hadoop wordcount-蒲公英云

hadoop wordcount

在hdfs上的文本内容如下

hello world hello java
hello c
hello hadoop map reduce

以下是自己对这个过程的总结

mapreduce执行的流程 input<k1,v1> -> map -><k2,v2> -> <k2,list<v2>> ->reduce<k3,v3> ->output 具体的步骤: map输入 <0,hello world hello java> <22, hello c> <29, hello hadoop map reduce> map输出 <hello,1> <world,1> <hello,1> <java, 1> <hello,1 > <c, 1> <hello, 1> <hadoop , 1> <map, 1> <reduce, 1> 进行shuffle 对map的输出进行排序分组 shuffle处理后 <hello, <1,1,1,1>> <world, <1>> <java, <1>> <c, <1>>... reduce 接受shuffle后的kv，遍历v的列表，进行求和 结果： <hello, 4> <world,1>... output到hdfs

代码

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;
public class WordCount { 
 /** * * map： * 将一行句子， 以空格切分 进行输出 <一个单词, 1> * @author hadoop * */
  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 {
      //String[] strs = value.toString().split("");
      StringTokenizer itr = new StringTokenizer(value.toString());
      while (itr.hasMoreTokens()) {
        word.set(itr.nextToken());
        context.write(word, one);
      }
    }
  }
  /** * reduce功能 * 接受map的数据(中间有shuffle过程) * 计数 * @author hadoop * */
  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 void main(String[] args) throws Exception {
    Configuration conf = new Configuration();
    Job job = Job.getInstance(conf, "word count");
    //设置主要的工作类
    job.setJarByClass(WordCount.class);
    //设置输入输出路径
    FileInputFormat.addInputPath(job, new Path(args[0]));
    FileOutputFormat.setOutputPath(job, new Path(args[1]));
    //设置map和reduce类
    job.setMapperClass(TokenizerMapper.class);  
    job.setReducerClass(IntSumReducer.class);
    //设置输出k， v 格式
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(IntWritable.class);
    //job.setCombinerClass(IntSumReducer.class); 
    //运行任务
    System.exit(job.waitForCompletion(true) ? 0 : 1);
  }
}