linux+eclipse+本地执行WordCount抛出下面异常:

Exception in thread "main" java.lang.NoClassDefFoundError: org/apache/hadoop/yarn/util/Apps。

解决:没有把yarn下的包以及yarn 下的lib目录下的包导入

package cn.itheima.bigdata.hadoop.mr.wordcount;

import java.io.IOException;

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.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

/**
 * 用来描述一个作业job(使用哪个mapper类,哪个reducer类,输入文件在哪,输出结果放哪。。。。)
 * 然后提交这个job给hadoop集群
 * @author duanhaitao@itcast.cn
 *
 */
//cn.itheima.bigdata.hadoop.mr.wordcount.WordCountRunner
public class WordCountRunner {

	public static void main(String[] args) throws Exception {
		Configuration conf = new Configuration();
		Job wcjob = Job.getInstance(conf);
		//设置job所使用的jar包
		conf.set("mapreduce.job.jar", "wcount.jar");
		
		//设置wcjob中的资源所在的jar包
		wcjob.setJarByClass(WordCountRunner.class);
		
		
		//wcjob要使用哪个mapper类
		wcjob.setMapperClass(WordCountMapper.class);
		//wcjob要使用哪个reducer类
		wcjob.setReducerClass(WordCountReducer.class);
		
		//wcjob的mapper类输出的kv数据类型
		wcjob.setMapOutputKeyClass(Text.class);
		wcjob.setMapOutputValueClass(LongWritable.class);
		
		//wcjob的reducer类输出的kv数据类型
		wcjob.setOutputKeyClass(Text.class);
		wcjob.setOutputValueClass(LongWritable.class);
		
		//指定要处理的原始数据所存放的路径
		FileInputFormat.setInputPaths(wcjob, "hdfs://yun12-01:9000/wc/srcdata");
	
		//指定处理之后的结果输出到哪个路径
		FileOutputFormat.setOutputPath(wcjob, new Path("hdfs://yun12-01:9000/wc/output"));
		
		boolean res = wcjob.waitForCompletion(true);
		
		System.exit(res?0:1);
		
		
	}
	
	
	
}
package cn.itheima.bigdata.hadoop.mr.wordcount;

import java.io.IOException;

import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

public class WordCountReducer extends Reducer<Text, LongWritable, Text, LongWritable>{
	
	
	// key: hello ,  values : {1,1,1,1,1.....}
	@Override
	protected void reduce(Text key, Iterable<LongWritable> values,Context context)
			throws IOException, InterruptedException {
		
		//定义一个累加计数器
		long count = 0;
		for(LongWritable value:values){
			
			count += value.get();
			
		}
		
		//输出<单词:count>键值对
		context.write(key, new LongWritable(count));
		
	}
	
	

}

package cn.itheima.bigdata.hadoop.mr.wordcount;

import java.io.IOException;

import org.apache.commons.lang.StringUtils;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

public class WordCountMapper extends Mapper<LongWritable, Text, Text, LongWritable>{
	
	@Override
	protected void map(LongWritable key, Text value,Context context)
			throws IOException, InterruptedException {

		//获取到一行文件的内容
		String line = value.toString();
		//切分这一行的内容为一个单词数组
		String[] words = StringUtils.split(line, " ");
		//遍历输出  <word,1>
		for(String word:words){
			
			context.write(new Text(word), new LongWritable(1));
			
		}
		
		
		
		
	}
	
	
	
	

}



GitHub 加速计划 / li / linux-dash
10.39 K
1.2 K
下载
A beautiful web dashboard for Linux
最近提交(Master分支:2 个月前 )
186a802e added ecosystem file for PM2 4 年前
5def40a3 Add host customization support for the NodeJS version 4 年前
Logo

旨在为数千万中国开发者提供一个无缝且高效的云端环境,以支持学习、使用和贡献开源项目。

更多推荐