您的位置:首页 > 运维架构

hadoop wordcount

2014-03-09 14:03 148 查看
寒假的时候写的,就是忘了保存。。今天找了好久才找出来,好吧。。有用的东西得记得保存。。

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;
import org.apache.hadoop.util.GenericOptionsParser;
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();//Text 实现了BinaryComparable类可以作为key值
public void map(Object key, Text value, Context context) throws IOException, InterruptedException {
StringTokenizer itr = new StringTokenizer(value.toString());//得到什么值
System.out.println("value什么东西 : "+value.toString());
System.out.println("key什么东西 : "+key.toString());

while (itr.hasMoreTokens()) {
word.set(itr.nextToken());
context.write(word, one);
}
}
}
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();
conf.set("mapred.job.tracker", "192.168.0.31:54311");
String[] ars=new String[]{"input","output"};
String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
if (otherArgs.length != 2) {
System.err.println("Usage: wordcount <in> <out>");
System.exit(2);
}
// JobConf conf1 = new JobConf(WordCount.class);
Job job = new Job(conf, "word count");//Job(Configuration conf, String jobName) 设置job名称和
job.setJarByClass(wordcount.class);
job.setMapperClass(TokenizerMapper.class); //为job设置Mapper类
job.setCombinerClass(IntSumReducer.class); //为job设置Combiner类
job.setReducerClass(IntSumReducer.class); //为job设置Reduce类
job.setOutputKeyClass(Text.class);        //设置输出key的类型
job.setOutputValueClass(IntWritable.class);//  设置输出value的类型
FileInputFormat.addInputPath(job, new Path(otherArgs[0])); //为map-reduce任务设置InputFormat实现类   设置输入路径
FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));//为map-reduce任务设置OutputFormat实现类  设置输出路径
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}
内容来自用户分享和网络整理,不保证内容的准确性,如有侵权内容,可联系管理员处理 点击这里给我发消息
标签: