acryl-datahub 0.15.0.2rc7__py3-none-any.whl → 0.15.0.3__py3-none-any.whl

datahub/ingestion/source/sql/clickhouse.py

@@ -218,9 +218,7 @@ def _get_all_table_comments_and_properties(self, connection, **kw):
              , comment
              , {properties_clause} AS properties
           FROM system.tables
-         WHERE name NOT LIKE '.inner%'""".format(
-            properties_clause=properties_clause
-        )
+         WHERE name NOT LIKE '.inner%'""".format(properties_clause=properties_clause)
     )
 
     all_table_comments: Dict[Tuple[str, str], Dict[str, Any]] = {}
@@ -268,7 +266,7 @@ def _get_table_or_view_names(self, relkind, connection, schema=None, **kw):
     info_cache = kw.get("info_cache")
     all_relations = self._get_all_relation_info(connection, info_cache=info_cache)
     relation_names = []
-    for key, relation in all_relations.items():
+    for _, relation in all_relations.items():
         if relation.database == schema and relation.relkind == relkind:
             relation_names.append(relation.relname)
     return relation_names
@@ -301,9 +299,7 @@ def _get_schema_column_info(self, connection, schema=None, **kw):
              , comment
           FROM system.columns
          WHERE {schema_clause}
-         ORDER BY database, table, position""".format(
-                    schema_clause=schema_clause
-                )
+         ORDER BY database, table, position""".format(schema_clause=schema_clause)
             )
         )
     )
@@ -474,7 +470,7 @@ class ClickHouseSource(TwoTierSQLAlchemySource):
         logger.debug(f"sql_alchemy_url={url}")
         engine = create_engine(url, **self.config.options)
         for db_row in engine.execute(text(all_tables_query)):
-            all_tables_set.add(f'{db_row["database"]}.{db_row["table_name"]}')
+            all_tables_set.add(f"{db_row['database']}.{db_row['table_name']}")
 
         return all_tables_set
 
@@ -503,7 +499,7 @@ class ClickHouseSource(TwoTierSQLAlchemySource):
 
         try:
             for db_row in engine.execute(text(query)):
-                dataset_name = f'{db_row["target_schema"]}.{db_row["target_table"]}'
+                dataset_name = f"{db_row['target_schema']}.{db_row['target_table']}"
                 if not self.config.database_pattern.allowed(
                     db_row["target_schema"]
                 ) or not self.config.table_pattern.allowed(dataset_name):
@@ -512,7 +508,7 @@ class ClickHouseSource(TwoTierSQLAlchemySource):
 
                 # Target
                 target_path = (
-                    f'{self.config.platform_instance+"." if self.config.platform_instance else ""}'
+                    f"{self.config.platform_instance + '.' if self.config.platform_instance else ''}"
                     f"{dataset_name}"
                 )
                 target = LineageItem(
@@ -525,7 +521,7 @@ class ClickHouseSource(TwoTierSQLAlchemySource):
 
                 # Source
                 platform = LineageDatasetPlatform.CLICKHOUSE
-                path = f'{db_row["source_schema"]}.{db_row["source_table"]}'
+                path = f"{db_row['source_schema']}.{db_row['source_table']}"
 
                 sources = [
                     LineageDataset(
@@ -552,9 +548,7 @@ class ClickHouseSource(TwoTierSQLAlchemySource):
                         target.dataset.path
                     ].upstreams = self._lineage_map[
                         target.dataset.path
-                    ].upstreams.union(
-                        target.upstreams
-                    )
+                    ].upstreams.union(target.upstreams)
 
                 else:
                     self._lineage_map[target.dataset.path] = target

datahub/ingestion/source/sql/oracle.py

@@ -234,9 +234,7 @@ class OracleInspectorObjectWrapper:
                     WHERE col.table_name = id.table_name
                     AND col.column_name = id.column_name
                     AND col.owner = id.owner
-                ) AS identity_options""".format(
-                dblink=dblink
-            )
+                ) AS identity_options""".format(dblink=dblink)
         else:
             identity_cols = "NULL as default_on_null, NULL as identity_options"
 

