fix(ingest/gc): infinite loop query entities (datahub-project#12274)

anshbansal · llance · commit c146922035f9 · 2025-01-13T14:46:34.000-05:00
diff --git a/metadata-ingestion/src/datahub/ingestion/source/gc/soft_deleted_entity_cleanup.py b/metadata-ingestion/src/datahub/ingestion/source/gc/soft_deleted_entity_cleanup.py
@@ -258,7 +258,7 @@ def _get_soft_deleted_queries(self) -> Iterable[str]:
                 )
                 break
             scroll_across_entities = result.get("scrollAcrossEntities")
-            if not scroll_across_entities:
+            if not scroll_across_entities or not scroll_across_entities.get("count"):
                 break
             scroll_id = scroll_across_entities.get("nextScrollId")
             self.report.num_queries_found += scroll_across_entities.get("count")

Original file line number	Diff line number	Diff line change
`@@ -258,7 +258,7 @@ def _get_soft_deleted_queries(self) -> Iterable[str]:`
`258`	`258`	`)`
`259`	`259`	`break`
`260`	`260`	`scroll_across_entities = result.get("scrollAcrossEntities")`
`261`		`- if not scroll_across_entities:`
	`261`	`+ if not scroll_across_entities or not scroll_across_entities.get("count"):`
`262`	`262`	`break`
`263`	`263`	`scroll_id = scroll_across_entities.get("nextScrollId")`
`264`	`264`	`self.report.num_queries_found += scroll_across_entities.get("count")`