如何统计hdfs中按日期分组的文件数

import java.io.IOException;
import java.text.SimpleDateFormat;
import java.util.Date;
import java.util.HashMap;
import java.util.Map;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileStatus;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;

public class HdfsFileCountByDate {
    public static void main(String[] args) throws IOException {
        Configuration conf = new Configuration();
        FileSystem fs = FileSystem.get(conf);
        
        Path directory = new Path("/path/to/directory"); // 指定目录
        
        FileStatus[] fileStatuses = fs.listStatus(directory);
        
        SimpleDateFormat dateFormat = new SimpleDateFormat("yyyy-MM-dd");
        Map<String, Integer> fileCountByDate = new HashMap<>();
        
        for (FileStatus fileStatus : fileStatuses) {
            Date creationTime = new Date(fileStatus.getModificationTime());
            String date = dateFormat.format(creationTime);
            
            if (fileCountByDate.containsKey(date)) {
                int count = fileCountByDate.get(date);
                fileCountByDate.put(date, count + 1);
            } else {
                fileCountByDate.put(date, 1);
            }
        }
        
        for (Map.Entry<String, Integer> entry : fileCountByDate.entrySet()) {
            System.out.println("日期：" + entry.getKey() + "，文件数：" + entry.getValue());
        }
    }
}