Hadoop完整代码小程序

前言：Hadoop当时我们弄时几乎没有什么中文文档。现在介绍的资料已经很多了，我就不再赘述。
业务描述：设定inputpath和ouputpath，根据访问日志分析某一个应用访问某一个API的总次数和总流量，统计后分别输出到两个文件中。注意：本案例我是改自阿里巴巴文初的那篇文章，他用的是0.17的版本，现在新的版本有很大的变动，我使用最新的0.20.2来改写了。

public class LogAnalysiser {
	public static class MapClass
			extends
			org.apache.hadoop.mapreduce.Mapper<LongWritable, Text, Text, LongWritable>

	{
		public void map(LongWritable key, Text value,
				OutputCollector<Text, LongWritable> output, Reporter reporter)

		throws IOException

		{
			String line = value.toString();// 没有配置RecordReader，所以默认采用line的实现，key就是行号，value就是行内容

			if (line == null || line.equals(""))

				return;

			String[] words = line.split(",");

			if (words == null || words.length < 8)

				return;

			String appid = words[1];

			String apiName = words[2];

			LongWritable recbytes = new LongWritable(Long.parseLong(words[7]));

			Text record = new Text();

			record.set(new StringBuffer("flow::").append(appid)

			.append("::").append(apiName).toString());

			reporter.progress();

			output.collect(record, recbytes);// 输出流量的统计结果，通过flow::作为前缀来标示。

			record.clear();

			record.set(new StringBuffer("count::").append(appid).append("::")
					.append(apiName).toString());

			output.collect(record, new LongWritable(1));// 输出次数的统计结果，通过count::作为前缀来标示

		}
	}
	public static class PartitionerClass extends
			org.apache.hadoop.mapreduce.Partitioner<Text, LongWritable>

	{
		public int getPartition(Text key, LongWritable value, int numPartitions)

		{

			if (numPartitions >= 2)// Reduce 个数，判断流量还是次数的统计分配到不同的Reduce

				if (key.toString().startsWith("flow::"))

					return 0;
				else
					return 1;
			else

				return 0;
		}

		/*public void configure(JobConf job) {
		}*/
         public void configure(Job job) {
		}
	}

	public static class ReduceClass
			extends
			org.apache.hadoop.mapreduce.Reducer<Text, LongWritable, Text, LongWritable>

	{
		public void reduce(Text key, Iterator<LongWritable> values,

		OutputCollector<Text, LongWritable> output, Reporter reporter)
				throws IOException
		{

			Text newkey = new Text();

			newkey.set(key.toString().substring(
					key.toString().indexOf("::") + 2));

			LongWritable result = new LongWritable();

			long tmp = 0;

			int counter = 0;

			while (values.hasNext())// 累加同一个key的统计结果

			{

				tmp = tmp + values.next().get();

				counter = counter + 1;// 担心处理太久，JobTracker长时间没有收到报告会认为TaskTracker已经失效，因此定时报告一下

				if (counter == 1000)

				{

					counter = 0;

					reporter.progress();

				}

			}

			result.set(tmp);

			output.collect(newkey, result);// 输出最后的汇总结果

		}

	}

	public static class CombinerClass
			extends
			org.apache.hadoop.mapreduce.Reducer<Text, LongWritable, Text, LongWritable>

	{

		public void reduce(Text key, Iterator<LongWritable> values,

		OutputCollector<Text, LongWritable> output, Reporter reporter)
				throws IOException

		{
			LongWritable result = new LongWritable();
			long tmp = 0;
			while (values.hasNext())// 累加同一个key的统计结果
			{

				tmp = tmp + values.next().get();
			}

			result.set(tmp);
		}

	}

	public static void main(String[] args)

	{

		try

		{

			run(args);

		} catch (Exception e)

		{

			e.printStackTrace();

		}

	}

	public static void run(String[] args) throws Exception

	{

		if (args == null || args.length < 2)

		{

			System.out.println("need inputpath and outputpath");

			return;

		}

		String inputpath = args[0];

		String outputpath = args[1];

		String shortin = args[0];

		String shortout = args[1];

		if (shortin.indexOf(File.separator) >= 0)

			shortin = shortin.substring(shortin.lastIndexOf(File.separator));

		if (shortout.indexOf(File.separator) >= 0)

			shortout = shortout.substring(shortout.lastIndexOf(File.separator));

