HDFS的Java客户端编写
总结： 之前在教材上看hdfs的Java客户端编写，只有关键代码，呵呵……。闲话不说，上正文。
1. Hadoop 的Java客户端编写建议在linux系统上开发
2. 可以使用eclipse,idea 等IDE工具，目前比较流行的是idea
3. 新建项目之后需要添加很多jar包，win，linux下添加jar方式略有不同
4. 使用代码会出现文件格式不认识，权限等问题。
具体：
1.首先测试从hdfs中下载文件:
下载文件的代码:(将hdfs://localhost:9000/jdk-7u65-linux-i586.tar.gz文件下载到本地/opt/download/doload.tgz)
package cn.qlq.hdfs;
import java.io.FileOutputStream;
import java.io.IOException;
import org.apache.commons.compress.utils.IOUtils;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FSDataInputStream;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
public class HdfsUtil {
public static void main(String a[]) throws IOException {
//to upload a file
Configuration conf = new Configuration();
FileSystem fs = FileSystem.get(conf);
Path path = new Path("hdfs://localhost:9000/jdk-7u65-linux-i586.tar.gz");
FSDataInputStream input = fs.open(path);
FileOutputStream output = new FileOutputStream("/opt/download/doload.tgz");
IOUtils.copy(input, output);
}
}
直接运行报错:
原因是程序不认识 hdfs://localhost:9000/jdk-7u65-linux-i586.tar.gz 这样的目录
log4j:WARN No appenders could be found for logger (org.apache.hadoop.metrics2.lib.MutableMetricsFactory).
log4j:WARN Please initialize the log4j system properly.
log4j:WARN See http://logging.apache.org/log4j/1.2/faq.html#noconfig for more info.
Exception in thread "main" java.lang.IllegalArgumentException: Wrong FS: hdfs://localhost:9000/jdk-7u65-linux-i586.tar.gz, expected: file:///
at org.apache.hadoop.fs.FileSystem.checkPath(FileSystem.java:643)
at org.apache.hadoop.fs.RawLocalFileSystem.pathToFile(RawLocalFileSystem.java:79)
at org.apache.hadoop.fs.RawLocalFileSystem.deprecatedGetFileStatus(RawLocalFileSystem.java:506)
at org.apache.hadoop.fs.RawLocalFileSystem.getFileLinkStatusInternal(RawLocalFileSystem.java:724)
at org.apache.hadoop.fs.RawLocalFileSystem.getFileStatus(RawLocalFileSystem.java:501)
at org.apache.hadoop.fs.FilterFileSystem.getFileStatus(FilterFileSystem.java:397)
at org.apache.hadoop.fs.ChecksumFileSystem$ChecksumFSInputChecker.<init>(ChecksumFileSystem.java:137)
at org.apache.hadoop.fs.ChecksumFileSystem.open(ChecksumFileSystem.java:339)
at org.apache.hadoop.fs.FileSystem.open(FileSystem.java:764)
at cn.qlq.hdfs.HdfsUtil.main(HdfsUtil.java:21)
解决办法:
- 第一种: 将hadoop安装目录下的etc目录中的core-site.xml拷贝到eclipse的src目录下。这样就不会报错
运行结果:
[root@localhost download]# ll total 140224 -rw-r--r--. 1 root root 143588167 Apr 20 05:55 doload.tgz [root@localhost download]# pwd /opt/download [root@localhost download]# ll total 140224 -rw-r--r--. 1 root root 143588167 Apr 20 05:55 doload.tgz
- 第二种:直接在程序中修改
我们先查看hdfs-site.xml中的内容:
<?xml version="1.0" encoding="UTF-8"?> <?xml-stylesheet type="text/xsl" href="configuration.xsl"?> <configuration> <property> <name>fs.defaultFS</name> <value>hdfs://localhost:9000</value> </property> <property> <name>hadoop.tmp.dir</name> <value>/opt/hadoop/hadoop-2.4.1/data/</value> </property> </configuration>
代码改为:
public static void main(String a[]) throws IOException {
//to upload a filed
Configuration conf = new Configuration();
//set hdfs root dir
conf.set("fs.defaultFS", "hdfs://localhost:9000");
FileSystem fs = FileSystem.get(conf);
Path path = new Path("hdfs://localhost:9000/jdk-7u65-linux-i586.tar.gz");
FSDataInputStream input = fs.open(path);
FileOutputStream output = new FileOutputStream("/opt/download/doload.tgz");
