施用java api操作Hadoop文件

使用java api操作Hadoop文件

<1>. 文件操作

1.1 上传本地文件到文件系统

     /*
     * upload the local file to the hds
     * notice that the path is full like /tmp/test.c
     */
    public static void uploadLocalFile2HDFS(String s, String d)
        throws IOException
    {
        Configuration config = new Configuration();
        FileSystem hdfs = FileSystem.get(config);

        Path src = new Path(s);
        Path dst = new Path(d);

        hdfs.copyFromLocalFile(src, dst);

        hdfs.close();
    }

1.2 创建新文件，并写入

     /*
   * create a new file in the hdfs.
     * notice that the toCreateFilePath is the full path
     * and write the content to the hdfs file.
     */
    public static void createNewHDFSFile(String toCreateFilePath, String content) throws IOException
    {
        Configuration config = new Configuration();
        FileSystem hdfs = FileSystem.get(config);

        FSDataOutputStream os = hdfs.create(new Path(toCreateFilePath));

        os.write(content.getBytes("UTF-8"));

        os.close();

        hdfs.close();
    }

1.3 删除文件

   /*
   * delete the hdfs file
     * notice that the dst is the full path name
     */
    public static boolean deleteHDFSFile(String dst) throws IOException
    {
        Configuration config = new Configuration();
        FileSystem hdfs = FileSystem.get(config);

        Path path = new Path(dst);
        boolean isDeleted = hdfs.delete(path);

        hdfs.close();

        return isDeleted;
    }

1.4 读取文件

     /** read the hdfs file content
     * notice that the dst is the full path name
     */
    public static byte[] readHDFSFile(String dst) throws Exception
    {
        Configuration conf = new Configuration();
        FileSystem fs = FileSystem.get(conf);

        // check if the file exists
        Path path = new Path(dst);
        if ( fs.exists(path) )
        {
            FSDataInputStream is = fs.open(path);
            // get the file info to create the buffer
            FileStatus stat = fs.getFileStatus(path);

            // create the buffer
            byte[] buffer = new byte[Integer.parseInt(String.valueOf(stat.getLen()))];
            is.readFully(0, buffer);

            is.close();
            fs.close();

            return buffer;
        }
        else
        {
            throw new Exception("the file is not found .");
        }
    }

<2>. 目录操作

2.1 创建目录

      /** make a new dir in the hdfs
     *
     * the dir may like '/tmp/testdir'
     */
    public static void mkdir(String dir) throws IOException
    {
        Configuration conf =  new Configuration();
        FileSystem fs = FileSystem.get(conf);

        fs.mkdirs(new Path(dir));

        fs.close();
    }

2.2 删除目录

      /** delete a dir in the hdfs
     *
     * dir may like '/tmp/testdir'
     */
    public static void deleteDir(String dir) throws IOException
    {
        Configuration conf = new Configuration();
        FileSystem fs = FileSystem.get(conf);

        fs.delete(new Path(dir));

        fs.close();
    }

2.3 读取某个目录下的所有文件

   public static void listAll(String dir) throws IOException
   {
        Configuration conf = new Configuration();
        FileSystem fs = FileSystem.get(conf);

        FileStatus[] stats = fs.listStatus(new Path(dir));

        for(int i = 0; i < stats.length; ++i)
        {
            if (stats[i].isFile())
            {
                // regular file
                System.out.println(stats[i].getPath().toString());
            }
            else if (stats[i].isDirectory())
            {
                // dir
                System.out.println(stats[i].getPath().toString());
            }
            else if(stats[i].isSymlink())
            {
                // is s symlink in linux
                System.out.println(stats[i].getPath().toString());
            }

        }
        fs.close();
    }

施用java api操作Hadoop文件

<1>. 文件操作

<2>. 目录操作

相关推荐