#ZjD dZddlZddlZddlZddlZddlmZmZmZm Z ddl Z ddl Z ddl Z ddl Z ddlZddlmZmZddlmZddlmZgdZeee jfZeeeeefZejeeeeeffZd ed efd ZGd d ZGddZ Gdde Z!Gdde Z"Gdde"Z# d%dedee$dee$d eed ef dZ%e%Z&dede e'eegedeefffdZ(dedeefd Z)ded!e e*ge$fd e'fd"Z+Gd#d$Z,dS)&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_dictencodingreturnc4tj|jS)z#Normalize the name of the encoding.)codecslookupname)rs T/Users/jameslopez/projects/MentorCore/.venv/lib/python3.11/site-packages/csvw/dsv.pynormalize_encodingr*s = " " ''ceZdZdZ ddeedeeeeffdZ dZ dee fdZ d Z d eeedffd Zd eeeeeffd ZdS)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 Z||_|dd|_t|tr@|j|_||_|j|n||_|r ||jd<t|j|_|j d|_ |j rB|j dtj krt|j d|j zfd}nd}||_d |_d |_d|_dS) Nrutf-8r escapecharquotingc(fd|DS)Nc`g|]*}t|r|n|+S) isinstancereplace).0s_new_old_types r zBUnicodeWriter.__init__.._escapedoubled..Zs<ZZZQRAu1E1EL $---1ZZZrr()rowr/r.r-s ```r_escapedoubledz.UnicodeWriter.__init__.._escapedoubledVs)[ZZZZZVYZZZZrc|SNr()r1s rr2z.UnicodeWriter.__init__.._escapedoubled\s rFr)rpoprr)r python_encodingas_python_formatting_parameterskwupdatergetr#csv QUOTE_NONEstrr2_close _rows_writtenwriter)selfrr r8r2s r__init__zUnicodeWriter.__init__Bs. z733 gw ' ' -#3DM==??DG GNN2    DG -%, "*4=99 '++l33 ? tw{{955GG&)$(O$%$7 [ [ [ [ [    ,  rct|jttjfrgt|jtjrt|j|_t j|jd|jd|_d|_n!|jt j d|_tj |jfi|j |_ |S)Nwt)rnewlineT)rF) r)rr=pathlibPathioopenrr>StringIOr;r@r8rAs r __enter__zUnicodeWriter.__enter__cs dfsGL1 2 2 -$&',// %TVWTVTDM2NNNDFDKK V^[,,,DFj334733  rrct|jdr|jdt|jdr,|jdSdS)z If the writer has been initialized passing `None` as target, the CSV data as `bytes` can be retrieved calling this method. seekrreadr"N)hasattrrrOrPencoderLs rrPzUnicodeWriter.readps` 466 " "  FKKNNN 466 " " 16;;==''00 0trcJ|jr|jdSdSr4r>rclose)rAtype_value tracebacks r__exit__zUnicodeWriter.__exit__{) ;  FLLNNNNN  rr1c|j|||xjdz c_dS)zWrite multiple rows.r N)r@writerowr2r?rAr1s rr\zUnicodeWriter.writerows@ T0055666 arrowsct|D]w\}}t|trH|dkr.|js'|||}||xdS)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?r\keysvalues)rAr^ir1s r writerowszUnicodeWriter.writerowss oo  FAs#t$$ #66$"46MM#((**---jjll MM#       r)NN)__name__ __module__ __qualname____doc__rPathTyperr r=rBrMbytesrPrYrr\tuplelistrarer(rrr r /s(%)59!eGSL12B    huo     HU39%56    huUD$->'?@rr c`eZdZdZ d dedeeeeffdZ dZ dZ dZ d Z d ZdS) 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|dd|_|dd|_t |t r|nd|_d|_d|_ |jrE|jj |_| |_ |j |n||_ |r ||j d<d|_g|_|jdkrd|_|j|_dS)Nrz utf-8-siglineterminatorr Fr")rrr5rrFr)r r linenoreaderr6r7r8r9r>comments_reader_encoding)rArr r8s rrBzUnicodeReader.__init__s *266*k+J+JKK vv.55 ",Wg">">HwwD   < - L8DM==??DG GNN2    DG -%, "  =G # #'DM !