MapReduce程序在Idea中的开发与调试

一、环境说明

• 系统：Win10
• Hadoop版本：2.10.1
• JDK：1.8

二、环境准备

1、下载hadoop

下载链接hadoop 2.10.1。下载后用解压到本地。

2、下载winutils

下载链接winutils，下载完成后解压到本地，然后复制hadoop对应版本或就近版本的文件夹中的hadoop.dll与winutils.exe文件到hadoop的bin目录中去。

3、配置环境变量

新建环境变量HADOOP_HOME，值为hadoop文件夹的位置

添加变量到PATH

4、最好需要重启电脑，让配置及运行文件生效

三、MapReduce程序编写

1、创建一个空的Maven项目

2、因为要使用到hadoop的一些api，所以需要引入依赖包，这里直接放上完整的pom文件，其中相关依赖版本号hadoop.version变量与你的hadoop版本一致

<?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.javayuli</groupId>
    <artifactId>MapReduceTest</artifactId>
    <version>1.0</version>

    <properties>
        <hadoop.version>2.10.1</hadoop.version>
    </properties>

    <repositories>
        <repository>
            <id>nexus-aliyun</id>
            <name>nexus-aliyun</name>
            <url>http://maven.aliyun.com/nexus/content/groups/public/</url>
            <releases>
                <enabled>true</enabled>
            </releases>
            <snapshots>
                <enabled>false</enabled>
            </snapshots>
        </repository>
    </repositories>
    <dependencies>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-hdfs</artifactId>
            <version>${hadoop.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-common</artifactId>
            <version>${hadoop.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-yarn-common</artifactId>
            <version>${hadoop.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-mapreduce-client-common</artifactId>
            <version>${hadoop.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-auth</artifactId>
            <version>${hadoop.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.lucene</groupId>
            <artifactId>lucene-analyzers-common</artifactId>
            <version>7.3.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.lucene</groupId>
            <artifactId>lucene-core</artifactId>
            <version>7.3.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.lucene</groupId>
            <artifactId>lucene-analyzers-icu</artifactId>
            <version>7.3.0</version>
        </dependency>
        <dependency>
            <groupId>jfree</groupId>
            <artifactId>jfreechart</artifactId>
            <version>1.0.13</version>
        </dependency>
    </dependencies>

    <build>
        <plugins>
            <plugin>
                <artifactId>maven-dependency-plugin</artifactId>
                <configuration>
                    <excludeTransitive>false</excludeTransitive>
                    <stripVersion>true</stripVersion>
                    <outputDirectory>./lib</outputDirectory>
                </configuration>

            </plugin>
        </plugins>
    </build>
</project>

3、编写一个Map程序

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

import java.io.IOException;

/**
 * @author 14516
 */
public class WordCountMap extends Mapper<LongWritable, Text, Text, IntWritable> {

    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        String line = value.toString();
        String[] split = line.split("");
        for (String s: split) {
            context.write(new Text(s), new IntWritable(1));
        }
    }
}

4、编写一个Reduce函数

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

import java.io.IOException;

/**
 * @author 14516
 */
public class WordCountReduce extends Reducer<Text, IntWritable, Text, IntWritable> {

    @Override
    protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
        int count = 0;
        for (IntWritable val: values) {
            count++;
        }
        context.write(key, new IntWritable(count));
    }
}

5、编写一个入口函数

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapred.FileInputFormat;
import org.apache.hadoop.mapred.FileOutputFormat;
import org.apache.hadoop.mapred.JobConf;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.util.GenericOptionsParser;
import org.apache.log4j.BasicConfigurator;

import java.io.IOException;

/**
 * @author 14516
 */
public class WordCount {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        // 自动快速地使用缺省Log4j环境
        BasicConfigurator.configure(); 
        Configuration configuration = new Configuration();
        String[] otherArgs = new GenericOptionsParser(configuration, args).getRemainingArgs();
        if (otherArgs.length < 2) {
            System.err.println("必须输入读取文件路径和输出路径");
            System.exit(2);
        }
        Job job = Job.getInstance();
        job.setJarByClass(WordCount.class);
        job.setJobName("Word Count");
        JobConf jobConfiguration = (JobConf) job.getConfiguration();
        // 设置读取文件的路径，都是从HDFS中读取。读取文件路径从脚本文件中传进来
        FileInputFormat.addInputPath(jobConfiguration, new Path(args[0]));
        // 设置mapreduce程序的输出路径，MapReduce的结果都是输入到文件中
        FileOutputFormat.setOutputPath(jobConfiguration, new Path(args[1]));
        // 设置实现了map函数的类
        job.setMapperClass(WordCountMap.class);
        // 设置实现了reduce函数的类
        job.setReducerClass(WordCountReduce.class);
        // 设置reduce函数的key值
        job.setOutputKeyClass(Text.class);
        // 设置reduce函数的value值
        job.setOutputValueClass(IntWritable.class);
        System.exit(job.waitForCompletion(true) ? 0 :1);
    }
}

6、配置打包

idea中File->Project Structure

选择WordCount

点击Apply，立即应用

7、新建一个运行配置

8、创建input文件夹，并在input文件夹中创建测试文件A.txt

9、运行程序

程序运行后，会自动创建output文件夹，此时part-r-00000中就是执行结果，即每个字符出现的频次。

10、打成jar包

经过上述步骤6之后，可以在Build->Build Artifacts中进行打包

打包后就可以将jar包上传到服务器进行运行。