fix(ingest/powerbi): fix broken lineage between chart and dataset (#1…

…1080)
datahub-project · Aug 7, 2024 · 2755cf3 · 2755cf3
1 parent 543e447
commit 2755cf3
Show file tree

Hide file tree

Showing 4 changed files with 368 additions and 351 deletions.
diff --git a/metadata-ingestion/src/datahub/ingestion/source/powerbi/powerbi.py b/metadata-ingestion/src/datahub/ingestion/source/powerbi/powerbi.py
@@ -89,6 +89,7 @@
 from datahub.metadata.urns import ChartUrn
 from datahub.sql_parsing.sqlglot_lineage import ColumnLineageInfo
 from datahub.utilities.dedup_list import deduplicate_list
+from datahub.utilities.urns.urn_iter import lowercase_dataset_urn
 
 # Logger instance
 logger = logging.getLogger(__name__)
@@ -127,7 +128,7 @@ def __init__(
     @staticmethod
     def urn_to_lowercase(value: str, flag: bool) -> str:
         if flag is True:
-            return value.lower()
+            return lowercase_dataset_urn(value)
 
         return value
 
@@ -390,11 +391,13 @@ def to_datahub_dataset(
 
         for table in dataset.tables:
             # Create a URN for dataset
-            ds_urn = builder.make_dataset_urn_with_platform_instance(
-                platform=self.__config.platform_name,
-                name=self.assets_urn_to_lowercase(table.full_name),
-                platform_instance=self.__config.platform_instance,
-                env=self.__config.env,
+            ds_urn = self.assets_urn_to_lowercase(
+                builder.make_dataset_urn_with_platform_instance(
+                    platform=self.__config.platform_name,
+                    name=table.full_name,
+                    platform_instance=self.__config.platform_instance,
+                    env=self.__config.env,
+                )
             )
 
             logger.debug(f"dataset_urn={ds_urn}")

diff --git a/metadata-ingestion/src/datahub/utilities/urns/urn_iter.py b/metadata-ingestion/src/datahub/utilities/urns/urn_iter.py
@@ -131,7 +131,7 @@ def _modify_at_path(
         _modify_at_path(getattr(model, path[0]), path[1:], new_value)
 
 
-def _lowercase_dataset_urn(dataset_urn: str) -> str:
+def lowercase_dataset_urn(dataset_urn: str) -> str:
     cur_urn = DatasetUrn.from_string(dataset_urn)
     new_urn = DatasetUrn(
         platform=cur_urn.platform, name=cur_urn.name.lower(), env=cur_urn.env
@@ -149,10 +149,10 @@ def lowercase_dataset_urns(
 ) -> None:
     def modify_urn(urn: str) -> str:
         if guess_entity_type(urn) == "dataset":
-            return _lowercase_dataset_urn(urn)
+            return lowercase_dataset_urn(urn)
         elif guess_entity_type(urn) == "schemaField":
             cur_urn = Urn.from_string(urn)
-            cur_urn._entity_ids[0] = _lowercase_dataset_urn(cur_urn._entity_ids[0])
+            cur_urn._entity_ids[0] = lowercase_dataset_urn(cur_urn._entity_ids[0])
             return str(cur_urn)
         return urn