mapreduce执行过程流程图_图解MapReduceMapReduce整体流程图

3.代码实例：

package cn.opensv.hadoop.ch1;

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.LongWritable;

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;

/**

* Hello world!

*

*/

public class WordCount1 {

public static class Map extends        Mapper {

private final static LongWritable one = new LongWritable(1);

private Text word = new Text();

@Override

public void map(LongWritable key, Text value, Context context)

throws IOException, InterruptedException {

String line = value.toString();

StringTokenizer tokenizer = new StringTokenizer(line);

while (tokenizer.hasMoreTokens()) {

word.set(tokenizer.nextToken());

context.write(word, one);

}

}

}

public static class Reduce extends Reducer {

@Override

public void reduce(Text key, Iterable values, Context context)

throws IOException, InterruptedException {

long sum = 0;

for (LongWritable val : values)  {

sum += val.get();

}

context.write(key, new LongWritable(sum));

}

}

public static void main(String[] args) throws Exception {

Configuration cfg = new Configuration();

Job job = new Job(cfg);

job.setJarByClass(WordCount1.class);

job.setJobName("wordcount1"); // 设置一个用户定义的job名称

job.setOutputKeyClass(Text.class); // 为job的输出数据设置Key类

job.setOutputValueClass(LongWritable.class); // 为job输出设置value类

job.setMapperClass(Map.class); // 为job设置Mapper类

job.setCombinerClass(Reduce.class); // 为job设置Combiner类

job.setReducerClass(Reduce.class); // 为job设置Reduce类

FileInputFormat.setInputPaths(job, new Path(args[0]));

FileOutputFormat.setOutputPath(job, new Path(args[1]));

job.waitForCompletion(true);

}

}