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 cba12050f [VL] Enable timestamp and binary type for HLL agg function
(#6619)
cba12050f is described below
commit cba12050f4b89fc9a4d09e7cf75486d74fd94465
Author: Zhen Li <[email protected]>
AuthorDate: Mon Jul 29 14:23:23 2024 +0800
[VL] Enable timestamp and binary type for HLL agg function (#6619)
[VL] Enable timestamp and binary type for HLL agg function.
---
.../scala/org/apache/gluten/extension/HLLRewriteRule.scala | 2 +-
.../gluten/execution/VeloxAggregateFunctionsSuite.scala | 14 ++++++++++++++
2 files changed, 15 insertions(+), 1 deletion(-)
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 7bae64ff8..2b17cbfd6 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
@@ -58,7 +58,7 @@ case class HLLRewriteRule(spark: SparkSession) extends
Rule[LogicalPlan] {
// be parsed by velox, it would cause the error: 'Unexpected type of HLL'.
dataType match {
case BooleanType | ByteType | ShortType | IntegerType | LongType |
FloatType | DoubleType |
- StringType | _: CharType | _: DecimalType | DateType =>
+ StringType | _: CharType | _: DecimalType | DateType | TimestampType
| BinaryType =>
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 992106d13..270334011 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
@@ -26,6 +26,8 @@ import org.apache.spark.sql.functions._
import org.apache.spark.sql.internal.SQLConf
import org.apache.spark.sql.types._
+import java.sql.Timestamp
+
abstract class VeloxAggregateFunctionsSuite extends
VeloxWholeStageTransformerSuite {
protected val rootPath: String = getClass.getResource("/").getPath
@@ -565,6 +567,18 @@ abstract class VeloxAggregateFunctionsSuite extends
VeloxWholeStageTransformerSu
"select approx_count_distinct(l_discount), count(distinct l_orderkey)
from lineitem") {
checkGlutenOperatorMatch[HashAggregateExecTransformer]
}
+ withTempPath {
+ path =>
+ val t1 = Timestamp.valueOf("2024-08-22 10:10:10.010")
+ val t2 = Timestamp.valueOf("2014-12-31 00:00:00.012")
+ val t3 = Timestamp.valueOf("1968-12-31 23:59:59.001")
+ Seq(t1, t2, t3).toDF("t").write.parquet(path.getCanonicalPath)
+
+
spark.read.parquet(path.getCanonicalPath).createOrReplaceTempView("view")
+ runQueryAndCompare("select approx_count_distinct(t) from view") {
+ checkGlutenOperatorMatch[HashAggregateExecTransformer]
+ }
+ }
}
test("max_by") {
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
