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。
 (3)选择window -> open perspective -> Other... , 选择有大象图标的 Map/Reduce,此时,就打开了Map/Reduce的开发环境。可以看到,右下角多了一个Map/Reduce Locations的框。如下图
 Map/Reduce Master (此处为Hadoop集群的Map/Reduce地址,应该和mapred-site.xml中的mapred.job.tracker设置相同)
 
  /**
   *  Licensed under the Apache License, Version 2.0 (the "License");
   *  you may not use this file except in compliance with the License.
   *  You may obtain a copy of the License at
   *
   *      http://www.apache.org/licenses/LICENSE-2.0
   *
   *  Unless required by applicable law or agreed to in writing, software
   *  distributed under the License is distributed on an "AS IS" BASIS,
   *  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
   *  See the License for the specific language governing permissions and
   *  limitations under the License.
   */
     
     
  package com.jialin.hadoop;
     
  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 {
      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 job = new Job(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);
      FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
      FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
      System.exit(job.waitForCompletion(true) ? 0 : 1);
    }
  }
 
 这个问题真是纠结了我好几天,最后修还hadoop源码hadoop-core-1.2.0.jar中的FileUtil,重新编译 hadoop-core-1.2.0.jar ,替换掉原来的。才得以解决
 至此高校云平台的hadoop集群基本开发环境已经出来了,剩下的就是在此基础上进行丰富了。如果是简单的测试,推荐使用单机hadoop方式,或者伪分布式。我之所以不选择单机或伪分布式,只是想尽可能地模拟真实环境。大家按需选择吧。