initial commit

kiszk · kiszk · commit 5143d35dfc25 · 2017-07-14T02:59:16.000+09:00
diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/objects/objects.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/objects/objects.scala
@@ -660,6 +660,12 @@ case class ExternalMapToCatalyst private(
     val entry = ctx.freshName("entry")
     val entries = ctx.freshName("entries")
 
+    val keyElementJavaType = ctx.javaType(keyType)
+    val valueElementJavaType = ctx.javaType(valueType)
+    ctx.addMutableState(keyElementJavaType, key, "")
+    ctx.addMutableState("boolean", valueIsNull, "")
+    ctx.addMutableState(valueElementJavaType, value, "")
+
     val (defineEntries, defineKeyValue) = child.dataType match {
       case ObjectType(cls) if classOf[java.util.Map[_, _]].isAssignableFrom(cls) =>
         val javaIteratorCls = classOf[java.util.Iterator[_]].getName
@@ -671,8 +677,8 @@ case class ExternalMapToCatalyst private(
         val defineKeyValue =
           s"""
             final $javaMapEntryCls $entry = ($javaMapEntryCls) $entries.next();
-            ${ctx.javaType(keyType)} $key = (${ctx.boxedType(keyType)}) $entry.getKey();
-            ${ctx.javaType(valueType)} $value = (${ctx.boxedType(valueType)}) $entry.getValue();
+            $key = (${ctx.boxedType(keyType)}) $entry.getKey();
+            $value = (${ctx.boxedType(valueType)}) $entry.getValue();
           """
 
         defineEntries -> defineKeyValue
@@ -686,17 +692,17 @@ case class ExternalMapToCatalyst private(
         val defineKeyValue =
           s"""
             final $scalaMapEntryCls $entry = ($scalaMapEntryCls) $entries.next();
-            ${ctx.javaType(keyType)} $key = (${ctx.boxedType(keyType)}) $entry._1();
-            ${ctx.javaType(valueType)} $value = (${ctx.boxedType(valueType)}) $entry._2();
+            $key = (${ctx.boxedType(keyType)}) $entry._1();
+            $value = (${ctx.boxedType(valueType)}) $entry._2();
           """
 
         defineEntries -> defineKeyValue
     }
 
     val valueNullCheck = if (ctx.isPrimitiveType(valueType)) {
-      s"boolean $valueIsNull = false;"
+      s"$valueIsNull = false;"
     } else {
-      s"boolean $valueIsNull = $value == null;"
+      s"$valueIsNull = $value == null;"
     }
 
     val arrayCls = classOf[GenericArrayData].getName
diff --git a/sql/core/src/test/scala/org/apache/spark/sql/DatasetPrimitiveSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/DatasetPrimitiveSuite.scala
@@ -21,6 +21,9 @@ import org.apache.spark.sql.test.SharedSQLContext
 
 case class IntClass(value: Int)
 
+case class InnerData(name: String, value: Int)
+case class NestedData(id: Int, param: Map[String, InnerData])
+
 package object packageobject {
   case class PackageClass(value: Int)
 }
@@ -135,4 +138,9 @@ class DatasetPrimitiveSuite extends QueryTest with SharedSQLContext {
     checkDataset(Seq(PackageClass(1)).toDS(), PackageClass(1))
   }
 
+  test("SPARK-19104: Lambda variables in ExternalMapToCatalyst should be global") {
+    val data = Seq.tabulate(10)(i => NestedData(1, Map("key" -> InnerData("name", i + 100))))
+    val ds = spark.createDataset(data)
+    checkDataset(ds, data: _*)
+  }
 }

Original file line number	Diff line number	Diff line change
`@@ -21,6 +21,9 @@ import org.apache.spark.sql.test.SharedSQLContext`
`21`	`21`
`22`	`22`	`case class IntClass(value: Int)`
`23`	`23`
	`24`	`+case class InnerData(name: String, value: Int)`
	`25`	`+case class NestedData(id: Int, param: Map[String, InnerData])`
	`26`	`+`
`24`	`27`	`package object packageobject {`
`25`	`28`	`case class PackageClass(value: Int)`
`26`	`29`	`}`
`@@ -135,4 +138,9 @@ class DatasetPrimitiveSuite extends QueryTest with SharedSQLContext {`
`135`	`138`	`checkDataset(Seq(PackageClass(1)).toDS(), PackageClass(1))`
`136`	`139`	`}`
`137`	`140`
	`141`	`+ test("SPARK-19104: Lambda variables in ExternalMapToCatalyst should be global") {`
	`142`	`+ val data = Seq.tabulate(10)(i => NestedData(1, Map("key" -> InnerData("name", i + 100))))`
	`143`	`+ val ds = spark.createDataset(data)`
	`144`	`+ checkDataset(ds, data: _*)`
	`145`	`+ }`
`138`	`146`	`}`