U bڕ@srddlmZddlmZmZddlmZddlZddlmZddl m Z ddl m Z m Z mZddlZddlmmZddlmZdd lmZmZmZmZmZdd lmZdd lmZm Z m!Z!dd l"m#Z#m$Z$dd l%m&Z&m'Z'm(Z(m)Z)m*Z*m+Z+ddl,m-Z-ddl.m/Z/ddl0m1Z1ddl2m3Z3ddl4m5Z5m6Z6m7Z7m8Z8m9Z9m:Z:ddl;mZ>m?Z?ddl@mAZAejBZBejCZCdGddddd dd!d d"d dd#d$ d%d&ZDGd'd(d(eZEGd)d*d*eEZFGd+d,d,eEZGGd-d.d.eGZHe!e3d/e3d0d1d2ed3dd4e d5d1gd6d7dHd:d d d dd d;d"d;d#d< d=d>ZIGd?d@d@ejJZKGdAdBdBZLGdCdDdDeLZMGdEdFdFeLZNdS)I) annotations)ABCabstractmethod)abcN)StringIO)islice)AnyCallableMapping)iNaT)CompressionOptionsDtypeArg IndexLabelJSONSerializableStorageOptionsAbstractMethodError)deprecate_kwargdeprecate_nonkeyword_argumentsdoc) ensure_stris_period_dtype) DataFrame MultiIndexSeriesisnanotna to_datetime)!create_series_with_explicit_dtype)NDFrame)concat) _shared_docs) IOHandles file_exists get_handle is_fsspec_urlis_urlstringify_path)convert_to_line_delimits)build_table_schemaparse_table_schema)validate_integerepoch TmsFinferr str | Nonestrintbool(Callable[[Any], JSONSerializable] | Noner r) objorient date_formatdouble_precision force_ascii date_unitdefault_handlerlines compressionindexindentstorage_optionsc  Cs| s|dkrtd|r(|dkr(td|dkrLt|trL|j|jpFdd}|dkrdt|trdt} n(t|trtt} nt|trt} nt d| |||||||| | d }|rt |}|dk rt |d | | d }|j |W5QRXn|SdS) N)splittablez?'index=False' is only valid when 'orient' is 'split' or 'table'recordsz3'lines' keyword only valid when 'orient' is recordsrBvalues)namez''obj' should be a Series or a DataFrame)r6r7r8 ensure_asciir:r;r>r?w)r=r@) ValueError isinstancerZto_framerErJSONTableWriter SeriesWriter FrameWriterNotImplementedErrorwriter(r$handle) path_or_bufr5r6r7r8r9r:r;r<r=r>r?r@writershandlesrT8/tmp/pip-unpacked-wheel-ck39h295/pandas/io/json/_json.pyto_jsonIsL     rVc @sZeZdZUded<dddddddddd d d Zd d ZddZeeddddZ dS)Writerr1_default_orientNrr0r2r3r4r6r7r8rFr:r>r;r?c CsV||_|dkr|j}||_||_||_||_||_||_||_| |_ d|_ | dSN) r5rXr6r7r8rFr:r;r>r?Zis_copy _format_axes) selfr5r6r7r8rFr:r>r;r?rTrTrU__init__s zWriter.__init__cCs t|dSrZrr\rTrTrUr[szWriter._format_axesc Cs0|jdk}t|j|j|j|j|j||j|jdS)Niso)r6r8rFr: iso_datesr;r?) r7dumps obj_to_writer6r8rFr:r;r?)r\r`rTrTrUrNs z Writer.write"NDFrame | Mapping[IndexLabel, Any]returncCsdS)zObject to write in JSON format.NrTr^rTrTrUrbszWriter.obj_to_write)Nr) __name__ __module__ __qualname____annotations__r]r[rNpropertyrrbrTrTrTrUrWs   rWc@s*eZdZdZeddddZddZdS) rKr>rcrdcCs,|js"|jdkr"|jj|jjdS|jSdS)NrA)rEdata)r>r6r5rErDr^rTrTrUrbszSeriesWriter.obj_to_writecCs*|jjjs&|jdkr&td|jddS)Nr>z(Series index must be unique for orient='')r5r> is_uniquer6rHr^rTrTrUr[szSeriesWriter._format_axesNrfrgrhrXrjrbr[rTrTrTrUrKsrKc@s*eZdZdZeddddZddZdS) rLcolumnsrcrdcCs0|js&|jdkr&|jjdd}|d=n|j}|S)NrA)r6r>)r>r6r5Zto_dict)r\rbrTrTrUrbs zFrameWriter.obj_to_writecCsP|jjjs&|jdkr&td|jd|jjjsL|jdkrLtd|jddS)z: Try to format axes if they are datelike. )r>roz+DataFrame index must be unique for orient='z'.)r>rorCz-DataFrame columns must be unique for orient='N)r5r>rmr6rHror^rTrTrUr[s  