U sVc @sdZddlmZddlZddlmZddlmZmZm Z ddl m Z m Z m Z ddlmZddlmZmZmZmZdd lmZerdd lmZdd d d dddZdddddd ddddddddZdS)z orc compat ) annotationsN) ModuleType) TYPE_CHECKINGAnyLiteral)FilePath ReadBuffer WriteBuffer)import_optional_dependency)is_categorical_dtypeis_interval_dtypeis_period_dtypeis_unsigned_integer_dtype) get_handle) DataFramezFilePath | ReadBuffer[bytes]zlist[str] | Noner)pathcolumnsreturnc KsRtd}t|ddd2}||j}|jfd|i|W5QRSQRXdS)a Load an ORC object from the file path, returning a DataFrame. .. versionadded:: 1.0.0 Parameters ---------- path : str, path object, or file-like object String, path object (implementing ``os.PathLike[str]``), or file-like object implementing a binary ``read()`` function. The string could be a URL. Valid URL schemes include http, ftp, s3, and file. For file URLs, a host is expected. A local file could be: ``file://localhost/path/to/table.orc``. columns : list, default None If not None, only these columns will be read from the file. **kwargs Any additional kwargs are passed to pyarrow. Returns ------- DataFrame Notes ----- Before using this function you should read the :ref:`user guide about ORC ` and :ref:`install optional dependencies `. pyarrow.orcrbFZis_textrN)r rZORCFilehandlereadZ to_pandas)rrkwargsorchandlesZorc_filer1/tmp/pip-unpacked-wheel-xj8nt62q/pandas/io/orc.pyread_orc s  rpyarrow)engineindex engine_kwargsz$FilePath | WriteBuffer[bytes] | NonezLiteral['pyarrow']z bool | Nonezdict[str, Any] | Nonez bytes | None)dfrr r!r"rc Cs:|dkr|jjddk }|dkr$i}|jD],}t|sNt|sNt|sNt|r*tdq*|dkrhtdt |dd}t d}|dk}|rt }|dk st t |d d d f}t|tst z"|j|jj||d |jf|Wn.tk r } ztd| W5d} ~ XYnXW5QRX|r6t|t j s.t |SdS) a Write a DataFrame to the ORC format. .. versionadded:: 1.5.0 Parameters ---------- df : DataFrame The dataframe to be written to ORC. Raises NotImplementedError if dtype of one or more columns is category, unsigned integers, intervals, periods or sparse. path : str, file-like object or None, default None If a string, it will be used as Root Directory path when writing a partitioned dataset. By file-like object, we refer to objects with a write() method, such as a file handle (e.g. via builtin open function). If path is None, a bytes object is returned. engine : str, default 'pyarrow' ORC library to use. Pyarrow must be >= 7.0.0. index : bool, optional If ``True``, include the dataframe's index(es) in the file output. If ``False``, they will not be written to the file. If ``None``, similar to ``infer`` the dataframe's index(es) will be saved. However, instead of being saved as values, the RangeIndex will be stored as a range in the metadata so it doesn't require much space and is faster. Other indexes will be included as columns in the file output. engine_kwargs : dict[str, Any] or None, default None Additional keyword arguments passed to :func:`pyarrow.orc.write_table`. Returns ------- bytes if no path argument is provided else None Raises ------ NotImplementedError Dtype of one or more columns is category, unsigned integers, interval, period or sparse. ValueError engine is not pyarrow. Notes ----- * Before using this function you should read the :ref:`user guide about ORC ` and :ref:`install optional dependencies `. * This function requires `pyarrow `_ library. * For supported dtypes please refer to `supported ORC features in Arrow `__. * Currently timezones in datetime columns are not preserved when a dataframe is converted into ORC files. Nrz6The dtype of one or more columns is not supported yet.rzengine must be 'pyarrow'z7.0.0) min_versionrwbFr)Zpreserve_index)r!namesZdtypesr r r rNotImplementedError ValueErrorr ioBytesIOAssertionErrorr isinstancerZ write_tableZTableZ from_pandasr TypeErrorgetvalue) r#rr r!r"ZdtyperZwas_nonererrrto_orcGsV>   r0)N)N)__doc__ __future__rr)typesrtypingrrrZpandas._typingrrr Zpandas.compat._optionalr Zpandas.core.dtypes.commonr r r rZpandas.io.commonrZpandasrrr0rrrrs$     )