acryl-datahub 0.15.0.2rc6__py3-none-any.whl → 0.15.0.2rc8__py3-none-any.whl

datahub/ingestion/source/csv_enricher.py

@@ -371,11 +371,11 @@ class CSVEnricherSource(Source):
         domain: Optional[str],
         description: Optional[str],
     ) -> Iterable[MetadataWorkUnit]:
-        maybe_terms_wu: Optional[
-            MetadataWorkUnit
-        ] = self.get_resource_glossary_terms_work_unit(
-            entity_urn=entity_urn,
-            term_associations=term_associations,
+        maybe_terms_wu: Optional[MetadataWorkUnit] = (
+            self.get_resource_glossary_terms_work_unit(
+                entity_urn=entity_urn,
+                term_associations=term_associations,
+            )
         )
         if maybe_terms_wu:
             self.report.num_glossary_term_workunits_produced += 1
@@ -389,31 +389,31 @@ class CSVEnricherSource(Source):
             self.report.num_tag_workunits_produced += 1
             yield maybe_tags_wu
 
-        maybe_owners_wu: Optional[
-            MetadataWorkUnit
-        ] = self.get_resource_owners_work_unit(
-            entity_urn=entity_urn,
-            owners=owners,
+        maybe_owners_wu: Optional[MetadataWorkUnit] = (
+            self.get_resource_owners_work_unit(
+                entity_urn=entity_urn,
+                owners=owners,
+            )
         )
         if maybe_owners_wu:
             self.report.num_owners_workunits_produced += 1
             yield maybe_owners_wu
 
-        maybe_domain_wu: Optional[
-            MetadataWorkUnit
-        ] = self.get_resource_domain_work_unit(
-            entity_urn=entity_urn,
-            domain=domain,
+        maybe_domain_wu: Optional[MetadataWorkUnit] = (
+            self.get_resource_domain_work_unit(
+                entity_urn=entity_urn,
+                domain=domain,
+            )
         )
         if maybe_domain_wu:
             self.report.num_domain_workunits_produced += 1
             yield maybe_domain_wu
 
-        maybe_description_wu: Optional[
-            MetadataWorkUnit
-        ] = self.get_resource_description_work_unit(
-            entity_urn=entity_urn,
-            description=description,
+        maybe_description_wu: Optional[MetadataWorkUnit] = (
+            self.get_resource_description_work_unit(
+                entity_urn=entity_urn,
+                description=description,
+            )
         )
         if maybe_description_wu:
             self.report.num_description_workunits_produced += 1
@@ -426,9 +426,9 @@ class CSVEnricherSource(Source):
         needs_write: bool,
     ) -> Tuple[EditableSchemaMetadataClass, bool]:
         field_path: str = sub_resource_row.field_path
-        term_associations: List[
-            GlossaryTermAssociationClass
-        ] = sub_resource_row.term_associations
+        term_associations: List[GlossaryTermAssociationClass] = (
+            sub_resource_row.term_associations
+        )
         tag_associations: List[TagAssociationClass] = sub_resource_row.tag_associations
         description: Optional[str] = sub_resource_row.description
         has_terms: bool = len(term_associations) > 0
@@ -517,9 +517,9 @@ class CSVEnricherSource(Source):
             # Boolean field to tell whether we need to write an MCPW.
             needs_write = False
 
-            current_editable_schema_metadata: Optional[
-                EditableSchemaMetadataClass
-            ] = None
+            current_editable_schema_metadata: Optional[EditableSchemaMetadataClass] = (
+                None
+            )
             if self.ctx.graph and not self.should_overwrite:
                 # Fetch the current editable schema metadata
                 current_editable_schema_metadata = self.ctx.graph.get_aspect(
@@ -655,9 +655,9 @@ class CSVEnricherSource(Source):
             entity_urn = row["resource"]
             entity_type = Urn.from_string(row["resource"]).get_type()
 