datahub/ingestion/source/sql/sql_generic_profiler.py

@@ -278,8 +278,7 @@ class GenericProfiler:
 
         if self.config.profiling.profile_table_size_limit is not None and (
             size_in_bytes is not None
-            and size_in_bytes / (2**30)
-            > self.config.profiling.profile_table_size_limit
+            and size_in_bytes / (2**30) > self.config.profiling.profile_table_size_limit
         ):
             self.report.profiling_skipped_size_limit[schema_name] += 1
             logger.debug(

datahub/ingestion/source/sql/teradata.py

@@ -599,7 +599,12 @@ ORDER by DataBaseName, TableName;
             setattr(  # noqa: B010
                 TeradataDialect,
                 "get_columns",
-                lambda self, connection, table_name, schema=None, use_qvci=self.config.use_qvci, **kw: optimized_get_columns(
+                lambda self,
+                connection,
+                table_name,
+                schema=None,
+                use_qvci=self.config.use_qvci,
+                **kw: optimized_get_columns(
                     self,
                     connection,
                     table_name,
@@ -613,7 +618,11 @@ ORDER by DataBaseName, TableName;
             setattr(  # noqa: B010
                 TeradataDialect,
                 "get_pk_constraint",
-                lambda self, connection, table_name, schema=None, **kw: optimized_get_pk_constraint(
+                lambda self,
+                connection,
+                table_name,
+                schema=None,
+                **kw: optimized_get_pk_constraint(
                     self, connection, table_name, schema, **kw
                 ),
             )
@@ -621,7 +630,11 @@ ORDER by DataBaseName, TableName;
             setattr(  # noqa: B010
                 TeradataDialect,
                 "get_foreign_keys",
-                lambda self, connection, table_name, schema=None, **kw: optimized_get_foreign_keys(
+                lambda self,
+                connection,
+                table_name,
+                schema=None,
+                **kw: optimized_get_foreign_keys(
                     self, connection, table_name, schema, **kw
                 ),
             )

datahub/ingestion/source/state/profiling_state_handler.py

@@ -41,9 +41,9 @@ class ProfilingHandler(StatefulIngestionUsecaseHandlerBase[ProfilingCheckpointSt
         run_id: str,
     ):
         self.state_provider = source.state_provider
-        self.stateful_ingestion_config: Optional[
-            ProfilingStatefulIngestionConfig
-        ] = config.stateful_ingestion
+        self.stateful_ingestion_config: Optional[ProfilingStatefulIngestionConfig] = (
+            config.stateful_ingestion
+        )
         self.pipeline_name = pipeline_name
         self.run_id = run_id
         self.checkpointing_enabled: bool = (

datahub/ingestion/source/state/redundant_run_skip_handler.py

@@ -48,9 +48,9 @@ class RedundantRunSkipHandler(
     ):
         self.source = source
         self.state_provider = source.state_provider
-        self.stateful_ingestion_config: Optional[
-            StatefulIngestionConfig
-        ] = config.stateful_ingestion
+        self.stateful_ingestion_config: Optional[StatefulIngestionConfig] = (
+            config.stateful_ingestion
+        )
         self.pipeline_name = pipeline_name
         self.run_id = run_id
         self._job_id = self._init_job_id()
@@ -145,8 +145,7 @@ class RedundantRunSkipHandler(
             )
 
             logger.debug(
-                f"{self.job_id} : Last run start, end times:"
-                f"({last_run_time_window})"
+                f"{self.job_id} : Last run start, end times:({last_run_time_window})"
             )
 
