chore(py): add unused-noqa lint rule (#12615)

metadata-ingestion-modules/airflow-plugin/pyproject.toml

@@ -44,6 +44,7 @@ extend-select = [
     "G010", # logging.warn -> logging.warning
     "I",    # isort
     "TID",  # flake8-tidy-imports
+    "RUF100",  # unused-noqa
 ]
 ignore = [
     "E501",  # Line length violations (handled by formatter)

metadata-ingestion-modules/airflow-plugin/src/datahub_airflow_plugin/datahub_listener.py

@@ -60,7 +60,7 @@
     # To placate mypy on Airflow versions that don't have the listener API,
     # we define a dummy hookimpl that's an identity function.
 
-    def hookimpl(f: _F) -> _F:  # type: ignore[misc] # noqa: F811
+    def hookimpl(f: _F) -> _F:  # type: ignore[misc]
         return f
 
 else:

metadata-ingestion-modules/airflow-plugin/tests/conftest.py

@@ -1,7 +1,7 @@
 import pathlib
 import site
 
-from datahub.testing.pytest_hooks import (  # noqa: F401,E402
+from datahub.testing.pytest_hooks import (  # noqa: F401
     load_golden_flags,
     pytest_addoption,
 )

metadata-ingestion-modules/dagster-plugin/pyproject.toml

@@ -44,6 +44,7 @@ extend-select = [
     "G010", # logging.warn -> logging.warning
     "I",    # isort
     "TID",  # flake8-tidy-imports
+    "RUF100",  # unused-noqa
 ]
 ignore = [
     "E501",  # Line length violations (handled by formatter)

metadata-ingestion-modules/dagster-plugin/tests/conftest.py

@@ -1,4 +1,4 @@
-from datahub.testing.pytest_hooks import (  # noqa: F401,E402
+from datahub.testing.pytest_hooks import (  # noqa: F401
     load_golden_flags,
     pytest_addoption,
 )

metadata-ingestion-modules/gx-plugin/pyproject.toml

@@ -44,6 +44,7 @@ extend-select = [
     "G010", # logging.warn -> logging.warning
     "I",    # isort
     "TID",  # flake8-tidy-imports
+    "RUF100",  # unused-noqa
 ]
 ignore = [
     "E501",  # Line length violations (handled by formatter)

metadata-ingestion-modules/gx-plugin/tests/conftest.py

@@ -1,5 +1,5 @@
 from datahub.testing.docker_utils import docker_compose_runner  # noqa: F401
-from datahub.testing.pytest_hooks import (  # noqa: F401,E402
+from datahub.testing.pytest_hooks import (  # noqa: F401
     load_golden_flags,
     pytest_addoption,
 )

metadata-ingestion-modules/prefect-plugin/pyproject.toml

@@ -44,6 +44,7 @@ extend-select = [
     "G010", # logging.warn -> logging.warning
     "I",    # isort
     "TID",  # flake8-tidy-imports
+    "RUF100",  # unused-noqa
 ]
 ignore = [
     "E501",  # Line length violations (handled by formatter)

metadata-ingestion/pyproject.toml

@@ -29,6 +29,7 @@ extend-select = [
     "G010", # logging.warn -> logging.warning
     "I",    # isort
     "TID",  # flake8-tidy-imports
+    "RUF100",  # unused-noqa
 ]
 extend-ignore = [
     "E501",  # Handled by formatter
@@ -38,6 +39,8 @@ extend-ignore = [
     "E203",  # Ignore whitespace before ':' (matches Black)
     "B019",  # Allow usages of functools.lru_cache
     "B008",  # Allow function call in argument defaults
+    "RUF012", # mutable-class-default; incompatible with pydantic
+    "RUF015", # unnecessary-iterable-allocation-for-first-element
     # TODO: Enable these later
     "B006",  # Mutable args
     "B017",  # Do not assert blind exception

metadata-ingestion/src/datahub/cli/docker_cli.py

@@ -430,7 +430,7 @@ def detect_quickstart_arch(arch: Optional[str]) -> Architectures:
     return quickstart_arch
 
