z fc @ s d Z d d l Z d d l m Z d d l m Z m Z m Z m Z m Z m
Z
m Z m Z m
Z
m Z m Z m Z m Z m Z d d l m Z y d d l m Z Wn! e k
r d d l m Z n Xd d d d
d d d
d d d d d d d d d d d d d g Z d d" d YZ d e f d YZ e d e d e f d YZ e d e d d# d YZ d d$ d YZ y e Wn e k
re Z n Xd d% d! YZ d S(& s+
csv.py - read/write/investigate CSV files
iN( t reduce( t Errort __version__t writert readert register_dialectt unregister_dialectt get_dialectt
list_dialectst field_size_limitt
QUOTE_MINIMALt QUOTE_ALLt QUOTE_NONNUMERICt
QUOTE_NONEt __doc__( t Dialect( t StringIOR
R R R
R R R t excelt excel_tabR R R R R R t SnifferR R t
DictReadert
DictWriterc B sV e Z d Z d Z e Z d Z d Z d Z d Z
d Z d Z d Z
d Z d Z RS( s Describe an Excel dialect.
This must be subclassed (see csv.excel). Valid attributes are:
delimiter, quotechar, escapechar, doublequote, skipinitialspace,
lineterminator, quoting.
t c C s) | j t k r t | _ n | j d S( N( t __class__R t Truet _validt _validate( t self( ( s /usr/lib64/python2.7/csv.pyt __init__- s c C s: y t | Wn% t k
r5 } t t | n Xd S( N( t _Dialectt TypeErrorR t str( R t e( ( s /usr/lib64/python2.7/csv.pyR 2 s N( t __name__t
__module__R t _namet FalseR t Nonet delimitert quotechart
escapechart doublequotet skipinitialspacet lineterminatort quotingR R ( ( ( s /usr/lib64/python2.7/csv.pyR s c B s2 e Z d Z d Z d Z e Z e Z d Z e
Z RS( s; Describe the usual properties of Excel-generated CSV files.t ,t "s
( R! R" R R& R' R R) R$ R* R+ R
R, ( ( ( s /usr/lib64/python2.7/csv.pyR 9 s c B s e Z d Z d Z RS( sE Describe the usual properties of Excel-generated TAB-delimited files.s ( R! R" R R& ( ( ( s /usr/lib64/python2.7/csv.pyR C s s excel-tabc B sP e Z d d d d d Z d Z e d Z e j d Z d Z RS( R c O sI | | _ | | _ | | _ t | | | | | _ | | _ d | _ d S( Ni ( t _fieldnamest restkeyt restvalR t dialectt line_num( R t ft
fieldnamesR0 R1 R2 t argst kwds( ( s /usr/lib64/python2.7/csv.pyR J s c C s | S( N( ( R ( ( s /usr/lib64/python2.7/csv.pyt __iter__S s c C sR | j d k r< y | j j | _ Wq< t k
r8 q< Xn | j j | _ | j S( N( R/ R% R t nextt
StopIterationR3 ( R ( ( s /usr/lib64/python2.7/csv.pyR5 V s
c C s
| | _ d S( N( R/ ( R t value( ( s /usr/lib64/python2.7/csv.pyR5 d s c C s | j d k r | j n | j j } | j j | _ x | g k rX | j j } q: Wt t | j | } t | j } t | } | | k r | | | | j <n4 | | k r x% | j | D] } | j | | <q Wn | S( Ni ( R3 R5 R R9 t dictt zipt lenR0 R1 ( R t rowt dt lft lrt key( ( s /usr/lib64/python2.7/csv.pyR9 h s
N( R! R" R% R R8 t propertyR5 t setterR9 ( ( ( s /usr/lib64/python2.7/csv.pyR I s c B s> e Z d d d d Z d Z d Z d Z d Z RS( R t raiseR c O sY | | _ | | _ | j d k r4 t d | n | | _ t | | | | | _ d S( NRF t ignores- extrasaction (%s) must be 'raise' or 'ignore'( RF RG ( R5 R1 t lowert
ValueErrort extrasactionR ( R R4 R5 R1 RJ R2 R6 R7 ( ( s /usr/lib64/python2.7/csv.pyR s
c C s, t t | j | j } | j | d S( N( R< R= R5 t writerow( R t header( ( s /usr/lib64/python2.7/csv.pyt writeheader s c C s | j d k ru g | D] } | | j k r | ^ q } | ru t d d j g | D] } t | ^ qP qu n g | j D] } | j | | j ^ q S( NRF s( dict contains fields not in fieldnames: s , ( RJ R5 RI t joint reprt getR1 ( R t rowdictt kt wrong_fieldst xRC ( ( s /usr/lib64/python2.7/csv.pyt
_dict_to_list s (2c C s | j j | j | S( N( R RK RU ( R RQ ( ( s /usr/lib64/python2.7/csv.pyRK s c C s= g } x$ | D] } | j | j | q
W| j j | S( N( t appendRU R t writerows( R t rowdictst rowsRQ ( ( s /usr/lib64/python2.7/csv.pyRW s
( R! R" R RM RU RK RW ( ( ( s /usr/lib64/python2.7/csv.pyR s
c B s> e Z d Z d Z d d Z d Z d Z d Z RS( se
"Sniffs" the format of a CSV file (i.e. delimiter, quotechar)
Returns a Dialect object.