-            term_associations: List[
-                GlossaryTermAssociationClass
-            ] = self.maybe_extract_glossary_terms(row)
+            term_associations: List[GlossaryTermAssociationClass] = (
+                self.maybe_extract_glossary_terms(row)
+            )
             tag_associations: List[TagAssociationClass] = self.maybe_extract_tags(row)
             owners: List[OwnerClass] = self.maybe_extract_owners(row, is_resource_row)
 

datahub/ingestion/source/datahub/config.py

@@ -25,6 +25,10 @@ DEFAULT_EXCLUDE_ASPECTS = {
     "globalSettingsKey",
     "globalSettingsInfo",
     "testResults",
+    "dataHubExecutionRequestKey",
+    "dataHubExecutionRequestInput",
+    "dataHubExecutionRequestSignal",
+    "dataHubExecutionRequestResult",
 }
 
 

datahub/ingestion/source/datahub/datahub_database_reader.py

@@ -152,7 +152,9 @@ class DataHubDatabaseReader:
     ) -> Iterable[Dict[str, Any]]:
         with self.engine.connect() as conn:
             if self.engine.dialect.name in ["postgresql", "mysql", "mariadb"]:
-                with conn.begin():  # Transaction required for PostgreSQL server-side cursor
+                with (
+                    conn.begin()
+                ):  # Transaction required for PostgreSQL server-side cursor
                     # Note that stream_results=True is mainly supported by PostgreSQL and MySQL-based dialects.
                     # https://docs.sqlalchemy.org/en/14/core/connections.html#sqlalchemy.engine.Connection.execution_options.params.stream_results
                     conn = conn.execution_options(
@@ -222,7 +224,7 @@ class DataHubDatabaseReader:
             )
         except Exception as e:
             logger.warning(
-                f'Failed to parse metadata for {row["urn"]}: {e}', exc_info=True
+                f"Failed to parse metadata for {row['urn']}: {e}", exc_info=True
             )
             self.report.num_database_parse_errors += 1
             self.report.database_parse_errors.setdefault(

datahub/ingestion/source/dbt/dbt_cloud.py

@@ -194,20 +194,20 @@ _DBT_GRAPHQL_MODEL_SEED_SNAPSHOT_FIELDS = """
 
 _DBT_FIELDS_BY_TYPE = {
     "models": f"""
-    { _DBT_GRAPHQL_COMMON_FIELDS }
-    { _DBT_GRAPHQL_NODE_COMMON_FIELDS }
-    { _DBT_GRAPHQL_MODEL_SEED_SNAPSHOT_FIELDS }
+    {_DBT_GRAPHQL_COMMON_FIELDS}
+    {_DBT_GRAPHQL_NODE_COMMON_FIELDS}
+    {_DBT_GRAPHQL_MODEL_SEED_SNAPSHOT_FIELDS}
     dependsOn
     materializedType
 """,
     "seeds": f"""
-    { _DBT_GRAPHQL_COMMON_FIELDS }
-    { _DBT_GRAPHQL_NODE_COMMON_FIELDS }
-    { _DBT_GRAPHQL_MODEL_SEED_SNAPSHOT_FIELDS }
+    {_DBT_GRAPHQL_COMMON_FIELDS}
+    {_DBT_GRAPHQL_NODE_COMMON_FIELDS}
+    {_DBT_GRAPHQL_MODEL_SEED_SNAPSHOT_FIELDS}
 """,
     "sources": f"""
-    { _DBT_GRAPHQL_COMMON_FIELDS }
-    { _DBT_GRAPHQL_NODE_COMMON_FIELDS }
+    {_DBT_GRAPHQL_COMMON_FIELDS}
+    {_DBT_GRAPHQL_NODE_COMMON_FIELDS}
     identifier
     sourceName
     sourceDescription
@@ -218,9 +218,9 @@ _DBT_FIELDS_BY_TYPE = {
     loader
 """,
     "snapshots": f"""
-    { _DBT_GRAPHQL_COMMON_FIELDS }
-    { _DBT_GRAPHQL_NODE_COMMON_FIELDS }
-    { _DBT_GRAPHQL_MODEL_SEED_SNAPSHOT_FIELDS }
+    {_DBT_GRAPHQL_COMMON_FIELDS}
+    {_DBT_GRAPHQL_NODE_COMMON_FIELDS}
+    {_DBT_GRAPHQL_MODEL_SEED_SNAPSHOT_FIELDS}
     parentsSources {{
       uniqueId
     }}
@@ -229,7 +229,7 @@ _DBT_FIELDS_BY_TYPE = {
     }}
 """,
     "tests": f"""
-    { _DBT_GRAPHQL_COMMON_FIELDS }
+    {_DBT_GRAPHQL_COMMON_FIELDS}
     state
     columnName
     status
@@ -315,7 +315,7 @@ class DBTCloudSource(DBTSourceBase, TestableSource):
             res = response.json()
             if "errors" in res:
                 raise ValueError(
-                    f'Unable to fetch metadata from dbt Cloud: {res["errors"]}'
+                    f"Unable to fetch metadata from dbt Cloud: {res['errors']}"
                 )
             data = res["data"]
         except JSONDecodeError as e:

