eclipse中配置hadoop超详细操作流程

首先下载eclipse的插件，下载链接有

https://github.com/HuangDongdong666/Hadoop-eclipse-plugin-2.8.3

https://github.com/winghc/hadoop2x-eclipse-plugin/tree/master/release

下载完之后，根据eclipse版本的不同，旧版本放在plugins这个文件夹下，新版本的，我的就是重装之后的eclipse就是放在dropins这个文件夹下。然后重开eclipse。

开启eclipse之后，点击help->install->add,输入hadoop-plungin，确定，之后可以在manager看到如下图所示的。(ok后勾选确定，可能会会有警告，忽略,重启eclipse即可)

打开Window->Preferences->HadoopMap/Reduce,，然后在dircetory输入你从虚拟机拉过来的已经解压的Hadoop文件夹!

接着，window->show view->others，弹出的窗口中选择Map/Reduce Locations，即可看到Map/Reduce的控制界面。在该页面右键new一个Hadoop Location，这是我的配置。

下载文件inutils.exe 和 winutils.exe

https://github.com/steveloughran/winutils(下载和自己hadoop版本一样的,或者接近的（<=自己的版本）)

下载了winutils.exe文件和hadoop.dll之后放入\hadoop-2.7.5\bin文件夹中

另外还要把hadoop.dll放在C:\Windows\System32文件夹下

接着，先测试下你的虚拟机和你的windows能不能连接上，如果用户对hadoop目录并没有写入权限，会导致异常的发生，命令如下 ：hdfs dfs -chmod -R 777 /，在左边Project Explorer能看的你的hdfs结构，然后就开始编代码吧。

（操作如下）

在主函数编写job时，要注意自己的端口号是多少。

问题总结：

（1）Could not locate Hadoop executable: D:\Program Files\hadoop-3.0.0\bin\winutils.exe

下载文件inutils.exe 和 winutils.exe

https://github.com/steveloughran/winutils

下载了winutils.exe文件和hadoop.dll之后放入\hadoop-2.7.5\bin文件夹中。

（2）如果用户对hadoop目录并没有写入权限，会导致异常的发生，命令如下 ：hdfs dfs -chmod -R 777 /

(3)异常Exception in thread "main" java.lang.UnsatisfiedLinkError: org.apache.hadoop.io.nativeio.NativeIO$Windows.access0(Ljava/lang/String;I)Z

https://blog.csdn.net/congcong68/article/details/42043093

(4)hadoop关于org.apache.hadoop.security.AccessControlException: Permission denied: user=Administrator, ac

https://blog.csdn.net/lunhuishizhe/article/details/50489849

(5)Hadoop Hdfs常用命令

(6)https://blog.csdn.net/sunshingheavy/article/details/53227581

hadoop测试样例

http://younglibin.iteye.com/blog/1925008

最后贴上本人的测试代码

package com.cby.test;

import java.io.File;
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 {

		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 {
		private IntWritable result = new IntWritable();

		public void reduce(Text key, Iterable values, Context context)
				throws IOException, InterruptedException {
			int sum = 0;
			for (IntWritable val : values) {
				sum += val.get();
			}
			result.set(sum);
			context.write(key, result);
		}
	}

//	static {
//		try {
//			System.load("D:/Program Files/hadoop-3.0.0/bin/hadoop.dll");
//		} catch (UnsatisfiedLinkError e) {
//			System.err.println("Native code library failed to load.\n" + e);
//			System.exit(1);
//		}
//	}

	public static void main(String[] args) throws Exception {
		Configuration conf = new Configuration();
		// conf.set("mapred.job.tracker", "192.168.247.130:9001");
		System.setProperty("hadoop.home.dir", "D:/Program Files/hadoop-3.0.0");
		args = new String[] { "/user/root/input", "/user/root/output1" };
		String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
		System.out.println(otherArgs.length);
		if (otherArgs.length != 2) {
			System.err.println("Usage: wordcount  ");
			System.out.println("测试结束");
			System.exit(2);
		}
		// conf.set("fs.defaultFS", "hdfs://192.168.6.77:9000");
		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);
		// 8020端口是fs.defaultFS的配置端口,一般默认为9000
		FileInputFormat.addInputPath(job, new Path("hdfs://192.168.247.130:8020" + otherArgs[0]));
		FileOutputFormat.setOutputPath(job, new Path("hdfs://192.168.247.130:8020" + otherArgs[1]));
		System.exit(job.waitForCompletion(true)  0 : 1);

	}
}