背景
最近好幾個專案在運行程序中客戶都提出檔案上傳大小的限制能否設定的大一些，用戶經常需要上傳好幾個G的資料檔案，如圖紙，視頻等，并且需要在上傳大檔案程序中進行優化實時展現進度條，進行技術評估后針對框架檔案上傳進行擴展升級，擴展介面支持大檔案分片上傳處理，減少服務器瞬時的記憶體壓力，同一個檔案上傳失敗后可以從成功上傳分片位置進行斷點續傳，檔案上傳成功后再次上傳無需等待達到秒傳的效果，優化用戶互動體驗，具體的實作流程如下圖所示
檔案MD5計算
對于檔案md5的計算我們使用spark-md5第三方庫，大檔案我們可以分片分別計算再合并節省時間，但是經測驗1G檔案計算MD5需要20s左右的時間，所以經過優化我們抽取檔案部分特征資訊（檔案第一片+檔案最后一片+檔案修改時間），來保證檔案的相對唯一性，只需要2s左右，大大提高前端計算效率，對于前端檔案內容塊的讀取我們需要使用html5的api中fileReader.readAsArrayBuffer方法，因為是異步觸發，封裝的方法提供一個回呼函式進行使用
createSimpleFileMD5(file, chunkSize, finishCaculate) {
var fileReader = new FileReader();
var blobSlice = File.prototype.mozSlice || File.prototype.webkitSlice || File.prototype.slice;
var chunks = Math.ceil(file.size / chunkSize);
var currentChunk = 0;
var spark = new SparkMD5.ArrayBuffer();
var startTime = new Date().getTime();
loadNext();
fileReader.onload = function() {
spark.append(this.result);
if (currentChunk == 0) {
currentChunk = chunks - 1;
loadNext();
} else {
var fileMD5 = hpMD5(spark.end() + file.lastModifiedDate);
finishCaculate(fileMD5)
}
};
function loadNext() {
var start = currentChunk * chunkSize;
var end = start + chunkSize >= file.size ? file.size : start + chunkSize;
fileReader.readAsArrayBuffer(blobSlice.call(file, start, end));
}
}
檔案分片切割
我們通過定義好檔案分片大小，使用blob物件支持的file.slice方法切割檔案，分片上傳請求需要同步按順序請求，因為使用了同步請求，前端ui會阻塞無法點擊，需要開啟worker執行緒進行操作，完成后通過postMessage方法傳遞訊息給主頁面通知ui進度條的更新，需要注意的是，worker執行緒方法不支持window物件，所以盡量不要使用第三方庫，使用原生的XMLHttpRequest物件發起請求，需要的引數通過onmessage方法傳遞獲取
頁面upload請求方法如下
upload() {
var file = document.getElementById("file").files[0];
if (!file) {
alert("請選擇需要上傳的檔案");
return;
}
if (file.size < pageData.chunkSize) {
alert("選擇的檔案請大于" + pageData.chunkSize / 1024 / 1024 + "M")
}
var filesize = file.size;
var filename = file.name;
pageData.chunkCount = Math.ceil(filesize / pageData.chunkSize);
this.createSimpleFileMD5(file, pageData.chunkSize, function(fileMD5) {
console.log("計算檔案MD：" + fileMD5);
pageData.showProgress = true;
var worker = new Worker('worker.js');
var param = {
token: GetTokenID(),
uploadUrl: uploadUrl,
filename: filename,
filesize: filesize,
fileMD5: fileMD5,
groupguid: pageData.groupguid1,
grouptype: pageData.grouptype1,
chunkCount: pageData.chunkCount,
chunkSize: pageData.chunkSize,
file: file
}
worker.onmessage = function(event) {
var workresult = event.data;
if (workresult.code == 0) {
pageData.percent = workresult.percent;
if (workresult.percent == 100) {
pageData.showProgress = false;
worker.terminate();
}
} else {
pageData.showProgress = false;
worker.terminate();
}
}
worker.postMessage(param);
})
}
worker.js執行方法如下
function FormAjax_Sync(token, data, url, success) {
var xmlHttp = new XMLHttpRequest();
xmlHttp.open("post", url, false);
xmlHttp.setRequestHeader("token", token);
xmlHttp.onreadystatechange = function() {
if (xmlHttp.status == 200) {
var result = JSON.parse(this.responseText);
var status = this.status
success(result, status);
}
};
xmlHttp.send(data);
}
onmessage = function(evt) {
var data = https://www.cnblogs.com/yanpeng19940119/p/evt.data;
console.log(data)
//傳遞的引數
