dev: enable ruff rule

metadata-ingestion/pyproject.toml

@@ -41,8 +41,7 @@ extend-ignore = [
     "RUF012", # mutable-class-default; incompatible with pydantic
     "RUF015", # unnecessary-iterable-allocation-for-first-element
     # TODO: Enable these later
-    "B006",  # Mutable args
-    "B904",  # Checks for raise statements in exception handlers that lack a from clause
+    "B006",  # Mutable args - 21 errors remain
 ]
 
 [tool.ruff.lint.mccabe]

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

@@ -231,7 +231,7 @@ def _docker_compose_v2() -> List[str]:
             # docker-compose v1 is not installed either.
             raise DockerComposeVersionError(
                 "You don't have Docker Compose installed. Please install Docker Compose. See https://docs.docker.com/compose/install/.",
-            )
+            ) from None
 
 
 def _attempt_stop(quickstart_compose_file: List[pathlib.Path]) -> None:

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

@@ -298,7 +298,7 @@ def search(
     except KeyError:
         raise click.UsageError(
             f"Failed to find a matching query flavor for {flavor}. Valid values are {[x.lower() for x in SearchFlavor._member_names_]}"
-        )
+        ) from None
     catalog = _get_datahub_lite(read_only=True)
     # sanitize query
     result_ids = set()

metadata-ingestion/src/datahub/cli/specific/dataproduct_cli.py

@@ -49,7 +49,7 @@ def _abort_if_non_existent_urn(graph: DataHubGraph, urn: str, operation: str) ->
         entity_type = parsed_urn.get_type()
     except Exception:
         click.secho(f"Provided urn {urn} does not seem valid", fg="red")
-        raise click.Abort()
+        raise click.Abort() from None
     else:
         if not graph.exists(urn):
             click.secho(

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

@@ -44,7 +44,7 @@ def resolve_callback(cls, value: dict) -> dict:
             try:
                 value = CallableConsumerConfig(value).callable_config()
             except Exception as e:
-                raise ConfigurationError(e)
+                raise ConfigurationError() from e
         return value
 
 

metadata-ingestion/src/datahub/ingestion/fs/s3_fs.py

@@ -48,12 +48,12 @@ def __init__(
     def __next__(self) -> FileInfo:
         try:
             return next(self._file_statuses)
-        except StopIteration:
+        except StopIteration as e:
             if self._token:
                 self.fetch()
                 return next(self._file_statuses)
             else:
-                raise StopIteration()
+                raise e
 
     def fetch(self):
         params = dict(Bucket=self._bucket, Prefix=self._prefix, MaxKeys=self._max_keys)

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

@@ -93,7 +93,7 @@ def link_asset_to_version_set(
         try:
             return response["linkAssetVersion"]["urn"]
         except KeyError:
-            raise ValueError(f"Unexpected response: {response}")
+            raise ValueError(f"Unexpected response: {response}") from None
 
     def link_asset_to_versioned_asset(
         self,
@@ -165,7 +165,7 @@ def unlink_asset_from_version_set(self, asset_urn: str) -> Optional[str]:
         try:
             return response["unlinkAssetVersion"]["urn"]
         except KeyError:
-            raise ValueError(f"Unexpected response: {response}")
+            raise ValueError(f"Unexpected response: {response}") from None
 
     def unlink_latest_asset_from_version_set(
         self, version_set_urn: str
@@ -198,4 +198,4 @@ def unlink_latest_asset_from_version_set(
         try:
             return response["unlinkAssetVersion"]["urn"]
         except KeyError:
-            raise ValueError(f"Unexpected response: {response}")
+            raise ValueError(f"Unexpected response: {response}") from None

