Word文档转Html完成报告在线预览

声明：本文参考文章：https://blog.csdn.net/yexiaomodemo/article/details/103358452

需求背景：

       由于业务需要实现一个通过FreeMarker来动态生成word报告，并且需要实现在线预览的功能。    然而再完成该功能的第一思路是 通过freemarker模板生成word文档，然后再将生成的word文档来生成html文件，最后实现预览。  然而再实现这条方案时出现freemarker生成的word模板是不可以用来生成html的，原因是生成的word文件内部代码与自己再操作系统创建的文件是不同的。    从而选择了第二条路，一个word文档的freemarker模板，一个html的freemarker模板，分别来生成文件。这其中因为我们只拿到了word的模板，所以需要用此文中的转换方法，来转换出一份html文件当作模板。

 

第一步：导入Pom依赖：

        <!-- Word转HTML start -->
		<dependency>
			<groupId>org.apache.poi</groupId>
			<artifactId>poi-scratchpad</artifactId>
			<version>3.14</version>
		</dependency>
 
		<dependency>
			<groupId>org.apache.poi</groupId>
			<artifactId>poi-ooxml</artifactId>
			<version>3.14</version>
		</dependency>
 
		<dependency>
			<groupId>fr.opensagres.xdocreport</groupId>
			<artifactId>xdocreport</artifactId>
			<version>1.0.6</version>
		</dependency>
 
		<dependency>
			<groupId>org.apache.poi</groupId>
			<artifactId>poi-ooxml-schemas</artifactId>
			<version>3.14</version>
		</dependency>
 
		<dependency>
			<groupId>org.apache.poi</groupId>
			<artifactId>ooxml-schemas</artifactId>
			<version>1.3</version>
		</dependency>
 
		<dependency>
			<groupId>org.jsoup</groupId>
			<artifactId>jsoup</artifactId>
			<version>1.11.3</version>
		</dependency>
		<!-- Word转HTML end -->

 

第二步：java代码实现

package com.mmxpw.mmw.file.view.word;
 
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;
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.parsers.ParserConfigurationException;
import javax.xml.transform.OutputKeys;
import javax.xml.transform.Transformer;
import javax.xml.transform.TransformerException;
import javax.xml.transform.TransformerFactory;
import javax.xml.transform.dom.DOMSource;
import javax.xml.transform.stream.StreamResult;
import java.io.*;
 
public class WordToHtml {
 
    /**
     * 将word2003转换为html文件
     *
     * @param wordPath word文件路径
     * @param wordName word文件名称无后缀
     * @param suffix   word文件后缀
     * @param htmlPath html存储地址
     * @throws IOException
     * @throws TransformerException
     * @throws ParserConfigurationException
     */
    public static String Word2003ToHtml(String wordPath, String wordName, String suffix, String htmlPath)
            throws IOException, TransformerException, ParserConfigurationException {
        String htmlName = wordName + ".html";
        final String imagePath = htmlPath + "image" + File.separator;
        // 判断html文件是否存在
        File htmlFile = new File(htmlPath + htmlName);
        if (htmlFile.exists()) {
            return htmlFile.getAbsolutePath();
        }
        // 原word文档
        final String file = wordPath + File.separator + wordName + suffix;

        File wordFile = new File(file);
        // 1) 加载word文档生成 XWPFDocument对象
        byte[] bytes = getBytes(new FileInputStream(wordFile));
        InputStream wrappedStream = new ByteArrayInputStream(bytes);

        //InputStream input = new FileInputStream(new File(file));
        HWPFDocument wordDocument = new HWPFDocument(wrappedStream);
        WordToHtmlConverter wordToHtmlConverter = new WordToHtmlConverter(
                DocumentBuilderFactory.newInstance().newDocumentBuilder().newDocument());
        // 设置图片存放的位置
        wordToHtmlConverter.setPicturesManager(new PicturesManager() {
            public String savePicture(byte[] content, PictureType pictureType, String suggestedName, float widthInches,
                                      float heightInches) {
                File imgPath = new File(imagePath);
                if (!imgPath.exists()) {// 图片目录不存在则创建
                    imgPath.mkdirs();
                }
                File file = new File(imagePath + suggestedName);
                try {
                    OutputStream os = new FileOutputStream(file);
                    os.write(content);
                    os.close();
                } catch (FileNotFoundException e) {
                    e.printStackTrace();
                } catch (IOException e) {
                    e.printStackTrace();
                }
                // 图片在html文件上的路径 相对路径
                return "image/" + suggestedName;
            }
        });
        // 解析word文档
        wordToHtmlConverter.processDocument(wordDocument);
        Document htmlDocument = wordToHtmlConverter.getDocument();
        // 生成html文件上级文件夹
        File folder = new File(htmlPath);
        if (!folder.exists()) {
            folder.mkdirs();
        }
        OutputStream outStream = new FileOutputStream(htmlFile);
        DOMSource domSource = new DOMSource(htmlDocument);
        StreamResult streamResult = new StreamResult(outStream);
        TransformerFactory factory = TransformerFactory.newInstance();
        Transformer serializer = factory.newTransformer();
        serializer.setOutputProperty(OutputKeys.ENCODING, "utf-8");
        serializer.setOutputProperty(OutputKeys.INDENT, "yes");
        serializer.setOutputProperty(OutputKeys.METHOD, "html");
        serializer.transform(domSource, streamResult);
        return htmlFile.getAbsolutePath();
       
    }
    /**
     *
     * 2007版本word转换成html
     *
     * @param wordPath  word文件路径
     * @param wordName word文件名称无后缀
     * @param suffix   word文件后缀
     * @param htmlPath html存储地址
     * @return
     * @throws IOException
     */
    public static String Word2007ToHtml(String wordPath, String wordName, String suffix, String htmlPath)
            throws IOException {
        String htmlName = wordName + ".html";
        String imagePath = htmlPath + "image" + File.separator;
        // 判断html文件是否存在
        File htmlFile = new File(htmlPath + htmlName);
        if (htmlFile.exists()) {
            return htmlFile.getAbsolutePath();
        }
        // word文件
        File wordFile = new File(wordPath + File.separator + wordName + suffix);
        // 1) 加载word文档生成 XWPFDocument对象
        InputStream in = new FileInputStream(wordFile);
        XWPFDocument document = new XWPFDocument(in);
        // 2) 解析 XHTML配置 (这里设置IURIResolver来设置图片存放的目录)
        File imgFolder = new File(imagePath);
        XHTMLOptions options = XHTMLOptions.create();
        options.setExtractor(new FileImageExtractor(imgFolder));
        // html中图片的路径 相对路径
        options.URIResolver(new BasicURIResolver("image"));
        options.setIgnoreStylesIfUnused(false);
        options.setFragment(true);
        // 3) 将 XWPFDocument转换成XHTML
        // 生成html文件上级文件夹
        File folder = new File(htmlPath);
        if (!folder.exists()) {
            folder.mkdirs();
        }
        OutputStream out = new FileOutputStream(htmlFile);
        XHTMLConverter.getInstance().convert(document, out, options);
        return htmlFile.getAbsolutePath();
    }
 
    public static void main(String[] args) {
        try {
            //Word2003ToHtml("D://","testWord",".doc","D://");
            Word2007ToHtml("E:\\templates", "OnLineWord", ".doc", "E://templates/");
        } catch (Exception e) {
            e.printStackTrace();
        }
    }
 
 
}