zFrameWriter._format_axesNrnrTrTrTrUrLsrLc sHeZdZdZdddddddddd fd d Zed d ddZZS)rJrCNrr0r1r2r3r4rYc s.tj||||||||| d |dkr:d|d} t| t||jd|_|jdkrht|jt rht d|jdkr|j t |jj kst|j|jj rd } t| |}|jd gd j} t| r|| d d || <t|jjr|j|_|js |jdd|_n|jdd|_d|_d|_||_dS)z Adds a `schema` attribute with the Table Schema, resets the index (can't do in caller, because the schema inference needs to know what the index is, forces orient to records, and forces date_format to 'iso'. )r;r?r_z8Trying to write with `orient='table'` and `date_format='zH'`. Table Schema requires dates to be formatted with `date_format='iso'`r>z6orient='table' is not supported for MultiIndex columnsz/Overlapping names between the index and columns timedelta)includecSs|SrZ) isoformat)xrTrTrU(z*JSONTableWriter.__init__..T)ZdropFrCN)superr]rHr)r>schemandimrIrorrMrEsetnameslen intersectioncopyZ select_dtypesZapplymaprdtypeZ to_timestampZ reset_indexr5r7r6) r\r5r6r7r8rFr:r>r;r?msgZ timedeltas __class__rTrUr]sP    zJSONTableWriter.__init__rcrdcCs|j|jdS)N)rzrk)rzr5r^rTrTrUrb6szJSONTableWriter.obj_to_write)Nr)rfrgrhrXr]rjrb __classcell__rTrTrrUrJs  "HrJr@decompression_optionsrP)r@rnumpy)Z old_arg_nameZ new_arg_namez2.0)versionZ allowed_args stacklevelframestrictDtypeArg | None int | None) rkeep_default_datesr precise_floatencoding_errorsr< chunksizer=nrowsr@cCs|dkr|rtd|dkr(|r(td|dkr<|dkr [index], columns -> [columns], data -> [values]}}`` - ``'records'`` : list like ``[{{column -> value}}, ... , {{column -> value}}]`` - ``'index'`` : dict like ``{{index -> {{column -> value}}}}`` - ``'columns'`` : dict like ``{{column -> {{index -> value}}}}`` - ``'values'`` : just the values array The allowed and default values depend on the value of the `typ` parameter. * when ``typ == 'series'``, - allowed orients are ``{{'split','records','index'}}`` - default is ``'index'`` - The Series index must be unique for orient ``'index'``. * when ``typ == 'frame'``, - allowed orients are ``{{'split','records','index', 'columns','values', 'table'}}`` - default is ``'columns'`` - The DataFrame index must be unique for orients ``'index'`` and ``'columns'``. - The DataFrame columns must be unique for orients ``'index'``, ``'columns'``, and ``'records'``. typ : {{'frame', 'series'}}, default 'frame' The type of object to recover. dtype : bool or dict, default None If True, infer dtypes; if a dict of column to dtype, then use those; if False, then don't infer dtypes at all, applies only to the data. For all ``orient`` values except ``'table'``, default is True. .. versionchanged:: 0.25.0 Not applicable for ``orient='table'``. convert_axes : bool, default None Try to convert the axes to the proper dtypes. For all ``orient`` values except ``'table'``, default is True. .. versionchanged:: 0.25.0 Not applicable for ``orient='table'``. convert_dates : bool or list of str, default True If True then default datelike columns may be converted (depending on keep_default_dates). If