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

@@ -640,8 +640,8 @@ def get_workunits_internal(self) -> Iterable[MetadataWorkUnit]:
                 )
             except Exception as e:
                 raise ConfigurationError(
-                    f"Cannot read remote file {self.config.filename}, error:{e}"
-                )
+                    f"Cannot read remote file {self.config.filename}"
+                ) from e
         else:
             with open(pathlib.Path(self.config.filename), encoding="utf-8-sig") as f:
                 rows = list(csv.DictReader(f, delimiter=self.config.delimiter))

metadata-ingestion/src/datahub/ingestion/source/dremio/dremio_api.py

@@ -271,12 +271,12 @@ def execute_query(self, query: str, timeout: int = 3600) -> List[Dict[str, Any]]
                     self.cancel_query(job_id)
                     raise DremioAPIException(
                         f"Query execution timed out after {timeout} seconds"
-                    )
+                    ) from None
                 except RuntimeError as e:
-                    raise DremioAPIException(f"{str(e)}")
+                    raise DremioAPIException() from e
 
         except requests.RequestException as e:
-            raise DremioAPIException(f"Error executing query: {str(e)}")
+            raise DremioAPIException("Error executing query") from e
 
     def fetch_results(self, job_id: str) -> List[Dict]:
         """Fetch job results with status checking"""

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

@@ -272,7 +272,7 @@ def create_schema_registry(
             return schema_registry_class.create(config, report)
         except Exception as e:
             logger.debug(e, exc_info=e)
-            raise ImportError(config.schema_registry_class)
+            raise ImportError(config.schema_registry_class) from e
 
     def __init__(self, config: KafkaSourceConfig, ctx: PipelineContext):
         super().__init__(config, ctx)

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

@@ -501,7 +501,7 @@ def get_project_name(self, model_name: str) -> str:
             raise ValueError(
                 f"Could not locate a project name for model {model_name}. Consider configuring a static project name "
                 f"in your config file"
-            )
+            ) from None
 
     def get_manifest_if_present(self, folder: pathlib.Path) -> Optional[LookerManifest]:
         manifest_file = folder / "manifest.lkml"

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

@@ -1494,7 +1494,7 @@ def get_request():
                     sleep_time = error_response.headers.get("retry-after")
                     if sleep_time is not None:
                         time.sleep(float(sleep_time))
-                    raise HTTPError429
+                    raise HTTPError429 from None
 
                 raise http_error
 

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

@@ -230,8 +230,8 @@ def _get_pulsar_metadata(self, url):
                 self.report.report_warning("HTTPError", message)
         except requests.exceptions.RequestException as e:
             raise Exception(
-                f"An ambiguous exception occurred while handling the request: {e}"
-            )
+                "An ambiguous exception occurred while handling the request"
+            ) from e
 
     @classmethod
     def create(cls, config_dict, ctx):

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

@@ -124,7 +124,7 @@ def __init__(self, config: SigmaSourceConfig, ctx: PipelineContext):
         try:
             self.sigma_api = SigmaAPI(self.config, self.reporter)
         except Exception as e:
-            raise ConfigurationError(f"Unable to connect sigma API. Exception: {e}")
+            raise ConfigurationError("Unable to connect sigma API") from e
 
     @staticmethod
     def test_connection(config_dict: dict) -> TestConnectionReport:

metadata-ingestion/src/datahub/ingestion/source/snowflake/snowflake_connection.py

@@ -312,7 +312,7 @@ def get_oauth_connection(self) -> NativeSnowflakeConnection:
             raise ValueError(
                 f"access_token not found in response {response}. "
                 "Please check your OAuth configuration."
-            )
+            ) from None
         connect_args = self.get_options()["connect_args"]
         return snowflake.connector.connect(
             user=self.username,

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

@@ -1562,8 +1562,9 @@ def get_connection_objects(
         query: str,
         connection_type: str,
         page_size: int,
-        query_filter: dict = {},
+        query_filter: Optional[dict] = None,
     ) -> Iterable[dict]:
+        query_filter = query_filter or {}
         query_filter = optimize_query_filter(query_filter)
 
