fsaintjacques commented on a change in pull request #7437:
URL: https://github.com/apache/arrow/pull/7437#discussion_r441633483
##########
File path: python/pyarrow/tests/test_dataset.py
##########
@@ -1522,19 +1522,20 @@ def _create_parquet_dataset_partitioned(root_path):
@pytest.mark.parquet
@pytest.mark.pandas
def test_parquet_dataset_factory_partitioned(tempdir):
- # TODO support for specifying partitioning scheme
-
root_path = tempdir / "test_parquet_dataset_factory_partitioned"
metadata_path, table = _create_parquet_dataset_partitioned(root_path)
- dataset = ds.parquet_dataset(metadata_path)
- # TODO partition column not yet included
- # assert dataset.schema.equals(table.schema)
+ partitioning = ds.partitioning(flavor="hive")
+ dataset = ds.parquet_dataset(metadata_path,
+ partitioning=partitioning,
+ partition_base_dir=str(root_path))
Review comment:
It is not needed anymore and 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:
us...@infra.apache.org
