Hadoop plusieurs entrées

Vous pouvez vous joindre à eux à l'aide de l'ID comme clé pour les deux mappeur.
Vous pouvez écrire votre carte tâche en tant que quelque chose comme cela

public void map(LongWritable k, Text value, Context context) throws IOException, InterruptedException
{
    //Get the line
    //split the line to get ID seperate
    //word1 = A 
    //word2 = 30
                //Likewise for A ABC
                   //word1 = A 
                  //word2 = ABC
    context.write(word1, word2);
}

Je pense que vous pouvez resuse la même Carte tâche.
Et puis écrire un commomn Réducteur de travail où Framework Hadoop groupes de données sur la clé.
Ainsi, vous serez en mesure d'obtenir l'ID comme clé.
Et Vous pouvez mettre en cache l'un de la valeur et puis concat.

String merge = "";
public void reduce(Text key, Iterable<Text> values, Context context)
{
    int i =0;
    for(Text value:values)
    {
        if(i == 0){
            merge = value.toString()+",";
        }
        else{
            merge += value.toString();
        }
        i++;
    }
    valEmit.set(merge);
    context.write(key, valEmit);
}

Enfin, vous pouvez écrire votre Chauffeur classe

public int run(String[] args) throws Exception {
 Configuration c=new Configuration();
 String[] files=new GenericOptionsParser(c,args).getRemainingArgs();
 Path p1=new Path(files[0]);
 Path p2=new Path(files[1]);
 Path p3=new Path(files[2]);
 FileSystem fs = FileSystem.get(c);
 if(fs.exists(p3)){
  fs.delete(p3, true);
  }
 Job job = new Job(c,"Multiple Job");
 job.setJarByClass(MultipleFiles.class);
 MultipleInputs.addInputPath(job, p1, TextInputFormat.class, MultipleMap1.class);
 MultipleInputs.addInputPath(job,p2, TextInputFormat.class, MultipleMap2.class);
 job.setReducerClass(MultipleReducer.class);
 .
 .
}

Vous pouvez trouver l'exemple ICI

Espère que cette aide.

Mise à JOUR

Input1

A 30
D 20

Input2

A ABC
D EFGH

Sortie

A ABC 30
D EFGH 20

Mapper.java

import java.io.IOException;

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

/**
 * @author sreeveni
 *
 */
public class Mapper1 extends Mapper<LongWritable, Text, Text, Text> {
    Text keyEmit = new Text();
    Text valEmit = new Text();

    public void map(LongWritable key, Text value, Context context)
            throws IOException, InterruptedException {
        String line = value.toString();
        String parts[] = line.split(" ");
        keyEmit.set(parts[0]);
        valEmit.set(parts[1]);
        context.write(keyEmit, valEmit);
    }
}

Reducer.java

import java.io.IOException;

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

/**
 * @author sreeveni
 *
 */
public class ReducerJoin extends Reducer<Text, Text, Text, Text> {

    Text valEmit = new Text();
    String merge = "";

    public void reduce(Text key, Iterable<Text> values, Context context)
            throws IOException, InterruptedException {
        String character = "";
        String number = "";
        for (Text value : values) {
            //ordering output
            String val = value.toString();
            char myChar = val.charAt(0);

            if (Character.isDigit(myChar)) {
                number = val;
            } else {
                character = val;
            }
        }
        merge = character + " " + number;
        valEmit.set(merge);
        context.write(key, valEmit);
    }

}

De la classe du pilote

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.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.MultipleInputs;
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;
/**
* @author sreeveni
*
*/
public class Driver extends Configured implements Tool {
public static void main(String[] args) throws Exception {
//TODO Auto-generated method stub
//checking the arguments count
if (args.length != 3) {
System.err
.println("Usage : <inputlocation>  <inputlocation>  <outputlocation> ");
System.exit(0);
}
int res = ToolRunner.run(new Configuration(), new Driver(), args);
System.exit(res);
}
@Override
public int run(String[] args) throws Exception {
//TODO Auto-generated method stub
String source1 = args[0];
String source2 = args[1];
String dest = args[2];
Configuration conf = new Configuration();
conf.set("mapred.textoutputformat.separator", " "); //changing default
//delimiter to user
//input delimiter
FileSystem fs = FileSystem.get(conf);
Job job = new Job(conf, "Multiple Jobs");
job.setJarByClass(Driver.class);
Path p1 = new Path(source1);
Path p2 = new Path(source2);
Path out = new Path(dest);
MultipleInputs.addInputPath(job, p1, TextInputFormat.class,
Mapper1.class);
MultipleInputs.addInputPath(job, p2, TextInputFormat.class,
Mapper1.class);
job.setReducerClass(ReducerJoin.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(Text.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(Text.class);
job.setOutputFormatClass(TextOutputFormat.class);
/*
* delete if exist
*/
if (fs.exists(out))
fs.delete(out, true);
TextOutputFormat.setOutputPath(job, out);
boolean success = job.waitForCompletion(true);
return success ? 0 : 1;
}
}

OriginalL'auteur Unmesha SreeVeni