Spenserrrr commented on code in PR #58751:
URL: https://github.com/apache/spark/pull/58751#discussion_r4010745746
##########
python/pyspark/sql/conversion.py:
##########
@@ -410,105 +402,168 @@ def convert_column(
assign_cols_by_name=assign_cols_by_name,
int_to_decimal_coercion_enabled=int_to_decimal_coercion_enabled,
ignore_unexpected_complex_type_values=ignore_unexpected_complex_type_values,
- is_legacy=is_legacy,
+ use_legacy_error_handling=use_legacy_error_handling,
)
# Wrap the nested RecordBatch as a single StructArray column
- return
ArrowBatchTransformer.wrap_struct(nested_batch).column(0)
+
converted.append(ArrowBatchTransformer.wrap_struct(nested_batch).column(0))
+ elif isinstance(col, pd.Series):
+ converted.append(
+ cls._convert_column(
+ col,
+ field,
+ timezone=timezone,
+ safecheck=safecheck,
+ arrow_cast=arrow_cast,
+ prefers_large_types=prefers_large_types,
+
int_to_decimal_coercion_enabled=int_to_decimal_coercion_enabled,
+
ignore_unexpected_complex_type_values=ignore_unexpected_complex_type_values,
+ use_legacy_error_handling=use_legacy_error_handling,
+ )
+ )
+ else:
+ raise PySparkTypeError(
+ errorClass="UDF_RETURN_TYPE",
Review Comment:
Thanks for the suggestion! I switched to the existing generic
NOT_EXPECTED_TYPE error class, since this validates converter inputs and
shouldn’t assume a UDF-specific call context.
--
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]