False, no dates will be converted. If a list of column names, then those columns will be converted and default datelike columns may also be converted (depending on keep_default_dates). keep_default_dates : bool, default True If parsing dates (convert_dates is not False), then try to parse the default datelike columns. A column label is datelike if * it ends with ``'_at'``, * it ends with ``'_time'``, * it begins with ``'timestamp'``, * it is ``'modified'``, or * it is ``'date'``. numpy : bool, default False Direct decoding to numpy arrays. Supports numeric data only, but non-numeric column and index labels are supported. Note also that the JSON ordering MUST be the same for each term if numpy=True. .. deprecated:: 1.0.0 precise_float : bool, default False Set to enable usage of higher precision (strtod) function when decoding string to double values. Default (False) is to use fast but less precise builtin functionality. date_unit : str, default None The timestamp unit to detect if converting dates. The default behaviour is to try and detect the correct precision, but if this is not desired then pass one of 's', 'ms', 'us' or 'ns' to force parsing only seconds, milliseconds, microseconds or nanoseconds respectively. encoding : str, default is 'utf-8' The encoding to use to decode py3 bytes. encoding_errors : str, optional, default "strict" How encoding errors are treated. `List of possible values `_ . .. versionadded:: 1.3.0 lines : bool, default False Read the file as a json object per line. chunksize : int, optional Return JsonReader object for iteration. See the `line-delimited json docs `_ for more information on ``chunksize``. This can only be passed if `lines=True`. If this is None, the file will be read into memory all at once. .. versionchanged:: 1.2 ``JsonReader`` is a context manager. {decompression_options} .. versionchanged:: 1.4.0 Zstandard support. nrows : int, optional The number of lines from the line-delimited jsonfile that has to be read. This can only be passed if `lines=True`. If this is None, all the rows will be returned. .. versionadded:: 1.1 {storage_options} .. versionadded:: 1.2.0 Returns ------- Series or DataFrame The type returned depends on the value of `typ`. See Also -------- DataFrame.to_json : Convert a DataFrame to a JSON string. Series.to_json : Convert a Series to a JSON string. json_normalize : Normalize semi-structured JSON data into a flat table. Notes ----- Specific to ``orient='table'``, if a :class:`DataFrame` with a literal :class:`Index` name of `index` gets written with :func:`to_json`, the subsequent read operation will incorrectly set the :class:`Index` name to ``None``. This is because `index` is also used by :func:`DataFrame.to_json` to denote a missing :class:`Index` name, and the subsequent :func:`read_json` operation cannot distinguish between the two. The same limitation is encountered with a :class:`MultiIndex` and any names