def test_standalone_spark_parquet_datasource(test_parquet_folder_connection_path, spark_session):
assert spark_session # Ensure a sparksession exists
datasource = SparkDFDatasource('SparkParquet', generators={
"subdir_reader": {
"class_name": "SubdirReaderBatchKwargsGenerator",
"base_directory": test_parquet_folder_connection_path
}
}
)
assert datasource.get_available_data_asset_names()["subdir_reader"]["names"] == [('test', 'file')]
batch = datasource.get_batch(batch_kwargs={
"path": os.path.join(test_parquet_folder_connection_path,
'test.parquet')
})
assert isinstance(batch, Batch)
# NOTE: below is a great example of CSV vs. Parquet typing: pandas reads content as string, spark as int
assert batch.data.head()['col_1'] == 1
assert batch.data.count() == 5
# Limit should also work
batch = datasource.get_batch(batch_kwargs={
"path": os.path.join(test_parquet_folder_connection_path,
'test.parquet'),
"limit": 2
})
assert isinstance(batch, Batch)
# NOTE: below is a great example of CSV vs. Parquet typing: pandas reads content as string, spark as int
assert batch.data.head()['col_1'] == 1
assert batch.data.count() == 2
def test_standalone_spark_parquet_datasource(test_parquet_folder_connection_path, spark_session):
assert spark_session # Ensure a sparksession exists
datasource = SparkDFDatasource('SparkParquet', base_directory=test_parquet_folder_connection_path)
assert datasource.get_available_data_asset_names() == {
"default": ['test']
}
dataset = datasource.get_batch('test',
expectation_suite_name="default",
batch_kwargs={
"path": os.path.join(test_parquet_folder_connection_path,
'test.parquet')
})
assert isinstance(dataset, SparkDFDataset)
# NOTE: below is a great example of CSV vs. Parquet typing: pandas reads content as string, spark as int
assert dataset.spark_df.head()['col_1'] == 1
assert dataset.spark_df.count() == 5
# Limit should also work
dataset = datasource.get_batch('test',
expectation_suite_name="default",
batch_kwargs={
"path": os.path.join(test_parquet_folder_connection_path,
'test.parquet'),
"limit": 2
})
assert isinstance(dataset, SparkDFDataset)
# NOTE: below is a great example of CSV vs. Parquet typing: pandas reads content as string, spark as int
assert dataset.spark_df.head()['col_1'] == 1
assert dataset.spark_df.count() == 2
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_standalone_spark_csv_datasource(test_folder_connection_path_csv,
test_backends):
if "SparkDFDataset" not in test_backends:
pytest.skip(
"Spark has not been enabled, so this test must be skipped.")
datasource = SparkDFDatasource(
"SparkParquet",
batch_kwargs_generators={
"subdir_reader": {
"class_name": "SubdirReaderBatchKwargsGenerator",
"base_directory": test_folder_connection_path_csv,
}
},
)
assert datasource.get_available_data_asset_names(
)["subdir_reader"]["names"] == [("test", "file")]
batch = datasource.get_batch(
batch_kwargs={
"path": os.path.join(test_folder_connection_path_csv, "test.csv"),
"reader_options": {
"header": True
},
})
assert isinstance(batch, Batch)
# NOTE: below is a great example of CSV vs. Parquet typing: pandas reads content as string, spark as int
assert batch.data.head()["col_1"] == "1"
def test_invalid_reader_sparkdf_datasource(tmp_path_factory):
pyspark_skip = pytest.importorskip("pyspark")
basepath = str(tmp_path_factory.mktemp("test_invalid_reader_sparkdf_datasource"))
datasource = SparkDFDatasource('mysparksource', base_directory=basepath)
with open(os.path.join(basepath, "idonotlooklikeacsvbutiam.notrecognized"), "w") as newfile:
newfile.write("a,b\n1,2\n3,4\n")
with pytest.raises(BatchKwargsError) as exc:
datasource.get_batch("idonotlooklikeacsvbutiam.notrecognized", expectation_suite_name="default", batch_kwargs={
"path": os.path.join(basepath, "idonotlooklikeacsvbutiam.notrecognized")
})
assert "Unable to determine reader for path" in exc.message
with pytest.raises(BatchKwargsError) as exc:
datasource.get_batch("idonotlooklikeacsvbutiam.notrecognized", expectation_suite_name="default", batch_kwargs={
"path": os.path.join(basepath, "idonotlooklikeacsvbutiam.notrecognized")
}, reader_method="blarg")
assert "Unknown reader method: blarg" in exc.message
with pytest.raises(BatchKwargsError) as exc:
datasource.get_batch("idonotlooklikeacsvbutiam.notrecognized", expectation_suite_name="default", batch_kwargs={
"path": os.path.join(basepath, "idonotlooklikeacsvbutiam.notrecognized")
}, reader_method="excel")
assert "Unsupported reader: excel" in exc.message
dataset = datasource.get_batch("idonotlooklikeacsvbutiam.notrecognized", expectation_suite_name="default", batch_kwargs={
"path": os.path.join(basepath, "idonotlooklikeacsvbutiam.notrecognized")
},
reader_method="csv", header=True)
assert dataset.spark_df.head()["a"] == "1"
def test_invalid_reader_sparkdf_datasource(tmp_path_factory):
