54 lines
1.7 KiB
Java
54 lines
1.7 KiB
Java
|
|
package com.baeldung;
|
||
|
|
|
||
|
|
import java.util.Arrays;
|
||
|
|
import java.util.List;
|
||
|
|
import java.util.regex.Pattern;
|
||
|
|
|
||
|
|
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.*;
|
||
|
|
import org.apache.spark.api.java.function.Function2;
|
||
|
|
import org.apache.spark.api.java.function.PairFunction;
|
||
|
|
|
||
|
|
import scala.Tuple2;
|
||
|
|
|
||
|
|
public class WordCount {
|
||
|
|
|
||
|
|
private static final Pattern SPACE = Pattern.compile(" ");
|
||
|
|
|
||
|
|
public static void main(String[] args) throws Exception {
|
||
|
|
if (args.length < 1) {
|
||
|
|
System.err.println("Usage: JavaWordCount <file>");
|
||
|
|
System.exit(1);
|
||
|
|
}
|
||
|
|
SparkConf sparkConf = new SparkConf().setAppName("JavaWordCount").setMaster("local");
|
||
|
|
JavaSparkContext ctx = new JavaSparkContext(sparkConf);
|
||
|
|
JavaRDD<String> lines = ctx.textFile(args[0], 1);
|
||
|
|
|
||
|
|
JavaRDD<String> words = lines.flatMap(s -> Arrays.asList(SPACE.split(s)).iterator());
|
||
|
|
JavaPairRDD<String, Integer> ones = words.mapToPair(
|
||
|
|
new PairFunction<String, String, Integer>() {
|
||
|
|
@Override
|
||
|
|
public Tuple2<String, Integer> call(String s) {
|
||
|
|
return new Tuple2<>(s, 1);
|
||
|
|
}
|
||
|
|
});
|
||
|
|
|
||
|
|
JavaPairRDD<String, Integer> counts = ones.reduceByKey(
|
||
|
|
new Function2<Integer, Integer, Integer>() {
|
||
|
|
@Override
|
||
|
|
public Integer call(Integer i1, Integer i2) {
|
||
|
|
return i1 + i2;
|
||
|
|
}
|
||
|
|
});
|
||
|
|
|
||
|
|
List<Tuple2<String, Integer>> output = counts.collect();
|
||
|
|
for (Tuple2<?, ?> tuple : output) {
|
||
|
|
System.out.println(tuple._1() + ": " + tuple._2());
|
||
|
|
}
|
||
|
|
ctx.stop();
|
||
|
|
}
|
||
|
|
}
|