HOME

�
m��fc@s�
dZd
dl
Z
d
dlmZ
d
dlmZmZmZmZm	Z	m
Z
mZmZm
Z
mZmZmZmZmZ
d
dlmZ
yd
dlmZ
Wn!ek
r�


d
dlmZ
n
Xddd	d
ddd
dddddddddddddgZdd"d��YZdef
d��YZe	de�
def
d��YZe	de�
dd#d��YZdd$d ��YZye
Wnek
r�



eZn
Xdd%d!��YZdS(&s+
csv.py - read/write/investigate CSV files
i����N(
treduce(tErrort__version__twritertreadertregister_dialecttunregister_dialecttget_dialectt
list_dialectstfield_size_limitt
QUOTE_MINIMALt	QUOTE_ALLtQUOTE_NONNUMERICt
QUOTE_NONEt__doc__(
tDialect(
tStringIOR
RRR
R
RRtexcelt	excel_tabR	RRRRRtSnifferRRt
DictReadert
DictWriterc
BsVeZ
dZd
ZeZdZdZdZ	dZ
dZdZdZ
d�Zd�ZRS(s�Describe an Excel dialect.

    This must be subclassed (see csv.excel).  Valid attributes are:
    delimiter, quotechar, escapechar, doublequote, skipinitialspace,
    lineterminator, quoting.

    tc

Cs)|jt
krt|_n|j�
dS(
N(t	__class__RtTruet_validt	_validate(
tself((s/usr/lib64/python2.7/csv.pyt__init__-s


c
Cs:yt|�

Wn%t
k
r5
}

tt|
�
�
�
n
XdS(
N(t_Dialectt	TypeErrorR
tstr(Rt
e((s/usr/lib64/python2.7/csv.pyR2s


N(t__name__t
__module__Rt_nametFalseRtNonet	delimitert	quotechart
escapechartdoublequotetskipinitialspacetlineterminatortquotingRR(((s/usr/lib64/python2.7/csv.pyRs







	c
Bs2eZ
dZd
ZdZeZeZdZ	e
ZRS(s;Describe the usual properties of Excel-generated CSV files.t
,t
"s
(R!R"RR&R'RR)R$R*R+R
R,(((s/usr/lib64/python2.7/csv.pyR9s






c
BseZ
dZd
ZRS(sEDescribe the usual properties of Excel-generated TAB-delimited files.s
	(R!R"RR&(((s/usr/lib64/python2.7/csv.pyRCs

s	excel-tabcBsPeZ
ddddd
�Zd�Zed��
Zejd��
Zd�ZRS(RcOsI||_||_
||_t|
|||�|_||_d
|_dS(Ni(t_fieldnamestrestkeytrestvalRtdialecttline_num(Rt
ft
fieldnamesR0R1R2targstkwds((s/usr/lib64/python2.7/csv.pyRJs	
	
	

	
c


Cs|S(
N((
R((s/usr/lib64/python2.7/csv.pyt__iter__Ss
c

CsR|jdkr<y|jj�|_Wq<tk
r8


q<Xn|jj|_|jS(
N(R/R%Rtnextt
StopIterationR3(
R((s/usr/lib64/python2.7/csv.pyR5Vs






cCs
|
|_dS(
N(
R/(Rtvalue((s/usr/lib64/python2.7/csv.pyR5`sc
Cs�|jd
kr|j

n|jj�}
|jj|_x|
gkrX|jj�}
q:Wtt|j
|
��
}t|j
�
}t|
�
}||kr�|
|||j<n4||kr�x%|j
|D]}|j||<q�Wn|S(Ni(	R3R5RR9tdicttziptlenR0R1(Rtrowt
dtlftlrtkey((s/usr/lib64/python2.7/csv.pyR9ds













