$HJjD 4dZddlZddlZddlZddlZddlmZmZmZm Z ddl Z ddl Z ddl Z ddl Z ddlZddlmZmZddlmZddlmZgdZeee j0fZeeeeefZej6eeeeeffZd ed efd ZGd d ZGddZ Gdde Z!Gdde Z"Gdde"Z# d#dedee$dee$d eed ef dZ%e%Z&dede e'eegedeefffdZ(dedeefdZ)dede e*ge$fd e'fd Z+Gd!d"Z,y)$aSupport for reading delimiter-separated value files. This module contains unicode aware replacements for :func:`csv.reader` and :func:`csv.writer`. It was stolen/extracted from the ``csvkit`` project to allow re-use when the whole ``csvkit`` package isn't required. The original implementations were largely copied from `examples in the csv module documentation `_. .. seealso:: http://en.wikipedia.org/wiki/Delimiter-separated_values N)OptionalUnionIOCallable)Iterable Generator)utils)Dialect) UnicodeWriter UnicodeReaderUnicodeReaderWithLineNumberUnicodeDictReaderNamedTupleReaderiterrowsrewriteadd_rowsfilter_rows_as_dictencodingreturnc@tj|jS)z#Normalize the name of the encoding.)codecslookupname)rs R/Users/ahmed/devFolder/claude-voice/.venv/lib/python3.12/site-packages/csvw/dsv.pynormalize_encodingr*s == " ' ''ceZdZdZ ddeedeeeeffdZ dZ dee fdZ d Z d eeedffd Zd eeeeeffd Zy)r u Write Unicode data to a csv file. :param f: The target to which to write the data; a local path specified as `str` or `pathlib.Path` or `None`, in which case the data, formatted as DSV can be retrieved via :meth:`~UnicodeWriter.read` :param dialect: Either a dialect name as recognized by `csv.writer` or a :class:`~Dialect` instance for dialect customization beyond what can be done with `csv.writer`. :param kw: Keyword arguments passed through to `csv.writer`. .. code-block:: python >>> from csvw import UnicodeWriter >>> with UnicodeWriter('data.tsv', delimiter=' ') as writer: ... writer.writerow(['ä', 'ö', 'ü']) Nfdialectc |||_|jdd|_t|trB|j |_|j |_|jj|n||_|r||jd<t|j|_|jjd|_ |jrO|jjdtjk7r#t|jd|jzfd}nd}||_d |_d |_d|_y) Nrutf-8r escapecharquotingch|Dcgc]"}t||r|j||n|$c}Scc}wN) isinstancereplace)row_type_old_newss r_escapedoubledz.UnicodeWriter.__init__.._escapedoubledVs:WZZVYQRAu1E $-1LVYZZZs'/c|Sr')r*s rr/z.UnicodeWriter.__init__.._escapedoubled\s rFr)rpoprr(r python_encodingas_python_formatting_parameterskwupdatergetr#csv QUOTE_NONEstrr/_close _rows_writtenwriter)selfrr r5r/s r__init__zUnicodeWriter.__init__Bs z73 gw '#33DM==?DG GGNN2 DG%, "*4==9 ''++l3 ??tww{{95G&)$(OO$%$7 [  ,  rct|jttjfrxt|jtjrt|j|_t j |jd|jd|_d|_n'|jt jd|_tj|jfi|j|_ |S)Nwt)rnewlineT)rC) r(rr:pathlibPathioopenrr;StringIOr8r=r5r>s r __enter__zUnicodeWriter.__enter__cs dffsGLL1 2$&&',,/TVVWWTVVTDMM2NDFDK VV^[[,DFjj34773  rrct|jdr|jjdt|jdr)|jjj dSy)z If the writer has been initialized passing `None` as target, the CSV data as `bytes` can be retrieved calling this method. seekrreadr"N)hasattrrrLrMencoderIs rrMzUnicodeWriter.readpsM 4666 " FFKKN 4666 "66;;=''0 0rcR|jr|jjyyr'r;rclose)r>type_value tracebacks r__exit__zUnicodeWriter.