依賴
<dependency>
<groupId>org.jsoup</groupId>
<artifactId>jsoup</artifactId>
<version>1.11.2</version>
</dependency>
<dependency>
<groupId>com.aspose</groupId>
<artifactId>aspose</artifactId?
<version>15.8.0<version>
</dependency>
public class Word{
public TitleTreeVO wordAnalysis(MultipartFile multipartFile) throws IOException{
byte[] byteArr = multipartFile.getBytes();
InputStream inputStream = new ByteArrayInputStream(byteArr);
List<DocumentContentVO> documentContentVOList = new LinkedList<>();
TitleTreeVO titleTreeVO = new TitleTreeVO();
try{
//
com.aspose.words.Document doc = new com.aspose.words.Document(inputStream);
//設置轉化的格式，HtmlSaveOptions轉換為HTML格式；
HtmlSaveOptions saveOptions = new HtmlSaveOptions();
saveOptions.setExportImagesAsBase64(false);
//將所有word中的圖片放在臨時文件夾中，并將html中的鏈接替換為臨時文件夾中絕對路徑
String property = System.getProperty("java.io.tmpdir");
saveOptions.setImagesFolder(property);
org.apache.commons.io.output.ByteArrayOutputStream baos = new ByteArrayOutputStream();
doc.save(baos, saveOptions);
String token - DmeTestRequestUtil.getToken();
//將html文件轉化為Document，方便后續使用jsoup的操作
org.jsoup.nodes.DocumenthtmlDoc = jsoup.parse(baos.toString());
//設置html中的圖片src路徑
this.setImagePath(htmlDoc, token);
//存儲word文檔的名稱
String subString = multipartFile.getOriginalFilename().substring(0,multipartFile.getOriginalFilename().lastIndexof("."));
JSONObject docPram = this.getDocParam(substring);
String saveDocUrl = "https://dme.cn-south-4.huaweicloud.com/rdm_hwdmeverify_app/publicservices/api/DocumentSave/create";
//首先根據文檔名稱生成第一條document的數據，產生的id將在標題實體中進行關聯
String dmeResult = DmeTestRequestUtil.getDmeResult(saveDocUrl,docPram,token);
JSONObject jsonObject1 = JSONObject.parseObject(dmeResult);
List data1 = jsonObject1.getObject("data", List.class);
JSONObject jsonObjectData1 = (JSONObject)data1.get(0);
String id = jsonObjectData1.getString("id");//文檔id
//存儲文檔的第一個標題的返回結果，其中包含該節點的id和title
documentContentVOList = this.exactContentFromHtml(htmlDoc);
this.dmeSave(documentContentVOList, id, "0", token);//第一個標題的父ID默認為0
} catch （Exception e）{
e.printStackTrace();
} finally {
inputStream.close();
}
return titleTreeVO;
}
}
//在解析為html文件的時候需要將圖片的地址進行一個替換，由最初的臨時文件地址替換為圖片
//設置圖片的路徑（src）
private void setImagePath(Document document) throws IOException{
Element imgs = document.select("img");
String token = DmeTestRequestUtil.getToken();
for (Element img : imgs){
//獲取出html中src內的地址值
String src = img.attr("src");
//通過地址查到對應的文件
File file = new File(src);
FileInputStream input = new FileInputStream(file);
//將file轉化為MultipartFile
MultipartFile multipartFile = new MockMultipartFile("file",file.getName(), "text/plain", IOUtils.toByteArray(input));
//該部分主要是第三方接口設置的必須傳的參數，在這里就先設置為定值，因為這些不干擾需求結果
FormVo formVo = new FormVo();
formVo.setAttributeName("File");
formVo.setModelName("Document");
formVo.setApplicationId("-1");
String uploadImgUrl = "圖片作為文件，進行上傳";
String uploadImage = DmeTestRequestUtil.getDmeResultUUploadFile(uploadImgUrl, multipartFile, formVo, token);
JSONObject uploadImgJs = JSONObject.parseObject(uploadImage);
List data = uploadImgJs = JSONObject("data", List.class);
//上傳完成后，第三方接口會返回一個文件的id，可以根據這個id進行文件的預覽和下載
