package com.test.wordcount;
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 {
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);
}
// String str=new String(value.toString());
// String[] arr=str.split(" ");
// for(int i=0;i<arr.length;i++)
// {
// word.set(arr[i]);
// context.write(word, one);
// }
}
}
public static class TokenizerReducer 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");
// Job job=new Job(conf,"word count");
job.setJarByClass(WordCount.class);
job.setMapperClass(TokenizerMapper.class);
job.setCombinerClass(TokenizerReducer.class);
job.setReducerClass(TokenizerReducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
FileInputFormat.addInputPath(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
System.exit(job.waitForCompletion(true)?0:1);
}
}
源码出自:《hadoop实战》
hadoop实战之单词计数WordCount源码
最新推荐文章于 2023-12-16 07:00:00 发布