3
\4? @ sL d Z ddlZddlmZmZmZmZmZmZm Z m
Z
m Z m Z m
Z
mZmZm Z ddlmZ ddlmZ ddlmZ ddd d
d d d
ddddddddddddddgZG d d d ZG d d deZede G d d deZed e G d d deZed!e G d"d dZG d#d dZye W n e k
r8 e Z Y 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) OrderedDict)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| _| j d S )NT) __class__r _valid _validate)self r /usr/lib64/python3.6/csv.py__init__+ s
zDialect.__init__c C s@ y t | W n. tk
r: } ztt|W Y d d }~X nX d S )N)_Dialect TypeErrorr str)r er r r r 0 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.,"TFz
N) r% r& r' r r) r* r+ r, r- r r. r r r r r 7 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 A s z excel-tabc @ s( e Zd ZdZdZdZdZdZdZe Z
dS )r z:Describe the usual properties of Unix-generated CSV files.r/ r0 TF
N) r% r& r' r r) r* r+ r, r- r r. r r r r r F 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
fieldnamesr4 r5 r6 argskwdsr r r r R s zDictReader.__init__c C s | S )Nr )r r r r __iter__[ s zDictReader.__iter__c C s@ | j d kr0yt| j| _ W n tk
r. Y nX | jj| _| j S )N)r3 nextr
StopIterationr7 )r r r r r9 ^ s
zDictReader.fieldnamesc C s
|| _ d S )N)r3 )r valuer r r r9 h s c C s | j dkr| j t| j}| jj | _ x|g kr:t| j}q&W tt| j|}t| j}t|}||k rz||d || j< n*||krx | j|d D ]}| j||< qW |S )Nr ) r7 r9 r= r r ziplenr4 r5 )r rowdZlfZlrkeyr r r __next__l s
zDictReader.__next__)NNNr ) r% r& r' r r< propertyr9 setterrE r r r r r Q s
c @ s6 e Zd ZdddZdd Zdd Zd
d Zd d
ZdS )r r raiser c O sB || _ || _|j dkr$td| || _t||f||| _d S )NrH ignorez-extrasaction (%s) must be 'raise' or 'ignore')rH rI )r9 r5 lower
ValueError extrasactionr )r r8 r9 r5 rL r6 r: r; r r r r s zDictWriter.__init__c C s t t| j| j}| j| d S )N)dictr@ r9 writerow)r headerr r r writeheader s zDictWriter.writeheaderc sN j dkr8 j j }|r8tddjdd |D fddjD S )NrH 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 | ]} j |jV qd S )N)getr5 )rR rD )rowdictr r r s z+DictWriter._dict_to_list..)rL keysr9 rK join)r rV Z wrong_fieldsr )rV r r
_dict_to_list s
zDictWriter._dict_to_listc C s | j j| j|S )N)r rN rZ )r rV r r r rN s zDictWriter.writerowc C s | j jt| j|S )N)r writerowsmaprZ )r Zrowdictsr r r r[ s zDictWriter.writerowsN)r rH r )r% r& r' r rP rZ rN 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 )Nr/ r1 ; :) preferred)r r r r r s zSniffer.__init__Nc C sd | j ||\}}}}|s(| j||\}}|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..dialectZsniffedz
N)r% r& r' r( r- r r. r r r r r6 s r6 r0 )_guess_quote_and_delimiter_guess_delimiterr r r+ r) r* r, )r sample
delimitersr* r+ r) r, r6 r r r sniff s
z
Sniffer.sniffc C s g }x0dD ](}t j|t jt jB }|j|}|r
P q
W |s>dS i }i }d}|j} x|D ]}
| d d
} |
| } | r|j| dd
|| < y| d d
} |
| } W n tk
r wVY nX | r|dks| |kr|j| dd
|| < y| d d
} W n tk
r wVY nX |
| rV|d
7 }qVW t||jd
}
|rZt||jd
}|| |k}|dkrbd}nd}d}t jdt j ||
d t j}|j
|rd}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.
I(?P[^\w\n"\'])(?P ?)(?P["\']).*?(?P=quote)(?P=delim)G(?:^|\n)(?P["\']).*?(?P=quote)(?P[^\w\n"\'])(?P ?)G(?P[^\w\n"\'])(?P ?)(?P["\']).*?(?P=quote)(?:$|\n)-(?:^|\n)(?P["\']).*?(?P=quote)(?:$|\n)r FNr quote delimZspace)rD r2 z]((%(delim)s)|^)\W*%(quote)s[^%(delim)s\n]*%(quote)s[^%(delim)s\n]*%(quote)s\W*((%(delim)s)|$))rl rj T)rf rg rh ri )r FNr ) recompileDOTALL MULTILINEfindall
groupindexrU KeyErrormaxescapesearch)r datard ZmatchesZrestrZregexpZquotesdelimsZspacesrr mnrD r* rl r, Z dq_regexpr+ r r r ra s`
z"Sniffer._guess_quote_and_delimiterc C s t td|jd}dd tdD }tdt|}d}i }i }i }dt|t| } }
x| t|k rn|d7 }xT|| |
D ]D} x>|D ]6} |j| i }
| j| }|
j|dd |
|< |
|| < qW qW x|j D ]} t || j }t|dkr|d d dkrqt|dkrht
|d d
d || < |j || || d || d t d d
|D f|| < q|d || < qW |j }t
|| }d}d}xt|dkr||krx\|D ]T\}}|d dkr|d dkr|d | |kr|dks||kr|||< qW |d8 }qW t|dkr`t |j d }|d j||d jd| k}||fS |
} |
|7 }
q\W |szdS t|dkrxF| jD ]<}||j kr|d j||d jd| k}||fS qW dd |j D }|j |d d }|d j||d jd| 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.
Nr2 c S s g | ] }t |qS r )chr)rR cr r r rT . s z,Sniffer._guess_delimiter..
r rk c S s | d S )Nrk r )rS r r r H s z*Sniffer._guess_delimiter..)rD c s s | ]}|d V qdS )rk Nr )rR itemr r r rW M s z+Sniffer._guess_delimiter..g ?g?g{Gz?z%c r c S s g | ]\}}||fqS r r )rR kvr r r rT w s )r r )listfiltersplitrangeminrA rU countrX itemsrt removesumfloatr` sort)r rw rd asciiZ chunkLengthZ iterationZ
charFrequencyZmodesrx startendlinecharZ
metaFrequencyZfreqr ZmodeListZtotalZ consistencyZ thresholdr r rl r, rC r r r rb st
zSniffer._guess_delimiterc
C s t t|| j|}t|}t|}i }xt|D ] }d ||< q2W d}x|D ]}|dkrZP |d7 }t||krpqLxt|j D ]x} xJtt t
gD ]0}
y|
|| P W q t t fk
r Y qX qW t|| }
|
|| kr~|| d kr|
|| < q~|| = q~W qLW d} x|j
D ]~\} } t| tdkrLt|| | krB| d7 } n| d8 } n s2 @
2