diff options
author | Cheng Hao <hao.cheng@intel.com> | 2014-09-19 15:29:22 -0700 |
---|---|---|
committer | Michael Armbrust <michael@databricks.com> | 2014-09-19 15:29:22 -0700 |
commit | 2c3cc7641d86fa5196406955325a042890f77563 (patch) | |
tree | 74abb137ac7aaf9736956a42fee1a521db171cbc /sql/hive | |
parent | fce5e251d636c788cda91345867e0294280c074d (diff) | |
download | spark-2c3cc7641d86fa5196406955325a042890f77563.tar.gz spark-2c3cc7641d86fa5196406955325a042890f77563.tar.bz2 spark-2c3cc7641d86fa5196406955325a042890f77563.zip |
[SPARK-3501] [SQL] Fix the bug of Hive SimpleUDF creates unnecessary type cast
When do the query like:
```
select datediff(cast(value as timestamp), cast('2002-03-21 00:00:00' as timestamp)) from src;
```
SparkSQL will raise exception:
```
[info] scala.MatchError: TimestampType (of class org.apache.spark.sql.catalyst.types.TimestampType$)
[info] at org.apache.spark.sql.catalyst.expressions.Cast.castToTimestamp(Cast.scala:77)
[info] at org.apache.spark.sql.catalyst.expressions.Cast.cast$lzycompute(Cast.scala:251)
[info] at org.apache.spark.sql.catalyst.expressions.Cast.cast(Cast.scala:247)
[info] at org.apache.spark.sql.catalyst.expressions.Cast.eval(Cast.scala:263)
[info] at org.apache.spark.sql.catalyst.optimizer.ConstantFolding$$anonfun$apply$5$$anonfun$applyOrElse$2.applyOrElse(Optimizer.scala:217)
[info] at org.apache.spark.sql.catalyst.optimizer.ConstantFolding$$anonfun$apply$5$$anonfun$applyOrElse$2.applyOrElse(Optimizer.scala:210)
[info] at org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:144)
[info] at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$4$$anonfun$apply$2.apply(TreeNode.scala:180)
[info] at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244)
[info] at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244)
```
Author: Cheng Hao <hao.cheng@intel.com>
Closes #2368 from chenghao-intel/cast_exception and squashes the following commits:
5c9c3a5 [Cheng Hao] make more clear code
49dfc50 [Cheng Hao] Add no-op for Cast and revert the position of SimplifyCasts
b804abd [Cheng Hao] Add unit test to show the failure in identical data type casting
330a5c8 [Cheng Hao] Update Code based on comments
b834ed4 [Cheng Hao] Fix bug of HiveSimpleUDF with unnecessary type cast which cause exception in constant folding
Diffstat (limited to 'sql/hive')
3 files changed, 13 insertions, 2 deletions
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 7d1ad53d8b..7cda0dd302 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 @@ -51,12 +51,13 @@ private[hive] abstract class HiveFunctionRegistry val function = functionInfo.getFunctionClass.newInstance().asInstanceOf[UDF] val method = function.getResolver.getEvalMethod(children.map(_.dataType.toTypeInfo)) - lazy val expectedDataTypes = method.getParameterTypes.map(javaClassToDataType) + val expectedDataTypes = method.getParameterTypes.map(javaClassToDataType) HiveSimpleUdf( functionClassName, children.zip(expectedDataTypes).map { case (e, NullType) => e + case (e, t) if (e.dataType == t) => e case (e, t) => Cast(e, t) } ) diff --git a/sql/hive/src/test/resources/golden/Cast Timestamp to Timestamp in UDF-0-66952a3949d7544716fd1a675498b1fa b/sql/hive/src/test/resources/golden/Cast Timestamp to Timestamp in UDF-0-66952a3949d7544716fd1a675498b1fa new file mode 100644 index 0000000000..7951defec1 --- /dev/null +++ b/sql/hive/src/test/resources/golden/Cast Timestamp to Timestamp in UDF-0-66952a3949d7544716fd1a675498b1fa @@ -0,0 +1 @@ +NULL diff --git a/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveQuerySuite.scala b/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveQuerySuite.scala index 8c8a8b124a..56bcd95eab 100644 --- a/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveQuerySuite.scala +++ b/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveQuerySuite.scala @@ -142,16 +142,25 @@ class HiveQuerySuite extends HiveComparisonTest { setConf("spark.sql.dialect", "sql") assert(sql("SELECT 1").collect() === Array(Seq(1))) setConf("spark.sql.dialect", "hiveql") - } test("Query expressed in HiveQL") { sql("FROM src SELECT key").collect() } + test("Query with constant folding the CAST") { + sql("SELECT CAST(CAST('123' AS binary) AS binary) FROM src LIMIT 1").collect() + } + createQueryTest("Constant Folding Optimization for AVG_SUM_COUNT", "SELECT AVG(0), SUM(0), COUNT(null), COUNT(value) FROM src GROUP BY key") + createQueryTest("Cast Timestamp to Timestamp in UDF", + """ + | SELECT DATEDIFF(CAST(value AS timestamp), CAST('2002-03-21 00:00:00' AS timestamp)) + | FROM src LIMIT 1 + """.stripMargin) + createQueryTest("Simple Average", "SELECT AVG(key) FROM src") |