fix doc error & make simpler

Author: jreback

doc/source/user_guide/io.rst

@@ -4866,7 +4866,7 @@ ORC
 
 .. versionadded:: 1.0.0
 
-Similar to the `parquet <io.parquet>` format, the `ORC Format <//https://orc.apache.org/>`__ binary columnar serialization
+Similar to the :ref:`parquet <io.parquet>` format, the `ORC Format <//https://orc.apache.org/>`__ is a binary columnar serialization
 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.
 

pandas/io/orc.py

@@ -3,8 +3,6 @@
 import distutils
 from typing import TYPE_CHECKING, List, Optional
 
-from pandas.compat._optional import import_optional_dependency
-
 from pandas._typing import FilePathOrBuffer
 
 from pandas.io.common import get_filepath_or_buffer
@@ -13,34 +11,9 @@
     from pandas import DataFrame
 
 
-class PyArrowImpl:
-    def __init__(self):
-        pyarrow = import_optional_dependency(
-            "pyarrow", extra="pyarrow is required for orc support."
-        )
-
-        # 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")
-
-        import pyarrow.orc
-
-        self.api = pyarrow
-
-    def read(
-        self, path: FilePathOrBuffer, columns: Optional[List[str]] = None, **kwargs
-    ) -> "DataFrame":
-        path, _, _, _ = get_filepath_or_buffer(path)
-        orc_file = self.api.orc.ORCFile(path)
-        result = orc_file.read(columns=columns, **kwargs).to_pandas()
-        return result
-
-
 def read_orc(
     path: FilePathOrBuffer, columns: Optional[List[str]] = None, **kwargs,
-):
+) -> "DataFrame":
     """
     Load an ORC object from the file path, returning a DataFrame.
 
@@ -70,5 +43,15 @@ def read_orc(
     DataFrame
     """
 
-    impl = PyArrowImpl()
-    return impl.read(path, columns=columns, **kwargs)
+    # 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")
+
+    import pyarrow.orc
+
+    path, _, _, _ = get_filepath_or_buffer(path)
+    orc_file = pyarrow.orc.ORCFile(path)
+    result = orc_file.read(columns=columns, **kwargs).to_pandas()
+    return result

pandas/tests/io/test_orc.py

@@ -5,12 +5,16 @@
 import numpy as np
 import pytest
 
+from pandas.compat import is_platform_windows
+
 import pandas as pd
 from pandas import read_orc
 import pandas.util.testing as tm
 
 pytest.importorskip("pyarrow", minversion="0.13.0")
 
+pytestmark = pytest.mark.skipif(is_platform_windows, "skipping on windows")
+
 pytestmark = pytest.mark.filterwarnings(
     "ignore:RangeIndex.* is deprecated:DeprecationWarning"
 )