<!-- WordToHtml .doc .odcx  poi  -->
<dependency>
    <groupId>org.apache.poi</groupId>
    <artifactId>poi-scratchpad</artifactId>
    <version>4.1.2</version>
</dependency>
 
<!-- 操作excel的庫 注意版本保持一致 poi poi-ooxml  poi-scratchpad -->
<dependency>
    <groupId>org.apache.poi</groupId>
    <artifactId>poi</artifactId>
    <version>4.1.2</version>
</dependency>
 
<!-- https://mvnrepository.com/artifact/org.apache.poi/poi-ooxml -->
<dependency>
    <groupId>org.apache.poi</groupId>
    <artifactId>poi-ooxml</artifactId>
    <version>4.1.2</version>
</dependency>
 
<dependency>
    <groupId>fr.opensagres.xdocreport</groupId>
    <artifactId>fr.opensagres.poi.xwpf.converter.xhtml</artifactId>
    <version>2.0.2</version>
</dependency>
 
<!-- https://mvnrepository.com/artifact/fr.opensagres.xdocreport/fr.opensagres.xdocreport.converter.docx.xwpf -->
<dependency>
    <groupId>fr.opensagres.xdocreport</groupId>
    <artifactId>fr.opensagres.xdocreport.converter.docx.xwpf</artifactId>
    <version>2.0.1</version>
</dependency>

/**
 * poi WordToHtml工具類
 */
@Slf4j
public class WordToHtml {
 
//    文件上傳保存路徑
    @Value(value = "${upload.path}")
    private final String uploadPath = "";
 
    //轉(zhuǎn)換的方法
    public File convert(MultipartFile file) {
        //獲得文件的名字
        String filename = file.getOriginalFilename();
        //獲得文件的擴展名
        String suffix = filename.substring(filename.lastIndexOf("."));
        String newName = UUID.randomUUID().toString();
        // TODO 需要保存在一個新的位置
        // File =new File 表示目錄的一個抽象,可以進(jìn)一步用exists()和isDirectory()方法判斷。
        File convFile = new File(uploadPath + newName + suffix);
        FileOutputStream fos = null;
        try {
            //創(chuàng)建文件
            convFile.createNewFile();
            //FileOutputStream 是輸出流 將文件輸出到磁盤或者數(shù)據(jù)庫中
            fos = new FileOutputStream(convFile);
            fos.write(file.getBytes());
        } catch (IOException ex) {
            log.error("上傳文件出錯！", ex);
            return null;
        } finally {
            IOUtils.closeQuietly(fos);
        }
 
        // 輸入文件名的所在文件夾
        // 加上反斜杠
        String parentDirectory = convFile.getParent();
        if (!parentDirectory.endsWith("\\")) {
            parentDirectory = parentDirectory + "\\";
        }
 
        if (filename.endsWith(".docx")) {
            return docxConvert(parentDirectory, convFile.getAbsolutePath(), newName);
        } else if (filename.endsWith(".doc")) {
            return docConvert(parentDirectory, convFile.getAbsolutePath(), newName);
        } else {
            log.error("不支持的文件格式！");
            return null;
        }
    }
 
 
    /**
     * html 流文件 修改內(nèi)容 width:595.3pt;  因為轉(zhuǎn)換的HTML頁面默認(rèn)內(nèi)容區(qū)域不是html自適應(yīng)大小，內(nèi)容位置不對
     * @param parentDirectory html文件所在文件夾
     * @param filename html舊文件地址
     * @param newName html新文件地址
     * @return
     */
    private File htmlreplace(String parentDirectory, String filename, String newName) {
        try {
//            讀取生成的Html
            FileInputStream inputStream = new FileInputStream(new File(parentDirectory + filename + ".html"));
            InputStream inputStrem = readInputStrem(inputStream);
//            清空文件內(nèi)容
            clearInfoForFile(parentDirectory + filename + ".html");
            // TODO: 2022/4/22 進(jìn)行流輸出Html文件 inputStrem
//            1、讀取內(nèi)容
            byte[] buffer = new byte[inputStrem.available()];
            inputStrem.read(buffer);
//            寫入內(nèi)容
            OutputStream outStream = new FileOutputStream(new File(parentDirectory + newName + ".html"));
            outStream.write(buffer);
            return new File(parentDirectory + newName + ".html");
        } catch (FileNotFoundException e) {
            log.error("Html轉(zhuǎn)換失敗！",e);
            return null;
        } catch (IOException e) {
            log.error("Html轉(zhuǎn)換失??！",e);
            return null;
        }
    }
 
    /**
     * 讀取HTML 流文件，并查詢當(dāng)中的width:595.3pt;  / white-space:pre-wrap; 或類似符號直接替換為空格
     *
     * @param inputStream
     * @return
     */
    private static InputStream readInputStrem(InputStream inputStream) {
//        匹配內(nèi)容
        String regEx_special = "width:595.3pt;";
 
        String regEx_special2 = "white-space:pre-wrap;";
 
