David Li created ARROW-16372:
--------------------------------

             Summary: [Python] Tests failing on s390x because they use Parquet
                 Key: ARROW-16372
                 URL: https://issues.apache.org/jira/browse/ARROW-16372
             Project: Apache Arrow
          Issue Type: Bug
          Components: Python
            Reporter: David Li


If I understand correctly, the Parquet implementation does not work on 
big-endian? So these tests need to be properly marked?

https://app.travis-ci.com/github/apache/arrow/jobs/568309096

{noformat}
=================================== FAILURES ===================================

______________________________ test_dataset_join _______________________________

tempdir = PosixPath('/tmp/pytest-of-root/pytest-0/test_dataset_join0')

    @pytest.mark.dataset

    def test_dataset_join(tempdir):

        t1 = pa.table({

            "colA": [1, 2, 6],

            "col2": ["a", "b", "f"]

        })

>       ds.write_dataset(t1, tempdir / "t1", format="parquet")

usr/local/lib/python3.8/dist-packages/pyarrow/tests/test_dataset.py:4428: 

_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

usr/local/lib/python3.8/dist-packages/pyarrow/dataset.py:880: in write_dataset

    format = _ensure_format(format)

_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

obj = 'parquet'

    def _ensure_format(obj):

        if isinstance(obj, FileFormat):

            return obj

        elif obj == "parquet":

            if not _parquet_available:

>               raise ValueError(_parquet_msg)

E               ValueError: The pyarrow installation is not built with support 
for the Parquet file format.

usr/local/lib/python3.8/dist-packages/pyarrow/dataset.py:283: ValueError

_________________________ test_dataset_join_unique_key _________________________

tempdir = 
PosixPath('/tmp/pytest-of-root/pytest-0/test_dataset_join_unique_key0')

    @pytest.mark.dataset

    def test_dataset_join_unique_key(tempdir):

        t1 = pa.table({

            "colA": [1, 2, 6],

            "col2": ["a", "b", "f"]

        })

>       ds.write_dataset(t1, tempdir / "t1", format="parquet")

usr/local/lib/python3.8/dist-packages/pyarrow/tests/test_dataset.py:4459: 

_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

usr/local/lib/python3.8/dist-packages/pyarrow/dataset.py:880: in write_dataset

    format = _ensure_format(format)

_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

obj = 'parquet'

    def _ensure_format(obj):

        if isinstance(obj, FileFormat):

            return obj

        elif obj == "parquet":

            if not _parquet_available:

>               raise ValueError(_parquet_msg)

E               ValueError: The pyarrow installation is not built with support 
for the Parquet file format.

usr/local/lib/python3.8/dist-packages/pyarrow/dataset.py:283: ValueError

_________________________ test_dataset_join_collisions _________________________

tempdir = 
PosixPath('/tmp/pytest-of-root/pytest-0/test_dataset_join_collisions0')

    @pytest.mark.dataset

    def test_dataset_join_collisions(tempdir):

        t1 = pa.table({

            "colA": [1, 2, 6],

            "colB": [10, 20, 60],

            "colVals": ["a", "b", "f"]

        })

>       ds.write_dataset(t1, tempdir / "t1", format="parquet")

usr/local/lib/python3.8/dist-packages/pyarrow/tests/test_dataset.py:4491: 

_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

usr/local/lib/python3.8/dist-packages/pyarrow/dataset.py:880: in write_dataset

    format = _ensure_format(format)

_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

obj = 'parquet'

    def _ensure_format(obj):

        if isinstance(obj, FileFormat):

            return obj

        elif obj == "parquet":

            if not _parquet_available:

>               raise ValueError(_parquet_msg)

E               ValueError: The pyarrow installation is not built with support 
for the Parquet file format.

usr/local/lib/python3.8/dist-packages/pyarrow/dataset.py:283: ValueError

_________________________ test_parquet_invalid_version _________________________

tempdir = 
PosixPath('/tmp/pytest-of-root/pytest-0/test_parquet_invalid_version0')

    def test_parquet_invalid_version(tempdir):

        table = pa.table({'a': [1, 2, 3]})

        with pytest.raises(ValueError, match="Unsupported Parquet format 
version"):

>           _write_table(table, tempdir / 'test_version.parquet', version="2.2")

E           NameError: name '_write_table' is not defined

usr/local/lib/python3.8/dist-packages/pyarrow/tests/parquet/test_basic.py:52: 
NameError{noformat}



--
This message was sent by Atlassian Jira
(v8.20.7#820007)

Reply via email to