o Nrfk+@s&ddlmZddlZddlZddlmZddlmZddlZ ddl m Z ddl m ZddlmZddlmZdd lmZmZdd lmZdd lmZdd lmZmZdd lmZ         d"ddZddZ e!deddddddddde j"ddf ddZ" d#ddZ#ddZ$d d!Z%dS)$) annotationsN)partial) zip_longest) open_files)compute) read_bytes)flatten) PANDAS_GE_200PANDAS_VERSION)dataframe_creation_dispatch) from_delayed)insert_meta_param_description make_meta)delayedrecordsTutf-8strictc  s|dur|dk}|dkr|rtd|d<|o|dkd<t|df||| |j|d|p-i} fdd t| |D} |rP| durGt} tt| i| S| S) aWrite dataframe into JSON text files This utilises ``pandas.DataFrame.to_json()``, and most parameters are passed through - see its docstring. Differences: orient is 'records' by default, with lines=True; this produces the kind of JSON output that is most common in big-data applications, and which can be chunked when reading (see ``read_json()``). Parameters ---------- df: dask.DataFrame Data to save url_path: str, list of str Location to write to. If a string, and there are more than one partitions in df, should include a glob character to expand into a set of file names, or provide a ``name_function=`` parameter. Supports protocol specifications such as ``"s3://"``. encoding, errors: The text encoding to implement, e.g., "utf-8" and how to respond to errors in the conversion (see ``str.encode()``). orient, lines, kwargs passed to pandas; if not specified, lines=True when orient='records', False otherwise. storage_options: dict Passed to backend file-system implementation compute: bool If true, immediately executes. If False, returns a set of delayed objects, which can be computed at a later time. compute_kwargs : dict, optional Options to be passed in to the compute method compression : string or None String like 'gzip' or 'xz'. name_function : callable, default None Function accepting an integer (partition index) and producing a string to replace the asterisk in the given filename globstring. Should preserve the lexicographic order of partitions. NrYszto_json..) ValueErrorrZ npartitionszipZ to_delayeddictlist dask_compute)dfurl_pathrrstorage_optionsrrrrZcompute_kwargsrr"Zoutfilespartsrr!r#to_jsons44  r.cCsD|}|j|fi|Wdn1swYtj|jSN)r.ospathnormpath)r*Zopenfiler"frrr#resrpandasiZinferFc  sdurdkdkrrtd|rdksstd|p!i}dur(ddur0ddttrHtsAtd ttd ttjd |rt|d f|||d |}r|\}}}|d}t fdd|D t fddt ||D}n |\}}d}d}d t |}durt || t  fddt||D}n(t|df|d|}t fdd|D  fdd|D}t|dS)a Create a dataframe from a set of JSON files This utilises ``pandas.read_json()``, and most parameters are passed through - see its docstring. Differences: orient is 'records' by default, with lines=True; this is appropriate for line-delimited "JSON-lines" data, the kind of JSON output that is most common in big-data scenarios, and which can be chunked when reading (see ``read_json()``). All other options require blocksize=None, i.e., one partition per input file. Parameters ---------- url_path: str, list of str Location to read from. If a string, can include a glob character to find a set of file names. Supports protocol specifications such as ``"s3://"``. encoding, errors: The text encoding to implement, e.g., "utf-8" and how to respond to errors in the conversion (see ``str.encode()``). orient, lines, kwargs passed to pandas; if not specified, lines=True when orient='records', False otherwise. storage_options: dict Passed to backend file-system implementation blocksize: None or int If None, files are not blocked, and you get one partition per input file. If int, which can only be used for line-delimited JSON files, each partition will be approximately this size in bytes, to the nearest newline character. sample: int Number of bytes to pre-load, to provide an empty dataframe structure to any blocks without data. Only relevant when using blocksize. encoding, errors: Text conversion, ``see bytes.decode()`` compression : string or None String like 'gzip' or 'xz'. engine : callable or str, default ``pd.read_json`` The underlying function that dask will use to read JSON files. By default, this will be the pandas JSON reader (``pd.read_json``). If a string is specified, this value will be passed under the ``engine`` key-word argument to ``pd.read_json`` (only supported for pandas>=2.0). include_path_column : bool or str, optional Include a column with the file path where each row in the dataframe originated. If ``True``, a new column is added to the dataframe called ``path``. If ``str``, sets new column name. Default is ``False``. path_converter : function or None, optional A function that takes one argument and returns a string. Used to convert paths in the ``path`` column, for instance, to strip a common prefix from all the paths. $META Returns ------- dask.DataFrame Examples -------- Load single file >>> dd.read_json('myfile.1.json') # doctest: +SKIP Load multiple files >>> dd.read_json('myfile.*.json') # doctest: +SKIP >>> dd.read_json(['myfile.1.json', 'myfile.2.json']) # doctest: +SKIP Load large line-delimited JSON files using partitions of approx 256MB size >> dd.read_json('data/file*.csv', blocksize=2**28) NrrzSJSON file chunking only allowed for JSON-linesinput (orient='records', lines=True).Tr1cSs|Sr/r)xrrr#szread_json..zYPandas>=2.0 is required to pass a string to the `engine` argument of `read_json` (pandas=z is currently installed).)engine ) blocksizesamplerZ include_pathrc3s|]}|VqdSr/r)rppath_converterrr# szread_json..c3s&|]\}}|gt|VqdSr/)len)rr;chunkr<rr#r>s r/c s.g|]\}}tt||d qS)meta)rread_json_chunk)rr@r1)rr7rinclude_path_columnr"rB path_dtyperr#r$s zread_json..rt)rrrc3s|]}|jVqdSr/)r1rr3r<rr#r>sc s,g|]}tt||jqSr)rread_json_filer1rG)r7rDr"rrr=rErr#r$s rA)r% isinstancestrr r rpd read_jsonrZCategoricalDtyperr&rCrrrr )r+rrr,r9r:rrrrBr7rDr=r"Zb_outfirstchunkspathsZ first_pathZ flat_pathsZ flat_chunksr-filesr) rr7rrDr"rrBrr=rEr#rLks[          rLc CsZt|||} | d|| fddd|} |dur"| jr"|S|r+t| |||} | S)NrrTrr)ioStringIOdecodeseekemptyadd_path_column) r@rrr7 column_namer1rEr"rBsr*rrr#rC-s rCc CsP|}||f||d|} Wdn1swY|r&t| |||} | S)NrQ)rW) r3rrr7rXr1rEr" open_filer*rrr#rH<s rHcCsB||jvr td|d|jdi|tj|gt||diS)Nz(Files already contain the column name: 'z^', so the path column cannot use this name. Please set `include_path_column` to a unique name.)dtyper)columnsr%ZassignrKZSeriesr?)r*rXr1r[rrr#rWDs  (rW) rNNTrrNNNr/)& __future__rrRr0 functoolsr itertoolsrr4rKZ fsspec.corerZ dask.baserr)Z dask.bytesrZ dask.corerZdask.dataframe._compatr r Zdask.dataframe.backendsr Zdask.dataframe.io.ior Zdask.dataframe.utilsr rZ dask.delayedrr.rZregister_inplacerLrCrHrWrrrr#s\           PB