java - Colons in Apache Spark application path -

i'm submitting apache spark application yarn programmatically:

package application.restapplication;  import org.apache.hadoop.conf.configuration; import org.apache.spark.sparkconf; import org.apache.spark.deploy.yarn.client; import org.apache.spark.deploy.yarn.clientarguments;  public class app {     public static void main(string[] args1) {         string[] args = new string[] {                 "--class", "org.apache.spark.examples.javawordcount",                 "--jar", "/opt/spark/examples/jars/spark-examples_2.11-2.0.0.jar",                 "--arg", "hdfs://hadoop-master:9000/input/file.txt"         };         configuration config = new configuration();         system.setproperty("spark_yarn_mode", "true");         sparkconf sparkconf = new sparkconf();         clientarguments cargs = new clientarguments(args);         client client = new client(cargs, config, sparkconf);         client.run();     } } 

i have problem line: "--arg", "hdfs://hadoop-master:9000/input/file.txt" - more colons:

16/08/29 09:54:16 error yarn.applicationmaster: uncaught exception:  java.lang.numberformatexception: input string: "9000/input/plik2.txt"     @ java.lang.numberformatexception.forinputstring(numberformatexception.java:65)     @ java.lang.integer.parseint(integer.java:580)     @ java.lang.integer.parseint(integer.java:615)     @ scala.collection.immutable.stringlike$class.toint(stringlike.scala:272)     @ scala.collection.immutable.stringops.toint(stringops.scala:29)     @ org.apache.spark.util.utils$.parsehostport(utils.scala:935)     @ org.apache.spark.deploy.yarn.applicationmaster.waitforsparkdriver(applicationmaster.scala:547)     @ org.apache.spark.deploy.yarn.applicationmaster.runexecutorlauncher(applicationmaster.scala:405)     @ org.apache.spark.deploy.yarn.applicationmaster.run(applicationmaster.scala:247)     @ org.apache.spark.deploy.yarn.applicationmaster$$anonfun$main$1.apply$mcv$sp(applicationmaster.scala:749)     @ org.apache.spark.deploy.sparkhadooputil$$anon$1.run(sparkhadooputil.scala:71)     @ org.apache.spark.deploy.sparkhadooputil$$anon$1.run(sparkhadooputil.scala:70)     @ java.security.accesscontroller.doprivileged(native method)     @ javax.security.auth.subject.doas(subject.java:422)     @ org.apache.hadoop.security.usergroupinformation.doas(usergroupinformation.java:1657)     @ org.apache.spark.deploy.sparkhadooputil.runassparkuser(sparkhadooputil.scala:70)     @ org.apache.spark.deploy.yarn.applicationmaster$.main(applicationmaster.scala:747)     @ org.apache.spark.deploy.yarn.executorlauncher$.main(applicationmaster.scala:774)     @ org.apache.spark.deploy.yarn.executorlauncher.main(applicationmaster.scala) 

how write (as argument) path file colons? try various combinations slashes, backslashes, %3a, etc...

according utils#parsehostport invoked during call, spark seems consider port text behind last : :

def parsehostport(hostport: string): (string, int) = {     // check cache first.     val cached = hostportparseresults.get(hostport)     if (cached != null) {       return cached     }      val indx: int = hostport.lastindexof(':')     // potentially broken - when dealing ipv6 addresses example, sigh ...     // hadoop not support ipv6 right now.     // now, assume if port exists, valid - not check if int > 0     if (-1 == indx) {       val retval = (hostport, 0)       hostportparseresults.put(hostport, retval)       return retval     }      val retval = (hostport.substring(0, indx).trim(), hostport.substring(indx + 1).trim().toint)     hostportparseresults.putifabsent(hostport, retval)     hostportparseresults.get(hostport) } 

as consequence, whole string 9000/input/file.txt supposed single port number. suggests not supposed refer input file hdfs file system. guess more skilled in apache spark give better advice.