Merge pull request #692 from hubmapconsortium/Derek-Furst/provenance-skip

Derek furst/provenance skip

Author: yuanzhou

src/app.py

@@ -769,42 +769,9 @@ def get_entity_provenance(id):
     # Normalize the raw provenance nodes based on the yaml schema
     normalized_provenance_dict = {
         'relationships': raw_provenance_dict['relationships'],
-        'nodes': []
+        'nodes': raw_provenance_dict['nodes']
     }
 
-    for node_dict in raw_provenance_dict['nodes']:
-        # The schema yaml doesn't handle Lab nodes, just leave it as is
-        if (node_dict['label'] == 'Entity') and (node_dict['entity_type'] != 'Lab'):
-            # Generate trigger data
-            # Skip some of the properties that are time-consuming to generate via triggers:
-            # director_ancestor for Sample, and direct_ancestors for Dataset
-            # Also skip next_revision_uuid and previous_revision_uuid for Dataset to avoid additional
-            # checks when the target Dataset is public but the revisions are not public
-            properties_to_skip = [
-                'direct_ancestors',
-                'direct_ancestor',
-                'next_revision_uuid',
-                'previous_revision_uuid'
-            ]
-
-            # We'll need to return all the properties (except the ones to skip from above list)
-            # including those generated by `on_read_trigger` to have a complete result
-            # The 'on_read_trigger' doesn't really need a token
-            complete_entity_dict = schema_manager.get_complete_entity_result(token, node_dict, properties_to_skip)
-
-            # Filter out properties not defined or not to be exposed in the schema yaml
-            normalized_entity_dict = schema_manager.normalize_entity_result_for_response(complete_entity_dict)
-
-            # Now the node to be used by provenance is all regulated by the schema
-            normalized_provenance_dict['nodes'].append(normalized_entity_dict)
-        elif node_dict['label'] == 'Activity':
-            # Normalize Activity nodes too
-            normalized_activity_dict = schema_manager.normalize_activity_result_for_response(node_dict)
-            normalized_provenance_dict['nodes'].append(normalized_activity_dict)
-        else:
-            # Skip Entity Lab nodes
-            normalized_provenance_dict['nodes'].append(node_dict)
-
     provenance_json = provenance.get_provenance_history(uuid, normalized_provenance_dict, auth_helper_instance)
 
     # Response with the provenance details

src/app_neo4j_queries.py

@@ -577,7 +577,7 @@ def get_provenance(neo4j_driver, uuid, depth):
     # More info on apoc.path.subgraphAll() procedure: https://neo4j.com/labs/apoc/4.0/graph-querying/expand-subgraph/
     query = (f"MATCH (n:Entity) "
              f"WHERE n.uuid = '{uuid}' "
-             f"CALL apoc.path.subgraphAll(n, {{ {max_level_str} relationshipFilter:'<ACTIVITY_INPUT|<ACTIVITY_OUTPUT' }}) "
+             f"CALL apoc.path.subgraphAll(n, {{ {max_level_str} relationshipFilter:'<ACTIVITY_INPUT|<ACTIVITY_OUTPUT', labelFilter:'-Lab' }}) "
              f"YIELD nodes, relationships "
              f"WITH [node in nodes | node {{ .*, label:labels(node)[0] }} ] as nodes, "
              f"[rel in relationships | rel {{ .*, fromNode: {{ label:labels(startNode(rel))[0], uuid:startNode(rel).uuid }}, toNode: {{ label:labels(endNode(rel))[0], uuid:endNode(rel).uuid }}, rel_data: {{ type: type(rel) }} }} ] as rels "