mapreduce 顺序组合

标签：

import java.io.IOException;
import java.util.StringTokenizer;

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.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.GenericOptionsParser;

public class Driver {

    public static class TokenizerMapper extends
            Mapper<Object, Text, Text, IntWritable> {
        private final static IntWritable one = new IntWritable(1);
        private Text word = new Text();
        public void map(Object key, Text value, Context context)
                throws IOException, InterruptedException {
            StringTokenizer itr = new StringTokenizer(value.toString());
            while (itr.hasMoreTokens()) {
                word.set(itr.nextToken());
                context.write(word, one);
            }
        }
    }

    public static class IntSumReducer extends
            Reducer<Text, IntWritable, Text, IntWritable> {
        private IntWritable result = new IntWritable();
        public void reduce(Text key, Iterable<IntWritable> values,
                Context context) throws IOException, InterruptedException {
            int sum = 0;
            for (IntWritable val : values) {
                sum += val.get();
            }
            result.set(sum);
            context.write(key, result);
        }
    }

    public static class SequenceMapper extends
            Mapper<Object, Text, Text, Text> {
        private Text word = new Text();
        public void map(Object key, Text value, Context context)
                throws IOException, InterruptedException {
            String []sep=value.toString().split("\t");
            word.set(sep[1]+"\t"+sep[0]);
            System.out.println(value.toString());
            context.write(word,new Text(""));
        }
    }

    public static class SequenceReducer extends
            Reducer<Text,Text,Text,Text> {
        public void reduce(Text key, Iterable<Text> values,
                Context context) throws IOException, InterruptedException {
            String[] sep = key.toString().split("\t");
            System.out.println( sep[0]+"++++++++="+ sep[1]);
            context.write(key,new Text(""));
        }
    }

    public static void main(String[] args) throws Exception {
        Configuration conf = new Configuration();
        String[] otherArgs = new GenericOptionsParser(conf, args)
                .getRemainingArgs();
        if (otherArgs.length < 2) {
            System.err.println("Usage: wordcount <in> <out>");
            System.exit(2);
        }
        Job job = new Job(conf, "word count");
        job.setJarByClass(Driver.class);
        job.setMapperClass(TokenizerMapper.class);
        job.setCombinerClass(IntSumReducer.class);
        job.setReducerClass(IntSumReducer.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);
        FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
        FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
        job.waitForCompletion(true);

        Configuration conf2 = new Configuration();
        Job job2 = new Job(conf2, "word count1");
        job2.setJarByClass(Driver.class);
        job2.setMapperClass(SequenceMapper.class);
        job2.setReducerClass(SequenceReducer.class);
        job2.setOutputKeyClass(Text.class);
        job2.setOutputValueClass(Text.class);
        FileInputFormat.addInputPath(job2, new Path(otherArgs[1]));
        FileOutputFormat.setOutputPath(job2, new Path(otherArgs[2]));
        job2.waitForCompletion(true);
    }
}

mapreduce 顺序组合

标签：

原文地址：http://www.cnblogs.com/1130136248wlxk/p/5011140.html