//        替換新內(nèi)容
        String replace = "white-space:pre-wrap;word-break:break-all;";
        try {
            //<1>創(chuàng)建字節(jié)數(shù)組輸出流，用來輸出讀取到的內(nèi)容
            ByteArrayOutputStream baos = new ByteArrayOutputStream();
            //<2>創(chuàng)建緩存大小
            byte[] buffer = new byte[1024]; // 1KB
            //每次讀取到內(nèi)容的長度
            int len = -1;
            //<3>開始讀取輸入流中的內(nèi)容
            while ((len = inputStream.read(buffer)) != -1) { //當(dāng)?shù)扔?1說明沒有數(shù)據(jù)可以讀取了
                baos.write(buffer, 0, len);   //把讀取到的內(nèi)容寫到輸出流中
            }
            //<4> 把字節(jié)數(shù)組轉(zhuǎn)換為字符串
            String content = baos.toString();
            //<5>關(guān)閉輸入流和輸出流
//            inputStream.close();
            baos.close();
//            log.info("讀取的內(nèi)容：{}", content);
//            判斷HTML內(nèi)容是否具有HTML的 width:595.3pt;
            Pattern compile = Pattern.compile(regEx_special, Pattern.CASE_INSENSITIVE);
            Matcher matcher = compile.matcher(content);
            String replaceAll = matcher.replaceAll("");
//            判斷是否具有white-space:pre-wrap;
            Pattern compile2 = Pattern.compile(regEx_special2, Pattern.CASE_INSENSITIVE);
            Matcher matcher2 = compile2.matcher(replaceAll);
            String replaceAll2 = matcher2.replaceAll(replace);
//            log.info("替換后的內(nèi)容：{}", replaceAll2);
//            將字符串轉(zhuǎn)化為輸入流返回
            InputStream stringStream = getStringStream(replaceAll2);
            //<6>返回結(jié)果
            return stringStream;
        } catch (Exception e) {
            e.printStackTrace();
            log.error("錯誤信息：{}", e.getMessage());
            return null;
        }
    }
 
    /**
     * 將一個字符串轉(zhuǎn)化為輸入流
     * @param sInputString 字符串
     * @return
     */
    public static InputStream getStringStream(String sInputString) {
        if (sInputString != null && !sInputString.trim().equals("")) {
            try {
                ByteArrayInputStream tInputStringStream = new ByteArrayInputStream(sInputString.getBytes());
                return tInputStringStream;
            } catch (Exception e) {
                e.printStackTrace();
            }
        }
        return null;
    }
 
    /**
     * 清空文件內(nèi)容
     * @param fileName
     */
    public static void clearInfoForFile(String fileName) {
        File file =new File(fileName);
        try {
            if(!file.exists()) {
                file.createNewFile();
            }
            FileWriter fileWriter =new FileWriter(file);
            fileWriter.write("");
            fileWriter.flush();
            fileWriter.close();
        } catch (IOException e) {
            e.printStackTrace();
        }
    }
 
    /**
     * 轉(zhuǎn)換.docx   當(dāng)word文檔字體大于5號字體時，會出現(xiàn)不規(guī)律排列文字換行(因為轉(zhuǎn)換的HTML頁面默認(rèn)內(nèi)容區(qū)域不是html原始區(qū)域)
     * @param parentDirectory html文件所在文件夾 （主要用于圖像的管理）
     * @param filename word文件地址
     * @param newName html文件地址
     * @return
     */
    private File docxConvert(String parentDirectory, String filename, String newName) {
        try {
            // 1) 加載word文檔生成 XWPFDocument對象
            XWPFDocument document = new XWPFDocument(new FileInputStream(filename));
 
//           設(shè)置存放圖片地址
            XHTMLOptions options = XHTMLOptions.create().setImageManager(new ImageManager(new File(parentDirectory), UUID.randomUUID().toString())).indent(4);
            OutputStream out = new FileOutputStream(new File(parentDirectory + newName + ".html"));
//            自定義編碼格式
            OutputStreamWriter writer = new OutputStreamWriter(out,"GBK");
//            生成HTML
            XHTMLConverter xhtmlConverter = (XHTMLConverter)XHTMLConverter.getInstance();
            xhtmlConverter.convert(document, writer, options);
//            將生成的HTML進(jìn)行內(nèi)容匹配替換
            File htmlreplace = htmlreplace(parentDirectory, newName, newName);
            return htmlreplace;
//            return new File(parentDirectory + newName + ".html");
        } catch (IOException ex) {
            log.error("word轉(zhuǎn)化出錯！", ex);
            return null;
        }
 
    }
 
 
    /**
     * 轉(zhuǎn)換.doc
     * @param parentDirectory html文件所在文件夾 （主要用于圖像的管理）
     * @param filename word文件地址
     * @param newName html文件地址
     * @return
     */
    private File docConvert(String parentDirectory, String filename, String newName) {
        try {
            HWPFDocument document = new HWPFDocument(new FileInputStream(filename));
            WordToHtmlConverter wordToHtmlConverter = new WordToHtmlConverter(
                    DocumentBuilderFactory.newInstance().newDocumentBuilder()
                            .newDocument());
 
