[
https://issues.apache.org/jira/browse/SPARK-19980?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Michel Lemay updated SPARK-19980:
---------------------------------
Description:
Applying an identity map transformation on a statically typed Dataset with a
POJO produces an unexpected result.
Given POJOs:
{code}
public class Stuff implements Serializable {
private String name;
public void setName(String name) { this.name = name; }
public String getName() { return name; }
}
public class Outer implements Serializable {
private String name;
private Stuff stuff;
public void setName(String name) { this.name = name; }
public String getName() { return name; }
public void setStuff(Stuff stuff) { this.stuff = stuff; }
public Stuff getStuff() { return stuff; }
}
{code}
Produces the result:
{code}
scala> val encoder = Encoders.bean(classOf[Outer])
encoder: org.apache.spark.sql.Encoder[pojos.Outer] = class[name[0]: string,
stuff[0]: struct<name:string>]
scala> val schema = encoder.schema
schema: org.apache.spark.sql.types.StructType =
StructType(StructField(name,StringType,true),
StructField(stuff,StructType(StructField(name,StringType,true)),true))
scala> schema.printTreeString
root
|-- name: string (nullable = true)
|-- stuff: struct (nullable = true)
| |-- name: string (nullable = true)
scala> val df = spark.read.schema(schema).json("stuff.json").as[Outer](encoder)
df: org.apache.spark.sql.Dataset[pojos.Outer] = [name: string, stuff:
struct<name: string>]
scala> df.show()
+----+-----+
|name|stuff|
+----+-----+
| v1| null|
+----+-----+
scala> df.map(x => x)(encoder).show()
+----+------+
|name| stuff|
+----+------+
| v1|[null]|
+----+------+
{code}
After identity transformation, `stuff` becomes an object with null values
inside it instead of staying null itself.
Doing the same with case classes preserves the nulls:
{code}
scala> case class ScalaStuff(name: String)
defined class ScalaStuff
scala> case class ScalaOuter(name: String, stuff: ScalaStuff)
defined class ScalaOuter
scala> val encoder2 = Encoders.product[ScalaOuter]
encoder2: org.apache.spark.sql.Encoder[ScalaOuter] = class[name[0]: string,
stuff[0]: struct<name:string>]
scala> val schema2 = encoder2.schema
schema2: org.apache.spark.sql.types.StructType =
StructType(StructField(name,StringType,true),
StructField(stuff,StructType(StructField(name,StringType,true)),true))
scala> schema2.printTreeString
root
|-- name: string (nullable = true)
|-- stuff: struct (nullable = true)
| |-- name: string (nullable = true)
scala>
scala> val df2 = spark.read.schema(schema2).json("stuff.json").as[ScalaOuter]
df2: org.apache.spark.sql.Dataset[ScalaOuter] = [name: string, stuff:
struct<name: string>]
scala> df2.show()
+----+-----+
|name|stuff|
+----+-----+
| v1| null|
+----+-----+
scala> df2.map(x => x).show()
+----+-----+
|name|stuff|
+----+-----+
| v1| null|
+----+-----+
{code}
stuff.json:
{code}
{"name":"v1", "stuff":null }
{code}
was:
Applying an identity map transformation on a statically typed Dataset with a
POJO produces an unexpected result.
Given POJOs:
{code}
public class Stuff implements Serializable {
private String name;
public void setName(String name) { this.name = name; }
public String getName() { return name; }
}
public class Outer implements Serializable {
private String name;
private Stuff stuff;
public void setName(String name) { this.name = name; }
public String getName() { return name; }
public void setStuff(Stuff stuff) { this.stuff = stuff; }
public Stuff getStuff() { return stuff; }
}
{code}
And test code:
{code}
val encoder = Encoders.bean(classOf[Outer])
val schema = encoder.schema
schema.printTreeString
val df = spark.read.schema(schema).json("stuff.json").as[Outer](encoder)
df.show()
df.map(x => x)(encoder).show()
{code}
Produces the result:
{code}
scala> val encoder = Encoders.bean(classOf[Outer])
encoder: org.apache.spark.sql.Encoder[pojos.Outer] = class[name[0]: string,
stuff[0]: struct<name:string>]
scala> val schema = encoder.schema
schema: org.apache.spark.sql.types.StructType =
StructType(StructField(name,StringType,true),
StructField(stuff,StructType(StructField(name,StringType,true)),true))
scala> schema.printTreeString
root
|-- name: string (nullable = true)
|-- stuff: struct (nullable = true)
| |-- name: string (nullable = true)
scala> val df = spark.read.schema(schema).json("stuff.json").as[Outer](encoder)
df: org.apache.spark.sql.Dataset[pojos.Outer] = [name: string, stuff:
struct<name: string>]
scala> df.show()
+----+-----+
|name|stuff|
+----+-----+
| v1| null|
+----+-----+
scala> df.map(x => x)(encoder).show()
+----+------+
|name| stuff|
+----+------+
| v1|[null]|
+----+------+
{code}
After identity transformation, `stuff` becomes an object with null values
inside it instead of staying null itself.
