viirya commented on code in PR #8626:
URL: https://github.com/apache/arrow-datafusion/pull/8626#discussion_r1436025576
##########
datafusion/optimizer/src/push_down_filter.rs:
##########
@@ -955,6 +965,36 @@ impl PushDownFilter {
}
}
+/// Convert cross join to join by pushing down filter predicate to the join
condition
+fn convert_cross_join_to_inner_join(cross_join: CrossJoin) -> Result<Join> {
+ let CrossJoin { left, right, .. } = cross_join;
+ let join_schema = build_join_schema(left.schema(), right.schema(),
&JoinType::Inner)?;
+ // predicate is given
+ Ok(Join {
+ left,
+ right,
+ join_type: JoinType::Inner,
+ join_constraint: JoinConstraint::On,
+ on: vec![],
+ filter: None,
+ schema: DFSchemaRef::new(join_schema),
+ null_equals_null: true,
+ })
+}
+
+/// Converts the inner join with empty equality predicate and empty filter
condition to the cross join
+fn convert_to_cross_join_if_beneficial(plan: LogicalPlan) ->
Result<LogicalPlan> {
+ if let LogicalPlan::Join(join) = &plan {
+ // Can be converted back to cross join
+ if join.on.is_empty() && join.filter.is_none() {
+ return LogicalPlanBuilder::from(join.left.as_ref().clone())
+ .cross_join(join.right.as_ref().clone())?
+ .build();
+ }
+ }
+ Ok(plan)
+}
Review Comment:
This is how `push_down_all_join` handles remaining predicates in Filter.
```rust
if keep_predicates.is_empty() {
Ok(plan)
} else {
// wrap the join on the filter whose predicates must be kept
match conjunction(keep_predicates) {
Some(predicate) => Ok(LogicalPlan::Filter(Filter::try_new(
predicate,
Arc::new(plan),
)?)),
None => Ok(plan),
}
}
```
And after it, `convert_to_cross_join_if_beneficial` is called. Where does
the Filter push down? Am I missing it?
```
let plan = push_down_all_join(
predicates,
vec![],
&join_plan,
left,
right,
vec![],
true,
)?;
convert_to_cross_join_if_beneficial(plan)?
```
--
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]
