cloud-fan commented on a change in pull request #27552: [SPARK-30808][SQL]
Enable Java 8 time API in Thrift server
URL: https://github.com/apache/spark/pull/27552#discussion_r385112690
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/HiveResult.scala
##########
@@ -36,27 +37,43 @@ 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) =>
- // If it is a describe command for a Hive table, we want to have the
output format
- // be similar with Hive.
- executedPlan.executeCollectPublic().map {
- case Row(name: String, dataType: String, comment) =>
- Seq(name, dataType,
- Option(comment.asInstanceOf[String]).getOrElse(""))
- .map(s => String.format(s"%-20s", s))
- .mkString("\t")
- }
- // SHOW TABLES in Hive only output table names, while ours output
database, table name, isTemp.
- case command @ ExecutedCommandExec(s: ShowTablesCommand) if !s.isExtended
=>
- 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) =>
+ // If it is a describe command for a Hive table, we want to have the
output format
+ // be similar with Hive.
+ executedPlan.executeCollectPublic().map {
+ case Row(name: String, dataType: String, comment) =>
+ Seq(name, dataType,
+ Option(comment.asInstanceOf[String]).getOrElse(""))
+ .map(s => String.format(s"%-20s", s))
+ .mkString("\t")
+ }
+ // SHOW TABLES in Hive only output table names,
+ // while ours output database, table name, isTemp.
+ case command @ ExecutedCommandExec(s: ShowTablesCommand) if
!s.isExtended =>
+ 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)
Review comment:
found a problem. `Dataset.ofRows` will set the input session as active, so
we should write `Dataset.ofRows(sessionWithJava8DatetimeEnabled, ...` and
remove the outer `sessionWithJava8DatetimeEnabled.withActive`.
----------------------------------------------------------------
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:
[email protected]
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
