ODIn/spark-instrumented-optimizer
1
0
Fork 0
Code Issues Pull requests Projects Releases Wiki Activity

[SPARK-6397][SQL] Check the missingInput simply

Browse source 
https://github.com/apache/spark/pull/5082

/cc liancheng

Author: Yadong Qi <qiyadong2010@gmail.com>

Closes #5132 from watermen/sql-missingInput-new and squashes the following commits:

1e5bdc5 [Yadong Qi] Check the missingInput simply
This commit is contained in:
Yadong Qi 2015-03-23 18:16:49 +08:00 committed by Cheng Lian
parent bf044def4c
commit 9f3273bd9c
2 changed files with 5 additions and 5 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

5
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/CheckAnalysis.scala
View file

@ -85,9 +85,8 @@ class CheckAnalysis {
cleaned.foreach(checkValidAggregateExpression)
case o if o.children.nonEmpty &&
!o.references.filter(_.name != "grouping__id").subsetOf(o.inputSet) =>
val missingAttributes = (o.references -- o.inputSet).map(_.prettyString).mkString(",")
case o if o.children.nonEmpty && o.missingInput.nonEmpty =>
val missingAttributes = o.missingInput.map(_.prettyString).mkString(",")
val input = o.inputSet.map(_.prettyString).mkString(",")
failAnalysis(s"resolved attributes $missingAttributes missing from $input")

5
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/QueryPlan.scala
View file

@ -17,7 +17,7 @@
package org.apache.spark.sql.catalyst.plans
import org.apache.spark.sql.catalyst.expressions.{Attribute, AttributeSet, Expression}
import org.apache.spark.sql.catalyst.expressions.{VirtualColumn, Attribute, AttributeSet, Expression}
import org.apache.spark.sql.catalyst.trees.TreeNode
import org.apache.spark.sql.types.{ArrayType, DataType, StructField, StructType}
@ -48,7 +48,8 @@ abstract class QueryPlan[PlanType <: TreeNode[PlanType]] extends TreeNode[PlanTy
* Subclasses should override this method if they produce attributes internally as it is used by
* assertions designed to prevent the construction of invalid plans.
*/
def missingInput: AttributeSet = references -- inputSet
def missingInput: AttributeSet = (references -- inputSet)
.filter(_.name != VirtualColumn.groupingIdName)
/**
* Runs [[transform]] with `rule` on all expressions present in this query operator.