背景
最近好幾個項目在運行過程中客戶都提出文件上傳大小的限制能否設置的大一些,用戶經常需要上傳好幾個G的資料文件,如圖紙,視頻等,並且需要在上傳大文件過程中進行優化實時展現進度條,進行技術評估後針對框架文件上傳進行擴展升級,擴展接口支持大文件分片上傳處理,減少服務器瞬時的內存壓力,同一個文件上傳失敗後可以從成功上傳分片位置進行斷點續傳,文件上傳成功後再次上傳無需等待達到秒傳的效果,優化用戶交互體驗,具體的實現流程如下圖所示(java fhadmin.cn
)
文件MD5計算
對於文件md5的計算我們使用spark-md5第三方庫,大文件我們可以分片分別計算再合併節省時間,但是經測試1G文件計算MD5需要20s左右的時間,所以經過優化我們抽取文件部分特徵信息(文件第一片+文件最後一片+文件修改時間),來保證文件的相對唯一性,只需要2s左右,大大提高前端計算效率,對於前端文件內容塊的讀取我們需要使用html5的api中fileReader.readAsArrayBuffer方法,因爲是異步觸發,封裝的方法提供一個回調函數進行使用
//java fhadmin.cn
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));
}
}
文件分片切割
我們通過定義好文件分片大小,使用blob對象支持的file.slice方法切割文件,分片上傳請求需要同步按順序請求,因爲使用了同步請求,前端ui會阻塞無法點擊,需要開啓worker線程進行操作,完成後通過postMessage方法傳遞消息給主頁面通知ui進度條的更新,需要注意的是,worker線程方法不支持window對象,所以儘量不要使用第三方庫,使用原生的XMLHttpRequest對象發起請求,需要的參數通過onmessage方法傳遞獲取
頁面upload請求方法如下
//java fhadmin.cn
upload() {
var file = document.getElementById("file").files[0];
if (!file) {
alert("請選擇需要上傳的文件");
return;
}
if (file.size < pageData.chunkSize) {
alert("選擇的文件請大於" + 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("計算文件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
//java fhadmin.cn
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 = evt.data;
console.log(data)
//傳遞的參數
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); //切割文件
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);
//上傳文件
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");
}
文件分片接收
前端文件分片處理完畢後,接下來我們詳細介紹下後端文件接受處理的方案,分片處理需要支持用戶隨時中斷上傳與文件重複上傳,我們新建表f_attachchunk來記錄文件分片的詳細信息,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:文件MD5唯一標識文件
- FileName:文件名稱
- ChunkSize:分片大小
- ChunkCount:分片總數量
- ChunkIndex:分片對應序號
- ChunkFilePath:分片存儲路徑(本地存儲文件方案使用)
- 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(雲存儲方案使用)
- UploadOSSChunkInfo:分片上傳單片信息(雲存儲方案使用)
- ChunkType:分片存儲方式(本地存儲,阿里雲,華爲雲,Minio標識)
- MergeStatus:分片合併狀態(未合併,已合併)
文件分片存儲後端一共分爲三步,檢查分片=》保存分片=》合併分片,我們這裏先以本地文件存儲爲例講解,雲存儲思路一致,後續會提供對應使用的api方法
檢查分片
檢查分片以數據庫文件分片記錄的FIleMD5與ChunkIndex組合來確定分片的唯一性,因爲本地分片temp文件是作爲臨時文件存儲,可能會出現手動清除施放磁盤空間的問題,所以數據庫存在記錄我們還需要對應的檢查實際文件情況
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 {
//刪除數據庫記錄
attachChunkService.delete(dbChunk.getChunkGuid());
}
} else {
//刪除數據庫記錄
attachChunkService.delete(dbChunk.getChunkGuid());
}
}
保存分片
保存分片分爲兩塊,文件存儲到本地,成功後數據庫插入對應分片信息
//獲取配置中附件上傳文件夾
String filePath = frameConfig.getAttachChunkPath() + "/" + fileMD5 + "/";
//根據附件guid創建文件夾
File targetFile = new File(filePath);
if (!targetFile.exists()) {
targetFile.mkdirs();
}
if (!existChunk) {
//保存文件到文件夾
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);
}
合併分片
在上傳分片方法中,如果當前分片是最後一片,上傳完畢後進行文件合併工作,同時進行數據庫合併狀態的更新,下一次同一個文件上傳時我們可以直接拷貝之前合併過的文件作爲新附件,減少合併這一步驟的I/O操作,合併文件我們採用BufferedOutputStream與BufferedInputStream兩個對象,固定緩衝區大小
if (chunkIndex == chunkCount - 1) {
//合併文件
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
//設置附件唯一guid
attachGuid = CommonUtil.getNewGuid();
attachmentDO.setAttguid(attachGuid);
attachmentService.insert(attachmentDO);
}
//java fhadmin.cn
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];//文件讀寫緩存 int readBytesLength = 0; //每次讀取字節數 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); }
雲文件分片上傳
雲文件上傳與本地文件上傳的區別就是,分片文件直接上傳到雲端,再調用雲存儲api進行文件合併與文件拷貝,數據庫相關記錄與檢查差異不大
阿里雲OSS
上傳分片前需要生成該文件的分片上傳組標識uploadid
//java fhadmin.cn
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,同時我們要將返回的分片信息PartETag序列化保存數據庫,用於後續的文件合併
//java fhadmin.cn
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); // 設置分片大小。除了最後一個分片沒有大小限制,其他的分片最小爲100 KB。 uploadPartRequest.setPartSize(chunkSize); // 設置分片號。每一個上傳的分片都有一個分片號,取值範圍是1~10000,如果超出此範圍,OSS將返回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文件。 UploadPartResult uploadPartResult = ossClient.uploadPart(uploadPartRequest); PartETag partETag = uploadPartResult.getPartETag(); result = JSON.toJSONString(partETag); ossClient.shutdown(); }catch (Exception e){ logger.error("OSS上傳文件Chunk失敗:" + e.getMessage()); } return result; }
合併分片時通過傳遞保存分片的PartETag對象數組進行操作,爲了附件獨立唯一性我們不直接使用合併後的文件,通過api進行文件拷貝副本使用
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合併文件失敗:" + e.getMessage());
result = false;
}
return result;
}
華爲雲OBS
華爲雲api與阿里雲api大致相同,只有個別參數名稱不同,直接上代碼
//java fhadmin.cn
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); // 設置分片大小。除了最後一個分片沒有大小限制,其他的分片最小爲100 KB。 uploadPartRequest.setPartSize((long) chunkSize); // 設置分片號。每一個上傳的分片都有一個分片號,取值範圍是1~10000,如果超出此範圍,OSS將返回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文件。 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上傳文件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合併文件失敗:" + e.getMessage()); result = false; } return result; }
Minio
文件存儲Minio應用比較廣泛,框架也同時支持了自己獨立部署的Minio文件存儲系統,Minio沒有對應的分片上傳api支持,我們可以在上傳完分片文件後,使用composeObject方法進行文件的合併
//java fhadmin.cn
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文件失敗:" + 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合併文件失敗:" + e.getMessage()); result = false; } return result; }