var token = data.token
var uploadUrl = data.uploadUrl
var filename = data.filename
var fileMD5 = data.fileMD5
var groupguid = data.groupguid
var grouptype = data.grouptype
var chunkCount = data.chunkCount
var chunkSize = data.chunkSize
var filesize = data.filesize
var filename = data.filename
var file = data.file
var start = 0;
var end;
var index = 0;
var startTime = new Date().getTime();
while (start < filesize) {
end = start + chunkSize;
if (end > filesize) {
end = filesize;
}
var chunk = file.slice(start, end); //切割檔案
var formData = new FormData();
formData.append("file", chunk, filename);
formData.append("fileMD5", fileMD5);
formData.append("chunkCount", chunkCount)
formData.append("chunkIndex", index);
formData.append("chunkSize", end - start);
formData.append("groupguid", groupguid);
formData.append("grouptype", grouptype);
//上傳檔案
FormAjax_Sync(token, formData, uploadUrl, function(result, status) {
var code = 0;
var percent = 0;
if (result.code == 0) {
console.log("分片共" + chunkCount + "個" + ",已成功上傳第" + index + "個")
percent = parseInt((parseInt(formData.get("chunkIndex")) + 1) * 100 / chunkCount);
} else {
filesize = -1;
code = -1
console.log("分片第" + index + "個上傳失敗")
}
self.postMessage({ code: code, percent: percent });
})
start = end;
index++;
}
console.log("上傳分片總時間：" + (new Date().getTime() - startTime));
console.log("分片完成");
}
檔案分片接收
前端檔案分片處理完畢后，接下來我們詳細介紹下后端檔案接受處理的方案，分片處理需要支持用戶隨時中斷上傳與檔案重復上傳，我們新建表f_attachchunk來記錄檔案分片的詳細資訊，表結構設計如下
CREATE TABLE `f_attachchunk` (
`ID` int(11) NOT NULL AUTO_INCREMENT,
`ChunkGuid` varchar(50) NOT NULL,
`FileMD5` varchar(100) DEFAULT NULL,
`FileName` varchar(200) DEFAULT NULL,
`ChunkSize` int(11) DEFAULT NULL,
`ChunkCount` int(11) DEFAULT NULL,
`ChunkIndex` int(11) DEFAULT NULL,
`ChunkFilePath` varchar(500) DEFAULT NULL,
`UploadUserGuid` varchar(50) DEFAULT NULL,
`UploadUserName` varchar(100) DEFAULT NULL,
`UploadDate` datetime DEFAULT NULL,
`UploadOSSID` varchar(200) DEFAULT NULL,
`UploadOSSChunkInfo` varchar(1000) DEFAULT NULL,
`ChunkType` varchar(50) DEFAULT NULL,
`MergeStatus` int(11) DEFAULT NULL,
PRIMARY KEY (`ID`)
) ENGINE=InnoDB AUTO_INCREMENT=237 DEFAULT CHARSET=utf8mb4;
- FileMD5：檔案MD5唯一標識檔案
- FileName：檔案名稱
- ChunkSize：分片大小
- ChunkCount：分片總數量
- ChunkIndex：分片對應序號
- ChunkFilePath：分片存盤路徑（本地存盤檔案方案使用）
- UploadUserGuid：上傳人主鍵
- UploadUserName：上傳人姓名
- UploadDate：上傳人日期
- UploadOSSID：分片上傳批次ID（云存盤方案使用）
- UploadOSSChunkInfo：分片上傳單片資訊（云存盤方案使用）
- ChunkType：分片存盤方式（本地存盤，阿里云，華為云，Minio標識）
- MergeStatus：分片合并狀態（未合并，已合并）
檔案分片存盤后端一共分為三步，檢查分片=》保存分片=》合并分片，我們這里先以本地檔案存盤為例講解，云存盤思路一致，后續會提供對應使用的api方法
檢查分片
檢查分片以資料庫檔案分片記錄的FIleMD5與ChunkIndex組合來確定分片的唯一性，因為本地分片temp檔案是作為臨時檔案存盤，可能會出現手動清除施放磁盤空間的問題，所以資料庫存在記錄我們還需要對應的檢查實際檔案情況
boolean existChunk = false;
AttachChunkDO dbChunk = attachChunkService.checkExistChunk(fileMD5, chunkIndex, "Local");
if (dbChunk != null) {
File chunkFile = new File(dbChunk.getChunkFilePath());
if (chunkFile.exists()) {
if (chunkFile.length() == chunkSize) {
existChunk = true;
} else {
//洗掉資料庫記錄
attachChunkService.delete(dbChunk.getChunkGuid());
}
} else {
//洗掉資料庫記錄
