mr Wordcount 程序

1.创建maven项目

 

 2.编写mr 程序

1.添加maven 依赖和插件

<dependencies>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>3.1.3</version>
        </dependency>
        <dependency>
            <groupId>junit</groupId>
            <artifactId>junit</artifactId>
            <version>4.12</version>
        </dependency>
        <dependency>
            <groupId>org.slf4j</groupId>
            <artifactId>slf4j-log4j12</artifactId>
            <version>1.7.30</version>
        </dependency>
    </dependencies>
    <build>
    <plugins>
        <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>

2. 日志文件，在resources 目下新建log4j.properties 文件

log4j.rootLogger=INFO, stdout 
log4j.appender.stdout=org.apache.log4j.ConsoleAppender 
log4j.appender.stdout.layout=org.apache.log4j.PatternLayout 
log4j.appender.stdout.layout.ConversionPattern=%d %p [%c] - %m%n 
log4j.appender.logfile=org.apache.log4j.FileAppender 
log4j.appender.logfile.File=target/spring.log 
log4j.appender.logfile.layout=org.apache.log4j.PatternLayout 
log4j.appender.logfile.layout.ConversionPattern=%d %p [%c] - %m%n

3. 编写maper 程序

package deng.com.mr.wordcount;

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;
/*
*Mapper<KEYIN, VALUEIN, KEYOUT, VALUEOUT>
KEYIN 数据类型： LongWritable 偏移量
* VALUEIN： Text
*
* */

public class WordCountMapper extends Mapper<LongWritable, Text,Text, IntWritable> {

    private Text kOut = new Text();
    private IntWritable v = new IntWritable(1);
    @Override
    protected void map(LongWritable key, Text value, Mapper<LongWritable, Text, Text, IntWritable>.Context context) throws IOException, InterruptedException {
        // value  : hello spark
        String line = value.toString();
        // 按空格切分
        String[] words = line.split(" ");
        for (String word : words) {
            // 封装
            kOut.set(word);
            // 写出
            context.write(kOut,v);
        }


    }
}

4. 编写reducer

package deng.com.mr.wordcount;

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

import java.io.IOException;

public class WordCountReducer extends Reducer<Text, IntWritable, Text,IntWritable> {
    private int sum;
    private IntWritable v = new IntWritable();
    @Override
    protected void reduce(Text key, Iterable<IntWritable> values, Reducer<Text, IntWritable, Text, IntWritable>.Context context) throws IOException, InterruptedException {
        // (hello,{1,1,1,1})
        sum=0;

        for (IntWritable value : values) {
            sum+=value.get();

        }
        v.set(sum);
        // 写出
        context.write(key,v);
    }
}

5. 编写driver

package deng.com.mr.wordcount;

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, InterruptedException, ClassNotFoundException {

        // 1.创建job
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);
        //2.关联jar包
        job.setJarByClass(WordCountDriver.class);
        //3. 关联map和reduce jar包
        job.setMapperClass(WordCountMapper.class);
        job.setReducerClass(WordCountReducer.class);
        //4. map kv 输出格式
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);
        //5. 最终的KV 输出格式
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);
        //6. 设置输入和输路径
        FileInputFormat.setInputPaths(job,new Path(args[0]));
        FileOutputFormat.setOutputPath(job,new Path(args[1]));
        //7. 提交job
        boolean result = job.waitForCompletion(true);
        System.exit(result?0:1);

    }
}

6. 打包

 

 7. 将不带依赖得jar包，重名为wc.jar,上传linux 集群环境

 

 8. 运行