[SPARK-26137][CORE] Use Java system property "file.separator" inste…

… of hard coded "/" in DependencyUtils

## What changes were proposed in this pull request?

Use Java system property "file.separator" instead of hard coded "/" in DependencyUtils.

## How was this patch tested?

Manual test:
Submit Spark application via REST API that reads data from Elasticsearch using spark-elasticsearch library.

Without fix application fails with error:
18/11/22 10:36:20 ERROR Version: Multiple ES-Hadoop versions detected in the classpath; please use only one
jar:file:/C:/<...>/spark-2.4.0-bin-hadoop2.6/work/driver-20181122103610-0001/myApp-assembly-1.0.jar
jar:file:/C:/<...>/myApp-assembly-1.0.jar

18/11/22 10:36:20 ERROR Main: Application [MyApp] failed:
java.lang.Error: Multiple ES-Hadoop versions detected in the classpath; please use only one
jar:file:/C:/<...>/spark-2.4.0-bin-hadoop2.6/work/driver-20181122103610-0001/myApp-assembly-1.0.jar
jar:file:/C:/<...>/myApp-assembly-1.0.jar

	at org.elasticsearch.hadoop.util.Version.<clinit>(Version.java:73)
	at org.elasticsearch.hadoop.rest.RestService.findPartitions(RestService.java:214)
	at org.elasticsearch.spark.rdd.AbstractEsRDD.esPartitions$lzycompute(AbstractEsRDD.scala:73)
	at org.elasticsearch.spark.rdd.AbstractEsRDD.esPartitions(AbstractEsRDD.scala:72)
	at org.elasticsearch.spark.rdd.AbstractEsRDD.getPartitions(AbstractEsRDD.scala:44)
	at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:253)
	at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:251)
	at scala.Option.getOrElse(Option.scala:121)
	at org.apache.spark.rdd.RDD.partitions(RDD.scala:251)
	at org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:49)
	at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:253)
	at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:251)
	at scala.Option.getOrElse(Option.scala:121)
	at org.apache.spark.rdd.RDD.partitions(RDD.scala:251)
	at org.apache.spark.SparkContext.runJob(SparkContext.scala:2126)
	at org.apache.spark.rdd.RDD$$anonfun$collect$1.apply(RDD.scala:945)
	at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
	at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
	at org.apache.spark.rdd.RDD.withScope(RDD.scala:363)
	at org.apache.spark.rdd.RDD.collect(RDD.scala:944)
	...
	at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
	at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
	at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
	at java.lang.reflect.Method.invoke(Method.java:498)
	at org.apache.spark.deploy.worker.DriverWrapper$.main(DriverWrapper.scala:65)
	at org.apache.spark.deploy.worker.DriverWrapper.main(DriverWrapper.scala)

With fix application runs successfully.

Closes apache#23102 from markpavey/JIRA_SPARK-26137_DependencyUtilsFileSeparatorFix.

Authored-by: Mark Pavey <[email protected]>
Signed-off-by: Sean Owen <[email protected]>

Author: Mark Pavey

core/src/main/scala/org/apache/spark/deploy/DependencyUtils.scala

@@ -61,11 +61,12 @@ private[deploy] object DependencyUtils extends Logging {
       hadoopConf: Configuration,
       secMgr: SecurityManager): String = {
     val targetDir = Utils.createTempDir()
+    val userJarName = userJar.split(File.separatorChar).last
     Option(jars)
       .map {
         resolveGlobPaths(_, hadoopConf)
           .split(",")
-          .filterNot(_.contains(userJar.split("/").last))
+          .filterNot(_.contains(userJarName))
           .mkString(",")
       }
       .filterNot(_ == "")

core/src/test/scala/org/apache/spark/deploy/SparkSubmitSuite.scala

@@ -962,6 +962,25 @@ class SparkSubmitSuite
     }
   }
 
+  test("remove copies of application jar from classpath") {
+    val fs = File.separator
+    val sparkConf = new SparkConf(false)
+    val hadoopConf = new Configuration()
+    val secMgr = new SecurityManager(sparkConf)
+
+    val appJarName = "myApp.jar"
+    val jar1Name = "myJar1.jar"
+    val jar2Name = "myJar2.jar"
+    val userJar = s"file:/path${fs}to${fs}app${fs}jar$fs$appJarName"
+    val jars = s"file:/$jar1Name,file:/$appJarName,file:/$jar2Name"
+
+    val resolvedJars = DependencyUtils
+      .resolveAndDownloadJars(jars, userJar, sparkConf, hadoopConf, secMgr)
+
+    assert(!resolvedJars.contains(appJarName))
+    assert(resolvedJars.contains(jar1Name) && resolvedJars.contains(jar2Name))
+  }
+
   test("Avoid re-upload remote resources in yarn client mode") {
     val hadoopConf = new Configuration()
     updateConfWithFakeS3Fs(hadoopConf)