attachChunkService.delete(dbChunk.getChunkGuid());
}
}
保存分片
保存分片分為兩塊，檔案存盤到本地，成功后資料庫插入對應分片資訊
//獲取配置中附件上傳檔案夾
String filePath = frameConfig.getAttachChunkPath() + "/" + fileMD5 + "/";
//根據附件guid創建檔案夾
File targetFile = new File(filePath);
if (!targetFile.exists()) {
targetFile.mkdirs();
}
if (!existChunk) {
//保存檔案到檔案夾
String chunkFileName = fileMD5 + "-" + chunkIndex + ".temp";
FileUtil.uploadFile(FileUtil.convertStreamToByte(fileContent), filePath, chunkFileName);
//插入chunk表
AttachChunkDO attachChunkDO = new AttachChunkDO(fileMD5, fileName, chunkSize, chunkCount, chunkIndex, filePath + chunkFileName, "Local");
attachChunkService.insert(attachChunkDO);
}
合并分片
在上傳分片方法中，如果當前分片是最后一片，上傳完畢后進行檔案合并作業，同時進行資料庫合并狀態的更新，下一次同一個檔案上傳時我們可以直接拷貝之前合并過的檔案作為新附件，減少合并這一步驟的I/O操作，合并檔案我們采用BufferedOutputStream與BufferedInputStream兩個物件，固定緩沖區大小
if (chunkIndex == chunkCount - 1) {
//合并檔案
String merageFileFolder = frameConfig.getAttachPath() + groupType + "/" + attachGuid;
File attachFolder = new File(merageFileFolder);
if (!attachFolder.exists()) {
attachFolder.mkdirs();
}
String merageFilePath = merageFileFolder + "/" + fileName;
merageFile(fileMD5, merageFilePath);
attachChunkService.updateMergeStatusToFinish(fileMD5);
//插入到附件庫
//設定附件唯一guid
attachGuid = CommonUtil.getNewGuid();
attachmentDO.setAttguid(attachGuid);
attachmentService.insert(attachmentDO);
}
public void merageFile(String fileMD5, String targetFilePath) throws Exception {
String merageFilePath = frameConfig.getAttachChunkPath()+"/"+fileMD5+"/"+fileMD5+".temp";
File merageFile = new File(merageFilePath);
if(!merageFile.exists()){
BufferedOutputStream destOutputStream = new BufferedOutputStream(new FileOutputStream(merageFilePath));
List<AttachChunkDO> attachChunkDOList = attachChunkService.selectListByFileMD5(fileMD5, "Local");
for (AttachChunkDO attachChunkDO : attachChunkDOList) {
File file = new File(attachChunkDO.getChunkFilePath());
byte[] fileBuffer = new byte[1024 * 1024 * 5];//檔案讀寫快取
int readBytesLength = 0; //每次讀取位元組數
BufferedInputStream sourceInputStream = new BufferedInputStream(new FileInputStream(file));
while ((readBytesLength = sourceInputStream.read(fileBuffer)) != -1) {
destOutputStream.write(fileBuffer, 0, readBytesLength);
}
sourceInputStream.close();
}
destOutputStream.flush();
destOutputStream.close();
}
FileUtil.copyFile(merageFilePath,targetFilePath);
}
云檔案分片上傳
云檔案上傳與本地檔案上傳的區別就是，分片檔案直接上傳到云端，再呼叫云存盤api進行檔案合并與檔案拷貝，資料庫相關記錄與檢查差異不大
阿里云OSS
上傳分片前需要生成該檔案的分片上傳組標識uploadid
public String getUplaodOSSID(String key){
key = "chunk/" + key + "/" + key;
TenantParams.attach appConfig = getAttach();
OSSClient ossClient = InitOSS(appConfig);
String bucketName = appConfig.getBucketname_auth();
InitiateMultipartUploadRequest request = new InitiateMultipartUploadRequest(bucketName, key);
InitiateMultipartUploadResult upresult = ossClient.initiateMultipartUpload(request);
String uploadId = upresult.getUploadId();
ossClient.shutdown();
return uploadId;
}
上傳分片時需要指定uploadid，同時我們要將回傳的分片資訊PartETag序列化保存資料庫，用于后續的檔案合并
