def ingest_data_driver(config_path: Path, base_url: Url,
data_graphs: Optional[List[Url]],
triple_store: Optional[Url], clear: bool) -> None:
"""Use an import.yaml file to ingest multiple CSV files into the data graph."""
with open(config_path, 'r', encoding='utf-8') as config_file:
config = yaml.safe_load(config_file)
validate(config, INGEST_CSV_CONFIG_SCHEMA)
steps = config['ingestion-steps']
if data_graphs is not None:
data_graph = data_graphs[0]
elif 'data-graph' in config:
data_graph = config['data-graph']
else:
logger.warning("Defaulting data-graph to %s", DEFAULT_DATA_GRAPH)
data_graph = DEFAULT_DATA_GRAPH
base_path = config_path.parent
if data_graphs is not None:
extra_data_graphs = data_graphs[1:]
elif 'extra-data-graphs' in config:
extra_data_graphs = config['extra-data-graphs']
else:
extra_data_graphs = []
conn = sparql_connection(base_url, data_graph, extra_data_graphs,
triple_store)
if clear:
clear_graph(conn)
for step in steps:
if 'owl' in step:
owl_file = step['owl']
print(f'Ingesting {str_highlight(str(owl_file)): <40}', end="")
try:
semtk3.upload_owl(base_path / owl_file, conn, "rack", "rack",
semtk3.SEMTK3_CONN_DATA)
except Exception as e:
print(str_bad(' FAIL'))
raise e
print(str_good(' OK'))
elif 'csv' in step:
ingest_csv(conn, step['nodegroup'], base_path / step['csv'])
def go() -> None:
return semtk3.upload_owl(owl_file, conn, "rack", "rack")