westonpace commented on a change in pull request #9323:
URL: https://github.com/apache/arrow/pull/9323#discussion_r576476421
##########
File path: python/pyarrow/tests/test_dataset.py
##########
@@ -1587,33 +1587,54 @@ def test_open_dataset_non_existing_file():
@pytest.mark.parquet
@pytest.mark.parametrize('partitioning', ["directory", "hive"])
[email protected]('null_fallback', ['xyz', None])
@pytest.mark.parametrize('partition_keys', [
(["A", "B", "C"], [1, 2, 3]),
([1, 2, 3], ["A", "B", "C"]),
(["A", "B", "C"], ["D", "E", "F"]),
([1, 2, 3], [4, 5, 6]),
+ ([1, None, 3], ["A", "B", "C"]),
+ ([1, 2, 3], ["A", None, "C"]),
+ ([None, 2, 3], [None, 2, 3]),
])
-def test_open_dataset_partitioned_dictionary_type(tempdir, partitioning,
- partition_keys):
+def test_open_dataset_partitioned_dictionary_type(
+ tempdir, partitioning, null_fallback, partition_keys
+):
# ARROW-9288 / ARROW-9476
import pyarrow.parquet as pq
- table = pa.table({'a': range(9), 'b': [0.] * 4 + [1.] * 5})
+
+ table = pa.table({'a': range(9), 'b': [0.0] * 4 + [1.0] * 5})
+
+ if None in partition_keys[0] or None in partition_keys[1]:
+ # Directory partitioning can't handle the first part being null
+ return
Review comment:
Good catch, this test had a few other issues as well that I've fixed.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
