版权声明： https://blog.csdn.net/qq_18298439/article/details/82150761
最近在做web网盘的系统，网盘最基本的功能便是文件上传，但是文件上传当遇到大文件的时候，在web端按传统方式上传简直是灾难，所以大文件上传可以采用分片上传的办法。其主要思路是：1.大文件上传时进行分片；2.分片上传；3.对分片文件进行合并。
思路比较清晰简单，但一些问题在于：1.大文件如何进行分片？2.分片如何进行记录和存储？3.如何校验每个分片文件的唯一性和顺序性？4.如何合并文件？
对于大文件如何分片，这个主要是在前端进行解决，在这里推荐大家用百度的WebUploader来实现前端所需。
对于对分片之后的文件进行存储的问题，我采用了临时文件存储的办法，临时文件存储着每个分块对应字节位的状态。
对于分片文件的区分，这里可以采用MD5码的方式（不清楚MD5码的可以先查一下），MD5码简单理解就像每个文件的身份证一样，每个不同的文件都有自己唯一的MD5码。
对于合并文件的时候，前端在对文件分片之后，在请求服务端合并的时候，请求中要带上分片序号和大小，服务器按照请求数据中给的分片序号和每片分块大小算出开始位置，与读取到的文件片段数据，写入文件即可。这里合并后的文件会存储俩个路径，一个是当前网盘目录下的路径，一个是真实的永久路径（目的是为了实现秒传的功能）。
前端分片的代码就不贴了，主要用的百度的WebUploader。
这里主要贴一些服务端的主要的代码
文件上传
/**
* 上传文件
*
* @param file 文件
* @param wholeMd5 文件整体md5码
* @param name 文件名
* @param type 文件类型
* @param lastModifiedDate 上传时间
* @param size 文件大小
* @param chunks 文件分块数
* @param chunk 正在执行的块
*/
@ApiOperation(value = "文件上传", hidden = true)
@IgnoreUserToken
@ApiResponses({
@ApiResponse(code = 500, response = RestError.class, message = "错误")
})
@PostMapping(value = "upload")
public ResponseEntity<Integer> fileUpload(@ApiParam(name = "文件") @RequestPart MultipartFile file,
@ApiParam(name = "md5") @RequestParam String wholeMd5,
@ApiParam(name = "名称") @RequestParam String name,
@ApiParam(name = "类型") @RequestParam String type,
@ApiParam(name = "日期") @RequestParam Date lastModifiedDate,
@ApiParam(name = "大小") @RequestParam long size,
@ApiParam(name = "开始位置") @RequestParam long start,
@ApiParam(name = "结束位置") @RequestParam long end,
@ApiParam(name = "总分块数") @RequestParam(name = "chunks", defaultValue = "1") int chunks,
@ApiParam(name = "第几个分块,从0开始") @RequestParam(name = "chunk", defaultValue = "0") int chunk) {
try {
log.info("文件开始上传");
this.fileServiceImpl.fileUpload(file.getInputStream(), wholeMd5, name, type, lastModifiedDate, size, chunks, chunk, start, end);
return ResponseEntity.ok(1);
} catch (Exception e) {
return new ResponseEntity(RestError.IO_ERROR.setReason(e.getMessage()).toString(), HttpStatus.INTERNAL_SERVER_ERROR);
}
} @Override
public boolean fileUpload(InputStream fileIS,
String wholeMd5,
String name, String type,
Date lastModifiedDate, long size,
int chunks,
int chunk,
long start,
long end) throws Exception {
boolean result = false;
try {
File tempDirFile = new File(fileDir, TEMP_DIR);
if (!tempDirFile.exists()) {
tempDirFile.mkdirs();
}
// 块目录文件夹
File wholeMd5FileDirectory = new File(tempDirFile.getAbsolutePath(), wholeMd5);
if (!wholeMd5FileDirectory.exists()) {
wholeMd5FileDirectory.mkdirs();
}
// 块文件
File chunkFile = new File(wholeMd5FileDirectory.getAbsolutePath(), chunk + FILE_SEPARATOR + chunks + FILE_EXT);
long chunkSize = end - start;
if (!chunkFile.exists() || chunkFile.length() != chunkSize) {
// 创建新的块文件
long startTime = System.currentTimeMillis();
log.info("创建建分片{} - {} ", start, end);
int length = StreamUtils.copy(fileIS, new FileOutputStream(chunkFile));
long endTime = System.currentTimeMillis();
