[SPARK-20680][SQL] Spark-sql do not support for void column datatype of view

Author: LantaoJin

sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala

@@ -1504,6 +1504,7 @@ class AstBuilder extends SqlBaseBaseVisitor[AnyRef] with Logging {
       case ("decimal", precision :: Nil) => DecimalType(precision.getText.toInt, 0)
       case ("decimal", precision :: scale :: Nil) =>
         DecimalType(precision.getText.toInt, scale.getText.toInt)
+      case ("void", Nil) => NullType
       case (dt, params) =>
         val dtStr = if (params.nonEmpty) s"$dt(${params.mkString(",")})" else dt
         throw new ParseException(s"DataType $dtStr is not supported.", ctx)

sql/catalyst/src/main/scala/org/apache/spark/sql/types/NullType.scala

@@ -33,6 +33,11 @@ class NullType private() extends DataType {
   override def defaultSize: Int = 1
 
   private[spark] override def asNullable: NullType = this
+
+  /**
+   * Readable string representation for NULL type.
+   */
+  override def simpleString: String = "void"
 }
 
 /**

sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/parser/DataTypeParserSuite.scala

@@ -58,6 +58,7 @@ class DataTypeParserSuite extends SparkFunSuite {
   checkDataType("varchAr(20)", StringType)
   checkDataType("cHaR(27)", StringType)
   checkDataType("BINARY", BinaryType)
+  checkDataType("void", NullType)
 
   checkDataType("array<doublE>", ArrayType(DoubleType, true))
   checkDataType("Array<map<int, tinYint>>", ArrayType(MapType(IntegerType, ByteType, true), true))

sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveDDLSuite.scala

@@ -1928,4 +1928,17 @@ class HiveDDLSuite
       }
     }
   }
+
+  test("SPARK-20680: Spark-sql do not support for void column datatype of view") {
+    withTable("t", "tabNullType") {
+      val client = spark.sharedState.externalCatalog.asInstanceOf[HiveExternalCatalog].client
+      client.runSqlHive("CREATE TABLE t (t1 int)")
+      client.runSqlHive("INSERT INTO t VALUES (3)")
+      client.runSqlHive("CREATE TABLE tabNullType AS SELECT NULL AS col FROM t")
+      checkAnswer(spark.table("tabNullType"), Row(null))
+      // table description shows "void" representation for NULL type.
+      val desc = spark.sql("DESC tabNullType").collect().toSeq
+      assert(desc.contains(Row("col", "void", null)))
+    }
+  }
 }