Copyright: arbitrary, seeding https://blog.csdn.net/qq_32662595/article/details/88189956!
- Upload the compressed file to the server
public List<FileVo> uploadFile(HttpSession session, MultipartFile[] files, String path, String user) {
for (MultipartFile file : files) {
if (!file.isEmpty()) {
String originalName = file.getOriginalFilename();
File savedFile = new File(path, originalName);
try {
FileUtils.copyInputStreamToFile(file.getInputStream(), savedFile);
} catch (IOException e) {
Logger.error("文件上传失败！");
}
try {
Fileupload upLoadFile = new Fileupload();
BeanUtils.copyProperties(fv, upLoadFile);
//.......可以添加文件上传记录
} catch (Exception e) {
//如果当前文件解析失败，继续解析下一个文件
//此处可添加错误文件解析记录
continue;
}
}
}
return allFiles;
}
返回上传完成的文件的信息，重点是文件保存的路径及文件名
-
unzip files
There are three forms of compressed files: JAR / ZIP / RAR
public void decompressFile(String url, String fileName, String fileType, String encode) {
if (StringUtils.isNotBlank(fileType.toUpperCase())) {
switch (fileType.toUpperCase()) {
case MYJZConfig.UPLOADDECOMPRESSTYPE_JAR:
ZipOrJarFileAction.getJarFileDecompression(url + fileName, url);
break;
case MYJZConfig.UPLOADDECOMPRESSTYPE_ZIP:
ZipOrJarFileAction.getDecompressionFile(url + fileName, url, encode);
break;
case MYJZConfig.UPLOADDECOMPRESSTYPE_RAR:
ZipOrJarFileAction.unrar(url + fileName, url);
break;
default:
throw new CustomException("目前支持JAR、ZIP、RAR,压缩文件类型不支持！");
}
}
}
解析JAR：
public static String getJarFileDecompression(String jarFilePath, String decompressionJarPath) {
JarFile jarFile = null;
File saveDir = new File(decompressionJarPath);
if (saveDir.isDirectory()) {
saveDir.mkdirs();
}
InputStream is = null;
FileOutputStream fos = null;
try {
jarFile = new JarFile(jarFilePath);
Enumeration<JarEntry> jarItems = jarFile.entries();
while (jarItems.hasMoreElements()) {
JarEntry jarItem = jarItems.nextElement();
// 判断是否是文件夹
if (!jarItem.isDirectory()) {
int index = jarItem.getName().lastIndexOf("/");
String dir = "";
if (index > 0) {
dir = jarItem.getName().substring(0, index);
}
new File(decompressionJarPath + dir).mkdirs();
File newFile = new File(decompressionJarPath + jarItem.getName());
if (!newFile.exists()) {
newFile.createNewFile();
}
is = jarFile.getInputStream(jarItem);
fos = new FileOutputStream(newFile);
byte[] b = new byte[1024];
int len;
while ((len = is.read(b)) != -1) {
fos.write(b, 0, len);
}
}
}
} catch (IOException e) {
logger.error("JAR文件解压失败 !");
} finally {
closeAll(fos, is, null, null, null, jarFile);
}
return decompressionJarPath;
}
/**
* 关闭流 这个地方的书写特点是，流的关闭顺序一般是从输出流到输入流 例如如下代码: FileInputStream fis=new
* FileInputStream("D:/test.txt"); BufferedInputStream bis=new
* BufferedInputStream(fis); FileOutputStream fos=new
* FileOutputStream("D:/test1.txt"); BufferedOutputStream bos=new
* BufferedOutputStream(fos);
*
* 我们在进行流关闭时是自下而上，所以顺序是bos->fos->bis->fis
*
* 而用该方法来关闭是为了省略代码，技巧在于1）自己知道自己所用流的顺序2）传参数时的小技巧， 可以这样调用
* closeAll(fos,null,null,null,null); closeAll(null,bis,null,null,null);
* 这样就可以保证顺序不出错了
*
* @param fos
* 文件输出流
* @param is
* 输入流
* @param zf
* 压缩文件
* @param zos
* 压缩文件输出流
* @return null
*/