log.info("分片上传耗时{}毫秒", (endTime - startTime));
if (length == (end - start)) {
result = true;
}
}
} catch (Exception e) {
log.error("文件上传出错{}", e.getCause());
e.printStackTrace();
throw e;
}
return result;
}检查文件的MD5
/**
* 检查文件的md5
*
* @param md5 文件md5
* @param fileSize 文件大小
* @return
*/
@ApiOperation(value = "检查文件的md5")
@GetMapping(value = "checkFileMd5/{md5}/{fileSize}/{md5CheckLength}")
@ApiResponses({
@ApiResponse(code = 500, response = RestError.class, message = "错误")
})
public ResponseEntity<Integer> checkFileMd5(@ApiParam("文件md5码") @PathVariable String md5,
@ApiParam("文件大小") @PathVariable long fileSize,
@ApiParam("文件用来检查md5的长度") @PathVariable long md5CheckLength) {
try {
log.info("开始检验md5[{}],是否存在", md5);
return ResponseEntity.ok(this.fileServiceImpl.checkFileMd5(md5, fileSize, md5CheckLength) ? 1 : 0);
} catch (Exception e) {
return new ResponseEntity(RestError.DATABASE_ERROR.setReason(e.getMessage()).toString(), HttpStatus.INTERNAL_SERVER_ERROR);
}
} @Override
public boolean checkFileMd5(String md5, long fileSize, long md5CheckLength) {
Optional<UploadFileInfo> uploadFileInfo = this.uploadFileDao.findByMd5AndSize(md5, fileSize);
boolean isExist = false;
if (uploadFileInfo.isPresent()) {
File wholeFile = new File(this.fileDir, uploadFileInfo.get().getDfsPath());
if (wholeFile.exists() && wholeFile.length() == fileSize && md5.equals(FileUtils.md5(wholeFile, 0, md5CheckLength))) {
isExist = true;
}
}
log.info("{}的文件{}存在", md5, isExist ? "" : "不");
return isExist;
}检查分片是否存在
/**
* 检查分片是否存在
*
* @param md5
* @param chunk
* @param chunks
* @param chunkStart
* @param chunkEnd
* @return
*/
@ApiOperation(value = "检查分片是否存在")
@ApiResponses({
@ApiResponse(code = 500, response = RestError.class, message = "错误")
})
@GetMapping(value = "checkChunk/{md5}/{blockMd5}/{md5CheckLength}/{chunk}/{chunks}/{chunkStart}/{chunkEnd}")
public ResponseEntity<Integer> checkChunk(@ApiParam("文件md5码") @PathVariable String md5,
@ApiParam("分块文件md5码") @PathVariable String blockMd5,
@ApiParam("用来检测分块文件md5码的长度") @PathVariable long md5CheckLength,
@ApiParam("第几个分块,从0开始") @PathVariable int chunk,
@ApiParam("总分块数") @PathVariable int chunks,
@ApiParam("分块开始位于的文件位置") @PathVariable long chunkStart,
@ApiParam("分块结束位于的文件位置") @PathVariable long chunkEnd) {
try {
log.info("开始检验分片[{}]-[{}]的md5[{}],是否存在", chunk, chunks, blockMd5);
return ResponseEntity.ok(this.fileServiceImpl.checkChunk(md5, blockMd5, md5CheckLength, chunk, chunks, chunkStart, chunkEnd) ? 1 : 0);
} catch (Exception e) {
return new ResponseEntity(RestError.DATABASE_ERROR.setReason(e.getMessage()).toString(), HttpStatus.INTERNAL_SERVER_ERROR);
}
} @Override
public boolean checkChunk(String md5, String blockMd5, long md5CheckLength, int chunk, int chunks, long chunkStart, long chunkEnd) {
boolean isExist = false;
File chunkFile = new File(fileDir, TEMP_DIR + File.separator + md5 + File.separator + chunk + FILE_SEPARATOR + chunks + FILE_EXT);
