[
https://issues.apache.org/jira/browse/SPARK-20866?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16024350#comment-16024350
]
Takeshi Yamamuro commented on SPARK-20866:
------------------------------------------
SPARK-18284 [~kiszk] fixed also resolved this issue;
{code}
-- w/o the SPARK-18284 patch
scala> case class Test(a: Int)
defined class Test
scala> val ds1 = (Test(10) :: Nil).toDS
ds1: org.apache.spark.sql.Dataset[Test] = [a: int]
scala> val ds2 = ds1.map(x => Test(x.a))
ds2: org.apache.spark.sql.Dataset[Test] = [a: int]
scala> ds1.schema == ds2.schema
res0: Boolean = false
scala> ds1.schema
res1: org.apache.spark.sql.types.StructType =
StructType(StructField(a,IntegerType,false))
scala> ds2.schema
res2: org.apache.spark.sql.types.StructType =
StructType(StructField(a,IntegerType,true))
-- w/ the SPARK-18284 patch
scala> case class Test(a: Int)
defined class Test
scala> val ds1 = (Test(10) :: Nil).toDS
ds1: org.apache.spark.sql.Dataset[Test] = [a: int]
scala> val ds2 = ds1.map(x => Test(x.a))
ds2: org.apache.spark.sql.Dataset[Test] = [a: int]
scala> ds1.schema == ds2.schema
res0: Boolean = true
scala> ds1.schema
res1: org.apache.spark.sql.types.StructType =
StructType(StructField(a,IntegerType,false))
scala> ds2.schema
res2: org.apache.spark.sql.types.StructType =
StructType(StructField(a,IntegerType,false))
{code}
> Dataset map does not respect nullable field
> --------------------------------------------
>
> Key: SPARK-20866
> URL: https://issues.apache.org/jira/browse/SPARK-20866
> Project: Spark
> Issue Type: Bug
> Components: SQL
> Affects Versions: 2.1.0
> Reporter: Colin Breame
>
> The Dataset.map does not respect the nullable fields within the schema.
> *Test code:*
> (run on spark-shell 2.1.0):
> {code}
> scala> case class Test(a: Int)
> defined class Test
> scala> val ds1 = (Test(10) :: Nil).toDS
> ds1: org.apache.spark.sql.Dataset[Test] = [a: int]
> scala> val ds2 = ds1.map(x => Test(x.a))
> ds2: org.apache.spark.sql.Dataset[Test] = [a: int]
> scala> ds1.schema == ds2.schema
> res65: Boolean = false
> scala> ds1.schema
> res62: org.apache.spark.sql.types.StructType =
> StructType(StructField(a,IntegerType,false))
> scala> ds2.schema
> res63: org.apache.spark.sql.types.StructType =
> StructType(StructField(a,IntegerType,true))
> {code}
> *Expected*
> The ds1 should equal ds2. i.e. the schema should be the same.
> *Actual*
> The schema is not equal - the StructField nullable property is true in ds2
> and false in ds1.
--
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
