BUG: Fix pd.read_orc raising AttributeError (pandas-dev#40970)

Author: amznero

doc/source/getting_started/install.rst

@@ -362,6 +362,21 @@ pyarrow                   0.15.0             Parquet, ORC, and feather reading /
 pyreadstat                                   SPSS files (.sav) reading
 ========================= ================== =============================================================
 
+.. _install.warn_orc:
+
+.. warning::
+
+    * If you want to use :func:`~pandas.read_orc`, it is highly recommended to install pyarrow using conda.
+      The following is a summary of the environment in which :func:`~pandas.read_orc` can work.
+
+      ========================= ================== =============================================================
+      System                    Conda              PyPI
+      ========================= ================== =============================================================
+      Linux                     Successful         Failed(pyarrow==3.0 Successful)
+      macOS                     Successful         Failed
+      Windows                   Failed             Failed
+      ========================= ================== =============================================================
+
 Access data in the cloud
 ^^^^^^^^^^^^^^^^^^^^^^^^
 

doc/source/user_guide/io.rst

@@ -5443,6 +5443,11 @@ Similar to the :ref:`parquet <io.parquet>` format, the `ORC Format <https://orc.
 for data frames. It is designed to make reading data frames efficient. pandas provides *only* a reader for the
 ORC format, :func:`~pandas.read_orc`. This requires the `pyarrow <https://arrow.apache.org/docs/python/>`__ library.
 
+.. warning::
+
+   * It is *highly recommended* to install pyarrow using conda due to some issues occurred by pyarrow.
+   * :func:`~pandas.read_orc` is not supported on Windows yet, you can find valid environments on :ref:`install optional dependencies <install.warn_orc>`.
+
 .. _io.sql:
 
 SQL queries

doc/source/whatsnew/v1.3.0.rst

@@ -791,6 +791,7 @@ I/O
 - Bug in :func:`read_sas` raising ``ValueError`` when ``datetimes`` were null (:issue:`39725`)
 - Bug in :func:`read_excel` dropping empty values from single-column spreadsheets (:issue:`39808`)
 - Bug in :meth:`DataFrame.to_string` misplacing the truncation column when ``index=False`` (:issue:`40907`)
+- Bug in :func:`read_orc` always raising ``AttributeError`` (:issue:`40918`)
 
 Period
 ^^^^^^

pandas/io/orc.py

@@ -1,10 +1,10 @@
 """ orc compat """
 from __future__ import annotations
 
-import distutils
 from typing import TYPE_CHECKING
 
 from pandas._typing import FilePathOrBuffer
+from pandas.compat._optional import import_optional_dependency
 
 from pandas.io.common import get_handle
 
@@ -42,13 +42,16 @@ def read_orc(
     Returns
     -------
     DataFrame
+
+    Notes
+    -------
+    Before using this function you should read the :ref:`user guide about ORC <io.orc>`
+    and :ref:`install optional dependencies <install.warn_orc>`.
     """
     # we require a newer version of pyarrow than we support for parquet
-    import pyarrow
 
-    if distutils.version.LooseVersion(pyarrow.__version__) < "0.13.0":
-        raise ImportError("pyarrow must be >= 0.13.0 for read_orc")
+    orc = import_optional_dependency("pyarrow.orc")
 
     with get_handle(path, "rb", is_text=False) as handles:
-        orc_file = pyarrow.orc.ORCFile(handles.handle)
+        orc_file = orc.ORCFile(handles.handle)
         return orc_file.read(columns=columns, **kwargs).to_pandas()

pandas/tests/io/test_orc.py

@@ -9,7 +9,6 @@
 from pandas import read_orc
 import pandas._testing as tm
 
-pytest.importorskip("pyarrow", minversion="0.13.0")
 pytest.importorskip("pyarrow.orc")
 
 pytestmark = pytest.mark.filterwarnings(