if (chunkFile.exists() && chunkFile.length() == (chunkEnd - chunkStart)) {
String calBlockMd5 = FileUtils.md5(chunkFile, 0, md5CheckLength);
if (blockMd5.equals(calBlockMd5)) {
isExist = true;
}
}
log.info("{}的{}-{}分块{}存在", md5, chunk, chunks, isExist ? "" : "不");
return isExist;
}合并文件
/**
* 合并文件
*
* @param fileInfo
* @return
*/
@ApiOperation(value = "合并文件", notes = "把分片上传的数据合并到一个文件")
@ApiResponses({
@ApiResponse(code = 500, response = RestError.class, message = "错误")
})
@PostMapping(value = "mergeChunks")
public ResponseEntity<Integer> mergeChunks(@Validated @RequestBody FileInfo fileInfo, BindingResult bindingResult) {
log.info("开始合并文件");
if (bindingResult.hasErrors()) {
log.error("错误的参数请求");
return new ResponseEntity("错误的参数请求", HttpStatus.BAD_REQUEST);
} else {
try {
DataEntity dataEntity = this.fileServiceImpl.mergeChunks(fileInfo);
log.info("合并文件完成, 保存的dataEntityId为:{}", dataEntity != null ? dataEntity.getId() : null);
return ResponseEntity.ok(dataEntity != null ? 1 : 0);
} catch (FileMargeException e) {
log.error(e.getMessage(), e);
return new ResponseEntity(RestError.FILE_MARGE_ERROR.setReason(e.getMessage()).toString(), HttpStatus.INTERNAL_SERVER_ERROR);
} catch (FileNotAllException e) {
log.error(e.getMessage(), e);
return new ResponseEntity(RestError.FILE_NOTALL_ERROR.setReason(e.getMessage()).toString(), HttpStatus.INTERNAL_SERVER_ERROR);
} catch (IOException e) {
log.error(e.getMessage(), e);
return new ResponseEntity(RestError.IO_ERROR.setReason(e.getMessage()).toString(), HttpStatus.INTERNAL_SERVER_ERROR);
}
}
} /**
* 合并文件
*
* @param fileInfo
* @return {DataEntity}
* @throws FileNotAllException
* @throws IOException
*/
@Override
public DataEntity mergeChunks(FileInfo fileInfo) throws IOException, FileNotAllException, FileMargeException {
// 先检查库里是否有文件的存记录
Optional<UploadFileInfo> uploadFileInfoOptional = this.uploadFileDao.findByMd5AndSize(fileInfo.getMd5(), fileInfo.getSize());
log.info("检查文件信息是否在数据库中存在");
UploadFileInfo uploadFileInfo = null;
if (uploadFileInfoOptional.isPresent()) {
log.info("文件信息:{}", fileInfo);
uploadFileInfo = uploadFileInfoOptional.get();
}
if (uploadFileInfo == null) {
uploadFileInfo = new UploadFileInfo();
}
//再检查文件是否存在
log.info("检查真实文件");
File wholeFile = new File(getRealFileRoot(), fileInfo.getMd5() + FILE_SEPARATOR + fileInfo.getName());
if (!wholeFile.exists() || wholeFile.length() != fileInfo.getSize()) {
log.info("文件不存在或者文件长度不符合! }");
if (wholeFile.exists()) {
log.info("长度为{}!={},", wholeFile.length(), fileInfo.getSize());
}
File tempDirFile = new File(fileDir, TEMP_DIR + File.separator + fileInfo.getMd5());
try {
if (tempDirFile.exists()) {
log.info("文件分片目录存在");
// 获取该目录下所有的碎片文件
File[] partFiles = tempDirFile.listFiles((f, name) -> name.endsWith(FILE_EXT));
log.info("文件分片个数为:", partFiles.length);
if (partFiles.length > 0) {
Arrays.sort(partFiles, (File f1, File f2) -> {
