| Current Path : /usr/local/lib/python2.5/ |
FreeBSD hs32.drive.ne.jp 9.1-RELEASE FreeBSD 9.1-RELEASE #1: Wed Jan 14 12:18:08 JST 2015 root@hs32.drive.ne.jp:/sys/amd64/compile/hs32 amd64 |
| Current File : //usr/local/lib/python2.5/csv.pyo |
³ò
h”Rc @ s° d Z d d k Z d d k l Z l Z l Z l Z l Z l Z l Z l
Z
l Z l Z l
Z
l Z l Z l Z d d k l Z y d d k l Z Wn# e j
o d d k l Z n Xd d d d d
d d d
d d d d d d d d d d g Z d d d „ ƒ YZ d e f d „ ƒ YZ e d e ƒ d
e f d „ ƒ YZ e d e ƒ d d d „ ƒ YZ d d! d „ ƒ YZ y e Wn e j
o
e Z n Xd d" d „ ƒ YZ d S(# s+
csv.py - read/write/investigate CSV files
iÿÿÿÿN( 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 t excelt excel_tabR 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( sÇ 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+ | i t j o
t | _ n | i ƒ d S( N( t __class__R t Truet _validt _validate( t self( ( s /usr/local/lib/python2.5/csv.pyt __init__+ s
c C s< y t | ƒ Wn' t j
o } t t | ƒ ƒ ‚ n Xd S( N( t _Dialectt TypeErrorR t str( R t e( ( s /usr/local/lib/python2.5/csv.pyR 0 s N( t __name__t
__module__R
t _namet FalseR t Nonet delimitert quotechart
escapechart doublequotet skipinitialspacet lineterminatort quotingR R ( ( ( s /usr/local/lib/python2.5/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/local/lib/python2.5/csv.pyR 7 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/local/lib/python2.5/csv.pyR A s s excel-tabc B s/ e Z d d d d d „ Z d „ Z d „ Z RS( R c O sI | | _ | | _ | | _ t | | | | Ž | _ | | _ d | _ d S( Ni ( t
fieldnamest restkeyt restvalR t dialectt line_num( R t fR. R/ R0 R1 t argst kwds( ( s /usr/local/lib/python2.5/csv.pyR H s c C s | S( N( ( R ( ( s /usr/local/lib/python2.5/csv.pyt __iter__Q s c C sý | i i ƒ } | i d j o | | _ | i i ƒ } n | i i | _ x! | g j o | i i ƒ } qM Wt t | i | ƒ ƒ } t | i ƒ } t | ƒ } | | j o | | | | i <n7 | | j o) x& | i | D] } | i | | <qÞ Wn | S( N(
R t nextR. R$ R2 t dictt zipt lenR/ R0 ( R t rowt dt lft lrt key( ( s /usr/local/lib/python2.5/csv.pyR7 T s$
N( R R! R$ R R6 R7 ( ( ( s /usr/local/lib/python2.5/csv.pyR G s c B s5 e Z d d d d „ Z d „ Z d „ Z d „ Z RS( R t raiseR c O s[ | | _ | | _ | i ƒ d j o t d | ‚ n | | _ t | | | | Ž | _ d S( NR@ t ignores- extrasaction (%s) must be 'raise' or 'ignore'( R@ s ignore( R. R0 t lowert
ValueErrort extrasactionR ( R R3 R. R0 RD R1 R4 R5 ( ( s /usr/local/lib/python2.5/csv.pyR l s c C sy | i d j o8 x5 | i ƒ D]# } | | i j o
t d ‚ q q Wn g } | i D] } | | i | | i ƒ qV ~ S( NR@ s& dict contains fields not in fieldnames( RD t keysR. RC t getR0 ( R t rowdictt kt _[1]R? ( ( s /usr/local/lib/python2.5/csv.pyt
_dict_to_listw s
c C s | i i | i | ƒ ƒ S( N( R t writerowRJ ( R RG ( ( s /usr/local/lib/python2.5/csv.pyRK ~ s c C s= g } x$ | D] } | i | i | ƒ ƒ q
W| i i | ƒ S( N( t appendRJ R t writerows( R t rowdictst rowsRG ( ( s /usr/local/lib/python2.5/csv.pyRM s
( R R! R RJ RK RM ( ( ( s /usr/local/lib/python2.5/csv.pyR k 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/local/lib/python2.5/csv.pyR ’ s c C sŽ | i | | ƒ \ } } } | p | i | | ƒ \ } } n | p
t d ‚ n d t f d „ ƒ Y} | | _ | p d | _ | | _ | S( sI
Returns a dialect (or None) corresponding to the sample
s Could not determine delimiterR1 c B s e Z d Z d Z e Z e Z RS( t sniffeds
( R R! R" R* R R+ R# R( ( ( ( s /usr/local/lib/python2.5/csv.pyR1 ¥ s R- ( t _guess_quote_and_delimitert _guess_delimiterR R R% R& R) ( R t samplet
delimitersR& R% R) R1 ( ( s /usr/local/lib/python2.5/csv.pyt sniff— s
c C sÿ g } xE d D]= } t i | t i t i Bƒ } | i | ƒ } | o Pq
q
W| p d Sn h } h } d } x | D]} | i d d }
| |
} | o | i | d ƒ d | | <n y | i d d }
| |
} Wn t j
o
qv n X| o8 | d j p
| | j o | i | d ƒ d | | <n y | i d
d }
Wn t j
o
qv n X| |
o | d 7} qv qv Wt | d „ | i
ƒ ƒ } | oF t | d „ | i
ƒ ƒ }
| |
| j } |
d
j o
d }
qòn
d }
d } | |
| 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> ?)sD (?P<delim>>[^\w
"'])(?P<space> ?)(?P<quote>["']).*?(?P=quote)(?:$|
)s* (?:^|
)(?P<quote>["']).*?(?P=quote)(?:$|
)R i t quotei t delimt spacec S s | | | | j o | p | S( ( ( t at bt quotes( ( s /usr/local/lib/python2.5/csv.pyt <lambda>ã s c S s | | | | j o | p | S( ( ( R] R^ t delims( ( s /usr/local/lib/python2.5/csv.pyR` ç s 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( R Ni ( t ret compilet DOTALLt MULTILINEt findallR$ t
groupindexRF t KeyErrort reduceRE ( R t dataRX t matchest restrt regexpR_ Ra t spacest mt nR? R& R[ R) ( ( s /usr/local/lib/python2.5/csv.pyRU ´ sZ
!