String id = (String)data.get(0);
//上傳文件file并返回上傳的路徑，將路徑拼接出來，并替換到html的document中
String imgPath = "/api/dme-library/LibraryFolder/preview?fileId="+id;
img.attr("src", imgPath);
input.close();
//刪除臨時文件夾中存儲的文件
file.deleteOnExit();
}
}
//該部分主要是第三方接口在調用時規定該接口的參數格式
//拼接參數
private JSONObject getDocParam(String name) {
Map<String, Object> mapStr = new HashMap<>();
Map<String, Object> paramMap = new HashMap<>();
paramMap.put("name", name);
mapStr.put("params", paramMap);
JSONObject jsonObject = new JSONObject(mapStr);
return jsonObject;
}
//處理樹形結構
private List<DocumentContentVO> exactContentFromHtml(Document htmlDoc) throws Exception{
Element eleList = htmlDoc.getElementsByTag("h1");
if(eleList == null || eleList.size() == 0){
throw new Exception("上傳的文件中不存在一級標題，請檢查");
}
Element hElement = htmlDoc.selectFirst("h1");//從第一個標題1 開始往下找
List<DocumentContentVO> allTreeList = new ArrayList<>();
List<DocumentContentVO> list2 = new ArrayList<>();
List<DocumentContentVO> list3 = new ArrayList<>();
List<DocumentContentVO> list4 = new ArrayList<>();
DocumentContentVO b1Map = new DocumentContentVO();
DocumentContentVO b2Map = new DocumentContentVO();
DocumentContentVO b3Map = new DocumentContentVO();
DocumentContentVO b4Map = new DocumentContentVO();
DocumentContentVO bMap = b1Map;
int i = 1;
b1Map.setTitle(hElement.toString());
b1Map.setIndex(i);
allTreeList.add(b1Map);
while (hElement.nextElementSibling() != null){
i++;
hElement = hElement.nextElementSibling();
String nodeName = hElement.nodeName();
String s = hElement.tagName();
if(Objects.equals(nodeName, "h1")){
b1Map = new DocumentContentVO();
bMap = b1Map;
b1Map.setTitle(hElement.toString());
b1Map.setIndex(i);
allTreeList.add(b1Map);
list2 = new ArrayList<>();
} else if (Objects.equals(nodeName, "h2")){
b2Map = new DocumentContentVO();
bMap = b2Map;
list3 = new ArrayList<>();
b2Map.setTitle(hElement.toString());
b2Map.setIndex(i);
list2.add(b2Map);
b1Map.setChildList(list2);
} else if (Objects.equals(nodeName, "h3")){
b3Map = new DocumentContentVO();
bMap = b3Map;
b3Map.setTitle(hElement.toString());
b3Map.setIndex(i);
list3.add(b3Map);
b2Map.setChildList(list3);
} else if(Objects.equals(nodeName, "h4")){
b4Map = new DocumentContentVO();
bMap = b4Map;
b4Map.setTitle(hElement.toString());
b4Map.setIndex(i);
list4.add(b4Map);
b3Map.setChildList(list4);
} else {
bMap.setContent(bMap.getContent() == null ? hElement.toString() : bMap.getContent() + hElement.toString());
}
}
return allTreeList;
}
//傳入html解析的樹和對應文檔id 通過遞歸實現保存
private String dmeSave(List<DocumentContentVO> treeList, String id , String parentId, String token){
String dmeResult = null;
for(DocumentContentVO documentContentVO : treeList) {
if(documentContentVO != null){
String title = documentContentVO.getTitle();
int sort = documentContentVO.getIndex();
String content = documentContentVO.getContent();
String url = "創建對應數據的第三方url";
JSONObject jsonObjectParam = this.paramJoin1(title, id, parentId, sort, content)
dmeResult = DmeTestRequestUtil.getDmeResult(url, jsonObjectParam, token);
List data = JSONObject.parseObject(dmeResult).getObject("data", List.class);
if(data != null && !data.isEmpty()){