 
-@docker.command()  # noqa: C901
+@docker.command()
 @click.option(
     "--version",
     type=str,
@@ -592,7 +592,7 @@ def detect_quickstart_arch(arch: Optional[str]) -> Architectures:
         "arch",
     ]
 )
-def quickstart(  # noqa: C901
+def quickstart(
     version: Optional[str],
     build_locally: bool,
     pull_images: bool,

metadata-ingestion/src/datahub/configuration/common.py

@@ -20,7 +20,7 @@
 from pydantic.fields import Field
 from typing_extensions import Protocol, Self
 
-from datahub.configuration._config_enum import ConfigEnum as ConfigEnum  # noqa: I250
+from datahub.configuration._config_enum import ConfigEnum as ConfigEnum
 from datahub.configuration.pydantic_migration_helpers import PYDANTIC_VERSION_2
 from datahub.utilities.dedup_list import deduplicate_list
 

metadata-ingestion/src/datahub/ingestion/api/decorators.py

@@ -3,7 +3,7 @@
 from typing import Callable, Dict, Optional, Type
 
 from datahub.ingestion.api.common import PipelineContext
-from datahub.ingestion.api.source import (  # noqa: I250
+from datahub.ingestion.api.source import (
     Source,
     SourceCapability as SourceCapability,
 )

metadata-ingestion/src/datahub/ingestion/graph/client.py

@@ -33,7 +33,7 @@
 from datahub.emitter.mcp import MetadataChangeProposalWrapper
 from datahub.emitter.rest_emitter import DatahubRestEmitter
 from datahub.emitter.serialization_helper import post_json_transform
-from datahub.ingestion.graph.config import (  # noqa: I250; TODO: Remove this alias
+from datahub.ingestion.graph.config import (
     DatahubClientConfig as DatahubClientConfig,
 )
 from datahub.ingestion.graph.connections import (

metadata-ingestion/src/datahub/ingestion/run/pipeline.py

@@ -439,7 +439,7 @@ def _time_to_print(self) -> bool:
             return True
         return False
 
-    def run(self) -> None:  # noqa: C901
+    def run(self) -> None:
         with contextlib.ExitStack() as stack:
             if self.config.flags.generate_memory_profiles:
                 import memray

metadata-ingestion/src/datahub/ingestion/source/looker/looker_common.py

@@ -923,15 +923,15 @@ def from_dict(
             tags=cast(List, dict.get("tags")) if dict.get("tags") is not None else [],
         )
 
-    @classmethod  # noqa: C901
+    @classmethod
     def from_api(  # noqa: C901
         cls,
         model: str,
         explore_name: str,
         client: LookerAPI,
         reporter: SourceReport,
         source_config: LookerDashboardSourceConfig,
-    ) -> Optional["LookerExplore"]:  # noqa: C901
+    ) -> Optional["LookerExplore"]:
         try:
             explore = client.lookml_model_explore(model, explore_name)
             views: Set[str] = set()
@@ -1183,7 +1183,7 @@ def _get_embed_url(self, base_url: str) -> str:
         base_url = remove_port_from_url(base_url)
         return f"{base_url}/embed/explore/{self.model_name}/{self.name}"
 
-    def _to_metadata_events(  # noqa: C901
+    def _to_metadata_events(
         self,
         config: LookerCommonConfig,
         reporter: SourceReport,

metadata-ingestion/src/datahub/ingestion/source/looker/looker_source.py

@@ -383,7 +383,7 @@ def add_reachable_explore(self, model: str, explore: str, via: str) -> None:
 
         self.reachable_explores[(model, explore)].append(via)
 
-    def _get_looker_dashboard_element(  # noqa: C901
+    def _get_looker_dashboard_element(
         self, element: DashboardElement
     ) -> Optional[LookerDashboardElement]:
         # Dashboard elements can use raw usage_queries against explores

metadata-ingestion/src/datahub/ingestion/source/nifi.py

@@ -488,7 +488,7 @@ def rest_api_base_url(self):
     def get_report(self) -> SourceReport:
         return self.report
 
-    def update_flow(self, pg_flow_dto: Dict, recursion_level: int = 0) -> None:  # noqa: C901
+    def update_flow(self, pg_flow_dto: Dict, recursion_level: int = 0) -> None:
         """
         Update self.nifi_flow with contents of the input process group `pg_flow_dto`
         """
@@ -894,7 +894,7 @@ def delete_provenance(self, provenance_uri):
         if not delete_response.ok:
             logger.error("failed to delete provenance ", provenance_uri)
 