String name1 = f1.getName();
String name2 = f2.getName();
if (name1.length() < name2.length()) {
return -1;
} else if (name1.length() > name2.length()) {
return 1;
} else {
return name1.compareTo(name2);
}
});
long size = 0;
FileChannel resultFileChannel = new FileOutputStream(wholeFile, true).getChannel();
for (int i = 0; i < partFiles.length; i++) {
size += partFiles[i].length();
if (size > wholeFile.length()) {
log.info("合并第{}块的文件{}", i, partFiles[i].getName());
// FileUtils.copy(partFiles[i], wholeFile, size);
FileChannel inChannel = new FileInputStream(partFiles[i]).getChannel();
resultFileChannel.transferFrom(inChannel, resultFileChannel.size(), inChannel.size());
inChannel.close();
}
}
if (size < wholeFile.length()) {
log.info("分片文件不完整");
throw new FileNotAllException();
}
}
log.info("删除分片数据信息");
this.threadPoolUtil.getExecutor().execute(() -> {
tempDirFile.listFiles(child -> child.delete());
tempDirFile.delete();
});
}
} catch (Exception e) {
throw new FileMargeException();
}
}
if (uploadFileInfo.getId() == null) {
log.info("保存上传的文件信息");
uploadFileInfo.setCreateTime(fileInfo.getCreateTime());
uploadFileInfo.setMd5(fileInfo.getMd5());
uploadFileInfo.setType(fileInfo.getType());
uploadFileInfo.setSize(wholeFile.length());
uploadFileInfo.setDfsPath(wholeFile.getAbsolutePath().substring(this.fileDir.length()+1));
this.uploadFileDao.save(uploadFileInfo);
}
// 文件大小, 应该在合并完成的时候更新
log.info("获取父目录信息");
DataEntity parent = this.getDataEntityById(fileInfo.getParentId());
// 如果文件信息里包含文件的相对路径, 就应该创建文件上传的真实目录
String path = fileInfo.getPath();
if (StringUtils.hasText(path)) {
log.info("包含相对目录,进行相对目录的创建");
path = FilenameUtils.getFullPathNoEndSeparator(path);
String[] paths = path.split("/");
for (String tempPath : paths) {
if (StringUtils.hasText(tempPath)) {
DataEntity dataEntity = this.dataEntityDao.findByNameAndParentAndUserId(tempPath, parent, UserUtil.getUserId());
if (dataEntity == null) {
dataEntity = new DataEntity();
dataEntity.setName(tempPath);
dataEntity.setDir(true);
dataEntity.setParent(parent);
parent = this.dataEntityDao.save(dataEntity);
} else {
parent = dataEntity;
}
}
}
}
log.info("创建目录信息");
DataEntity dataEntity = new DataEntity();
dataEntity.setName(fileInfo.getName());
dataEntity.setExt(fileInfo.getExt());
dataEntity.setDataType(fileInfo.getFileType());
dataEntity.setFileInfo(uploadFileInfo);
dataEntity.setParent(parent);
dataEntity.setSize(uploadFileInfo.getSize());
dataEntity = this.saveAndRenameFile(dataEntity);
this.saveAndCreateFile(dataEntity);
//判断上传文件的类型，选择调用解析接口
String fileType = fileInfo.getFileType();
if ("images".equals(fileType)||"vector".equals(fileType)||"terrain".equals(fileType)||"original".equals(fileType)) {
String resultInfo = analysis(dataEntity,fileInfo);
log.info("解析结果："+resultInfo);
}
return dataEntity;
}
关于秒传功能，其实原理就是检验文件MD5，在一个文件上传前先获取文件内容MD5值或者部分取值MD5，然后在查找自己的记录是否已存在相同的MD5，如果存在就直接从服务器真实路径取，而不需要重新进行分片上传了，从而达到秒传的效果。