hadoop 的hdfsapi操作

标签：大数据   hadoop   

• hdfs 的api 相关操作

一： hdfs api 操作

1.1 读取内容：

package it.xuegod.hadoop.hdfs;
import java.io.IOException;
import java.io.InputStream;
import java.net.MalformedURLException;
import java.net.URL;
import java.net.URLConnection;
import java.nio.file.FileSystem;

import org.apache.hadoop.fs.FsUrlStreamHandlerFactory;
import org.junit.Test;
import org.apache.hadoop.conf.Configuration;

public class TestHdfs {

    @Test
    public void readFile() throws IOException {
        URL.setURLStreamHandlerFactory(new FsUrlStreamHandlerFactory());

        URL url = new URL("hdfs://172.17.100.11:8020/input/file1");
        URLConnection conn = url.openConnection();      
        InputStream is = conn.getInputStream();
        byte[] buf = new byte[is.available()];
        is.read(buf);
        is.close();
        String str = new String(buf);
        System.out.println(str);

    }

}

1.2 读取hdfs的数据

package it.xuegod.hadoop.hdfs;
import java.io.ByteArrayOutputStream;
import java.io.IOException;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FSDataInputStream;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.junit.Test;

/**
 * 
 * 
 * @author zhangyy
 *
 *read file
 *
 */

public class readFileApi {

    @Test
    public void readFileByApi() throws IOException {

        Configuration conf = new Configuration();
        conf.set("fs.defaultFS", "hdfs://172.17.100.11:8020");
        FileSystem fs = FileSystem.get(conf);

        Path p = new Path("/input/file1");
        FSDataInputStream fis = fs.open(p);
        byte[] buf = new byte[1024];
        int len = -1;

        ByteArrayOutputStream baos = new ByteArrayOutputStream();
        while((len = fis.read(buf)) != -1) {
            baos.write(buf, 0, len);

        }
        fis.close();
        baos.close();

        System.out.println(new String(baos.toByteArray()));     
    }

}

package it.xuegod.hadoop.hdfs;
import java.io.ByteArrayOutputStream;
import java.io.IOException;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FSDataInputStream;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IOUtils;
import org.junit.Test;

/**
 * 
 * 
 * @author zhangyy
 * 
 * readfile 
 *
 */
public class readFileApi2 {

    @Test
    public void readFileByApi() throws IOException {

        Configuration conf = new Configuration();
        conf.set("fs.defaultFS", "hdfs://172.17.100.11:8020");
        FileSystem fs = FileSystem.get(conf);
        ByteArrayOutputStream baos = new ByteArrayOutputStream();
        Path p = new Path("/input/file1");
        FSDataInputStream fis = fs.open(p);
        IOUtils.copyBytes(fis, baos, 1024);
        System.out.println(new String(baos.toByteArray()));     
    }

}

1.3: 在hdfs上面的建立文件

package it.xuegod.hadoop.hdfs;

import java.io.ByteArrayOutputStream;
import java.io.IOException;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FSDataInputStream;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IOUtils;
import org.junit.Test;

/**
 * 
 * 
 * @author zhangyy
 * 
 * readfile 
 *
 */
public class mkdirFileApi {

    @Test
    public void mkdirFileByApi() throws IOException {

        Configuration conf = new Configuration();
        conf.set("fs.defaultFS", "hdfs://172.17.100.11:8020");
        FileSystem fs = FileSystem.get(conf);
        fs.mkdirs(new Path("/myhadoop"));

    }

}

###1.4: put写入文件

package it.xuegod.hadoop.hdfs;

import java.io.ByteArrayOutputStream;
import java.io.IOException;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FSDataInputStream;
import org.apache.hadoop.fs.FSDataOutputStream;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IOUtils;
import org.junit.Test;

/**
 * 
 * 
 * @author zhangyy
 * 
 * readfile 
 *
 */
public class putFileApi {

    @Test
    public void putFileByApi() throws IOException {

        Configuration conf = new Configuration();
        conf.set("fs.defaultFS", "hdfs://172.17.100.11:8020");
        FileSystem fs = FileSystem.get(conf);
        FSDataOutputStream out = fs.create(new Path("/myhadoop/a.txt"));
        out.write("helloword".getBytes());
        out.close();
    }

}

1.5 删除文件

package it.xuegod.hadoop.hdfs;

import java.io.ByteArrayOutputStream;
import java.io.IOException;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FSDataInputStream;
import org.apache.hadoop.fs.FSDataOutputStream;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IOUtils;
import org.junit.Test;

/**
 * 
 * 
 * @author zhangyy
 * 
 * rmfile 
 *
 */
public class rmFileApi {

    @Test
    public void rmFileByApi() throws IOException {

        Configuration conf = new Configuration();
        conf.set("fs.defaultFS", "hdfs://172.17.100.11:8020");
        FileSystem fs = FileSystem.get(conf);
        Path p = new Path("/myhadoop");
        fs.delete(p,true);
    }

}

hadoop 的hdfsapi操作

标签：大数据   hadoop   

原文地址：http://blog.51cto.com/flyfish225/2096394