measure_merge_performance_with_distributions

oc_meta/plugins/editor.py

@@ -177,7 +177,6 @@ def merge(self, g_set: GraphSet, res: URIRef, other: URIRef) -> None:
         """
         # First get all related entities with a single SPARQL query
         related_entities = set()
-
         if other in self.relationship_cache:
             related_entities.update(self.relationship_cache[other])
         else:
@@ -201,7 +200,6 @@ def merge(self, g_set: GraphSet, res: URIRef, other: URIRef) -> None:
 
             self.relationship_cache[other] = other_related
             related_entities.update(other_related)
-
         if res in self.relationship_cache:
             related_entities.update(self.relationship_cache[res])
         else:
@@ -230,7 +228,6 @@ def merge(self, g_set: GraphSet, res: URIRef, other: URIRef) -> None:
         entities_to_import.update(related_entities)
         entities_to_import = {e for e in entities_to_import 
                             if not self.entity_cache.is_cached(e)}
-
         # Import only non-cached entities if there are any
         if entities_to_import:
             try:

oc_meta/run/merge/entities.py

@@ -162,6 +162,7 @@ def fetch_related_entities_batch(self, meta_editor: MetaEditor, merged_entities:
                 print(f"Error fetching related entities for surviving batch {i}-{i+batch_size}: {e}")
 
         return all_related_entities
+
     def process_file(self, csv_file: str) -> str:
         """Process a single CSV file with cross-row batch processing"""
         data = self.read_csv(csv_file)