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

datahub/ingestion/graph/client.py

@@ -519,9 +519,9 @@ class DataHubGraph(DatahubRestEmitter):
         :return: Optionally, a map of aspect_name to aspect_value as a dictionary if present, aspect_value will be set to None if that aspect was not found. Returns None on HTTP status 404.
         :raises HttpError: if the HTTP response is not a 200
         """
-        assert len(aspects) == len(
-            aspect_types
-        ), f"number of aspects requested ({len(aspects)}) should be the same as number of aspect types provided ({len(aspect_types)})"
+        assert len(aspects) == len(aspect_types), (
+            f"number of aspects requested ({len(aspects)}) should be the same as number of aspect types provided ({len(aspect_types)})"
+        )
 
         # TODO: generate aspects list from type classes
         response_json = self.get_entity_raw(entity_urn, aspects)
@@ -1576,9 +1576,7 @@ class DataHubGraph(DatahubRestEmitter):
                     ... assertionResult
                 }
             }
-        """ % (
-            self._assertion_result_shared()
-        )
+        """ % (self._assertion_result_shared())
 
         variables = {
             "assertionUrn": urn,

datahub/ingestion/run/pipeline.py

@@ -76,8 +76,9 @@ class LoggingCallback(WriteCallback):
         failure_metadata: dict,
     ) -> None:
         logger.error(
-            f"{self.name} failed to write record with workunit {record_envelope.metadata['workunit_id']}"
-            f" with {failure_exception} and info {failure_metadata}"
+            f"{self.name} failed to write record with workunit {record_envelope.metadata['workunit_id']}",
+            extra={"failure_metadata": failure_metadata},
+            exc_info=failure_exception,
         )
 
 
@@ -108,9 +109,9 @@ class DeadLetterQueueCallback(WriteCallback):
                         mcp.systemMetadata.properties = {}
                     if "workunit_id" not in mcp.systemMetadata.properties:
                         # update the workunit id
-                        mcp.systemMetadata.properties[
-                            "workunit_id"
-                        ] = record_envelope.metadata["workunit_id"]
+                        mcp.systemMetadata.properties["workunit_id"] = (
+                            record_envelope.metadata["workunit_id"]
+                        )
                 record_envelope.record = mcp
         self.file_sink.write_record_async(record_envelope, self.logging_callback)
 
@@ -700,7 +701,7 @@ class Pipeline:
             num_failures_sink = len(self.sink.get_report().failures)
             click.secho(
                 message_template.format(
-                    status=f"with at least {num_failures_source+num_failures_sink} failures"
+                    status=f"with at least {num_failures_source + num_failures_sink} failures"
                 ),
                 fg=self._get_text_color(
                     running=currently_running, failures=True, warnings=False
@@ -718,7 +719,7 @@ class Pipeline:
             num_warn_global = len(global_warnings)
             click.secho(
                 message_template.format(
-                    status=f"with at least {num_warn_source+num_warn_sink+num_warn_global} warnings"
+                    status=f"with at least {num_warn_source + num_warn_sink + num_warn_global} warnings"
                 ),
                 fg=self._get_text_color(
                     running=currently_running, failures=False, warnings=True

datahub/ingestion/run/pipeline_config.py

@@ -92,9 +92,9 @@ class PipelineConfig(ConfigModel):
     pipeline_name: Optional[str] = None
     failure_log: FailureLoggingConfig = FailureLoggingConfig()
 
-    _raw_dict: Optional[
-        dict
-    ] = None  # the raw dict that was parsed to construct this config
+    _raw_dict: Optional[dict] = (
+        None  # the raw dict that was parsed to construct this config
+    )
 
