hsiang-c commented on code in PR #5138:
URL: https://github.com/apache/datafusion-comet/pull/5138#discussion_r3677864451
##########
native/core/src/execution/operators/expand.rs:
##########
@@ -65,6 +66,47 @@ impl ExpandExec {
cache,
}
}
+
+ /// Derives the operator's output schema from *every* projection, not just
the first.
+ ///
+ /// Each projection produces the same output columns, so their types agree
except where a
+ /// native kernel drifts on nested field nullability. Widening each
column's nested `nullable`
+ /// flags across all projections gives a schema that is valid for all of
them; deriving it from
+ /// `projections[0]` alone yields a schema that the remaining projections
cannot be stamped
+ /// with. See <https://github.com/apache/datafusion-comet/issues/5137>.
+ pub fn build_schema(
+ projections: &[Vec<Arc<dyn PhysicalExpr>>],
+ input_schema: &SchemaRef,
+ ) -> Result<SchemaRef, DataFusionError> {
+ let mut data_types = projections
+ .first()
+ .ok_or_else(|| {
+ DataFusionError::Internal("Expand should have at least one
projection".to_string())
+ })?
+ .iter()
+ .map(|expr| expr.data_type(input_schema))
+ .collect::<Result<Vec<_>, _>>()?;
+
+ for projection in &projections[1..] {
+ if projection.len() != data_types.len() {
+ return Err(DataFusionError::Internal(format!(
+ "Expand projections produce differing column counts: {}
and {}",
+ data_types.len(),
+ projection.len()
+ )));
+ }
+ for (data_type, expr) in data_types.iter_mut().zip(projection) {
+ *data_type = widen_nested_nullability(data_type,
&expr.data_type(input_schema)?);
+ }
+ }
+
+ let fields: Vec<Field> = data_types
+ .into_iter()
+ .enumerate()
+ .map(|(idx, dt)| Field::new(format!("col_{idx}"), dt, true))
Review Comment:
Is it required to keep the field name as is?
--
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]
