wyzhao commented on a change in pull request #8672:
URL: https://github.com/apache/arrow/pull/8672#discussion_r529067072
##########
File path: python/pyarrow/tests/test_parquet.py
##########
@@ -2009,6 +2021,37 @@ def test_filters_inclusive_set(tempdir,
use_legacy_dataset):
assert False not in result_df['boolean'].values
[email protected]
+@parametrize_legacy_dataset
+def test_filters_no_partition_found(tempdir, use_legacy_dataset):
+ fs = LocalFileSystem._get_instance()
+ base_path = tempdir
+
+ integer_keys = [0, 1]
+ string_keys = ['a', 'b', 'c']
+ boolean_keys = [True, False]
+ partition_spec = [
+ ['integer', integer_keys],
+ ['string', string_keys],
+ ['boolean', boolean_keys]
+ ]
+
+ df = pd.DataFrame({
+ 'integer': np.array(integer_keys, dtype='i4').repeat(15),
+ 'string': np.tile(np.tile(np.array(string_keys, dtype=object), 5), 2),
+ 'boolean': np.tile(np.tile(np.array(boolean_keys, dtype='bool'), 5),
+ 3),
+ }, columns=['integer', 'string', 'boolean'])
+
+ _generate_partition_directories(fs, base_path, partition_spec, df)
+
+ with pytest.raises(ValueError, match=r"No partition is found."):
Review comment:
I removed this change. Will have a separate JIRA.
----------------------------------------------------------------
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]