            // converter默認(rèn)對圖片不作處理，需要手動下載圖片并嵌入到html中
            wordToHtmlConverter.setPicturesManager(new PicturesManager() {
                @Override
                public String savePicture(byte[] bytes, PictureType pictureType, String s, float v, float v1) {
                    String imageFilename = parentDirectory + "";
                    String identity = UUID.randomUUID().toString();
                    File imageFile = new File(imageFilename, identity + s);
                    imageFile.getParentFile().mkdirs();
                    InputStream in = null;
                    FileOutputStream out = null;
 
                    try {
                        in = new ByteArrayInputStream(bytes);
                        out = new FileOutputStream(imageFile);
                        IOUtils.copy(in, out);
 
                    } catch (IOException ex) {
                        log.error("word轉(zhuǎn)化出錯！", ex);
                    } finally {
                        if (in != null) {
                            IOUtils.closeQuietly(in);
                        }
 
                        if (out != null) {
                            IOUtils.closeQuietly(out);
                        }
 
                    }
                    return imageFile.getName();
                }
            });
 
            wordToHtmlConverter.processDocument(document);
            Document htmlDocument = wordToHtmlConverter.getDocument();
            ByteArrayOutputStream out = new ByteArrayOutputStream();
            DOMSource domSource = new DOMSource(htmlDocument);
            StreamResult streamResult = new StreamResult(out);
 
//            設(shè)置轉(zhuǎn)換屬性
            TransformerFactory tf = TransformerFactory.newInstance();
            Transformer serializer = tf.newTransformer();
            serializer.setOutputProperty(OutputKeys.ENCODING, "GBK");
            serializer.setOutputProperty(OutputKeys.INDENT, "yes");
            serializer.setOutputProperty(OutputKeys.METHOD, "html");
            serializer.transform(domSource, streamResult);
            out.close();
 
            String result = new String(out.toByteArray());
            FileWriter writer = new FileWriter(parentDirectory + newName + ".html");
            writer.write(result);
            writer.close();
        } catch (IOException | TransformerException | ParserConfigurationException ex) {
            log.error("word轉(zhuǎn)化出錯！", ex);
        }
        return new File(parentDirectory + newName + ".html");
    }
 
    /**
     * 將上傳的Word文檔轉(zhuǎn)化成HTML字符串
     *
     * @param file
     * @return
     */
    public String convertToHtml(MultipartFile file) {
        String wordContent = "";
        // 將Word文件轉(zhuǎn)換為html
        File file2 = convert(file);
        // 讀取html文件
        if (file2 != null) {
            return "文件轉(zhuǎn)換成功";
        }
        return "文件轉(zhuǎn)換失敗";
    }
 
    /**
     * wordToHtml
     * @param wordFilePath word文件路徑
     * @param htmlFilePath html文件路徑
     * @throws IOException
     * @throws ParserConfigurationException
     * @throws TransformerException
     */
    public static File wordToHtml(String wordFilePath,String htmlFilePath) {
//        提取出word文檔名稱和后綴
        String filename = wordFilePath.substring(wordFilePath.lastIndexOf("/")+1);
//        提取出html文件存放路徑和文件名稱
        String newName = htmlFilePath.substring(htmlFilePath.lastIndexOf("/")+1,htmlFilePath.lastIndexOf("."));
        File convFile = new File(htmlFilePath);
        // 輸入文件名的所在文件夾
        // 加上反斜杠
        String parentDirectory = convFile.getParent();
        if (!parentDirectory.endsWith("\\")) {
            parentDirectory = parentDirectory + "\\";
        }
 
        if (filename.endsWith(".docx")) {
            return new WordToHtml().docxConvert(parentDirectory, wordFilePath, newName);
        } else if (filename.endsWith(".doc")) {
            return new WordToHtml().docConvert(parentDirectory, wordFilePath, newName);
        } else {
            log.error("不支持的文件格式！");
            return null;
        }
 
    }
}

/**
 * @Author：wk
 * @Create：2022/4/21/15:10
 * @Description：WordToHtml測試類 poi
 * @Version：1.0
 */
@Slf4j
public class WordToHtmlTest {
 
    public static void main(String[] args) {
        long timeMillis = System.currentTimeMillis();
        log.info("開始轉(zhuǎn)換！");
        String wordFilePath = "src/main/resources/word/nc.docx";
        String htmlFilePath = "src/main/resources/html/nc5.html";
        File file = WordToHtml.wordToHtml(wordFilePath, htmlFilePath);
        // 讀取html文件
        if (file != null) {
            log.info("文件存放路徑：{}",file.getPath());
            log.info("轉(zhuǎn)換結(jié)束！用時：{}ms",System.currentTimeMillis()-timeMillis);
            return;
        }
        log.error("文件轉(zhuǎn)換失??！");
    }
 
}