GroupBy bug in Spark's Java API, see https://issues.apache.org/jira/browse/SPARK-4459

pom.xml

<project>
  <groupId>edu.berkeley</groupId>
  <artifactId>simple-project</artifactId>
  <modelVersion>4.0.0</modelVersion>
  <name>Simple Project</name>
  <packaging>jar</packaging>
  <version>1.0</version>
  <repositories>
    <repository>
      <id>Akka repository</id>
      <url>http://repo.akka.io/releases</url>
    </repository>
  </repositories>
  <dependencies>
    <dependency> <!-- Spark dependency -->
      <groupId>org.apache.spark</groupId>
      <artifactId>spark-core_2.10</artifactId>
      <version>1.0.2</version>
    </dependency>
  </dependencies>
</project>

SimpleApp.java

import org.apache.spark.api.java.*;
import org.apache.spark.api.java.function.Function;
import scala.Tuple2;

public class SimpleApp {
    private static Function<Tuple2<String,Long>, Long> indexMod4 = new Function<Tuple2<String,Long>, Long>() {
        @Override
        public Long call(Tuple2<String, Long> arg0) throws Exception {
            return (long)(arg0._2 / 4);
        }
    };

    public static void main(String[] args) {
        String logFile = "$YOUR_SPARK_HOME/README.md"; // Should be some file on your system
        JavaSparkContext sc = new JavaSparkContext("local", "Simple App",
            "$YOUR_SPARK_HOME", new String[]{"target/simple-project-1.0.jar"});
        JavaRDD<String> logData = sc.textFile(logFile).cache();

        long numAs = logData.filter(new Function<String, Boolean>() {
            public Boolean call(String s) { return s.contains("a"); }
        }).count();

        long numBs = logData.filter(new Function<String, Boolean>() {
            public Boolean call(String s) { return s.contains("b"); }
        }).count();

        final JavaRDD<Long,Iterable<Tuple2<String,Long>>> parsedFiles1 = logData
            .zipWithIndex()
            .groupBy(indexMod4);

        System.out.println("Lines with a: " + numAs + ", lines with b: " + numBs);
    }
}

If you make a simple maven project with the attached pom.xml and src/main/java/SimpleApp.java, you should find that "mvn package" fails with a "no suitable method found for groupBy(org.apache.spark.api.java.function.Function<scala.Tuple2<java.lang.String,java.lang.Long>,java.lang.Long>)"