You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@spark.apache.org by "sachin aggarwal (JIRA)" <ji...@apache.org> on 2015/12/03 06:40:10 UTC
[jira] [Updated] (SPARK-12117) Column Aliases are Ignored in
callUDF while using struct()
[ https://issues.apache.org/jira/browse/SPARK-12117?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
sachin aggarwal updated SPARK-12117:
------------------------------------
Description:
case where this works:
val TestDoc1 = sqlContext.createDataFrame(Seq(("sachin aggarwal", "1"), ("Rishabh", "2"))).toDF("myText", "id")
TestDoc1.select(callUDF("mydef",struct($"myText".as("Text"),$"id".as("label"))).as("col1")).show
steps to reproduce:
1)create a file copy following text--filename(a.json)
{ "myText": "Sachin Aggarwal", "id": "1"}
{ "myText": "Rishabh", "id": "2"}
2)define a simple UDF
def mydef(r:Row)={println(r.schema); r.getAs("Text").asInstanceOf[String]}
3)register the udf
sqlContext.udf.register("mydef" ,mydef _)
4)read the input file
val TestDoc2=sqlContext.read.json("/tmp/a.json")
5)make a call to UDF
TestDoc2.select(callUDF("mydef",struct($"myText".as("Text"),$"id".as("label"))).as("col1")).explain(true)
ERROR received:
java.lang.IllegalArgumentException: Field "Text" does not exist.
at org.apache.spark.sql.types.StructType$$anonfun$fieldIndex$1.apply(StructType.scala:234)
at org.apache.spark.sql.types.StructType$$anonfun$fieldIndex$1.apply(StructType.scala:234)
at scala.collection.MapLike$class.getOrElse(MapLike.scala:128)
at scala.collection.AbstractMap.getOrElse(Map.scala:58)
at org.apache.spark.sql.types.StructType.fieldIndex(StructType.scala:233)
at org.apache.spark.sql.catalyst.expressions.GenericRowWithSchema.fieldIndex(rows.scala:212)
at org.apache.spark.sql.Row$class.getAs(Row.scala:325)
at org.apache.spark.sql.catalyst.expressions.GenericRow.getAs(rows.scala:191)
at $line414.$read$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$$$$$c57ec8bf9b0d5f6161b97741d596ff0$$$$wC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.mydef(<console>:107)
at $line419.$read$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$$$$$c57ec8bf9b0d5f6161b97741d596ff0$$$$wC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$anonfun$1.apply(<console>:110)
at $line419.$read$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$$$$$c57ec8bf9b0d5f6161b97741d596ff0$$$$wC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$anonfun$1.apply(<console>:110)
at org.apache.spark.sql.catalyst.expressions.ScalaUDF$$anonfun$2.apply(ScalaUDF.scala:75)
at org.apache.spark.sql.catalyst.expressions.ScalaUDF$$anonfun$2.apply(ScalaUDF.scala:74)
at org.apache.spark.sql.catalyst.expressions.ScalaUDF.eval(ScalaUDF.scala:964)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$SpecificMutableProjection.apply(Unknown Source)
at org.apache.spark.sql.execution.Project$$anonfun$1$$anonfun$apply$2.apply(basicOperators.scala:55)
at org.apache.spark.sql.execution.Project$$anonfun$1$$anonfun$apply$2.apply(basicOperators.scala:53)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
at scala.collection.Iterator$$anon$10.next(Iterator.scala:312)
at scala.collection.Iterator$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.execution.SparkPlan$$anonfun$5.apply(SparkPlan.scala:215)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$5.apply(SparkPlan.scala:215)
at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1848)
at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1848)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
at org.apache.spark.scheduler.Task.run(Task.scala:88)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1177)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:642)
at java.lang.Thread.run(Thread.java:857)
was:
case where this works:
val TestDoc1 = sqlContext.createDataFrame(Seq(("sachin aggarwal", "1"), ("Rishabh", "2"))).toDF("myText", "id")
TestDoc1.select(callUDF("mydef",struct($"myText".as("Text"),$"id".as("label"))).as("col1")).show
steps to reproduce:
1)create a file copy following text--filename(a.json)
{ "myText": "Mauricio A. Hernandez", "id": "1"}
{ "myText": "Popa, Lucian", "id": "2"}
2)define a simple UDF
def mydef(r:Row)={println(r.schema); r.getAs("Text").asInstanceOf[String]}
3)register the udf
sqlContext.udf.register("mydef" ,mydef _)
4)read the input file
val TestDoc2=sqlContext.read.json("/tmp/a.json")
5)make a call to UDF
TestDoc2.select(callUDF("mydef",struct($"myText".as("Text"),$"id".as("label"))).as("col1")).explain(true)
ERROR received:
java.lang.IllegalArgumentException: Field "Text" does not exist.