datahub/ingestion/source/dbt/dbt_common.py

@@ -506,16 +506,18 @@ class DBTNode:
     materialization: Optional[str]  # table, view, ephemeral, incremental, snapshot
     # see https://docs.getdbt.com/reference/artifacts/manifest-json
     catalog_type: Optional[str]
-    missing_from_catalog: bool  # indicates if the node was missing from the catalog.json
+    missing_from_catalog: (
+        bool  # indicates if the node was missing from the catalog.json
+    )
 
     owner: Optional[str]
 
     columns: List[DBTColumn] = field(default_factory=list)
     upstream_nodes: List[str] = field(default_factory=list)  # list of upstream dbt_name
     upstream_cll: List[DBTColumnLineageInfo] = field(default_factory=list)
-    raw_sql_parsing_result: Optional[
-        SqlParsingResult
-    ] = None  # only set for nodes that don't depend on ephemeral models
+    raw_sql_parsing_result: Optional[SqlParsingResult] = (
+        None  # only set for nodes that don't depend on ephemeral models
+    )
     cll_debug_info: Optional[SqlParsingDebugInfo] = None
 
     meta: Dict[str, Any] = field(default_factory=dict)
@@ -869,10 +871,10 @@ class DBTSourceBase(StatefulIngestionSourceBase):
                                 "platform": DBT_PLATFORM,
                                 "name": node.dbt_name,
                                 "instance": self.config.platform_instance,
+                                # Ideally we'd include the env unconditionally. However, we started out
+                                # not including env in the guid, so we need to maintain backwards compatibility
+                                # with existing PROD assertions.
                                 **(
-                                    # Ideally we'd include the env unconditionally. However, we started out
-                                    # not including env in the guid, so we need to maintain backwards compatibility
-                                    # with existing PROD assertions.
                                     {"env": self.config.env}
                                     if self.config.env != mce_builder.DEFAULT_ENV
                                     and self.config.include_env_in_assertion_guid

datahub/ingestion/source/dremio/dremio_api.py

@@ -181,7 +181,7 @@ class DremioAPIOperations:
             return
 
         # On-prem Dremio authentication (PAT or Basic Auth)
-        for retry in range(1, self._retry_count + 1):
+        for _ in range(1, self._retry_count + 1):
             try:
                 if connection_args.authentication_method == "PAT":
                     self.session.headers.update(
@@ -191,9 +191,9 @@ class DremioAPIOperations:
                     )
                     return
                 else:
-                    assert (
-                        connection_args.username and connection_args.password
-                    ), "Username and password are required for authentication"
+                    assert connection_args.username and connection_args.password, (
+                        "Username and password are required for authentication"
+                    )
                     host = connection_args.hostname
                     port = connection_args.port
                     protocol = "https" if connection_args.tls else "http"

datahub/ingestion/source/dremio/dremio_datahub_source_mapping.py

@@ -101,9 +101,9 @@ class DremioToDataHubSourceTypeMapping:
         Add a new source type if not in the map (e.g., Dremio ARP).
         """
         dremio_source_type = dremio_source_type.upper()
-        DremioToDataHubSourceTypeMapping.SOURCE_TYPE_MAPPING[
-            dremio_source_type
-        ] = datahub_source_type
+        DremioToDataHubSourceTypeMapping.SOURCE_TYPE_MAPPING[dremio_source_type] = (
+            datahub_source_type
+        )
 
         if category:
             if category.lower() == "file_object_storage":

datahub/ingestion/source/elastic_search.py

@@ -111,10 +111,10 @@ class ElasticToSchemaFieldConverter:
 