         # Calls the get_connection_object_page function to get the objects,

metadata-ingestion/src/datahub/ingestion/source/tableau/tableau_common.py

@@ -514,7 +514,8 @@ class MetadataQueryException(Exception):
 }
 
 
-def get_tags_from_params(params: List[str] = []) -> GlobalTagsClass:
+def get_tags_from_params(params: Optional[List[str]] = None) -> GlobalTagsClass:
+    params = params or []
     tags = [
         TagAssociationClass(tag=builder.make_tag_urn(tag.upper()))
         for tag in params

metadata-ingestion/src/datahub/lite/duckdb_lite.py

@@ -284,9 +284,10 @@ def search(
         self,
         query: str,
         flavor: SearchFlavor,
-        aspects: List[str] = [],
+        aspects: Optional[List[str]] = None,
         snippet: bool = True,
     ) -> Iterable[Searchable]:
+        aspects = aspects or []
         if flavor == SearchFlavor.FREE_TEXT:
             base_query = f"SELECT distinct(urn), 'urn', NULL from metadata_aspect_v2 where urn ILIKE '%{query}%' UNION SELECT urn, aspect_name, metadata from metadata_aspect_v2 where metadata->>'$.name' ILIKE '%{query}%'"
             for r in self.duckdb_client.execute(base_query).fetchall():

metadata-ingestion/src/datahub/lite/lite_local.py

@@ -90,7 +90,7 @@ def search(
         self,
         query: str,
         flavor: SearchFlavor,
-        aspects: List[str] = [],
+        aspects: Optional[List[str]] = None,
         snippet: bool = True,
     ) -> Iterable[Searchable]:
         pass

metadata-ingestion/src/datahub/lite/lite_util.py

@@ -70,9 +70,10 @@ def search(
         self,
         query: str,
         flavor: SearchFlavor,
-        aspects: List[str] = [],
+        aspects: Optional[List[str]] = None,
         snippet: bool = True,
     ) -> Iterable[Searchable]:
+        aspects = aspects or []
         yield from self.lite.search(query, flavor, aspects, snippet)
 
     def ls(self, path: str) -> List[Browseable]:
@@ -96,10 +97,10 @@ def get_datahub_lite(config_dict: dict, read_only: bool = False) -> "DataHubLite
     lite_type = lite_local_config.type
     try:
         lite_class = lite_registry.get(lite_type)
-    except KeyError:
+    except KeyError as e:
         raise Exception(
             f"Failed to find a registered lite implementation for {lite_type}. Valid values are {[k for k in lite_registry.mapping.keys()]}"
-        )
+        ) from e
 
     lite_specific_config = lite_class.get_config_class().parse_obj(
         lite_local_config.config

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

@@ -1,10 +1,10 @@
 from collections import deque
 from itertools import chain
 from sys import getsizeof
-from typing import Any, Iterator
+from typing import Any, Iterator, Optional
 
 
-def total_size(o: Any, handlers: Any = {}) -> int:
+def total_size(o: Any, handlers: Optional[Any] = None) -> int:
     """Returns the approximate memory footprint an object and all of its contents.
     Automatically finds the contents of the following builtin containers and
     their subclasses:  tuple, list, deque, dict, set and frozenset.
@@ -14,6 +14,7 @@ def total_size(o: Any, handlers: Any = {}) -> int:
 
     Based on https://github.com/ActiveState/recipe-577504-compute-mem-footprint/blob/master/recipe.py
     """
+    handlers = handlers or {}
 
     def dict_handler(d: dict) -> Iterator[Any]:
         return chain.from_iterable(d.items())

metadata-ingestion/tests/integration/bigquery_v2/test_bigquery.py

@@ -54,7 +54,8 @@ def random_email():
     )
 
 
-def recipe(mcp_output_path: str, source_config_override: dict = {}) -> dict:
+def recipe(mcp_output_path: str, source_config_override: Optional[dict] = None) -> dict:
+    source_config_override = source_config_override or {}
     return {
         "source": {
             "type": "bigquery",