hadoop MapReduce WordCount简单版java代码

xiayu

　　package com.hadoop;
　　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.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.input.TextInputFormat;  
　　import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;  
　　import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;

　　public>　　//映射类 WordCountMap map

　　public static>　　private final IntWritable one = new IntWritable(1);  
　　private Text word = new Text();  
　　public void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {  
　　String line = value.toString();  
　　StringTokenizer token = new StringTokenizer(line);  
　　while (token.hasMoreTokens()) {  
　　word.set(token.nextToken());  
　　context.write(word, one);  
　　}  
　　}  
　　}  
　　//归约类 WordCountReduce reduce

　　public static>　　public void reduce(Text key, Iterable<IntWritable> values,  
　　Context context) throws IOException, InterruptedException {  
　　int sum = 0;  
　　for (IntWritable val : values) {  
　　sum += val.get();  
　　}  
　　context.write(key, new IntWritable(sum));  
　　}  
　　}  
　　public static void main(String[] args) throws Exception {  
　　//hadoop配置文件
　　Configuration conf = new Configuration();  
　　//任务，将配置文件装载到任务中
　　Job job = new Job(conf);  
　　job.setJarByClass(WordCount.class);  
　　job.setJobName("wordcount");  
　　job.setOutputKeyClass(Text.class);  
　　job.setOutputValueClass(IntWritable.class);  
　　job.setMapperClass(WordCountMap.class);  
　　job.setReducerClass(WordCountReduce.class);  
　　job.setInputFormatClass(TextInputFormat.class);  
　　job.setOutputFormatClass(TextOutputFormat.class);  
　　FileInputFormat.addInputPath(job, new Path("/input"));  
　　FileOutputFormat.setOutputPath(job, new Path("/output"));  
　　job.waitForCompletion(true);  
　　}
　　}