2021-01-09 15:20:56 +01:00
|
|
|
""" orc compat """
|
|
|
|
|
|
|
|
import distutils
|
|
|
|
from typing import TYPE_CHECKING, List, Optional
|
|
|
|
|
|
|
|
from pandas._typing import FilePathOrBuffer
|
|
|
|
|
2021-01-30 22:29:33 +01:00
|
|
|
from pandas.io.common import get_filepath_or_buffer
|
2021-01-09 15:20:56 +01:00
|
|
|
|
|
|
|
if TYPE_CHECKING:
|
|
|
|
from pandas import DataFrame
|
|
|
|
|
|
|
|
|
|
|
|
def read_orc(
|
2021-01-30 22:29:33 +01:00
|
|
|
path: FilePathOrBuffer, columns: Optional[List[str]] = None, **kwargs,
|
2021-01-09 15:20:56 +01:00
|
|
|
) -> "DataFrame":
|
|
|
|
"""
|
|
|
|
Load an ORC object from the file path, returning a DataFrame.
|
|
|
|
|
|
|
|
.. versionadded:: 1.0.0
|
|
|
|
|
|
|
|
Parameters
|
|
|
|
----------
|
|
|
|
path : str, path object or file-like object
|
|
|
|
Any valid string path is acceptable. 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``.
|
|
|
|
|
|
|
|
If you want to pass in a path object, pandas accepts any
|
|
|
|
``os.PathLike``.
|
|
|
|
|
|
|
|
By file-like object, we refer to objects with a ``read()`` method,
|
2021-01-30 22:29:33 +01:00
|
|
|
such as a file handler (e.g. via builtin ``open`` function)
|
2021-01-09 15:20:56 +01:00
|
|
|
or ``StringIO``.
|
|
|
|
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
|
|
|
|
"""
|
|
|
|
# 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")
|
|
|
|
|
2021-01-30 22:29:33 +01:00
|
|
|
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
|