依赖
<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);
//设置转化的格式，HtmlSaveOptions转换为HTML格式；
HtmlSaveOptions saveOptions = new HtmlSaveOptions();
saveOptions.setExportImagesAsBase64(false);
//将所有word中的图片放在临时文件夹中，并将html中的链接替换为临时文件夹中绝对路径
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();
//将html文件转化为Document，方便后续使用jsoup的操作
org.jsoup.nodes.DocumenthtmlDoc = jsoup.parse(baos.toString());
//设置html中的图片src路径
this.setImagePath(htmlDoc, token);
//存储word文档的名称
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";
//首先根据文档名称生成第一条document的数据，产生的id将在标题实体中进行关联
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");//文档id
//存储文档的第一个标题的返回结果，其中包含该节点的id和title
documentContentVOList = this.exactContentFromHtml(htmlDoc);
this.dmeSave(documentContentVOList, id, "0", token);//第一个标题的父ID默认为0
} catch （Exception e）{
e.printStackTrace();
} finally {
inputStream.close();
}
return titleTreeVO;
}
}
//在解析为html文件的时候需要将图片的地址进行一个替换，由最初的临时文件地址替换为图片
//设置图片的路径（src）
private void setImagePath(Document document) throws IOException{
Element imgs = document.select("img");
String token = DmeTestRequestUtil.getToken();
for (Element img : imgs){
//获取出html中src内的地址值
String src = img.attr("src");
//通过地址查到对应的文件
File file = new File(src);
FileInputStream input = new FileInputStream(file);
//将file转化为MultipartFile
MultipartFile multipartFile = new MockMultipartFile("file",file.getName(), "text/plain", IOUtils.toByteArray(input));
//该部分主要是第三方接口设置的必须传的参数，在这里就先设置为定值，因为这些不干扰需求结果
FormVo formVo = new FormVo();
formVo.setAttributeName("File");
formVo.setModelName("Document");
formVo.setApplicationId("-1");
String uploadImgUrl = "图片作为文件，进行上传";
String uploadImage = DmeTestRequestUtil.getDmeResultUUploadFile(uploadImgUrl, multipartFile, formVo, token);
JSONObject uploadImgJs = JSONObject.parseObject(uploadImage);
List data = uploadImgJs = JSONObject("data", List.class);
//上传完成后，第三方接口会返回一个文件的id，可以根据这个id进行文件的预览和下载
String id = (String)data.get(0);
//上传文件file并返回上传的路径，将路径拼接出来，并替换到html的document中
String imgPath = "/api/dme-library/LibraryFolder/preview?fileId="+id;
img.attr("src", imgPath);
input.close();
//删除临时文件夹中存储的文件
file.deleteOnExit();
}
}
//该部分主要是第三方接口在调用时规定该接口的参数格式
//拼接参数
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;
}
//处理树形结构
private List<DocumentContentVO> exactContentFromHtml(Document htmlDoc) throws Exception{
Element eleList = htmlDoc.getElementsByTag("h1");
if(eleList == null || eleList.size() == 0){
throw new Exception("上传的文件中不存在一级标题，请检查");
}
Element hElement = htmlDoc.selectFirst("h1");//从第一个标题1 开始往下找
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;
}
//传入html解析的树和对应文档id 通过递归实现保存
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 = "创建对应数据的第三方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;
}
//第三方接口规定的参数样式，需要进行拼接
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));
}
}
/**
* 根据documentId查询取该篇文档的标题内容树形结构
*/
//根据documentId查询对应的word文档的树形结构
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();
}
//根据文档id获取到该文档的所有标题，（此时获取的集合没有父子级关系）
private List<TitleTreeVO> getAllTitleByDocId(String docId){
String url = "第三方标题表的查询";
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;
}
//通过递归获取到各级的子标题和内容
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;
}