     @staticmethod
     def get_column_type(elastic_column_type: str) -> SchemaFieldDataType:
-        type_class: Optional[
-            Type
-        ] = ElasticToSchemaFieldConverter._field_type_to_schema_field_type.get(
-            elastic_column_type
+        type_class: Optional[Type] = (
+            ElasticToSchemaFieldConverter._field_type_to_schema_field_type.get(
+                elastic_column_type
+            )
         )
         if type_class is None:
             logger.warning(

datahub/ingestion/source/gc/datahub_gc.py

@@ -292,6 +292,7 @@ class DataHubGcSource(Source):
             tokens = list_access_tokens.get("tokens", [])
             total = list_access_tokens.get("total", 0)
             if tokens == []:
+                # Due to a server bug we cannot rely on just total
                 break
             for token in tokens:
                 self.report.expired_tokens_revoked += 1

datahub/ingestion/source/gc/soft_deleted_entity_cleanup.py

@@ -99,6 +99,7 @@ class SoftDeletedEntitiesCleanupConfig(ConfigModel):
 
 @dataclass
 class SoftDeletedEntitiesReport(SourceReport):
+    num_calls_made: Dict[str, int] = field(default_factory=dict)
     num_entities_found: Dict[str, int] = field(default_factory=dict)
     num_soft_deleted_entity_processed: int = 0
     num_soft_deleted_retained_due_to_age: int = 0
@@ -154,9 +155,9 @@ class SoftDeletedEntitiesCleanup:
             current_count = self.report.num_hard_deleted_by_type.get(entity_type, 0)
             self.report.num_hard_deleted_by_type[entity_type] = current_count + 1
             if entity_type not in self.report.sample_hard_deleted_aspects_by_type:
-                self.report.sample_hard_deleted_aspects_by_type[
-                    entity_type
-                ] = LossyList()
+                self.report.sample_hard_deleted_aspects_by_type[entity_type] = (
+                    LossyList()
+                )
             self.report.sample_hard_deleted_aspects_by_type[entity_type].append(urn)
 
     def delete_entity(self, urn: str) -> None:
@@ -242,6 +243,11 @@ class SoftDeletedEntitiesCleanup:
 
         while True:
             try:
+                if entity_type not in self.report.num_calls_made:
+                    self.report.num_calls_made[entity_type] = 1
+                else:
+                    self.report.num_calls_made[entity_type] += 1
+                self._print_report()
                 result = self.ctx.graph.execute_graphql(
                     graphql_query,
                     {
@@ -270,7 +276,13 @@ class SoftDeletedEntitiesCleanup:
                 )
                 break
             scroll_across_entities = result.get("scrollAcrossEntities")
-            if not scroll_across_entities or not scroll_across_entities.get("count"):
+            if not scroll_across_entities:
+                break
+            search_results = scroll_across_entities.get("searchResults")
+            count = scroll_across_entities.get("count")
+            if not count or not search_results:
+                # Due to a server bug we cannot rely on just count as it was returning response like this
+                # {'count': 1, 'nextScrollId': None, 'searchResults': []}
                 break
             if entity_type == "DATA_PROCESS_INSTANCE":
                 # Temp workaround. See note in beginning of the function
@@ -282,7 +294,7 @@ class SoftDeletedEntitiesCleanup:
             self.report.num_entities_found[entity_type] += scroll_across_entities.get(
                 "count"
             )
-            for query in scroll_across_entities.get("searchResults"):
+            for query in search_results:
                 yield query["entity"]["urn"]
 
     def _get_urns(self) -> Iterable[str]:

