Hadoop MapReduce 的基本helloworld程序

本程序实现最简单的MapReduce程序：计算文章的词频统计，wordcount
头文件

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapred.*;

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

其他部分

public class WordCount  {
    public static class Map extends MapReduceBase implements Mapper<LongWritable, Text, Text, IntWritable>{
        private final static IntWritable one = new IntWritable(1);
        private Text word = new Text();
        @Override
        public void map(LongWritable longWritable, Text text, OutputCollector<Text, IntWritable> outputCollector, Reporter reporter) throws IOException {
            String line = text.toString();
            StringTokenizer tokenizer = new StringTokenizer(line);
            while(tokenizer.hasMoreTokens()){
                word.set(tokenizer.nextToken());
                outputCollector.collect(word,one);
            }
        }
    }

    public static class Reduce extends MapReduceBase implements Reducer<Text,IntWritable,Text, IntWritable>{
        @Override
        public void reduce(Text text, Iterator<IntWritable> iterator, OutputCollector<Text, IntWritable> outputCollector, Reporter reporter) throws IOException {
            int sum= 0;
            while(iterator.hasNext()){
                sum += iterator.next().get();
            }
            outputCollector.collect(text, new IntWritable(sum));
        }
    }

    public static void main(String[] args) throws Exception{
        //Configuration conf = new Configuration();

        //Configuration conf=new Configuration();

        JobConf conf = new JobConf(WordCount.class);
        conf.set("fs.defaultFS", "hdfs://localhost:9000");
        conf.set("fs.hdfs.omp", "org.apache.hadoop.hdfs.DistributedFileSystem");
        conf.setJobName("wordCount");
        conf.setOutputKeyClass(Text.class);
        conf.setOutputValueClass(IntWritable.class);
        conf.setMapperClass(Map.class);
        conf.setReducerClass(Reduce.class);
        conf.setInputFormat(TextInputFormat.class);
        conf.setOutputFormat(TextOutputFormat.class);
        FileInputFormat.setInputPaths(conf,new Path("/input/book.txt"));
        FileOutputFormat.setOutputPath(conf, new Path("/output"));
        JobClient.runJob(conf);
    }

}