֦i@ H d Z ddlZddlZddlmZmZmZmZmZm Z m
Z
m Z m Z m
Z
mZmZmZmZmZm Z ddlmZ ddlmZ g dZ G d d Z G d d
e Z ed
e G d d e Z ed
e G d de Z ede G d d Z G d d Z G d d Z y)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
QUOTE_STRINGS
QUOTE_NOTNULL__doc__)Dialect)StringIO)r r
r r r r r r r excel excel_tabr r r r r r
Snifferr r
DictReader
DictWriter unix_dialectc @ e Zd ZdZdZdZdZdZdZdZ dZ
dZ dZ d Z
d Zy)r zDescribe a CSV dialect.
This must be subclassed (see csv.excel). Valid attributes are:
delimiter, quotechar, escapechar, doublequote, skipinitialspace,
lineterminator, quoting.
FNc X | j t k7 rd| _ | j y )NT) __class__r _valid _validateselfs /usr/lib64/python3.12/csv.py__init__zDialect.__init__- s >>W $ DK c f t | y # t $ r}t t | d }~ww xY wN)_Dialect TypeErrorr str)r" es r# r zDialect._validate2 s, TN A- s 0+0)__name__
__module__ __qualname__r _namer delimiter quotechar
escapechar doublequoteskipinitialspacelineterminatorquotingr$ r r% r# r r sA
E
FIIJKNG
r% r c ( e Zd ZdZdZdZdZdZdZe Z
y)r z;Describe the usual properties of Excel-generated CSV files.,"TF
N) r, r- r. r r0 r1 r3 r4 r5 r r6 r7 r% r# r r 9 s$ EIIK NGr% r c e Zd ZdZdZy)r zEDescribe the usual properties of Excel-generated TAB-delimited files. N)r, r- r. r r0 r7 r% r# r r C s
OIr% r z excel-tabc ( e Zd ZdZdZdZdZdZdZe Z
y)r z:Describe the usual properties of Unix-generated CSV files.r9 r: TF
N) r, r- r. r r0 r1 r3 r4 r5 r
r6 r7 r% r# r r H s$ DIIK NGr% r unixc | e Zd Z ddZd Zed Zej d Zd Z e e
j Z y)r Nc |t | |u r t | }|| _ || _ || _ t ||g|i || _ || _ d| _ y Nr )iterlist _fieldnamesrestkeyrestvalr dialectline_num)r" f
fieldnamesrG rH rI argskwdss r# r$ zDictReader.__init__T sZ !d:&6*&D j)J% Q7$7$7
r% c | S r' r7 r! s r# __iter__zDictReader.__iter___ s r% c | j t | j | _ | j j | _ | j S # t $ r Y 2w xY wr' )rF nextr
StopIterationrJ r! s r# rL zDictReader.fieldnamesb sW #
#' #4 ,,
!
s A AAc || _ y r' )rF )r" values r# rL zDictReader.fieldnamesl s
r% c | j dk( r | j t | j }| j j | _ |g k( rt | j }|g k( rt t | j | }t
| j }t
| }||k r||d || j < |S ||kD r#| j |d D ] }| j ||< |S rC ) rJ rL rR r dictziplenrG rH )r" rowdlflrkeys r# __next__zDictReader.__next__p s ==A OO4;; ,,
Rit{{#C Ri T__c* +
!