__exit__{ ;; FFLLN rr*c|jj|j||xjdz c_y)zWrite multiple rows.r N)r=writerowr/r<)r>r*s rrYzUnicodeWriter.writerows0 T0056 arrowsct|D]f\}}t|tr@|dk(r+|js|j |j |j }|j |hy)aL Writes each row in `rows` formatted as CSV row. This behaves as [`csvwriter.writerows`](https://docs.python.org/3/library/csv.html#csv.csvwriter.writerows) except when an iterable of `dict` objects is passed. In that case, it is assumed that all items in `rows` are `dict`s and all have the same keys in the same order (as what would be read by `UnicodeDictReader`). Then, the keys of the first item are written as header row and the values of each row are written as subsequent rows. :param rows: The data to be written. rN) enumerater(dictr<rYkeysvalues)r>rZir*s r writerowszUnicodeWriter.writerowssX oFAs#t$6$"4"4MM#((*-jjl MM#  &r)NN)__name__ __module__ __qualname____doc__rPathTyperr r:r?rJbytesrMrVrrYtuplelistr]rar1rrr r /s(%)59!eGSL12B  huo  HU39%56 huUD$->'?@rr cReZdZdZ d dedeeeeffdZ dZ dZ dZ d Z d Zy) r a Read Unicode data from a csv file. :param f: The source from which to read the data; a local path specified as `str` or `pathlib.Path`, a file-like object or a `list` of lines. :param dialect: Either a dialect name as recognized by `csv.reader` or a :class:`~Dialect` instance for dialect customization beyond what can be done with `csv.writer`. :param kw: Keyword arguments passed through to `csv.reader`. .. code-block:: python >>> with UnicodeReader('tests/fixtures/frictionless-data.csv', delimiter='|') as reader: ... for row in reader: ... print(row) ... break ... ['FK', 'Year', 'Location name', 'Value', 'binary', 'anyURI', 'email', 'boolean', 'array', 'geojson'] Nrr c ||_t|jdd|_|jdd|_t |t r|nd|_d|_d|_ |jrL|jj|_|j|_ |jj|n||_ |r||jd<d|_g|_|jdk(rd|_|j|_y)Nrz utf-8-siglineterminatorr Fr")rrr2rrCr(r r linenoreaderr3r4r5r6r;comments_reader_encoding)r>rr r5s rr?zUnicodeReader.__init__s *266*k+JK vv.5 ",Wg">wD   << LL88DM==?DG GGNN2 DG%, "  ==G #'DM !% rct|jttjfrt|jtjrt|j|_t j |jd|j|jxsd|_d|_ nlt|jdsVg}|jD]>}|jt|tr|j|jn|@||_tj|jfi|j |_d|_|S)NrtrB)moderrCTrM)r(rr:rDrErFrGrrCr;rNappendrgdecoder8rnr5rm)r>lineslines rrJzUnicodeReader.__enter__s dffsGLL1 2$&&',,/TVVWWTVV$PTP\P\Pb`bcDFDK(E :dE;RT[[7X\]DFjj34773   rc|xjdz c_t|jDcgc]/}t|tr|n|j |j 1}}|xjtd|Dz c_|Scc}w)Nr c3PK|]}t|jd yw) N)ricount).0r.s r z*UnicodeReader._next_row..s<147==.s$&)rmnextrnr(r:rvrpsum)r>r.r*s r _next_rowzUnicodeReader._next_rows} q $++&(&As#A$2G2G)H H& ( s<<<<  (s4B c|j}|jrK|r>|jjr(|dj|jjsK|rt |dhk(r|jj s$|j |jjkr|r>|jjr(|dj|jjs%|r|j |jjkr{|jj|j |jjj|j|jjjf|j}|r@|jjr*|dj|jjr2|rt |dhk(r|jj r[|j |jjkr|Dcgc]}|jj|c}|jjd}|Scc}w)NrrB)rr commentPrefix startswithset skipBlankRowsrmskipRowsroru delimiterjoinlstripstriptrimmer skipColumns)r>r*r.s r__next__zUnicodeReader.