[SPARK-6887] ColumnBuilder misses FloatType

• Type: Bug
• Status: Resolved
• Priority: Major
• Resolution: Fixed
• Affects Version/s: 1.4.0
• Fix Version/s: 1.4.0
• Component/s: SQL
• Assignee: Yin Huai
• Reporter: Yin Huai
• Created: 13/Apr/15 22:14
• Updated: 15/Apr/15 20:04
• Resolved: 15/Apr/15 20:04

Description

To reproduce ...

import org.apache.spark.sql.types._
import org.apache.spark.sql.Row

val schema = StructType(StructField("c", FloatType, true) :: Nil)

val rdd = sc.parallelize(1 to 100).map(i => Row(i.toFloat))

sqlContext.createDataFrame(rdd, schema).registerTempTable("test")

sqlContext.sql("cache table test")

sqlContext.table("test").show

The exception is ...

15/04/13 15:00:12 INFO DAGScheduler: Job 0 failed: collect at SparkPlan.scala:88, took 0.474392 s
org.apache.spark.SparkException: Job aborted due to stage failure: Task 5 in stage 0.0 failed 1 times, most recent failure: Lost task 5.0 in stage 0.0 (TID 5, localhost): java.lang.ClassCastException: org.apache.spark.sql.catalyst.expressions.MutableFloat cannot be cast to org.apache.spark.sql.catalyst.expressions.MutableLong
	at org.apache.spark.sql.catalyst.expressions.SpecificMutableRow.setLong(SpecificMutableRow.scala:292)
	at org.apache.spark.sql.columnar.compression.LongDelta$Decoder.next(compressionSchemes.scala:539)
	at org.apache.spark.sql.columnar.compression.CompressibleColumnAccessor$class.extractSingle(CompressibleColumnAccessor.scala:37)
	at org.apache.spark.sql.columnar.NativeColumnAccessor.extractSingle(ColumnAccessor.scala:64)
	at org.apache.spark.sql.columnar.BasicColumnAccessor.extractTo(ColumnAccessor.scala:54)
	at org.apache.spark.sql.columnar.NativeColumnAccessor.org$apache$spark$sql$columnar$NullableColumnAccessor$$super$extractTo(ColumnAccessor.scala:64)
	at org.apache.spark.sql.columnar.NullableColumnAccessor$class.extractTo(NullableColumnAccessor.scala:52)
	at org.apache.spark.sql.columnar.NativeColumnAccessor.extractTo(ColumnAccessor.scala:64)
	at org.apache.spark.sql.columnar.InMemoryColumnarTableScan$$anonfun$8$$anonfun$13$$anon$2.next(InMemoryColumnarTableScan.scala:295)
	at org.apache.spark.sql.columnar.InMemoryColumnarTableScan$$anonfun$8$$anonfun$13$$anon$2.next(InMemoryColumnarTableScan.scala:290)
	at scala.collection.Iterator$$anon$13.next(Iterator.scala:372)
	at org.apache.spark.sql.execution.Aggregate$$anonfun$execute$1$$anonfun$6.apply(Aggregate.scala:130)
	at org.apache.spark.sql.execution.Aggregate$$anonfun$execute$1$$anonfun$6.apply(Aggregate.scala:126)
	at org.apache.spark.rdd.RDD$$anonfun$14.apply(RDD.scala:640)
	at org.apache.spark.rdd.RDD$$anonfun$14.apply(RDD.scala:640)
	at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
	at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:277)
	at org.apache.spark.rdd.RDD.iterator(RDD.scala:244)
	at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
	at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:277)
	at org.apache.spark.rdd.RDD.iterator(RDD.scala:244)
	at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:68)
	at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41)
	at org.apache.spark.scheduler.Task.run(Task.scala:64)
	at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:210)
	at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
	at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
	at java.lang.Thread.run(Thread.java:745)

Issue Links

• links to: [Github] Pull Request #5499 (yhuai)