Cheng Lian created SPARK-6708:
---------------------------------

             Summary: Using Hive UDTF may throw ClassNotFoundException
                 Key: SPARK-6708
                 URL: https://issues.apache.org/jira/browse/SPARK-6708
             Project: Spark
          Issue Type: Bug
          Components: SQL
    Affects Versions: 1.3.0, 1.2.1, 1.1.1
            Reporter: Cheng Lian


Spark shell session for reproducing this issue:
{code}
import sqlContext._

sql("create table t1 (str string)")
sql("select v.va from t1 lateral view json_tuple(str, 'a') v as 
va").queryExecution.analyzed
{code}
Exception thrown:
{noformat}
java.lang.ClassNotFoundException: json_tuple
        at 
scala.tools.nsc.interpreter.AbstractFileClassLoader.findClass(AbstractFileClassLoader.scala:83)
        at java.lang.ClassLoader.loadClass(ClassLoader.java:424)
        at java.lang.ClassLoader.loadClass(ClassLoader.java:357)
        at 
org.apache.spark.sql.hive.HiveFunctionWrapper.createFunction(Shim13.scala:148)
        at 
org.apache.spark.sql.hive.HiveGenericUdtf.function$lzycompute(hiveUdfs.scala:274)
        at 
org.apache.spark.sql.hive.HiveGenericUdtf.function(hiveUdfs.scala:274)
        at 
org.apache.spark.sql.hive.HiveGenericUdtf.outputInspector$lzycompute(hiveUdfs.scala:280)
        at 
org.apache.spark.sql.hive.HiveGenericUdtf.outputInspector(hiveUdfs.scala:280)
        at 
org.apache.spark.sql.hive.HiveGenericUdtf.outputDataTypes$lzycompute(hiveUdfs.scala:285)
        at 
org.apache.spark.sql.hive.HiveGenericUdtf.outputDataTypes(hiveUdfs.scala:285)
        at 
org.apache.spark.sql.hive.HiveGenericUdtf.makeOutput(hiveUdfs.scala:291)
        at 
org.apache.spark.sql.catalyst.expressions.Generator.output(generators.scala:60)
        at 
org.apache.spark.sql.catalyst.plans.logical.Generate$$anonfun$2.apply(basicOperators.scala:60)
        at 
org.apache.spark.sql.catalyst.plans.logical.Generate$$anonfun$2.apply(basicOperators.scala:60)
        at scala.Option.map(Option.scala:145)
        at 
org.apache.spark.sql.catalyst.plans.logical.Generate.generatorOutput(basicOperators.scala:60)
        at 
org.apache.spark.sql.catalyst.plans.logical.Generate.output(basicOperators.scala:70)
        at 
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan$$anonfun$resolveChildren$1.apply(LogicalPlan.scala:117)
        at 
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan$$anonfun$resolveChildren$1.apply(LogicalPlan.scala:117)
        at 
scala.collection.TraversableLike$$anonfun$flatMap$1.apply(TraversableLike.scala:251)
        at 
scala.collection.TraversableLike$$anonfun$flatMap$1.apply(TraversableLike.scala:251)
        at scala.collection.immutable.List.foreach(List.scala:318)
        at 
scala.collection.TraversableLike$class.flatMap(TraversableLike.scala:251)
        at scala.collection.AbstractTraversable.flatMap(Traversable.scala:105)
        at 
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveChildren(LogicalPlan.scala:117)
        at 
org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveReferences$$anonfun$apply$7$$anonfun$applyOrElse$2$$anonfun$11.apply(Analyzer.scala:292)
        at 
org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveReferences$$anonfun$apply$7$$anonfun$applyOrElse$2$$anonfun$11.apply(Analyzer.scala:292)
        at 
org.apache.spark.sql.catalyst.analysis.package$.withPosition(package.scala:48)
        at 
org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveReferences$$anonfun$apply$7$$anonfun$applyOrElse$2.applyOrElse(Analyzer.scala:292)
        at 
org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveReferences$$anonfun$apply$7$$anonfun$applyOrElse$2.applyOrElse(Analyzer.scala:284)
        at 
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformUp$1.apply(TreeNode.scala:252)
        at 
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformUp$1.apply(TreeNode.scala:252)
        at 
org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:51)
        at 
org.apache.spark.sql.catalyst.trees.TreeNode.transformUp(TreeNode.scala:251)
        at 
org.apache.spark.sql.catalyst.plans.QueryPlan.org$apache$spark$sql$catalyst$plans$QueryPlan$$transformExpressionUp$1(QueryPlan.scala:108)
