Hadoop 学习笔记（二） HDFS API

4.删除HDFS上的文件
package proj;

import java.io.IOException;

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

public class DeleteFile {

    public static void main(String[] args) throws IOException {
        Configuration conf = new Configuration();
        //要点：没有这句会传到本地文件系统，而不是hdfs
        conf.set("fs.default.name","hdfs://localhost:9000");
        FileSystem hdfs = FileSystem.get(conf);
        Path delef = new Path("in/test3.txt");
        boolean isDeleted = hdfs.delete(delef, false);
        //递归删除
        //boolean isDelete = hdfs.delete(delef, true);
        System.out.println("delete? "+ isDeleted);
    }

}

检查文件是否存在
package proj;

import java.io.IOException;

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

public class CheckFile {

    public static void main(String[] args) throws IOException {
        Configuration conf = new Configuration();
        //要点：没有这句会传到本地文件系统，而不是hdfs
        conf.set("fs.default.name","hdfs://localhost:9000");
        FileSystem hdfs = FileSystem.get(conf);
        Path findf = new Path("in/hello.c");
        boolean exist = hdfs.exists(findf);
        System.out.println("exist ? " + exist);
        
    }

}

查找某个文件在HDFS集群的位置
package proj;

import java.io.IOException;

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

public class FileLocal {
    public static void main(String[] args) throws IOException{
        Configuration conf = new Configuration();
        //要点：没有这句会传到本地文件系统，而不是hdfs
        conf.set("fs.default.name","hdfs://localhost:9000");
        FileSystem hdfs = FileSystem.get(conf);
        Path fpath = new Path("in/hello.c");
        
        FileStatus filestatus = hdfs.getFileStatus(fpath);
        BlockLocation[] blkLocations = hdfs.getFileBlockLocations(filestatus, 0, filestatus.getLen());
        int blockLen = blkLocations.length;
        for (int i = 0; i < blockLen; i++) {
            String[] hosts = blkLocations[i].getHosts();
            System.out.println("block "+i+" location "+ hosts[i]);
        }
    }
}

获取HDFS集群上所有节点名称
package proj;

import java.io.IOException;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.hdfs.DistributedFileSystem;
import org.apache.hadoop.hdfs.protocol.DatanodeInfo;

public class GetList {

    public static void main(String[] args) throws IOException {

        Configuration conf = new Configuration();
        //要点：没有这句会传到本地文件系统，而不是hdfs
        conf.set("fs.default.name","hdfs://localhost:9000");
        FileSystem fs = FileSystem.get(conf);
        DistributedFileSystem hdfs = (DistributedFileSystem)fs;
        DatanodeInfo[] dataNodeStats = hdfs.getDataNodeStats();
        String[] names = new String[dataNodeStats.length];
        for (int i = 0; i < dataNodeStats.length; i++) {
            names[i] = dataNodeStats[i].getHostName();
            System.out.println("node " + i + " name " + names[i]);
        }
    }

}