             # If current run's time window is subset of last run's time window, then skip.
@@ -212,8 +211,7 @@ class RedundantRunSkipHandler(
             )
 
         self.log(
-            "Adjusted start, end times: "
-            f"({suggested_start_time}, {suggested_end_time})"
+            f"Adjusted start, end times: ({suggested_start_time}, {suggested_end_time})"
         )
         return (suggested_start_time, suggested_end_time)
 

datahub/ingestion/source/state/stale_entity_removal_handler.py

@@ -111,9 +111,9 @@ class StaleEntityRemovalHandler(
         self.state_type_class = state_type_class
         self.pipeline_name = pipeline_name
         self.run_id = run_id
-        self.stateful_ingestion_config: Optional[
-            StatefulStaleMetadataRemovalConfig
-        ] = config.stateful_ingestion
+        self.stateful_ingestion_config: Optional[StatefulStaleMetadataRemovalConfig] = (
+            config.stateful_ingestion
+        )
         self.checkpointing_enabled: bool = (
             True
             if (

datahub/ingestion/source/state_provider/datahub_ingestion_checkpointing_provider.py

@@ -70,20 +70,20 @@ class DatahubIngestionCheckpointingProvider(IngestionCheckpointingProviderBase):
             self.orchestrator_name, pipeline_name, job_name
         )
 
-        latest_checkpoint: Optional[
-            DatahubIngestionCheckpointClass
-        ] = self.graph.get_latest_timeseries_value(
-            entity_urn=data_job_urn,
-            aspect_type=DatahubIngestionCheckpointClass,
-            filter_criteria_map={
-                "pipelineName": pipeline_name,
-            },
+        latest_checkpoint: Optional[DatahubIngestionCheckpointClass] = (
+            self.graph.get_latest_timeseries_value(
+                entity_urn=data_job_urn,
+                aspect_type=DatahubIngestionCheckpointClass,
+                filter_criteria_map={
+                    "pipelineName": pipeline_name,
+                },
+            )
         )
         if latest_checkpoint:
             logger.debug(
                 f"The last committed ingestion checkpoint for pipelineName:'{pipeline_name}',"
                 f" job_name:'{job_name}' found with start_time:"
-                f" {datetime.utcfromtimestamp(latest_checkpoint.timestampMillis/1000)}"
+                f" {datetime.utcfromtimestamp(latest_checkpoint.timestampMillis / 1000)}"
             )
             return latest_checkpoint
         else:

datahub/ingestion/source/state_provider/file_ingestion_checkpointing_provider.py

@@ -67,7 +67,7 @@ class FileIngestionCheckpointingProvider(IngestionCheckpointingProviderBase):
             logger.debug(
                 f"The last committed ingestion checkpoint for pipelineName:'{pipeline_name}',"
                 f" job_name:'{job_name}' found with start_time:"
-                f" {datetime.utcfromtimestamp(latest_checkpoint.timestampMillis/1000)}"
+                f" {datetime.utcfromtimestamp(latest_checkpoint.timestampMillis / 1000)}"
             )
             return latest_checkpoint
         else:

datahub/ingestion/source/tableau/tableau.py

@@ -281,9 +281,9 @@ class TableauConnectionConfig(ConfigModel):
         return authentication
 
     def make_tableau_client(self, site: str) -> Server:
-        authentication: Union[
-            TableauAuth, PersonalAccessTokenAuth
-        ] = self.get_tableau_auth(site)
+        authentication: Union[TableauAuth, PersonalAccessTokenAuth] = (
+            self.get_tableau_auth(site)
+        )
         try:
             server = Server(
                 self.connect_uri,
@@ -635,7 +635,7 @@ class TableauConfig(
         project_path_pattern = values.get("project_path_pattern")
         if project_pattern is None and project_path_pattern is None and projects:
             logger.warning(
-                "projects is deprecated, please use " "project_path_pattern instead."
+                "projects is deprecated, please use project_path_pattern instead."
             )
             logger.info("Initializing project_pattern from projects")
             values["project_pattern"] = AllowDenyPattern(
@@ -708,18 +708,18 @@ class DatabaseTable:
     """
 
     urn: str
-    id: Optional[
-        str
-    ] = None  # is not None only for tables that came from Tableau metadata
+    id: Optional[str] = (
+        None  # is not None only for tables that came from Tableau metadata
+    )
     num_cols: Optional[int] = None
 