-    def construct_workunits(self) -> Iterable[MetadataWorkUnit]:  # noqa: C901
+    def construct_workunits(self) -> Iterable[MetadataWorkUnit]:
         rootpg = self.nifi_flow.root_process_group
         flow_name = rootpg.name  # self.config.site_name
         flow_urn = self.make_flow_urn()

metadata-ingestion/src/datahub/ingestion/source/openapi.py

@@ -270,7 +270,7 @@ def build_wu(
         mce = MetadataChangeEvent(proposedSnapshot=dataset_snapshot)
         return ApiWorkUnit(id=dataset_name, mce=mce)
 
-    def get_workunits_internal(self) -> Iterable[ApiWorkUnit]:  # noqa: C901
+    def get_workunits_internal(self) -> Iterable[ApiWorkUnit]:
         config = self.config
 
         sw_dict = self.config.get_swagger()

metadata-ingestion/src/datahub/ingestion/source/openapi_parser.py

@@ -111,7 +111,7 @@ def check_sw_version(sw_dict: dict) -> None:
         )
 
 
-def get_endpoints(sw_dict: dict) -> dict:  # noqa: C901
+def get_endpoints(sw_dict: dict) -> dict:
     """
     Get all the URLs, together with their description and the tags
     """

metadata-ingestion/src/datahub/ingestion/source/powerbi_report_server/report_server_domain.py

@@ -33,7 +33,7 @@ class CatalogItem(BaseModel):
     )
 
     @validator("display_name", always=True)
-    def validate_diplay_name(cls, value, values):  # noqa: N805
+    def validate_diplay_name(cls, value, values):
         if values["created_by"]:
             return values["created_by"].split("\\")[-1]
         return ""

metadata-ingestion/src/datahub/ingestion/source/sql/athena.py

@@ -55,7 +55,7 @@
 except ImportError:
     _F = typing.TypeVar("_F", bound=typing.Callable[..., typing.Any])
 
-    def override(f: _F, /) -> _F:  # noqa: F811
+    def override(f: _F, /) -> _F:
         return f
 
 
@@ -104,7 +104,7 @@ def get_view_definition(self, connection, view_name, schema=None, **kw):
             return "\n".join([r for r in res])
 
     @typing.no_type_check
-    def _get_column_type(self, type_: Union[str, Dict[str, Any]]) -> TypeEngine:  # noqa: C901
+    def _get_column_type(self, type_: Union[str, Dict[str, Any]]) -> TypeEngine:
         """Derives the data type of the Athena column.
 
         This method is overwritten to extend the behavior of PyAthena.

metadata-ingestion/src/datahub/ingestion/source/sql/hive_metastore.py

@@ -67,7 +67,7 @@
 
 
 class HiveMetastoreConfigMode(StrEnum):
-    hive: str = "hive"  # noqa: F811
+    hive: str = "hive"
     presto: str = "presto"
     presto_on_hive: str = "presto-on-hive"
     trino: str = "trino"

metadata-ingestion/src/datahub/ingestion/source/sql/mssql/source.py

@@ -401,7 +401,7 @@ def loop_job_steps(
                 data_job.add_property(name=data_name, value=str(data_value))
             yield from self.construct_job_workunits(data_job)
 
-    def loop_stored_procedures(  # noqa: C901
+    def loop_stored_procedures(
         self,
         inspector: Inspector,
         schema: str,

metadata-ingestion/src/datahub/ingestion/source/sql/sql_common.py

@@ -635,7 +635,7 @@ def make_data_reader(self, inspector: Inspector) -> Optional[DataReader]:
 
         return None
 
-    def loop_tables(  # noqa: C901
+    def loop_tables(
         self,
         inspector: Inspector,
         schema: str,

metadata-ingestion/src/datahub/ingestion/source/sql/teradata.py

@@ -649,7 +649,7 @@ def __init__(self, config: TeradataConfig, ctx: PipelineContext):
             )
 