     @validator("run_id", pre=True, always=True)
     def run_id_should_be_semantic(

datahub/ingestion/source/abs/datalake_profiler_config.py

@@ -85,8 +85,8 @@ class DataLakeProfilerConfig(ConfigModel):
                 if field_level_metric.startswith("include_field_"):
                     values.setdefault(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"
+            )
 
         return values

datahub/ingestion/source/abs/source.py

@@ -508,7 +508,12 @@ class ABSSource(StatefulIngestionSourceBase):
                         ):
                             abs_path = self.create_abs_path(obj.name)
                             logger.debug(f"Sampling file: {abs_path}")
-                            yield abs_path, obj.name, obj.last_modified, obj.size,
+                            yield (
+                                abs_path,
+                                obj.name,
+                                obj.last_modified,
+                                obj.size,
+                            )
                 except Exception as e:
                     # This odd check if being done because boto does not have a proper exception to catch
                     # The exception that appears in stacktrace cannot actually be caught without a lot more work
@@ -552,9 +557,12 @@ class ABSSource(StatefulIngestionSourceBase):
         if os.path.isfile(prefix):
             logger.debug(f"Scanning single local file: {prefix}")
             file_name = prefix
-            yield prefix, file_name, datetime.utcfromtimestamp(
-                os.path.getmtime(prefix)
-            ), os.path.getsize(prefix)
+            yield (
+                prefix,
+                file_name,
+                datetime.utcfromtimestamp(os.path.getmtime(prefix)),
+                os.path.getsize(prefix),
+            )
         else:
             logger.debug(f"Scanning files under local folder: {prefix}")
             for root, dirs, files in os.walk(prefix):
@@ -565,9 +573,12 @@ class ABSSource(StatefulIngestionSourceBase):
                     full_path = PurePath(
                         os.path.normpath(os.path.join(root, file))
                     ).as_posix()
-                    yield full_path, file, datetime.utcfromtimestamp(
-                        os.path.getmtime(full_path)
-                    ), os.path.getsize(full_path)
+                    yield (
+                        full_path,
+                        file,
+                        datetime.utcfromtimestamp(os.path.getmtime(full_path)),
+                        os.path.getsize(full_path),
+                    )
 
     def get_workunits_internal(self) -> Iterable[MetadataWorkUnit]:
         self.container_WU_creator = ContainerWUCreator(
@@ -613,7 +624,7 @@ class ABSSource(StatefulIngestionSourceBase):
                                 table_data.table_path
                             ].timestamp = table_data.timestamp
 
-                for guid, table_data in table_dict.items():
+                for _, table_data in table_dict.items():
                     yield from self.ingest_table(table_data, path_spec)
 
     def get_workunit_processors(self) -> List[Optional[MetadataWorkUnitProcessor]]:

datahub/ingestion/source/aws/glue.py

@@ -521,7 +521,7 @@ class GlueSource(StatefulIngestionSourceBase):
         # otherwise, a node represents a transformation
         else:
             node_urn = mce_builder.make_data_job_urn_with_flow(
-                flow_urn, job_id=f'{node["NodeType"]}-{node["Id"]}'
+                flow_urn, job_id=f"{node['NodeType']}-{node['Id']}"
             )
 
         return {
@@ -679,7 +679,7 @@ class GlueSource(StatefulIngestionSourceBase):
             )
         )
 
-        return MetadataWorkUnit(id=f'{job_name}-{node["Id"]}', mce=mce)
+        return MetadataWorkUnit(id=f"{job_name}-{node['Id']}", mce=mce)
 
     def get_all_databases(self) -> Iterable[Mapping[str, Any]]:
         logger.debug("Getting all databases")
@@ -750,13 +750,13 @@ class GlueSource(StatefulIngestionSourceBase):
     ) -> Optional[MetadataWorkUnit]:
         if self.source_config.emit_s3_lineage:
             # extract dataset properties aspect
-            dataset_properties: Optional[
-                DatasetPropertiesClass
-            ] = mce_builder.get_aspect_if_available(mce, DatasetPropertiesClass)
+            dataset_properties: Optional[DatasetPropertiesClass] = (
+                mce_builder.get_aspect_if_available(mce, DatasetPropertiesClass)
+            )
             # extract dataset schema aspect
-            schema_metadata: Optional[
-                SchemaMetadataClass
-            ] = mce_builder.get_aspect_if_available(mce, SchemaMetadataClass)
+            schema_metadata: Optional[SchemaMetadataClass] = (
+                mce_builder.get_aspect_if_available(mce, SchemaMetadataClass)
+            )
 
