Java使用aspose.word完美实现docx转doc

Java使用aspose.word完美实现docx转doc，同时打开转后的doc文件也不会报错，处理效率高于Docx4j

一、处理逻辑

• 1、使用aspose先将docx字节数组转为html数组，
• 2、将html数组转为所需要的格式的文档(doc或docx)

二、实现代码

代码实现

    /**
     * docx字节数组转doc字节数组
     * @Title: docxToDoc
     * @Description: docx字节数组转doc字节数组
     * @param content
     * @return: byte
     */
    private static byte[] docxToDoc(byte[] content) {
        // docx字节数组转成html字符串
        String htmlStr = byteToHtmlStr(content);
        // html字节数组转doc字节数组
        return AsposeWordUtils.htmlToWord(htmlStr.getBytes(StandardCharsets.UTF_8), SaveFormat.DOC);
    }
    
    /**
     * word字节数组转为html字符串
     * @Title: byteToHtmlStr
     * @Description: word字节数组转为html字符串
     * @param content
     * @return: String
     */
    private static String byteToHtmlStr(byte[] content) {
        String result = "";
        try {
            byte[] htmlContent = AsposeWordUtils.wordToHtml(content);
            InputStream is = new ByteArrayInputStream(htmlContent);
            InputStreamReader streamReader = new InputStreamReader(is, StandardCharsets.UTF_8);
            BufferedReader reader = new BufferedReader(streamReader);
            String line;
            StringBuilder html = new StringBuilder();
            while ((line = reader.readLine()) != null) {
                html.append(line);
            }
            reader.close();
            result = String.valueOf(html);
        } catch (IOException e) {
            logger.error("html转字符串异常", e);
        }
        return result;
    }

AsposeWordUtils工具类

/**
     * html字节数组转word字节数组
     * @Title: htmlToWordTest
     * @Description: html字节数组转word字节数组
     * @param content html字节数组
     * @param toType 值为SaveFormat.DOCX或SavaFormat.Doc对应的值
     * @return: byte
     */
    public static byte[] htmlToWord(byte[] content, Integer toType) {
        byte[] result = new byte[1];
        try {
            ByteArrayOutputStream os = new ByteArrayOutputStream();
            InputStream is = new ByteArrayInputStream(content);
            Document doc = new Document();
            DocumentBuilder builder = new DocumentBuilder(doc);
            InputStreamReader streamReader = new InputStreamReader(is, StandardCharsets.UTF_8);
            BufferedReader reader = new BufferedReader(streamReader);
            String line;
            StringBuilder html = new StringBuilder();
            while ((line = reader.readLine()) != null) {
                html.append(line);
            }
            reader.close();
            builder.insertHtml(String.valueOf(html));
            doc.save(os, toType);
            log.info("html转word成功！");
            result = os.toByteArray();
        } catch (Exception e) {
            log.error("html转word失败！", e);
        }
        return result;
    }

    /**
     * word字节数组转html字节数组
     * @Title: wordToHtml
     * @Description: word字节数组转html字节数组
     * @param content doc、docx字节数组
     * @return: byte
     */
    public static byte[] wordToHtml(byte[] content) {
        byte[] result = new byte[1] ;
        try {
            ByteArrayOutputStream os = new ByteArrayOutputStream();
            InputStream sbs = new ByteArrayInputStream(content);
            Document document = new Document(sbs);
            HtmlSaveOptions options = new HtmlSaveOptions(SaveFormat.HTML);
            options.setExportImagesAsBase64(true);
            document.save(os, options);
            log.info("html转word成功！");
            result = os.toByteArray();
        } catch (Exception e) {
            log.error("word转html失败！", e);
        }
        return result;
    }