at org.apache.spark.sql.types.StructType$$anonfun$fieldIndex$1.apply(StructType.scala:234)
at org.apache.spark.sql.types.StructType$$anonfun$fieldIndex$1.apply(StructType.scala:234)
at scala.collection.MapLike$class.getOrElse(MapLike.scala:128)
at scala.collection.AbstractMap.getOrElse(Map.scala:58)
at org.apache.spark.sql.types.StructType.fieldIndex(StructType.scala:233)
at org.apache.spark.sql.catalyst.expressions.GenericRowWithSchema.fieldIndex(rows.scala:212)
at org.apache.spark.sql.Row$class.getAs(Row.scala:325)
at org.apache.spark.sql.catalyst.expressions.GenericRow.getAs(rows.scala:191)
at $line414.$read$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$$$$$c57ec8bf9b0d5f6161b97741d596ff0$$$$wC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.mydef(<console>:107)
at $line419.$read$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$$$$$c57ec8bf9b0d5f6161b97741d596ff0$$$$wC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$anonfun$1.apply(<console>:110)
at $line419.$read$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$$$$$c57ec8bf9b0d5f6161b97741d596ff0$$$$wC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$anonfun$1.apply(<console>:110)
at org.apache.spark.sql.catalyst.expressions.ScalaUDF$$anonfun$2.apply(ScalaUDF.scala:75)
at org.apache.spark.sql.catalyst.expressions.ScalaUDF$$anonfun$2.apply(ScalaUDF.scala:74)
at org.apache.spark.sql.catalyst.expressions.ScalaUDF.eval(ScalaUDF.scala:964)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$SpecificMutableProjection.apply(Unknown Source)
at org.apache.spark.sql.execution.Project$$anonfun$1$$anonfun$apply$2.apply(basicOperators.scala:55)
at org.apache.spark.sql.execution.Project$$anonfun$1$$anonfun$apply$2.apply(basicOperators.scala:53)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
at scala.collection.Iterator$$anon$10.next(Iterator.scala:312)
at scala.collection.Iterator$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.execution.SparkPlan$$anonfun$5.apply(SparkPlan.scala:215)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$5.apply(SparkPlan.scala:215)
at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1848)
at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1848)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
at org.apache.spark.scheduler.Task.run(Task.scala:88)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1177)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:642)
at java.lang.Thread.run(Thread.java:857)
> Column Aliases are Ignored in callUDF while using struct()
> ----------------------------------------------------------
>
> Key: SPARK-12117
> URL: https://issues.apache.org/jira/browse/SPARK-12117
> Project: Spark
> Issue Type: Bug
> Components: SQL
> Affects Versions: 1.5.1
> Reporter: sachin aggarwal
>
> case where this works:
> val TestDoc1 = sqlContext.createDataFrame(Seq(("sachin aggarwal", "1"), ("Rishabh", "2"))).toDF("myText", "id")
> TestDoc1.select(callUDF("mydef",struct($"myText".as("Text"),$"id".as("label"))).as("col1")).show
> steps to reproduce:
> 1)create a file copy following text--filename(a.json)
> { "myText": "Sachin Aggarwal", "id": "1"}
> { "myText": "Rishabh", "id": "2"}
> 2)define a simple UDF
> def mydef(r:Row)={println(r.schema); r.getAs("Text").asInstanceOf[String]}
> 3)register the udf
> sqlContext.udf.register("mydef" ,mydef _)
> 4)read the input file
> val TestDoc2=sqlContext.read.json("/tmp/a.json")
> 5)make a call to UDF
> TestDoc2.select(callUDF("mydef",struct($"myText".as("Text"),$"id".as("label"))).as("col1")).explain(true)
> ERROR received:
> java.lang.IllegalArgumentException: Field "Text" does not exist.
> at org.apache.spark.sql.types.StructType$$anonfun$fieldIndex$1.apply(StructType.scala:234)
> at org.apache.spark.sql.types.StructType$$anonfun$fieldIndex$1.apply(StructType.scala:234)
> at scala.collection.MapLike$class.getOrElse(MapLike.scala:128)
> at scala.collection.AbstractMap.getOrElse(Map.scala:58)
> at org.apache.spark.sql.types.StructType.fieldIndex(StructType.scala:233)
> at org.apache.spark.sql.catalyst.expressions.GenericRowWithSchema.fieldIndex(rows.scala:212)
> at org.apache.spark.sql.Row$class.getAs(Row.scala:325)
> at org.apache.spark.sql.catalyst.expressions.GenericRow.getAs(rows.scala:191)
> at $line414.$read$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$$$$$c57ec8bf9b0d5f6161b97741d596ff0$$$$wC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.mydef(<console>:107)
> at $line419.$read$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$$$$$c57ec8bf9b0d5f6161b97741d596ff0$$$$wC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$anonfun$1.apply(<console>:110)
> at $line419.$read$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$$$$$c57ec8bf9b0d5f6161b97741d596ff0$$$$wC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$anonfun$1.apply(<console>:110)
> at org.apache.spark.sql.catalyst.expressions.ScalaUDF$$anonfun$2.apply(ScalaUDF.scala:75)
> at org.apache.spark.sql.catalyst.expressions.ScalaUDF$$anonfun$2.apply(ScalaUDF.scala:74)
> at org.apache.spark.sql.catalyst.expressions.ScalaUDF.eval(ScalaUDF.scala:964)
> at org.apache.spark.sql.catalyst.expressions.GeneratedClass$SpecificMutableProjection.apply(Unknown Source)
> at org.apache.spark.sql.execution.Project$$anonfun$1$$anonfun$apply$2.apply(basicOperators.scala:55)
> at org.apache.spark.sql.execution.Project$$anonfun$1$$anonfun$apply$2.apply(basicOperators.scala:53)
> at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
> at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
> at scala.collection.Iterator$$anon$10.next(Iterator.scala:312)
> at scala.collection.Iterator$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.execution.SparkPlan$$anonfun$5.apply(SparkPlan.scala:215)
> at org.apache.spark.sql.execution.SparkPlan$$anonfun$5.apply(SparkPlan.scala:215)
> at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1848)
> at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1848)
> at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
> at org.apache.spark.scheduler.Task.run(Task.scala:88)
> at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
> at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1177)
> at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:642)
> at java.lang.Thread.run(Thread.java:857)
--
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