Hadoop job多文件读入 MutltiInputs

MutltiInputs（多输入）;使用多个输入作为job的输入来源

---------------------------------------------
也就是在InputFormat 前把添加各种不同的序列源
里面的方法也就是  addInputPath等等。。。。
map也可以在这个流程中套进来

 

APP类：

package com.mao.hdfs.multiInput;

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.MultipleInputs;
import org.apache.hadoop.mapreduce.lib.input.SequenceFileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

public class WCApp {
    public static void main(String[] args) throws Exception {
        Configuration conf = new Configuration();
        conf.set("fs.defaultFS","file:///"); //本地运行

        Job job = Job.getInstance(conf);
        //设置job属性
        job.setJobName("WCAppMulti");                                    //作业名称
        job.setJarByClass(WCApp.class);                             //搜索类

        //多个输入
        MultipleInputs.addInputPath(job,new Path("file:///d:/mr/txt"), TextInputFormat.class,WCTextMapper.class);
        MultipleInputs.addInputPath(job,new Path("file:///d:/mr/seq"), SequenceFileInputFormat.class,WCSeqMapper.class);

        //设置输出
        FileOutputFormat.setOutputPath(job,new Path(args[0]));

        job.setReducerClass(WCReducer.class);                       //reduce类
        job.setNumReduceTasks(3);                                   //reduce个数

        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);              //输出map

        job.setOutputKeyClass(Text.class);                          //输出key
        job.setOutputValueClass(IntWritable.class);                 //输出value
        job.waitForCompletion(true);
    }
}

mapper类：

package com.mao.hdfs.multiInput;

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;

/**
 * WCTextMapper
 */
public class WCTextMapper extends Mapper<LongWritable, Text, Text, IntWritable> {
    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);
        }
    }
}

package com.mao.hdfs.multiInput;

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;

/**
 * WCTextMapper
 */
public class WCSeqMapper extends Mapper<IntWritable, Text, Text, IntWritable> {
    protected void map(IntWritable 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);
        }
    }
}

Reducer类：

package com.mao.hdfs.multiInput;

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

import java.io.IOException;

/**
 * WCReducer
 */
public class WCReducer extends Reducer<Text, IntWritable,Text,IntWritable> {

    protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
        int count = 0;
        for (IntWritable iw : values){
            count = count + iw.get();
        }
        context.write(key,new IntWritable(count));
    }
}