hadoop学习过程-2013.08.22.2--hadoop1.2.1修改WordCount并编译

最新推荐文章于 2022-02-09 20:04:37 发布

prg1986

最新推荐文章于 2022-02-09 20:04:37 发布

阅读量1.2k

点赞数

分类专栏： hadoop 文章标签： hadoop wordcount

本文链接：https://blog.csdn.net/prg1986/article/details/10474347

版权

hadoop 专栏收录该内容

5 篇文章 0 订阅

订阅专栏

这篇博客详细介绍了如何在Hadoop 1.2.1环境下修改并编译WordCount示例。首先，展示了修改后的WordCount代码，接着列举了编译所需依赖的jar包，包括hadoop-core-1.2.1.jar和commons-cli-1.2.jar。然后，说明了如何在Eclipse中创建Java项目，导入代码和jar文件，并导出为wordcount.jar。最后，提供了在Hadoop集群上运行该jar包的命令，并提示参考相关运行步骤。

摘要由CSDN通过智能技术生成

hadoop1.2.1修改WordCount并编译

1. 代码:

package org.apache.hadoop.examples;

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 {
			System.out.print("(" + key + ":" + value + ") ---map---> [");
			StringTokenizer itr = new StringTokenizer(value.toString());
			while (itr.hasMoreTokens()) {
				word.set(itr.nextToken());
				System.out.print("(" + word + ":" + one + "), ");
				context.write(word, one);
			}
			System.out.println("]");
		}
	}

	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 {
			String vals="#";
			int sum = 0;
			for (IntWritable val : values) {
				vals+=(val+",");
				sum += val.get();
			}
			vals+="#";
			System.out.print("(" + key+":" +vals+ ") ---reduce---> ");
			
			result.set(sum);
			System.out.println("(" + key + ":" + result+ ")");
			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);
	}
}