实现wordcount功能

新建一个maven工程

在pom.xml中添加相关依赖

<?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.lzc.hadoop</groupId>
  <artifactId>hadoop-api</artifactId>
  <version>1.0-SNAPSHOT</version>
 
  <name>hadoop-api</name>
  <!-- FIXME change it to the project's website -->
  <url>http://www.example.com</url>
  <properties>
    <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
    <maven.compiler.source>1.7</maven.compiler.source>
    <maven.compiler.target>1.7</maven.compiler.target>
    <hadoop.version>2.6.0-cdh5.7.0</hadoop.version>
  </properties>
    <repositories>
        <repository>
            <id>cloudera</id>
            <url>https://repository.cloudera.com/artifactory/cloudera-repos</url>
        </repository>
    </repositories>
  <dependencies>
    <dependency>
      <groupId>org.apache.hadoop</groupId>
      <artifactId>hadoop-client</artifactId>
      <version>${hadoop.version}</version>
    </dependency>
    <dependency>
      <groupId>junit</groupId>
      <artifactId>junit</artifactId>
      <version>4.10</version>
      <scope>test</scope>
    </dependency>
  </dependencies>
</project>

实现代码

package com.lzc.hadoop.mapreduce;


import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

import java.io.IOException;

public class WordCount2App {

    /**
     * Map:读取输入的文件
     */
    public static class MyMapper extends Mapper<LongWritable, Text, Text, LongWritable> {

        LongWritable one = new LongWritable(1);

        @Override
        protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
            // 接收到的每一行数据
            String line = value.toString();

            // 按照指定分隔符进行拆分
            String[] words = line.split(" ");

            for (String word : words) {
                // 通过上下文把map的结果输出
                context.write(new Text(word), one);
            }
        }
    }

    /**
     * Reduce:归并操作
     */
    public static class MyReducer extends Reducer<Text, LongWritable, Text, LongWritable>{
        @Override
        protected void reduce(Text key, Iterable<LongWritable> values, Context context) throws IOException, InterruptedException {

            long sum = 0;
            for (LongWritable value : values) {
                // 求key出现的次数总和
                sum += value.get();
            }
            // 最终统计结果的输出
            context.write(key, new LongWritable(sum));
         }
    }

    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        Configuration configuration = new Configuration();
        // 准备清理已经存在的输出目录（相同的代码和脚本再次执行会报错 ）
        Path outputPath = new Path(args[1]);
        FileSystem fileSystem = FileSystem.get(configuration);
        if (fileSystem.exists(outputPath)) {
            fileSystem.delete(outputPath, true);
            System.out.println("output file exists, but is has deleted");
        }

        // 创建Job
        Job job = Job.getInstance(configuration, "wordcount");

        // 设置Job的处理类
        job.setJarByClass(WordCount2App.class);

        // 设置作业处理的输入路径
        FileInputFormat.setInputPaths(job, new Path(args[0]));

        // 设置map的参数
        job.setMapperClass(MyMapper.class);
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(LongWritable.class);

        // 设置reduce相关参数
        job.setReducerClass(MyReducer.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(LongWritable.class);

        // 设置作业处理的输出路径
        FileOutputFormat.setOutputPath(job, new Path(args[1]));

        System.exit(job.waitForCompletion(true)? 0 : 1);

    }
}

将程序打包成jar包

运行程序

1.首先查看HDFS上的单词文件

[root@localhost data]# hadoop fs -text /hello.txt
18/08/25 09:05:25 WARN util.NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable
hello lzc
hello hadoop
hello hdfs

2.执行jar包

hadoop jar /home/data/hadoop-api-1.0-SNAPSHOT.jar com.lzc.hadoop.mapreduce.WordCount2App hdfs://192.168.126.129:8020/hello.txt hdfs://192.168.126.129:8020/output/wc

由于执行的命令过长，可以将命令保存在shell脚本里。

新建一个shell脚本，将上面的命令写入

[root@localhost data]# vim wc_mr.sh

执行shell脚本

[root@localhost data]# ./wc_mr.sh

查看执行过程

执行完毕

查看执行结果

1.查看输出的文件名

[root@localhost data]# hadoop fs -ls /output/wc
18/08/25 09:04:11 WARN util.NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable
Found 2 items
-rw-r--r--   1 root supergroup          0 2018-08-25 09:02 /output/wc/_SUCCESS
-rw-r--r--   1 root supergroup         30 2018-08-25 09:02 /output/wc/part-r-00000

/output/wc/part-r-00000为输出的结果文件

2.查看结果

[root@localhost data]# hadoop fs -text /output/wc/part-r-00000
18/08/25 09:04:57 WARN util.NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable
hadoop	1
hdfs	1
hello	3
lzc	1