IOUtils.copy(input, output);
}
2.下面代码演示了hdfs的基本操作:
package cn.qlq.hdfs;
import java.io.FileInputStream;
import java.io.FileNotFoundException;
import java.io.FileOutputStream;
import java.io.IOException;
import java.net.URI;
import java.net.URISyntaxException;
import org.apache.commons.compress.utils.IOUtils;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FSDataInputStream;
import org.apache.hadoop.fs.FSDataOutputStream;
import org.apache.hadoop.fs.FileStatus;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.LocatedFileStatus;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.fs.RemoteIterator;
import org.junit.Before;
import org.junit.Test;
public class HdfsUtil {
private FileSystem fs = null;
@Before
public void befor() throws IOException, InterruptedException, URISyntaxException{
//读取classpath下的xxx-site.xml 配置文件，并解析其内容，封装到conf对象中
Configuration conf = new Configuration();
//也可以在代码中对conf中的配置信息进行手动设置，会覆盖掉配置文件中的读取的值
conf.set("fs.defaultFS", "hdfs://localhost:9000/");
//根据配置信息，去获取一个具体文件系统的客户端操作实例对象
fs = FileSystem.get(new URI("hdfs://localhost:9000/"),conf,"root");
}
/**
* 上传文件，比较底层的写法
*
* @throws Exception
*/
@Test
public void upload() throws Exception {
Path dst = new Path("hdfs://localhost:9000/aa/qingshu.txt");
FSDataOutputStream os = fs.create(dst);
FileInputStream is = new FileInputStream("/opt/download/haha.txt");
IOUtils.copy(is, os);
}
/**
* 上传文件，封装好的写法
* @throws Exception
* @throws IOException
*/
@Test
public void upload2() throws Exception, IOException{
fs.copyFromLocalFile(new Path("/opt/download/haha.txt"), new Path("hdfs://localhost:9000/aa/qingshu2.txt"));
}
/**
* download file
* @throws IOException
*/
@Test
public void download() throws IOException {
Path path = new Path("hdfs://localhost:9000/jdk-7u65-linux-i586.tar.gz");
FSDataInputStream input = fs.open(path);
FileOutputStream output = new FileOutputStream("/opt/download/doload.tgz");
IOUtils.copy(input, output);
}
/**
* 下载文件
* @throws Exception
* @throws IllegalArgumentException
*/
@Test
public void download2() throws Exception {
fs.copyToLocalFile(new Path("hdfs://localhost:9000/aa/qingshu2.txt"), new Path("/opt/download/haha2.txt"));
}
/**
* 查看文件信息
* @throws IOException
* @throws IllegalArgumentException
* @throws FileNotFoundException
*
*/
@Test
public void listFiles() throws FileNotFoundException, IllegalArgumentException, IOException {
// listFiles列出的是文件信息，而且提供递归遍历
RemoteIterator<LocatedFileStatus> files = fs.listFiles(new Path("/"), true);
while(files.hasNext()){
LocatedFileStatus file = files.next();
Path filePath = file.getPath();
String fileName = filePath.getName();
System.out.println(fileName);
}
System.out.println("---------------------------------");
//listStatus 可以列出文件和文件夹的信息，但是不提供自带的递归遍历
FileStatus[] listStatus = fs.listStatus(new Path("/"));
for(FileStatus status: listStatus){
String name = status.getPath().getName();
System.out.println(name + (status.isDirectory()?" is dir":" is file"));
}
}
/**
* 创建文件夹
* @throws Exception
* @throws IllegalArgumentException
*/
@Test
public void mkdir() throws IllegalArgumentException, Exception {
fs.mkdirs(new Path("/aaa/bbb/ccc"));
}
/**
* 删除文件或文件夹
* @throws IOException
* @throws IllegalArgumentException
*/
@Test
public void rm() throws IllegalArgumentException, IOException {
fs.delete(new Path("/aa"), true);
}
}
