`VgdZddlmZddlZddlmZddlmZmZm Z ddl m Z m Z m Z ddlmZddlmZmZmZmZdd lmZerdd lmZ d dd Z dd ddd  ddZy)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) DataFramec td}t|dd5}|j|j}|jdd|i|j cdddS#1swYyxYw)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.orcrbFis_textcolumnsN)r rORCFilehandleread to_pandas)pathrkwargsorchandlesorc_files N/var/www/html/hubwallet-dev/venv/lib/python3.12/site-packages/pandas/io/orc.pyread_orcr# sg@ %] 3C D$ .D';;w~~.x}}7W77AACDDDs =A!!A*pyarrow)engineindex engine_kwargsc||jjddu}|i}|jD]9}t|s"t |st |s t |s0td|dk7r tdt|d}td}|du}|rtj}|Jt|d d 5}t|tsJ |j|j j#|| |j$fi| ddd|r,t|tjsJ|j)Sy#t&$r} td| d} ~ wwxYw#1swYUxYw) 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.r$zengine must be 'pyarrow'z7.0.0) min_versionrwbFr)preserve_index)r&namesdtypesr r rrNotImplementedError ValueErrorr ioBytesIOr isinstancer write_tableTable from_pandasr TypeErrorgetvalue) dfrr%r&r'dtyperwas_noner es r"to_orcr<Gs{| }q!-    ' 'u%(/%H  344 'G DF $] 3Ct|Hzz|    D$ . '&*---  COO ((E(B    $ +++}}  %H    s*>E 9E E EEE  E))N)rzFilePath | ReadBuffer[bytes]rzlist[str] | Nonereturnr) r8rrz$FilePath | WriteBuffer[bytes] | Noner%zLiteral['pyarrow']r&z bool | Noner'zdict[str, Any] | Noner=z bytes | None)__doc__ __future__rr0typesrtypingrrrpandas._typingrr r pandas.compat._optionalr pandas.core.dtypes.commonr r rrpandas.io.commonrpandasrr#r<rr"rHs"   ?( EI$D &$D1A$D$DR26i"++/ ii .i  i  i ) iirG