Tsuyoshi OZAWA created SPARK-4678:
-------------------------------------
Summary: A SQL query with subquery fails
Key: SPARK-4678
URL: https://issues.apache.org/jira/browse/SPARK-4678
Project: Spark
Issue Type: Bug
Components: SQL
Affects Versions: 1.1.1
Reporter: Tsuyoshi OZAWA
{code}
spark-sql> create external table if NOT EXISTS randomText100GB(text string)
location 'hdfs:///user/ozawa/randomText100GB';
spark-sql> CREATE TABLE wordcount AS
> SELECT word, count(1) AS count
> FROM (SELECT
EXPLODE(SPLIT(LCASE(REGEXP_REPLACE(text,'[\\p{Punct},\\p{Cntrl}]','')),' '))
> AS word FROM randomText100GB) words
> GROUP BY word;
org.apache.spark.SparkException: Job aborted due to stage failure: Task 9 in
stage 1.0 failed 4 times, most recent failure: Lost task 9.3 in stage 1.0 (TID
25, hadoop-slave2.c.gcp-s
amples.internal):
org.apache.spark.sql.catalyst.errors.package$TreeNodeException: Binding
attribute, tree: word#5
org.apache.spark.sql.catalyst.errors.package$.attachTree(package.scala:47)
org.apache.spark.sql.catalyst.expressions.BindReferences$$anonfun$bindReference$1.applyOrElse(BoundAttribute.scala:43)
org.apache.spark.sql.catalyst.expressions.BindReferences$$anonfun$bindReference$1.applyOrElse(BoundAttribute.scala:42)
org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:165)
org.apache.spark.sql.catalyst.trees.TreeNode.transform(TreeNode.scala:156)
org.apache.spark.sql.catalyst.expressions.BindReferences$.bindReference(BoundAttribute.scala:42)
org.apache.spark.sql.catalyst.expressions.InterpretedMutableProjection$$anonfun$$init$$2.apply(Projection.scala:52)
org.apache.spark.sql.catalyst.expressions.InterpretedMutableProjection$$anonfun$$init$$2.apply(Projection.scala:52)
scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244)
scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244)
scala.collection.IndexedSeqOptimized$class.foreach(IndexedSeqOptimized.scala:33)
scala.collection.mutable.WrappedArray.foreach(WrappedArray.scala:34)
scala.collection.TraversableLike$class.map(TraversableLike.scala:244)
scala.collection.AbstractTraversable.map(Traversable.scala:105)
org.apache.spark.sql.catalyst.expressions.InterpretedMutableProjection.<init>(Projection.scala:52)
org.apache.spark.sql.execution.SparkPlan$$anonfun$newMutableProjection$1.apply(SparkPlan.scala:106)
org.apache.spark.sql.execution.SparkPlan$$anonfun$newMutableProjection$1.apply(SparkPlan.scala:106)
org.apache.spark.sql.execution.Project$$anonfun$1.apply(basicOperators.scala:43)
org.apache.spark.sql.execution.Project$$anonfun$1.apply(basicOperators.scala:42)
org.apache.spark.rdd.RDD$$anonfun$13.apply(RDD.scala:596)
org.apache.spark.rdd.RDD$$anonfun$13.apply(RDD.scala:596)
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:262)
org.apache.spark.rdd.RDD.iterator(RDD.scala:229)
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:262)
org.apache.spark.rdd.RDD.iterator(RDD.scala:229)
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:262)
org.apache.spark.rdd.RDD.iterator(RDD.scala:229)
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:68)
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41)
org.apache.spark.scheduler.Task.run(Task.scala:54)
org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:178)
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
java.lang.Thread.run(Thread.java:745)
{code}
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
