[
https://issues.apache.org/jira/browse/SPARK-15192?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Cheng Lian updated SPARK-15192:
-------------------------------
Description:
When we create a Dataset from an RDD of rows with a specific schema, if the
nullability of a value does not match the nullability defined in the schema, we
will throw an exception that is not easy to understand.
It will be good to verify the nullability in a more explicit way.
{code}
import org.apache.spark.sql.types._
import org.apache.spark.sql.Row
val schema = new StructType().add("a", StringType, false).add("b", StringType,
false)
val rdd = sc.parallelize(Row(null, "123") :: Row("234", null) :: Nil)
spark.createDataFrame(rdd, schema).show
{code}
{noformat}
java.lang.RuntimeException: Error while decoding: java.lang.NullPointerException
createexternalrow(if (isnull(input[0, string])) null else input[0,
string].toString, if (isnull(input[1, string])) null else input[1,
string].toString, StructField(a,StringType,false),
StructField(b,StringType,false))
:- if (isnull(input[0, string])) null else input[0, string].toString
: :- isnull(input[0, string])
: : +- input[0, string]
: :- null
: +- input[0, string].toString
: +- input[0, string]
+- if (isnull(input[1, string])) null else input[1, string].toString
:- isnull(input[1, string])
: +- input[1, string]
:- null
+- input[1, string].toString
+- input[1, string]
at
org.apache.spark.sql.catalyst.encoders.ExpressionEncoder.fromRow(ExpressionEncoder.scala:244)
at
org.apache.spark.sql.Dataset$$anonfun$org$apache$spark$sql$Dataset$$execute$1$1$$anonfun$apply$13.apply(Dataset.scala:2119)
at
org.apache.spark.sql.Dataset$$anonfun$org$apache$spark$sql$Dataset$$execute$1$1$$anonfun$apply$13.apply(Dataset.scala:2119)
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.Dataset$$anonfun$org$apache$spark$sql$Dataset$$execute$1$1.apply(Dataset.scala:2119)
at
org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:57)
at org.apache.spark.sql.Dataset.withNewExecutionId(Dataset.scala:2407)
at
org.apache.spark.sql.Dataset.org$apache$spark$sql$Dataset$$execute$1(Dataset.scala:2118)
at
org.apache.spark.sql.Dataset.org$apache$spark$sql$Dataset$$collect(Dataset.scala:2125)
at org.apache.spark.sql.Dataset$$anonfun$head$1.apply(Dataset.scala:1859)
at org.apache.spark.sql.Dataset$$anonfun$head$1.apply(Dataset.scala:1858)
at org.apache.spark.sql.Dataset.withTypedCallback(Dataset.scala:2437)
at org.apache.spark.sql.Dataset.head(Dataset.scala:1858)
at org.apache.spark.sql.Dataset.take(Dataset.scala:2075)
at org.apache.spark.sql.Dataset.showString(Dataset.scala:239)
at org.apache.spark.sql.Dataset.show(Dataset.scala:530)
at org.apache.spark.sql.Dataset.show(Dataset.scala:490)
at org.apache.spark.sql.Dataset.show(Dataset.scala:499)
... 50 elided
Caused by: java.lang.NullPointerException
at
org.apache.spark.sql.catalyst.expressions.GeneratedClass$SpecificSafeProjection.apply(Unknown
Source)
at
org.apache.spark.sql.catalyst.encoders.ExpressionEncoder.fromRow(ExpressionEncoder.scala:241)
... 72 more
{noformat}
was:
When we create a Dataset from an RDD of rows with a specific schema, if the
nullability of a value does not match the nullability defined in the schema, we
will throw an exception that is not easy to understand.
It will be good to verify the nullability in a more explicit way.
{code}
import org.apache.spark.sql.types._
import org.apache.spark.sql.Row
val schema = new StructType().add("a", StringType, false).add("b", StringType,
false)
val rdd = sc.parallelize(Row(null, "123") :: Row("234", null) :: Nil)
spark.createDataFrame(rdd, schema).show
java.lang.RuntimeException: Error while decoding: java.lang.NullPointerException
createexternalrow(if (isnull(input[0, string])) null else input[0,
string].toString, if (isnull(input[1, string])) null else input[1,
string].toString, StructField(a,StringType,false),
StructField(b,StringType,false))
:- if (isnull(input[0, string])) null else input[0, string].toString
: :- isnull(input[0, string])
: : +- input[0, string]
: :- null
: +- input[0, string].toString
: +- input[0, string]
+- if (isnull(input[1, string])) null else input[1, string].toString
:- isnull(input[1, string])
: +- input[1, string]
:- null
+- input[1, string].toString
+- input[1, string]
at
org.apache.spark.sql.catalyst.encoders.ExpressionEncoder.fromRow(ExpressionEncoder.scala:244)
at
org.apache.spark.sql.Dataset$$anonfun$org$apache$spark$sql$Dataset$$execute$1$1$$anonfun$apply$13.apply(Dataset.scala:2119)
at
org.apache.spark.sql.Dataset$$anonfun$org$apache$spark$sql$Dataset$$execute$1$1$$anonfun$apply$13.apply(Dataset.scala:2119)