private static void closeAll(FileOutputStream fos, InputStream is, ZipFile zf, ZipOutputStream zos,
BufferedInputStream bis, JarFile jarFile) {
if (null != fos) {
try {
fos.close();
} catch (IOException e) {
fos = null;
}
}
if (null != bis) {
try {
bis.close();
} catch (IOException e) {
bis = null;
}
}
if (null != zos) {
try {
zos.close();
} catch (IOException e) {
zos = null;
}
}
if (null != is) {
try {
is.close();
} catch (IOException e) {
is = null;
}
}
if (null != zf) {
try {
zf.close();
} catch (IOException e) {
zf = null;
}
}
if (null != fos) {
try {
fos.close();
} catch (IOException e) {
fos = null;
}
}
if (null != is) {
try {
is.close();
} catch (IOException e) {
is = null;
}
}
if (null != jarFile) {
try {
jarFile.close();
} catch (IOException e) {
jarFile = null;
}
}
}
Decompression zip- "
public static String getDecompressionFile(String zipFilePath, String deCompressionPath, String readEncoding) {
FileOutputStream fos = null;
InputStream is = null;
ZipFile zipFileItems = null;
String zipPath = null;
try {
// 以指定格式打开zip文件
zipFileItems = new ZipFile(zipFilePath, Charset.forName(readEncoding));
// 介意后的文件夹名
zipPath = deCompressionPath + zipFileItems.getName();
// 获取zip文件的条目
Enumeration<? extends ZipEntry> items = zipFileItems.entries();
while (items.hasMoreElements()) {
// 压缩文件中当前的所操作文件或文件夹的对象
ZipEntry zipCurrentItem = items.nextElement();
/*
* zipCurrentItem的具体定位流程演示(每次循环的值) 1)/0_dir.txt 2)/1_dir.txt
* 3)/2_dir.txt 4)/3_dir.txt 5)/test/0_tes.txt 6)/test/1_tes.txt
* 7)/test/2_tes.txt 8)/test/3_tes.txt
*/
if (zipCurrentItem.isDirectory()) {// 遇到文件夹时深入文件夹递归
File newFile = new File(deCompressionPath + zipCurrentItem.getName());
if (!newFile.exists()) {
newFile.mkdirs();
}
} else {
// 获取当前条目文件的输入流
is = zipFileItems.getInputStream(zipCurrentItem);
byte[] b = new byte[1024];
File newFile = new File(deCompressionPath + zipCurrentItem.getName());
if (!newFile.exists()) {
new File(deCompressionPath).mkdirs();// 创建路径
newFile.createNewFile();
}
fos = new FileOutputStream(newFile);
int len;
while ((len = is.read(b)) != -1) {
fos.write(b, 0, len);
}
}
}
zipFileItems.close();
} catch (FileNotFoundException e) {
logger.error("你输入的文件路径有误，请检查文件路径及其后缀是否正确！");
} catch (IOException e) {
logger.error("文件流异常断开！");
} finally {
closeAll(fos, is, zipFileItems, null, null, null);
}
return zipPath;
}
Extract the rar:
public static void unrar(String orgPath, String disPath) {
Archive archive = null;
FileOutputStream fos = null;
try {
archive = new Archive(new NativeStorage(new File(orgPath)));
if (archive.isEncrypted()) {
}
FileHeader fh = archive.nextFileHeader();
File destFileName = null;
while (fh != null) {
String compressFileName = fh.getFileNameString().trim();
destFileName = new File(disPath + compressFileName);
if (fh.isDirectory()) {
if (!destFileName.exists()) {
destFileName.mkdirs();
}
fh = archive.nextFileHeader();
continue;
}
if (!destFileName.getParentFile().exists()) {
destFileName.getParentFile().mkdirs();
}
fos = new FileOutputStream(destFileName);
archive.extractFile(fh, fos);
fos.close();
fos = null;
fh = archive.nextFileHeader();
}
archive.close();
archive = null;
} catch (Exception e) {
