lyne7-sc commented on code in PR #25053:
URL: https://github.com/apache/datafusion/pull/25053#discussion_r3980478052
##########
datafusion/physical-expr/src/equivalence/properties/joins.rs:
##########
@@ -107,6 +91,96 @@ 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,
+) -> 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() {
+ let probe_exprs = ordering
+ .iter()
+ .map(|sort|
probe.eq_group().normalize_expr(Arc::clone(&sort.expr)))
+ .collect::<Vec<_>>();
+
+ // Outer joins must have the same match status throughout the group.
+ if preserves_unmatched_probe
+ && !on
+ .iter()
+ .all(|(probe_key, _)| probe_exprs.contains(probe_key))
+ {
+ continue;
+ }
+ if !ordering_covers_unique_build_key(build, &on, &probe_exprs) {
+ continue;
+ }
+ valid_orderings.push(ordering.clone());
+ }
+ let mut probe_orderings = OrderingEquivalenceClass::new(valid_orderings);
+ if probe_orderings.is_empty() {
+ return Ok(probe_orderings);
+ }
+ let mut build_orderings = build.oeq_class().clone();
+ match probe_side {
+ JoinSide::Left =>
build_orderings.add_offset(probe.schema.fields().len() as _)?,
+ JoinSide::Right =>
probe_orderings.add_offset(build.schema.fields().len() as _)?,
+ JoinSide::None => unreachable!(),
+ }
+ Ok(probe_orderings.join_suffix(&build_orderings))
+}
+
+/// Check whether the probe ordering determines a unique build key.
+/// Join keys and probe ordering expressions must already be normalized.
+fn ordering_covers_unique_build_key(
+ build: &EquivalenceProperties,
+ on: &[(PhysicalExprRef, PhysicalExprRef)],
+ probe_exprs: &[PhysicalExprRef],
+) -> bool {
+ build.constraints().iter().any(|constraint| {
+ let (Constraint::PrimaryKey(indices) | Constraint::Unique(indices)) =
constraint;
+ !indices.is_empty()
+ && indices.iter().all(|&index| {
+ let Some(field) = build.schema.fields().get(index) else {
+ return false;
+ };
+ // UNIQUE can contain repeated NULLs. Without null-equality
+ // information, only non-null UNIQUE columns prove uniqueness.
+ if matches!(constraint, Constraint::Unique(_)) &&
field.is_nullable() {
+ return false;
Review Comment:
Fixed in 13c29698f. The uniqueness proof now uses the join’s actual
null-equality semantics: nullable unique is accepted with `NullEqualsNothing`
and rejected with `NullEqualsNull`. I’ve added a regression test covering both
ordering decisions, cache invalidation, and correct `ORDER BY` with `LIMIT`
results.
--
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]
