|rPq t|�}t� fdd�|D ��} | | } | dkr |�|| f� q W t|dd� d d �}d d� |D �S ) zE Return associated languages associated to given characters. c s s | ]}t |�V qd S )N)r )r r7 r r r" � <genexpr>� s z%alphabet_languages.<locals>.<genexpr>Fc s g | ]}|� kr|�qS r r )r �c)r6 r r" r# � s z&alphabet_languages.<locals>.<listcomp>g�������?c S s | d S )Nr r )�xr r r" �<lambda>� � z$alphabet_languages.<locals>.<lambda>T)�key�reversec S s g | ] }|d �qS )r r )r Zcompatible_languager r r" r# � s )�anyr r2 rB �lenr3 r+ ) r6 rC r4 Zsource_have_accentsr5 Zlanguage_charactersr@ rA r Zcharacter_match_count�ratior )r6 r" �alphabet_languages� s rN )r5 �ordered_charactersr c s6 | t krtd�| ���d}�x |D �]}|t | kr6q"t | dt | �|�� }t | t | �|�d� }|d|�|�� �||�|�d� � �fdd�|D ��d�}� fdd�|D ��d�}t|�dkr�|dkr�|d 7 }q"t|�dkr�|dkr�|d 7 }q"|t|� d k�s |t|� d kr"|d 7 }q"q"W |t|� S ) aN Determine if a ordered characters list (by occurrence from most appearance to rarest) match a particular language. The result is a ratio between 0. (absolutely no correspondence) and 1. (near perfect fit). Beware that is function is not strict on the match in order to ease the detection. (Meaning close match is 1.) z{} not availabler Nc s g | ] }|� k�qS r r )r �e)�characters_beforer r" r# � s z1characters_popularity_compare.<locals>.<listcomp>Tc s g | ] }|� k�qS r r )r rP )�characters_afterr r" r# � s � r g�������?)r � ValueErrorr' �index�countrL )r5 rO Zcharacter_approved_countr7 Zcharacters_before_sourceZcharacters_after_sourceZbefore_match_countZafter_match_countr )rR rQ r" � characters_popularity_compare� s: rW )�decoded_sequencer c C s� t � }x�| D ]�}|�� dkr q t|�}|dkr0q d}x |D ]}t||�dkr:|}P q:W |dkrb|}||krx|�� ||< q || |�� 7 < q W t|�� �S )a Given a decoded text sequence, return a list of str. Unicode range / alphabet separation. Ex. a text containing English/Latin with a bit a Hebrew will return two items in the resulting list; One containing the latin letters and the other hebrew. FN)r �isalphar r �lower�list�values)rX Zlayersr7 r Zlayer_target_rangeZdiscovered_ranger r r" �alpha_unicode_split� s( r] )�resultsr c sp t � � xD| D ]<}x6|D ].}|\}}|� kr6|g� |< q� | �|� qW q W � fdd�� D �}t|dd� dd�S )z� This function merge results previously given by the function coherence_ratio. The return type is the same as coherence_ratio. c s. g | ]&}|t t� | �t� | � d �f�qS )rS )�round�sumrL )r r5 )�per_language_ratiosr r" r# s z*merge_coherence_ratios.<locals>.<listcomp>c S s | d S )Nr r )rF r r r" rG " rH z(merge_coherence_ratios.<locals>.<lambda>T)rI rJ )r r3 r+ )r^ �resultZ sub_resultr5 rM �merger )ra r" �merge_coherence_ratios s rd i 皙�����?)rX � threshold� lg_inclusionr c C s� g }d}d}|dk r |� d�ng }d|kr8d}|�d� x�t| �D ]�}t|�}|�� } tdd� | D ��} | tkrrqBd d � | D �} xZ|p�t| |�D ]H} t| | �} | |k r�q�n| d kr�|d 7 }|� | t | d �f� |dkr�P q�W qBW t |dd� dd�S )z� Detect ANY language that can be identified in given sequence. The sequence will be analysed by layers. A layer = Character extraction by alphabets/ranges. Fr N�,z Latin BasedTc s s | ]\}}|V qd S )Nr )r rE �or r r" rD < s z"coherence_ratio.<locals>.<genexpr>c S s g | ] \}}|�qS r r )r rE ri r r r" r# A s z#coherence_ratio.<locals>.<listcomp>g�������?r rS � c S s | d S )Nr r )rF r r r" rG T rH z!coherence_ratio.<locals>.<lambda>)rI rJ ) �split�remover] r � most_commonr` r rN rW r3 r_ r+ )rX rf rg r^ rC Zsufficient_match_countZlg_inclusion_listZlayerZsequence_frequenciesrm r Zpopular_character_orderedr5 rM r r r" �coherence_ratio% s4 rn )F)re N)+r% �codecsr � collectionsr r � functoolsr �typingr r r r Zassetsr Zconstantr r r r Zmdr Zmodelsr �utilsr r r r r �strr0 r8 r9 r> �boolrB rN �floatrW r] rd rn r r r r" �<module> s4 % #:'