throw new CustomException("RAR 文件解压异常！");
} finally {
if (fos != null) {
try {
fos.close();
} catch (Exception e) {
fos = null;
}
}
if (archive != null) {
try {
archive.close();
} catch (Exception e) {
archive = null;
}
}
}
}
- Parsing the file contents
public static DecompressVo parseHtml(String path) {
// 网页数据
Document doc = Jsoup.parse(readHtml(path));
Map<String, String> dataMap = new HashMap<>();
// 查询基本信息
List<String> baseInfo = new LinkedList<>();
Elements peronalAndOffices = doc.getElementsByTag("section");
if (peronalAndOffices != null) {
for (Element peronalAndOffice : peronalAndOffices) {
Elements pTagInfos = peronalAndOffice.getElementsByTag("p");
for (Element ptag : pTagInfos) {
if (ptag.hasText()) {
if (ptag.childNodes().size() < 2) {
if (("Photo").equalsIgnoreCase(ptag.text())) {
// 获取图片路径
Elements pics = peronalAndOffice.getElementsByTag("img");
for (Element pic : pics) {
// 将获取到的图片进行base64编码
dataMap.put("photo", pic.attr("src"));
}
}
} else {
Elements perosonals = ptag.children();
for (Element personal : perosonals) {
baseInfo.add(personal.text());
}
}
}
}
}
}
for (int i = 0; i < baseInfo.size(); i += 2) {
if (StringUtils.isNotBlank(baseInfo.get(i))) {
dataMap.put(baseInfo.get(i), baseInfo.get(i + 1));
}
}
// 记录
List<List<String>> attendList = new ArrayList<>();
List<List<String>> docList = new ArrayList<>();
Elements attendAndDocment = doc.getElementsByTag("table");
if (null != attendAndDocment && attendAndDocment.size() == 2) {
Element attends = attendAndDocment.get(0);
Elements attendTr = attends.getElementsByTag("tr");
for (Element tr : attendTr) {
Elements contents = tr.getElementsByTag("td");
if (null != contents && !contents.isEmpty()) {
List<String> tds = new LinkedList<>();
for (Element td : contents) {
tds.add(td.text());
}
if (tds.size() > 1) {
attendList.add(tds);
}
}
}
// 文档信息
Element docs = attendAndDocment.get(1);
Elements docsTr = docs.getElementsByTag("tr");
for (Element docTr : docsTr) {
Elements docContent = docTr.getElementsByTag("td");
if (null != docContent && !docContent.isEmpty()) {
List<String> doctd = new LinkedList<>();
for (Element dct : docContent) {
doctd.add(dct.text());
}
if (doctd.size() > 1) {
docList.add(doctd);
}
}
}
}
DecompressVo decompressVo = new DecompressVo();
decompressVo.setBaseInfo(dataMap);
decompressVo.setAttends(attendList);
decompressVo.setDocs(docList);
return decompressVo;
}
- The data stored in the database
public void analysis(HttpSession session, String sessionAttr, String url, String suffix) {
// 递归文件夹，获取文件家中的html文件
List<String> paths = TraversalFile.getFileUrlByTraversal(url, suffix);
if (!CollectionUtils.isEmpty(paths)) {
int count = 0;
for (String path : paths) {
// 百分比进度
count++;
double total = paths.size();
session.setAttribute(sessionAttr, (int) ((count / total) * 100));
DecompressVo datas = HtmlParser.parseHtml(path);
/**
* {Email=NA, Registered by=admin,
* photo=../upload_teaching/f54cb43e0212b28e982891c40642c5ca,
* Gender=Female, Name=tenzin dolma, Parent name=dharpo, Home
* address=NA, Local address=TIPA BOY HOSTEL, TIPA.. MCLEOD
* GANJ, DHARAMSHALA - 1762 19, HP, INDIA, SNO=10 DS,
