From 6325a2f82a95a63bee020122620bc4f5fd25d059 Mon Sep 17 00:00:00 2001
From: Takeshi Yamamuro <yamamuro@apache.org>
Date: Tue, 14 Mar 2017 18:51:05 +0100
Subject: [PATCH] [SPARK-19923][SQL] Remove unnecessary type conversions per
call in Hive
## What changes were proposed in this pull request?
This pr removed unnecessary type conversions per call in Hive: https://github.com/apache/spark/blob/master/sql/hive/src/main/scala/org/apache/spark/sql/hive/hiveUDFs.scala#L116
## How was this patch tested?
Existing tests
Author: Takeshi Yamamuro <yamamuro@apache.org>
Closes #17264 from maropu/SPARK-19923.
---
.../scala/org/apache/spark/sql/hive/hiveUDFs.scala | 3 ++-
.../apache/spark/sql/hive/orc/OrcFileFormat.scala | 13 +++++++++----
2 files changed, 11 insertions(+), 5 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 506949cb68..51c814cf32 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
@@ -108,12 +108,13 @@ private[hive] case class HiveSimpleUDF(
private[hive] class DeferredObjectAdapter(oi: ObjectInspector, dataType: DataType)
extends DeferredObject with HiveInspectors {
+ private val wrapper = wrapperFor(oi, dataType)
private var func: () => Any = _
def set(func: () => Any): Unit = {
this.func = func
}
override def prepare(i: Int): Unit = {}
- override def get(): AnyRef = wrap(func(), oi, dataType)
+ override def get(): AnyRef = wrapper(func()).asInstanceOf[AnyRef]
}
private[hive] case class HiveGenericUDF(
diff --git a/sql/hive/src/main/scala/org/apache/spark/sql/hive/orc/OrcFileFormat.scala b/sql/hive/src/main/scala/org/apache/spark/sql/hive/orc/OrcFileFormat.scala
index f496c01ce9..3a34ec55c8 100644
--- a/sql/hive/src/main/scala/org/apache/spark/sql/hive/orc/OrcFileFormat.scala
+++ b/sql/hive/src/main/scala/org/apache/spark/sql/hive/orc/OrcFileFormat.scala
@@ -20,6 +20,8 @@ package org.apache.spark.sql.hive.orc
import java.net.URI
import java.util.Properties
+import scala.collection.JavaConverters._
+
import org.apache.hadoop.conf.Configuration
import org.apache.hadoop.fs.{FileStatus, Path}
import org.apache.hadoop.hive.conf.HiveConf.ConfVars
@@ -196,6 +198,11 @@ private[orc] class OrcSerializer(dataSchema: StructType, conf: Configuration)
private[this] val cachedOrcStruct = structOI.create().asInstanceOf[OrcStruct]
+ // Wrapper functions used to wrap Spark SQL input arguments into Hive specific format
+ private[this] val wrappers = dataSchema.zip(structOI.getAllStructFieldRefs().asScala.toSeq).map {
+ case (f, i) => wrapperFor(i.getFieldObjectInspector, f.dataType)
+ }
+
private[this] def wrapOrcStruct(
struct: OrcStruct,
oi: SettableStructObjectInspector,
@@ -208,10 +215,8 @@ private[orc] class OrcSerializer(dataSchema: StructType, conf: Configuration)
oi.setStructFieldData(
struct,
fieldRefs.get(i),
- wrap(
- row.get(i, dataSchema(i).dataType),
- fieldRefs.get(i).getFieldObjectInspector,
- dataSchema(i).dataType))
+ wrappers(i)(row.get(i, dataSchema(i).dataType))
+ )
i += 1
}
}
--
GitLab