java编写WordCound的Spark程序，Scala编写wordCound程序

1、创建一个maven项目，项目的相关信息如下：

<groupId>cn.toto.spark</groupId>
<artifactId>bigdata</artifactId>
<version>1.0-SNAPSHOT</version>

2、修改Maven仓库的位置配置：

3、首先要编写Maven的Pom文件

<?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>cn.toto.spark</groupId>
    <artifactId>bigdata</artifactId>
    <version>1.0-SNAPSHOT</version>

    <properties>
        <maven.compiler.source>1.7</maven.compiler.source>
        <maven.compiler.target>1.7</maven.compiler.target>
        <encoding>UTF-8</encoding>
        <scala.version>2.10.6</scala.version>
        <spark.version>1.6.2</spark.version>
        <hadoop.version>2.6.4</hadoop.version>
    </properties>

    <dependencies>
        <dependency>
            <groupId>org.scala-lang</groupId>
            <artifactId>scala-library</artifactId>
            <version>${scala.version}</version>
        </dependency>

        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-core_2.10</artifactId>
            <version>${spark.version}</version>
        </dependency>

        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>${hadoop.version}</version>
        </dependency>
    </dependencies>

    <build>
        <sourceDirectory>src/main/scala</sourceDirectory>
        <testSourceDirectory>src/test/scala</testSourceDirectory>
        <plugins>
            <plugin>
                <groupId>net.alchim31.maven</groupId>
                <artifactId>scala-maven-plugin</artifactId>
                <version>3.2.2</version>
                <executions>
                    <execution>
                        <goals>
                            <goal>compile</goal>
                            <goal>testCompile</goal>
                        </goals>
                        <configuration>
                            <args>
                                <arg>-make:transitive</arg>
                                <arg>-dependencyfile</arg>
                                <arg>${project.build.directory}/.scala_dependencies</arg>
                            </args>
                        </configuration>
                    </execution>
                </executions>
            </plugin>

            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-shade-plugin</artifactId>
                <version>2.4.3</version>
                <executions>
                    <execution>
                        <phase>package</phase>
                        <goals>
                            <goal>shade</goal>
                        </goals>
                        <configuration>
                            <filters>
                                <filter>
                                    <artifact>*:*</artifact>
                                    <excludes>
                                        <exclude>META-INF/*.SF</exclude>
                                        <exclude>META-INF/*.DSA</exclude>
                                        <exclude>META-INF/*.RSA</exclude>
                                    </excludes>
                                </filter>
                            </filters>
                        </configuration>
                    </execution>
                </executions>
            </plugin>
        </plugins>
    </build>

</project>

4、编写Java代码

package cn.toto.spark;

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;

/**
 * Created by toto on 2017/7/6.
 */
public class JavaWordCount {

    public static void main(String[] args) {
        SparkConf conf = new SparkConf().setAppName("JavaWordCount");
        //创建java sparkcontext
        JavaSparkContext jsc = new JavaSparkContext(conf);
        //读取数据
        JavaRDD<String> lines = jsc.textFile(args[0]);
        //切分
        JavaRDD<String> words = lines.flatMap(new FlatMapFunction<String, String>() {
            @Override
            public Iterable<String> call(String line) throws Exception {
                return Arrays.asList(line.split(" "));
            }
        });
        //遇见一个单词就记作一个1
        JavaPairRDD<String, Integer> wordAndOne = words.mapToPair(new PairFunction<String, String, Integer>() {
            @Override
            public Tuple2<String, Integer> call(String word) throws Exception {
                return new Tuple2<String, Integer>(word, 1);
            }
        });
        //分组聚合
        JavaPairRDD<String, Integer> result = wordAndOne.reduceByKey(new Function2<Integer, Integer, Integer>() {
            @Override
            public Integer call(Integer i1, Integer i2) throws Exception {
                return i1 + i2;
            }
        });
        //反转顺序
        JavaPairRDD<Integer, String> swapedPair = result.mapToPair(new PairFunction<Tuple2<String, Integer>, Integer, String>() {
            @Override
            public Tuple2<Integer, String> call(Tuple2<String, Integer> tp) throws Exception {
                return new Tuple2<Integer, String>(tp._2, tp._1);
            }
        });
        //排序并调换顺序
        JavaPairRDD<String, Integer> finalResult = swapedPair.sortByKey(false).mapToPair(new PairFunction<Tuple2<Integer, String>, String, Integer>() {
            @Override
            public Tuple2<String, Integer> call(Tuple2<Integer, String> tp) throws Exception {
                return tp.swap();
            }
        });

        //保存
        finalResult.saveAsTextFile(args[1]);
        jsc.stop();
    }
}

5、准备数据

数据放置在E:\wordcount\input中：

里面的文件内容是：

6、通过工具传递参数：

7、运行结果：

---

8、scala编写wordCount

单词统计的代码如下：

import org.apache.spark.rdd.RDD
import org.apache.spark.{SparkConf, SparkContext}

/**
  * Created by ZhaoXing on 2016/6/30.
  */
object ScalaWordCount {

  def main(args: Array[String]) {

    val conf = new SparkConf().setAppName("ScalaWordCount")
    //非常重要的一个对象SparkContext
    val sc = new SparkContext(conf)

    //textFile方法生成了两个RDD： HadoopRDD[LongWritable, Text]  ->  MapPartitionRDD[String]
    val lines: RDD[String] = sc.textFile(args(0))
    //flatMap方法生成了一个MapPartitionRDD[String]
    val words: RDD[String] = lines.flatMap(_.split(" "))

    //Map方法生成了一个MapPartitionRDD[(String, Int)]
    val wordAndOne: RDD[(String, Int)] = words.map((_, 1))

    val counts: RDD[(String, Int)] = wordAndOne.reduceByKey(_+_)

    val sortedCounts: RDD[(String, Int)] = counts.sortBy(_._2, false)
    //保存的HDFS
    //sortedCounts.saveAsTextFile(args(1))
    counts.saveAsTextFile(args(1))
    //释放SparkContext
    sc.stop()

  }
}