public String uploadChunk(InputStream stream,String key, int chunkIndex, int chunkSize, String uploadId){
key = "chunk/" + key + "/" + key;
String result = "";
try{
TenantParams.attach appConfig = getAttach();
OSSClient ossClient = InitOSS(appConfig);
String bucketName = appConfig.getBucketname_auth();
UploadPartRequest uploadPartRequest = new UploadPartRequest();
uploadPartRequest.setBucketName(bucketName);
uploadPartRequest.setKey(key);
uploadPartRequest.setUploadId(uploadId);
uploadPartRequest.setInputStream(stream);
// 設定分片大小，除了最后一個分片沒有大小限制，其他的分片最小為100 KB，
uploadPartRequest.setPartSize(chunkSize);
// 設定分片號，每一個上傳的分片都有一個分片號，取值范圍是1~10000，如果超出此范圍，OSS將回傳InvalidArgument錯誤碼，
uploadPartRequest.setPartNumber(chunkIndex+1);
// 每個分片不需要按順序上傳，甚至可以在不同客戶端上傳，OSS會按照分片號排序組成完整的檔案，
UploadPartResult uploadPartResult = ossClient.uploadPart(uploadPartRequest);
PartETag partETag = uploadPartResult.getPartETag();
result = JSON.toJSONString(partETag);
ossClient.shutdown();
}catch (Exception e){
logger.error("OSS上傳檔案Chunk失敗:" + e.getMessage());
}
return result;
}
合并分片時通過傳遞保存分片的PartETag物件陣列進行操作，為了附件獨立唯一性我們不直接使用合并后的檔案，通過api進行檔案拷貝副本使用
public boolean merageFile(String uploadId, List<PartETag> chunkInfoList,String key,AttachmentDO attachmentDO,boolean checkMerge){
key = "chunk/" + key + "/" + key;
boolean result = true;
try{
TenantParams.attach appConfig = getAttach();
OSSClient ossClient = InitOSS(appConfig);
String bucketName = appConfig.getBucketname_auth();
if(!checkMerge){
CompleteMultipartUploadRequest completeMultipartUploadRequest = new CompleteMultipartUploadRequest(bucketName, key, uploadId, chunkInfoList);
CompleteMultipartUploadResult completeMultipartUploadResult = ossClient.completeMultipartUpload(completeMultipartUploadRequest);
}
String attachKey = getKey(attachmentDO);
ossClient.copyObject(bucketName,key,bucketName,attachKey);
ossClient.shutdown();
}catch (Exception e){
e.printStackTrace();
logger.error("OSS合并檔案失敗:" + e.getMessage());
result = false;
}
return result;
}
華為云OBS
華為云api與阿里云api大致相同，只有個別引數名稱不同，直接上代碼
public String getUplaodOSSID(String key) throws Exception {
key = "chunk/" + key + "/" + key;
TenantParams.attach appConfig = getAttach();
ObsClient obsClient = InitOBS(appConfig);
String bucketName = appConfig.getBucketname_auth();
InitiateMultipartUploadRequest request = new InitiateMultipartUploadRequest(bucketName, key);
InitiateMultipartUploadResult result = obsClient.initiateMultipartUpload(request);
String uploadId = result.getUploadId();
obsClient.close();
return uploadId;
}
public String uploadChunk(InputStream stream, String key, int chunkIndex, int chunkSize, String uploadId) {
key = "chunk/" + key + "/" + key;
String result = "";
try {
TenantParams.attach appConfig = getAttach();
ObsClient obsClient = InitOBS(appConfig);
String bucketName = appConfig.getBucketname_auth();
UploadPartRequest uploadPartRequest = new UploadPartRequest();
uploadPartRequest.setBucketName(bucketName);
uploadPartRequest.setUploadId(uploadId);
uploadPartRequest.setObjectKey(key);
uploadPartRequest.setInput(stream);