        at 
org.apache.spark.sql.catalyst.plans.QueryPlan$$anonfun$2$$anonfun$apply$2.apply(QueryPlan.scala:123)
        at 
scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244)
        at 
scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244)
        at 
scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
        at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
        at scala.collection.TraversableLike$class.map(TraversableLike.scala:244)
        at scala.collection.AbstractTraversable.map(Traversable.scala:105)
        at 
org.apache.spark.sql.catalyst.plans.QueryPlan$$anonfun$2.apply(QueryPlan.scala:122)
        at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
        at scala.collection.Iterator$class.foreach(Iterator.scala:727)
        at scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
        at 
scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:48)
        at 
scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:103)
        at 
scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:47)
        at scala.collection.TraversableOnce$class.to(TraversableOnce.scala:273)
        at scala.collection.AbstractIterator.to(Iterator.scala:1157)
        at 
scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:265)
        at scala.collection.AbstractIterator.toBuffer(Iterator.scala:1157)
        at 
scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:252)
        at scala.collection.AbstractIterator.toArray(Iterator.scala:1157)
        at 
org.apache.spark.sql.catalyst.plans.QueryPlan.transformExpressionsUp(QueryPlan.scala:127)
        at 
org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveReferences$$anonfun$apply$7.applyOrElse(Analyzer.scala:284)
        at 
org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveReferences$$anonfun$apply$7.applyOrElse(Analyzer.scala:196)
        at 
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformUp$2.apply(TreeNode.scala:256)
        at 
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformUp$2.apply(TreeNode.scala:256)
        at 
org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:51)
        at 
org.apache.spark.sql.catalyst.trees.TreeNode.transformUp(TreeNode.scala:255)
        at 
org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveReferences$.apply(Analyzer.scala:196)
        at 
org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveReferences$.apply(Analyzer.scala:195)
        at 
org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$apply$1$$anonfun$apply$2.apply(RuleExecutor.scala:61)
        at 
org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$apply$1$$anonfun$apply$2.apply(RuleExecutor.scala:59)
        at 
scala.collection.LinearSeqOptimized$class.foldLeft(LinearSeqOptimized.scala:111)
        at scala.collection.immutable.List.foldLeft(List.scala:84)
        at 
org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$apply$1.apply(RuleExecutor.scala:59)
        at 
org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$apply$1.apply(RuleExecutor.scala:51)
        at scala.collection.immutable.List.foreach(List.scala:318)
        at 
org.apache.spark.sql.catalyst.rules.RuleExecutor.apply(RuleExecutor.scala:51)
        at 
org.apache.spark.sql.SQLContext$QueryExecution.analyzed$lzycompute(SQLContext.scala:1106)
        at 
org.apache.spark.sql.SQLContext$QueryExecution.analyzed(SQLContext.scala:1106)
        at 
org.apache.spark.sql.SQLContext$QueryExecution.assertAnalyzed(SQLContext.scala:1104)
        at org.apache.spark.sql.DataFrame.<init>(DataFrame.scala:133)
        at org.apache.spark.sql.DataFrame$.apply(DataFrame.scala:51)
        at org.apache.spark.sql.hive.HiveContext.sql(HiveContext.scala:97)
{noformat}
The problem is that we passed the function name rather than the resolved UDTF 
class name to {{HiveGenericUdtf}} 
[here|https://github.com/apache/spark/blob/9b40c17ab161b64933539abeefde443cb4f98673/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveQl.scala#L1288].



--
This message was sent by Atlassian JIRA
(v6.3.4#6332)

---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org

Reply via email to