Github user maropu commented on a diff in the pull request: https://github.com/apache/spark/pull/18300#discussion_r126273573 --- Diff: sql/core/src/test/scala/org/apache/spark/sql/DataFrameSuite.scala --- @@ -112,6 +112,91 @@ class DataFrameSuite extends QueryTest with SharedSQLContext { ) } + test("union by name") { + // Simple case + var df1 = Seq((1, 2, 3)).toDF("a", "b", "c") + var df2 = Seq((3, 1, 2)).toDF("c", "a", "b") + var df3 = Seq((2, 3, 1)).toDF("b", "c", "a") + val unionDf = df1.unionByName(df2.unionByName(df3)) + checkAnswer(unionDf, + Row(1, 2, 3) :: Row(1, 2, 3) :: Row(1, 2, 3) :: Nil + ) + + // Check if adjacent unions are combined into a single one + assert(unionDf.queryExecution.optimizedPlan.collect { case u: Union => true }.size == 1) + + // Check some type coercion + df1 = Seq((1, "a")).toDF("c0", "c1") + df2 = Seq((3, 1L)).toDF("c1", "c0") + checkAnswer(df1.unionByName(df2), Row(1L, "a") :: Row(1L, "3") :: Nil) + + df1 = Seq((1, 1.0)).toDF("c0", "c1") + df2 = Seq((8L, 3.0)).toDF("c1", "c0") + checkAnswer(df1.unionByName(df2), Row(1.0, 1.0) :: Row(3.0, 8.0) :: Nil) + + df1 = Seq((2.0f, 7.4)).toDF("c0", "c1") + df2 = Seq(("a", 4.0)).toDF("c1", "c0") + checkAnswer(df1.unionByName(df2), Row(2.0, "7.4") :: Row(4.0, "a") :: Nil) + + df1 = Seq((1, "a", 3.0)).toDF("c0", "c1", "c2") + df2 = Seq((1.2, 2, "bc")).toDF("c2", "c0", "c1") + df3 = Seq(("def", 1.2, 3)).toDF("c1", "c2", "c0") + checkAnswer(df1.unionByName(df2.unionByName(df3)), + Row(1, "a", 3.0) :: Row(2, "bc", 1.2) :: Row(3, "def", 1.2) :: Nil + ) + + // Failure cases --- End diff -- ok
--- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature enabled and wishes so, or if the feature is enabled but not working, please contact infrastructure at infrastruct...@apache.org or file a JIRA ticket with INFRA. --- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org