Hadoop学习笔记0004——eclipse安装hadoop插件

注意：如果没有DFSLocations项，就新建一个Map/ReduceProject工程；

8、测试

 （1）在HDFS上创建目录input

hadoop fs -mkdir input

hadoop fs -put /usr /hadoop/README.txt input

（ 3）新建WordCount项目

File—>Project，选择Map/Reduce Project，输入项目名称WordCount等。

    在WordCount项目里新建class，名称为WordCount，代码如下：

package com.hadoop.test;

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);
	}
}

（4）点击WordCount.java，右键，点击Run As—>RunConfigurations，配置运行参数，即输入和输出文件夹hdfs://192.168.0.134:9000/user/root/inputhdfs://192.168.0.134:9000/user/root/output

点击Run按钮，运行程序。

展开DFS Locations，如下图所示，双击打开part-r00000查看结果

5..到工程的输出目录找到class文件，会有两个class文件，因为FileUtil.java有内部类;

6.将该class文件添加到hadoop-core-1.2.1.jar中对应的目录，覆盖原文件;