__next__snn <<4<<55q6$$T\\%?%?@SbT!1t||7Q7Q[[4<<#8#88DLL66A))$,,*D*DEt||/D/D!DMM((  ..33C8?? @Z@Z[aac*nn&4<<55q6$$T\\%?%?@SbT!1t||7Q7Q[[4<<#8#88588Cq4<<''*C89Q9Q9RSC 9s-"I+cR|jr|jjyyr'rQ)r>exc_typeexc_valexc_tbs rrVzUnicodeReader.__exit__rWrc|Sr'r1rIs r__iter__zUnicodeReader.__iter__s rr')rbrcrdre LinesOrPathrrr r:r?rJrrrVrr1rrr r sK.6: . .eGSL12 .D $rr c"eZdZdZfdZxZS)rz A `UnicodeReader` yielding (lineno, row) pairs, where "lineno" is the 1-based number of the the **text line** where the (possibly multi-line) row data starts in the DSV file. cBt|}|jdz|fS)zI :return: a pair (1-based line number in the input, row) r )superrrmr>r* __class__s rrz$UnicodeReaderWithLineNumber.__next__s% g {{Q##r)rbrcrdrer __classcell__rs@rrrs$$rrceZdZdZ d deeedeedeeffd Zedeeeffd Z de ffd Z de fd Z xZ S) ra A `UnicodeReader` yielding one `dict` per row. :param f: As for :class:`UnicodeReader` :param fieldnames: .. code-block:: python >>> with UnicodeDictReader( ... 'tests/fixtures/frictionless-data.csv', ... dialect=Dialect(delimiter='|', header=False), ... fieldnames=[str(i) for i in range(1, 11)]) as reader: ... for row in reader: ... print(row) ... break ... OrderedDict([('1', 'FK'), ('2', 'Year'), ('3', 'Location name'), ('4', 'Value'), ('5', 'binary'), ('6', 'anyURI'), ('7', 'email'), ('8', 'boolean'), ('9', 'array'), ('10', 'geojson')]) fieldnamesrestkeyrestvalc ^||_||_||_d|_t ||fi|yNr) _fieldnamesrrline_numrr?)r>rrrrr5rs rr?zUnicodeDictReader.__init__&s4&    !b!rrcZ|j t| |_|jj |_|jrIt t|jt |jk7rtjd|jS#t$rYwxYw)z:Get the fieldnames, i.e. the dictionary keys for the rows.zDuplicate column names!) rrr StopIterationrnrlenrwarningswarn)r>rs rrzUnicodeDictReader.fieldnames3s    # #(7#3#5  ,,   3t''()S1A1A-BB 78 !  sB B*)B*c|jdk(r |jt| }|jj|_|gk(rt| }|gk(r|j |Sr)rrrrrnitemrs rrzUnicodeDictReader.__next__Asa ==A  OOg  ,, Ri'"$CRiyy~rc(tjdt|j|D}t |j}t |}||kr||d||j <|S||kDr#|j|dD]}|j ||<|S)zTurn a row into a dict.c3*K|] \}}||f ywr'r1)r}kvs rr~z)UnicodeDictReader.item..Qs#Q7Ptq!QF7PsN) collections OrderedDictziprrrr)r>r*dlflrkeys rrzUnicodeDictReader.itemOs  # ##Qs4??C7P#Q Q  ! X 7!"#hAdllO"Wrs+#,r)NNN)rbrcrdrerrir:r?propertyr DictRowTyperrrrs@rrrs2/3%)%) "!c+ "c] " c] "  HT#Y/     +  ; rrc^eZdZdZeej ZejdZ dZ y)ra A `UnicodeReader` yielding one `namedtuple` per row. .. note:: This reader has some limitations, notably that fieldnames must be normalized to be admissible Python names, but also bad performance (compared with `UnicodeDictReader`). ctt|j|j}t j d|S)zY Creates a namedtuple class suitable for the columns of the CSV content. Row)rimap_normalize_fieldnamerr namedtuple)r>rs rclszNamedTupleReader.clshs2 #d77IJ %%eZ88rc $tj||}|jD]}|j|d|jdi|j Dcic]&\}}||jvs|j ||(c}}Scc}}w)zCreate a namedtuple from a row.Nr1)rrr setdefaultritemsr)r>r*rrrrs rrzNamedTupleReader.itemps  " "4 -OOD LLt $$txx_;<779]941aT__H\t((+Q.9]_ _]s B 2B N) rbrcrdre staticmethodr normalize_namer functoolscached_propertyrrr1rrrr\s8((<(<=99_rr lines_or_file namedtuplesdictsc+K|r |r td|rt}n|rt}nt}||fd|i|5}|Ed{dddy7 #1swYyxYww)aConvenience factory function for csv reader. :param lines_or_file: Content to be read. Either a file handle, a file path or a list of strings. :param namedtuples: Yield namedtuples. :param dicts: Yield dicts. :param encoding: Encoding of the content. :param kw: Keyword parameters are passed through to csv.reader. :return: A generator over the rows. z:either namedtuples or dicts can be chosen as output formatrN) ValueErrorrrr )rrrrr5_readerrs rrrys]uUVV" #  8 8R 8A  9 8 9 8s,3AA A A  A A  AAfnamevisitorc tj|}|jsJtjd5}tj|j }dddt |fi|5}tfi|5}t|D]"\}}|||}||j|$ ddddddtj|y#1swY{xYw#1swY4xYw#1swY8xYw)aDUtility function to rewrite rows in dsv files. :param fname: Path of the dsv file to operate on. :param visitor: A callable that takes a line-number and a row as input and returns a (modified) row or None to filter out the row. :param kw: Keyword parameters are passed through to csv.reader/csv.writer. FdeleteN) rDrEis_filetempfileNamedTemporaryFilerr r r\rYshutilmove) rrr5fptmpreader_r=r`r*s rrrs LL E ==??  $ $E 2bll277# 3 u # #w 3 %" %#G,3ao?OOC(-& $  KKU 3 2& % $ #s5 C2 C0?C$C$1C0C!$C- )C00C9rZctjd5}tj|j}dddtj|}t 5}|j r-t|5}|D]}|j| ddd|j|dddtj||y#1swYxYw#1swYExYw#1swY8xYw)z! Add rows to a CSV file. FrN) rrrDrErr existsr rYrarr)rrZrrr=rr*s rrrs  $ $E 2bll277# 3 LL E s v <<>u%"COOC(#&    KKU 3 2 &%  s/ C C%;CC% CC" C%%C.filter_c Jt|}t||fi||jS)aRewrite a dsv file, filtering the rows. :param fname: Path to dsv file :param filter_: callable which accepts a `dict` with a row's data as single argument returning a `Boolean` indicating whether to keep the row (`True`) or to discard it `False`. :param kw: Keyword arguments to be passed `UnicodeReader` and `UnicodeWriter`. :return: The number of rows that have been removed. ) DictFilterrremoved)rrr5s rrrs'!G E7!b! ??rcXeZdZdZdeeeefgeffdZde de ede e efdZ y) rzMUtility to apply a filter to a row as dict, while iterating over rows a list.rc.d|_||_d|_yr)headerfilterr)r>rs rr?zDictFilter.__init__s+/   rr`r*rc|dk(r ||_|S|rGtt|j|}|j|r|S|xjdz c_y)Nrr )rr]rrr)r>r`r*rs r__call__zDictFilter.__call__sO 6DKJ DKK-.D{{4  LLA LrN) rbrcrdrerr]r:boolr?intrirrr1rrrrsMW$sCx.)94)? @ # DI (492E rr)FFr")-rerFr8rrtypingrrrrrDrrrrcollections.abcrrrBr dsv_dialectsr __all__r:rErfrrrirrr r rrrrrrnrrrr]rrr1rrrs  00/!  gll" #Hb(3-/0 %%c5d3i+@&@A ((( ffRffR $- $J JZ_(_<,1%*'.K"4.TN } 8 8hT#Y/?tTRUYAW/W&X,HT#Y" x (D64<2H SV r