You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@spark.apache.org by "Jia Li (JIRA)" <ji...@apache.org> on 2015/10/23 10:37:27 UTC
[jira] [Created] (SPARK-11277) sort_array throws exception
scala.MatchError
Jia Li created SPARK-11277:
------------------------------
Summary: sort_array throws exception scala.MatchError
Key: SPARK-11277
URL: https://issues.apache.org/jira/browse/SPARK-11277
Project: Spark
Issue Type: Bug
Components: SQL
Affects Versions: 1.6.0
Environment: Linux
Reporter: Jia Li
Priority: Minor
I was trying out the sort_array function then hit this exception.
I looked into the spark source code. I found the root cause is that sort_array does not check for an array of NULLs. It's not meaningful to sort an array of entirely NULLs anyway.
I already have a fix for this issue and I'm going to create a pull request for it.
scala> sqlContext.sql("select sort_array(array(null, null)) from t1").show()
scala.MatchError: ArrayType(NullType,true) (of class org.apache.spark.sql.types.ArrayType)
at org.apache.spark.sql.catalyst.expressions.SortArray.lt$lzycompute(collectionOperations.scala:68)
at org.apache.spark.sql.catalyst.expressions.SortArray.lt(collectionOperations.scala:67)
at org.apache.spark.sql.catalyst.expressions.SortArray.nullSafeEval(collectionOperations.scala:111)
at org.apache.spark.sql.catalyst.expressions.BinaryExpression.eval(Expression.scala:341)
at org.apache.spark.sql.catalyst.optimizer.ConstantFolding$$anonfun$apply$9$$anonfun$applyOrElse$2.applyOrElse(Optimizer.scala:440)
at org.apache.spark.sql.catalyst.optimizer.ConstantFolding$$anonfun$apply$9$$anonfun$applyOrElse$2.applyOrElse(Optimizer.scala:433)
at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$3.apply(TreeNode.scala:227)
at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$3.apply(TreeNode.scala:227)
at org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:51)
at org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:226)
at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:232)
at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:232)
at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$4.apply(TreeNode.scala:249)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
at scala.collection.Iterator$class.foreach(Iterator.scala:727)
at scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
at scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:48)
at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:103)
at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:47)
at scala.collection.TraversableOnce$class.to(TraversableOnce.scala:273)
at scala.collection.AbstractIterator.to(Iterator.scala:1157)
at scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:265)
at scala.collection.AbstractIterator.toBuffer(Iterator.scala:1157)
at scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:252)
at scala.collection.AbstractIterator.toArray(Iterator.scala:1157)
at org.apache.spark.sql.catalyst.trees.TreeNode.transformChildren(TreeNode.scala:279)
at org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:232)
at org.apache.spark.sql.catalyst.plans.QueryPlan.transformExpressionDown$1(QueryPlan.scala:75)
at org.apache.spark.sql.catalyst.plans.QueryPlan.org$apache$spark$sql$catalyst$plans$QueryPlan$$recursiveTransform$1(QueryPlan.scala:85)
at org.apache.spark.sql.catalyst.plans.QueryPlan$$anonfun$org$apache$spark$sql$catalyst$plans$QueryPlan$$recursiveTransform$1$1.apply(QueryPlan.scala:89)
at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244)
at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
at scala.collection.TraversableLike$class.map(TraversableLike.scala:244)
at scala.collection.AbstractTraversable.map(Traversable.scala:105)
at org.apache.spark.sql.catalyst.plans.QueryPlan.org$apache$spark$sql$catalyst$plans$QueryPlan$$recursiveTransform$1(QueryPlan.scala:89)
at org.apache.spark.sql.catalyst.plans.QueryPlan$$anonfun$1.apply(QueryPlan.scala:93)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
at scala.collection.Iterator$class.foreach(Iterator.scala:727)
at scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
at scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:48)
at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:103)
at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:47)
at scala.collection.TraversableOnce$class.to(TraversableOnce.scala:273)
at scala.collection.AbstractIterator.to(Iterator.scala:1157)
at scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:265)
at scala.collection.AbstractIterator.toBuffer(Iterator.scala:1157)
at scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:252)
at scala.collection.AbstractIterator.toArray(Iterator.scala:1157)
at org.apache.spark.sql.catalyst.plans.QueryPlan.transformExpressionsDown(QueryPlan.scala:93)
at org.apache.spark.sql.catalyst.optimizer.ConstantFolding$$anonfun$apply$9.applyOrElse(Optimizer.scala:433)
at org.apache.spark.sql.catalyst.optimizer.ConstantFolding$$anonfun$apply$9.applyOrElse(Optimizer.scala:432)
at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$3.apply(TreeNode.scala:227)
at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$3.apply(TreeNode.scala:227)
at org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:51)
at org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:226)
at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:232)
at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:232)
at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$4.apply(TreeNode.scala:249)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
at scala.collection.Iterator$class.foreach(Iterator.scala:727)
at scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
at scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:48)
at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:103)
at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:47)
at scala.collection.TraversableOnce$class.to(TraversableOnce.scala:273)
at scala.collection.AbstractIterator.to(Iterator.scala:1157)
at scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:265)
at scala.collection.AbstractIterator.toBuffer(Iterator.scala:1157)
at scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:252)
at scala.collection.AbstractIterator.toArray(Iterator.scala:1157)
at org.apache.spark.sql.catalyst.trees.TreeNode.transformChildren(TreeNode.scala:279)
at org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:232)
at org.apache.spark.sql.catalyst.trees.TreeNode.transform(TreeNode.scala:217)
at org.apache.spark.sql.catalyst.optimizer.ConstantFolding$.apply(Optimizer.scala:432)
at org.apache.spark.sql.catalyst.optimizer.ConstantFolding$.apply(Optimizer.scala:431)
at org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1$$anonfun$apply$1.apply(RuleExecutor.scala:83)
at org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1$$anonfun$apply$1.apply(RuleExecutor.scala:80)
at scala.collection.IndexedSeqOptimized$class.foldl(IndexedSeqOptimized.scala:51)
at scala.collection.IndexedSeqOptimized$class.foldLeft(IndexedSeqOptimized.scala:60)
at scala.collection.mutable.WrappedArray.foldLeft(WrappedArray.scala:34)
at org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1.apply(RuleExecutor.scala:80)
at org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1.apply(RuleExecutor.scala:72)
at scala.collection.immutable.List.foreach(List.scala:318)
at org.apache.spark.sql.catalyst.rules.RuleExecutor.execute(RuleExecutor.scala:72)
at org.apache.spark.sql.execution.QueryExecution.optimizedPlan$lzycompute(QueryExecution.scala:43)
at org.apache.spark.sql.execution.QueryExecution.optimizedPlan(QueryExecution.scala:43)
at org.apache.spark.sql.execution.QueryExecution.sparkPlan$lzycompute(QueryExecution.scala:48)
at org.apache.spark.sql.execution.QueryExecution.sparkPlan(QueryExecution.scala:46)
at org.apache.spark.sql.execution.QueryExecution.executedPlan$lzycompute(QueryExecution.scala:52)
at org.apache.spark.sql.execution.QueryExecution.executedPlan(QueryExecution.scala:52)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:53)
at org.apache.spark.sql.DataFrame.withNewExecutionId(DataFrame.scala:1952)
at org.apache.spark.sql.DataFrame.org$apache$spark$sql$DataFrame$$execute$1(DataFrame.scala:1422)
at org.apache.spark.sql.DataFrame.org$apache$spark$sql$DataFrame$$collect(DataFrame.scala:1429)
at org.apache.spark.sql.DataFrame$$anonfun$head$1.apply(DataFrame.scala:1348)
at org.apache.spark.sql.DataFrame$$anonfun$head$1.apply(DataFrame.scala:1347)
at org.apache.spark.sql.DataFrame.withCallback(DataFrame.scala:1962)
at org.apache.spark.sql.DataFrame.head(DataFrame.scala:1347)
at org.apache.spark.sql.DataFrame.take(DataFrame.scala:1412)
at org.apache.spark.sql.DataFrame.showString(DataFrame.scala:178)
at org.apache.spark.sql.DataFrame.show(DataFrame.scala:401)
at org.apache.spark.sql.DataFrame.show(DataFrame.scala:362)
at org.apache.spark.sql.DataFrame.show(DataFrame.scala:370)
at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:20)
at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:25)
at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:27)
at $iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:29)
at $iwC$$iwC$$iwC$$iwC.<init>(<console>:31)
at $iwC$$iwC$$iwC.<init>(<console>:33)
at $iwC$$iwC.<init>(<console>:35)
at $iwC.<init>(<console>:37)
at <init>(<console>:39)
at .<init>(<console>:43)
at .<clinit>(<console>)
at .<init>(<console>:7)
at .<clinit>(<console>)
at $print(<console>)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:606)
at org.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:1065)
at org.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1340)
at org.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:840)
at org.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:871)
at org.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:819)
at org.apache.spark.repl.SparkILoop.reallyInterpret$1(SparkILoop.scala:857)
at org.apache.spark.repl.SparkILoop.interpretStartingWith(SparkILoop.scala:902)
at org.apache.spark.repl.SparkILoop.command(SparkILoop.scala:814)
at org.apache.spark.repl.SparkILoop.processLine$1(SparkILoop.scala:657)
at org.apache.spark.repl.SparkILoop.innerLoop$1(SparkILoop.scala:665)
at org.apache.spark.repl.SparkILoop.org$apache$spark$repl$SparkILoop$$loop(SparkILoop.scala:670)
at org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$process$1.apply$mcZ$sp(SparkILoop.scala:997)
at org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$process$1.apply(SparkILoop.scala:945)
at org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$process$1.apply(SparkILoop.scala:945)
at scala.tools.nsc.util.ScalaClassLoader$.savingContextLoader(ScalaClassLoader.scala:135)
at org.apache.spark.repl.SparkILoop.org$apache$spark$repl$SparkILoop$$process(SparkILoop.scala:945)
at org.apache.spark.repl.SparkILoop.process(SparkILoop.scala:1059)
at org.apache.spark.repl.Main$.main(Main.scala:31)
at org.apache.spark.repl.Main.main(Main.scala)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:606)
at org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:680)
at org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:180)
at org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:205)
at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:120)
at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@spark.apache.org
For additional commands, e-mail: issues-help@spark.apache.org