Your IP : 3.135.220.239
U
e5d? � @ s@ d Z ddlZddlmZmZmZmZmZmZm Z m
Z
m Z m Z m
Z
mZmZm Z ddlmZ ddlmZ dddd d
d d d
dddddddddddddgZG dd � d �ZG d d
� d
e�Zed
e� G d d� de�Zed e� G d d� de�Zed e� G d!d� d�ZG d"d� d�Zze W n ek
�r, e ZY nX G d#d� d�Z dS )$z+
csv.py - read/write/investigate CSV files
� N)�Error� __version__�writer�reader�register_dialect�unregister_dialect� get_dialect�
list_dialects�field_size_limit�
QUOTE_MINIMAL� QUOTE_ALL�QUOTE_NONNUMERIC�
QUOTE_NONE�__doc__)�Dialect)�StringIOr r r
r r r r �excel� excel_tabr
r r r r r �Snifferr r �
DictReader�
DictWriter� unix_dialectc @ sD e Zd ZdZdZdZdZdZdZdZ dZ
dZ dZ dd� Z
dd� ZdS ) r z�Describe a CSV dialect.
This must be subclassed (see csv.excel). Valid attributes are:
delimiter, quotechar, escapechar, doublequote, skipinitialspace,
lineterminator, quoting.
� FNc C s | j tkrd| _| �� d S )NT)� __class__r �_valid� _validate��self� r �/usr/lib64/python3.8/csv.py�__init__* s
zDialect.__init__c
C s@ z t | � W n. tk
r: } ztt|���W 5 d }~X Y nX d S �N)�_Dialect� TypeErrorr �str)r �er r r r / s zDialect._validate)�__name__�
__module__� __qualname__r �_namer � delimiter� quotecharZ
escapechar� doublequote�skipinitialspace�lineterminator�quotingr r r r r r r s c @ s( e Zd ZdZdZdZdZdZdZe Z
dS )r z;Describe the usual properties of Excel-generated CSV files.�,�"TF�
N) r& r' r( r r* r+ r, r- r. r r/ r r r r r 6 s c @ s e Zd ZdZdZdS )r zEDescribe the usual properties of Excel-generated TAB-delimited files.� N)r& r' r( r r* r r r r r @ s z excel-tabc @ s( e Zd ZdZdZdZdZdZdZe Z
dS )r z:Describe the usual properties of Unix-generated CSV files.r0 r1 TF�
N) r& r' r( r r* r+ r, r- r. r r/ r r r r r E s Zunixc @ s@ e Zd Zd dd�Zdd� Zedd� �Zejd d� �Zd
d � ZdS )
r Nr c O s6 || _ || _|| _t||f|�|�| _|| _d| _d S �Nr )� _fieldnames�restkey�restvalr �dialect�line_num)r �f�
fieldnamesr7 r8 r9 �args�kwdsr r r r Q s zDictReader.__init__c C s | S r! r r r r r �__iter__Z s zDictReader.__iter__c C s@ | j d kr0zt| j�| _ W n tk
r. Y nX | jj| _| j S r! )r6 �nextr �
StopIterationr: r r r r r< ] s
zDictReader.fieldnamesc C s
|| _ d S r! )r6 )r �valuer r r r< g s c C s� | j dkr| j t| j�}| jj | _ |g kr8t| j�}q$tt| j|��}t| j�}t|�}||k rv||d � || j< n&||kr�| j|d � D ]}| j||< q�|S r5 ) r: r< r@ r �dict�zip�lenr7 r8 )r �row�dZlfZlr�keyr r r �__next__k s
