[
https://issues.apache.org/jira/browse/SPARK-16408?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15365668#comment-15365668
]
zenglinxi commented on SPARK-16408:
-----------------------------------
I think we should add an parameter (spark.input.dir.recursive) to control the
value of recursive, and make this parameter works by modify some code, like:
{noformat}
diff --git
a/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/commands.scala
b/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/commands.scala
index 6b16d59..3be8553 100644
--- a/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/commands.scala
+++ b/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/commands.scala
@@ -113,8 +113,9 @@ case class AddFile(path: String) extends RunnableCommand {
override def run(sqlContext: SQLContext): Seq[Row] = {
val hiveContext = sqlContext.asInstanceOf[HiveContext]
+ val recursive =
sqlContext.sparkContext.getConf.getBoolean("spark.input.dir.recursive", false)
hiveContext.runSqlHive(s"ADD FILE $path")
- hiveContext.sparkContext.addFile(path)
+ hiveContext.sparkContext.addFile(path, recursive)
Seq.empty[Row]
}
}
{noformat}
> SparkSQL Added file get Exception: is a directory and recursive is not turned
> on
> --------------------------------------------------------------------------------
>
> Key: SPARK-16408
> URL: https://issues.apache.org/jira/browse/SPARK-16408
> Project: Spark
> Issue Type: Task
> Components: SQL
> Affects Versions: 1.6.2
> Reporter: zenglinxi
>
> when use Spark-sql to execute sql like:
> {quote}
> add file hdfs://xxx/user/test;
> {quote}
> if the HDFS path( hdfs://xxx/user/test) is a directory, then we will get an
> exception like:
> {quote}
> org.apache.spark.SparkException: Added file hdfs://xxx/user/test is a
> directory and recursive is not turned on.
> at org.apache.spark.SparkContext.addFile(SparkContext.scala:1372)
> at org.apache.spark.SparkContext.addFile(SparkContext.scala:1340)
> at org.apache.spark.sql.hive.execution.AddFile.run(commands.scala:117)
> at
> org.apache.spark.sql.execution.ExecutedCommand.sideEffectResult$lzycompute(commands.scala:58)
> at
> org.apache.spark.sql.execution.ExecutedCommand.sideEffectResult(commands.scala:56)
> at
> org.apache.spark.sql.execution.ExecutedCommand.doExecute(commands.scala:70)
> {quote}
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
