Saif Addin created SPARK-21281:
----------------------------------
Summary: Casting empty typed array column return different results
depending on the api used
Key: SPARK-21281
URL: https://issues.apache.org/jira/browse/SPARK-21281
Project: Spark
Issue Type: Bug
Components: Spark Core
Affects Versions: 2.1.1
Reporter: Saif Addin
Hi all
I am running this piece of code
{code:java}
val data = spark.read.parquet("somedata.parquet")
data.withColumn("my_new_column", array().cast("array<string>")).show
{code}
and it works fine
{code:java}
+------+---------+--------------------+---+
|itemid|sentiment| text|my_new_column|
+------+---------+--------------------+---+
| 1| 0| ...| []|
| 2| 0| ...| []|
| 3| 1| omg...| []|
| 4| 0| .. Omga...| []|
{code}
but when I do
{code:java}
val data = spark.read.parquet("somedata.parquet")
import org.apache.spark.sql.types._
data.withColumn("my_new_column", array().cast(ArrayType(IntegerType))).show
{code}
I get:
{code:java}
scala.MatchError: NullType (of class org.apache.spark.sql.types.NullType$)
at org.apache.spark.sql.catalyst.expressions.Cast.castToInt(Cast.scala:264)
at
org.apache.spark.sql.catalyst.expressions.Cast.org$apache$spark$sql$catalyst$expressions$Cast$$cast(Cast.scala:433)
at org.apache.spark.sql.catalyst.expressions.Cast.castArray(Cast.scala:380)
at
org.apache.spark.sql.catalyst.expressions.Cast.org$apache$spark$sql$catalyst$expressions$Cast$$cast(Cast.scala:437)
at
org.apache.spark.sql.catalyst.expressions.Cast.cast$lzycompute(Cast.scala:447)
at org.apache.spark.sql.catalyst.expressions.Cast.cast(Cast.scala:447)
at org.apache.spark.sql.catalyst.expressions.Cast.nullSafeEval(Cast.scala:449)
at
org.apache.spark.sql.catalyst.expressions.UnaryExpression.eval(Expression.scala:325)
at
org.apache.spark.sql.catalyst.optimizer.ConstantFolding$$anonfun$apply$1$$anonfun$applyOrElse$1.applyOrElse(expressions.scala:50)
at
org.apache.spark.sql.catalyst.optimizer.ConstantFolding$$anonfun$apply$1$$anonfun$applyOrElse$1.applyOrElse(expressions.scala:43)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$3.apply(TreeNode.scala:288)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$3.apply(TreeNode.scala:288)
at
org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:70)
at
org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:287)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:293)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:293)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$5.apply(TreeNode.scala:331)
at
org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:188)
at
org.apache.spark.sql.catalyst.trees.TreeNode.transformChildren(TreeNode.scala:329)
at
org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:293)
at
org.apache.spark.sql.catalyst.plans.QueryPlan.transformExpressionDown$1(QueryPlan.scala:248)
at
org.apache.spark.sql.catalyst.plans.QueryPlan.org$apache$spark$sql$catalyst$plans$QueryPlan$$recursiveTransform$1(QueryPlan.scala:258)
at
org.apache.spark.sql.catalyst.plans.QueryPlan$$anonfun$org$apache$spark$sql$catalyst$plans$QueryPlan$$recursiveTransform$1$1.apply(QueryPlan.scala:262)
at
scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
at
scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
at
scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
at scala.collection.TraversableLike$class.map(TraversableLike.scala:234)
at scala.collection.AbstractTraversable.map(Traversable.scala:104)
at
org.apache.spark.sql.catalyst.plans.QueryPlan.org$apache$spark$sql$catalyst$plans$QueryPlan$$recursiveTransform$1(QueryPlan.scala:262)
at
org.apache.spark.sql.catalyst.plans.QueryPlan$$anonfun$6.apply(QueryPlan.scala:267)
at
org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:188)
at
org.apache.spark.sql.catalyst.plans.QueryPlan.transformExpressionsDown(QueryPlan.scala:267)
at
org.apache.spark.sql.catalyst.optimizer.ConstantFolding$$anonfun$apply$1.applyOrElse(expressions.scala:43)
at
org.apache.spark.sql.catalyst.optimizer.ConstantFolding$$anonfun$apply$1.applyOrElse(expressions.scala:42)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$3.apply(TreeNode.scala:288)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$3.apply(TreeNode.scala:288)
at
org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:70)
at
org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:287)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:293)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:293)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$5.apply(TreeNode.scala:331)
at
org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:188)
at
org.apache.spark.sql.catalyst.trees.TreeNode.transformChildren(TreeNode.scala:329)
at
org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:293)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:293)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:293)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$5.apply(TreeNode.scala:331)
at
org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:188)
at
org.apache.spark.sql.catalyst.trees.TreeNode.transformChildren(TreeNode.scala:329)
at
org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:293)
at org.apache.spark.sql.catalyst.trees.TreeNode.transform(TreeNode.scala:277)
at
org.apache.spark.sql.catalyst.optimizer.ConstantFolding$.apply(expressions.scala:42)
at
org.apache.spark.sql.catalyst.optimizer.ConstantFolding$.apply(expressions.scala:41)
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$1.apply(RuleExecutor.scala:82)
at
scala.collection.IndexedSeqOptimized$class.foldl(IndexedSeqOptimized.scala:57)
at
scala.collection.IndexedSeqOptimized$class.foldLeft(IndexedSeqOptimized.scala:66)
at scala.collection.mutable.WrappedArray.foldLeft(WrappedArray.scala:35)
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$1.apply(RuleExecutor.scala:74)
at scala.collection.immutable.List.foreach(List.scala:381)
at
org.apache.spark.sql.catalyst.rules.RuleExecutor.execute(RuleExecutor.scala:74)
at
org.apache.spark.sql.execution.QueryExecution.optimizedPlan$lzycompute(QueryExecution.scala:73)
at
org.apache.spark.sql.execution.QueryExecution.optimizedPlan(QueryExecution.scala:73)
at
org.apache.spark.sql.execution.QueryExecution.sparkPlan$lzycompute(QueryExecution.scala:79)
at
org.apache.spark.sql.execution.QueryExecution.sparkPlan(QueryExecution.scala:75)
at
org.apache.spark.sql.execution.QueryExecution.executedPlan$lzycompute(QueryExecution.scala:84)
at
org.apache.spark.sql.execution.QueryExecution.executedPlan(QueryExecution.scala:84)
at org.apache.spark.sql.Dataset.withTypedCallback(Dataset.scala:2791)
at org.apache.spark.sql.Dataset.head(Dataset.scala:2112)
at org.apache.spark.sql.Dataset.take(Dataset.scala:2327)
at org.apache.spark.sql.Dataset.showString(Dataset.scala:248)
at org.apache.spark.sql.Dataset.show(Dataset.scala:636)
at org.apache.spark.sql.Dataset.show(Dataset.scala:595)
at org.apache.spark.sql.Dataset.show(Dataset.scala:604)
... 50 elided
{code}
--
This message was sent by Atlassian JIRA
(v6.4.14#64029)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
