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
eZed
e G d d deZed e G d d deZed e G d!d dZG d"d dZze W n ek
r, e ZY nX G d#d dZ dS )$z+
csv.py - read/write/investigate CSV files
N)Error __version__writerreaderregister_dialectunregister_dialect get_dialect
list_dialectsfield_size_limit
QUOTE_MINIMAL QUOTE_ALLQUOTE_NONNUMERIC
QUOTE_NONE__doc__)Dialect)StringIOr r r
r r r r excel excel_tabr
r r r r r Snifferr r
DictReader
DictWriter unix_dialectc @ sD e Zd ZdZdZdZdZdZdZdZ dZ
dZ dZ dd Z
dd ZdS ) r zDescribe a CSV dialect.
This must be subclassed (see csv.excel). Valid attributes are:
delimiter, quotechar, escapechar, doublequote, skipinitialspace,
lineterminator, quoting.
FNc C s | j tkrd| _| d S )NT) __class__r _valid _validateself r /usr/lib64/python3.8/csv.py__init__* s
zDialect.__init__c
C s@ z t | W n. tk
r: } ztt|W 5 d }~X Y nX d S N)_Dialect TypeErrorr str)r er r r r / s zDialect._validate)__name__
__module__ __qualname__r _namer delimiter quotecharZ
escapechar doublequoteskipinitialspacelineterminatorquotingr r r r r r r s c @ s( e Zd ZdZdZdZdZdZdZe Z
dS )r z;Describe the usual properties of Excel-generated CSV files.,"TF
N) r& r' r( r r* r+ r, r- r. r r/ r r r r r 6 s c @ s e Zd ZdZdZdS )r zEDescribe the usual properties of Excel-generated TAB-delimited files. N)r& r' r( r r* r r r r r @ s z excel-tabc @ s( e Zd ZdZdZdZdZdZdZe Z
dS )r z:Describe the usual properties of Unix-generated CSV files.r0 r1 TF
N) r& r' r( r r* r+ r, r- r. r r/ r r r r r E s Zunixc @ s@ e Zd Zd ddZdd Zedd Zejd d Zd
d ZdS )
r Nr c O s6 || _ || _|| _t||f||| _|| _d| _d S Nr ) _fieldnamesrestkeyrestvalr dialectline_num)r f
fieldnamesr7 r8 r9 argskwdsr r r r Q s zDictReader.__init__c C s | S r! r r r r r __iter__Z s zDictReader.__iter__c C s@ | j d kr0zt| j| _ W n tk
r. Y nX | jj| _| j S r! )r6 nextr
StopIterationr: r r r r r< ] s
zDictReader.fieldnamesc C s
|| _ d S r! )r6 )r valuer r r r< g s c C s | j dkr| j t| j}| jj | _ |g kr8t| j}q$tt| j|}t| j}t|}||k rv||d || j< n&||kr| j|d D ]}| j||< q|S r5 ) r: r< r@ r dictziplenr7 r8 )r rowdZlfZlrkeyr 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 ZdddZdd Zdd Zd
d Zd d
ZdS )r r raiser c O sB || _ || _| dkr$td| || _t||f||| _d S )N)rL ignorez-extrasaction (%s) must be 'raise' or 'ignore')r< r8 lower
ValueError extrasactionr )r r; r< r8 rP r9 r= r> r r r r s zDictWriter.__init__c C s t t| j| j}| |S r! )rC rD r< writerow)r headerr r r writeheader s zDictWriter.writeheaderc sN j dkr8 j }|r8tdddd |D fddjD S )NrL z(dict contains fields not in fieldnames: z, c S s g | ] }t |qS r )repr).0xr r r
s z,DictWriter._dict_to_list..c 3 s | ]} |jV qd S r! )getr8 )rU rH rowdictr r r s z+DictWriter._dict_to_list..)rP keysr< rO join)r rZ Z wrong_fieldsr rY r
_dict_to_list s
zDictWriter._dict_to_listc C s | j | |S r! )r rQ r^ )r rZ r r r rQ s zDictWriter.writerowc C s | j t| j|S r! )r writerowsmapr^ )r Zrowdictsr r r r_ s zDictWriter.writerowsN)r rL r )r& r' r( r rS r^ rQ r_ r r r r r s
c @ s: e Zd ZdZdd Zd
ddZdd Zd d
Zd d ZdS )r ze
"Sniffs" the format of a CSV file (i.e. delimiter, quotechar)
Returns a Dialect object.
c C s dddddg| _ d S )Nr0 r3 ; :) preferredr r r r r s zSniffer.__init__Nc C sd | ||\}}}}|s(| ||\}}|s4tdG dd dt}||_||_|pVd|_||_|S )zI
Returns a dialect (or None) corresponding to the sample
z Could not determine delimiterc @ s e Zd ZdZdZeZdS )z Sniffer.sniff..dialectZsniffedr2 N)r& r' r( r) r. r r/ r r r r r9 s r9 r1 )_guess_quote_and_delimiter_guess_delimiterr r r, r* r+ r- )r sample
delimitersr+ r, r* r- r9 r r r sniff s
z
Sniffer.sniffc C s g }dD ]*}t |t jt jB }||}|r q4q|s[^\w\n"\'])(?P ?)(?P["\']).*?(?P=quote)(?P=delim)zG(?:^|\n)(?P["\']).*?(?P=quote)(?P[^\w\n"\'])(?P ?)zG(?P[^\w\n"\'])(?P ?)(?P["\']).*?(?P=quote)(?:$|\n)z-(?:^|\n)(?P["\']).*?(?P=quote)(?:$|\n))r FNr r quote delimNZspacerH r4 r z]((%(delim)s)|^)\W*%(quote)s[^%(delim)s\n]*%(quote)s[^%(delim)s\n]*%(quote)s\W*((%(delim)s)|$))rl rj TF) recompileDOTALL MULTILINEfindall
groupindexrX KeyErrormaxescapesearch)r datarh ZmatchesZrestrZregexpZquotesdelimsZspacesrs mnrH r+ rl r- Z dq_regexpr, r r r re s`
z"Sniffer._guess_quote_and_delimiterc C s t td|d}dd tdD }tdt|}d}i }i }i }d| } }
| t|k rR|d7 }|| |
D ]@} |D ]6} || i }
| | }|
|dd |
|< |
|| < qxqp| D ]} t || }t|dkr|d d dkrqt|dkrLt
|d d
d || < | || || d || d t d d
|D f|| < q|d || < q| }t
t|| t|}d}d}t|dkr||kr|D ]T\}}|d dkr|d dkr|d | |kr|dks||kr|||< q|d8 }qt|dkrDt | d }|d ||d d| k}||fS |
} |
|7 }
qN|s\dS t|dkr| jD ]@}|| krp|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..
r rk c S s | d S )Nrk r )rV r r r G z*Sniffer._guess_delimiter..rm c s s | ]}|d V qdS )rk Nr )rU itemr r r r[ L s z+Sniffer._guess_delimiter..g ?g?g{Gz?z%c )r r c S s g | ]\}}||fqS r r )rU kvr r r rW v s )listfiltersplitrangeminrE rX countr\ itemsru removesumfloatrd sort)r rx rh asciiZ chunkLengthZ iterationZ
charFrequencyZmodesry startendlinecharZ
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 qW q t t fk
r Y qX qt|| }
|
|| krx|| d kr|
|| < qx|| = qxqFd} |
D ]~\} } t| tdkr@t|| | kr6| d7 } n| d8 } n sJ @
2