统计hdfs中文件记录数的代码

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.NullWritable;
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 java.io.IOException;

public class HDFSRecordCount {

    public static class RecordCountMapper extends Mapper<LongWritable, Text, NullWritable, NullWritable> {

        @Override
        protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
            // 每读取一行记录，输出一个键值对
            context.write(NullWritable.get(), NullWritable.get());
        }
    }

    public static class RecordCountReducer extends Reducer<NullWritable, NullWritable, NullWritable, LongWritable> {

        @Override
        protected void reduce(NullWritable key, Iterable<NullWritable> values, Context context) throws IOException, InterruptedException {
            long count = 0;
            // 统计记录数
            for (NullWritable value : values) {
                count++;
            }
            // 输出记录数
            context.write(NullWritable.get(), new LongWritable(count));
        }
    }

    public static void main(String[] args) throws Exception {
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf, "HDFS Record Count");
        job.setJarByClass(HDFSRecordCount.class);
        job.setMapperClass(RecordCountMapper.class);
        job.setReducerClass(RecordCountReducer.class);
        job.setOutputKeyClass(NullWritable.class);
        job.setOutputValueClass(NullWritable.class);
        FileInputFormat.addInputPath(job, new Path("hdfs://your-hdfs-path"));
        FileOutputFormat.setOutputPath(job, new Path("hdfs://your-output-path"));
        System.exit(job.waitForCompletion(true) ? 0 : 1);
    }
}