nits

HyukjinKwon · HyukjinKwon · commit 5b1d1c3db6c1 · 2020-11-25T19:40:50.000+09:00
diff --git a/core/src/main/scala/org/apache/spark/SparkContext.scala b/core/src/main/scala/org/apache/spark/SparkContext.scala
@@ -40,7 +40,7 @@ import org.apache.hadoop.mapred.{FileInputFormat, InputFormat, JobConf, Sequence
 import org.apache.hadoop.mapreduce.{InputFormat => NewInputFormat, Job => NewHadoopJob}
 import org.apache.hadoop.mapreduce.lib.input.{FileInputFormat => NewFileInputFormat}
 
-import org.apache.spark.annotation.DeveloperApi
+import org.apache.spark.annotation.{DeveloperApi, Experimental}
 import org.apache.spark.broadcast.Broadcast
 import org.apache.spark.deploy.{LocalSparkCluster, SparkHadoopUtil}
 import org.apache.spark.executor.{Executor, ExecutorMetrics, ExecutorMetricsSource}
@@ -1533,6 +1533,7 @@ class SparkContext(config: SparkConf) extends Logging {
   def listFiles(): Seq[String] = addedFiles.keySet.toSeq
 
   /**
+   * :: Experimental ::
    * Add an archive to be downloaded and unpacked with this Spark job on every node.
    *
    * If an archive is added during execution, it will not be available until the next TaskSet
@@ -1547,15 +1548,18 @@ class SparkContext(config: SparkConf) extends Logging {
    *
    * @since 3.1.0
    */
+  @Experimental
   def addArchive(path: String): Unit = {
     addFile(path, false, false, isArchive = true)
   }
 
   /**
+   * :: Experimental ::
    * Returns a list of archive paths that are added to resources.
    *
    * @since 3.1.0
    */
+  @Experimental
   def listArchives(): Seq[String] = addedArchives.keySet.toSeq
 
   /**
diff --git a/core/src/main/scala/org/apache/spark/util/Utils.scala b/core/src/main/scala/org/apache/spark/util/Utils.scala
@@ -586,7 +586,7 @@ private[spark] object Utils extends Logging {
       lowerSrc.endsWith(".tar.gz") || lowerSrc.endsWith(".tgz") || lowerSrc.endsWith(".tar")) {
       FileUtil.unTar(source, dest)
     } else {
-      logWarning("Cannot unpack " + source)
+      logWarning(s"Cannot unpack $source, just copying it to $dest.")
       copyRecursive(source, dest)
     }
   }
diff --git a/core/src/test/scala/org/apache/spark/deploy/SparkSubmitSuite.scala b/core/src/test/scala/org/apache/spark/deploy/SparkSubmitSuite.scala
@@ -335,7 +335,7 @@ class SparkSubmitSuite
     sys.props("SPARK_SUBMIT") should be ("true")
   }
 
-  test("SPARK-33530: handles standalone mode") {
+  test("SPARK-33530: handles standalone mode with archives") {
     val clArgs = Seq(
       "--master", "spark://localhost:1234",
       "--executor-memory", "5g",
@@ -356,7 +356,6 @@ class SparkSubmitSuite
     childArgsStr should include ("arg1 arg2")
     mainClass should be ("org.SomeClass")
 
-    // In yarn cluster mode, also adding jars to classpath
     classpath(0) should endWith ("thejar.jar")
     classpath(1) should endWith ("one.jar")
     classpath(2) should endWith ("two.jar")

Original file line number	Diff line number	Diff line change
`@@ -586,7 +586,7 @@ private[spark] object Utils extends Logging {`
`586`	`586`	`lowerSrc.endsWith(".tar.gz") \|\| lowerSrc.endsWith(".tgz") \|\| lowerSrc.endsWith(".tar")) {`
`587`	`587`	`FileUtil.unTar(source, dest)`
`588`	`588`	`} else {`
`589`		`- logWarning("Cannot unpack " + source)`
	`589`	`+ logWarning(s"Cannot unpack $source, just copying it to $dest.")`
`590`	`590`	`copyRecursive(source, dest)`
`591`	`591`	`}`
`592`	`592`	`}`