             if dataset_properties and "Location" in dataset_properties.customProperties:
                 location = dataset_properties.customProperties["Location"]
@@ -765,9 +765,9 @@ class GlueSource(StatefulIngestionSourceBase):
                         location, self.source_config.env
                     )
                     assert self.ctx.graph
-                    schema_metadata_for_s3: Optional[
-                        SchemaMetadataClass
-                    ] = self.ctx.graph.get_schema_metadata(s3_dataset_urn)
+                    schema_metadata_for_s3: Optional[SchemaMetadataClass] = (
+                        self.ctx.graph.get_schema_metadata(s3_dataset_urn)
+                    )
 
                     if self.source_config.glue_s3_lineage_direction == "upstream":
                         fine_grained_lineages = None

datahub/ingestion/source/aws/s3_boto_utils.py

@@ -40,7 +40,7 @@ def get_s3_tags(
                 ]
             )
         except s3.meta.client.exceptions.ClientError:
-            logger.warn(f"No tags found for bucket={bucket_name}")
+            logger.warning(f"No tags found for bucket={bucket_name}")
 
     if use_s3_object_tags and key_name is not None:
         s3_client = aws_config.get_s3_client()
@@ -53,7 +53,7 @@ def get_s3_tags(
         else:
             # Unlike bucket tags, if an object does not have tags, it will just return an empty array
             # as opposed to an exception.
-            logger.warn(f"No tags found for bucket={bucket_name} key={key_name}")
+            logger.warning(f"No tags found for bucket={bucket_name} key={key_name}")
     if len(tags_to_add) == 0:
         return None
     if ctx.graph is not None:
@@ -65,7 +65,7 @@ def get_s3_tags(
         if current_tags:
             tags_to_add.extend([current_tag.tag for current_tag in current_tags.tags])
     else:
-        logger.warn("Could not connect to DatahubApi. No current tags to maintain")
+        logger.warning("Could not connect to DatahubApi. No current tags to maintain")
     # Remove duplicate tags
     tags_to_add = sorted(list(set(tags_to_add)))
     new_tags = GlobalTagsClass(

datahub/ingestion/source/aws/sagemaker_processors/feature_groups.py

@@ -257,7 +257,7 @@ class FeatureGroupProcessor:
             mce = MetadataChangeEvent(proposedSnapshot=feature_snapshot)
 
         return MetadataWorkUnit(
-            id=f'{feature_group_details["FeatureGroupName"]}-{feature["FeatureName"]}',
+            id=f"{feature_group_details['FeatureGroupName']}-{feature['FeatureName']}",
             mce=mce,
         )
 

datahub/ingestion/source/aws/sagemaker_processors/models.py

@@ -212,7 +212,7 @@ class ModelProcessor:
         mce = MetadataChangeEvent(proposedSnapshot=endpoint_snapshot)
 
         return MetadataWorkUnit(
-            id=f'{endpoint_details["EndpointName"]}',
+            id=f"{endpoint_details['EndpointName']}",
             mce=mce,
         )
 
@@ -503,7 +503,7 @@ class ModelProcessor:
         mce = MetadataChangeEvent(proposedSnapshot=model_snapshot)
 
         return MetadataWorkUnit(
-            id=f'{model_details["ModelName"]}',
+            id=f"{model_details['ModelName']}",
             mce=mce,
         )
 

datahub/ingestion/source/bigquery_v2/bigquery.py

@@ -132,9 +132,9 @@ class BigqueryV2Source(StatefulIngestionSourceBase, TestableSource):
         self.filters = BigQueryFilter(self.config, self.report)
         self.identifiers = BigQueryIdentifierBuilder(self.config, self.report)
 
