Repository: spark Updated Branches: refs/heads/branch-2.0 e69639f43 -> f52a95248
[SPARK-15597][SQL] Add SparkSession.emptyDataset ## What changes were proposed in this pull request? This patch adds a new function emptyDataset to SparkSession, for creating an empty dataset. ## How was this patch tested? Added a test case. Author: Reynold Xin <r...@databricks.com> Closes #13344 from rxin/SPARK-15597. (cherry picked from commit a52e6813392ba4bdb1b818694b7ced8f6caa6a2b) Signed-off-by: Andrew Or <and...@databricks.com> Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/f52a9524 Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/f52a9524 Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/f52a9524 Branch: refs/heads/branch-2.0 Commit: f52a9524865b8c56058a65b29a1aaacffb709f69 Parents: e69639f Author: Reynold Xin <r...@databricks.com> Authored: Fri May 27 11:13:09 2016 -0700 Committer: Andrew Or <and...@databricks.com> Committed: Fri May 27 11:13:17 2016 -0700 ---------------------------------------------------------------------- .../main/scala/org/apache/spark/sql/SparkSession.scala | 12 ++++++++++++ .../test/scala/org/apache/spark/sql/DatasetSuite.scala | 6 ++++++ 2 files changed, 18 insertions(+) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/spark/blob/f52a9524/sql/core/src/main/scala/org/apache/spark/sql/SparkSession.scala ---------------------------------------------------------------------- diff --git a/sql/core/src/main/scala/org/apache/spark/sql/SparkSession.scala b/sql/core/src/main/scala/org/apache/spark/sql/SparkSession.scala index aa60048..c9276cf 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/SparkSession.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/SparkSession.scala @@ -224,6 +224,18 @@ class SparkSession private( /** * :: Experimental :: + * Creates a new [[Dataset]] of type T containing zero elements. + * + * @return 2.0.0 + */ + @Experimental + def emptyDataset[T: Encoder]: Dataset[T] = { + val encoder = implicitly[Encoder[T]] + new Dataset(self, LocalRelation(encoder.schema.toAttributes), encoder) + } + + /** + * :: Experimental :: * Creates a [[DataFrame]] from an RDD of Product (e.g. case classes, tuples). * * @group dataframes http://git-wip-us.apache.org/repos/asf/spark/blob/f52a9524/sql/core/src/test/scala/org/apache/spark/sql/DatasetSuite.scala ---------------------------------------------------------------------- diff --git a/sql/core/src/test/scala/org/apache/spark/sql/DatasetSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/DatasetSuite.scala index 2a65916..e395007 100644 --- a/sql/core/src/test/scala/org/apache/spark/sql/DatasetSuite.scala +++ b/sql/core/src/test/scala/org/apache/spark/sql/DatasetSuite.scala @@ -46,6 +46,12 @@ class DatasetSuite extends QueryTest with SharedSQLContext { 1, 1, 1) } + test("emptyDataset") { + val ds = spark.emptyDataset[Int] + assert(ds.count() == 0L) + assert(ds.collect() sameElements Array.empty[Int]) + } + test("range") { assert(spark.range(10).map(_ + 1).reduce(_ + _) == 55) assert(spark.range(10).map{ case i: java.lang.Long => i + 1 }.reduce(_ + _) == 55) --------------------------------------------------------------------- To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org For additional commands, e-mail: commits-h...@spark.apache.org
