mapreduce统计单词

源代码：

WordCountMapper.java:

package cn.idcast.mapreduce;

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

import java.io.IOException;

/*
 四个泛型解释：
 KEYIN:k1的类型
 VALUEIN:v1的类型

 KEYOUT:k2的类型
 VALUEOUT:v2的类型
*/
public class WordCountMapper extends Mapper<LongWritable,Text,Text,LongWritable> {

    //map方法就是将K1和v1 转为k2和v2
    /*
        参数:
           key    :k1    行偏移量
           value  :v1    每一行的文本数据
           context:表示上下文对象
     */
    /*
       如何将K1和v1 转为k2和v2
       k1         v1
       0    hello,world,hadoop
       15   hdfs,hive,hello
      -------------------------

       k2         v2
       hello      1
       world      1
       hdfs       1
       hadoop     1
       hello      1
     */
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        Text text = new Text();
        LongWritable longWritable = new LongWritable();
        //1:将一行的文本数据进行拆分
        String[] split = value.toString().split(",");

        //2:遍历数组，组装k2和v2
        for (String word : split) {
            //3:将k2和v2写入上下文中
            text.set(word);
            longWritable.set(1);
            context.write(text,longWritable);
        }

    }
}

WordCountReducer.java:

package cn.idcast.mapreduce;

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

import java.io.IOException;

/*
 四个泛型解释：
 KEYIN:k2的类型
 VALUEIN:v2的类型

 KEYOUT:k3的类型
 VALUEOUT:v3的类型
*/
public class WordCountReducer extends Reducer<Text,LongWritable,Text,LongWritable> {
    //reduce方法作用：将新的k2和v2转为 k3和v3，将k3 和v3写入上下文中
    /*
        参数:
           key    :新k2
           values :集合 新v2
           context:表示上下文对象
          -----------------------
           如何将新的k2和v2转为k3和v3
           新 k2         v2
             hello       <1,1,1>
             world       <1,1>
             hadoop      <1>
         -------------------------
              k3         v3
             hello        3
             world        2
             hadoop       1
     */
    @Override
    protected void reduce(Text key, Iterable<LongWritable> values, Context context) throws IOException, InterruptedException {
        long count=0;
        //1:遍历集合，将集合中的数字相加，得到v3
        for (LongWritable value : values) {
            count +=value.get();
        }
        //2:将k3和v3写入上下文中
        context.write(key,new LongWritable(count));
    }
}

JobMain.java:

package cn.idcast.mapreduce;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
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.lib.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;

import java.net.URI;

public class JobMain extends Configured implements Tool {

    //该方法用于指定一个job任务
    @Override
    public int run(String[] args) throws Exception {
        //1:创建一个job任务对象
        Job job = Job.getInstance(super.getConf(), "wordcount");
        //如果打包运行出错，则需要加该配置
        job.setJarByClass(JobMain.class);
        //2:配置job任务对象（八个步骤）

        //第一步:指定文件的读取方式和读取路径
        job.setInputFormatClass(TextInputFormat.class);
        TextInputFormat.addInputPath(job,new Path("hdfs://node1:8020/wordcount"));

        //第二部:指定Map阶段的处理方式
        job.setMapperClass(WordCountMapper.class);
        //设置Map阶段k2的类型
        job.setMapOutputKeyClass(Text.class);
        //设置Map阶段v2的类型
        job.setMapOutputValueClass(LongWritable.class);

        //第三,四，五，六 采用默认方式，现阶段不做处理

        //第七步:指定Reduce阶段的处理方式和数据类型
        job.setReducerClass(WordCountReducer.class);
        //设置k3的类型
        job.setOutputKeyClass(Text.class);
        //设置v3的类型
        job.setOutputValueClass(LongWritable.class);

        //第八步:设置输出类型
        job.setOutputFormatClass(TextOutputFormat.class);
        //设置输出的路径
        Path path=new Path("hdfs://node1:8020/wordcount_out");
        TextOutputFormat.setOutputPath(job,path);

        //获取FileSystem
        FileSystem fs = FileSystem.get(new URI("hdfs://node1:8020/wordcount_out"),new Configuration());
        //判断目录是否存在
        if (fs.exists(path)) {
            fs.delete(path, true);
            System.out.println("存在此输出路径，已删除！！！");
        }
        //等待任务结束
        boolean bl = job.waitForCompletion(true);
        return bl ? 0:1;
    }

    public static void main(String[] args) throws Exception {
        Configuration configuration = new Configuration();
        //启动job任务
        int run = ToolRunner.run(configuration, new JobMain(), args);
        System.exit(run);
    }
}

记录一个小错误：

发现key重复输出了，原因：reduce步骤中把提交上下文放到循环里去了，导致每加一次就输出一次