def _handle_metadata(catalog, entity):
url_prefix = CATALOG_ENTITY_URLS.get(f'{catalog}_{entity}')
if url_prefix is None:
LOGGER.debug('URL not available for %s %s', catalog, entity)
# Set human as default when the relevant class QID
# is not an instance-of (P31) value
if SUPPORTED_ENTITIES.get(entity) == keys.CLASS_QUERY:
class_qid = target_database.get_class_qid(catalog, entity)
else:
class_qid = HUMAN_QID
return class_qid, url_prefix
def gather_qids(entity, catalog, catalog_pid):
LOGGER.info(
'Gathering Wikidata %s items with no %s identifiers ...',
entity,
catalog,
)
query_type = keys.DATASET, constants.SUPPORTED_ENTITIES.get(entity)
qids = set(
sparql_queries.run_query(
query_type,
target_database.get_class_qid(catalog, entity),
catalog_pid,
0,
))
LOGGER.info('Got %d Wikidata items', len(qids))
return qids
def gather_target_ids(entity, catalog, catalog_pid, aggregated):
LOGGER.info('Gathering Wikidata %s items with %s identifiers ...', entity,
catalog)
query_type = keys.IDENTIFIER, constants.SUPPORTED_ENTITIES.get(entity)
for qid, target_id in sparql_queries.run_query(
query_type,
target_database.get_class_qid(catalog, entity),
catalog_pid,
0,
):
if not aggregated.get(qid):
aggregated[qid] = {keys.TID: set()}
aggregated[qid][keys.TID].add(target_id)
LOGGER.info('Got %d %s identifiers', len(aggregated), catalog)