Spark first example

this code will count the number of words in a text file.

package geo1.op1;

import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaPairRDD;
import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.api.java.JavaSparkContext;
import org.apache.spark.api.java.function.FlatMapFunction;
import org.apache.spark.api.java.function.Function2;
import org.apache.spark.api.java.function.PairFunction;
import scala.Tuple2;

import java.util.Arrays;

public class WordCount {
    private static final FlatMapFunction<String, String> WORDS_EXTRACTOR = new FlatMapFunction<String, String>() {
        // @Override
        public Iterable<String> call(String s) throws Exception {
            return Arrays.asList(s.split(" "));
        }
    };

    private static final PairFunction<String, String, Integer> WORDS_MAPPER = new PairFunction<String, String, Integer>() {
        // @Override
        public Tuple2<String, Integer> call(String s) throws Exception {
            return new Tuple2<String, Integer>(s, 1);
        }
    };

    private static final Function2<Integer, Integer, Integer> WORDS_REDUCER = new Function2<Integer, Integer, Integer>() {
        // @Override
        public Integer call(Integer a, Integer b) throws Exception {
            return a + b;
        }
    };

    public static void main(String[] args) {
//        if (args.length < 1) {
//            System.err
//                    .println("Please provide the input file full path as argument");
//            System.exit(0);
//        }

        String inputPath="/home/steve/Documents/words.txt";
        String outputFolder="/home/steve/Documents/ans";
        SparkConf conf = new SparkConf().setAppName(
                "org.sparkexample.WordCount").setMaster("local");
        JavaSparkContext context = new JavaSparkContext(conf);

        JavaRDD<String> file = context.textFile(inputPath);
        JavaRDD<String> words = file.flatMap(WORDS_EXTRACTOR);
        JavaPairRDD<String, Integer> pairs = words.mapToPair(WORDS_MAPPER);
        JavaPairRDD<String, Integer> counter = pairs.reduceByKey(WORDS_REDUCER);

        counter.saveAsTextFile(outputFolder);
    }
}

pom.xml

<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
  xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
  <modelVersion>4.0.0</modelVersion>

  <groupId>geo1</groupId>
  <artifactId>op1</artifactId>
  <version>0.0.1-SNAPSHOT</version>
  <packaging>jar</packaging>

  <name>op1</name>
  <url>http://maven.apache.org</url>

  <properties>
    <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
  </properties>

  <dependencies>
    <dependency>
      <groupId>junit</groupId>
      <artifactId>junit</artifactId>
      <version>3.8.1</version>
      <scope>test</scope>
    </dependency>
    <dependency>
        <groupId>org.apache.spark</groupId>
        <artifactId>spark-core_2.10</artifactId>
        <version>1.2.0</version>
    </dependency>
  </dependencies>
</project>