word域代码转换html丢失解决办法.docxVIP

Word转html存在域代码丢失。Aspose，jacob，poi都无法解决在使用jocob转换成html时域代码会被!--[if supportFields]!—[end if]--包裹可以统一提取出来转换成latex ，latex转换成图片，解决word域代码丢失问题privatevoidprocessFormula(ListNode nodes) throwsUnsupportedEncodingException{for(inti = nodes.size()-1;i=0;i--){Node node =nodes.get(i);if(nodeinstanceof Element){Element e = (Element)node;processFormula(e.childNodes());}elseif(nodeinstanceof Comment){StringcommentText = node.toString();if(commentText.contains(!--[if supportFields])){Comment comment = (Comment)node;String latex = EqFormulaLatexUtil.getLatex(comment);if(StringUtils.isNotBlank(latex)){String latexTemp = newString(Base64.encodeBase64(latex.getBytes()));latex = URLEncoder.encode(latex, utf-8);latex = latex.replace(+, %20);String url = LATEXURL+latex;node.after(img encode=encode data-latex=+latexTemp+ src=+url+/);}}}}}/** * */package .tlsys.rawpaper2x.utils;importjava.io.File;importjava.io.IOException;.URLEncoder;importjava.util.ArrayList;importjava.util.List;importorg.jsoup.Jsoup;importorg.jsoup.nodes.Comment;importorg.jsoup.nodes.Document;importorg.jsoup.nodes.Element;importorg.jsoup.select.Elements;importorg.springframework.util.CollectionUtils;mon.util.StringUtils;/** * @author feiwang8 * * 2016年8月24日下午3:45:05 */public class EqFormulaLatexUtil {/** * 左括号替代符号 */public static final String LEFTBRACKETRE = く;/** * 右括号替代符号 */public static final String RIGHTBRACKETRE = ぐ;/** * 左括号 */public static final String LEFTBRACKET = (;/** * 右括号 */public static final String RIGHTBRACKET = );/** * 双正则 */public static final String REGEXPART_F=^((\\([\\s\\S]*\\)|[^\\(\\)])+),((\\([\\s\\S]*\\)|[^\\(\\)])+)$;/** * 单正则 */public static final String REGEXPART=((\\([\\s\\S]*\\)|[^\\(\\)])+);/** * 逗号替代符号 */public static final String COMMARE = ぃ;/** * 逗号 */public static final String COMMA = ,;/** * 更加comment 获取 latex * @paramcomment html Comment * @return latex */public static String getLatex(Comment comment){returngetLatex(comment.toString());}/** * 根据comment 获取 latex * @paramcomment htm