hadoop数据去重代码

以下是一个简单的Hadoop MapReduce去重代码，它可以从输入文件中读取数据并将其写入输出文件中，同时删除重复的记录：

public class Deduplication {
    public static class Map extends Mapper<Object, Text, Text, NullWritable> {
        private Text word = new Text();

        public void map(Object key, Text value, Context context) throws IOException, InterruptedException {
            word.set(value);
            context.write(word, NullWritable.get());
        }
    }

    public static class Reduce extends Reducer<Text, NullWritable, Text, NullWritable> {
        public void reduce(Text key, Iterable<NullWritable> values, Context context) throws IOException, InterruptedException {
            context.write(key, NullWritable.get());
        }
    }

    public static void main(String[] args) throws Exception {
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf, "deduplication");
        job.setJarByClass(Deduplication.class);
        job.setMapperClass(Map.class);
        job.setCombinerClass(Reduce.class);
        job.setReducerClass(Reduce.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(NullWritable.class);
        FileInputFormat.addInputPath(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));
        System.exit(job.waitForCompletion(true) ? 0 : 1);
    }
}