[GitHub] spark pull request #12850: [SPARK-15076][SQL] Add ReorderAssociativeOperator...

[cloud-fan <gi...@git.apache.org>]

Github user cloud-fan commented on a diff in the pull request:

    https://github.com/apache/spark/pull/12850#discussion_r65464426
  
    --- Diff: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala ---
    @@ -738,6 +739,49 @@ object InferFiltersFromConstraints extends Rule[LogicalPlan] with PredicateHelpe
     }
     
     /**
    + * Reorder associative integral-type operators and fold all constants into one.
    + */
    +object ReorderAssociativeOperator extends Rule[LogicalPlan] {
    +  private def isAssociativelyFoldable(e: Expression): Boolean =
    +    e.deterministic && e.isInstanceOf[BinaryArithmetic] && e.dataType.isInstanceOf[IntegralType] &&
    +      isSingleOperatorExpr(e)
    +
    +  private def isSingleOperatorExpr(e: Expression): Boolean = e.find {
    +    case a: Add if a.getClass == e.getClass => false
    +    case m: Multiply if m.getClass == e.getClass => false
    +    case _: BinaryArithmetic => true
    +    case _ => false
    +  }.isEmpty
    +
    +  private def getOperandList(e: Expression): Seq[Expression] = e match {
    +    case BinaryArithmetic(a, b) => getOperandList(a) ++ getOperandList(b)
    +    case other => other :: Nil
    +  }
    +
    +  def apply(plan: LogicalPlan): LogicalPlan = plan transform {
    +    case q: LogicalPlan => q transformExpressionsDown {
    --- End diff --
    
    how about
    ```
    def flattenAdd(e: Expression): Seq[Expression] = e match {
      case Add(l, r) => flattenAdd(l) ++ flattenAdd(r)
      case other => other
    }
    
    ...
    plan transformAllExpressions {
      case a: Add if a.deterministic && a.dataType.isInstanceOf[IntegralType] =>
        val (foldables, others) => flattenAdd(a).partition(_.foldable)
        if (foldables.size > 1) {
          val foldableExpr = foldables.reduce(Add(_, _))
          val c = Literal.create(foldableExpr.eval(), a.dataType)
          if (others.isEmpty) c else Add(others.reduce(Add(_, _)), c)
        } else {
          a
        }
    }
    ```
    
    We can duplicate some code for `Multiply`, and I think this maybe more readable than the current version.


---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastructure@apache.org or file a JIRA ticket
with INFRA.
---

---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org