This is an automated email from the ASF dual-hosted git repository.
dongjoon pushed a commit to branch branch-3.0
in repository https://gitbox.apache.org/repos/asf/spark.git
The following commit(s) were added to refs/heads/branch-3.0 by this push:
new 4b84e57 [SPARK-32877][SQL][TEST] Add test for Hive UDF complex decimal type
4b84e57 is described below
commit 4b84e571f06dec953d532e60942b0e96b4100abe
Author: ulysses <yo...@weidian.com>
AuthorDate: Thu Sep 24 22:16:05 2020 -0700
[SPARK-32877][SQL][TEST] Add test for Hive UDF complex decimal type
### What changes were proposed in this pull request?
Add test to cover Hive UDF whose input contains complex decimal type.
Add comment to explain why we can't make `HiveSimpleUDF` extend `ImplicitTypeCasts`.
### Why are the changes needed?
For better test coverage with Hive which we compatible or not.
### Does this PR introduce _any_ user-facing change?
No.
### How was this patch tested?
Add test.
Closes #29863 from ulysses-you/SPARK-32877-test.
Authored-by: ulysses <yo...@weidian.com>
Signed-off-by: Dongjoon Hyun <dh...@apple.com>
(cherry picked from commit f2fc96667481169affbc20cec95b9fc1c19fc7c3)
Signed-off-by: Dongjoon Hyun <dh...@apple.com>
---
.../scala/org/apache/spark/sql/hive/hiveUDFs.scala | 5 ++++
.../spark/sql/hive/execution/HiveUDFSuite.scala | 31 ++++++++++++++++++++++
2 files changed, 36 insertions(+)
diff --git a/sql/hive/src/main/scala/org/apache/spark/sql/hive/hiveUDFs.scala b/sql/hive/src/main/scala/org/apache/spark/sql/hive/hiveUDFs.scala
index 05d608a..3117781 100644
--- a/sql/hive/src/main/scala/org/apache/spark/sql/hive/hiveUDFs.scala
+++ b/sql/hive/src/main/scala/org/apache/spark/sql/hive/hiveUDFs.scala
@@ -41,6 +41,11 @@ import org.apache.spark.sql.hive.HiveShim._
import org.apache.spark.sql.types._
import org.apache.spark.util.Utils
+/**
+ * Here we cannot extends `ImplicitTypeCasts` to compatible with UDF input data type, the reason is:
+ * we use children data type to reflect UDF method first and will get exception if it fails so that
+ * we can never go into `ImplicitTypeCasts`.
+ */
private[hive] case class HiveSimpleUDF(
name: String, funcWrapper: HiveFunctionWrapper, children: Seq[Expression])
extends Expression
diff --git a/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveUDFSuite.scala b/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveUDFSuite.scala
index 7bca2af..d3c8428 100644
--- a/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveUDFSuite.scala
+++ b/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveUDFSuite.scala
@@ -34,6 +34,7 @@ import org.apache.spark.sql.{AnalysisException, QueryTest, Row}
import org.apache.spark.sql.catalyst.plans.logical.Project
import org.apache.spark.sql.execution.command.FunctionsCommand
import org.apache.spark.sql.functions.max
+import org.apache.spark.sql.hive.HiveUtils
import org.apache.spark.sql.hive.test.TestHiveSingleton
import org.apache.spark.sql.internal.SQLConf
import org.apache.spark.sql.test.SQLTestUtils
@@ -658,6 +659,25 @@ class HiveUDFSuite extends QueryTest with TestHiveSingleton with SQLTestUtils {
}
}
+ test("SPARK-32877: add test for Hive UDF complex decimal type") {
+ assume(HiveUtils.isHive23)
+ withUserDefinedFunction("testArraySum" -> false) {
+ sql(s"CREATE FUNCTION testArraySum AS '${classOf[ArraySumUDF].getName}'")
+ checkAnswer(
+ sql("SELECT testArraySum(array(1, 1.1, 1.2))"),
+ Seq(Row(3.3)))
+
+ val msg = intercept[AnalysisException] {
+ sql("SELECT testArraySum(1)")
+ }.getMessage
+ assert(msg.contains(s"No handler for UDF/UDAF/UDTF '${classOf[ArraySumUDF].getName}'"))
+
+ val msg2 = intercept[AnalysisException] {
+ sql("SELECT testArraySum(1, 2)")
+ }.getMessage
+ assert(msg2.contains(s"No handler for UDF/UDAF/UDTF '${classOf[ArraySumUDF].getName}'"))
+ }
+ }
}
class TestPair(x: Int, y: Int) extends Writable with Serializable {
@@ -741,3 +761,14 @@ class StatelessUDF extends UDF {
result
}
}
+
+class ArraySumUDF extends UDF {
+ import scala.collection.JavaConverters._
+ def evaluate(values: java.util.List[java.lang.Double]): java.lang.Double = {
+ var r = 0d
+ for (v <- values.asScala) {
+ r += v
+ }
+ r
+ }
+}
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@spark.apache.org
For additional commands, e-mail: commits-help@spark.apache.org