goutamadwant commented on code in PR #24767:
URL: https://github.com/apache/datafusion/pull/24767#discussion_r4002736633
##########
datafusion/spark/src/function/aggregate/collect.rs:
##########
@@ -180,27 +234,49 @@ impl<T: Accumulator> NullToEmptyListAccumulator<T> {
pub fn new(inner: T, list_type: DataType) -> Self {
Self { inner, list_type }
}
+
+ fn normalize_input(&self, value: &ArrayRef) -> Result<ArrayRef> {
+ let DataType::List(field) = &self.list_type else {
+ return internal_err!(
+ "collect_list/collect_set expected List return type, got {:?}",
+ self.list_type
+ );
+ };
+ if value.data_type() == field.data_type() {
+ Ok(Arc::clone(value))
+ } else {
+ Ok(cast(value.as_ref(), field.data_type())?)
+ }
+ }
}
impl<T: Accumulator> Accumulator for NullToEmptyListAccumulator<T> {
fn update_batch(&mut self, values: &[ArrayRef]) -> Result<()> {
- self.inner.update_batch(values)
+ let [value] = values else {
+ return self.inner.update_batch(values);
+ };
+ let value = self.normalize_input(value)?;
Review Comment:
Addressed with shared update/retract normalization and an
update-retract-evaluate regression for the nested runtime/declared schema
mismatch. Both collect_list and collect_set are covered.
--
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]