beginning with ``'level_'``. Examples -------- >>> df = pd.DataFrame([['a', 'b'], ['c', 'd']], ... index=['row 1', 'row 2'], ... columns=['col 1', 'col 2']) Encoding/decoding a Dataframe using ``'split'`` formatted JSON: >>> df.to_json(orient='split') '{{"columns":["col 1","col 2"],"index":["row 1","row 2"],"data":[["a","b"],["c","d"]]}}' >>> pd.read_json(_, orient='split') col 1 col 2 row 1 a b row 2 c d Encoding/decoding a Dataframe using ``'index'`` formatted JSON: >>> df.to_json(orient='index') '{{"row 1":{{"col 1":"a","col 2":"b"}},"row 2":{{"col 1":"c","col 2":"d"}}}}' >>> pd.read_json(_, orient='index') col 1 col 2 row 1 a b row 2 c d Encoding/decoding a Dataframe using ``'records'`` formatted JSON. Note that index labels are not preserved with this encoding. >>> df.to_json(orient='records') '[{{"col 1":"a","col 2":"b"}},{{"col 1":"c","col 2":"d"}}]' >>> pd.read_json(_, orient='records') col 1 col 2 0 a b 1 c d Encoding with Table Schema >>> df.to_json(orient='table') '{{"schema":{{"fields":[{{"name":"index","type":"string"}},{{"name":"col 1","type":"string"}},{{"name":"col 2","type":"string"}}],"primaryKey":["index"],"pandas_version":"1.4.0"}},"data":[{{"index":"row 1","col 1":"a","col 2":"b"}},{{"index":"row 2","col 1":"c","col 2":"d"}}]}}' rBz)cannot pass both dtype and orient='table'z0cannot pass both convert_axes and orient='table'NT)r6typr convert_axes convert_datesrrrr:encodingr<rr=rr@r)rH JsonReaderread)rPr6rrrrrrrr:rrr<rr=rr@Z json_readerrTrTrU read_json;sB  rc @s~eZdZdZd dddddddddd d d Zd d ZddZddddZddZddZ ddZ ddZ ddZ ddZ dS)!rz JsonReader provides an interface for reading in a JSON file. If initialized with ``lines=True`` and ``chunksize``, can be iterated over ``chunksize`` lines at a time. Otherwise, calling ``read`` reads in the whole document. Nrr3rr rr0) rrrr<rr=rr@rcCs||_||_||_||_||_||_||_| |_| |_| |_ ||_ ||_ | |_ | |_ d|_||_||_d|_|j dk rtd|j d|_ |j std|jdk rtd|jd|_|j std||}|||_dS)Nrrrrz*chunksize can only be passed if lines=Truerz&nrows can only be passed if lines=True)r6rrrrrrrr:rr=r@r<r nrows_seenrrrSr+rH_get_data_from_filepath_preprocess_datark)r\filepath_or_bufferr6rrrrrrrr:rr<rr=rr@rrkrTrTrUr]ps8   zJsonReader.__init__c CsPt|dr.|js.|js.||}W5QRXt|dsL|jsD|jrLt|}|S)a& At this point, the data either has a `read` attribute (e.g. a file object or a StringIO) or is a string that is a JSON document. If self.chunksize, we prepare the data for the `__next__` method. Otherwise, we read it into memory for the `read` method. r)hasattrrrrr)r\rkrTrTrUrs zJsonReader._preprocess_datacCsTt|}t|tr*t|s*t|s*t|rPt|d|j|j|j |j d|_ |j j }|S)aL The function read_json accepts three input types: 1. filepath (string-like) 2. file-like object (e.g. open file object, StringIO) 3. JSON string This method turns (1) into (2) to simplify the rest of the processing. It returns input types (2) and (3) unchanged. r)rr=r@errors) r'rIr1r&r%r#r$rr=r@rrSrO)r\rrTrTrUrs& z"JsonReader._get_data_from_filepathr1rdcCs&dddddd|DDdS)zG Combines a list of JSON objects into one JSON object. [,cSsg|] }|r|qSrTrT.0linerTrTrU sz-JsonReader._combine_lines..css|]}|VqdSrZ)striprrTrTrU sz,JsonReader._combine_lines..])join)r\r<rTrTrU_combine_liness$zJsonReader._combine_linescCs|jrj|jrt|}qv|jrDtt|j|j}||}||}qvt |j}| d}|||}n ||j}| |S)zA Read the whole JSON input into a pandas object.  ) r<rr rlistrrkr_get_object_parserrrAclose)r\r5r< lines_jsonrkZ data_linesrTrTrUrs      zJsonReader.readc Cs|j}|j}|j|j|j|j|j|j|j|jd}d}|dkrNt |f| }|dks^|dkrt |t sp||d<t |f| }|S)z> Parses a json document into a pandas object. )r6rrrrrrr:NrZseriesr)rrr6rrrrrr: FrameParserparserIr3 SeriesParser)r\jsonrrkwargsr5rTrTrUrs&  zJsonReader._get_object_parsercCs|jdk r|jdS)z If we opened a stream earlier, in _get_data_from_filepath, we should close it. If an open stream or file was passed, we leave it open. N)rSrr^rTrTrUr s zJsonReader.closecCs|jr|j|jkr|ttt|j|j}|rv||}| |}t |j|jt ||_ |jt |7_|S|tdSrZ) rrr StopIterationrrrkrrrranger~r>)r\r<rr5rTrTrU__next__s   zJsonReader.__next__cCs|SrZrTr^rTrTrU __enter__'szJsonReader.__enter__cCs |dSrZ)r)r\exc_type exc_value tracebackrTrTrU__exit__*szJsonReader.__exit__)Nr)rfrgrh__doc__r]rrrrrrrrrrTrTrTrUrgs 4 rc@seZdZUded<ded<dZdddd dZd%d dddZddZddZddZ ddZ ddZ ddZ d&ddddd Z d!d"Zd#d$Zd S)'Parserztuple[str, ...] _split_keysr1rX)rRr.usnsi3l,b/l`'rlF[L'NTFrrc Cs||_|dkr|j}||_||_|dkr,d}| dk rd| } | |jkrVtd|j|j| |_n |jd|_||_ ||_ ||_ ||_ | |_ ||_d|_dS)NrAFzdate_unit must be one of rR)rrXr6rlower _STAMP_UNITSrH _MIN_STAMPS min_stamprrrrr:rr5) r\rr6rrrrrrr:rTrTrUr]:s(   zParser.__init__cCs8t|t|j}|r4d|}td|dS)zT Checks that dict has only the appropriate keys for orient='split'. z, z!JSON data had unexpected key(s): N)r|keys differencerrrH)r\decodedZbad_keysZbad_keys_joinedrTrTrUcheck_keys_splitbs zParser.check_keys_splitcCsB|jr|n||jdkr&dS|jr4|||jSrZ)r _parse_numpy_parse_no_numpyr5r _convert_axes_try_convert_typesr^rTrTrUrks  z Parser.parsecCs t|dSrZrr^rTrTrUryszParser._parse_numpycCs t|dSrZrr^rTrTrUr|szParser._parse_no_numpycCsP|j}|dk st|jD]2}|j|||ddd\}}|rt|j||qdS)z& Try to convert axes. NFT)rErk use_dtypesr)r5AssertionErrorZ _AXIS_ORDERS_try_convert_dataZ _get_axissetattr)r\r5Z axis_nameZnew_axisresultrTrTrUrs   zParser._convert_axescCs t|dSrZrr^rTrTrUrszParser._try_convert_typesr3)rrc Cs|r|js.tt|r|dfS|tjdfS|jdkr:nXt|jtrR|j|n|j}|dk rz| |dfWSt t fk r|dfYSX|r| |\}}|r|dfS|jdkrz| d}Wnt t fk rYnX|jj dkr&|jdkr&z| d}Wnt t fk r$YnXt|r|jdksH|jdkrz | d}||krf|}Wnt t tfk rYnX|jd krz| d}Wnt t fk rYnX|d krt|r|jd kr|dfS|dfS) zO Try to parse a ndarray like into a column by inferring dtype. FTNobjectZfloat64ffloatint64r2r>rA)rallrZfillnanpnanrIdictgetastype TypeErrorrH_try_convert_to_datekindr~ OverflowErrorr6)r\rErkrrrnew_datarrTrTrUrsZ    "   zParser._try_convert_datac Cst|s|dfS|}|jdkrHz|d}Wntttfk rFYnXt|jjtj rt |j ||j kB|j t kB}|s|dfS|jr|jfn|j}|D]@}zt|d|d}Wntttfk rYqYnX|dfS|dfS)z Try to parse a ndarray like into