def test_spark_datasource_processes_dataset_options(
test_folder_connection_path_csv, test_backends, empty_data_context):
context: DataContext = empty_data_context
if "SparkDFDataset" not in test_backends:
pytest.skip(
"Spark has not been enabled, so this test must be skipped.")
datasource = SparkDFDatasource(
"PandasCSV",
batch_kwargs_generators={
"subdir_reader": {
"class_name": "SubdirReaderBatchKwargsGenerator",
"base_directory": test_folder_connection_path_csv,
}
},
)
batch_kwargs = datasource.build_batch_kwargs("subdir_reader",
data_asset_name="test")
batch_kwargs["dataset_options"] = {"caching": False, "persist": False}
batch = datasource.get_batch(batch_kwargs)
validator = BridgeValidator(
batch,
ExpectationSuite(expectation_suite_name="foo", data_context=context))
dataset = validator.get_dataset()
assert dataset.caching is False
assert dataset._persist is False
def test_pandas_datasource_processes_dataset_options(test_folder_connection_path):
datasource = SparkDFDatasource('PandasCSV', generators={
"subdir_reader": {
"class_name": "SubdirReaderBatchKwargsGenerator",
"base_directory": test_folder_connection_path
}
}
)
batch_kwargs = datasource.build_batch_kwargs("subdir_reader", name="test")
batch_kwargs["dataset_options"] = {"caching": False, "persist": False}
batch = datasource.get_batch(batch_kwargs)
validator = Validator(batch, ExpectationSuite(expectation_suite_name="foo"))
dataset = validator.get_dataset()
assert dataset.caching is False
assert dataset._persist is False
def test_pandas_datasource_processes_dataset_options(test_folder_connection_path, test_backends):
if "SparkDFDataset" not in test_backends:
pytest.skip("Spark has not been enabled, so this test must be skipped.")
datasource = SparkDFDatasource('PandasCSV', batch_kwargs_generators={
"subdir_reader": {
"class_name": "SubdirReaderBatchKwargsGenerator",
"base_directory": test_folder_connection_path
}
}
)
batch_kwargs = datasource.build_batch_kwargs("subdir_reader", name="test")
batch_kwargs["dataset_options"] = {"caching": False, "persist": False}
batch = datasource.get_batch(batch_kwargs)
validator = Validator(batch, ExpectationSuite(expectation_suite_name="foo"))
dataset = validator.get_dataset()
assert dataset.caching is False
assert dataset._persist is False