单词统计以序列格式输出

wordcount1类

/**
 * wordcount单词统计
 */
public class wordcount1 {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        //单例作业
        Configuration conf = new Configuration();
        conf.set("fs.defaultFS","file:///");
        Job job = Job.getInstance(conf);

        //设置job的各种属性
        job.setJobName("wordcountAPP");                 //设置job名称
        job.setJarByClass(wordcount1.class);              //设置搜索类
//        job.setInputFormatClass(org.apache.hadoop.mapreduce.lib.input.TextInputFormat.class);  //设置输入格式

        //设置输出格式类
        job.setOutputFormatClass(org.apache.hadoop.mapreduce.lib.output.SequenceFileOutputFormat.class);

        FileInputFormat.addInputPath(job, new Path(args[0])); //添加输入路径
        FileOutputFormat.setOutputPath(job,new Path(args[1]));//设置输出路径

        job.setInputFormatClass(org.apache.hadoop.mapreduce.lib.input.TextInputFormat.class);
        job.setMapperClass(map.class);                   //设置mapper类
        job.setReducerClass(reduce.class);               //设置reduecer类

        job.setNumReduceTasks(1);                         //设置reduce个数

        job.setMapOutputKeyClass(Text.class);            //设置之map输出key
        job.setMapOutputValueClass(IntWritable.class);   //设置map输出value
        job.setOutputKeyClass(Text.class);               //设置mapreduce 输出key
        job.setOutputValueClass(IntWritable.class);      //设置mapreduce输出value
        job.waitForCompletion(true);
    }
}

mapper类和reducer类源码见

点击打开链接

查看生成的序列文件

设置分区

定义分区类

package com.cr.hdfs.com.cr;


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


public class Mypartioner extends Partitioner<Text,IntWritable>{


    public int getPartition(Text text, IntWritable intWritable, int i) {
        System.out.println("start mypartionner");
        return 0;
    }
}

在wordcount设置分区类和合成类

/**
 * wordcount单词统计
 */
public class wordcount1 {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        //单例作业
        Configuration conf = new Configuration();
        conf.set("fs.defaultFS","file:///");
        Job job = Job.getInstance(conf);

        //设置job的各种属性
        job.setJobName("wordcountAPP");                 //设置job名称
        job.setJarByClass(wordcount1.class);              //设置搜索类
//        job.setInputFormatClass(org.apache.hadoop.mapreduce.lib.input.TextInputFormat.class);  //设置输入格式

        //设置输出格式类
        job.setOutputFormatClass(org.apache.hadoop.mapreduce.lib.output.SequenceFileOutputFormat.class);

        //设置自定义分区类
        job.setPartitionerClass(Mypartioner.class);
        //设置合成类
        job.setCombinerClass(reduce.class);

        FileInputFormat.addInputPath(job, new Path(args[0])); //添加输入路径
        FileOutputFormat.setOutputPath(job,new Path(args[1]));//设置输出路径

        job.setInputFormatClass(org.apache.hadoop.mapreduce.lib.input.TextInputFormat.class);
        job.setMapperClass(map.class);                   //设置mapper类
        job.setReducerClass(reduce.class);               //设置reduecer类

        job.setNumReduceTasks(3);                         //设置reduce个数

        job.setMapOutputKeyClass(Text.class);            //设置之map输出key
        job.setMapOutputValueClass(IntWritable.class);   //设置map输出value
        job.setOutputKeyClass(Text.class);               //设置mapreduce 输出key
        job.setOutputValueClass(IntWritable.class);      //设置mapreduce输出value
        job.waitForCompletion(true);
    }

reducer类

package com.cr.hdfs;

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

import java.io.IOException;

public class reduce extends Reducer<Text,IntWritable,Text,IntWritable>{
    @Override
    protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
        System.out.println("come into reduce...");
        int count = 0;
        for(IntWritable iw : values){
            count += iw.get();
        }

        //获取当前线程
        String tno = Thread.currentThread().getName();
        System.out.println("线程==>"+ tno + "===>  reducer ===>  " + key.toString() + "===>" + count);
        context.write(key,new IntWritable(count));

    }
}

mapper类

package com.cr.hdfs;

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 map extends Mapper<LongWritable,Text,Text,IntWritable> {

    /**
     * WordCountMapper 处理文本为<k,v>对
     * @param key 每一行字节数的偏移量
     * @param value 每一行的文本
     * @param context 上下文
     * @throws IOException
     * @throws InterruptedException
     */
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        Text keyOut = new Text();
        IntWritable valueout = new IntWritable();
        String[] arr = value.toString().split(" ");
        for(String s : arr){
            keyOut.set(s);
            valueout.set(1);
            context.write(keyOut,valueout);
        }
        System.out.println("come into mapper...");

    }
}

运行结果

come into mapper...
come into mapper...
come into reduce...
线程==>LocalJobRunner Map Task Executor #0===>  reducer ===>  are===>1
come into reduce...
线程==>LocalJobRunner Map Task Executor #0===>  reducer ===>  hello===>2
come into reduce...
线程==>LocalJobRunner Map Task Executor #0===>  reducer ===>  how===>1
come into reduce...
线程==>LocalJobRunner Map Task Executor #0===>  reducer ===>  world===>1
come into reduce...
线程==>LocalJobRunner Map Task Executor #0===>  reducer ===>  you===>1
come into reduce...
线程==>pool-3-thread-1===>  reducer ===>  are===>1
come into reduce...
线程==>pool-3-thread-1===>  reducer ===>  hello===>2
come into reduce...
线程==>pool-3-thread-1===>  reducer ===>  how===>1
come into reduce...
线程==>pool-3-thread-1===>  reducer ===>  world===>1
come into reduce...
线程==>pool-3-thread-1===>  reducer ===>  you===>1

产生了三个reduce聚合的文件

查看结果

发现只有第一个聚合文件里面有内容，后面两个都没有