address comments

apache · Dec 2, 2020 · bff924d · bff924d
1 parent ada2bd8
commit bff924d
Show file tree

Hide file tree

Showing 3 changed files with 29 additions and 3 deletions.
diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/internal/SQLConf.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/internal/SQLConf.scala
@@ -2925,7 +2925,7 @@ object SQLConf {
   val LEGACY_CREATE_HIVE_TABLE_BY_DEFAULT =
     buildConf("spark.sql.legacy.createHiveTableByDefault")
       .internal()
-      .doc("When set to true, CREATE TABLE syntax without a table provider will use hive " +
+      .doc("When set to true, CREATE TABLE syntax without USING or STORED AS will use Hive " +
         s"instead of the value of ${DEFAULT_DATA_SOURCE_NAME.key} as the table provider.")
       .version("3.1.0")
       .booleanConf

diff --git a/sql/core/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveSessionCatalog.scala b/sql/core/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveSessionCatalog.scala
@@ -643,6 +643,9 @@ class ResolveSessionCatalog(
       if (!createHiveTableByDefault || (ctas && conf.convertCTAS)) {
         (nonHiveStorageFormat, conf.defaultDataSourceName)
       } else {
+        logWarning("A Hive serde table will be created as there is no table provider " +
+          s"specified. You can set ${SQLConf.LEGACY_CREATE_HIVE_TABLE_BY_DEFAULT.key} to false " +
+          "so that native data source table will be created instead.")
         (defaultHiveStorage, DDLUtils.HIVE_PROVIDER)
       }
     }
@@ -659,8 +662,14 @@ class ResolveSessionCatalog(
       comment: Option[String],
       storageFormat: CatalogStorageFormat,
       external: Boolean): CatalogTable = {
-    if (external && location.isEmpty) {
-      throw new AnalysisException(s"CREATE EXTERNAL TABLE must be accompanied by LOCATION")
+    if (external) {
+      if (DDLUtils.isHiveTable(Some(provider))) {
+        if (location.isEmpty) {
+          throw new AnalysisException(s"CREATE EXTERNAL TABLE must be accompanied by LOCATION")
+        }
+      } else {
+        throw new AnalysisException(s"Operation not allowed: CREATE EXTERNAL TABLE ... USING")
+      }
     }
 
     val tableType = if (location.isDefined) {

diff --git a/sql/core/src/test/scala/org/apache/spark/sql/sources/CreateTableAsSelectSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/sources/CreateTableAsSelectSuite.scala
@@ -170,6 +170,23 @@ class CreateTableAsSelectSuite extends DataSourceTest with SharedSparkSession {
     }
   }
 
+  test("disallows CREATE EXTERNAL TABLE ... USING ... AS query") {
+    withTable("t") {
+      val error = intercept[AnalysisException] {
+        sql(
+          s"""
+             |CREATE EXTERNAL TABLE t USING PARQUET
+             |OPTIONS (PATH '${path.toURI}')
+             |AS SELECT 1 AS a, 2 AS b
+           """.stripMargin
+        )
+      }.getMessage
+
+      assert(error.contains("Operation not allowed") &&
+        error.contains("CREATE EXTERNAL TABLE ..."))
+    }
+  }
+
   test("create table using as select - with partitioned by") {
     val catalog = spark.sessionState.catalog
     withTable("t") {