c C s: t d | i d ƒ ƒ } g } t d ƒ D] } | t | ƒ q) ~ } t d t | ƒ ƒ } d } h } h } h }
d t | t | ƒ ƒ } } x¥| t | ƒ j o‘| d 7} xk | | | !D]\ }
xS | D]K } | i | h ƒ } |
i | ƒ } | i | d ƒ d | | <| | | <qÉ Wq¼ WxÓ | i ƒ D]Å } | | i
ƒ } t | ƒ d j o | d d d j o q)n t | ƒ d j o_ t d „ | ƒ | | <| i | | ƒ | | d | | d t d „ | ƒ d f | | <q)| d | | <q)W| i
ƒ } t
| | ƒ } d } d } x© t |
ƒ d j o• | | j oˆ xw | D]o \ } } | d d j oR | d d j oA | d | | j o( | d j p
| | j o | |
| <q³qDqDW| d
8} q Wt |
ƒ d j oH |
i ƒ d } | d i | ƒ | d i d | ƒ j } | | f Sn | } | | 7} q‘ W|
p d Sn t |
ƒ d j oc x` | i D]Q } | |
i ƒ j o8 | d i | ƒ | d i d | ƒ j } | | f SqbqbWn g } |
i
ƒ D] \ } } | | | f qÌ~ } | i ƒ | d
d } | d i | ƒ | d i d | ƒ j } | | f S( s¼
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 freqencies 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 j o | p | S( i ( ( R] R^ ( ( s /usr/local/lib/python2.5/csv.pyR` # s c S s d | d | d f S( i i ( ( R] R^ ( ( s /usr/local/lib/python2.5/csv.pyR` ) s g ð?gÍÌÌÌÌÌì?g{®Gáz„?s %c R iÿÿÿÿN( R i ( t filterR$ t splitt ranget chrt minR: RF t countRE t itemsRi t removet floatRS t sort( R Rj RX RI t ct asciit chunkLengtht iterationt
charFrequencyt modesRa t startt endt linet chart
metaFrequencyt freqRw t modeListt totalt consistencyt thresholdRH t vR[ R) R< t _[2]( ( s /usr/local/lib/python2.5/csv.pyRV ô s† -
(
"
3
c
C s* t t | ƒ | i | ƒ ƒ } | i ƒ } t | ƒ } h } x t | ƒ D] } d | | <qI Wd } x | D]} | d j o Pn | d 7} t | ƒ | j o qj n x | i ƒ D]´ } xY t t t
t g D]5 }
y |
| | ƒ PWqÌ t t
f j
o qÌ XqÌ Wt | | ƒ }
|
t j o
t }
n |
| | j o* | | d j o |
| | <qg| | =q³ q³ Wqj Wd } x¨ | i ƒ D]š \ } } t | ƒ t d ƒ j o3 t | | ƒ | j o | d 7} q | d 8} q‚y | | | ƒ Wn# t t f j
o | d 7} q‚X| d 8} q‚W| d j S( Ni i i ( R R RY R7 R: Rs R$ RE t intt longRy t complexRC t
OverflowErrorRw t typeR (
R RW t rdrt headert columnst columnTypest it checkedR; t colt thisTypet hasHeadert colType( ( s /usr/local/lib/python2.5/csv.pyt
has_header] sX
N( R R! R
R R$ RY RU RV Rœ ( ( ( s /usr/local/lib/python2.5/csv.pyR s @ i( ( ( ( ( R
Rb 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 NameErrorRy R ( ( ( s /usr/local/lib/python2.5/csv.pys <module> s. ^
$