		SimpleDateFormat formater = new SimpleDateFormat("yyyy.MM.dd");

		shortout = new StringBuffer(shortout).append("-")

		.append(formater.format(new Date())).toString();

		if (!shortin.startsWith("/"))

			shortin = "/" + shortin;

		if (!shortout.startsWith("/"))

			shortout = "/" + shortout;

		shortin = "/user/root" + shortin;

		shortout = "/user/root" + shortout;

		File inputdir = new File(inputpath);

		File outputdir = new File(outputpath);

		if (!inputdir.exists() || !inputdir.isDirectory())

		{

			System.out.println("inputpath not exist or isn't dir!");

			return;

		}

		if (!outputdir.exists())

		{

			new File(outputpath).mkdirs();

		}
		Configuration conf = new Configuration();
		Job job = new Job(conf, "analysis job");
		job.setJarByClass(LogAnalysiser.class);
		// JobConf conf = new JobConf(new Configuration(),
		// LogAnalysiser.class);// 构建Config

		FileSystem fileSys = FileSystem.get(conf);

		fileSys.copyFromLocalFile(new Path(inputpath), new Path(shortin));// 将本地文件系统的文件拷贝到HDFS中

		job.setJobName("analysisjob");

		job.setOutputKeyClass(Text.class);// 输出的key类型，在OutputFormat会检查

		job.setOutputValueClass(LongWritable.class); // 输出的value类型，在OutputFormat会检查

		job.setMapperClass(MapClass.class);

		job.setCombinerClass(CombinerClass.class);

		job.setReducerClass(ReduceClass.class);

		job.setPartitionerClass(PartitionerClass.class);

		// job.set("mapred.reduce.tasks", "2");//老版本中的写法
		// 强制需要有两个Reduce来分别处理流量和次数的统计,现在的版本中已经没有这个方法了
		job.setNumReduceTasks(2);//新版本0.22.x中的方法
		FileInputFormat.setInputPaths(job, shortin);// hdfs中的输入路径

		FileOutputFormat.setOutputPath(job, new Path(shortout));// hdfs中输出路径

		Date startTime = new Date();

		System.out.println("Job started: " + startTime);

		// JobClient.runJob(job);

		Date end_time = new Date();

		System.out.println("Job ended: " + end_time);

		System.out.println("The job took "
				+ (end_time.getTime() - startTime.getTime()) / 1000
				+ " seconds.");

		// 删除输入和输出的临时文件

		fileSys.copyToLocalFile(new Path(shortout), new Path(outputpath));

		fileSys.delete(new Path(shortin), true);

		fileSys.delete(new Path(shortout), true);

	}
}

//执行类
public class ExampleDriver {

  public static void main(String argv[]){

    ProgramDriver pgd = new ProgramDriver();

    try {

      pgd.addClass("analysislog", LogAnalysiser.class, "A map/reduce program that analysis log .");

      pgd.driver(argv);

    }

    catch(Throwable e){

      e.printStackTrace();

    }

  }

}

完整的代码能补上传一个啊，我也在研究这个，刚刚照着文档在虚拟机下开了集群。程序还不是很清楚怎么写，哈哈

这个东西还在研究中。

这个东西用什么用，用在什么场景中？

建议楼主把代码以附件的形式给出, 多点文字.

曾经自己看过hadoop相关的书，但是感觉有纸上谈兵的感觉；毕竟没有比较大的应用平台的话，看再多的资料也不见得有用；建议先读一下google的那篇论文，了解一下MapReduce的思想；然后怎样学习，怎样练习，大家不妨一起讨论一下。

那些是基本，做之前当然要先看

谢谢,几个小问题:
1、Mapper 和 Reducer为什么还用的是0.19的版本呢,job倒是0.2的版本了
2、map里不要用split, StringTokenizer都很少用,效率太低,一般只用indexOf,效率提高20倍.
3、你这个例子比较特殊 combiner和reducer执行了同样的操作,那还有必要写combiner吗? 而且造成误解, 让人以为combiner和reducer一样就行了,那复杂点的mapreduce必然会出错.

那个count=count+1防止taskrunner报错的小窍门, 特别好.