-    paths: Optional[
-        Set[str]
-    ] = None  # maintains all browse paths encountered for this table
+    paths: Optional[Set[str]] = (
+        None  # maintains all browse paths encountered for this table
+    )
 
-    parsed_columns: Optional[
-        Set[str]
-    ] = None  # maintains all columns encountered for this table during parsing SQL queries
+    parsed_columns: Optional[Set[str]] = (
+        None  # maintains all columns encountered for this table during parsing SQL queries
+    )
 
     def update_table(
         self,
@@ -2310,8 +2310,7 @@ class TableauSiteSource:
             c.EMBEDDED_DATA_SOURCE,
         ):
             logger.debug(
-                f"datasource {ds.get(c.NAME)} type {ds.get(c.TYPE_NAME)} is "
-                f"unsupported"
+                f"datasource {ds.get(c.NAME)} type {ds.get(c.TYPE_NAME)} is unsupported"
             )
             return None
 
@@ -2493,9 +2492,9 @@ class TableauSiteSource:
     def _enrich_database_tables_with_parsed_schemas(
         self, parsing_result: SqlParsingResult
     ) -> None:
-        in_tables_schemas: Dict[
-            str, Set[str]
-        ] = transform_parsing_result_to_in_tables_schemas(parsing_result)
+        in_tables_schemas: Dict[str, Set[str]] = (
+            transform_parsing_result_to_in_tables_schemas(parsing_result)
+        )
 
         if not in_tables_schemas:
             logger.info("Unable to extract table schema from parsing result")
@@ -3559,25 +3558,25 @@ class TableauSiteSource:
 
             generated_project_keys.add(project_key.guid())
 
-            parent_project_key: Optional[
-                Union[ProjectKey, SiteKey]
-            ] = None  # It is going
+            parent_project_key: Optional[Union[ProjectKey, SiteKey]] = (
+                None  # It is going
+            )
             # to be used as a parent container key for the current tableau project
 
             if project_.parent_id is not None:
                 # Go to the parent project as we need to generate container first for parent
                 parent_project_key = self.gen_project_key(project_.parent_id)
 
-                parent_tableau_project: Optional[
-                    TableauProject
-                ] = self.tableau_project_registry.get(project_.parent_id)
+                parent_tableau_project: Optional[TableauProject] = (
+                    self.tableau_project_registry.get(project_.parent_id)
+                )
 
                 if (
                     parent_tableau_project is None
                 ):  # It is not in project registry because of project_pattern
-                    assert (
-                        project_.parent_name
-                    ), f"project {project_.name} should not be null"
+                    assert project_.parent_name, (
+                        f"project {project_.name} should not be null"
+                    )
                     parent_tableau_project = TableauProject(
                         id=project_.parent_id,
                         name=project_.parent_name,
@@ -3605,7 +3604,7 @@ class TableauSiteSource:
                 parent_container_key=parent_project_key,
             )
 
-        for id_, project in self.tableau_project_registry.items():
+        for project in self.tableau_project_registry.values():
             logger.debug(
                 f"project {project.name} and it's parent {project.parent_name} and parent id {project.parent_id}"
             )
@@ -3669,16 +3668,16 @@ class TableauSiteSource:
             if self.config.extract_usage_stats:
                 with PerfTimer() as timer:
                     self._populate_usage_stat_registry()
-                    self.report.extract_usage_stats_timer[
-                        self.site_content_url
-                    ] = timer.elapsed_seconds(digits=2)
+                    self.report.extract_usage_stats_timer[self.site_content_url] = (
+                        timer.elapsed_seconds(digits=2)
+                    )
 
             if self.config.permission_ingestion:
                 with PerfTimer() as timer:
                     self._fetch_groups()
-                    self.report.fetch_groups_timer[
-                        self.site_content_url
-                    ] = timer.elapsed_seconds(digits=2)
+                    self.report.fetch_groups_timer[self.site_content_url] = (
+                        timer.elapsed_seconds(digits=2)
+                    )
 
