java doc/docx 转HTML

doc 和 docx 略有不同，对于doc，可以用下面这种方式:

HWPFDocument wordDocument = new HWPFDocument(is);
            WordToHtmlConverter converter = new WordToHtmlConverter(DocumentBuilderFactory.newInstance().newDocumentBuilder().newDocument());
            //对HWPFDocument进行转换
            converter.setPicturesManager(new PicturesManager() {
                @Override
                public String savePicture(byte[] content, PictureType pictureType, String suggestedName, float widthInches, float heightInches) {
                    String type = pictureType.name();
                    return "data:image/" + type + ";base64," + new String(Base64.encodeBase64(content));
                }
            });
            converter.processDocument(wordDocument);

            Transformer transformer = TransformerFactory.newInstance().newTransformer();
            transformer.setOutputProperty(OutputKeys.ENCODING, "utf-8");
            //是否添加空格
            transformer.setOutputProperty(OutputKeys.INDENT, "yes");
            transformer.setOutputProperty(OutputKeys.METHOD, "html");
            transformer.transform(
                    new DOMSource(converter.getDocument()),
                    new StreamResult(response.getWriter()));
            response.getWriter().flush();
            wordDocument.close();

需要导入以下的类：

import org.apache.poi.hwpf.HWPFDocument;
import org.apache.poi.hwpf.converter.PicturesManager;
import org.apache.poi.hwpf.converter.WordToHtmlConverter;
import org.apache.poi.hwpf.usermodel.PictureType;

由于我做的是doc转HTML在线预览，所以为了方便图片都转成了base64编码。

下面是docx的情况：

XWPFDocument document = new XWPFDocument(is);
            List list = document.getAllPictures();

            ByteArrayOutputStream outputStream = new ByteArrayOutputStream();
            XHTMLConverter.getInstance().convert(document, outputStream, null);

            String s = new String(outputStream.toByteArray());
            s = setImg(s, list);
            response.getWriter().write(s);
            response.getWriter().flush();

            document.close();

这个需要另外的setImg方法来修改生成的HTML，使用jsoup解析:

private String setImg(String html, List list){
        Document doc = Jsoup.parse(html);
        Elements elements = doc.getElementsByTag("img");
        if (elements != null && elements.size() > 0 && list != null){
            for(Element element : elements){
                String src = element.attr("src");
                for (XWPFPictureData data: list){
                    if (src.contains(data.getFileName())){
                        String type = src.substring(src.lastIndexOf(".") + 1);
                        String base64 = "data:image/" + type + ";base64," + new String(Base64.encodeBase64(data.getData()));
                        element.attr("src", base64);
                        break;
                    }
                }
            }
        }

        return doc.toString();
    }

需要导入：

import org.apache.poi.xwpf.converter.xhtml.XHTMLConverter;
import org.apache.poi.xwpf.usermodel.XWPFDocument;
import org.apache.poi.xwpf.usermodel.XWPFPictureData;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;

以上