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.Dataset$$anonfun$org$apache$spark$sql$Dataset$$execute$1$1.apply(Dataset.scala:2119)
at
org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:57)
at org.apache.spark.sql.Dataset.withNewExecutionId(Dataset.scala:2407)
at
org.apache.spark.sql.Dataset.org$apache$spark$sql$Dataset$$execute$1(Dataset.scala:2118)
at
org.apache.spark.sql.Dataset.org$apache$spark$sql$Dataset$$collect(Dataset.scala:2125)
at org.apache.spark.sql.Dataset$$anonfun$head$1.apply(Dataset.scala:1859)
at org.apache.spark.sql.Dataset$$anonfun$head$1.apply(Dataset.scala:1858)
at org.apache.spark.sql.Dataset.withTypedCallback(Dataset.scala:2437)
at org.apache.spark.sql.Dataset.head(Dataset.scala:1858)
at org.apache.spark.sql.Dataset.take(Dataset.scala:2075)
at org.apache.spark.sql.Dataset.showString(Dataset.scala:239)
at org.apache.spark.sql.Dataset.show(Dataset.scala:530)
at org.apache.spark.sql.Dataset.show(Dataset.scala:490)
at org.apache.spark.sql.Dataset.show(Dataset.scala:499)
... 50 elided
Caused by: java.lang.NullPointerException
at
org.apache.spark.sql.catalyst.expressions.GeneratedClass$SpecificSafeProjection.apply(Unknown
Source)
at
org.apache.spark.sql.catalyst.encoders.ExpressionEncoder.fromRow(ExpressionEncoder.scala:241)
... 72 more
{code}
> RowEncoder needs to verify nullability in a more explicit way
> -------------------------------------------------------------
>
> Key: SPARK-15192
> URL: https://issues.apache.org/jira/browse/SPARK-15192
> Project: Spark
> Issue Type: Bug
> Components: SQL
> Reporter: Yin Huai
>
> When we create a Dataset from an RDD of rows with a specific schema, if the
> nullability of a value does not match the nullability defined in the schema,
> we will throw an exception that is not easy to understand.
> It will be good to verify the nullability in a more explicit way.
> {code}
> import org.apache.spark.sql.types._
> import org.apache.spark.sql.Row
> val schema = new StructType().add("a", StringType, false).add("b",
> StringType, false)
> val rdd = sc.parallelize(Row(null, "123") :: Row("234", null) :: Nil)
> spark.createDataFrame(rdd, schema).show
> {code}
> {noformat}
> java.lang.RuntimeException: Error while decoding:
> java.lang.NullPointerException
> createexternalrow(if (isnull(input[0, string])) null else input[0,
> string].toString, if (isnull(input[1, string])) null else input[1,
> string].toString, StructField(a,StringType,false),
> StructField(b,StringType,false))
> :- if (isnull(input[0, string])) null else input[0, string].toString
> : :- isnull(input[0, string])
> : : +- input[0, string]
> : :- null
> : +- input[0, string].toString
> : +- input[0, string]
> +- if (isnull(input[1, string])) null else input[1, string].toString
> :- isnull(input[1, string])
> : +- input[1, string]
> :- null
> +- input[1, string].toString
> +- input[1, string]
> at
> org.apache.spark.sql.catalyst.encoders.ExpressionEncoder.fromRow(ExpressionEncoder.scala:244)
> at
> org.apache.spark.sql.Dataset$$anonfun$org$apache$spark$sql$Dataset$$execute$1$1$$anonfun$apply$13.apply(Dataset.scala:2119)
> at
> org.apache.spark.sql.Dataset$$anonfun$org$apache$spark$sql$Dataset$$execute$1$1$$anonfun$apply$13.apply(Dataset.scala:2119)
> 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.Dataset$$anonfun$org$apache$spark$sql$Dataset$$execute$1$1.apply(Dataset.scala:2119)
> at
> org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:57)
> at org.apache.spark.sql.Dataset.withNewExecutionId(Dataset.scala:2407)
> at
> org.apache.spark.sql.Dataset.org$apache$spark$sql$Dataset$$execute$1(Dataset.scala:2118)
> at
> org.apache.spark.sql.Dataset.org$apache$spark$sql$Dataset$$collect(Dataset.scala:2125)
> at org.apache.spark.sql.Dataset$$anonfun$head$1.apply(Dataset.scala:1859)
> at org.apache.spark.sql.Dataset$$anonfun$head$1.apply(Dataset.scala:1858)
> at org.apache.spark.sql.Dataset.withTypedCallback(Dataset.scala:2437)
> at org.apache.spark.sql.Dataset.head(Dataset.scala:1858)
> at org.apache.spark.sql.Dataset.take(Dataset.scala:2075)
> at org.apache.spark.sql.Dataset.showString(Dataset.scala:239)
> at org.apache.spark.sql.Dataset.show(Dataset.scala:530)
> at org.apache.spark.sql.Dataset.show(Dataset.scala:490)
> at org.apache.spark.sql.Dataset.show(Dataset.scala:499)
> ... 50 elided
> Caused by: java.lang.NullPointerException
> at
> org.apache.spark.sql.catalyst.expressions.GeneratedClass$SpecificSafeProjection.apply(Unknown
> Source)
> at
> org.apache.spark.sql.catalyst.encoders.ExpressionEncoder.fromRow(ExpressionEncoder.scala:241)
> ... 72 more
> {noformat}
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
