Github user cloud-fan commented on a diff in the pull request:
https://github.com/apache/spark/pull/19201#discussion_r138401827
--- Diff:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/QueryPlanConstraints.scala
---
@@ -106,91 +106,48 @@ trait QueryPlanConstraints { self: LogicalPlan =>
* Infers an additional set of constraints from a given set of equality
constraints.
* For e.g., if an operator has constraints of the form (`a = 5`, `a =
b`), this returns an
* additional constraint of the form `b = 5`.
- *
- * [SPARK-17733] We explicitly prevent producing recursive constraints
of the form `a = f(a, b)`
- * as they are often useless and can lead to a non-converging set of
constraints.
*/
private def inferAdditionalConstraints(constraints: Set[Expression]):
Set[Expression] = {
- val constraintClasses =
generateEquivalentConstraintClasses(constraints)
-
+ val aliasedConstraints =
eliminateAliasedExpressionInConstraints(constraints)
var inferredConstraints = Set.empty[Expression]
- constraints.foreach {
+ aliasedConstraints.foreach {
case eq @ EqualTo(l: Attribute, r: Attribute) =>
- val candidateConstraints = constraints - eq
- inferredConstraints ++= candidateConstraints.map(_ transform {
- case a: Attribute if a.semanticEquals(l) &&
- !isRecursiveDeduction(r, constraintClasses) => r
- })
- inferredConstraints ++= candidateConstraints.map(_ transform {
- case a: Attribute if a.semanticEquals(r) &&
- !isRecursiveDeduction(l, constraintClasses) => l
- })
+ val candidateConstraints = aliasedConstraints - eq
+ inferredConstraints ++= replaceConstraints(candidateConstraints,
l, r)
+ inferredConstraints ++= replaceConstraints(candidateConstraints,
r, l)
case _ => // No inference
}
inferredConstraints -- constraints
}
/**
- * Generate a sequence of expression sets from constraints, where each
set stores an equivalence
- * class of expressions. For example, Set(`a = b`, `b = c`, `e = f`)
will generate the following
- * expression sets: (Set(a, b, c), Set(e, f)). This will be used to
search all expressions equal
- * to an selected attribute.
+ * Replace the aliased expression in [[Alias]] with the alias name if
both exist in constraints.
+ * Thus non-converging inference can be prevented.
+ * E.g. `a = f(a, b)`, `a = f(b, c) && c = g(a, b)`.
--- End diff --
This example doesn't even have an alias...
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
