diff options
-rw-r--r-- | sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/hiveOperators.scala | 6 | ||||
-rw-r--r-- | sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveQuerySuite.scala | 6 |
2 files changed, 11 insertions, 1 deletions
diff --git a/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/hiveOperators.scala b/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/hiveOperators.scala index a839231449..240aa0df49 100644 --- a/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/hiveOperators.scala +++ b/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/hiveOperators.scala @@ -344,12 +344,16 @@ case class InsertIntoHiveTable( writer.commitJob() } + override def execute() = result + /** * Inserts all the rows in the table into Hive. Row objects are properly serialized with the * `org.apache.hadoop.hive.serde2.SerDe` and the * `org.apache.hadoop.mapred.OutputFormat` provided by the table definition. + * + * Note: this is run once and then kept to avoid double insertions. */ - def execute() = { + private lazy val result: RDD[Row] = { val childRdd = child.execute() assert(childRdd != 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 8b2bdd513b..5118f4b3f9 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 @@ -28,6 +28,12 @@ import org.apache.spark.sql.{SchemaRDD, execution, Row} */ class HiveQuerySuite extends HiveComparisonTest { + test("CREATE TABLE AS runs once") { + hql("CREATE TABLE foo AS SELECT 1 FROM src LIMIT 1").collect() + assert(hql("SELECT COUNT(*) FROM foo").collect().head.getLong(0) === 1, + "Incorrect number of rows in created table") + } + createQueryTest("between", "SELECT * FROM src WHERE key Between 1 and 2") |