             # Populate the map of database names and database hostnames to be used later to map
             # databases to platform instances.
@@ -3691,9 +3690,9 @@ class TableauSiteSource:
 
             with PerfTimer() as timer:
                 self._populate_projects_registry()
-                self.report.populate_projects_registry_timer[
-                    self.site_content_url
-                ] = timer.elapsed_seconds(digits=2)
+                self.report.populate_projects_registry_timer[self.site_content_url] = (
+                    timer.elapsed_seconds(digits=2)
+                )
 
             if self.config.add_site_container:
                 yield from self.emit_site_container()
@@ -3701,23 +3700,23 @@ class TableauSiteSource:
 
             with PerfTimer() as timer:
                 yield from self.emit_workbooks()
-                self.report.emit_workbooks_timer[
-                    self.site_content_url
-                ] = timer.elapsed_seconds(digits=2)
+                self.report.emit_workbooks_timer[self.site_content_url] = (
+                    timer.elapsed_seconds(digits=2)
+                )
 
             if self.sheet_ids:
                 with PerfTimer() as timer:
                     yield from self.emit_sheets()
-                    self.report.emit_sheets_timer[
-                        self.site_content_url
-                    ] = timer.elapsed_seconds(digits=2)
+                    self.report.emit_sheets_timer[self.site_content_url] = (
+                        timer.elapsed_seconds(digits=2)
+                    )
 
             if self.dashboard_ids:
                 with PerfTimer() as timer:
                     yield from self.emit_dashboards()
-                    self.report.emit_dashboards_timer[
-                        self.site_content_url
-                    ] = timer.elapsed_seconds(digits=2)
+                    self.report.emit_dashboards_timer[self.site_content_url] = (
+                        timer.elapsed_seconds(digits=2)
+                    )
 
             if self.embedded_datasource_ids_being_used:
                 with PerfTimer() as timer:
@@ -3743,6 +3742,6 @@ class TableauSiteSource:
             if self.database_tables:
                 with PerfTimer() as timer:
                     yield from self.emit_upstream_tables()
-                    self.report.emit_upstream_tables_timer[
-                        self.site_content_url
-                    ] = timer.elapsed_seconds(digits=2)
+                    self.report.emit_upstream_tables_timer[self.site_content_url] = (
+                        timer.elapsed_seconds(digits=2)
+                    )

datahub/ingestion/source/unity/config.py

@@ -254,7 +254,9 @@ class UnityCatalogSourceConfig(
     )
 
     # TODO: Remove `type:ignore` by refactoring config
-    profiling: Union[UnityCatalogGEProfilerConfig, UnityCatalogAnalyzeProfilerConfig] = Field(  # type: ignore
+    profiling: Union[
+        UnityCatalogGEProfilerConfig, UnityCatalogAnalyzeProfilerConfig
+    ] = Field(  # type: ignore
         default=UnityCatalogGEProfilerConfig(),
         description="Data profiling configuration",
         discriminator="method",

datahub/ingestion/source/unity/proxy.py

@@ -363,7 +363,7 @@ class UnityCatalogApiProxy(UnityCatalogProxyProfilingMixin):
 