a date column. Try to coerce object in epoch/iso formats and integer/float in epoch formats. Return a boolean if parsing was successful. Frrraise)runitT)r~rrrrHr issubclasstypernumberrZ_valuesrr rr:rr)r\rkrZin_rangeZ date_unitsr:rTrTrUrs2   zParser._try_convert_to_datecCs t|dSrZrr^rTrTrU_try_convert_datesszParser._try_convert_dates)NTTFFFN)TT)rfrgrhrirrr]rrrrrrrrrrTrTrTrUr.s6  ( Q%rc@s,eZdZdZdZddZddZddZd S) rr>)rEr>rkcCsVt|j|jd}|jdkrDdd|D}||tf||_nt|td|_dS)NrrAcSsi|]\}}t||qSrTr1rkvrTrTrU sz0SeriesParser._parse_no_numpy..dtype_if_empty) loadsrrr6itemsrrr5r)r\rkrrTrTrUrs   zSeriesParser._parse_no_numpycCsdd|jd}|jdkr d|d<tjtf|}||j}|jdkrldd|D}||tf||_ n*|jdkrt|dt i|_ nt|t d |_ dS) NTrrr)ror>labelledrAcSsi|]\}}t||qSrTrrrTrTrUr&sz-SeriesParser._parse_numpy..rr) rr6 functoolspartialrrrrrr5r)r\Z load_kwargsZloads_rkrrTrTrUrs&      zSeriesParser._parse_numpycCs4|jdkrdS|jd|j|jd\}}|r0||_dS)Nrkr)r5rr)r\r5rrTrTrUr2s  zSeriesParser._try_convert_typesN)rfrgrhrXrrrrrTrTrTrUr s  rc@s>eZdZdZdZddZddZddd Zd d Zd d Z dS)rro)ror>rkcCs|j}|j}|dkrTt|ddd|jd}t|rH|dj|d|df}t||_n|dkrt|dd|jd}d d |D}| |tf||_n<|d krtt|dd|jd|_ntt|ddd|jd|_dS) NroT)rrrrrrqrrrArcSsi|]\}}t||qSrTrrrTrTrUrTsz,FrameParser._parse_numpy..rD) rr6rrr~Trr5rr)r\rr6argsrrTrTrUr@sH  zFrameParser._parse_numpycCs|j}|j}|dkr.tt||jddd|_n|dkrrddt||jdD}||tfddi||_nX|dkrtjt||jdddd |_n2|d krt ||jd|_ntt||jddd|_dS) NrorrrAcSsi|]\}}t||qSrTrrrTrTrUrpsz/FrameParser._parse_no_numpy..rr>)rr6rB) rr6rrrr5rr from_dictr*)r\rr6rrTrTrUrfs2      zFrameParser._parse_no_numpyNc Cs|dkrdd}|j}|dk s"td}i}t|D]8\}\}}|||rf|||\} } | rf| }d}|||<q6|rt||jd} |j| _| |_dS)zM Take a conversion function and possibly recreate the frame. NcSsdS)NTrTcolcrTrTrUrwrxz0FrameParser._process_converter..FTrp)r5r enumeraterrr>ro) r\rZfiltr5Z needs_new_objZnew_objirrrrZ new_framerTrTrU_process_converters"   zFrameParser._process_convertercs2jdkrdSjrfdddS)Ncsj||ddS)NFr)rrr^rTrUrwrxz0FrameParser._try_convert_types..)r5rrrr^rTr^rUrs  zFrameParser._try_convert_typescsZjdkrdSjdkr gtddddfddfdddS) NTr3rdcSsTt|tsdS|}|dsL|dsL|dksL|dksL|dksL|drPdSdS) zK Return if this col is ok to try for a date parse. FZ_at_timemodifieddatedatetime timestampT)rIr1rendswith startswith)rZ col_lowerrTrTrUis_oks" z-FrameParser._try_convert_dates..is_okcs |SrZ)rrr^rTrUrwrxz0FrameParser._try_convert_dates..csjr|p|kSrZ)rrrr r\rTrUrws)r5rr|rr^rTr rUrs  zFrameParser._try_convert_dates)N) rfrgrhrXrrrrrrrTrTrTrUr<s&  r) Nr,r-Tr.NFr/TrN)NNrNNTTFFNNrFNr/NN)O __future__rrrr collectionsrior itertoolsrtypingrr r rrZpandas._libs.jsonZ_libsrZpandas._libs.tslibsr Zpandas._typingr r rrrZ pandas.errorsrZpandas.util._decoratorsrrrZpandas.core.dtypes.commonrrZpandasrrrrrrZpandas.core.constructionrZpandas.core.genericrZpandas.core.reshape.concatr Zpandas.core.shared_docsr!Zpandas.io.commonr"r#r$r%r&r'Zpandas.io.json._normalizer(Zpandas.io.json._table_schemar)r*Zpandas.io.parsers.readersr+rrarVrWrKrLrJrIteratorrrrrrTrTrTrUs              &>7P  (&H_0