docx转html方案验证-支持latex,表格,图片(aspose)

方案总结：

1:poi(html属性支持) 存在一个bug,对于table中的cell中既有文本又有图片的在转化后图片丢失

2:tika(主要是提取内容，转换出来的html不太好)

3.openoffice(依赖安装，转出的html不太好)

4. aspose(功能强大但是付费)，但也可以免费使用，缺点：不支持扩展原因代码不是开源的

5.mammoth(对比poi缺少标签的属性比如颜色字体)，这个不存在一个cell中既有文本又有图片的在转化后图片丢失的问题，对于样式这块支持扩展，样例很多

1.maven依赖

    <dependency>
            <groupId>org.apache.poi</groupId>
            <artifactId>poi</artifactId>
            <version>3.14</version>
        </dependency>
        <dependency>
            <groupId>org.apache.poi</groupId>
            <artifactId>poi-examples</artifactId>
            <version>3.14</version>
        </dependency>
        <dependency>
            <groupId>org.apache.poi</groupId>
            <artifactId>poi-excelant</artifactId>
            <version>3.14</version>
        </dependency>
        <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>org.apache.poi</groupId>
            <artifactId>ooxml-schemas</artifactId>
            <version>1.3</version>
        </dependency>
        <dependency>
            <groupId>com.aspose</groupId>
            <artifactId>aspose-words</artifactId>
            <version>18.6</version>
            <scope>system</scope>
            <systemPath>${project.basedir}/lib/aspose-words-18.6-jdk16.jar</systemPath>
        </dependency>
        <dependency>
            <groupId>com.aspose</groupId>
            <artifactId>aspose-cells</artifactId>
            <version>8.5.2</version>
            <scope>system</scope>
            <systemPath>${project.basedir}/lib/aspose-cells-8.5.2.jar</systemPath>
        </dependency>
        <dependency>
            <groupId>org.apache.pdfbox</groupId>
            <artifactId>pdfbox</artifactId>
            <version>2.0.9</version>
        </dependency>
        <dependency>
            <groupId>fr.opensagres.xdocreport</groupId>
            <artifactId>xdocreport</artifactId>
            <version>1.0.6</version>
        </dependency>
        <dependency>
            <groupId>org.apache.xmlbeans</groupId>
            <artifactId>xmlbeans</artifactId>
            <version>2.6.0</version>
        </dependency>
        <dependency>
            <groupId>net.sf.cssbox</groupId>
            <artifactId>pdf2dom</artifactId>
            <version>1.8</version>
        </dependency>
        <dependency>
            <groupId>org.projectlombok</groupId>
            <artifactId>lombok</artifactId>
            <version>1.16.10</version>
        </dependency>

        <!-- Hutool工具类 -->
        <!-- https://mvnrepository.com/artifact/cn.hutool/hutool-all -->
        <dependency>
            <groupId>cn.hutool</groupId>
            <artifactId>hutool-all</artifactId>
            <version>5.3.8</version>
        </dependency>

2.代码实现

2.1 wordBytes2HtmlFile方法

 public static File wordBytes2HtmlFile(byte[] wordBytes, String htmlFilePath) {
        try {
            log.info("实现`aspose-words`授权 -> 去掉头部水印");
            /*
              实现匹配文件授权 -> 去掉头部水印 `Evaluation Only. Created with Aspose.Words. Copyright 2003-2018 Aspose Pty Ltd.` |
                                          `Evaluation Only. Created with Aspose.Cells for Java. Copyright 2003 - 2020 Aspose Pty Ltd.`
             */
//            InputStream is = new ClassPathResource("license.xml").getInputStream();
            // 从当前类加载器中加载资源
            InputStream is = Thread.currentThread().getContextClassLoader().getResourceAsStream("license.xml");
            if (is != null) {
                License license = new License();
                license.setLicense(is);
            }
        } catch (Exception e) {
            log.error("《`aspose-words`授权》 失败： {}", e.getMessage());
        }
        // Load word document from disk.
        com.aspose.words.Document doc = new com.aspose.words.Document(new ByteArrayInputStream(wordBytes));
        // Save the document into MHTML.
        doc.save(htmlFilePath, SaveFormat.HTML);
        return new File(htmlFilePath);
    }

2.2 readBytes方法

    public static byte[] readBytes(String filePath) {
        return FileUtil.readBytes(filePath);
    }

2.3main方法

    public static void main(String[] args) {
//        word2HtmlFile("D:\\doc","JKLJLJLGJ.docx","JKLJLJLGJ.1111.html");

        File htmlFile = wordBytes2HtmlFile(readBytes("D:\\doc\\xxxx.docx"),
                "D:\\doc\\xxxxxxxaaaa.html");

    }