Hadoop-22、第一個MapReduce--wordcount

原創

2020-06-07 02:26

依賴還是用之前的，在pom中添加，import changes

<dependencies>
        <dependency>
            <groupId>junit</groupId>
            <artifactId>junit</artifactId>
            <version>RELEASE</version>
        </dependency>
        <dependency>
            <groupId>org.apache.logging.log4j</groupId>
            <artifactId>log4j-core</artifactId>
            <version>2.8.2</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-common</artifactId>
            <version>2.7.2</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>2.7.2</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-hdfs</artifactId>
            <version>2.7.2</version>
        </dependency>
        <dependency>
            <groupId>org.testng</groupId>
            <artifactId>testng</artifactId>
            <version>RELEASE</version>
            <scope>compile</scope>
        </dependency>
    </dependencies>

建立log4j.properties

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

WcMapper.java

package com.atguigu.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;

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

    private Text word = new Text();
    private  IntWritable one = new IntWritable(1);

    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        //拿到這一行數據
        String line = value.toString();
        // 按照空格切分數據
        //System.out.println(line);
        String[] words = line.split(" ");

        // 遍歷數組，把單詞變成(word,1)的形式交給框架
        for (String word : words){
            //System.out.println(word);
            this.word.set(word);
            context.write(this.word, this.one);
        }
    }
}

WcReducer.java

package com.atguigu.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 WcReducer extends Reducer<Text, IntWritable, Text, IntWritable> {

    private  IntWritable total = new IntWritable();

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

        //包裝結果並輸出
        total.set(sum) ;
        context.write(key, total);
    }
}

WcDriver.java

package com.atguigu.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 WcDriver{
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        //1. 獲取一個Job實例
        Job job = Job.getInstance(new Configuration());

        //2. 設置我們的類路徑（classpath）
        job.setJarByClass(WcDriver.class);

        //3. 設置Mapper和Reducer
        job.setMapperClass(WcMapper.class);
        job.setReducerClass(WcReducer.class);

        //4. 設置Mapper和Reducer輸出的類型 Text:hadoop.io
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);

        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);

        //5.設置輸入輸出數據
        FileInputFormat.setInputPaths(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));

        //6. 提交我們的Job
        boolean b = job.waitForCompletion(true);
        System.exit(b ? 0:1);
    }

}