7月28日

学习mapreduce编程

分别写三个类

Mapper类

package com.j.mapreduce.wordcount2;

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阶段输入的value的类型：TEXT
*KEYOUT,map阶段输出的key的类型：TEXT
* VALUEOUT,map阶段输出的value的类型：IntWritable
* */

public class wordcountMapper extends Mapper<LongWritable, Text,Text, IntWritable> {
    private Text outkey =new Text();
    private IntWritable outvalue=new IntWritable(1);

    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        //获取一行
        String line = value.toString();//alue.toString().var   用.var可以自动生产变量
        //切割
        String[] words = line.split(" ");//分割标志根据原文件来写
        //循环写出
        for (String word : words) {
            //封装成outkey
            outkey.set(word);
            //写出
            context.write(outkey, outvalue);
        }

    }
}

reducer类

package com.j.mapreduce.wordcount2;

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阶段输入的value的类型：Intwritable
*KEYOUT,reduce阶段输出的key的类型：TEXT
* VALUEOUT,reduce阶段输出的value的类型：IntWritable
* */
public class wordcountReducer extends Reducer<Text, IntWritable,Text,IntWritable> {
    @Override
    protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
        int sum=0;
        //Iterable<IntWritable> values 一个集合是迭代器的祖宗可以通过迭代器方式访问
        //values.iterator().hasNext();
        //累加
        for (IntWritable value : values) {
            sum+=value.get();
        }
        //转换成intwritable类型
        IntWritable outvalue = new IntWritable();
        outvalue.set(sum);
        //写出
        context.write(key,outvalue);
    }
}

Driver类

package com.j.mapreduce.wordcount2;

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reduce
        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(args[0]));
        FileOutputFormat.setOutputPath(job,new Path(args[1]));
        //提交obj
        boolean result = job.waitForCompletion(true);
        System.exit(result? 0 : 1);
    }
}

将写好的程序通过maven打包成jar包，放到服务器进行运行

hadoop jar wc.jar com.j.mapreduce.wordcount2.wordcountDriver /sanguo /output 注意末尾的输出路径要不存在

注意如果xshell报错，我在查阅了一番资料之后，需要修改一个地方，

Container exited with a non-zero exit code 1. Error file: prelaunch.err.

Last 4096 bytes of prelaunch.err :

Last 4096 bytes of stderr :

Error: Could not find or load main class org.apache.hadoop.mapreduce.v2.app.MRAppMaster

Please check whether your etc/hadoop/mapred-site.xml contains the below configuration:

<name>yarn.app.mapreduce.am.env</name>

<value>HADOOP_MAPRED_HOME=${full path of your hadoop distribution directory}</value>

</property>

<name>mapreduce.map.env</name>

<value>HADOOP_MAPRED_HOME=${full path of your hadoop distribution directory}</value>

</property>

<name>mapreduce.reduce.env</name>

<value>HADOOP_MAPRED_HOME=${full path of your hadoop distribution directory}</value>

</property>

可以通过修改自己的mapred-site.xml

来修改

<name>mapreduce.application.classpath</name>

<value>

/opt/module/hadoop-3.1.3/etc/*,

/opt/module/hadoop-3.1.3/etc/hadoop/*,

/opt/module/hadoop-3.1.3/lib/*,

/opt/module/hadoop-3.1.3/share/hadoop/common/*,

/opt/module/hadoop-3.1.3/share/hadoop/common/lib/*,

/opt/module/hadoop-3.1.3/share/hadoop/mapreduce/*,

/opt/module/hadoop-3.1.3/share/hadoop/mapreduce/lib-examples/*,

/opt/module/hadoop-3.1.3/share/hadoop/hdfs/*,

/opt/module/hadoop-3.1.3/share/hadoop/hdfs/lib/*,

/opt/module/hadoop-3.1.3/share/hadoop/yarn/*,

/opt/module/hadoop-3.1.3/share/hadoop/yarn/lib/*,

</value>

</property>

注意里面的路劲与自己Linux的系统中hadoop路径相同

并分发给其他集群，xsync mapred-site.xml 即可

学习时间：12：19到15：54