最近碰到需要解析各类压缩包并入库的需求,废话不多说直接上代码
package com.anylangtech.corpus.utils;
import com.github.junrar.Archive;
import com.github.junrar.exception.RarException;
import com.github.junrar.rarfile.FileHeader;
import lombok.Cleanup;
import org.apache.commons.compress.archivers.tar.TarArchiveEntry;
import org.apache.commons.compress.archivers.tar.TarArchiveInputStream;
import org.apache.commons.compress.utils.IOUtils;
import java.io.*;
import java.nio.charset.Charset;
import java.util.ArrayList;
import java.util.Enumeration;
import java.util.List;
import java.util.zip.ZipEntry;
import java.util.zip.ZipFile;
public class UncompressionUtils {
/**
* @description: 解压zip文件
* @param [zipPath, descDir]
* @return void
* @author wrt
* @date 2022/4/7 15:00
*/
public static void unZipFile(String zipPath, String descDir) {
try {
File zipFile = new File(zipPath);
if (!zipFile.exists()) {
throw new IOException("需解压文件不存在.");
}
File pathFile = new File(descDir);
if (!pathFile.exists()) {
pathFile.mkdirs();
}
ZipFile zip = new ZipFile(zipFile, Charset.forName("GBK"));
int count = 0;
for (Enumeration entries = zip.entries(); entries.hasMoreElements(); ) {
ZipEntry entry = (ZipEntry) entries.nextElement();
//避免文件名过长超出linux文件名长度限制255
String zipEntryName;
if(entry.getName().length() > 50){
zipEntryName = entry.getName().substring(0,50) + count + entry.getName().substring(entry.getName().lastIndexOf("."));
} else {
zipEntryName = entry.getName();
}
InputStream in = zip.getInputStream(entry);
String outPath = (descDir + File.separator + zipEntryName).replaceAll("\\*", "/");
// 判断路径是否存在,不存在则创建文件路径
File file = new File(outPath.substring(0, outPath.lastIndexOf('/')));
if (!file.exists()) {
file.mkdirs();
}
// 判断文件全路径是否为文件夹,如果是上面已经上传,不需要解压
if (new File(outPath).isDirectory()) {
continue;
}
// 输出文件路径信息
OutputStream out = new FileOutputStream(outPath);
byte[] buf1 = new byte[1024];
int len;
while ((len = in.read(buf1)) > 0) {
out.write(buf1, 0, len);
}
in.close();
out.close();
count++;
}
} catch (Exception e) {
e.printStackTrace();
}
}
/**
* @description: 解压rar文件
* @param [srcRarPath, dstDirectoryPath]
* @return void
* @author wrt
* @date 2022/4/7 15:03
*/
public static void unRarFile(String rarPath, String descDir) {
File outFile = new File(descDir);
// 目标目录不存在时,创建该文件夹
if (!outFile.exists()) {
outFile.mkdirs();
}
try {
@Cleanup Archive archive = new Archive(new FileInputStream(rarPath));
FileHeader fileHeader = archive.nextFileHeader();
while (fileHeader != null) {
// 解决中文乱码问题【压缩文件中文乱码】
String fileName = fileHeader.getFileNameW().isEmpty() ? fileHeader.getFileNameString() : fileHeader.getFileNameW();
// 文件夹
if (fileHeader.isDirectory()) {
File fol = new File(descDir + File.separator + fileName.trim());
fol.mkdirs();
} else { // 文件
// 解决linux系统中\分隔符无法识别问题
String[] fileParts = fileName.split("\\\\");
StringBuilder filePath = new StringBuilder();
for (String filePart : fileParts) {
filePath.append(filePart).append(File.separator);
}
fileName = filePath.substring(0, filePath.length() - 1);
File out = new File(descDir + File.separator + fileName.trim());
if (!out.exists()) {
// 相对路径可能多级,可能需要创建父目录.
if (!out.getParentFile().exists()) {
out.getParentFile().mkdirs();
}
out.createNewFile();
}
@Cleanup FileOutputStream os = new FileOutputStream(out);
archive.extractFile(fileHeader, os);
}
fileHeader = archive.nextFileHeader();
}
} catch (IOException | RarException e) {
e.printStackTrace();
}
}
/**
* @description: 解压tar文件
* @param [inputStream, unTarPath]
* @return void
* @author wrt
* @date 2022/4/7 15:03
*/
public static void unTarFile(InputStream inputStream, String descDir) {
FileInputStream fis = null;
try (TarArchiveInputStream tis = new TarArchiveInputStream(inputStream)) {
TarArchiveEntry nte = null;
while ((nte = tis.getNextTarEntry()) != null) {
String dir = descDir + File.separator + nte.getName();
FileOutputStream fos = null;
BufferedOutputStream bos = null;
try {
if (nte.isDirectory()) {
File file1 = new File(dir);
file1.mkdirs();
} else {
File file2 = new File(dir);
fos = new FileOutputStream(file2);
bos = new BufferedOutputStream(fos);
IOUtils.copy(tis, bos);
}
} catch (Exception e) {
e.printStackTrace();
} finally {
if (bos != null) {
bos.close();
}
if (fos != null) {
fos.close();
}
}
}
} catch (IOException e) {
e.printStackTrace();
}
}
/**
* @description: 获取文件夹下所有文件
* @param [obj]
* @return java.util.List<java.io.File>
* @author wrt
* @date 2022/4/7 15:31
*/
public static List<File> getListFiles(Object obj) {
File directory = null;
if (obj instanceof File) {
directory = (File) obj;
} else {
directory = new File(obj.toString());
}
ArrayList<File> files = new ArrayList<File>();
if (directory.isFile()) {
files.add(directory);
return files;
} else if (directory.isDirectory()) {
File[] fileArr = directory.listFiles();
for (int i = 0; i < fileArr.length; i++) {
File fileOne = fileArr[i];
files.addAll(getListFiles(fileOne));
}
}
return files;
}
}