重庆分公司
重庆分公司，新征程启航
为企业提供网站建设、域名注册、服务器等服务
贴一段java读取hdfs解压gzziptar.gz保存到hdfs的代码
package main.java;
import java.io.*;
import java.util.LinkedList;
import java.util.List;
import java.util.zip.*;
import org.apache.commons.compress.archivers.ArchiveException;
import org.apache.commons.compress.archivers.ArchiveInputStream;
import org.apache.commons.compress.archivers.ArchiveStreamFactory;
import org.apache.commons.compress.archivers.tar.TarArchiveEntry;
import java.io.IOException;
import java.net.URI;
import org.apache.commons.compress.compressors.gzip.GzipCompressorInputStream;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.fs.FSDataInputStream;
import org.apache.hadoop.fs.FSDataOutputStream;;
/**
* 解压tar.gz zip gz文件包 这里的数据源和输出目录都为HDFS
*
*/
public class GZipHdfs {
private BufferedOutputStream bufferedOutputStream;
String zipfileName = null;
public GZipHdfs(String fileName) {
this.zipfileName = fileName;
}
/*
* 执行入口,rarFileName为需要解压的文件路径(具体到文件),destDir为解压目标路径 路径为HDFS
*/
public List
GZipHdfs GZipHdfs = new GZipHdfs(rarFileName);
Configuration conf = new Configuration();
FileSystem fs = FileSystem.get(URI.create(destDir), conf);
boolean result = fs.isDirectory(new Path(destDir));
if (!result) {
fs.mkdirs(new Path(destDir));
}
String outputDirectory = destDir;
List
fs.close();
return r;
}
public List
FileInputStream fis = null;
ArchiveInputStream in = null;
BufferedInputStream bufferedInputStream = null;
List
try {
FSDataInputStream hdfsInputStream = fs.open(new Path(zipfileName));
GZIPInputStream is = new GZIPInputStream(new BufferedInputStream(
hdfsInputStream));
in = new ArchiveStreamFactory().createArchiveInputStream("tar", is);
bufferedInputStream = new BufferedInputStream(in);
TarArchiveEntry entry = (TarArchiveEntry) in.getNextEntry();
while (entry != null) {
String name = entry.getName();
String[] names = name.split("/");
String fileName = outputDirectory;
for (int i = 0; i < names.length; i++) {
String str = names[i];
fileName = fileName + "/" + str;
}
FSDataOutputStream hdfsOutStream = fs.create(new Path(fileName));
bufferedOutputStream = new BufferedOutputStream(
hdfsOutStream);
int b;
while ((b = bufferedInputStream.read()) != -1) {
bufferedOutputStream.write(b);
}
bufferedOutputStream.flush();
bufferedOutputStream.close();
entry = (TarArchiveEntry) in.getNextEntry();
tarList.add(name);
}
} catch (FileNotFoundException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
} catch (ArchiveException e) {
e.printStackTrace();
} finally {
try {
if (bufferedInputStream != null) {
bufferedInputStream.close();
}
} catch (IOException e) {
e.printStackTrace();
}
}
return tarList;
}
/*
* 执行入口,rarFileName为需要解压的文件路径(具体到文件),destDir为解压目标路径 路径为HDFS
*/
public List
GZipHdfs GZipHdfs = new GZipHdfs(rarFileName);
Configuration conf = new Configuration();
FileSystem fs = FileSystem.get(URI.create(destDir), conf);
boolean result = fs.isDirectory(new Path(destDir));
if (!result) {
fs.mkdirs(new Path(destDir));
}
String outputDirectory = destDir;
List
fs.close();
return r;
}
public List
FileInputStream fis = null;
ArchiveInputStream in = null;
BufferedInputStream bufferedInputStream = null;
List
try {
FSDataInputStream hdfsInputStream = fs.open(new Path(zipfileName));
ZipInputStream is = new ZipInputStream(new BufferedInputStream(
hdfsInputStream));
bufferedInputStream = new BufferedInputStream(is);
ZipEntry entry =is.getNextEntry();
while (entry != null) {
String name = entry.getName();
String[] names = name.split("/");
String fileName = outputDirectory;
for (int i = 0; i < names.length; i++) {
String str = names[i];
fileName = fileName + "/" + str;
}
FSDataOutputStream hdfsOutStream = fs.create(new Path(fileName));
bufferedOutputStream = new BufferedOutputStream(
hdfsOutStream);
int b;
while ((b = bufferedInputStream.read()) != -1) {
bufferedOutputStream.write(b);
}
bufferedOutputStream.flush();
bufferedOutputStream.close();
entry = (ZipEntry) is.getNextEntry();
zipList.add(name);
}
} catch (FileNotFoundException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
} finally {
try {
if (bufferedInputStream != null) {
bufferedInputStream.close();
}
} catch (IOException e) {
e.printStackTrace();
}
}
return zipList;
}
/*
* 执行入口,rarFileName为需要解压的文件路径(具体到文件),destDir为解压目标路径 路径为HDFS
*/
public List
GZipHdfs GZipHdfs = new GZipHdfs(rarFileName);
Configuration conf = new Configuration();
FileSystem fs = FileSystem.get(URI.create(destDir), conf);
boolean result = fs.isDirectory(new Path(destDir));
if (!result) {
fs.mkdirs(new Path(destDir));
}
String outputDirectory = destDir;
List
fs.close();
return r;
}
public List
FileInputStream fis = null;
ArchiveInputStream in = null;
BufferedInputStream bufferedInputStream = null;
List
try {
FSDataInputStream hdfsInputStream = fs.open(new Path(zipfileName));
GzipCompressorInputStream is = new GzipCompressorInputStream(new BufferedInputStream(
hdfsInputStream));
bufferedInputStream = new BufferedInputStream(is);
String[] nameList = zipfileName.split("/");
String name=nameList[nameList.length-1].replace(".gz","");
String fileName = outputDirectory+"/"+name;
FSDataOutputStream hdfsOutStream = fs.create(new Path(fileName));
bufferedOutputStream = new BufferedOutputStream(
hdfsOutStream);
int b;
while ((b = bufferedInputStream.read()) != -1) {
bufferedOutputStream.write(b);
}
bufferedOutputStream.flush();
bufferedOutputStream.close();
tarList.add(name);
} catch (FileNotFoundException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
} finally {
try {
if (bufferedInputStream != null) {
bufferedInputStream.close();
}
} catch (IOException e) {
e.printStackTrace();
}
}
return tarList;
}
}
创新互联服务项目包括韶关网站建设、韶关网站制作、韶关网页制作以及韶关网络营销策划等。多年来，我们专注于互联网行业，利用自身积累的技术优势、行业经验、深度合作伙伴关系等，向广大中小型企业、政府机构等提供互联网行业的解决方案，韶关网站推广取得了明显的社会效益与经济效益。目前，我们服务的客户以成都为中心已经辐射到韶关省份的部分城市，未来相信会继续扩大服务区域并继续获得客户的支持与信任！
分享名称：贴一段java读取hdfs解压gzziptar.gz保存到hdfs的代码
网站地址：http://cqcxhl.cn/article/jsidps.html