mapreduce的多输入的问题

mapreduce的多输入的问题

• CountForSeqMapper.java

public class CountForSeqMapper extends Mapper<Text,IntWritable,Text,IntWritable>{
    @Override
    protected void map(Text key, IntWritable value, Context context) throws IOException, InterruptedException {
       String s = key.toString()+"2";
       context.write(new Text(s),value);
    }
}

• CountForTextMapper

public class CountForTextMapper extends Mapper<LongWritable,Text,Text,IntWritable> {
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        String[] words = value.toString().split(",");
        for (String word : words) {
            context.write(new Text(word),new IntWritable(1));
        }
    }
}

• CountReducer

public class CountReducer extends Reducer<Text,IntWritable,Text,IntWritable> {
    @Override
    protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
        int sum =0;
        for (IntWritable value : values) {
            sum = sum+value.get();
        }
        context.write(new Text(key),new IntWritable(sum));
    }
}

• CountJob

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.TextOutputFormat;

public class CountJob {
    public static void main(String[]args) throws Exception{
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);
        //设置主类
        job.setJarByClass(CountJob.class);
        //设置reduce
        job.setReducerClass(CountReducer.class);
        //设置map的输出
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);
        //设置reduce的输出
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);

        //多值输入
        MultipleInputs.addInputPath(job,new Path("/data/sequence/hello"), SequenceFileInputFormat.class,CountForSeqMapper.class);
        MultipleInputs.addInputPath(job,new Path("/data/text/a.txt"), TextInputFormat.class,CountForTextMapper.class);
        //输出
        TextOutputFormat.setOutputPath(job, new Path("/data/output"));
        job.waitForCompletion(true);
    }
}