% rcVt|jttjfrnt|jtjrt|j|_t j|jd|j|jpd|_d|_ nlt|jdsWg}|jD]F}| t|tr| |jn|G||_tj|jfi|j|_d|_|S)NrtrE)moderrFTrP)r)rr=rGrHrIrJrrFr>rQappendrkdecoder;rrr8rq)rAlineslines rrMzUnicodeReader.__enter__s dfsGL1 2 2 $&',// %TVWTV$PTP\Pb`bcccDFDKK(( E ^ ^ :dE;R;R\T[[777X\]]]]DFj334733   rcxjdz c_fdtjD}xjtd|Dz c_|S)Nr crg|]3}t|tr|n|j4Sr()r)r=rzrtr+r,rAs rr0z+UnicodeReader._next_row..sK(((As## HAA$2G)H)H(((rc3ZK|]&}t|dV'dS) N)rmcount)r+r,s r z*UnicodeReader._next_row..s4<<1477==..<<<<<.s)888q4<''**888r)rr commentPrefix startswithset skipBlankRowsrqskipRowsrsry delimiterjoinlstripstrip skipColumnsr]s` r__next__zUnicodeReader.__next__snn < T '4<5 'q6$$T\%?@@ ' '!$SbT!1!1t|7Q!1[4<#888DL6A))$,*DEE!%t|/D!D!DM((  .33C88?? @Z[[aacc*nn&& '4<5 'q6$$T\%?@@ ' '!$SbT!1!1t|7Q!1[4<#8889888C8889Q9R9RSC rcJ|jr|jdSdSr4rT)rAexc_typeexc_valexc_tbs rrYzUnicodeReader.__exit__rZrc|Sr4r(rLs r__iter__zUnicodeReader.__iter__s rr4)rfrgrhri LinesOrPathrrr r=rBrMrrrYrr(rrr r s.6: . . .eGSL12 . . . .D $rr c"eZdZdZfdZxZS)rz A `UnicodeReader` yielding (lineno, row) pairs, where "lineno" is the 1-based number of the the **text line** where the (possibly multi-line) row data starts in the DSV file. c\t}|jdz|fS)zI :return: a pair (1-based line number in the input, row) r )superrrqrAr1 __class__s rrz$UnicodeReaderWithLineNumber.__next__s+ gg  {Q##r)rfrgrhrir __classcell__rs@rrrsB$$$$$$$$$rrceZdZdZ d deeedeedeeffd Zedeeeffd Z de ffd Z de fd Z xZ S) ra A `UnicodeReader` yielding one `dict` per row. :param f: As for :class:`UnicodeReader` :param fieldnames: .. code-block:: python >>> with UnicodeDictReader( ... 'tests/fixtures/frictionless-data.csv', ... dialect=Dialect(delimiter='|', header=False), ... fieldnames=[str(i) for i in range(1, 11)]) as reader: ... for row in reader: ... print(row) ... break ... OrderedDict([('1', 'FK'), ('2', 'Year'), ('3', 'Location name'), ('4', 'Value'), ('5', 'binary'), ('6', 'anyURI'), ('7', 'email'), ('8', 'boolean'), ('9', 'array'), ('10', 'geojson')]) N fieldnamesrestkeyrestvalc t||_||_||_d|_t j|fi|dSNr) _fieldnamesrrline_numrrB)rArrrrr8rs rrBzUnicodeDictReader.__init__&sG&   !!b!!!!!rrcT|j7 t|_n#t$rYnwxYw|jj|_|jrKt t|jt |jkrtj d|jS)z:Get the fieldnames, i.e. the dictionary keys for the rows.NzDuplicate column names!) rrr StopIterationrrrlenrwarningswarn)rArs rrzUnicodeDictReader.fieldnames3s   # #(77#3#3#5#5        ,   93t'(())S1A-B-BBB 7888s %0 ==c |jdkr|jt}|jj|_|gkr&t}|gk&||Sr)rrrrrritemrs rrzUnicodeDictReader.__next__Ass =A   OOgg   , Rii''""$$CRiiyy~~rc$tjdt|j|D}t |j}t |}||kr||d||j<n"||kr|j|dD] }|j||< |S)zTurn a row into a dict.c3$K|] \}}||fV dSr4r()r+kvs rrz)UnicodeDictReader.item..Qs*#Q#Qtq!QF#Q#Q#Q#Q#Q#QrN) collections OrderedDictziprrrr)rAr1dlflrkeys rrzUnicodeDictReader.itemOs  ##Q#Qs4?C7P7P#Q#Q#Q Q Q  ! ! XX 77!"