c C s d d d d d g | _ d S( NR- s t ;t t :( t preferred( R ( ( s /usr/lib64/python2.7/csv.pyR s c C s | j | | \ } } } } | s? | j | | \ } } n | sQ t d n d t f d Y} | | _ | | _ | p d | _ | | _ | S( sI
Returns a dialect (or None) corresponding to the sample
s Could not determine delimiterR2 c B s e Z d Z d Z e Z RS( t sniffeds
( R! R" R# R+ R
R, ( ( ( s /usr/lib64/python2.7/csv.pyR2 s R. ( t _guess_quote_and_delimitert _guess_delimiterR R R) R& R' R* ( R t samplet
delimitersR' R) R& R* R2 ( ( s /usr/lib64/python2.7/csv.pyt sniff s c C sE g } xC d D]; } t j | t j t j B } | j | } | r
Pq
q
W| sb d t d d f Si } i } d } x | D] } | j d d }
| |
} | r | j | d d | | <n y | j d d }
| |
} Wn t k
r q{ n X| r0| d k s| | k r0| j | d d | | <n y | j d
d }
Wn t k
r[q{ n X| |
r{ | d 7} q{ q{ Wt
| d | j } | rt
| d | j }
| |
| k } |
d
k rd }
qn d }
d } t j d i t j |
d 6| d 6t j } | j
| r/t } n t } | | |
| f S( 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> ?)sC (?P<delim>[^\w
"'])(?P<space> ?)(?P<quote>["']).*?(?P=quote)(?:$|
)s* (?:^|
)(?P<quote>["']).*?(?P=quote)(?:$|
)R i t quotei t delimt spacec S s | | | | k r | p | S( N( ( t at bt quotes( ( s /usr/lib64/python2.7/csv.pyt <lambda> s c S s | | | | k r | p | S( N( ( Rg Rh t delims( ( s /usr/lib64/python2.7/csv.pyRj s s
s] ((%(delim)s)|^)\W*%(quote)s[^%(delim)s\n]*%(quote)s[^%(delim)s\n]*%(quote)s\W*((%(delim)s)|$)( sF (?P<delim>[^\w
"'])(?P<space> ?)(?P<quote>["']).*?(?P=quote)(?P=delim)sC (?:^|
)(?P<quote>["']).*?(?P=quote)(?P<delim>[^\w
"'])(?P<space> ?)sC (?P<delim>[^\w
"'])(?P<space> ?)(?P<quote>["']).*?(?P=quote)(?:$|
)s* (?:^|
)(?P<quote>["']).*?(?P=quote)(?:$|
)N( t ret compilet DOTALLt MULTILINEt findallR$ R% t
groupindexRP t KeyErrorR t keyst escapet searchR ( R t dataRb t matchest restrt regexpRi Rk t spacest mt nRC R' Re R* t dq_regexpR) ( ( s /usr/lib64/python2.7/csv.pyR_ sb
' c C s t d | j d } g t d D] } t | ^ q% } t d t | } d } i } i } i } d t | t | }
} x|
t | k r| d 7} xk | |
| !D]\ } xS | D]K }
| j |
i } | j |
} | j | d d | | <| | |
<q Wq Wx | j D] }
| |
j
} t | d k rb| d d d k rbq n t | d k rt d | | |
<| j | |
| |
d | |
d t d | d f | |
<q | d | |
<q W| j
} t
| | } d } d } x t | d k r| | k rxp | D]h \ } } | d d k r4| d d k r4| d | | k r| d k s| | k r| | | <qq4q4W| d
8} qWt | d k r| j d } | d j | | d j d | k } | | f S| }
| | 7} q W| s"d St | d k rxZ | j D]L } | | j k r>| d j | | d j d | k } | | f Sq>Wn g | j
D] \ } } | | f ^ q} | j | d
d } | d j | | d j d | k } | | f S( 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
i i
i i c S s | d | d k r | p | S( Ni ( ( Rg Rh ( ( s /usr/lib64/python2.7/csv.pyRj I R c S s d | d | d f S( Ni i ( ( Rg Rh ( ( s /usr/lib64/python2.7/csv.pyRj O R g ?g?g{Gz?s %c R iN( R i ( t filterR% t splitt ranget chrt minR> RP t countRs t itemsR t removet floatR] t sort( R Rv Rb t ct asciit chunkLengtht iterationt
charFrequencyt modesRk t startt endt linet chart
metaFrequencyt freqR t modeListt totalt consistencyt thresholdRR t vRe R* R@ ( ( s /usr/lib64/python2.7/csv.pyR` sx %
&
!
+
c
C s t t | | j | } | j } t | } i } x t | D] } d | | <qI Wd } x | D] } | d k r Pn | d 7} t | | k r qj n x | j D] } xW t t t
t g D]3 }
y |
| | PWq t t
f k
r q Xq Wt | | }
|
t k r$t }
n |
| | k r | | d k rQ|
| | <q[| | =q q Wqj Wd } x | j D] \ } } t | t d k rt | | | k r| d 7} q
| d 8} qvy | | | Wn! t t f k
r| d 7} qvX| d 8} qvW| d k S( Ni i i ( R R Rc R9 R> R R% Rs t intt longR t complexRI t
OverflowErrorR t typeR (
R Ra t rdrRL t columnst columnTypest it checkedR? t colt thisTypet hasHeadert colType( ( s /usr/lib64/python2.7/csv.pyt
has_header sN
N( R! R" R R R% Rc R_ R` R ( ( ( s /usr/lib64/python2.7/csv.pyR s M i( ( ( ( ( R Rl t functoolsR t _csvR R R R R R R R R R
R R R
R R t cStringIOR t ImportErrort __all__R R R R R t NameErrorR R ( ( ( s /usr/lib64/python2.7/csv.pyt <module> s2 ^
6"
All system for education purposes only. For more tools: Telegram @jackleet