spark单词统计开发（java版）

1.java代码

import java.util.Arrays;
import java.util.Iterator;

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.Function;
import org.apache.spark.api.java.function.Function2;
import org.apache.spark.api.java.function.PairFunction;
import org.apache.spark.api.java.function.VoidFunction;

import scala.Tuple2;

public class WordCount {

    public static void main(String[] args) {
        SparkConf conf = new SparkConf();

        conf.setAppName("WordCounter")//
                .setMaster("local");

        String fileName = "F:\\scala\\countjava\\src\\main\\resources\\file.txt";

        JavaSparkContext sc = new JavaSparkContext(conf);
        JavaRDD<String> lines = sc.textFile(fileName, 1);

        JavaRDD<String> words = lines
                .flatMap(new FlatMapFunction<String, String>() {
                    private static final long serialVersionUID = 1L;

                    @Override
                    public Iterator<String> call(String line) throws Exception {
                        return Arrays.asList(line.split(" ")).iterator();
                    }
                });

        JavaPairRDD<String, Integer> pairs = words
                .mapToPair(new PairFunction<String, String, Integer>() {
                    private static final long serialVersionUID = 1L;

                    @Override
                    public Tuple2<String, Integer> call(String word)
                            throws Exception {
                        return new Tuple2<String, Integer>(word, 1);
                    }
                });

        JavaPairRDD<String, Integer> result = pairs.reduceByKey(
                new Function2<Integer, Integer, Integer>() {
                    private static final long serialVersionUID = 1L;

                    @Override
                    public Integer call(Integer e, Integer acc)
                            throws Exception {
                        return e + acc;
                    }
                }, 1);

        result.map(
                new Function<Tuple2<String, Integer>, Tuple2<String, Integer>>() {

                    private static final long serialVersionUID = 1L;

                    @Override
                    public Tuple2<String, Integer> call(
                            Tuple2<String, Integer> v1) throws Exception {
                        return new Tuple2<>(v1._1, v1._2);
                    }
                })//
                .sortBy(new Function<Tuple2<String, Integer>, Integer>() {
                    private static final long serialVersionUID = 1L;

                    @Override
                    public Integer call(Tuple2<String, Integer> v1)
                            throws Exception {
                        return v1._2;
                    }
                }, false, 1)//
                .foreach(new VoidFunction<Tuple2<String, Integer>>() {
                    private static final long serialVersionUID = 1L;

                    @Override
                    public void call(Tuple2<String, Integer> e)
                            throws Exception {
                        System.out.println("【" + e._1 + "】出现了" + e._2 + "次");
                    }
                });
        sc.close();

    }
}

2.依赖资源

<?xml version="1.0" encoding="UTF-8"?>
<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>com.count.liyang</groupId>
    <artifactId>count-java</artifactId>
    <version>1.0-SNAPSHOT</version>

    <dependencies>
        <!-- https://mvnrepository.com/artifact/org.apache.spark/spark-core_2.11 -->
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-core_2.11</artifactId>
            <version>2.0.0</version>
        </dependency>

    </dependencies>
    <build>
        <plugins>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-compiler-plugin</artifactId>
                <version>3.5.1</version>
                <configuration>
                    <source>1.8</source>
                    <target>1.8</target>
                    <encoding>UTF-8</encoding>
                    <compilerArguments>
                        <!-- <extdirs>src/main/webapp/plugins/ueditor/jsp/lib</extdirs> -->
                    </compilerArguments>
                </configuration>
            </plugin>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-surefire-plugin</artifactId>
                <version>2.18.1</version>
                <configuration>
                    <useFile>false</useFile>
                    <disableXmlReport>true</disableXmlReport>
                    <!-- If you have classpath issue like NoDefClassError,... -->
                    <!-- useManifestOnlyJar>false</useManifestOnlyJar -->
                    <includes>
                        <include>**/*Test.*</include>
                        <include>**/*Suite.*</include>
                    </includes>
                </configuration>
            </plugin>
        </plugins>
    </build>
</project>