N(	R!R"R%RR8tpropertyR5tsetterR9(((s/usr/lib64/python2.7/csv.pyRIs
	
	
cBs>eZ
dd
dd�Zd�Zd�Zd�Zd�ZRS(RtraiseRcOsY||_||_
|j�dkr4td|�n||_t|
|||�|_dS(NRFtignores-extrasaction (%s) must be 'raise' or 'ignore'(RFsignore(R5R1tlowert
ValueErrortextrasactionR(RR4R5R1RJR2R6R7((s/usr/lib64/python2.7/csv.pyR|s	
	





	
c
Cs,tt
|j|j��
}
|j|
�

dS(
N(R<R=R5twriterow(Rtheader((s/usr/lib64/python2.7/csv.pytwriteheader�s

cCs�|jd
kr\g|
D]}||j
kr|^q}|r\tddj|�
�
�
q\ng|j
D]}|
j||j�^qfS(NRFs(dict contains fields not in fieldnames: s, (RJR5RItjointgetR1(Rtrowdictt
ktwrong_fieldsRC((s/usr/lib64/python2.7/csv.pyt
_dict_to_list�s

(



cCs|jj
|j|
�
�
S(
N(RRKRS(RRP((s/usr/lib64/python2.7/csv.pyRK�s
cCs=g}x$|
D]}|j|j
|�
�

q
W|jj|�
S(
N(tappendRSRt	writerows(RtrowdictstrowsRP((s/usr/lib64/python2.7/csv.pyRU�s




(R!R"RRMRSRKRU(((s/usr/lib64/python2.7/csv.pyR{s


			cBs>eZ
dZd
�Zdd�
Zd�Zd�Zd�ZRS(se
    "Sniffs" the format of a CSV file (i.e. delimiter, quotechar)
    Returns a Dialect object.
    c

Csd
ddddg|_dS(NR-s
	t
;t
 t
:(
t	preferred(
R((s/usr/lib64/python2.7/csv.pyR�scCs�|j|
|�\}}}}|s?|j
|
|�\}}n|sQtd
�ndtf
d��Y}||_||_|p�d|_||_|S(sI
        Returns a dialect (or None) corresponding to the sample
        sCould not determine delimiterR2c
BseZ
dZd
ZeZRS(tsniffeds
(R!R"R#R+R
R,(((s/usr/lib64/python2.7/csv.pyR2�s


R.(t_guess_quote_and_delimitert_guess_delimiterR
RR)R&R'R*(Rtsamplet
delimitersR'R)R&R*R2((s/usr/lib64/python2.7/csv.pytsniff�s

	

	
	
	cCs<g}xCdD];}tj
|tjtjB�}|j|
�
}|r
Pq
q
W|sbdtddfSi}i}d}x
|D]�}	|jdd}
|	|
}|r�|j|d�d||<ny|jd	d}
|	|
}Wnt	k
r�


q{n
X|r0
|dks
||kr0
|j|d�d||<ny|jd
d}
Wnt	k
r[



q{n
X|	|
r{|d7}q{q{Wt
|d�
|j��}|r�
t
|d�
|j��}
||
|k}|
d
kr�
d}
q�
nd}
d}tj
di|
d	6|d6tj�}|j|
�
r&t
}nt}|||
|fS(s�

        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.
        sF(?P<delim>[^\w
"'])(?P<space> ?)(?P<quote>["']).*?(?P=quote)(?P=delim)sC(?:^|
)(?P<quote>["']).*?(?P=quote)(?P<delim>[^\w
"'])(?P<space> ?)sD(?P<delim>>[^\w
"'])(?P<space> ?)(?P<quote>["']).*?(?P=quote)(?:$|
)s*(?:^|
)(?P<quote>["']).*?(?P=quote)(?:$|
)Ritquotei
tdelimtspacecSs||||
kr|p|
S(
N((t
at
btquotes((s/usr/lib64/python2.7/csv.pyt<lambda>�s
cSs||||
kr|p|
S(
N((ReRftdelims((s/usr/lib64/python2.7/csv.pyRh�s
s

