anew commented on code in PR #57412:
URL: https://github.com/apache/spark/pull/57412#discussion_r3633353751
##########
python/pyspark/pipelines/api.py:
##########
@@ -652,16 +673,31 @@ def create_auto_cdc_flow(
},
)
- if stored_as_scd_type is not None and str(stored_as_scd_type) != "1":
+ if stored_as_scd_type is not None and str(stored_as_scd_type) not in ("1",
"2"):
raise PySparkTypeError(
errorClass="NOT_EXPECTED_TYPE",
messageParameters={
"arg_name": "stored_as_scd_type",
- "expected_type": "Literal[1, '1']",
+ "expected_type": "Literal[1, 2, '1', '2']",
"arg_type": type(stored_as_scd_type).__name__,
},
)
+ # Track-history columns describe how consecutive upserts are coalesced
into history records,
+ # a notion that only exists under SCD2. Reject them for any other SCD
type. The engine
+ # enforces this too, but failing here gives a clearer, client-side error.
+ is_scd2 = stored_as_scd_type is not None and str(stored_as_scd_type) == "2"
+ if not is_scd2 and (
Review Comment:
Good point - addressed
--
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]
