hadoop自定义多文件及多文件夹输出

      博主用的是hadoop1.0.4版本。实现多文件及多文件夹输出主要用到MultipleOutputs这个类。这是包路径 org.apache.hadoop.mapreduce.lib.output。偏好用最简单的例子分举例分析如下：

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 MultipleOutputs<Text,IntWritable> mos;
        protected void setup(Context context) throws IOException,InterruptedException {
            mos = new MultipleOutputs<Text,IntWritable>(context);
        }
        
        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);
            //在这里可以灵活的按照自己的想法去输出
            // （多文件输出）出现次数大于10和小于10的分别输出在不同的文件
            if(sum<10)
               mos.write(key, new IntWritable(sum),"summax10");
            else 
               mos.write(key, new IntWritable(sum),"summin10");
            // （多文件夹输出）出现次数大于10和小于10的分别输出在不同的文件夹 
            if(sum<10)
                mos.write("11",key, new IntWritable(sum),"summax10/");
            else 
                mos.write("22",key, new IntWritable(sum),"summin10/");
            
            
        }
        protected void cleanup(Context context) throws IOException,InterruptedException {
            mos.close();
        }
    }
    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.setNumReduceTasks(2);
        job.setMapperClass(TokenizerMapper.class);
        job.setCombinerClass(IntSumReducer.class);
        job.setReducerClass(IntSumReducer.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);
        //另外就是配置的时候设置如下，需要将不同的文件输出格式添加。
        MultipleOutputs.addNamedOutput(job,"11",TextOutputFormat.class,Text.class,IntWritable.class);
        MultipleOutputs.addNamedOutput(job,"22",TextOutputFormat.class,Text.class,IntWritable.class);
         FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
        FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
        System.exit(job.waitForCompletion(true) ? 0 : 1);
    }
}
}

多文件的输入输出在注意在cleanup中调用close()方法不然会报错。

当然此刻也可以使用自己实现的MultipleOutputFormat类，可以参考这位同学的博客