pytest.importorskip("pyspark")
basepath = str(
tmp_path_factory.mktemp("test_invalid_reader_sparkdf_datasource"))
datasource = SparkDFDatasource('mysparksource',
batch_kwargs_generators={
"subdir_reader": {
"class_name":
"SubdirReaderBatchKwargsGenerator",
"base_directory": basepath
}
})
with open(os.path.join(basepath, "idonotlooklikeacsvbutiam.notrecognized"),
"w") as newfile:
newfile.write("a,b\n1,2\n3,4\n")
with pytest.raises(BatchKwargsError) as exc:
datasource.get_batch(
batch_kwargs={
"path":
os.path.join(basepath,
"idonotlooklikeacsvbutiam.notrecognized")
})
assert "Unable to determine reader for path" in exc.value.message
with pytest.raises(BatchKwargsError) as exc:
datasource.get_batch(
batch_kwargs={
"path":
os.path.join(basepath,
"idonotlooklikeacsvbutiam.notrecognized"),
"reader_method":
"blarg"
})
assert "Unknown reader method: blarg" in exc.value.message
with pytest.raises(BatchKwargsError) as exc:
datasource.get_batch(
batch_kwargs={
"path":
os.path.join(basepath,
"idonotlooklikeacsvbutiam.notrecognized"),
"reader_method":
"excel"
})
assert "Unknown reader: excel" in exc.value.message
batch = datasource.get_batch(
batch_kwargs={
"path":
os.path.join(basepath, "idonotlooklikeacsvbutiam.notrecognized"),
"reader_method":
"csv",
"reader_options": {
'header': True
}
})
assert batch.data.head()["a"] == "1"
def test_standalone_spark_csv_datasource(test_folder_connection_path):
datasource = SparkDFDatasource('SparkParquet',
base_directory=test_folder_connection_path)
assert datasource.get_available_data_asset_names() == {
"default": set(['test'])
}
dataset = datasource.get_batch('test', header=True)
assert isinstance(dataset, SparkDFDataset)
# NOTE: below is a great example of CSV vs. Parquet typing: pandas reads content as string, spark as int
assert dataset.spark_df.head()['col_1'] == '1'
def test_invalid_reader_sparkdf_datasource(tmp_path_factory, test_backends):
if "SparkDFDataset" not in test_backends:
pytest.skip("Spark has not been enabled, so this test must be skipped.")
basepath = str(tmp_path_factory.mktemp("test_invalid_reader_sparkdf_datasource"))
datasource = SparkDFDatasource(
"mysparksource",
batch_kwargs_generators={
"subdir_reader": {
"class_name": "SubdirReaderBatchKwargsGenerator",
"base_directory": basepath,
}
},
)
with open(
os.path.join(basepath, "idonotlooklikeacsvbutiam.notrecognized"), "w"
) as newfile:
newfile.write("a,b\n1,2\n3,4\n")
with pytest.raises(BatchKwargsError) as exc:
datasource.get_batch(
batch_kwargs={
"path": os.path.join(basepath, "idonotlooklikeacsvbutiam.notrecognized")
}
)
assert "Unable to determine reader for path" in exc.value.message
with pytest.raises(BatchKwargsError) as exc:
datasource.get_batch(
batch_kwargs={
"path": os.path.join(
basepath, "idonotlooklikeacsvbutiam.notrecognized"
),
"reader_method": "blarg",
}
)
assert "Unknown reader method: blarg" in exc.value.message
with pytest.raises(BatchKwargsError) as exc:
datasource.get_batch(
batch_kwargs={
"path": os.path.join(
basepath, "idonotlooklikeacsvbutiam.notrecognized"
),
"reader_method": "excel",
}
)
assert "Unknown reader: excel" in exc.value.message
batch = datasource.get_batch(
batch_kwargs={
"path": os.path.join(basepath, "idonotlooklikeacsvbutiam.notrecognized"),
"reader_method": "csv",
"reader_options": {"header": True},
}
)
assert batch.data.head()["a"] == "1"
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_standalone_spark_csv_datasource(test_folder_connection_path):
pyspark_skip = pytest.importorskip("pyspark")
datasource = SparkDFDatasource('SparkParquet', base_directory=test_folder_connection_path)
assert datasource.get_available_data_asset_names() == {
"default": ['test']
}
dataset = datasource.get_batch('test',
expectation_suite_name="default",
batch_kwargs={
"path": os.path.join(test_folder_connection_path,
'test.csv')
},
reader_options={"header": True})
assert isinstance(dataset, SparkDFDataset)
# NOTE: below is a great example of CSV vs. Parquet typing: pandas reads content as string, spark as int
assert dataset.spark_df.head()['col_1'] == '1'
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
def test_standalone_spark_csv_datasource(test_folder_connection_path):
pyspark_skip = pytest.importorskip("pyspark")
datasource = SparkDFDatasource('SparkParquet',
generators={"subdir_reader": {
"class_name": "SubdirReaderBatchKwargsGenerator",
"base_directory": test_folder_connection_path
}
}
)
assert datasource.get_available_data_asset_names()["subdir_reader"]["names"] == [('test', 'file')]
batch = datasource.get_batch(batch_kwargs={
"path": os.path.join(test_folder_connection_path,
'test.csv'),
"reader_options": {"header": True}
})
assert isinstance(batch, Batch)
# NOTE: below is a great example of CSV vs. Parquet typing: pandas reads content as string, spark as int
assert batch.data.head()['col_1'] == '1'
