def run_node(node: Node,
catalog: DataCatalog,
is_async: bool = False,
run_id: str = None) -> Node:
"""Run a single `Node` with inputs from and outputs to the `catalog`.
Args:
node: The ``Node`` to run.
catalog: A ``DataCatalog`` containing the node's inputs and outputs.
is_async: If True, the node inputs and outputs are loaded and saved
asynchronously with threads. Defaults to False.
run_id: The id of the pipeline run
Returns:
The node argument.
"""
if is_async:
node = _run_node_async(node, catalog, run_id)
else:
node = _run_node_sequential(node, catalog, run_id)
for name in node.confirms:
catalog.confirm(name)
return node
def test_confirm(self, mocker, caplog):
"""Confirm the dataset"""
mock_ds = mocker.Mock()
data_catalog = DataCatalog(data_sets={"mocked": mock_ds})
data_catalog.confirm("mocked")
mock_ds.confirm.assert_called_once_with()
assert caplog.record_tuples == [("kedro.io.data_catalog", logging.INFO,
"Confirming DataSet 'mocked'")]
def run_node(node: Node, catalog: DataCatalog) -> Node:
"""Run a single `Node` with inputs from and outputs to the `catalog`.
Args:
node: The ``Node`` to run.
catalog: A ``DataCatalog`` containing the node's inputs and outputs.
Returns:
The node argument.
"""
inputs = {name: catalog.load(name) for name in node.inputs}
outputs = node.run(inputs)
for name, data in outputs.items():
catalog.save(name, data)
for name in node.confirms:
catalog.confirm(name)
return node