如何用java程序把本地文件拷貝到hdfs上並顯示進度

把程序打成jar包放到Linux上

轉到目錄下執行命令 hadoop jar mapreducer.jar /home/clq/export/java/count.jar  hdfs://ubuntu:9000/out06/count/

上面一個是本地文件，一個是上傳hdfs位置

成功後出現：打印出來，你所要打印的字符。

package com.clq.hdfs;  
       
import java.io.BufferedInputStream;  
import java.io.FileInputStream;  
import java.io.IOException;  
import java.io.InputStream;  
import java.net.URI;  
import org.apache.hadoop.conf.Configuration;  
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.apache.hadoop.util.Progressable;  
       
public class FileCopyWithProgress {  
//********************************  
//把本地的一個文件拷貝到hdfs上  
//********************************  
    public static void main(String[] args) throws IOException {  
        String localSrc = args[0];  
        String dst = args[1];  
        InputStream in = new BufferedInputStream(new FileInputStream(localSrc));  
        Configuration conf = new Configuration();  
        FileSystem fs = FileSystem.get(URI.create(dst), conf);  
        FSDataOutputStream out = fs.create(new Path(dst), new Progressable() {  
            @Override
            public void progress() {  
                System.out.print(".");  
            }  
        });  
        IOUtils.copyBytes(in, out, conf, true);  
    }  
       
}

查看本欄目

可能出現異常：

Exception in thread "main" org.apache.hadoop.ipc.RemoteException: java.io.IOException: Cannot create /out06; already exists as a directory

at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.startFileInternal(FSNamesystem.java:1569)

at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.startFile(FSNamesystem.java:1527)

at org.apache.hadoop.hdfs.server.namenode.NameNode.create(NameNode.java:710)

at org.apache.hadoop.hdfs.server.namenode.NameNode.create(NameNode.java:689)

at sun.reflect.GeneratedMethodAccessor7.invoke(Unknown Source)

at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)

at java.lang.reflect.Method.invoke(Method.java:606)

at org.apache.hadoop.ipc.RPC$Server.call(RPC.java:587)

at org.apache.hadoop.ipc.Server$Handler$1.run(Server.java:1432)

at org.apache.hadoop.ipc.Server$Handler$1.run(Server.java:1428)

at java.security.AccessController.doPrivileged(Native Method)

at javax.security.auth.Subject.doAs(Subject.java:415)

說明你這個路徑在hdfs上已經存在，換一個即可。