def test_get_batch_with_no_s3_configured(batch_with_split_on_whole_table_s3):
# if S3 was not configured
execution_engine_no_s3 = PandasExecutionEngine()
execution_engine_no_s3._s3 = None
with pytest.raises(ge_exceptions.ExecutionEngineError):
execution_engine_no_s3.get_batch_data(
batch_spec=batch_with_split_on_whole_table_s3)
def test_get_batch_with_no_azure_configured(azure_batch_spec):
# if Azure BlobServiceClient was not configured
execution_engine_no_azure = PandasExecutionEngine()
execution_engine_no_azure._azure = None
# Raises error due the connection object not being set
with pytest.raises(ge_exceptions.ExecutionEngineError):
execution_engine_no_azure.get_batch_data(batch_spec=azure_batch_spec)
def test_get_batch_with_no_s3_configured():
batch_spec = S3BatchSpec(
path="s3a://i_dont_exist",
reader_method="read_csv",
splitter_method="_split_on_whole_table",
)
# if S3 was not configured
execution_engine_no_s3 = PandasExecutionEngine()
with pytest.raises(ge_exceptions.ExecutionEngineError):
execution_engine_no_s3.get_batch_data(batch_spec=batch_spec)
def test_get_batch_with_split_on_whole_table_s3():
region_name: str = "us-east-1"
bucket: str = "test_bucket"
conn = boto3.resource("s3", region_name=region_name)
conn.create_bucket(Bucket=bucket)
client = boto3.client("s3", region_name=region_name)
test_df: pd.DataFrame = pd.DataFrame(data={"col1": [1, 2], "col2": [3, 4]})
keys: List[str] = [
"path/A-100.csv",
"path/A-101.csv",
"directory/B-1.csv",
"directory/B-2.csv",
]
for key in keys:
client.put_object(Bucket=bucket,
Body=test_df.to_csv(index=False).encode("utf-8"),
Key=key)
path = "path/A-100.csv"
full_path = f"s3a://{os.path.join(bucket, path)}"
test_df = PandasExecutionEngine().get_batch_data(batch_spec=S3BatchSpec(
path=full_path,
reader_method="read_csv",
splitter_method="_split_on_whole_table",
))
assert test_df.dataframe.shape == (2, 2)
# if S3 was not configured
execution_engine_no_s3 = PandasExecutionEngine()
execution_engine_no_s3._s3 = None
with pytest.raises(ge_exceptions.ExecutionEngineError):
execution_engine_no_s3.get_batch_data(batch_spec=S3BatchSpec(
path=full_path,
reader_method="read_csv",
splitter_method="_split_on_whole_table",
))
def test_get_batch_with_gcs_misconfigured(gcs_batch_spec):
# gcs_batchspec point to data that the ExecutionEngine does not have access to
execution_engine_no_gcs = PandasExecutionEngine()
# Raises error if batch_spec causes ExecutionEngine error
with pytest.raises(ge_exceptions.ExecutionEngineError):
execution_engine_no_gcs.get_batch_data(batch_spec=gcs_batch_spec)