Doing the same with case classes preserves the nulls:
{code}
scala> case class ScalaStuff(name: String)
defined class ScalaStuff
scala> case class ScalaOuter(name: String, stuff: ScalaStuff)
defined class ScalaOuter
scala> val encoder2 = Encoders.product[ScalaOuter]
encoder2: org.apache.spark.sql.Encoder[ScalaOuter] = class[name[0]: string,
stuff[0]: struct<name:string>]
scala> val schema2 = encoder2.schema
schema2: org.apache.spark.sql.types.StructType =
StructType(StructField(name,StringType,true),
StructField(stuff,StructType(StructField(name,StringType,true)),true))
scala> schema2.printTreeString
root
|-- name: string (nullable = true)
|-- stuff: struct (nullable = true)
| |-- name: string (nullable = true)
scala>
scala> val df2 = spark.read.schema(schema2).json("stuff.json").as[ScalaOuter]
df2: org.apache.spark.sql.Dataset[ScalaOuter] = [name: string, stuff:
struct<name: string>]
scala> df2.show()
+----+-----+
|name|stuff|
+----+-----+
| v1| null|
+----+-----+
scala> df2.map(x => x).show()
+----+-----+
|name|stuff|
+----+-----+
| v1| null|
+----+-----+
{code}
stuff.json:
{code}
{"name":"v1", "stuff":null }
{code}
> Basic Dataset transformation on POJOs does not preserves nulls.
> ---------------------------------------------------------------
>
> Key: SPARK-19980
> URL: https://issues.apache.org/jira/browse/SPARK-19980
> Project: Spark
> Issue Type: Bug
> Components: SQL
> Affects Versions: 2.1.0
> Reporter: Michel Lemay
>
> Applying an identity map transformation on a statically typed Dataset with a
> POJO produces an unexpected result.
> Given POJOs:
> {code}
> public class Stuff implements Serializable {
> private String name;
> public void setName(String name) { this.name = name; }
> public String getName() { return name; }
> }
> public class Outer implements Serializable {
> private String name;
> private Stuff stuff;
> public void setName(String name) { this.name = name; }
> public String getName() { return name; }
> public void setStuff(Stuff stuff) { this.stuff = stuff; }
> public Stuff getStuff() { return stuff; }
> }
> {code}
> Produces the result:
> {code}
> scala> val encoder = Encoders.bean(classOf[Outer])
> encoder: org.apache.spark.sql.Encoder[pojos.Outer] = class[name[0]: string,
> stuff[0]: struct<name:string>]
> scala> val schema = encoder.schema
> schema: org.apache.spark.sql.types.StructType =
> StructType(StructField(name,StringType,true),
> StructField(stuff,StructType(StructField(name,StringType,true)),true))
> scala> schema.printTreeString
> root
> |-- name: string (nullable = true)
> |-- stuff: struct (nullable = true)
> | |-- name: string (nullable = true)
> scala> val df =
> spark.read.schema(schema).json("stuff.json").as[Outer](encoder)
> df: org.apache.spark.sql.Dataset[pojos.Outer] = [name: string, stuff:
> struct<name: string>]
> scala> df.show()
> +----+-----+
> |name|stuff|
> +----+-----+
> | v1| null|
> +----+-----+
> scala> df.map(x => x)(encoder).show()
> +----+------+
> |name| stuff|
> +----+------+
> | v1|[null]|
> +----+------+
> {code}
> After identity transformation, `stuff` becomes an object with null values
> inside it instead of staying null itself.
> Doing the same with case classes preserves the nulls:
> {code}
> scala> case class ScalaStuff(name: String)
> defined class ScalaStuff
> scala> case class ScalaOuter(name: String, stuff: ScalaStuff)
> defined class ScalaOuter
> scala> val encoder2 = Encoders.product[ScalaOuter]
> encoder2: org.apache.spark.sql.Encoder[ScalaOuter] = class[name[0]: string,
> stuff[0]: struct<name:string>]
> scala> val schema2 = encoder2.schema
> schema2: org.apache.spark.sql.types.StructType =
> StructType(StructField(name,StringType,true),
> StructField(stuff,StructType(StructField(name,StringType,true)),true))
> scala> schema2.printTreeString
> root
> |-- name: string (nullable = true)
> |-- stuff: struct (nullable = true)
> | |-- name: string (nullable = true)
> scala>
> scala> val df2 = spark.read.schema(schema2).json("stuff.json").as[ScalaOuter]
> df2: org.apache.spark.sql.Dataset[ScalaOuter] = [name: string, stuff:
> struct<name: string>]
> scala> df2.show()
> +----+-----+
> |name|stuff|
> +----+-----+
> | v1| null|
> +----+-----+
> scala> df2.map(x => x).show()
> +----+-----+
> |name|stuff|
> +----+-----+
> | v1| null|
> +----+-----+
> {code}
> stuff.json:
> {code}
> {"name":"v1", "stuff":null }
> {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