uploadPartRequest.setOffset(chunkIndex * chunkSize);
// 設定分片大小，除了最后一個分片沒有大小限制，其他的分片最小為100 KB，
uploadPartRequest.setPartSize((long) chunkSize);
// 設定分片號，每一個上傳的分片都有一個分片號，取值范圍是1~10000，如果超出此范圍，OSS將回傳InvalidArgument錯誤碼，
uploadPartRequest.setPartNumber(chunkIndex + 1);
// 每個分片不需要按順序上傳，甚至可以在不同客戶端上傳，OSS會按照分片號排序組成完整的檔案，
UploadPartResult uploadPartResult = obsClient.uploadPart(uploadPartRequest);
PartEtag partETag = new PartEtag(uploadPartResult.getEtag(), uploadPartResult.getPartNumber());
result = JSON.toJSONString(partETag);
obsClient.close();
} catch (Exception e) {
e.printStackTrace();
logger.error("OBS上傳檔案Chunk:" + e.getMessage());
}
return result;
}
public boolean merageFile(String uploadId, List<PartEtag> chunkInfoList, String key, AttachmentDO attachmentDO, boolean checkMerge) {
key = "chunk/" + key + "/" + key;
boolean result = true;
try {
TenantParams.attach appConfig = getAttach();
ObsClient obsClient = InitOBS(appConfig);
String bucketName = appConfig.getBucketname_auth();
if (!checkMerge) {
CompleteMultipartUploadRequest request = new CompleteMultipartUploadRequest(bucketName, key, uploadId, chunkInfoList);
obsClient.completeMultipartUpload(request);
}
String attachKey = getKey(attachmentDO);
obsClient.copyObject(bucketName, key, bucketName, attachKey);
obsClient.close();
} catch (Exception e) {
e.printStackTrace();
logger.error("OBS合并檔案失敗:" + e.getMessage());
result = false;
}
return result;
}
Minio
檔案存盤Minio應用比較廣泛，框架也同時支持了自己獨立部署的Minio檔案存盤系統，Minio沒有對應的分片上傳api支持，我們可以在上傳完分片檔案后，使用composeObject方法進行檔案的合并
public boolean uploadChunk(InputStream stream, String key, int chunkIndex) {
boolean result = true;
try {
MinioClient minioClient = InitMinio();
String bucketName = frameConfig.getMinio_bucknetname();
PutObjectOptions option = new PutObjectOptions(stream.available(), -1);
key = "chunk/" + key + "/" + key;
minioClient.putObject(bucketName, key + "-" + chunkIndex, stream, option);
} catch (Exception e) {
logger.error("Minio上傳Chunk檔案失敗:" + e.getMessage());
result = false;
}
return result;
}
public boolean merageFile(String key, int chunkCount, AttachmentDO attachmentDO, boolean checkMerge) {
boolean result = true;
try {
MinioClient minioClient = InitMinio();
String bucketName = frameConfig.getMinio_bucknetname();
key = "chunk/" + key + "/" + key;
if (!checkMerge) {
List<ComposeSource> sourceObjectList = new ArrayList<ComposeSource>();
for (int i = 0; i < chunkCount; i++) {
ComposeSource composeSource = ComposeSource.builder().bucket(bucketName).object(key + "-" + i).build();
sourceObjectList.add(composeSource);
}
minioClient.composeObject(ComposeObjectArgs.builder().bucket(bucketName).object(key).sources(sourceObjectList).build());
}
String attachKey = getKey(attachmentDO);
minioClient.copyObject(
CopyObjectArgs.builder()
.bucket(bucketName)
.object(attachKey)
.source(
CopySource.builder()
.bucket(bucketName)
.object(key)
.build())
.build());
} catch (Exception e) {
logger.error("Minio合并檔案失敗:" + e.getMessage());
result = false;
}
return result;
}
轉載請註明出處，本文鏈接：https://www.uj5u.com/houduan/393840.html
標籤：Java