-        redundant_lineage_run_skip_handler: Optional[
-            RedundantLineageRunSkipHandler
-        ] = None
+        redundant_lineage_run_skip_handler: Optional[RedundantLineageRunSkipHandler] = (
+            None
+        )
         if self.config.enable_stateful_lineage_ingestion:
             redundant_lineage_run_skip_handler = RedundantLineageRunSkipHandler(
                 source=self,

datahub/ingestion/source/bigquery_v2/bigquery_audit.py

@@ -37,9 +37,9 @@ class BigqueryTableIdentifier:
 
     # Note: this regex may get overwritten by the sharded_table_pattern config.
     # The class-level constant, however, will not be overwritten.
-    _BIGQUERY_DEFAULT_SHARDED_TABLE_REGEX: ClassVar[
-        str
-    ] = _BIGQUERY_DEFAULT_SHARDED_TABLE_REGEX
+    _BIGQUERY_DEFAULT_SHARDED_TABLE_REGEX: ClassVar[str] = (
+        _BIGQUERY_DEFAULT_SHARDED_TABLE_REGEX
+    )
     _BIGQUERY_WILDCARD_REGEX: ClassVar[str] = "((_(\\d+)?)\\*$)|\\*$"
     _BQ_SHARDED_TABLE_SUFFIX: str = "_yyyymmdd"
 

datahub/ingestion/source/bigquery_v2/bigquery_config.py

@@ -137,9 +137,9 @@ class BigQueryCredential(ConfigModel):
     @root_validator(skip_on_failure=True)
     def validate_config(cls, values: Dict[str, Any]) -> Dict[str, Any]:
         if values.get("client_x509_cert_url") is None:
-            values[
-                "client_x509_cert_url"
-            ] = f'https://www.googleapis.com/robot/v1/metadata/x509/{values["client_email"]}'
+            values["client_x509_cert_url"] = (
+                f"https://www.googleapis.com/robot/v1/metadata/x509/{values['client_email']}"
+            )
         return values
 
     def create_credential_temp_file(self) -> str:
@@ -611,9 +611,9 @@ class BigQueryV2Config(
         cls, v: Optional[List[str]], values: Dict
     ) -> Optional[List[str]]:
         if values.get("use_exported_bigquery_audit_metadata"):
-            assert (
-                v and len(v) > 0
-            ), "`bigquery_audit_metadata_datasets` should be set if using `use_exported_bigquery_audit_metadata: True`."
+            assert v and len(v) > 0, (
+                "`bigquery_audit_metadata_datasets` should be set if using `use_exported_bigquery_audit_metadata: True`."
+            )
 
         return v
 

datahub/ingestion/source/bigquery_v2/bigquery_platform_resource_helper.py

@@ -87,9 +87,9 @@ class BigQueryPlatformResourceHelper:
             key=platform_resource_key, graph_client=self.graph
         )
         if platform_resource:
-            self.platform_resource_cache[
-                platform_resource_key.primary_key
-            ] = platform_resource
+            self.platform_resource_cache[platform_resource_key.primary_key] = (
+                platform_resource
+            )
             return platform_resource
         return None
 
@@ -115,7 +115,11 @@ class BigQueryPlatformResourceHelper:
                 and platform_resource.resource_info.value
             ):
                 try:
-                    existing_info: Optional[BigQueryLabelInfo] = platform_resource.resource_info.value.as_pydantic_object(BigQueryLabelInfo)  # type: ignore
+                    existing_info: Optional[BigQueryLabelInfo] = (
+                        platform_resource.resource_info.value.as_pydantic_object(  # type: ignore
+                            BigQueryLabelInfo
+                        )
+                    )
                 except ValidationError as e:
                     logger.error(
                         f"Error converting existing value to BigQueryLabelInfo: {e}. Creating new one. Maybe this is because of a non backward compatible schema change."

