MapReduce 的格式输入----MultipleInputs多个输入

针对 MapReduce的数据嘚瑟输入格式可能不同，有些数据可能以制表符分隔文本文件，有些数据可能是二进制顺序文件，即使它们的格式相同，它们的表示也看可能不同，因此需要分别进行解析。

MultipleInputs可以妥善处理这些问题，它允许为每条输入路径指定InputFprmat和Mapper

public static voidaddInputPath(JobConf conf, Path path, Class<?extendsInputFormat> inputFormatClass)

请看一个demo案例：

一个是sequencefile文件，一个是keyvalue文件

原理图：

1、SeqMapper

package hadoop.mr.input.multiple;

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;

/**
* SeqMapper
*/
public class SeqMapper extends Mapper<IntWritable, IntWritable, IntWritable, IntWritable> {

protected void map(IntWritable key, IntWritable value, Context context) throws IOException, InterruptedException {
context.write(key,value);
}
}

2、KeyValueTextMapper

package hadoop.mr.input.multiple;

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;

/**
* KeyValueTextMapper
*/
public class KeyValueTextMapper extends Mapper<Text, Text, IntWritable, IntWritable> {

protected void map(Text key, Text value, Context context) throws IOException, InterruptedException {
IntWritable year = new IntWritable(Integer.parseInt(key.toString()));
IntWritable temp = new IntWritable(Integer.parseInt(value.toString()));
context.write(year,temp);
}
}

3、MaxTempReducer

package hadoop.mr.input.multiple;

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

import java.io.IOException;

/**
* MaxTempReducer
*/
public class MaxTempReducer extends Reducer<IntWritable, IntWritable, IntWritable, IntWritable>{

protected void reduce(IntWritable key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
int max = Integer.MIN_VALUE ;
for(IntWritable iw : values){
max = max > iw.get() ? max : iw.get() ;
}
context.write(key,new IntWritable(max));
}
}

4、App

package hadoop.mr.input.multiple;

import hadoop.mr.input.nline.WordCountMapper;
import hadoop.mr.input.nline.WordCountReducer;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
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.*;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

/**
*/
public class App {
public static void main(String[] args) throws Exception {
args = new String[]{"d:/java/mr/data" , "d:/java/mr/out"} ;
Configuration conf = new Configuration();
conf.set("fs.defaultFS","file:///");
conf.set("mapreduce.framework.name","local");

FileSystem fs = FileSystem.get(conf);
if(fs.exists(new Path(args[1]))){
fs.delete(new Path(args[1]),true);
}

Job job = Job.getInstance(conf);

job.setJobName("WordCount");
job.setJarByClass(App.class);

job.setReducerClass(MaxTempReducer.class);

FileOutputFormat.setOutputPath(job,new Path(args[1]));

MultipleInputs.addInputPath(job,new Path("d:/java/mr/data/temp.seq"), SequenceFileInputFormat.class,SeqMapper.class);
job.getConfiguration().set(KeyValueLineRecordReader.KEY_VALUE_SEPERATOR," ");
MultipleInputs.addInputPath(job,new Path("d:/java/mr/data/temp.dat"), KeyValueTextInputFormat.class,KeyValueTextMapper.class);

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

job.setNumReduceTasks(2);

job.waitForCompletion(true);
}
}