datahub/ingestion/source/gcs/gcs_source.py

@@ -141,8 +141,9 @@ class GCSSource(StatefulIngestionSourceBase):
         source.source_config.platform = PLATFORM_GCS
 
         source.is_s3_platform = lambda: True  # type: ignore
-        source.create_s3_path = lambda bucket_name, key: unquote(f"s3://{bucket_name}/{key}")  # type: ignore
-
+        source.create_s3_path = lambda bucket_name, key: unquote(  # type: ignore
+            f"s3://{bucket_name}/{key}"
+        )
         return source
 
     def get_workunit_processors(self) -> List[Optional[MetadataWorkUnitProcessor]]:

datahub/ingestion/source/ge_data_profiler.py

@@ -267,7 +267,6 @@ def _is_single_row_query_method(query: Any) -> bool:
         "get_column_max",
         "get_column_mean",
         "get_column_stdev",
-        "get_column_stdev",
         "get_column_nonnull_count",
         "get_column_unique_count",
     }
@@ -328,7 +327,7 @@ def _is_single_row_query_method(query: Any) -> bool:
 
 
 def _run_with_query_combiner(
-    method: Callable[Concatenate["_SingleDatasetProfiler", P], None]
+    method: Callable[Concatenate["_SingleDatasetProfiler", P], None],
 ) -> Callable[Concatenate["_SingleDatasetProfiler", P], None]:
     @functools.wraps(method)
     def inner(
@@ -1538,9 +1537,7 @@ def create_bigquery_temp_table(
         query_job: Optional["google.cloud.bigquery.job.query.QueryJob"] = (
             # In google-cloud-bigquery 3.15.0, the _query_job attribute was
             # made public and renamed to query_job.
-            cursor.query_job
-            if hasattr(cursor, "query_job")
-            else cursor._query_job  # type: ignore[attr-defined]
+            cursor.query_job if hasattr(cursor, "query_job") else cursor._query_job  # type: ignore[attr-defined]
         )
         assert query_job
         temp_destination_table = query_job.destination

datahub/ingestion/source/ge_profiling_config.py

@@ -220,9 +220,9 @@ class GEProfilingConfig(GEProfilingBaseConfig):
                         )
                     values[field_level_metric] = False
 
-            assert (
-                max_num_fields_to_profile is None
-            ), f"{max_num_fields_to_profile_key} should be set to None"
+            assert max_num_fields_to_profile is None, (
+                f"{max_num_fields_to_profile_key} should be set to None"
+            )
 
         # Disable expensive queries.
         if values.get("turn_off_expensive_profiling_metrics"):

datahub/ingestion/source/iceberg/iceberg.py

@@ -296,9 +296,9 @@ class IcebergSource(StatefulIngestionSourceBase):
                 custom_properties["snapshot-id"] = str(
                     table.current_snapshot().snapshot_id
                 )
-                custom_properties[
-                    "manifest-list"
-                ] = table.current_snapshot().manifest_list
+                custom_properties["manifest-list"] = (
+                    table.current_snapshot().manifest_list
+                )
             dataset_properties = DatasetPropertiesClass(
                 name=table.name()[-1],
                 description=table.metadata.properties.get("comment", None),

datahub/ingestion/source/identity/azure_ad.py

@@ -354,9 +354,9 @@ class AzureADSource(StatefulIngestionSourceBase):
                     yield MetadataWorkUnit(id=group_status_wu_id, mcp=group_status_mcp)
 
         # Populate GroupMembership Aspects for CorpUsers
-        datahub_corp_user_urn_to_group_membership: Dict[
-            str, GroupMembershipClass
-        ] = defaultdict(lambda: GroupMembershipClass(groups=[]))
+        datahub_corp_user_urn_to_group_membership: Dict[str, GroupMembershipClass] = (
+            defaultdict(lambda: GroupMembershipClass(groups=[]))
+        )
         if (
             self.config.ingest_group_membership
             and len(self.selected_azure_ad_groups) > 0

datahub/ingestion/source/identity/okta.py

@@ -344,9 +344,9 @@ class OktaSource(StatefulIngestionSourceBase):
                 ).as_workunit()
 
