All Downloads are FREE. Search and download functionalities are using the official Maven repository.

spark.examples.JavaWordCount Maven / Gradle / Ivy

package spark.examples;

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

import java.util.Arrays;
import java.util.List;

public class JavaWordCount {
  public static void main(String[] args) throws Exception {
    if (args.length < 2) {
      System.err.println("Usage: JavaWordCount  ");
      System.exit(1);
    }

    JavaSparkContext ctx = new JavaSparkContext(args[0], "JavaWordCount",
        System.getenv("SPARK_HOME"), System.getenv("SPARK_EXAMPLES_JAR"));
    JavaRDD lines = ctx.textFile(args[1], 1);

    JavaRDD words = lines.flatMap(new FlatMapFunction() {
      public Iterable call(String s) {
        return Arrays.asList(s.split(" "));
      }
    });
    
    JavaPairRDD ones = words.map(new PairFunction() {
      public Tuple2 call(String s) {
        return new Tuple2(s, 1);
      }
    });
    
    JavaPairRDD counts = ones.reduceByKey(new Function2() {
      public Integer call(Integer i1, Integer i2) {
        return i1 + i2;
      }
    });

    List> output = counts.collect();
    for (Tuple2 tuple : output) {
      System.out.println(tuple._1 + ": " + tuple._2);
    }
    System.exit(0);
  }
}




© 2015 - 2025 Weber Informatics LLC | Privacy Policy