You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@spark.apache.org by ma...@apache.org on 2014/11/21 01:51:01 UTC
spark git commit: [SPARK-4244] [SQL] Support Hive Generic UDFs with
constant object inspector parameters
Repository: spark
Updated Branches:
refs/heads/master d39f2e9c6 -> 84d79ee9e
[SPARK-4244] [SQL] Support Hive Generic UDFs with constant object inspector parameters
Query `SELECT named_struct(lower("AA"), "12", lower("Bb"), "13") FROM src LIMIT 1` will throw exception, some of the Hive Generic UDF/UDAF requires the input object inspector is `ConstantObjectInspector`, however, we won't get that before the expression optimization executed. (Constant Folding).
This PR is a work around to fix this. (As ideally, the `output` of LogicalPlan should be identical before and after Optimization).
Author: Cheng Hao <ha...@intel.com>
Closes #3109 from chenghao-intel/optimized and squashes the following commits:
487ff79 [Cheng Hao] rebase to the latest master & update the unittest
Project: http://git-wip-us.apache.org/repos/asf/spark/repo
Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/84d79ee9
Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/84d79ee9
Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/84d79ee9
Branch: refs/heads/master
Commit: 84d79ee9ec47465269f7b0a7971176da93c96f3f
Parents: d39f2e9
Author: Cheng Hao <ha...@intel.com>
Authored: Thu Nov 20 16:50:59 2014 -0800
Committer: Michael Armbrust <mi...@databricks.com>
Committed: Thu Nov 20 16:50:59 2014 -0800
----------------------------------------------------------------------
.../org/apache/spark/sql/hive/HiveInspectors.scala | 2 ++
.../scala/org/apache/spark/sql/hive/hiveUdfs.scala | 14 ++++++--------
...for generic udf-0-cc120a2331158f570a073599985d3f55 | 1 +
.../spark/sql/hive/execution/HiveQuerySuite.scala | 8 ++++++++
4 files changed, 17 insertions(+), 8 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/spark/blob/84d79ee9/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveInspectors.scala
----------------------------------------------------------------------
diff --git a/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveInspectors.scala b/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveInspectors.scala
index ada980a..0eeac86 100644
--- a/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveInspectors.scala
+++ b/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveInspectors.scala
@@ -326,6 +326,8 @@ private[hive] trait HiveInspectors {
})
ObjectInspectorFactory.getStandardConstantMapObjectInspector(keyOI, valueOI, map)
}
+ case Literal(_, dt) => sys.error(s"Hive doesn't support the constant type [$dt].")
+ case _ if expr.foldable => toInspector(Literal(expr.eval(), expr.dataType))
case _ => toInspector(expr.dataType)
}
http://git-wip-us.apache.org/repos/asf/spark/blob/84d79ee9/sql/hive/src/main/scala/org/apache/spark/sql/hive/hiveUdfs.scala
----------------------------------------------------------------------
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 86f7eea..b255a2e 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
@@ -21,7 +21,7 @@ import org.apache.hadoop.hive.ql.udf.generic.GenericUDFUtils.ConversionHelper
import scala.collection.mutable.ArrayBuffer
-import org.apache.hadoop.hive.serde2.objectinspector.ObjectInspector
+import org.apache.hadoop.hive.serde2.objectinspector.{ObjectInspector, ConstantObjectInspector}
import org.apache.hadoop.hive.serde2.objectinspector.ObjectInspectorFactory.ObjectInspectorOptions
import org.apache.hadoop.hive.serde2.objectinspector.ObjectInspectorFactory
import org.apache.hadoop.hive.ql.exec.{UDF, UDAF}
@@ -108,9 +108,7 @@ private[hive] case class HiveSimpleUdf(functionClassName: String, children: Seq[
udfType != null && udfType.deterministic()
}
- override def foldable = {
- isUDFDeterministic && children.foldLeft(true)((prev, n) => prev && n.foldable)
- }
+ override def foldable = isUDFDeterministic && children.forall(_.foldable)
// Create parameter converters
@transient
@@ -154,7 +152,8 @@ private[hive] case class HiveGenericUdf(functionClassName: String, children: Seq
protected lazy val argumentInspectors = children.map(toInspector)
@transient
- protected lazy val returnInspector = function.initialize(argumentInspectors.toArray)
+ protected lazy val returnInspector =
+ function.initializeAndFoldConstants(argumentInspectors.toArray)
@transient
protected lazy val isUDFDeterministic = {
@@ -162,9 +161,8 @@ private[hive] case class HiveGenericUdf(functionClassName: String, children: Seq
(udfType != null && udfType.deterministic())
}
- override def foldable = {
- isUDFDeterministic && children.foldLeft(true)((prev, n) => prev && n.foldable)
- }
+ override def foldable =
+ isUDFDeterministic && returnInspector.isInstanceOf[ConstantObjectInspector]
@transient
protected lazy val deferedObjects =
http://git-wip-us.apache.org/repos/asf/spark/blob/84d79ee9/sql/hive/src/test/resources/golden/constant object inspector for generic udf-0-cc120a2331158f570a073599985d3f55
----------------------------------------------------------------------
diff --git a/sql/hive/src/test/resources/golden/constant object inspector for generic udf-0-cc120a2331158f570a073599985d3f55 b/sql/hive/src/test/resources/golden/constant object inspector for generic udf-0-cc120a2331158f570a073599985d3f55
new file mode 100644
index 0000000..7bc77e7
--- /dev/null
+++ b/sql/hive/src/test/resources/golden/constant object inspector for generic udf-0-cc120a2331158f570a073599985d3f55
@@ -0,0 +1 @@
+{"aa":"10","aaaaaa":"11","aaaaaa":"12","bb12":"13","s14s14":"14"}
http://git-wip-us.apache.org/repos/asf/spark/blob/84d79ee9/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveQuerySuite.scala
----------------------------------------------------------------------
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 0dd766f..af45dfd 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
@@ -56,6 +56,14 @@ class HiveQuerySuite extends HiveComparisonTest with BeforeAndAfter {
Locale.setDefault(originalLocale)
}
+ createQueryTest("constant object inspector for generic udf",
+ """SELECT named_struct(
+ lower("AA"), "10",
+ repeat(lower("AA"), 3), "11",
+ lower(repeat("AA", 3)), "12",
+ printf("Bb%d", 12), "13",
+ repeat(printf("s%d", 14), 2), "14") FROM src LIMIT 1""")
+
createQueryTest("NaN to Decimal",
"SELECT CAST(CAST('NaN' AS DOUBLE) AS DECIMAL(1,1)) FROM src LIMIT 1")
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@spark.apache.org
For additional commands, e-mail: commits-help@spark.apache.org