mapreduce读取sequencefile文件中的数据

 sequencefile中的数据是以key，value对存储的。

 通过mapreduce模式，可以读取sequencefile中的数据。

 public class MapReduceReadFile {

     private static SequenceFile.Reader reader = null;
     private static Configuration conf = new Configuration();

     public static class ReadFileMapper extends
             Mapper<LongWritable, Text, LongWritable, Text> {

         /* (non-Javadoc)
          * @see org.apache.hadoop.mapreduce.Mapper#map(KEYIN, VALUEIN, org.apache.hadoop.mapreduce.Mapper.Context)
          */
         @Override
         public void map(LongWritable key, Text value, Context context) {
             key = (LongWritable) ReflectionUtils.newInstance(
                     reader.getKeyClass(), conf);
             value = (Text) ReflectionUtils.newInstance(
                     reader.getValueClass(), conf);
             try {
                 while (reader.next(key, value)) {
                     System.out.printf("%s\t%s\n", key, value);
                     context.write(key, value);
                 }
             } catch (IOException e1) {
                 e1.printStackTrace();
             } catch (InterruptedException e) {
                 e.printStackTrace();
             }
         }

     }
     /**
      * @param args
      * @throws IOException
      * @throws InterruptedException
      * @throws ClassNotFoundException
      */
     public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException {

         Job job = new Job(conf,"read seq file");
         job.setJarByClass(MapReduceReadFile.class);
         job.setMapperClass(ReadFileMapper.class);
         job.setMapOutputValueClass(Text.class);
         Path path = new Path("logfile2");
         FileSystem fs = FileSystem.get(conf);
         reader = new SequenceFile.Reader(fs, path, conf);
         FileInputFormat.addInputPath(job, path);
         FileOutputFormat.setOutputPath(job, new Path("result"));
         System.exit(job.waitForCompletion(true)?0:1);
     }