             # Disabling the below because the cached view definition is not the view definition the column in tablesv actually holds the last statement executed against the object... not necessarily the view definition
-            # setattr(  # noqa: B010
+            # setattr(
             #   TeradataDialect,
             #    "get_view_definition",
             #   lambda self, connection, view_name, schema=None, **kw: optimized_get_view_definition(
@@ -746,7 +746,7 @@ def get_db_name(self, inspector: Inspector) -> str:
         else:
             raise Exception("Unable to get database name from Sqlalchemy inspector")
 
-    def cached_loop_tables(  # noqa: C901
+    def cached_loop_tables(
         self,
         inspector: Inspector,
         schema: str,
@@ -782,7 +782,7 @@ def cached_get_table_properties(
                 break
         return description, properties, location
 
-    def cached_loop_views(  # noqa: C901
+    def cached_loop_views(
         self,
         inspector: Inspector,
         schema: str,

metadata-ingestion/src/datahub/sql_parsing/schema_resolver.py

@@ -13,7 +13,7 @@
 from datahub.ingestion.source.bigquery_v2.bigquery_audit import BigqueryTableIdentifier
 from datahub.metadata.schema_classes import SchemaFieldClass, SchemaMetadataClass
 from datahub.metadata.urns import DataPlatformUrn
-from datahub.sql_parsing._models import _TableName as _TableName  # noqa: I250
+from datahub.sql_parsing._models import _TableName as _TableName
 from datahub.sql_parsing.sql_parsing_common import PLATFORMS_WITH_CASE_SENSITIVE_TABLES
 from datahub.utilities.file_backed_collections import ConnectionWrapper, FileBackedDict
 from datahub.utilities.urns.field_paths import get_simple_field_path_from_v2_field_path

metadata-ingestion/src/datahub/sql_parsing/sqlglot_lineage.py

@@ -473,7 +473,7 @@ def _create_table_ddl_cll(
     return column_lineage
 
 
-def _select_statement_cll(  # noqa: C901
+def _select_statement_cll(
     statement: _SupportedColumnLineageTypes,
     dialect: sqlglot.Dialect,
     root_scope: sqlglot.optimizer.Scope,

metadata-ingestion/src/datahub/upgrade/upgrade.py

@@ -293,9 +293,9 @@ def is_client_server_compatible(client: VersionStats, server: VersionStats) -> i
         return server.version.micro - client.version.micro
 
 
-def _maybe_print_upgrade_message(  # noqa: C901
+def _maybe_print_upgrade_message(
     version_stats: Optional[DataHubVersionStats],
-) -> None:  # noqa: C901
+) -> None:
     days_before_cli_stale = 7
     days_before_quickstart_stale = 7
 

metadata-ingestion/src/datahub/utilities/mapping.py

@@ -171,7 +171,7 @@ def __init__(
         self.owner_source_type = owner_source_type
         self.match_nested_props = match_nested_props
 
-    def process(self, raw_props: Mapping[str, Any]) -> Dict[str, Any]:  # noqa: C901
+    def process(self, raw_props: Mapping[str, Any]) -> Dict[str, Any]:
         # Defining the following local variables -
         # operations_map - the final resulting map when operations are processed.
         # Against each operation the values to be applied are stored.

metadata-ingestion/tests/conftest.py

@@ -41,7 +41,7 @@
 except ImportError:
     pass
 
-import freezegun  # noqa: F401,E402
+import freezegun  # noqa: E402
 
 # The freezegun library has incomplete type annotations.
 # See https://github.com/spulec/freezegun/issues/469

metadata-ingestion/tests/test_helpers/docker_helpers.py

@@ -4,7 +4,7 @@
 
 import pytest
 
-from datahub.testing.docker_utils import (  # noqa: F401,I250
+from datahub.testing.docker_utils import (
     docker_compose_runner as docker_compose_runner,
     is_responsive as is_responsive,
     wait_for_port as wait_for_port,

metadata-ingestion/tests/unit/bigquery/test_bigqueryv2_usage_source.py

@@ -114,7 +114,7 @@ def test_bigqueryv2_filters():
     )
     OR
     protoPayload.metadata.tableDataRead.reason = "JOB"
-)"""  # noqa: W293
+)"""
 
     corrected_start_time = config.start_time - config.max_query_duration
     corrected_end_time = config.end_time + config.max_query_duration