This is an automated email from the ASF dual-hosted git repository.
zhli pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/incubator-gluten.git
The following commit(s) were added to refs/heads/main by this push:
new efd6f31fb [VL] Support DecimalType for approx_count_distinct (#5868)
efd6f31fb is described below
commit efd6f31fb44ea21846c0292d5ea31a3e05aa3af3
Author: Joey <[email protected]>
AuthorDate: Mon May 27 20:44:36 2024 +0800
[VL] Support DecimalType for approx_count_distinct (#5868)
[VL] Support DecimalType for approx_count_distinct.
---
.../org/apache/gluten/extension/HLLRewriteRule.scala | 1 +
.../execution/VeloxAggregateFunctionsSuite.scala | 20 ++++++++++++++++++++
2 files changed, 21 insertions(+)
diff --git
a/backends-velox/src/main/scala/org/apache/gluten/extension/HLLRewriteRule.scala
b/backends-velox/src/main/scala/org/apache/gluten/extension/HLLRewriteRule.scala
index cb1e626a1..03819fc10 100644
---
a/backends-velox/src/main/scala/org/apache/gluten/extension/HLLRewriteRule.scala
+++
b/backends-velox/src/main/scala/org/apache/gluten/extension/HLLRewriteRule.scala
@@ -73,6 +73,7 @@ case class HLLRewriteRule(spark: SparkSession) extends
Rule[LogicalPlan] {
case LongType => true
case ShortType => true
case StringType => true
+ case _: DecimalType => true
case _ => false
}
}
diff --git
a/backends-velox/src/test/scala/org/apache/gluten/execution/VeloxAggregateFunctionsSuite.scala
b/backends-velox/src/test/scala/org/apache/gluten/execution/VeloxAggregateFunctionsSuite.scala
index faa361edf..ffed63731 100644
---
a/backends-velox/src/test/scala/org/apache/gluten/execution/VeloxAggregateFunctionsSuite.scala
+++
b/backends-velox/src/test/scala/org/apache/gluten/execution/VeloxAggregateFunctionsSuite.scala
@@ -571,6 +571,26 @@ abstract class VeloxAggregateFunctionsSuite extends
VeloxWholeStageTransformerSu
}
}
+ test("approx_count_distinct decimal") {
+ // The data type of l_discount is decimal.
+ runQueryAndCompare("""
+ |select approx_count_distinct(l_discount) from
lineitem;
+ |""".stripMargin) {
+ checkGlutenOperatorMatch[HashAggregateExecTransformer]
+ }
+ runQueryAndCompare(
+ "select approx_count_distinct(l_discount), count(distinct l_orderkey)
from lineitem") {
+ df =>
+ {
+ assert(
+ getExecutedPlan(df).count(
+ plan => {
+ plan.isInstanceOf[HashAggregateExecTransformer]
+ }) == 0)
+ }
+ }
+ }
+
test("max_by") {
runQueryAndCompare(s"""
|select max_by(l_linenumber, l_comment) from
lineitem;
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