##hAdlOO "WWrss+ & &#r)NNN)rfrgrhrirrmr=rBpropertyr DictRowTyperrrrs@rrrs2/3%)%) " "!c+ "c] " c] " " " " " "  HT#Y/      X   +       ;        rrcXeZdZdZeejZej dZ dZ dS)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`). cztt|j|j}t jd|S)zY Creates a namedtuple class suitable for the columns of the CSV content. Row)rmmap_normalize_fieldnamerr namedtuple)rArs rclszNamedTupleReader.clshs3 #d7IIJJ %eZ888rct|}jD]}||djdifd|DS)zCreate a namedtuple from a row.NcTi|]$\}}|jv||%Sr()rr)r+rrrAs r z)NamedTupleReader.item..vs9]]]41aT_H\H\t((++QH\H\H\rr()rrr setdefaultritems)rAr1rrs` rrzNamedTupleReader.itemps  " "4 - -O % %D LLt $ $ $ $tx__]]]]17799]]]__ _rN) rfrgrhri staticmethodr normalize_namer functoolscached_propertyrrr(rrrr\sd(<(<==999_____rrFr" lines_or_file namedtuplesdictsc+K|r|rtd|rt}n|rt}nt}||fd|i|5}|Ed{VddddS#1swxYwYdS)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 )rrrrr8_readerrs rrrysWuWUVVV "  #  8 8 8R 8 8A s AAAfnamevisitorc tj|}|sJtjd5}tj|j}dddn #1swxYwYt |fi|5}t|fi|5}t|D](\}}|||}|| |) dddn #1swxYwYdddn #1swxYwYtj ||dS)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) rGrHis_filetempfileNamedTemporaryFilerr r r`r\shutilmove) rrr8fptmpreader_r@rdr1s rrrs L  E ==???  $E 2 2 2$bl27##$$$$$$$$$$$$$$$ u # # # #)w 3 % %" % % )#G,, ) )3gaoo?OOC((( ) ) ) ) ) ) ) ) ) ) ) ) ) ) ) ))))))))))))))))  KUsHA&&A*-A*>C) 9C C)C C)C C))C-0C-r^ctjd5}tj|j}dddn #1swxYwYtj|}t |5}|rBt|5}|D]}|| dddn #1swxYwY| |dddn #1swxYwYtj ||dS)z! Add rows to a CSV file. FrN) rrrGrHrr existsr r\rerr)rr^rrr@rr1s rrrs  $E 2 2 2$bl27##$$$$$$$$$$$$$$$ L  E s  v <<>> )u%% )"))COOC(((() ) ) ) ) ) ) ) ) ) ) ) ) ) ) )    KUsE<AA*$C"B6* C"6B: :C"=B: >C""C&)C&filter_c Jt|}t||fi||jS)aRewrite a dsv file, filtering the rows. :param fname: Path to dsv file :param filter_: callable which accepts a `dict` with a row's data as single argument returning a `Boolean` indicating whether to keep the row (`True`) or to discard it `False`. :param kw: Keyword arguments to be passed `UnicodeReader` and `UnicodeWriter`. :return: The number of rows that have been removed. ) DictFilterrremoved)rrr8s rrrs1!!G E7!!b!!! ?rcxeZdZdZdeeeefgeffdZde de ede e efdZ dS) rzMUtility to apply a filter to a row as dict, while iterating over rows a list.rc0d|_||_d|_dSr)headerfilterr)rArs rrBzDictFilter.__init__s+/   rrdr1rc|dkr ||_|S|rItt|j|}||r|S|xjdz c_dS)Nrr )rrarrr)rArdr1rs r__call__zDictFilter.__call__sf 66DKJ  DK--..D{{4    LLA LLtrN) rfrgrhrirrar=boolrBintrmrrr(rrrrsWW$sCx.)94)? @ # DI (492E      rr)FFr")-rirIr;rrtypingrrrrrGrrrrcollections.abcrrrEr dsv_dialectsr __all__r=rHrjrrrmrrr r rrrrrrrrrrrarrr(rrrsf   000000000000////////!!!!!!    gl" #Hb(3-/0 %c5d3i+@&@A (((((( ffffffffRffffffffR $ $ $ $ $- $ $ $JJJJJ JJJZ_____(___<,1%*'.K"4.TN } 8 8hT#Y/?tTRUYAW/W&X,HT#Y" x (D64<2H SV    r