Github user gengliangwang commented on a diff in the pull request:
https://github.com/apache/spark/pull/18692#discussion_r144466472
--- Diff:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/joins.scala
---
@@ -152,3 +152,71 @@ object EliminateOuterJoin extends Rule[LogicalPlan]
with PredicateHelper {
if (j.joinType == newJoinType) f else Filter(condition,
j.copy(joinType = newJoinType))
}
}
+
+/**
+ * A rule that uses propagated constraints to infer join conditions. The
optimization is applicable
+ * only to CROSS joins.
+ *
+ * For instance, if there is a CROSS join, where the left relation has 'a
= 1' and the right
+ * relation has 'b = 1', then the rule infers 'a = b' as a join predicate.
+ */
+object InferJoinConditionsFromConstraints extends Rule[LogicalPlan] with
PredicateHelper {
+
+ def apply(plan: LogicalPlan): LogicalPlan = {
+ if (SQLConf.get.constraintPropagationEnabled) {
+ inferJoinConditions(plan)
+ } else {
+ plan
+ }
+ }
+
+ private def inferJoinConditions(plan: LogicalPlan): LogicalPlan = plan
transform {
+ case join @ Join(left, right, Cross, conditionOpt) =>
+ val leftConstraints =
join.constraints.filter(_.references.subsetOf(left.outputSet))
+ val rightConstraints =
join.constraints.filter(_.references.subsetOf(right.outputSet))
--- End diff --
I don't think we need to separate the constraints as left only and right
only.
The following case can infer `t1.col1 = t2.col1`:
```scala
Seq((1, 2)).toDF("col1", "col2").write.saveAsTable("t1")
Seq((1, 2)).toDF("col1", "col2").write.saveAsTable("t2")
val df = spark.sql("SELECT * FROM t1 CROSS JOIN t2 ON t1.col1 >= t2.col1 " +
"WHERE t1.col1 = t1.col2 + t2.col2 and t2.col1 = t1.col2 + t2.col2")
```
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
