fix(ingest): avoid requiring sqlalchemy for dynamodb classification (#10213)

metadata-ingestion/src/datahub/ingestion/glossary/classification_mixin.py

@@ -15,7 +15,6 @@ from datahub.ingestion.api.workunit import MetadataWorkUnit
 from datahub.ingestion.glossary.classifier import ClassificationConfig, Classifier
 from datahub.ingestion.glossary.classifier_registry import classifier_registry
 from datahub.ingestion.source.common.data_reader import DataReader
-from datahub.ingestion.source.sql.sqlalchemy_data_reader import SAMPLE_SIZE_MULTIPLIER
 from datahub.metadata.com.linkedin.pegasus2avro.common import (
     AuditStamp,
     GlossaryTermAssociation,
@@ -26,6 +25,9 @@ from datahub.metadata.com.linkedin.pegasus2avro.schema import SchemaMetadata
 from datahub.utilities.lossy_collections import LossyDict, LossyList
 from datahub.utilities.perf_timer import PerfTimer
 
+SAMPLE_SIZE_MULTIPLIER = 1.2
+
+
 logger: logging.Logger = logging.getLogger(__name__)
 
 
@@ -289,7 +291,7 @@ def classification_workunit_processor(
     classification_handler: ClassificationHandler,
     data_reader: Optional[DataReader],
     table_id: List[str],
-    data_reader_kwargs: dict = {},
+    data_reader_kwargs: Optional[dict] = None,
 ) -> Iterable[MetadataWorkUnit]:
     """
     Classification handling for a particular table.
@@ -317,7 +319,7 @@ def classification_workunit_processor(
                             table_id,
                             classification_handler.config.classification.sample_size
                             * SAMPLE_SIZE_MULTIPLIER,
-                            **data_reader_kwargs,
+                            **(data_reader_kwargs or {}),
                         )
                         if data_reader
                         else dict()

metadata-ingestion/src/datahub/ingestion/source/bigquery_v2/bigquery.py

@@ -38,6 +38,7 @@ from datahub.ingestion.api.source import (
 )
 from datahub.ingestion.api.workunit import MetadataWorkUnit
 from datahub.ingestion.glossary.classification_mixin import (
+    SAMPLE_SIZE_MULTIPLIER,
     ClassificationHandler,
     classification_workunit_processor,
 )
@@ -77,7 +78,6 @@ from datahub.ingestion.source.sql.sql_utils import (
     gen_schema_container,
     get_domain_wu,
 )
-from datahub.ingestion.source.sql.sqlalchemy_data_reader import SAMPLE_SIZE_MULTIPLIER
 from datahub.ingestion.source.state.profiling_state_handler import ProfilingHandler
 from datahub.ingestion.source.state.redundant_run_skip_handler import (
     RedundantLineageRunSkipHandler,

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

@@ -48,6 +48,7 @@ from datahub.ingestion.api.source import (
 )
 from datahub.ingestion.api.workunit import MetadataWorkUnit
 from datahub.ingestion.glossary.classification_mixin import (
+    SAMPLE_SIZE_MULTIPLIER,
     ClassificationHandler,
     ClassificationReportMixin,
 )
@@ -68,7 +69,6 @@ from datahub.ingestion.source.sql.sql_utils import (
     schema_requires_v2,
 )
 from datahub.ingestion.source.sql.sqlalchemy_data_reader import (
-    SAMPLE_SIZE_MULTIPLIER,
     SqlAlchemyTableDataReader,
 )
 from datahub.ingestion.source.state.stale_entity_removal_handler import (

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

@@ -72,6 +72,3 @@ class SqlAlchemyTableDataReader(DataReader):
 
     def close(self) -> None:
         self.connection.close()
-
-
-SAMPLE_SIZE_MULTIPLIER = 1.2