zDictReader.__next__)NNNr ) r& r' r( r r? �propertyr< �setterrI r r r r r P s �
c @ s6 e Zd Zddd�Zdd� Zdd � Zd
d � Zd d
� ZdS )r r �raiser c O sB || _ || _|�� dkr$td| ��|| _t||f|�|�| _d S )N)rL �ignorez-extrasaction (%s) must be 'raise' or 'ignore')r< r8 �lower�
ValueError� extrasactionr )r r; r< r8 rP r9 r= r> r r r r � s �zDictWriter.__init__c C s t t| j| j��}| �|�S r! )rC rD r< �writerow)r �headerr r r � writeheader� s zDictWriter.writeheaderc sN �j dkr8� �� �j }|r8tdd�dd� |D �� ��� �fdd��jD �S )NrL z(dict contains fields not in fieldnames: z, c S s g | ] }t |��qS r )�repr)�.0�xr r r �
<listcomp>� s z,DictWriter._dict_to_list.<locals>.<listcomp>c 3 s | ]}� � |�j�V qd S r! )�getr8 )rU rH ��rowdictr r r � <genexpr>� s z+DictWriter._dict_to_list.<locals>.<genexpr>)rP �keysr< rO �join)r rZ Z wrong_fieldsr rY r �
_dict_to_list� s
�zDictWriter._dict_to_listc C s | j �| �|��S r! )r rQ r^ )r rZ r r r rQ � s zDictWriter.writerowc C s | j �t| j|��S r! )r � writerows�mapr^ )r Zrowdictsr r r r_ � s zDictWriter.writerowsN)r rL r )r& r' r( r rS r^ rQ r_ r r r r r � s �
c @ s: e Zd ZdZdd� Zd
dd�Zdd� Zd d
� Zd d � ZdS )r ze
"Sniffs" the format of a CSV file (i.e. delimiter, quotechar)
Returns a Dialect object.
c C s dddddg| _ d S )Nr0 r3 �;� �:)� preferredr r r r r � s zSniffer.__init__Nc C sd | � ||�\}}}}|s(| �||�\}}|s4td��G dd� dt�}||_||_|pVd|_||_|S )zI
Returns a dialect (or None) corresponding to the sample
z Could not determine delimiterc @ s e Zd ZdZdZeZdS )z Sniffer.sniff.<locals>.dialectZsniffedr2 N)r& r' r( r) r. r r/ r r r r r9 � s r9 r1 )�_guess_quote_and_delimiter�_guess_delimiterr r r, r* r+ r- )r �sample�
delimitersr+ r, r* r- r9 r r r �sniff� s
�
�
z
Sniffer.sniffc C s� g }dD ]*}t �|t jt jB �}|�|�}|r q4q|s<dS i }i }d}|j} |D ]�}
| d d } |
| } | r�|�| d�d || < z| d d } |
| } W n tk
r� Y qRY nX | r�|dks�| |kr�|�| d�d || < z| d d } W n tk
�r Y qRY nX |
| rR|d7 }qRt||jd �}
|�rXt||jd �}|| |k}|d
k�r`d }nd }d}t �d t � |�|
d
� t j�}|�
|��r�d}nd}|
|||fS )a�
Looks for text enclosed between two identical quotes
(the probable quotechar) which are preceded and followed
by the same character (the probable delimiter).
For example:
,'some text',
The quote with the most wins, same with the delimiter.
If there is no quotechar the delimiter can't be determined
this way.
