[
https://issues.apache.org/jira/browse/SPARK-16648?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15385886#comment-15385886
]
liancheng commented on SPARK-16648:
-----------------------------------
The problematic code is the newly introduced {{TreeNode.withNewChildren}}.
{{Last}} is a unary expression with two {{Expression}} arguments:
{code}
case class Last(child: Expression, ignoreNullsExpr: Expression) extends
DeclarativeAggregate {
...
override def children: Seq[Expression] = child :: Nil
...
}
{code}
Argument {{ignoreNullsExpr}} defaults to {{Literal.FalseLiteral}}. Thus
{{LAST_VALUE(FALSE)}} is equivalent to {{Last(Literal.FalseLiteral,
Literal.FalseLiteral)}}. This breaks the following case branch in
{{TreeNode.withNewChildren}}:
{code}
case arg: TreeNode[_] if containsChild(arg) => // Both `child` and
`ignoreNullsExpr` hit this branch,
val newChild = remainingNewChildren.remove(0) // but only `child` is the
real child node of `Last`.
val oldChild = remainingOldChildren.remove(0)
if (newChild fastEquals oldChild) {
oldChild
} else {
changed = true
newChild
}
{code}
> LAST_VALUE(FALSE) OVER () throws IndexOutOfBoundsException
> ----------------------------------------------------------
>
> Key: SPARK-16648
> URL: https://issues.apache.org/jira/browse/SPARK-16648
> Project: Spark
> Issue Type: Bug
> Components: SQL
> Affects Versions: 2.0.0
> Reporter: liancheng
>
> {code:sql}
> SELECT LAST_VALUE(FALSE) OVER ();
> {code}
> Exception thrown:
> {noformat}
> java.lang.IndexOutOfBoundsException: 0
> at
> scala.collection.mutable.ResizableArray$class.apply(ResizableArray.scala:43)
> at scala.collection.mutable.ArrayBuffer.apply(ArrayBuffer.scala:48)
> at scala.collection.mutable.ArrayBuffer.remove(ArrayBuffer.scala:169)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$2.apply(TreeNode.scala:244)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:179)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.withNewChildren(TreeNode.scala:214)
> at
> org.apache.spark.sql.catalyst.analysis.TypeCoercion$ImplicitTypeCasts$$anonfun$apply$12.applyOrElse(TypeCoercion.scala:637)
> at
> org.apache.spark.sql.catalyst.analysis.TypeCoercion$ImplicitTypeCasts$$anonfun$apply$12.applyOrElse(TypeCoercion.scala:615)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$3.apply(TreeNode.scala:279)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$3.apply(TreeNode.scala:279)
> at
> org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:69)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:278)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:284)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:284)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$5.apply(TreeNode.scala:321)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:179)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.transformChildren(TreeNode.scala:319)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:284)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:284)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:284)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$5.apply(TreeNode.scala:321)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:179)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.transformChildren(TreeNode.scala:319)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:284)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:284)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:284)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$5.apply(TreeNode.scala:321)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:179)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.transformChildren(TreeNode.scala:319)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:284)
> at
> org.apache.spark.sql.catalyst.plans.QueryPlan.transformExpressionDown$1(QueryPlan.scala:156)
> at
> org.apache.spark.sql.catalyst.plans.QueryPlan.org$apache$spark$sql$catalyst$plans$QueryPlan$$recursiveTransform$1(QueryPlan.scala:166)
> at
> org.apache.spark.sql.catalyst.plans.QueryPlan$$anonfun$org$apache$spark$sql$catalyst$plans$QueryPlan$$recursiveTransform$1$1.apply(QueryPlan.scala:170)
> at
> scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
> at
> scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
> at scala.collection.immutable.List.foreach(List.scala:381)
> at scala.collection.TraversableLike$class.map(TraversableLike.scala:234)
> at scala.collection.immutable.List.map(List.scala:285)
> at
> org.apache.spark.sql.catalyst.plans.QueryPlan.org$apache$spark$sql$catalyst$plans$QueryPlan$$recursiveTransform$1(QueryPlan.scala:170)
> at
> org.apache.spark.sql.catalyst.plans.QueryPlan$$anonfun$4.apply(QueryPlan.scala:175)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:179)
> at
> org.apache.spark.sql.catalyst.plans.QueryPlan.transformExpressionsDown(QueryPlan.scala:175)
> at
> org.apache.spark.sql.catalyst.plans.QueryPlan.transformExpressions(QueryPlan.scala:144)
> at
> org.apache.spark.sql.catalyst.plans.logical.LogicalPlan$$anonfun$resolveExpressions$1.applyOrElse(LogicalPlan.scala:79)
> at
> org.apache.spark.sql.catalyst.plans.logical.LogicalPlan$$anonfun$resolveExpressions$1.applyOrElse(LogicalPlan.scala:78)
> at
> org.apache.spark.sql.catalyst.plans.logical.LogicalPlan$$anonfun$resolveOperators$1.apply(LogicalPlan.scala:61)
> at
> org.apache.spark.sql.catalyst.plans.logical.LogicalPlan$$anonfun$resolveOperators$1.apply(LogicalPlan.scala:61)
> at
> org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:69)
> at
> org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveOperators(LogicalPlan.scala:60)
> at
> org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveExpressions(LogicalPlan.scala:78)
> at
> org.apache.spark.sql.catalyst.analysis.TypeCoercion$ImplicitTypeCasts$.apply(TypeCoercion.scala:615)
> at
> org.apache.spark.sql.catalyst.analysis.TypeCoercion$ImplicitTypeCasts$.apply(TypeCoercion.scala:614)
> at
> org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1$$anonfun$apply$1.apply(RuleExecutor.scala:85)
> at
> org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1$$anonfun$apply$1.apply(RuleExecutor.scala:82)
> at
> scala.collection.LinearSeqOptimized$class.foldLeft(LinearSeqOptimized.scala:124)
> at scala.collection.immutable.List.foldLeft(List.scala:84)
> at
> org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1.apply(RuleExecutor.scala:82)
> at
> org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1.apply(RuleExecutor.scala:74)
> at scala.collection.immutable.List.foreach(List.scala:381)
> at
> org.apache.spark.sql.catalyst.rules.RuleExecutor.execute(RuleExecutor.scala:74)
> at
> org.apache.spark.sql.execution.QueryExecution.analyzed$lzycompute(QueryExecution.scala:65)
> at
> org.apache.spark.sql.execution.QueryExecution.analyzed(QueryExecution.scala:63)
> at
> org.apache.spark.sql.execution.QueryExecution.assertAnalyzed(QueryExecution.scala:49)
> at org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:64)
> at org.apache.spark.sql.SparkSession.sql(SparkSession.scala:582)
> ... 48 elided
> {noformat}
> This bug is a regression. Spark 1.6 doesn't have this issue.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
