Mapreduce剔除缺失数据信息大于n个字段的记录

public class Test {
        public static void main(String[] args)throws Exception {
            Configuration conf = new Configuration();
            Job job = Job.getInstance(conf);
            //设置文件的输入和输出
            FileInputFormat.setInputPaths(job,new Path("src/main/java/Code/切分测试/Input/Test.txt"));
            FileOutputFormat.setOutputPath(job,new Path("src/main/java/Code/切分测试/st"));

            //设置
            job.setMapperClass(mapper.class);
            job.setReducerClass(reducer.class);

            job.setMapOutputKeyClass(Text.class);
            job.setMapOutputValueClass(Text.class);

            job.setOutputKeyClass(Text.class);
            job.setOutputValueClass(Text.class);

            Boolean bl= job.waitForCompletion(true);
            System.exit(bl?0:1);
        }
        public static class mapper extends Mapper<LongWritable,Text,Text,Text>{
            @Override
            protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
                String[] split = value.toString().split(",");
                //TODO 剔除包含a字母大于3个的字段
                /*
                在map阶段,每执行一行数据,就会重新执行一次map
                也就是说int count = 0每执行一行数据之后都会被刷新一次,也就是重置为0
                 */
                int count=0;
                for (String s : split) {
                    if (s.contains("a")){
                        count+=1;
                    }
                    if (count>=3){
                        return;
                    }
                }
                context.write(value,new Text(""));
            }

        }
    public  static  class  reducer extends Reducer<Text,Text,Text,Text>{
        @Override
        protected void reduce(Text key, Iterable<Text> values, Context context) throws IOException, InterruptedException {
            for (Text value : values) {
                context.write(key,value);
            }
        }
    }
}

结果:

那么我们去处理n字段的时候用同样的方法即可!