datahub/ingestion/source/bigquery_v2/bigquery_schema_gen.py

@@ -311,8 +311,10 @@ class BigQuerySchemaGenerator:
                         platform_resource: PlatformResource = self.platform_resource_helper.generate_label_platform_resource(
                             label, tag_urn, managed_by_datahub=False
                         )
-                        label_info: BigQueryLabelInfo = platform_resource.resource_info.value.as_pydantic_object(  # type: ignore
-                            BigQueryLabelInfo
+                        label_info: BigQueryLabelInfo = (
+                            platform_resource.resource_info.value.as_pydantic_object(  # type: ignore
+                                BigQueryLabelInfo
+                            )
                         )
                         tag_urn = TagUrn.from_string(label_info.datahub_urn)
 
@@ -820,8 +822,10 @@ class BigQuerySchemaGenerator:
                         platform_resource: PlatformResource = self.platform_resource_helper.generate_label_platform_resource(
                             label, tag_urn, managed_by_datahub=False
                         )
-                        label_info: BigQueryLabelInfo = platform_resource.resource_info.value.as_pydantic_object(  # type: ignore
-                            BigQueryLabelInfo
+                        label_info: BigQueryLabelInfo = (
+                            platform_resource.resource_info.value.as_pydantic_object(  # type: ignore
+                                BigQueryLabelInfo
+                            )
                         )
                         tag_urn = TagUrn.from_string(label_info.datahub_urn)
 
@@ -860,8 +864,10 @@ class BigQuerySchemaGenerator:
                         platform_resource: PlatformResource = self.platform_resource_helper.generate_label_platform_resource(
                             label, tag_urn, managed_by_datahub=False
                         )
-                        label_info: BigQueryLabelInfo = platform_resource.resource_info.value.as_pydantic_object(  # type: ignore
-                            BigQueryLabelInfo
+                        label_info: BigQueryLabelInfo = (
+                            platform_resource.resource_info.value.as_pydantic_object(  # type: ignore
+                                BigQueryLabelInfo
+                            )
                         )
                         tag_urn = TagUrn.from_string(label_info.datahub_urn)
 
@@ -1203,9 +1209,9 @@ class BigQuerySchemaGenerator:
                     report=self.report,
                 )
 
-        self.report.metadata_extraction_sec[
-            f"{project_id}.{dataset.name}"
-        ] = timer.elapsed_seconds(digits=2)
+        self.report.metadata_extraction_sec[f"{project_id}.{dataset.name}"] = (
+            timer.elapsed_seconds(digits=2)
+        )
 
     def get_core_table_details(
         self, dataset_name: str, project_id: str, temp_table_dataset_prefix: str

datahub/ingestion/source/bigquery_v2/lineage.py

@@ -697,7 +697,7 @@ class BigqueryLineageExtractor:
                         if parsed_queries[-1]:
                             query = f"""create table `{destination_table.get_sanitized_table_ref().table_identifier.get_table_name()}` AS
                             (
-                                {parsed_queries[-1].sql(dialect='bigquery')}
+                                {parsed_queries[-1].sql(dialect="bigquery")}
                             )"""
                         else:
                             query = e.query
@@ -809,11 +809,11 @@ class BigqueryLineageExtractor:
                             upstream_lineage, temp_table_upstream
                         )
 
-                        upstreams[
-                            ref_temp_table_upstream
-                        ] = _merge_lineage_edge_columns(
-                            upstreams.get(ref_temp_table_upstream),
-                            collapsed_lineage,
+                        upstreams[ref_temp_table_upstream] = (
+                            _merge_lineage_edge_columns(
+                                upstreams.get(ref_temp_table_upstream),
+                                collapsed_lineage,
+                            )
                         )
             else:
                 upstreams[upstream_table_ref] = _merge_lineage_edge_columns(
@@ -1004,9 +1004,9 @@ class BigqueryLineageExtractor:
                 dataset_urn
             )
             for gcs_dataset_urn in gcs_urns:
-                schema_metadata_for_gcs: Optional[
-                    SchemaMetadataClass
-                ] = graph.get_schema_metadata(gcs_dataset_urn)
+                schema_metadata_for_gcs: Optional[SchemaMetadataClass] = (
+                    graph.get_schema_metadata(gcs_dataset_urn)
+                )
                 if schema_metadata and schema_metadata_for_gcs:
                     fine_grained_lineage = self.get_fine_grained_lineages_with_gcs(
                         dataset_urn,

