读取hadoop文件内容

 

 

import java.net.URI;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FSDataInputStream;
import org.apache.hadoop.fs.FileStatus;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;

public class ReadHdfsFile {

	public static String getHdfsFileContent(String hdfsFile) throws Exception {
		
		Configuration conf = new Configuration();
		String content = "";	
		FileSystem fs = FileSystem.get(new URI(hdfsFile), conf);
		Path path = new Path(hdfsFile);
		if(fs.exists(path)){
			FSDataInputStream  fis = fs.open(path); // 打开文件流
			FileStatus  stat = fs.getFileStatus(path); // 读取文件状态
			byte[] buf = new byte[Integer.parseInt(String.valueOf(stat.getLen()))] ; 
			fis.readFully(0, buf);
			fis.close();// 文件流关闭
			fs.close();//文件操作系统关闭
			content = new String(buf);
		}
		return content;
	}
	
	
	public static void main(String[] args) {
		
		try {
			System.out.println(getHdfsFileContent("/log_data/act"));
		} catch (Exception e) {
			// TODO Auto-generated catch block
			e.printStackTrace();
		}
	}
}