X
7 !"#hAdllO "Wrs+ # ,r% )NNNr )
r, r- r. r$ rP propertyrL setterr_ classmethodtypes GenericAlias__class_getitem__r7 r% r# r r S sX AE ! !, $E$6$67r% r c T e Zd Z ddZd Zd Zd Zd Z ee j Z y)r c |t | |u r t | }|| _ || _ |j }|dvrt d|z || _ t ||g|i || _ y )N)raiseignorez-extrasaction (%s) must be 'raise' or 'ignore')rD rE rL rH lower
ValueError extrasactionr )r" rK rL rH rl rI rM rN s r# r$ zDictWriter.__init__ s{ !d:&6*&D j)J$ #))+ 2 2 L + , -
- ( Q7$7$7 r% c v t t | j | j }| j | S r' )rW rX rL writerow)r" headers r# writeheaderzDictWriter.writeheader s* c$//4??;<}}V$$r% c j dk( rSj j z
}|r4t ddj |D cg c]
}t | c} z fd j D S c c}w )Nrh z(dict contains fields not in fieldnames: z, c 3 V K | ] }j |j " y wr' )getrH ).0r^ rowdictr" s r# z+DictWriter._dict_to_list.. s! J/3 C ./s &))rl keysrL rk joinrepr)r" ru wrong_fieldsxs `` r#
_dict_to_listzDictWriter._dict_to_list st '"<<>DOO;L !K#'99|-L|!d1g|-L#M"N O OJ$//JJ .Ms A;c V | j j | j | S r' )r rn r| )r" ru s r# rn zDictWriter.writerow s" {{##D$6$6w$?@@r% c ` | j j t | j | S r' )r writerowsmapr| )r" rowdictss r# r zDictWriter.writerows s$ {{$$S););X%FGGr% N)r rh r ) r, r- r. r$ rp r| rn r rb rc rd re r7 r% r# r r s7 ?F 8%KAH $E$6$67r% r c 0 e Zd ZdZd ZddZd Zd Zd Zy) r ze
"Sniffs" the format of a CSV file (i.e. delimiter, quotechar)
Returns a Dialect object.
c g d| _ y )N)r9 r= ; :) preferredr! s r# r$ zSniffer.__init__ s 3r% Nc | j || \ }}}}|s| j || \ }}|s t d G d dt }||_ ||_ |xs d|_ ||_ |S )zI
Returns a dialect (or None) corresponding to the sample
z Could not determine delimiterc e Zd ZdZdZeZy) Sniffer.sniff..dialectsniffedr; N)r, r- r. r/ r5 r r6 r7 r% r# rI r s E #N#Gr% rI r: )_guess_quote_and_delimiter_guess_delimiterr r r3 r0 r1 r4 )r" sample
delimitersr1 r3 r0 r4 rI s r# sniffz
Sniffer.sniff s 226:F < ; +;*.*?*?@J+L 'I' 78 8 $g $ * % % ,#3 r% c , g }dD ]L }t j |t j t j z }|j | }|sL n |syi }i }d}j
} |D ]k }
| d dz
} |
| } | r|j
| d dz || < | d dz
} |
| } | r || |v r|j
| d dz || < | d dz
} |
| sg|dz
}m t ||j }
|r't ||j }|| |k( }|d k( rd
}nd
}d}t j d t j | |
d z t j }|j | rd
}nd}|
|||fS # t $ r Y w xY w# t $ r Y 'w xY w)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.
)zI(?P[^\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 delimspacer^ r? r z]((%(delim)s)|^)\W*%(quote)s[^%(delim)s\n]*%(quote)s[^%(delim)s\n]*%(quote)s\W*((%(delim)s)|$))r r TF) recompileDOTALL MULTILINEfindall
groupindexrs KeyErrormaxescapesearch)r" datar matchesrestrregexpquotesdelimsspacesr mnr^ r1 r r4 dq_regexpr3 s r# r z"Sniffer._guess_quote_and_delimiter s HE ZZryy2<<'?@F nnT*GH '&&
A7#a'AA$C $jja 01 4s
w'!+d
*cZ.? $jja 01 4s
w'!+ t! # & FJJ/ FJJ/E %e} 6 } E JJ (* %(8) L MNPll\ D ! K K;/?@@I
s$
E6F6 FF FFc t t d|j d }t d D cg c]
}t | }}t dt
| }d}i }i }i } d|} }
|
t
| k r |dz
}||
| D ]I } |D ]B }
|j |
i }| j |
}|j |d dz ||< |||
< D K |j D ] }
t ||
j }t
| dk( r |d d dk( r9t
| dkD rLt |d ||
< |j ||
||
d ||
d t d |D z
f||
< |d ||
< |j }t t ||z t
| }d
}d }t
| dk( rR||k\ rM|D ]/ \ }}|d dkD s|d dkD s|d |z |k\ s$|||v s+|| |< 1 |d z }t
| dk( r||k\ rMt
| dk( rLt | j d }|d j | |d j d
|z k( }||fS | }
| |z
} |
t
| k r | syt
| dkD rU| j D ]F }|| j v s|d j | |d j d
|z k( }||fc S | j D cg c] \ }}||f }}}|j! |d d }|d j | |d j d
|z k( }||fS c c}w c c}}w )a
The delimiter /should/ occur the same number of times on
each row. However, due to malformed data, it may not. We don't want
an all or nothing approach, so we allow for small variations in this
number.