datahub/ingestion/source/bigquery_v2/queries.py

@@ -387,9 +387,7 @@ AND
     OR
     protoPayload.metadata.tableDataRead.reason = "JOB"
 )
-""".strip(
-    "\t \n"
-)
+""".strip("\t \n")
 
 
 def bigquery_audit_metadata_query_template_lineage(

datahub/ingestion/source/bigquery_v2/queries_extractor.py

@@ -271,9 +271,9 @@ class BigQueryQueriesExtractor(Closeable):
             # Preprocessing stage that deduplicates the queries using query hash per usage bucket
             # Note: FileBackedDict is an ordered dictionary, so the order of execution of
             # queries is inherently maintained
-            queries_deduped: FileBackedDict[
-                Dict[int, ObservedQuery]
-            ] = self.deduplicate_queries(queries)
+            queries_deduped: FileBackedDict[Dict[int, ObservedQuery]] = (
+                self.deduplicate_queries(queries)
+            )
             self.report.num_unique_queries = len(queries_deduped)
             logger.info(f"Found {self.report.num_unique_queries} unique queries")
 

datahub/ingestion/source/bigquery_v2/usage.py

@@ -763,9 +763,9 @@ class BigQueryUsageExtractor:
                     )
 
                 if event.query_event.default_dataset:
-                    custom_properties[
-                        "defaultDatabase"
-                    ] = event.query_event.default_dataset
+                    custom_properties["defaultDatabase"] = (
+                        event.query_event.default_dataset
+                    )
             if event.read_event:
                 if event.read_event.readReason:
                     custom_properties["readReason"] = event.read_event.readReason

datahub/ingestion/source/cassandra/cassandra.py

@@ -91,7 +91,6 @@ class KeyspaceKey(ContainerKey):
     supported=True,
 )
 class CassandraSource(StatefulIngestionSourceBase):
-
     """
     This plugin extracts the following:
 

datahub/ingestion/source/cassandra/cassandra_utils.py

@@ -107,10 +107,10 @@ class CassandraToSchemaFieldConverter:
 
     @staticmethod
     def get_column_type(cassandra_column_type: str) -> SchemaFieldDataType:
-        type_class: Optional[
-            Type
-        ] = CassandraToSchemaFieldConverter._field_type_to_schema_field_type.get(
-            cassandra_column_type
+        type_class: Optional[Type] = (
+            CassandraToSchemaFieldConverter._field_type_to_schema_field_type.get(
+                cassandra_column_type
+            )
         )
         if type_class is None:
             logger.warning(

datahub/ingestion/source/confluent_schema_registry.py

@@ -293,9 +293,9 @@ class ConfluentSchemaRegistry(KafkaSchemaRegistryBase):
     def _load_json_schema_with_resolved_references(
         self, schema: Schema, name: str, subject: str
     ) -> dict:
-        imported_json_schemas: List[
-            JsonSchemaWrapper
-        ] = self.get_schemas_from_confluent_ref_json(schema, name=name, subject=subject)
+        imported_json_schemas: List[JsonSchemaWrapper] = (
+            self.get_schemas_from_confluent_ref_json(schema, name=name, subject=subject)
+        )
         schema_dict = json.loads(schema.schema_str)
         reference_map = {}
         for imported_schema in imported_json_schemas:
@@ -332,9 +332,9 @@ class ConfluentSchemaRegistry(KafkaSchemaRegistryBase):
             )
 
         elif schema.schema_type == "PROTOBUF":
-            imported_schemas: List[
-                ProtobufSchema
-            ] = self.get_schemas_from_confluent_ref_protobuf(schema)
+            imported_schemas: List[ProtobufSchema] = (
+                self.get_schemas_from_confluent_ref_protobuf(schema)
+            )
             base_name: str = topic.replace(".", "_")
             fields = protobuf_util.protobuf_schema_to_mce_fields(
                 ProtobufSchema(

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/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(