[
https://issues.apache.org/jira/browse/SPARK-19666?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15875645#comment-15875645
]
Takeshi Yamamuro commented on SPARK-19666:
------------------------------------------
In my case, when I passed a invalid bean, I got a empty DF;
{code}
scala> :paste
class BeanClass extends Serializable {
private[this] var data: Int = 0
def get(): Int = data
def set(i: Int): Unit = { data = i }
}
scala> val rdd = sc.parallelize((0 until 10)).map { i => val data = new
BeanClass(); data.set(i); data }
rdd: org.apache.spark.rdd.RDD[BeanClass] = MapPartitionsRDD[1] at map at
<console>:25
scala> val df = spark.createDataFrame(rdd, classOf[BeanClass])
df: org.apache.spark.sql.DataFrame = []
scala> df.show
++
||
++
||
||
||
||
||
||
||
||
||
||
++
{code}
Even in this case, I want better error messages.
Probably, it seems okay to add error handling around here:
https://github.com/apache/spark/blob/master/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/JavaTypeInference.scala#L124
i.e.) If we get a empty `properties`, it just throws an AnalysisException, or
something.
> Exception when calling createDataFrame with typed RDD
> -----------------------------------------------------
>
> Key: SPARK-19666
> URL: https://issues.apache.org/jira/browse/SPARK-19666
> Project: Spark
> Issue Type: Bug
> Components: SQL
> Affects Versions: 2.1.0
> Reporter: Colin Breame
>
> The following code:
> {code}
> var tmp = sc.parallelize(Seq(new __Message()))
> val spark = SparkSession.builder().getOrCreate()
> var df = spark.createDataFrame(tmp, classOf[__Message])
> {code}
> Produces this error message.
> {code}
> Exception in thread "main" java.lang.NullPointerException
> at org.spark_project.guava.reflect.TypeToken.method(TypeToken.java:465)
> at
> org.apache.spark.sql.catalyst.JavaTypeInference$$anonfun$2.apply(JavaTypeInference.scala:126)
> at
> org.apache.spark.sql.catalyst.JavaTypeInference$$anonfun$2.apply(JavaTypeInference.scala:125)
> at
> scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
> at
> scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
> at
> scala.collection.IndexedSeqOptimized$class.foreach(IndexedSeqOptimized.scala:33)
> at scala.collection.mutable.ArrayOps$ofRef.foreach(ArrayOps.scala:186)
> at scala.collection.TraversableLike$class.map(TraversableLike.scala:234)
> at scala.collection.mutable.ArrayOps$ofRef.map(ArrayOps.scala:186)
> at
> org.apache.spark.sql.catalyst.JavaTypeInference$.org$apache$spark$sql$catalyst$JavaTypeInference$$inferDataType(JavaTypeInference.scala:125)
> at
> org.apache.spark.sql.catalyst.JavaTypeInference$$anonfun$2.apply(JavaTypeInference.scala:127)
> at
> org.apache.spark.sql.catalyst.JavaTypeInference$$anonfun$2.apply(JavaTypeInference.scala:125)
> at
> scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
> at
> scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
> at
> scala.collection.IndexedSeqOptimized$class.foreach(IndexedSeqOptimized.scala:33)
> at scala.collection.mutable.ArrayOps$ofRef.foreach(ArrayOps.scala:186)
> at scala.collection.TraversableLike$class.map(TraversableLike.scala:234)
> at scala.collection.mutable.ArrayOps$ofRef.map(ArrayOps.scala:186)
> at
> org.apache.spark.sql.catalyst.JavaTypeInference$.org$apache$spark$sql$catalyst$JavaTypeInference$$inferDataType(JavaTypeInference.scala:125)
> at
> org.apache.spark.sql.catalyst.JavaTypeInference$$anonfun$2.apply(JavaTypeInference.scala:127)
> at
> org.apache.spark.sql.catalyst.JavaTypeInference$$anonfun$2.apply(JavaTypeInference.scala:125)
> at
> scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
> at
> scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
> at
> scala.collection.IndexedSeqOptimized$class.foreach(IndexedSeqOptimized.scala:33)
> at scala.collection.mutable.ArrayOps$ofRef.foreach(ArrayOps.scala:186)
> at scala.collection.TraversableLike$class.map(TraversableLike.scala:234)
> at scala.collection.mutable.ArrayOps$ofRef.map(ArrayOps.scala:186)
> at
> org.apache.spark.sql.catalyst.JavaTypeInference$.org$apache$spark$sql$catalyst$JavaTypeInference$$inferDataType(JavaTypeInference.scala:125)
> at
> org.apache.spark.sql.catalyst.JavaTypeInference$$anonfun$2.apply(JavaTypeInference.scala:127)
> at
> org.apache.spark.sql.catalyst.JavaTypeInference$$anonfun$2.apply(JavaTypeInference.scala:125)
> at
> scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
> at
> scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
> at
> scala.collection.IndexedSeqOptimized$class.foreach(IndexedSeqOptimized.scala:33)
> at scala.collection.mutable.ArrayOps$ofRef.foreach(ArrayOps.scala:186)
> at scala.collection.TraversableLike$class.map(TraversableLike.scala:234)
> at scala.collection.mutable.ArrayOps$ofRef.map(ArrayOps.scala:186)
> at
> org.apache.spark.sql.catalyst.JavaTypeInference$.org$apache$spark$sql$catalyst$JavaTypeInference$$inferDataType(JavaTypeInference.scala:125)
> at
> org.apache.spark.sql.catalyst.JavaTypeInference$$anonfun$2.apply(JavaTypeInference.scala:127)
> at
> org.apache.spark.sql.catalyst.JavaTypeInference$$anonfun$2.apply(JavaTypeInference.scala:125)
> at
> scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
> at
> scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
> at
> scala.collection.IndexedSeqOptimized$class.foreach(IndexedSeqOptimized.scala:33)
> at scala.collection.mutable.ArrayOps$ofRef.foreach(ArrayOps.scala:186)
> at scala.collection.TraversableLike$class.map(TraversableLike.scala:234)
> at scala.collection.mutable.ArrayOps$ofRef.map(ArrayOps.scala:186)
> at
> org.apache.spark.sql.catalyst.JavaTypeInference$.org$apache$spark$sql$catalyst$JavaTypeInference$$inferDataType(JavaTypeInference.scala:125)
> at
> org.apache.spark.sql.catalyst.JavaTypeInference$.inferDataType(JavaTypeInference.scala:55)
> at org.apache.spark.sql.SparkSession.getSchema(SparkSession.scala:708)
> at
> org.apache.spark.sql.SparkSession.createDataFrame(SparkSession.scala:347)
> at uk.co.gresearch.aggregator.Main$.main(Main.scala:46)
> at uk.co.gresearch.aggregator.Main.main(Main.scala)
> {code}
--
This message was sent by Atlassian JIRA
(v6.3.15#6346)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
