ah.. thanks , your code also works for me, I figured it's because I tried to encode a tuple of (MyClass, Int):
package org.apache.spark /** */ import org.apache.spark.sql.catalyst.util.{ArrayData, GenericArrayData} import org.apache.spark.sql.types._ import org.apache.spark.sql.{Encoders, SQLContext} object Hello { // this class has to be OUTSIDE the method that calls it!! otherwise gives error about typetag not found // the UDT stuff from https://github.com/apache/spark/blob/master/sql/core/src/main/scala/org/apache/spark/sql/test/ExamplePointUDT.scala // and http://stackoverflow.com/questions/32440461/how-to-define-schema-for-custom-type-in-spark-sql class Person4 { @scala.beans.BeanProperty def setX(x:Int): Unit = {} @scala.beans.BeanProperty def getX():Int = {1} } def main(args: Array[String]) { val logFile = "YOUR_SPARK_HOME/README.md" // Should be some file on your system val conf = new SparkConf().setMaster("local[*]").setAppName("Simple Application") val sc = new SparkContext(conf) val raw = Array((new Person4(), 1), (new Person4(), 1)) val myrdd = sc.parallelize(raw) val sqlContext = new SQLContext(sc) implicit val personEncoder = Encoders.bean[Person4](classOf[Person4]) implicit val personEncoder2 = Encoders.tuple(personEncoder, Encoders.INT) import sqlContext.implicits._ //// -------- this works -------------- Seq(new Person4(), new Person4()).toDS() //// ---------- this doesn't ----- Seq((new Person4(),1), (new Person4(),1)).toDS() sc.stop() } } On Tue, May 9, 2017 at 1:37 PM, Michael Armbrust <mich...@databricks.com> wrote: > Must be a bug. This works for me > <https://databricks-prod-cloudfront.cloud.databricks.com/public/4027ec902e239c93eaaa8714f173bcfc/1023043053387187/908554720841389/2840265927289860/latest.html> > in > Spark 2.1. > > On Tue, May 9, 2017 at 12:10 PM, Yang <teddyyyy...@gmail.com> wrote: > >> somehow the schema check is here >> >> https://github.com/apache/spark/blob/master/sql/catalyst/ >> src/main/scala/org/apache/spark/sql/catalyst/ScalaReflec >> tion.scala#L697-L750 >> >> supposedly beans are to be handled, but it's not clear to me which line >> handles the type of beans. if that's clear, I could probably annotate my >> bean class properly >> >> On Tue, May 9, 2017 at 11:19 AM, Michael Armbrust <mich...@databricks.com >> > wrote: >> >>> I think you are supposed to set BeanProperty on a var as they do here >>> <https://github.com/apache/spark/blob/f830bb9170f6b853565d9dd30ca7418b93a54fe3/mllib/src/main/scala/org/apache/spark/mllib/tree/configuration/Strategy.scala#L71-L83>. >>> If you are using scala though I'd consider using the case class encoders. >>> >>> On Tue, May 9, 2017 at 12:21 AM, Yang <teddyyyy...@gmail.com> wrote: >>> >>>> I'm trying to use Encoders.bean() to create an encoder for my custom >>>> class, but it fails complaining about can't find the schema: >>>> >>>> >>>> class Person4 { @scala.beans.BeanProperty def setX(x:Int): Unit = {} >>>> @scala.beans.BeanProperty def getX():Int = {1} } val personEncoder = >>>> Encoders.bean[Person4](classOf[Person4]) scala> val person_rdd =sc. >>>> parallelize(Array( (new Person4(), 1), (new Person4(), 2) )) person_rdd >>>> : org.apache.spark.rdd.RDD[(Person4, Int)] = ParallelCollectionRDD[1] >>>> at parallelize at <con sole>:31 scala> sqlcontext.createDataFrame(per >>>> son_rdd) java.lang.UnsupportedOperationException: Schema for type >>>> Person4 is not supported at org.apache.spark.sql.catalyst. >>>> ScalaReflection$.schemaFor(ScalaReflection.scala:716) at org.apache. >>>> spark.sql.catalyst.ScalaReflection$$anonfun$schemaFor$2.apply( >>>> ScalaReflection.scala:71 2) at org.apache.spark.sql.catalyst. >>>> ScalaReflection$$anonfun$schemaFor$2.apply(ScalaReflection.scala:71 1) >>>> at scala.collection.TraversableLike$$anonfun$map$1.apply(Traver >>>> sableLike.scala:234) at >>>> >>>> >>>> but if u look at the encoder's schema, it does know it: >>>> but the system does seem to understand the schema for "Person4": >>>> >>>> >>>> scala> personEncoder.schema >>>> res38: org.apache.spark.sql.types.StructType = >>>> StructType(StructField(x,IntegerType,false)) >>>> >>>> >>> >> >