[Hadoop]基于Eclipse的Hadoop应用开发环境配置

1. 安装Eclipse
   下载Eclipse（点击进入下载），解压安装。我安装在/usr/local/software/目录下。

   

2. 在eclipse上安装hadoop插件

   下载hadoop插件（点击进入下载） 把插件放到eclipse/plugins目录下。

3. 重启eclipse，配置hadoop installation directory

   如果安装插件成功，打开Window–>Preferens，你会发现Hadoop Map/Reduce选项，在这个选项里你需要配置Hadoop installation directory。配置完成后退出。

   

4. 配置Map/Reduce Locations

   在Window–>Show View中打开Map/Reduce Locations。

   

   

   在Map/Reduce Locations中新建一个Hadoop Location。在这个View中，右键–>New Hadoop Location。在弹出的对话框中你需要配置Location name，如Hadoop1.0，还有Map/Reduce Master和DFS Master。这里面的Host、Port分别为你在mapred-site.xml、core-site.xml中配置的地址及端口。如：
   Map/Reduce Master

   192.168.239.130
   9001
   

   DFS Master

   192.168.239.130
   9000
   

   

   配置完后退出。点击DFS Locations–>Hadoop如果能显示文件夹(2)说明配置正确，如果显示”拒绝连接”，请检查你的配置。

   

5. 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 WordCount;

import java.io.IOException;
import java.util.StringTokenizer;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
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;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;



public class WordCount extends Configured implements Tool{
    /**
     * 
     * @author root
     *
     */
    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);
            }// while
        }// map
    }// mapper
    /**
     * 
     * @author root
     *
     */
    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();
            }//for

            result.set(sum);
            context.write(key, result);
        }// reduce 
    }// reducer
    /**
     * 
     * @param args
     * @return
     * @throws Exception
     */
    public int run(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 name
        Job job = new Job(conf, "word count");
        // class 
        job.setJarByClass(WordCount.class);
        // mapper
        job.setMapperClass(TokenizerMapper.class);
        // combiner
        job.setCombinerClass(IntSumReducer.class);
        // reducer
        job.setReducerClass(IntSumReducer.class);
        // output key format
        job.setOutputKeyClass(Text.class);
        // outout value format
        job.setOutputValueClass(IntWritable.class);
        // input path
        FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
        // output path
        FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));

        job.waitForCompletion(true);

        return job.isSuccessful() ? 0: 1;
    }
    /**
     * 
     * @param args
     * @throws Exception
     */
    public static void main(String[] args) throws Exception {
        int res = ToolRunner.run(new Configuration(), new WordCount(), args);
        System.exit(res);
    }
}