* Remarks=contact no. 9882270774, Phone=NA, Region=Dhasa,
* Country=Tibet, Registered date=2016-Dec-13 12:09}
*
* 保存到数据库 1. 保存基本信息
*
* 2. 保存会议信息
*
* 3. 保存文档信息
*/
// 获取照片地址
String photoMd5 = null;
String photo = datas.getBaseInfo().get("photo");
if (StringUtils.isNotBlank(photo)) {
File file = new File(path);
String dir = file.getParentFile().getParent();
photo = photo.replace("..", "");
photo = dir + photo;
photoMd5 = MD5Utils.encryptToBase64(photo);
}
OdmsPeronalOfficealWithBLOBs odOfficeal = new OdmsPeronalOfficealWithBLOBs();
odOfficeal.setId(UUIDUtils.getUUID() + "_" + datas.getBaseInfo().get("Name"));
odOfficeal.setEmail(datas.getBaseInfo().get("Email"));
odOfficeal.setRegisteredby(datas.getBaseInfo().get("Registered by"));
odOfficeal.setGender(datas.getBaseInfo().get("Gender"));
odOfficeal.setName(datas.getBaseInfo().get("Name"));
odOfficeal.setHomeaddress(datas.getBaseInfo().get("Home address"));
odOfficeal.setLocaladdress(datas.getBaseInfo().get("Local address"));
odOfficeal.setSno(datas.getBaseInfo().get("SNO"));
odOfficeal.setRemarks(datas.getBaseInfo().get("Remarks"));
odOfficeal.setPhone(datas.getBaseInfo().get("Phone"));
odOfficeal.setRegion(datas.getBaseInfo().get("Region"));
odOfficeal.setCountry(datas.getBaseInfo().get("Country"));
odOfficeal.setRegistereddate(datas.getBaseInfo().get("Registered date"));
odOfficeal.setParentname(datas.getBaseInfo().get("Parent name"));
odOfficeal.setPhoto(photo);
odOfficeal.setPhotomd5(photoMd5);
try {
peronalOfficealMapper.insertSelective(odOfficeal);
} catch (Exception e) {
continue;
}
// 会议
List<List<String>> attends = datas.getAttends();
if (!CollectionUtils.isEmpty(attends)) {
for (List<String> list : attends) {
OdmsTeachingattendance attend = new OdmsTeachingattendance();
attend.setPersonalid(odOfficeal.getId());
attend.setTeachingname(list.get(0));
attend.setCategory(list.get(1));
attend.setAddedby(list.get(2));
attend.setRdata(list.get(3));
attendMapper.insertSelective(attend);
}
}
// 文档
List<List<String>> docs = datas.getDocs();
if (!CollectionUtils.isEmpty(docs)) {
for (List<String> doc : docs) {
OdmsDocuments data = new OdmsDocuments();
data.setPersonalid(odOfficeal.getId());
data.setRdate(doc.get(0));
data.setCategory(doc.get(2));
data.setEnteredby(doc.get(1));
data.setNumber(doc.get(3));
documentMapper.insertSelective(data);
}
}
}
}
}
- Gets the index of the specified file type
public static List<String> getFileUrlByTraversal(String dir, String suffix) {
List<String> paths = new ArrayList<String>();
paths = getAllFilePaths(new File(dir), paths, suffix);
logger.info(paths.toString());
return paths;
}
private static List<String> getAllFilePaths(File filePath, List<String> filePaths, String suffix) {
File[] files = filePath.listFiles();
if (files == null) {
return filePaths;
}
for (File f : files) {
if (f.isDirectory()) {
getAllFilePaths(f, filePaths, suffix);
} else {
if (StringUtils.isNotBlank(suffix)) {
if (f.getName().endsWith(suffix)) {
String pu = f.getPath();
filePaths.add(pu);
}
} else {
filePaths.add(f.getPath());
}
}
}
return filePaths;
}
Focus is on the use of JSOUP
this ..., parsing completed