     @staticmethod
     def _create_metastore(
-        obj: Union[GetMetastoreSummaryResponse, MetastoreInfo]
+        obj: Union[GetMetastoreSummaryResponse, MetastoreInfo],
     ) -> Optional[Metastore]:
         if not obj.name:
             return None

datahub/ingestion/source/unity/source.py

@@ -205,9 +205,9 @@ class UnityCatalogSource(StatefulIngestionSourceBase, TestableSource):
         self.table_refs: Set[TableReference] = set()
         self.view_refs: Set[TableReference] = set()
         self.notebooks: FileBackedDict[Notebook] = FileBackedDict()
-        self.view_definitions: FileBackedDict[
-            Tuple[TableReference, str]
-        ] = FileBackedDict()
+        self.view_definitions: FileBackedDict[Tuple[TableReference, str]] = (
+            FileBackedDict()
+        )
 
         # Global map of tables, for profiling
         self.tables: FileBackedDict[Table] = FileBackedDict()

datahub/ingestion/source/unity/usage.py

@@ -103,7 +103,9 @@ class UnityCatalogUsageExtractor:
                                 query, table_info
                             )
                         for source_table in table_info.source_tables:
-                            with self.report.usage_perf_report.aggregator_add_event_timer:
+                            with (
+                                self.report.usage_perf_report.aggregator_add_event_timer
+                            ):
                                 self.usage_aggregator.aggregate_event(
                                     resource=source_table,
                                     start_time=query.start_time,

datahub/ingestion/source/usage/clickhouse_usage.py

@@ -213,15 +213,15 @@ class ClickHouseUsageSource(Source):
     def _aggregate_access_events(
         self, events: List[ClickHouseJoinedAccessEvent]
     ) -> Dict[datetime, Dict[ClickHouseTableRef, AggregatedDataset]]:
-        datasets: Dict[
-            datetime, Dict[ClickHouseTableRef, AggregatedDataset]
-        ] = collections.defaultdict(dict)
+        datasets: Dict[datetime, Dict[ClickHouseTableRef, AggregatedDataset]] = (
+            collections.defaultdict(dict)
+        )
 
         for event in events:
             floored_ts = get_time_bucket(event.starttime, self.config.bucket_duration)
 
             resource = (
-                f'{self.config.platform_instance+"." if self.config.platform_instance else ""}'
+                f"{self.config.platform_instance + '.' if self.config.platform_instance else ''}"
                 f"{event.database}.{event.table}"
             )
 

datahub/ingestion/source/usage/starburst_trino_usage.py

@@ -235,9 +235,9 @@ class TrinoUsageSource(Source):
     def _aggregate_access_events(
         self, events: List[TrinoJoinedAccessEvent]
     ) -> Dict[datetime, Dict[TrinoTableRef, AggregatedDataset]]:
-        datasets: Dict[
-            datetime, Dict[TrinoTableRef, AggregatedDataset]
-        ] = collections.defaultdict(dict)
+        datasets: Dict[datetime, Dict[TrinoTableRef, AggregatedDataset]] = (
+            collections.defaultdict(dict)
+        )
 
         for event in events:
             floored_ts = get_time_bucket(event.starttime, self.config.bucket_duration)

datahub/ingestion/source/usage/usage_common.py

@@ -89,7 +89,7 @@ def make_usage_workunit(
     top_sql_queries: Optional[List[str]] = None
     if query_freq is not None:
         if top_n_queries < len(query_freq):
-            logger.warn(
+            logger.warning(
                 f"Top N query limit exceeded on {str(resource)}.  Max number of queries {top_n_queries} <  {len(query_freq)}. Truncating top queries to {top_n_queries}."
             )
             query_freq = query_freq[0:top_n_queries]

datahub/ingestion/transformer/add_dataset_dataproduct.py

@@ -80,10 +80,10 @@ class AddDatasetDataProduct(DatasetDataproductTransformer):
                         ).add_asset(container_urn)
                         data_products_container[data_product_urn] = container_product
                     else:
-                        data_products_container[
-                            data_product_urn
-                        ] = data_products_container[data_product_urn].add_asset(
-                            container_urn
+                        data_products_container[data_product_urn] = (
+                            data_products_container[data_product_urn].add_asset(
+                                container_urn
+                            )
                         )
 
         mcps: List[

datahub/ingestion/transformer/add_dataset_properties.py

@@ -61,9 +61,9 @@ class AddDatasetProperties(DatasetPropertiesTransformer):
     ) -> Optional[DatasetPropertiesClass]:
         assert dataset_properties_aspect
 