         # Step 2: Populate GroupMembership Aspects for CorpUsers
-        datahub_corp_user_urn_to_group_membership: Dict[
-            str, GroupMembershipClass
-        ] = defaultdict(lambda: GroupMembershipClass(groups=[]))
+        datahub_corp_user_urn_to_group_membership: Dict[str, GroupMembershipClass] = (
+            defaultdict(lambda: GroupMembershipClass(groups=[]))
+        )
         if self.config.ingest_group_membership and okta_groups is not None:
             # Fetch membership for each group.
             for okta_group in okta_groups:

datahub/ingestion/source/kafka/kafka.py

@@ -419,10 +419,10 @@ class KafkaSource(StatefulIngestionSourceBase, TestableSource):
             custom_props = self.build_custom_properties(
                 topic, topic_detail, extra_topic_config
             )
-            schema_name: Optional[
-                str
-            ] = self.schema_registry_client._get_subject_for_topic(
-                topic, is_key_schema=False
+            schema_name: Optional[str] = (
+                self.schema_registry_client._get_subject_for_topic(
+                    topic, is_key_schema=False
+                )
             )
             if schema_name is not None:
                 custom_props["Schema Name"] = schema_name
@@ -610,11 +610,13 @@ class KafkaSource(StatefulIngestionSourceBase, TestableSource):
 
     def fetch_topic_configurations(self, topics: List[str]) -> Dict[str, dict]:
         logger.info("Fetching config details for all topics")
-        configs: Dict[
-            ConfigResource, concurrent.futures.Future
-        ] = self.admin_client.describe_configs(
-            resources=[ConfigResource(ConfigResource.Type.TOPIC, t) for t in topics],
-            request_timeout=self.source_config.connection.client_timeout_seconds,
+        configs: Dict[ConfigResource, concurrent.futures.Future] = (
+            self.admin_client.describe_configs(
+                resources=[
+                    ConfigResource(ConfigResource.Type.TOPIC, t) for t in topics
+                ],
+                request_timeout=self.source_config.connection.client_timeout_seconds,
+            )
         )
         logger.debug("Waiting for config details futures to complete")
         concurrent.futures.wait(configs.values())

datahub/ingestion/source/kafka_connect/kafka_connect.py

@@ -110,9 +110,8 @@ class KafkaConnectSource(StatefulIngestionSourceBase):
             connector_manifest = self._get_connector_manifest(
                 connector_name, connector_url
             )
-            if (
-                connector_manifest is None
-                or not self.config.connector_patterns.allowed(connector_manifest.name)
+            if connector_manifest is None or not self.config.connector_patterns.allowed(
+                connector_manifest.name
             ):
                 self.report.report_dropped(connector_name)
                 continue

datahub/ingestion/source/kafka_connect/sink_connectors.py

@@ -199,9 +199,9 @@ class BigQuerySinkConnector(BaseConnector):
             transforms.append(transform)
             for key in self.connector_manifest.config.keys():
                 if key.startswith(f"transforms.{name}."):
-                    transform[
-                        key.replace(f"transforms.{name}.", "")
-                    ] = self.connector_manifest.config[key]
+                    transform[key.replace(f"transforms.{name}.", "")] = (
+                        self.connector_manifest.config[key]
+                    )
 
         if "defaultDataset" in connector_manifest.config:
             defaultDataset = connector_manifest.config["defaultDataset"]

datahub/ingestion/source/kafka_connect/source_connectors.py

@@ -123,9 +123,9 @@ class ConfluentJDBCSourceConnector(BaseConnector):
             transforms.append(transform)
             for key in self.connector_manifest.config.keys():
                 if key.startswith(f"transforms.{name}."):
-                    transform[
-                        key.replace(f"transforms.{name}.", "")
-                    ] = self.connector_manifest.config[key]
+                    transform[key.replace(f"transforms.{name}.", "")] = (
+                        self.connector_manifest.config[key]
+                    )
 
         return self.JdbcParser(
             db_connection_url,

datahub/ingestion/source/looker/looker_common.py

@@ -596,9 +596,9 @@ class LookerUtil:
 
