From 4ba63b193c1ac292493e06343d9d618c12c5ef3f Mon Sep 17 00:00:00 2001 From: jiangxingbo Date: Tue, 13 Sep 2016 17:04:51 +0200 Subject: [SPARK-17142][SQL] Complex query triggers binding error in HashAggregateExec ## What changes were proposed in this pull request? In `ReorderAssociativeOperator` rule, we extract foldable expressions with Add/Multiply arithmetics, and replace with eval literal. For example, `(a + 1) + (b + 2)` is optimized to `(a + b + 3)` by this rule. For aggregate operator, output expressions should be derived from groupingExpressions, current implemenation of `ReorderAssociativeOperator` rule may break this promise. A instance could be: ``` SELECT ((t1.a + 1) + (t2.a + 2)) AS out_col FROM testdata2 AS t1 INNER JOIN testdata2 AS t2 ON (t1.a = t2.a) GROUP BY (t1.a + 1), (t2.a + 2) ``` `((t1.a + 1) + (t2.a + 2))` is optimized to `(t1.a + t2.a + 3)`, which could not be derived from `ExpressionSet((t1.a +1), (t2.a + 2))`. Maybe we should improve the rule of `ReorderAssociativeOperator` by adding a GroupingExpressionSet to keep Aggregate.groupingExpressions, and respect these expressions during the optimize stage. ## How was this patch tested? Add new test case in `ReorderAssociativeOperatorSuite`. Author: jiangxingbo Closes #14917 from jiangxb1987/rao. --- .../optimizer/ReorderAssociativeOperatorSuite.scala | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) (limited to 'sql/catalyst/src/test') diff --git a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/optimizer/ReorderAssociativeOperatorSuite.scala b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/optimizer/ReorderAssociativeOperatorSuite.scala index 05e15e9ec4..a1ab0a8344 100644 --- a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/optimizer/ReorderAssociativeOperatorSuite.scala +++ b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/optimizer/ReorderAssociativeOperatorSuite.scala @@ -20,7 +20,7 @@ package org.apache.spark.sql.catalyst.optimizer import org.apache.spark.sql.catalyst.dsl.expressions._ import org.apache.spark.sql.catalyst.dsl.plans._ import org.apache.spark.sql.catalyst.expressions._ -import org.apache.spark.sql.catalyst.plans.PlanTest +import org.apache.spark.sql.catalyst.plans.{Inner, PlanTest} import org.apache.spark.sql.catalyst.plans.logical.{LocalRelation, LogicalPlan} import org.apache.spark.sql.catalyst.rules.RuleExecutor @@ -60,4 +60,18 @@ class ReorderAssociativeOperatorSuite extends PlanTest { comparePlans(optimized, correctAnswer) } + + test("nested expression with aggregate operator") { + val originalQuery = + testRelation.as("t1") + .join(testRelation.as("t2"), Inner, Some("t1.a".attr === "t2.a".attr)) + .groupBy("t1.a".attr + 1, "t2.a".attr + 1)( + (("t1.a".attr + 1) + ("t2.a".attr + 1)).as("col")) + + val optimized = Optimize.execute(originalQuery.analyze) + + val correctAnswer = originalQuery.analyze + + comparePlans(optimized, correctAnswer) + } } -- cgit v1.2.3