s]((%(delim)s)|^)\W*%(quote)s[^%(delim)s\n]*%(quote)s[^%(delim)s\n]*%(quote)s\W*((%(delim)s)|$)(sF(?P<delim>[^\w
"'])(?P<space> ?)(?P<quote>["']).*?(?P=quote)(?P=delim)sC(?:^|
)(?P<quote>["']).*?(?P=quote)(?P<delim>[^\w
"'])(?P<space> ?)sD(?P<delim>>[^\w
"'])(?P<space> ?)(?P<quote>["']).*?(?P=quote)(?:$|
)s*(?:^|
)(?P<quote>["']).*?(?P=quote)(?:$|
)N(tretcompiletDOTALLt	MULTILINEtfindallR$R%t
groupindexROtKeyErrorRtkeystsearchR(RtdataR`tmatchestrestrtregexpRgRitspacest
mt
nRCR'RcR*t	dq_regexpR)((s/usr/lib64/python2.7/csv.pyR]�s`









































	

	cCstd|
jd
�
�}
gtd�
D]}t|�
^q%}tdt|
�
�}d}i}i}i}	dt|t|
�
�}
}x�|
t|
�
kr|d7}xk|
|
|!D]\}xS|D]K}
|j|
i�}|j|
�
}|j|d�d||<|||
<q�Wq�Wx�|j	�D]�}
||
j
�}t|�
dkrb
|dddkrb
q 
nt|�
dkr�
td�|�||
<|j||
�

||
d||
dtd�|�df||
<q 
|d||
<q 
W|j
�}t
||�
}d}d	}x�t|	�
dkr�||kr�xp|D]h\}}|ddkr4|ddkr4|d||kr�|dks�||kr�||	|<q�q4q4W|d
8}qWt|	�
dkr|	j	�d}|
dj|�
|
djd|�
k}||fS|}
||7}q�W|	s"dSt|	�
dkr�xZ|jD]L}||	j	�kr>|
dj|�
|
djd|�
k}||fSq>Wng|	j
�D]\}}||f^q�}|j�
|d
d}|
dj|�
|
djd|�
k}||fS(s�
        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.
        s

ii
ii
cSs|d
|
d
kr|p|
S(Ni
((ReRf((s/usr/lib64/python2.7/csv.pyRhD
scSsd
|d|
dfS(Nii
((ReRf((s/usr/lib64/python2.7/csv.pyRhJ
sg�?g�������?g{�G�z�?s%c Ri����N(Ri(tfilterR%tsplittrangetchrtminR>ROtcountRqtitemsRtremovetfloatR[tsort(RRsR`t
ctasciitchunkLengtht	iterationt
charFrequencytmodesRitstarttendtlinetchart
metaFrequencytfreqR�tmodeListttotaltconsistencyt	thresholdRQt
vRcR*R@((s/usr/lib64/python2.7/csv.pyR^
sx%














&

	



	


!

 















+




c
	Cstt
|
�
|j|
�
�}|j�}t|�
}i}xt|�
D]}d||<qIWd
}x�|D]�}|dkr�Pn|d7}t|�
|kr�qjnx�|j�D]�}	xWtt	t
tgD]3}
y|
||	�

PWq�tt
fk
r�


q�Xq�Wt||	�
}
|
t	kr$
t}
n|
||	kr�||	dkrQ
|
||	<q[
||	=q�q�WqjWd
}x�|j�D]�\}	}t|�
td
�
kr�
t||	�
|kr�
|d7}q
|d8}qv
y|||	�

Wn!ttfk
r�



|d7}qv
X|d8}qv
W|d
kS(Niii
(RRRaR9R>R}R%RqtinttlongR�tcomplexRIt
OverflowErrorR�ttypeR(
RR_trdrRLtcolumnstcolumnTypest
itcheckedR?tcoltthisTypet	hasHeadertcolType((s/usr/lib64/python2.7/csv.pyt
has_header~
sN














	











N(	R!R"RRR%RaR]R^R�(((s/usr/lib64/python2.7/csv.pyR�s
		L	i((((( RRjt	functoolsRt_csvR
RRRRRRRR	R
RRR
RRt	cStringIORtImportErrort__all__RRRRR�t	NameErrorR�R(((s/usr/lib64/python2.7/csv.pyt<module>s2

^





	



2"