     @staticmethod
     def _extract_view_from_field(field: str) -> str:
-        assert (
-            field.count(".") == 1
-        ), f"Error: A field must be prefixed by a view name, field is: {field}"
+        assert field.count(".") == 1, (
+            f"Error: A field must be prefixed by a view name, field is: {field}"
+        )
         return field.split(".")[0]
 
     @staticmethod
@@ -815,9 +815,9 @@ class LookerExplore:
     project_name: Optional[str] = None
     label: Optional[str] = None
     description: Optional[str] = None
-    upstream_views: Optional[
-        List[ProjectInclude]
-    ] = None  # captures the view name(s) this explore is derived from
+    upstream_views: Optional[List[ProjectInclude]] = (
+        None  # captures the view name(s) this explore is derived from
+    )
     upstream_views_file_path: Dict[str, Optional[str]] = dataclasses_field(
         default_factory=dict
     )  # view_name is key and file_path is value. A single file may contains multiple views
@@ -889,7 +889,7 @@ class LookerExplore:
                     upstream_views.extend(parsed_explore.upstream_views or [])
                 else:
                     logger.warning(
-                        f'Could not find extended explore {extended_explore} for explore {dict["name"]} in model {model_name}'
+                        f"Could not find extended explore {extended_explore} for explore {dict['name']} in model {model_name}"
                     )
         else:
             # we only fallback to the view_names list if this is not an extended explore
@@ -903,7 +903,7 @@ class LookerExplore:
                 )
                 if not info:
                     logger.warning(
-                        f'Could not resolve view {view_name} for explore {dict["name"]} in model {model_name}'
+                        f"Could not resolve view {view_name} for explore {dict['name']} in model {model_name}"
                     )
                 else:
                     upstream_views.append(
@@ -935,9 +935,9 @@ class LookerExplore:
         try:
             explore = client.lookml_model_explore(model, explore_name)
             views: Set[str] = set()
-            lkml_fields: List[
-                LookmlModelExploreField
-            ] = explore_field_set_to_lkml_fields(explore)
+            lkml_fields: List[LookmlModelExploreField] = (
+                explore_field_set_to_lkml_fields(explore)
+            )
 
             if explore.view_name is not None and explore.view_name != explore.name:
                 # explore is not named after a view and is instead using a from field, which is modeled as view_name.
@@ -1034,9 +1034,9 @@ class LookerExplore:
                         if measure_field.name is None:
                             continue
                         else:
-                            field_name_vs_raw_explore_field[
-                                measure_field.name
-                            ] = measure_field
+                            field_name_vs_raw_explore_field[measure_field.name] = (
+                                measure_field
+                            )
 
                             view_fields.append(
                                 ViewField(
@@ -1072,11 +1072,11 @@ class LookerExplore:
             if view_project_map:
                 logger.debug(f"views and their projects: {view_project_map}")
 
-            upstream_views_file_path: Dict[
-                str, Optional[str]
-            ] = create_upstream_views_file_path_map(
-                lkml_fields=lkml_fields,
-                view_names=views,
+            upstream_views_file_path: Dict[str, Optional[str]] = (
+                create_upstream_views_file_path_map(
+                    lkml_fields=lkml_fields,
+                    view_names=views,
+                )
             )
             if upstream_views_file_path:
                 logger.debug(f"views and their file-paths: {upstream_views_file_path}")

datahub/ingestion/source/looker/looker_config.py

@@ -166,9 +166,9 @@ def _get_generic_definition(
         # e.g. spark1 or hive2 or druid_18
         platform = re.sub(r"[0-9]+", "", dialect_name.split("_")[0])
 
-    assert (
-        platform is not None
-    ), f"Failed to extract a valid platform from connection {looker_connection}"
+    assert platform is not None, (
+        f"Failed to extract a valid platform from connection {looker_connection}"
+    )
     db = looker_connection.database
     schema = looker_connection.schema  # ok for this to be None
     return platform, db, schema