JSONObject jsonObject = (JSONObject)data.get(0);
String parentIdNext = jsonObject.getString("id");
if(documentContentVO.getChildList() != null && documentContentVO.getChildList().size() > 0){
dmeSave(documentContentVO.getChildList(), id , parentIdNext,token);
}
}
}
}
return dmeResult;
}
//第三方接口規定的參數樣式，需要進行拼接
private JSONObject paramJoin1(String title, String id, String parentId, int sort, String content) {
Map<String, Object> mapStr = new HashMap<>();
Map<String, Object> paramMap = new HashMap<>();
if(id != null){
paramMap.put("title", title);
paramMap.put("sort", sort);
paramMap.put("parentId",parentId);
paramMap.put("content", content);
paramMap.put("documentId", id);
} else {
paramMap.put("title", title);
}
mapStr.put("params", paramMap);
return JSONObject.parseObject(JSON.toJSONString(mapStr));
}
}
/**
* 根據documentId查詢取該篇文檔的標題內容樹形結構
*/
//根據documentId查詢對應的word文檔的樹形結構
public List<TitleTreeVO> getTreeCon(JSONObject reqJSON) {
String id = reqJSON.getString("id");
List<TitleTreeVO> allTitleByDocId = this.getAllTitleByDocId(id);
TitleTreeVO titleTreeVO = new TitleTreeVO();
titleTreeVO.setId("0");
this.getChild(titleTreeVO, allTitleByDocId);
return titleTreeVO.getChildList();
}
//根據文檔id獲取到該文檔的所有標題，（此時獲取的集合沒有父子級關系）
private List<TitleTreeVO> getAllTitleByDocId(String docId){
String url = "第三方標題表的查詢";
JSONObject docIdParam = getDocIdParam(docId);
String token = DmeTestRequestUtil.getDmeResult(url,docIdParam,token);
JSONObject jsonObject = JSONObject.parseObject(dmeResult);
List date = jsonObject.getObject("data", List.class);
List<TitleTreeVO> titleList = new ArrayList<>();
if(data != null && !data.isEmpty()){
for(Object title : data){
JSONObject titleJson = (JSONObject)title;
TitleTreeVO titleTreeVO = new TitleTreeVO();
titleTreeVO.setContent(titleJson.getString("content"));
titleTreeVO.setTitle(titleJson.getString("title"));
titleTreeVO.setId(titleJson.getString("id"));
titleTreeVO.setIndex(Integer.parseInt(titleJson.getString("sort")));
titleTreeVO.setDocumentId(titleJson.getString("documentId"));
titleTreeVO.setParentId(titleJson.getString("parentId"));
titleList.add(titleTreeVO);
}
}
return titleList;
}
//通過遞歸獲取到各級的子標題和內容
private TitleTreeVO getChild(TitleTreeVO parentTitleTreeVO, List<TitleTreeVO> titleListOld) {
List<TitleTreeVO> titleList = new ArrayList<>();
if(titleListOld != null && titleListOld.size() > 0){
List<TitleTreeVO> titleCollect = titleListOld.stream().filter(e -> e.getParentId().equals(parentTitleTreeVO.getId())).collect(Collectors.toList());
if(titleCollect.size() > 0){
for(TitleTreeVO title : titleCollect){
TitleTreeVO titleTreeVO = new TitleTreeVO();
titleTreeVO.setIndex(title.getIndex());
titleTreeVO.setTitle(title.getTitle());
titleTreeVO.setId(title.getId());
titleTreeVO.setContent(title.getContent());
titleTreeVO.setDocumentId(title.getDocumentId());
titleTreeVO.setParentId(title.getParentId());
titleList.add(titleTreeVO);
this.getChild(titleTreeVO, titleListOld);
}
}
}
List<TitleTreeVO> titleSortList = titleList.stream().sorted(Comparator.comparing(TitleTreeVO::getIndex)).collect(Collectors.toList());
parentTitleTreeVO.setChildList(titleSortList);
return parentTitleTreeVO;
}
浙公網安備 33010602011771號