diff options
| author | ravipesala <ravindra.pesala@huawei.com> | 2014-12-01 13:26:44 -0800 |
|---|---|---|
| committer | Michael Armbrust <michael@databricks.com> | 2014-12-01 13:28:04 -0800 |
| commit | 6a9ff19dc06745144d5b311d4f87073c81d53a8f (patch) | |
| tree | f6bcc0ddb1f51320ad1c3aeebb74aa2b1642249a /sql | |
| parent | b57365a1ec89e31470f424ff37d5ebc7c90a39d8 (diff) | |
| download | spark-6a9ff19dc06745144d5b311d4f87073c81d53a8f.tar.gz spark-6a9ff19dc06745144d5b311d4f87073c81d53a8f.tar.bz2 spark-6a9ff19dc06745144d5b311d4f87073c81d53a8f.zip | |
[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.pesala@huawei.com>
Author: Michael Armbrust <michael@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
Diffstat (limited to 'sql')
| -rwxr-xr-x | sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/SqlParser.scala | 3 | ||||
| -rw-r--r-- | sql/core/src/test/scala/org/apache/spark/sql/SQLQuerySuite.scala | 7 |
2 files changed, 9 insertions, 1 deletions
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 a9ff10f2d5..a2bcd73b60 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 <~ ")" ^^ 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 84ee3051eb..f83e647014 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) + } } |