Repository: spark Updated Branches: refs/heads/branch-1.2 f2bb90a29 -> 5006aab9d
[SPARK-4650][SQL] Supporting multi column support in countDistinct function like count(distinct c1,c2..) in Spark SQL Supporting multi column support in countDistinct function like count(distinct c1,c2..) in Spark SQL Author: ravipesala <ravindra.pes...@huawei.com> Author: Michael Armbrust <mich...@databricks.com> Closes #3511 from ravipesala/countdistinct and squashes the following commits: cc4dbb1 [ravipesala] style 070e12a [ravipesala] Supporting multi column support in count(distinct c1,c2..) in Spark SQL (cherry picked from commit 6a9ff19dc06745144d5b311d4f87073c81d53a8f) Signed-off-by: Michael Armbrust <mich...@databricks.com> Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/5006aab9 Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/5006aab9 Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/5006aab9 Branch: refs/heads/branch-1.2 Commit: 5006aab9d6f8dd4ce3dd11d388f96790c04cf25c Parents: f2bb90a Author: ravipesala <ravindra.pes...@huawei.com> Authored: Mon Dec 1 13:26:44 2014 -0800 Committer: Michael Armbrust <mich...@databricks.com> Committed: Mon Dec 1 13:29:35 2014 -0800 ---------------------------------------------------------------------- .../main/scala/org/apache/spark/sql/catalyst/SqlParser.scala | 3 ++- .../src/test/scala/org/apache/spark/sql/SQLQuerySuite.scala | 7 +++++++ 2 files changed, 9 insertions(+), 1 deletion(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/spark/blob/5006aab9/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/SqlParser.scala ---------------------------------------------------------------------- diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/SqlParser.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/SqlParser.scala index a9ff10f..a2bcd73 100755 --- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/SqlParser.scala +++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/SqlParser.scala @@ -277,7 +277,8 @@ class SqlParser extends AbstractSparkSQLParser { | SUM ~> "(" ~> DISTINCT ~> expression <~ ")" ^^ { case exp => SumDistinct(exp) } | COUNT ~ "(" ~> "*" <~ ")" ^^ { case _ => Count(Literal(1)) } | COUNT ~ "(" ~> expression <~ ")" ^^ { case exp => Count(exp) } - | COUNT ~> "(" ~> DISTINCT ~> expression <~ ")" ^^ { case exp => CountDistinct(exp :: Nil) } + | COUNT ~> "(" ~> DISTINCT ~> repsep(expression, ",") <~ ")" ^^ + { case exps => CountDistinct(exps) } | APPROXIMATE ~ COUNT ~ "(" ~ DISTINCT ~> expression <~ ")" ^^ { case exp => ApproxCountDistinct(exp) } | APPROXIMATE ~> "(" ~> floatLit ~ ")" ~ COUNT ~ "(" ~ DISTINCT ~ expression <~ ")" ^^ http://git-wip-us.apache.org/repos/asf/spark/blob/5006aab9/sql/core/src/test/scala/org/apache/spark/sql/SQLQuerySuite.scala ---------------------------------------------------------------------- diff --git a/sql/core/src/test/scala/org/apache/spark/sql/SQLQuerySuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/SQLQuerySuite.scala index 84ee305..f83e647 100644 --- a/sql/core/src/test/scala/org/apache/spark/sql/SQLQuerySuite.scala +++ b/sql/core/src/test/scala/org/apache/spark/sql/SQLQuerySuite.scala @@ -992,4 +992,11 @@ class SQLQuerySuite extends QueryTest with BeforeAndAfterAll { "nulldata2 on nulldata1.value <=> nulldata2.value"), (1 to 2).map(i => Seq(i))) } + + test("Multi-column COUNT(DISTINCT ...)") { + val data = TestData(1,"val_1") :: TestData(2,"val_2") :: Nil + val rdd = sparkContext.parallelize((0 to 1).map(i => data(i))) + rdd.registerTempTable("distinctData") + checkAnswer(sql("SELECT COUNT(DISTINCT key,value) FROM distinctData"), 2) + } } --------------------------------------------------------------------- To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org For additional commands, e-mail: commits-h...@spark.apache.org
