[GitHub] [spark] juliuszsompolski commented on a change in pull request #28705: [SPARK-30808][SQL] Enable Java 8 time API in Thrift server

[GitBox <gi...@apache.org>]

juliuszsompolski commented on a change in pull request #28705:
URL: https://github.com/apache/spark/pull/28705#discussion_r434136228



##########
File path: sql/core/src/main/scala/org/apache/spark/sql/execution/HiveResult.scala
##########
@@ -37,30 +37,45 @@ object HiveResult {
    * Returns the result as a hive compatible sequence of strings. This is used in tests and
    * `SparkSQLDriver` for CLI applications.
    */
-  def hiveResultString(executedPlan: SparkPlan): Seq[String] = executedPlan match {
-    case ExecutedCommandExec(_: DescribeCommandBase) =>
-      formatDescribeTableOutput(executedPlan.executeCollectPublic())
-    case _: DescribeTableExec =>
-      formatDescribeTableOutput(executedPlan.executeCollectPublic())
-    // SHOW TABLES in Hive only output table names while our v1 command outputs
-    // database, table name, isTemp.
-    case command @ ExecutedCommandExec(s: ShowTablesCommand) if !s.isExtended =>
-      command.executeCollect().map(_.getString(1))
-    // SHOW TABLES in Hive only output table names while our v2 command outputs
-    // namespace and table name.
-    case command : ShowTablesExec =>
-      command.executeCollect().map(_.getString(1))
-    // SHOW VIEWS in Hive only outputs view names while our v1 command outputs
-    // namespace, viewName, and isTemporary.
-    case command @ ExecutedCommandExec(_: ShowViewsCommand) =>
-      command.executeCollect().map(_.getString(1))
-    case other =>
-      val result: Seq[Seq[Any]] = other.executeCollectPublic().map(_.toSeq).toSeq
-      // We need the types so we can output struct field names
-      val types = executedPlan.output.map(_.dataType)
-      // Reformat to match hive tab delimited output.
-      result.map(_.zip(types).map(e => toHiveString(e)))
-        .map(_.mkString("\t"))
+  def hiveResultString(ds: Dataset[_]): Seq[String] = {
+    val executedPlan = ds.queryExecution.executedPlan
+    executedPlan match {
+      case ExecutedCommandExec(_: DescribeCommandBase) =>
+        formatDescribeTableOutput(executedPlan.executeCollectPublic())
+      case _: DescribeTableExec =>
+        formatDescribeTableOutput(executedPlan.executeCollectPublic())
+      // SHOW TABLES in Hive only output table names while our v1 command outputs
+      // database, table name, isTemp.
+      case command @ ExecutedCommandExec(s: ShowTablesCommand) if !s.isExtended =>
+        command.executeCollect().map(_.getString(1))
+      // SHOW TABLES in Hive only output table names while our v2 command outputs
+      // namespace and table name.
+      case command : ShowTablesExec =>
+        command.executeCollect().map(_.getString(1))
+      // SHOW VIEWS in Hive only outputs view names while our v1 command outputs
+      // namespace, viewName, and isTemporary.
+      case command @ ExecutedCommandExec(_: ShowViewsCommand) =>
+        command.executeCollect().map(_.getString(1))
+      case _ =>
+        val sessionWithJava8DatetimeEnabled = {
+          val cloned = ds.sparkSession.cloneSession()
+          cloned.conf.set(SQLConf.DATETIME_JAVA8API_ENABLED.key, true)
+          cloned
+        }
+        sessionWithJava8DatetimeEnabled.withActive {
+          // We cannot collect the original dataset because its encoders could be created
+          // with disabled Java 8 date-time API.
+          val result: Seq[Seq[Any]] = Dataset.ofRows(ds.sparkSession, ds.logicalPlan)
+            .queryExecution
+            .executedPlan
+            .executeCollectPublic().map(_.toSeq).toSeq
+          // We need the types so we can output struct field names
+          val types = executedPlan.output.map(_.dataType)
+          // Reformat to match hive tab delimited output.
+          result.map(_.zip(types).map(e => toHiveString(e)))
+            .map(_.mkString("\t"))
+        }
+    }

Review comment:
       SparkSQLCLIDriver is the only non-test user of this function, and if we want the CLI to always use the new Java 8 date-time APIs, I think we could better explicitly set it there, rather than cloning the session, and cloning the Dataset here to do it.




----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

For queries about this service, please contact Infrastructure at:
users@infra.apache.org



---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org