windows下使用eclipse开发hadoop

标签：

一. 配置hadoop插件

1. 安装插件

将hadoop-eclipse-plugin-1.1.2.jar复制到eclipse/plugins目录下，重启eclipse

2. 打开MapReduce视图

window -> open perspective -> other 选择Map/Reduce 图标是一个蓝色的象

3. 添加一个MapReduce环境

在eclipse下端，控制台旁边会多一个Tab “Map/Reduce Locations”, 在下面空白的地方点右键，选择“New Hadoop location”，配置如下：

Location name(起一个名字)

Map/Reduce Master (Job Tracker的IP和端口，根据mapred-site.xml配置的mapred.job.tracker来填写)

DFS Master (Name Node的IP和端口，根据core-site.xml中配置的fs.default.name来填写)

4. 使用eclipse对HDFS内容进行修改

经过上一步骤，左侧“Project Explorer”中会出现配置好的HDFS，点击右键，可以进行新建文件，删除文件等操作。

注意：每一次操作完在eclipse中不能马上显示变化，必须得刷新一下。

二. 开发hadoop程序

1. WordCount.java

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 {
		// 使用程序生成临时jar文件
		File jarFile = EJob.createTempJar("bin");
		EJob.addClasspath("/cloud/hadoop/conf");
		ClassLoader classLoader = EJob.getClassLoader();
		Thread.currentThread().setContextClassLoader(classLoader);

		// 设置hadoop配置参数
		Configuration conf = new Configuration();
		conf.set("fs.default.name", "hdfs://hadoop001:9000");  
		conf.set("hadoop.job.user", "root");  
		conf.set("mapred.job.tracker", "hadoop001:9001");

		Job job = new Job(conf, "word count");
		((JobConf) job.getConfiguration()).setJar(jarFile.toString());
		job.setJarByClass(WordCount.class);
		job.setMapperClass(TokenizerMapper.class);
		job.setCombinerClass(IntSumReducer.class);
		job.setReducerClass(IntSumReducer.class);
		job.setOutputKeyClass(Text.class);
		job.setOutputValueClass(IntWritable.class);
		
		String input = "hdfs://hadoop001:9000/user/root/tmp_file_1";
		String output = "hdfs://hadoop001:9000/user/root/tmp_file_2";
		FileInputFormat.addInputPath(job, new Path(input));
		FileOutputFormat.setOutputPath(job, new Path(output));
		System.exit(job.waitForCompletion(true) ? 0 : 1);
	}
}

// 生成临时jar文件的类
public class EJob {

	// To declare global field
	private static List<URL> classPath = new ArrayList<URL>();

	// To declare method
	public static File createTempJar(String root) throws IOException {
		if (!new File(root).exists()) {
			return null;
		}
		Manifest manifest = new Manifest();
		manifest.getMainAttributes().putValue("Manifest-Version", "1.0");
		final File jarFile = File.createTempFile("EJob-", ".jar", new File(
				System.getProperty("java.io.tmpdir")));

		Runtime.getRuntime().addShutdownHook(new Thread() {
			public void run() {
				jarFile.delete();
			}
		});

		JarOutputStream out = new JarOutputStream(
				new FileOutputStream(jarFile), manifest);
		createTempJarInner(out, new File(root), "");
		out.flush();
		out.close();
		return jarFile;
	}

	private static void createTempJarInner(JarOutputStream out, File f,
			String base) throws IOException {
		if (f.isDirectory()) {
			File[] fl = f.listFiles();
			if (base.length() > 0) {
				base = base + "/";
			}
			for (int i = 0; i < fl.length; i++) {
				createTempJarInner(out, fl[i], base + fl[i].getName());
			}
		} else {
			out.putNextEntry(new JarEntry(base));
			FileInputStream in = new FileInputStream(f);
			byte[] buffer = new byte[1024];
			int n = in.read(buffer);
			while (n != -1) {
				out.write(buffer, 0, n);
				n = in.read(buffer);
			}
			in.close();
		}
	}

	public static ClassLoader getClassLoader() {
		ClassLoader parent = Thread.currentThread().getContextClassLoader();
		if (parent == null) {
			parent = EJob.class.getClassLoader();
		}
		if (parent == null) {
			parent = ClassLoader.getSystemClassLoader();
		}
		return new URLClassLoader(classPath.toArray(new URL[0]), parent);
	}

	public static void addClasspath(String component) {

		if ((component != null) && (component.length() > 0)) {
			try {
				File f = new File(component);

				if (f.exists()) {
					URL key = f.getCanonicalFile().toURL();
					if (!classPath.contains(key)) {
						classPath.add(key);
					}
				}
			} catch (IOException e) {
			}
		}
	}

}

windows下使用eclipse开发hadoop

标签：

原文地址：http://blog.csdn.net/zdp072/article/details/43094821