Hadoop HDFS 的 I/O 流操作

HDFS 文件上传

@Test
public void putFileToHDFS() throws Exception {

    // 1 获取文件系统
    Configuration configuration = new Configuration();
    FileSystem fs = FileSystem.get(new URI("hdfs://hadoop102:9000"), configuration, "root");

    // 2 创建输入流
    FileInputStream fis = new FileInputStream(new File("/Users/ylj/demo/io.txt"));
    // 3 获取输出流
    FSDataOutputStream fos = fs.create(new Path("/demo/test/io.txt"));
    // 4 流对拷
    IOUtils.copyBytes(fis, fos, configuration);
    // 5 关闭资源
    IOUtils.closeStream(fis);
    IOUtils.closeStream(fos);

    fs.close();
    
    System.out.println("~~ok~~");
}

HDFS 文件下载

@Test
public void getFileFromHDFS() throws Exception{
    // 1 获取文件系统
    Configuration configuration = new Configuration();
    FileSystem fs = FileSystem.get(new URI("hdfs://hadoop102:9000"), configuration, "root");
    // 2 获取输人流
    FSDataInputStream fis = fs.open(new Path("/demo/test/io.txt"));
    // 3 获取输出流
    FileOutputStream fos = new FileOutputStream(new File("/Users/ylj/demo/io_bak.txt"));
    // 4 流的对拷
    IOUtils.copyBytes(fis, fos, configuration);
    // 5 关闭资源
    IOUtils.closeStream(fis);
    IOUtils.closeStream(fos);

    fs.close();

    System.out.println("~~ok~~");
}

定位文件读取

@Test
public void readFileSeek1() throws Exception {
    // 1 获取文件系统
    Configuration configuration = new Configuration();
    FileSystem fs = FileSystem.get(new URI("hdfs://hadoop102:9000"), configuration, "root");
    // 2 获取输入流
    FSDataInputStream fis = fs.open(new Path("/test/demo/hadoop-2.7.2.tar.gz"));
    // 3 创建输出流
    FileOutputStream fos = new FileOutputStream(new File("/Users/ylj/demo/hadoop-2.7.2.tar.gz.part1"));

    // 4 流的拷贝
    byte[] buf = new byte[1024];
    for (int i = 0; i < 1024 * 128; i++) {
        fis.read(buf);
        fos.write(buf);
    }
    //5 关闭资源
    IOUtils.closeStream(fis);
    IOUtils.closeStream(fos);

    fs.close();

    System.out.println("~~ok~~");
}

@Test
public void readFileSeek2() throws Exception {
    // 1 获取文件系统
    Configuration configuration = new Configuration();
    FileSystem fs = FileSystem.get(new URI("hdfs://hadoop102:9000"), configuration,"root");
    // 2 打开输入流
    FSDataInputStream fis = fs.open(new Path("/test/demo/hadoop-2.7.2.tar.gz"));
    // 3 定位输入数据位置
    fis.seek(1024 * 1024 * 128);
    // 4 创建输出流
    FileOutputStream fos = new FileOutputStream(new File("/Users/ylj/demo/hadoop-2.7.2.tar.gz.part2"));
    // 5 流的对拷
    IOUtils.copyBytes(fis, fos, configuration);
    // 6 关闭资源
    IOUtils.closeStream(fis);
    IOUtils.closeStream(fos);

    fs.close();

    System.out.println("~~ok~~");
}

文件合并

cat hadoop-2.7.2.tar.gz.part2 >> hadoop-2.7.2.tar.gz.part1