mr-WordCount 简单测试代码

local模式

1. 需要windows版本的hadoop（本文为hadoop-3.1.0）
2. 配置windows环境变量
3. pom.xml文件中导入依赖
4. 编写代码

pom.xml文件中导入依赖

<dependencies>
        <dependency>
            <!--程序运行时，所需hadoop配置-->
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>3.1.3</version>
        </dependency>
        <dependency>
            <!--单元测试-->
            <groupId>junit</groupId>
            <artifactId>junit</artifactId>
            <version>4.12</version>
        </dependency>
        <dependency>
            <!--日志控制-->
            <groupId>org.slf4j</groupId>
            <artifactId>slf4j-log4j12</artifactId>
            <version>1.7.30</version>
        </dependency>
    </dependencies>

编写代码

• Mapper

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;

/**
 * KEYIN, map阶段输入的key的类型：LongWritable
 * VALUEIN,map阶段输入value类型：Text
 * KEYOUT,map阶段输出的Key类型：Text
 * VALUEOUT,map阶段输出的value类型：IntWritable
 */
public class WordCountMapper extends Mapper<LongWritable, Text, Text, IntWritable> {
    private Text outK = new Text();
    private IntWritable outV = new IntWritable(1);

    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        // 1 获取一行
        String line = value.toString();
        // 2 切割
        String[] words = line.split(" ");
        // 3 循环写出
        for (String word : words) {
            // 封装outk
            outK.set(word);
            // 写出
            context.write(outK, outV);
        }
    }
}

• Reducer

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

import java.io.IOException;

/**
 * KEYIN, reduce阶段输入的key的类型：Text
 * VALUEIN,reduce阶段输入value类型：IntWritable
 * KEYOUT,reduce阶段输出的Key类型：Text
 * VALUEOUT,reduce阶段输出的value类型：IntWritable
 */
public class WordCountReducer extends Reducer<Text, IntWritable, Text, IntWritable> {
    private IntWritable outV = new IntWritable();

    @Override
    protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
        int sum = 0;
        // 累加
        for (IntWritable value : values) {
            sum += value.get();
        }
        outV.set(sum);
        // 写出
        context.write(key, outV);
    }
}

• Driver

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.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

import java.io.IOException;

public class WordCountDriver {

    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {

        // 1 获取job
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);

        // 2 设置jar包路径
        job.setJarByClass(WordCountDriver.class);

        // 3 关联mapper和reducer
        job.setMapperClass(WordCountMapper.class);
        job.setReducerClass(WordCountReducer.class);

        // 4 设置map输出的kv类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);

        // 5 设置最终输出的kV类型
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);

        // 6 设置输入路径和输出路径
        FileInputFormat.setInputPaths(job, new Path("e:\\input\\inputword"));
        // 输出路径不能存在
        FileOutputFormat.setOutputPath(job, new Path("e:\\hadoop\\output1"));

        // 7 提交job
        boolean result = job.waitForCompletion(true);

        System.exit(result ? 0 : 1);
    }

}

yarn模式

1. 修改Driver类
2. 用maven打jar包，需要添加的打包插件依赖
3. 打包上传到集群下

1）修改Driver类

// 6 设置输入和输出路径（将上述代码替换即可）
FileInputFormat.setInputPaths(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));

2）用maven打jar包，需要添加的打包插件依赖

<build>
        <plugins>
            <plugin>
                <!--打包插件版本-->
                <artifactId>maven-compiler-plugin</artifactId>
                <version>3.6.1</version>
                <configuration>
                    <source>1.8</source>
                    <target>1.8</target>
                </configuration>
            </plugin>
            <!--控制项目运行时所需依赖被打包-->
            <plugin>
                <artifactId>maven-assembly-plugin</artifactId>
                <configuration>
                    <descriptorRefs>
                        <descriptorRef>jar-with-dependencies</descriptorRef>
                    </descriptorRefs>
                </configuration>
                <executions>
                    <execution>
                        <id>make-assembly</id>
                        <phase>package</phase>
                        <goals>
                            <goal>single</goal>
                        </goals>
                    </execution>
                </executions>
            </plugin>
        </plugins>
    </build>

3）打包上传到集群下

hadoop jar MapReduceDemo-1.0-SNAPSHOT-jar-with-dependencies.jar com.atguigu.mapreduce.wc.WordCountDriver /input /output/output1