diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/SparkSqlParser.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/SparkSqlParser.scala
index be2eddbb0e423761f36e2048d9df9bdd42d20c26..8c68d1e3a2379e91874ec41289f6ed620a015003 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/execution/SparkSqlParser.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/SparkSqlParser.scala
@@ -1010,9 +1010,7 @@ class SparkSqlAstBuilder(conf: SQLConf) extends AstBuilder {
.orElse(Some("org.apache.hadoop.mapred.TextInputFormat")),
outputFormat = defaultHiveSerde.flatMap(_.outputFormat)
.orElse(Some("org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat")),
- // Note: Keep this unspecified because we use the presence of the serde to decide
- // whether to convert a table created by CTAS to a datasource table.
- serde = None,
+ serde = defaultHiveSerde.flatMap(_.serde),
compressed = false,
properties = Map())
}
diff --git a/sql/hive/src/test/scala/org/apache/spark/sql/hive/HiveDDLCommandSuite.scala b/sql/hive/src/test/scala/org/apache/spark/sql/hive/HiveDDLCommandSuite.scala
index 9ce3338647398dd5c95e138c539021c5e41996e2..81337493c7f287618e2f400e736d6a681a29fe0f 100644
--- a/sql/hive/src/test/scala/org/apache/spark/sql/hive/HiveDDLCommandSuite.scala
+++ b/sql/hive/src/test/scala/org/apache/spark/sql/hive/HiveDDLCommandSuite.scala
@@ -30,10 +30,12 @@ import org.apache.spark.sql.catalyst.plans.PlanTest
import org.apache.spark.sql.catalyst.plans.logical.{Generate, ScriptTransformation}
import org.apache.spark.sql.execution.command._
import org.apache.spark.sql.execution.datasources.CreateTable
-import org.apache.spark.sql.hive.test.TestHive
+import org.apache.spark.sql.hive.test.{TestHive, TestHiveSingleton}
+import org.apache.spark.sql.internal.SQLConf
+import org.apache.spark.sql.test.SQLTestUtils
import org.apache.spark.sql.types.StructType
-class HiveDDLCommandSuite extends PlanTest {
+class HiveDDLCommandSuite extends PlanTest with SQLTestUtils with TestHiveSingleton {
val parser = TestHive.sessionState.sqlParser
private def extractTableDesc(sql: String): (CatalogTable, Boolean) = {
@@ -556,4 +558,24 @@ class HiveDDLCommandSuite extends PlanTest {
assert(partition2.get.apply("c") == "1" && partition2.get.apply("d") == "2")
}
+ test("Test the default fileformat for Hive-serde tables") {
+ withSQLConf("hive.default.fileformat" -> "orc") {
+ val (desc, exists) = extractTableDesc("CREATE TABLE IF NOT EXISTS fileformat_test (id int)")
+ assert(exists)
+ assert(desc.storage.inputFormat == Some("org.apache.hadoop.hive.ql.io.orc.OrcInputFormat"))
+ assert(desc.storage.outputFormat == Some("org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat"))
+ assert(desc.storage.serde == Some("org.apache.hadoop.hive.ql.io.orc.OrcSerde"))
+ }
+
+ withSQLConf("hive.default.fileformat" -> "parquet") {
+ val (desc, exists) = extractTableDesc("CREATE TABLE IF NOT EXISTS fileformat_test (id int)")
+ assert(exists)
+ val input = desc.storage.inputFormat
+ val output = desc.storage.outputFormat
+ val serde = desc.storage.serde
+ assert(input == Some("org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat"))
+ assert(output == Some("org.apache.hadoop.hive.ql.io.parquet.MapredParquetOutputFormat"))
+ assert(serde == Some("org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe"))
+ }
+ }
}
diff --git a/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/SQLQuerySuite.scala b/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/SQLQuerySuite.scala
index 6f2a16662bf101218372bbf1d61186a8e486c64e..e26b6b57ef569565faef4ab64235d0b5b00c39ff 100644
--- a/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/SQLQuerySuite.scala
+++ b/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/SQLQuerySuite.scala
@@ -492,7 +492,7 @@ class SQLQuerySuite extends QueryTest with SQLTestUtils with TestHiveSingleton {
def checkRelation(
tableName: String,
- isDataSourceParquet: Boolean,
+ isDataSourceTable: Boolean,
format: String,
userSpecifiedLocation: Option[String] = None): Unit = {
val relation = EliminateSubqueryAliases(
@@ -501,7 +501,7 @@ class SQLQuerySuite extends QueryTest with SQLTestUtils with TestHiveSingleton {
sessionState.catalog.getTableMetadata(TableIdentifier(tableName))
relation match {
case LogicalRelation(r: HadoopFsRelation, _, _) =>
- if (!isDataSourceParquet) {
+ if (!isDataSourceTable) {
fail(
s"${classOf[MetastoreRelation].getCanonicalName} is expected, but found " +
s"${HadoopFsRelation.getClass.getCanonicalName}.")
@@ -514,7 +514,7 @@ class SQLQuerySuite extends QueryTest with SQLTestUtils with TestHiveSingleton {
assert(catalogTable.provider.get === format)
case r: MetastoreRelation =>
- if (isDataSourceParquet) {
+ if (isDataSourceTable) {
fail(
s"${HadoopFsRelation.getClass.getCanonicalName} is expected, but found " +
s"${classOf[MetastoreRelation].getCanonicalName}.")
@@ -524,8 +524,15 @@ class SQLQuerySuite extends QueryTest with SQLTestUtils with TestHiveSingleton {
assert(r.catalogTable.storage.locationUri.get === location)
case None => // OK.
}
- // Also make sure that the format is the desired format.
+ // Also make sure that the format and serde are as desired.
assert(catalogTable.storage.inputFormat.get.toLowerCase.contains(format))
+ assert(catalogTable.storage.outputFormat.get.toLowerCase.contains(format))
+ val serde = catalogTable.storage.serde.get
+ format match {
+ case "sequence" | "text" => assert(serde.contains("LazySimpleSerDe"))
+ case "rcfile" => assert(serde.contains("LazyBinaryColumnarSerDe"))
+ case _ => assert(serde.toLowerCase.contains(format))
+ }
}
// When a user-specified location is defined, the table type needs to be EXTERNAL.
@@ -587,6 +594,30 @@ class SQLQuerySuite extends QueryTest with SQLTestUtils with TestHiveSingleton {
}
}
+ test("CTAS with default fileformat") {
+ val table = "ctas1"
+ val ctas = s"CREATE TABLE IF NOT EXISTS $table SELECT key k, value FROM src"
+ withSQLConf(SQLConf.CONVERT_CTAS.key -> "true") {
+ withSQLConf("hive.default.fileformat" -> "textfile") {
+ withTable(table) {
+ sql(ctas)
+ // We should use parquet here as that is the default datasource fileformat. The default
+ // datasource file format is controlled by `spark.sql.sources.default` configuration.
+ // This testcase verifies that setting `hive.default.fileformat` has no impact on
+ // the target table's fileformat in case of CTAS.
+ assert(sessionState.conf.defaultDataSourceName === "parquet")
+ checkRelation(tableName = table, isDataSourceTable = true, format = "parquet")
+ }
+ }
+ withSQLConf("spark.sql.sources.default" -> "orc") {
+ withTable(table) {
+ sql(ctas)
+ checkRelation(tableName = table, isDataSourceTable = true, format = "orc")
+ }
+ }
+ }
+ }
+
test("CTAS without serde with location") {
withSQLConf(SQLConf.CONVERT_CTAS.key -> "true") {
withTempDir { dir =>