)zI(?P<delim>[^\w\n"\'])(?P<space> ?)(?P<quote>["\']).*?(?P=quote)(?P=delim)zG(?:^|\n)(?P<quote>["\']).*?(?P=quote)(?P<delim>[^\w\n"\'])(?P<space> ?)zG(?P<delim>[^\w\n"\'])(?P<space> ?)(?P<quote>["\']).*?(?P=quote)(?:$|\n)z-(?:^|\n)(?P<quote>["\']).*?(?P=quote)(?:$|\n))r FNr r �quote� �delimNZspace�rH r4 r z]((%(delim)s)|^)\W*%(quote)s[^%(delim)s\n]*%(quote)s[^%(delim)s\n]*%(quote)s\W*((%(delim)s)|$))rl rj TF) �re�compile�DOTALL� MULTILINE�findall�
groupindexrX �KeyError�max�escape�search)r �datarh ZmatchesZrestrZregexpZquotes�delimsZspacesrs �m�nrH r+ rl r- Z dq_regexpr, r r r re � s`
�� z"Sniffer._guess_quote_and_delimiterc C s t td|�d���}dd� td�D �}tdt|��}d}i }i }i }d| } }
| t|�k �rR|d7 }|| |
� D ]@} |D ]6} |�| i �}
| �| �}|
�|d�d |
|< |
|| < qxqp|�� D ]�} t || � � �}t|�dkr�|d d dkr�q�t|�dk�rLt
|d d
� d �|| < |� || � || d || d t d d
� |D �� f|| < q�|d || < q�|� � }t
t|| t|���}d}d}t|�dk�r�||k�r�|D ]T\}}|d dk�r�|d dk�r�|d | |k�r�|dk�s�||k�r�|||< �q�|d8 }�q�t|�dk�rDt |�� �d }|d �|�|d �d| �k}||fS |
} |
|7 }
qN|�s\dS t|�dk�r�| jD ]@}||�� k�rp|d �|�|d �d| �k}||f S �qpdd� |� � D �}|�� |d d }|d �|�|d �d| �k}||fS )a�
The delimiter /should/ occur the same number of times on
each row. However, due to malformed data, it may not. We don't want
an all or nothing approach, so we allow for small variations in this
number.
1) build a table of the frequency of each character on every line.
2) build a table of frequencies of this frequency (meta-frequency?),
e.g. 'x occurred 5 times in 10 rows, 6 times in 1000 rows,
7 times in 2 rows'
3) use the mode of the meta-frequency to determine the /expected/
frequency for that character
4) find out how often the character actually meets that goal
5) the character that best meets its goal is the delimiter
For performance reasons, the data is evaluated in chunks, so it can
try and evaluate the smallest portion of the data possible, evaluating
additional chunks as necessary.
Nr4 c S s g | ] }t |��qS r )�chr)rU �cr r r rW - s z,Sniffer._guess_delimiter.<locals>.<listcomp>� �
r rk c S s | d S )Nrk r )rV r r r �<lambda>G � z*Sniffer._guess_delimiter.<locals>.<lambda>rm c s s | ]}|d V qdS )rk Nr )rU �itemr r r r[ L s z+Sniffer._guess_delimiter.<locals>.<genexpr>g �?g�������?g{�G�z�?z%c )r r c S s g | ]\}}||f�qS r r )rU �k�vr r r rW v s ���)�list�filter�split�range�minrE rX �countr\ �itemsru �remove�sum�floatrd �sort)r rx rh �asciiZ chunkLengthZ iterationZ
charFrequencyZmodesry �start�end�line�charZ
metaFrequencyZfreqr� ZmodeListZtotalZ consistencyZ thresholdr� r� rl r- rG r r r rf s�
� �� �
� �zSniffer._guess_delimiterc
C s� t t|�| �|��}t|�}t|�}i }t|�D ] }d ||< q0d}|D ]�}|dkrV q�|d7 }t|�|krlqFt|�� �D ]x} tt t
fD ]4}
z|
|| � W q�W q� t t fk
r� Y q�X q�t|| �}
|
|| krx|| d kr�|
|| < qx|| = qxqFd} |�
� D ]~\} } t| �td�k�r@t|| �| k�r6| d7 } n| d8 } n<z| || � W n" t tfk
�rr | d7 } Y n
X | d8 } �q | dkS )Nr � rk )r r ri r@ rE r� r� r\ �intr� �complexrO �
OverflowErrorr� �typer# )
r rg ZrdrrR �columnsZ columnTypes�i�checkedrF �colZthisTypeZ hasHeaderZcolTyper r r �
has_header sJ
zSniffer.has_header)N) r& r' r( r r ri re rf r� r r r r r � s
Lg) r rn Z_csvr r r r r r r r r
r r r
r r r" �ior �__all__r r r r r r� � NameErrorr� r r r r r �<module> sJ @ �
2