搭建基于eclipse的hadoop开发环境的笔记

最新推荐文章于 2020-02-17 00:07:13 发布

原创最新推荐文章于 2020-02-17 00:07:13 发布 · 551 阅读

0 ·

CC 4.0 BY-SA版权

hadoop 专栏收录该内容

5 篇文章

订阅专栏

本文详细介绍了如何解决Java WordCount程序中常见的错误，并提供了代码实现。包括如何启动Hadoop NameNode、处理已存在的输出文件夹问题以及程序的运行流程。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

常见问题：

1)Error:Call to localhost/127.0.0.1:9001 failed on connection exception:java.net.ConnectException: Connection refused

看看namenode是否启动，若没有，重新格式化一下 $bin/hadoop namenode -format，再启动。

2)out输出文件夹若已经存在，必须保证它为空，否则会出错。解决方法是要么删掉这个文件夹要么清空它。

WordCount.java

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();

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 );
}
}
}

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();
String[] otherArgs = new GenericOptionsParser(conf,
args).getRemainingArgs();
if (otherArgs.length != 2) {
System.err .println("Usage: wordcount <in> <out>");
System.exit(2);
}
Job job = new Job(conf, "word count");
job.setJarByClass(WordCount. class );
job.setMapperClass(TokenizerMapper. class );
job.setCombinerClass(IntSumReducer. class );
job.setReducerClass(IntSumReducer.class );
job.setOutputKeyClass(Text.class );
job.setOutputValueClass(IntWritable.class );
FileInputFormat. addInputPath(job, new Path(otherArgs[0]));
FileOutputFormat.setOutputPath (job, new Path(otherArgs[1]));
System.exit(job.waitForCompletion( true) ? 0 : 1);
}
}