lyne7-sc commented on code in PR #25053:
URL: https://github.com/apache/datafusion/pull/25053#discussion_r4038361096
##########
datafusion/physical-expr/src/equivalence/properties/joins.rs:
##########
@@ -107,6 +95,112 @@ pub fn join_equivalence_properties(
Ok(result)
}
+/// Append build orderings only when equal probe ordering values identify at
most
+/// one build row. The suffix is then constant within each probe ordering
group,
+/// even if probe rows repeat. For an outer join preserving the probe side, all
+/// join keys must be fixed within the group, and the caller must rule out
filters,
+/// so the group cannot mix matched build rows with NULL-extended rows.
+fn unique_build_join_orderings(
+ probe: &EquivalenceProperties,
+ build: &EquivalenceProperties,
+ on: &[(PhysicalExprRef, PhysicalExprRef)],
+ probe_side: JoinSide,
+ preserves_unmatched_probe: bool,
+ null_equality: NullEquality,
+) -> Result<OrderingEquivalenceClass> {
+ if build.constraints().is_empty() || build.oeq_class().is_empty() {
+ return Ok(OrderingEquivalenceClass::default());
+ }
+ let on = on
+ .iter()
+ .map(|(left, right)| {
+ let (probe_key, build_key) = match probe_side {
+ JoinSide::Left => (left, right),
+ JoinSide::Right => (right, left),
+ JoinSide::None => unreachable!(),
+ };
+ (
+ probe.eq_group().normalize_expr(Arc::clone(probe_key)),
+ build.eq_group().normalize_expr(Arc::clone(build_key)),
+ )
+ })
+ .collect::<Vec<_>>();
+ let mut valid_orderings = Vec::new();
+ for ordering in probe.oeq_class().iter() {
+ // Within a group of equal ordering values, these expressions are
+ // constant. Keep this assumption local to the ordering proof.
+ let mut group = probe.eq_group().clone();
+ for sort in ordering {
+ let expr = probe.eq_group().normalize_expr(Arc::clone(&sort.expr));
+ group.add_constant(ConstExpr::from(expr));
+ }
+ let probe_key_is_fixed = |key: &PhysicalExprRef| {
+ !is_volatile(key) && group.is_expr_constant(key).is_some()
Review Comment:
thanks for the follow-up review. I reproduced both issues locally. The proof
now checks volatility before normalization on both sides and accounts for
probe-key nullability under null-safe equality. Added regressions for the
incorrect LIMIT results and the unbounded-probe stall.
--
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]
