转载 POI3.5 word转html(样式缺失)

转载于https://www.jb51.net/article/101730.htm
原博客用的poi3.14，由于个人项目已经用了poi3.15，所以对引入的jar包版本做了修改，但工具类已经用的转载博客的，只对类名做了修改，后面发现转化的样式效果并不理想（主要体现在：表格，括号、图片、标题编号…），就舍弃了 world转html的功能，只用了富文本框 。
转载的目的在于备忘，后面如果再用到这个功能，进行改造。
jar包：

<dependency><groupId>org.apache.poi</groupId><artifactId>poi</artifactId><version>3.15</version>
</dependency>
<dependency><groupId>org.apache.poi</groupId><artifactId>poi-scratchpad</artifactId><version>3.15</version>
</dependency>
<dependency><groupId>org.apache.poi</groupId><artifactId>poi-ooxml</artifactId><version>3.15</version>
</dependency>
<dependency><groupId>fr.opensagres.xdocreport</groupId><artifactId>xdocreport</artifactId><version>1.0.5</version>
</dependency>
<dependency><groupId>org.apache.poi</groupId><artifactId>poi-ooxml-schemas</artifactId><version>3.15</version>
</dependency>
<dependency><groupId>org.apache.poi</groupId><artifactId>ooxml-schemas</artifactId><version>1.3</version>
</dependency>

工具类：

import org.apache.poi.hwpf.HWPFDocument;
import org.apache.poi.hwpf.converter.WordToHtmlConverter;
import org.apache.poi.xwpf.converter.core.BasicURIResolver;
import org.apache.poi.xwpf.converter.core.FileImageExtractor;
import org.apache.poi.xwpf.converter.xhtml.XHTMLConverter;
import org.apache.poi.xwpf.converter.xhtml.XHTMLOptions;
import org.apache.poi.xwpf.usermodel.XWPFDocument;
import org.w3c.dom.Document;import javax.xml.parsers.DocumentBuilderFactory;
import javax.xml.transform.OutputKeys;
import javax.xml.transform.Transformer;
import javax.xml.transform.TransformerFactory;
import javax.xml.transform.dom.DOMSource;
import javax.xml.transform.stream.StreamResult;
import java.io.File;
import java.io.FileInputStream;
import java.io.FileOutputStream;
import java.io.OutputStreamWriter;public class PoiUtils {
    // doc转换为htmlvoid docToHtml() throws Exception {
    String sourceFileName = "C:\\aaa\\test.doc";String targetFileName = "C:\\aaa\\worldToHtml.html";String imagePathStr = "C:\\aaa\\image\\";HWPFDocument wordDocument = new HWPFDocument(new FileInputStream(sourceFileName));Document document = DocumentBuilderFactory.newInstance().newDocumentBuilder().newDocument();WordToHtmlConverter wordToHtmlConverter = new WordToHtmlConverter(document);// 保存图片，并返回图片的相对路径wordToHtmlConverter.setPicturesManager((content, pictureType, name, width, height) -> {
    try (FileOutputStream out = new FileOutputStream(imagePathStr + name)) {
    out.write(content);} catch (Exception e) {
    e.printStackTrace();}return "image/" + name;});wordToHtmlConverter.processDocument(wordDocument);Document htmlDocument = wordToHtmlConverter.getDocument();DOMSource domSource = new DOMSource(htmlDocument);StreamResult streamResult = new StreamResult(new File(targetFileName));TransformerFactory tf = TransformerFactory.newInstance();Transformer serializer = tf.newTransformer();serializer.setOutputProperty(OutputKeys.ENCODING, "utf-8");serializer.setOutputProperty(OutputKeys.INDENT, "yes");serializer.setOutputProperty(OutputKeys.METHOD, "html");serializer.transform(domSource, streamResult);}// docx转换为htmlpublic void docxToHtml() throws Exception {
    String sourceFileName = "C:\\aaa\\test.docx";String targetFileName = "C:\\aaa\\worldToHtml.html";String imagePathStr = "C:\\aaa\\image\\";OutputStreamWriter outputStreamWriter = null;try {
    XWPFDocument document = new XWPFDocument(new FileInputStream(sourceFileName));XHTMLOptions options = XHTMLOptions.create();// 存放图片的文件夹options.setExtractor(new FileImageExtractor(new File(imagePathStr)));// html中图片的路径options.URIResolver(new BasicURIResolver("image"));outputStreamWriter = new OutputStreamWriter(new FileOutputStream(targetFileName), "utf-8");XHTMLConverter xhtmlConverter = (XHTMLConverter) XHTMLConverter.getInstance();xhtmlConverter.convert(document, outputStreamWriter, options);} finally {
    if (outputStreamWriter != null) {
    outputStreamWriter.close();}}}
}

controller:

import org.springframework.web.bind.annotation.GetMapping;
import org.springframework.web.bind.annotation.PostMapping;
import org.springframework.web.bind.annotation.RequestMapping;
import org.springframework.web.bind.annotation.RestController;
@RestController
@RequestMapping("/test")
public class TestController {
    @GetMapping({
    "/test"})public void qryAll() throws Exception {
    PoiUtils poiUtils = new PoiUtils();poiUtils.docxToHtml();}
}

若要改造，可在配置文件配置
存储目录（image、doc/docx、html），在controller上传文件后生成新的文件名，存储到 doc/docx 文件夹，调用 PoiUtils 的方法（docxToHtml/docToHtml 把文件名作为参数）即可。