zzjmay 2020-01-17
HDFS,是Hadoop Distributed File System的简称,是Hadoop抽象文件系统的一种实现。Hadoop抽象文件系统可以与本地系统、Amazon S3等集成,甚至可以通过Web协议(webhsfs)来操作。HDFS的文件分布在集群机器上,同时提供副本进行容错及可靠性保证。例如客户端写入读取文件的直接操作都是分布在集群各个机器上的,没有单点性能压力。
HDFS相关的搭建可以看我前面的一篇博文,我们今天主要来讲下怎么操作hdfs的api和 hdfs命令行,
<repositories> <repository> <id>cloudera</id> <url>https://repository.cloudera.com/artifactory/cloudera-repos</url> </repository> </repositories> //导包 <dependency> <groupId>org.apache.hadoop</groupId> <artifactId>hadoop-client</artifactId> <version>${hadoop.version}</version> </dependency>
this.configuration = new Configuration(); this.fileSystem = FileSystem.get(new URI(this.HDFS_PATH),configuration,"hadoop"); Path path = new Path("/hdfsapi/test"); boolean result = fileSystem.mkdirs(path);
Path path = new Path("/gwyy.txt"); FSDataInputStream fsDataInputStream = fileSystem.open(path); FileOutputStream fileOutputStream = new FileOutputStream(new File("a.txt")); byte[] buffer = new byte[1024]; int length = 0; StringBuffer sb = new StringBuffer(); while( ( length = fsDataInputStream.read(buffer)) != -1) { sb.append(new String(buffer,0,buffer.length)); fileOutputStream.write(buffer,0,buffer.length); } System.out.println(sb.toString());
FSDataOutputStream out = fileSystem.create(new Path("/fuck.txt")); out.writeUTF("aaabbb"); out.flush(); out.close();
boolean a = fileSystem.rename(new Path("/fuck.txt"),new Path("/fuck.aaa")); System.out.println(a);
fileSystem.copyFromLocalFile(new Path("a.txt"),new Path("/copy_a.txt"));
InputStream in = new BufferedInputStream(new FileInputStream(new File("hive-1.1.0-cdh5.15.1.tar.gz"))); Path dst = new Path("/hive.tar.gz"); //显示进度条 FSDataOutputStream out = fileSystem.create(dst, new Progressable() { @Override public void progress() { System.out.flush(); System.out.print(‘.‘); } }); byte[] buffer = new byte[4096]; int length = 0; //写入到 hdfs while((length = in.read(buffer,0,buffer.length)) != -1) { out.write(buffer,0,buffer.length); }
fileSystem.copyToLocalFile(new Path("/fuck.aaa"),new Path("./"));
FileStatus[] fileStatuses = fileSystem.listStatus(new Path("/")); for (FileStatus f:fileStatuses) { System.out.println(f.getPath()); }
RemoteIterator<LocatedFileStatus> remoteIterator = fileSystem.listFiles(new Path("/"),true); while(remoteIterator.hasNext()) { LocatedFileStatus file = remoteIterator.next(); System.out.println(file.getPath()); }
FileStatus fileStatus = fileSystem.getFileStatus(new Path("/jdk-8u221-linux-x64.tar.gz")); BlockLocation[] blockLocations = fileSystem.getFileBlockLocations(fileStatus,0,fileStatus.getLen()); //查看区块 for (BlockLocation b:blockLocations) { for (String name:b.getNames()) { System.out.println(name + b.getOffset() + b.getLength()); } }
如果路径是目录并设置为*如果为true,则删除目录,否则引发异常。在*对于文件,递归可以设置为true或false。 boolean a = fileSystem.delete(new Path("/gwyy.txt"),true); System.out.println(a);
hadoop fs -ls /
hadoop fs -put gwyy.txt /
hf -copyFromLocal xhc.txt /
####从本地移动文件到hdfs 本地文件删除 hf -moveFromLocal a.txt /
hadoop fs -cat /gwyy.txt hadoop fs -text /gwyy.txt
hadoop fs -get /a.txt ./
hadoop fs -mkdir /hdfs-test
hadoop fs -mv /a.txt /hdfs-test/a.txt
hadoop fs -cp /hdfs-test/a.txt /hdfs-test/a.txt.back
hadoop fs -getmerge /hdfs-test ./t.txt
hf -rm /hdfs-test/a.txt.back
hadoop fs -rmdir /hdfs-test 只能删除空目录 hadoop fs -rm -r /hdfs-test 删除目录不管有没有东西都删