-        server_dataset_properties_aspect: Optional[
-            DatasetPropertiesClass
-        ] = graph.get_dataset_properties(entity_urn)
+        server_dataset_properties_aspect: Optional[DatasetPropertiesClass] = (
+            graph.get_dataset_properties(entity_urn)
+        )
         # No need to take any action if server properties is None or there is not customProperties in server properties
         if (
             server_dataset_properties_aspect is None

datahub/ingestion/transformer/add_dataset_schema_tags.py

@@ -89,9 +89,9 @@ class AddDatasetSchemaTags(DatasetSchemaMetadataTransformer):
         server_field_map: dict = {}
         if self.config.semantics == TransformerSemantics.PATCH:
             assert self.ctx.graph
-            server_schema_metadata_aspect: Optional[
-                SchemaMetadataClass
-            ] = self.ctx.graph.get_schema_metadata(entity_urn=entity_urn)
+            server_schema_metadata_aspect: Optional[SchemaMetadataClass] = (
+                self.ctx.graph.get_schema_metadata(entity_urn=entity_urn)
+            )
             if server_schema_metadata_aspect is not None:
                 if not schema_metadata_aspect:
                     schema_metadata_aspect = server_schema_metadata_aspect

datahub/ingestion/transformer/add_dataset_schema_terms.py

@@ -108,9 +108,9 @@ class AddDatasetSchemaTerms(DatasetSchemaMetadataTransformer):
         ] = {}  # Map to cache server field objects, where fieldPath is key
         if self.config.semantics == TransformerSemantics.PATCH:
             assert self.ctx.graph
-            server_schema_metadata_aspect: Optional[
-                SchemaMetadataClass
-            ] = self.ctx.graph.get_schema_metadata(entity_urn=entity_urn)
+            server_schema_metadata_aspect: Optional[SchemaMetadataClass] = (
+                self.ctx.graph.get_schema_metadata(entity_urn=entity_urn)
+            )
             if server_schema_metadata_aspect is not None:
                 if not schema_metadata_aspect:
                     schema_metadata_aspect = server_schema_metadata_aspect

datahub/ingestion/transformer/dataset_domain_based_on_tags.py

@@ -60,10 +60,10 @@ class DatasetTagDomainMapper(DatasetDomainTransformer):
                 domain_aspect.domains.extend(mapped_domains.domains)
                 if self.config.semantics == TransformerSemantics.PATCH:
                     # Try merging with server-side domains
-                    patch_domain_aspect: Optional[
-                        DomainsClass
-                    ] = AddDatasetDomain._merge_with_server_domains(
-                        self.ctx.graph, entity_urn, domain_aspect
+                    patch_domain_aspect: Optional[DomainsClass] = (
+                        AddDatasetDomain._merge_with_server_domains(
+                            self.ctx.graph, entity_urn, domain_aspect
+                        )
                     )
                     return cast(Optional[Aspect], patch_domain_aspect)
                 return cast(Optional[Aspect], domain_aspect)

datahub/ingestion/transformer/extract_ownership_from_tags.py

@@ -141,9 +141,9 @@ class ExtractOwnersFromTagsTransformer(DatasetTagsTransformer):
                 else:
                     owner_type = get_owner_type(self.config.owner_type)
                     if owner_type == OwnershipTypeClass.CUSTOM:
-                        assert (
-                            self.config.owner_type_urn is not None
-                        ), "owner_type_urn must be set if owner_type is CUSTOM"
+                        assert self.config.owner_type_urn is not None, (
+                            "owner_type_urn must be set if owner_type is CUSTOM"
+                        )
 
                     owners.append(
                         OwnerClass(