Windows下Eclipse安裝Hadoop插件

一、下載hadoop-eclipse-plugin-2.7.3插件，並解壓

二、將hadoop-eclipse-plugin-2.7.3.jar拷貝到${ECLIPSE_HOME}下的plugins文件夾，

     並重啓eclipse，便可出現如下視圖：

    

三、將hadoop-eclipse-plugin-2.7.3下的bin目錄全部文件拷貝到window下的Hadoop目錄下的bin目錄中

四、同時將bin目錄下的hadoop.dll拷貝到C:\windows\system32目錄下

五、eclipse配置hadoop安裝目錄

    

六、建立Hadoop Location

    

七、運行WordCount實例

    1. 建立輸入目錄input，並上傳數據文件input.txt，不可建立輸出文件夾，否則會報錯。

    

    2. 配置運行參數（以下圖），最後點擊run便可

        說明：input指的的文件夾，直接掛在"/"目錄下，與hdfs://192.168.241.129:9000/input對應

    

3. 輸入結果以下圖

    

4. 附：WordCount.java源碼

package com.hadoop.example;

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 {
		System.setProperty("HADOOP_USER_NAME", "root");
		System.setProperty("hadoop.home.dir", "D:/install/hadoop-2.7.3");
//		System.setProperty("yarn.resourcemanager.address", "master:8032");
		System.setProperty("yarn.resourcemanager.hostname", "master");
		Configuration conf = new Configuration();
		String[] otherArgs = new GenericOptionsParser(conf, args)
				.getRemainingArgs();
		if (otherArgs.length < 2) {
			System.err.println("Usage: wordcount <in> [<in>...] <out>");
			System.exit(2);
		}
		Job job = Job.getInstance(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);
		for (int i = 0; i < otherArgs.length - 1; ++i) {
			FileInputFormat.addInputPath(job, new Path(otherArgs[i]));
		}
		FileOutputFormat.setOutputPath(job, new Path(
				otherArgs[otherArgs.length - 1]));
		System.exit(job.waitForCompletion(true) ? 0 : 1);
	}
}

五、可打成Runnable JarFile包運行

#可運行包執行命令：hadoop jar {jar} {input} {output}
hadoop jar WordCount.jar hdfs://192.168.241.129:9000/input hdfs://192.168.241.129:9000/output