override clone for String.

apache · Sep 2, 2015 · 1469cb0 · 1469cb0
1 parent fc48307
commit 1469cb0
Show file tree

Hide file tree

Showing 2 changed files with 11 additions and 0 deletions.
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/columnar/ColumnType.scala b/sql/core/src/main/scala/org/apache/spark/sql/columnar/ColumnType.scala
@@ -339,6 +339,8 @@ private[sql] object STRING extends NativeColumnType(StringType, 7, 8) {
   override def copyField(from: InternalRow, fromOrdinal: Int, to: MutableRow, toOrdinal: Int) {
     setField(to, toOrdinal, getField(from, fromOrdinal))
   }
+
+  override def clone(v: UTF8String): UTF8String = v.clone()
 }
 
 private[sql] object DATE extends NativeColumnType(DateType, 8, 4) {

diff --git a/sql/core/src/test/scala/org/apache/spark/sql/columnar/InMemoryColumnarQuerySuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/columnar/InMemoryColumnarQuerySuite.scala
@@ -191,4 +191,13 @@ class InMemoryColumnarQuerySuite extends QueryTest with SharedSQLContext {
       ctx.table("InMemoryCache_different_data_types").collect())
     ctx.dropTempTable("InMemoryCache_different_data_types")
   }
+
+  test("SPARK-10422: String column in InMemoryColumnarCache needs to override clone method") {
+    val df =
+      ctx.range(1, 30000).selectExpr("id % 500 as id").rdd.map(id => Tuple1(s"str_$id")).toDF("i")
+    val cached = df.cache()
+    // count triggers the caching action. It should not throw.
+    cached.count()
+    cached.unpersist()
+  }
 }