uros-b commented on code in PR #56671:
URL: https://github.com/apache/spark/pull/56671#discussion_r3461526317
##########
python/pyspark/pipelines/tests/test_auto_cdc_flow.py:
##########
@@ -72,11 +72,27 @@ def test_create_auto_cdc_flow_with_all_args(self):
column_list=[col("id"), col("val")],
stored_as_scd_type=1,
name="my_flow",
+ spark_conf={"spark.sql.shuffle.partitions": "8"},
)
flow = cast(AutoCdcFlow, registry.auto_cdc_flows[0])
self.assertEqual(flow.name, "my_flow")
self.assertEqual(flow.stored_as_scd_type, 1)
+ self.assertEqual(flow.spark_conf, {"spark.sql.shuffle.partitions":
"8"})
+
+ def test_create_auto_cdc_flow_spark_conf_defaults_to_empty(self):
+ registry = LocalGraphElementRegistry()
+ with graph_element_registration_context(registry):
+ dp.create_streaming_table("target")
+ dp.create_auto_cdc_flow(
+ target="target",
+ source="source",
+ keys=[col("key")],
+ sequence_by=expr("seq"),
+ )
+
+ flow = cast(AutoCdcFlow, registry.auto_cdc_flows[0])
+ self.assertEqual(flow.spark_conf, {})
Review Comment:
A note regarding testing completeness: no server-integration test asserts
that spark_conf actually reaches AutoCdcFlow.sqlConf end-to-end via
PythonPipelineSuite (the other AutoCDC args are tested there).
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
