[
https://issues.apache.org/jira/browse/PHOENIX-2287?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14909415#comment-14909415
]
maghamravikiran commented on PHOENIX-2287:
------------------------------------------
[~jmahonin]
The patch looks good.
For the DecimalType, would it be ideal to explicitly specify the precision
and scale to the defaults as that will ensure the phoenix-spark module works
with prior versions of spark. I notice SYSTEM_DEFAULT has been added in 1.5.0 v
only.
> Spark Plugin Exception - java.lang.ClassCastException:
> org.apache.spark.sql.catalyst.expressions.GenericMutableRow cannot be cast to
> org.apache.spark.sql.Row
> -------------------------------------------------------------------------------------------------------------------------------------------------------------
>
> Key: PHOENIX-2287
> URL: https://issues.apache.org/jira/browse/PHOENIX-2287
> Project: Phoenix
> Issue Type: Bug
> Affects Versions: 4.5.2
> Environment: - HBase 1.1.1 running in standalone mode on OS X
> - Spark 1.5.0
> - Phoenix 4.5.2
> Reporter: Babar Tareen
> Assignee: Josh Mahonin
> Attachments: PHOENIX-2287.patch
>
>
> Running the DataFrame example on Spark Plugin page
> (https://phoenix.apache.org/phoenix_spark.html) results in following
> exception. The same code works as expected with Spark 1.4.1.
> {code:java}
> import org.apache.spark.SparkContext
> import org.apache.spark.sql.SQLContext
> import org.apache.phoenix.spark._
> val sc = new SparkContext("local", "phoenix-test")
> val sqlContext = new SQLContext(sc)
> val df = sqlContext.load(
> "org.apache.phoenix.spark",
> Map("table" -> "TABLE1", "zkUrl" -> "127.0.0.1:2181")
> )
> df
> .filter(df("COL1") === "test_row_1" && df("ID") === 1L)
> .select(df("ID"))
> .show
> {code}
> Exception
> {quote}
> java.lang.ClassCastException:
> org.apache.spark.sql.catalyst.expressions.GenericMutableRow cannot be cast to
> org.apache.spark.sql.Row
> at org.apache.spark.sql.SQLContext$$anonfun$7.apply(SQLContext.scala:439)
> ~[spark-sql_2.11-1.5.0.jar:1.5.0]
> at scala.collection.Iterator$$anon$11.next(Iterator.scala:363)
> ~[scala-library-2.11.4.jar:na]
> at scala.collection.Iterator$$anon$11.next(Iterator.scala:363)
> ~[scala-library-2.11.4.jar:na]
> at scala.collection.Iterator$$anon$11.next(Iterator.scala:363)
> ~[scala-library-2.11.4.jar:na]
> at
> org.apache.spark.sql.execution.aggregate.TungstenAggregationIterator.processInputs(TungstenAggregationIterator.scala:366)
> ~[spark-sql_2.11-1.5.0.jar:1.5.0]
> at
> org.apache.spark.sql.execution.aggregate.TungstenAggregationIterator.start(TungstenAggregationIterator.scala:622)
> ~[spark-sql_2.11-1.5.0.jar:1.5.0]
> at
> org.apache.spark.sql.execution.aggregate.TungstenAggregate$$anonfun$doExecute$1.org$apache$spark$sql$execution$aggregate$TungstenAggregate$$anonfun$$executePartition$1(TungstenAggregate.scala:110)
> ~[spark-sql_2.11-1.5.0.jar:1.5.0]
> at
> org.apache.spark.sql.execution.aggregate.TungstenAggregate$$anonfun$doExecute$1$$anonfun$2.apply(TungstenAggregate.scala:119)
> ~[spark-sql_2.11-1.5.0.jar:1.5.0]
> at
> org.apache.spark.sql.execution.aggregate.TungstenAggregate$$anonfun$doExecute$1$$anonfun$2.apply(TungstenAggregate.scala:119)
> ~[spark-sql_2.11-1.5.0.jar:1.5.0]
> at
> org.apache.spark.rdd.MapPartitionsWithPreparationRDD.compute(MapPartitionsWithPreparationRDD.scala:64)
> ~[spark-core_2.11-1.5.0.jar:1.5.0]
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297)
> ~[spark-core_2.11-1.5.0.jar:1.5.0]
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:264)
> ~[spark-core_2.11-1.5.0.jar:1.5.0]
> at
> org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> ~[spark-core_2.11-1.5.0.jar:1.5.0]
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297)
> ~[spark-core_2.11-1.5.0.jar:1.5.0]
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:264)
> ~[spark-core_2.11-1.5.0.jar:1.5.0]
> at
> org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:73)
> ~[spark-core_2.11-1.5.0.jar:1.5.0]
> at
> org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41)
> ~[spark-core_2.11-1.5.0.jar:1.5.0]
> at org.apache.spark.scheduler.Task.run(Task.scala:88)
> ~[spark-core_2.11-1.5.0.jar:1.5.0]
> at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
> ~[spark-core_2.11-1.5.0.jar:1.5.0]
> at
> java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
> [na:1.8.0_45]
> at
> java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
> [na:1.8.0_45]
> at java.lang.Thread.run(Thread.java:745) [na:1.8.0_45]
> {quote}
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