1) build a table of the frequency of each character on every line.
2) build a table of frequencies of this frequency (meta-frequency?),
e.g. 'x occurred 5 times in 10 rows, 6 times in 1000 rows,
7 times in 2 rows'
3) use the mode of the meta-frequency to determine the /expected/
frequency for that character
4) find out how often the character actually meets that goal
5) the character that best meets its goal is the delimiter
For performance reasons, the data is evaluated in chunks, so it can
try and evaluate the smallest portion of the data possible, evaluating
additional chunks as necessary.
Nr?
r r c | d S )Nr r7 )r{ s r# z*Sniffer._guess_delimiter..N s 1Q4r% r c 3 & K | ] }|d yw)r Nr7 )rt items r# rv z+Sniffer._guess_delimiter..S s (CUTaUs g ?g?g{Gz?z%c )r r )rE filtersplitrangechrminrY rs countrw itemsr removesumfloatr sort)r" r r cascii chunkLength iteration
charFrequencymodesr startendlinechar
metaFrequencyfreqr modeListtotal consistency thresholdkvr r4 r[ s r# r zSniffer._guess_delimiter s & F4D!123!&s,AQ, "c$i(
sc$i NI U3 !D$1$5$5dB$?M ::d+D*7*;*;D!*Dq*HM$'*7M$'
" ( &**, ]4 0 6 6 89u:?uQx{a'7 u:>"%e "@E$K LLt-#(;q>5;q>%((CU(C%C4D #EE$K #((E$K - {{}H#kI 5s4yABE KIf+"{i'? $DAqtaxAaD1H qT%ZK 7 ' /1
?()F1I %
t#
f+"{i'? 6{a V[[]+A.$(GMM%$8$(GMM%%-$@%A /00 E ; Cc c$i f v;?^^
%(,Q
a(8(,Q
eai(@)A$ /00 $ %+LLN3N5Aa!AN3
b ! GMM% 0 GMM%%- 8 9'((_ -R 4s M8Mc t t | | j | }t | }t | }i }t | D ] }d ||< d}|D ]d }|dkD r n]|dz
}t | |k7 r t
|j D ]+ } t }
|
|| |
|| k7 s || |
|| < )|| = - f d} |j D ]C \ } } t | t r t || | k7 r| dz
} -| dz } 3 | || | dz } E | dkD S # t t f$ r t || }
Y w xY w# t t f$ r | dz
} Y w xY w)Nr r )r r r rR rY r rE rw complexrk
OverflowErrorr
isinstanceintr) )
r" r rdrro columns columnTypesicheckedrZ colthisType hasHeadercolTypes
r#
has_headerzSniffer.has_header s Xf%tzz&'9:cf+ w A$Q C| qLG3x7"K , , ./"- SX&
{3 //"3'/+3 C( ( , 0 6 ' - - /LC'3'vc{#w. NI NI#F3K( NI 0 1} ; #M2 - "3s8}H-0 #I. # NI#s$ D D= D:9D:=EEr' ) r, r- r. r r$ r r r r r7 r% r# r r s% 4
:IAXd)N= r% r ) r r rc _csvr r r r r r r r
r r r
r r r r r r( ior __all__r r r r r r r7 r% r# r s
% > G % i (7 &38 38l 8 8FW W r%