在线预览文档简单例子

我就是我 2022-06-02 23:58 552阅读 0赞

以下是一个Java实现简单浏览器预览服务端文档的例子，文档包括pdf，excel，word，ppt，思路是将excel，word转化为html；将ppt转为图片，再转为html；将pdf以pdf流的形式返回给浏览器，一般的浏览器都支持预览pdf。

maven依赖

  1. <dependency>
  2.   <groupId>org.apache.poi</groupId>
  3.   <artifactId>ooxml-schemas</artifactId>
  4.   <version>1.1</version>
  5. </dependency>
  6. <dependency>
  7.   <groupId>org.apache.poi</groupId>
  8.   <artifactId>poi</artifactId>
  9.   <version>3.15</version>
  10. </dependency>
  11. <dependency>
  12.   <groupId>org.apache.poi</groupId>
  13.   <artifactId>poi-ooxml</artifactId>
  14.   <version>3.15</version>
  15. </dependency>
  16. <dependency>
  17.   <groupId>org.apache.poi</groupId>
  18.   <artifactId>poi-scratchpad</artifactId>
  19.   <version>3.15</version>
  20. </dependency>
  21. <dependency>
  22.   <groupId>fr.opensagres.xdocreport</groupId>
  23.   <artifactId>org.apache.poi.xwpf.converter.core</artifactId>
  24.   <version>1.0.4</version>
  25. </dependency>
  26. <dependency>
  27.   <groupId>fr.opensagres.xdocreport</groupId>
  28.   <artifactId>org.apache.poi.xwpf.converter.xhtml</artifactId>
  29.   <version>1.0.4</version>
  30. </dependency>
  31. <dependency>
  32.   <groupId>org.apache.xmlbeans</groupId>
  33.   <artifactId>xmlbeans</artifactId>
  34.   <version>2.5.0</version>
  35. </dependency>

预览pdf

  1. byte[] datas = readFile(f);
  2. response.setContentType("application/pdf");
  3. response.setContentLength(datas.length);
  4. OutputStream os = res.getOutputStream();
  5. os.write(datas, 0, datas.length);
  6. os.flush();
  7. os.close();

预览页面

将转为html或者图片的文档，嵌入此html中返回给浏览器展示。

  1. private static final StringBuilder ORIGIN_HTML = new StringBuilder("<!DOCTYPE html>\n" +
  2.         "<html lang=\"en\">\n" +
  3.         "<head>\n" +
  4.         "    <meta http-equiv=\"Content-Type\" content=\"text/html;charset=utf-8\" />\n" +
  5.         "    <meta http-equiv=\"X-UA-Compatible\" content=\"IE=edge\">\n" +
  6.         "    <title>预览</title>\n" +
  7.         "    <link rel=\"stylesheet\" href=\"/resource/css/simple.slide.css\">\n" +
  8.         "    <link rel=\"stylesheet\" href=\"/resource/css/preview.css\">\n" +
  9.         "    <script type=\"text/javascript\" src=\"../../resource/jquery-1.9.0.min.js\"></script>\n" +
  10.         "    <script type=\"text/javascript\" src=\"/resource/simple.slide.js\"></script>\n" +
  11.         "    <script type=\"text/javascript\">\n" +
  12.         "        $(function(){\n" +
  13.         "           $(\".pptimage\").simpleSlide();\n" +
  14.         "        });\n" +
  15.         "    </script>\n" +
  16.         "</head>\n" +
  17.         "<body>\n" +
  18.         "       ####\n" +
  19.         "</body>\n" +
  20.         "</html>");

word07转为html

  1. public static void doc07ToHtml(String from, OutputStream out, String imagePath){
  2.     try{
  3.         Map<String, String> map = new HashMap<String, String>();
  4.         //1.如果图片文件夹存在,删除重新创建之
  5.         File imagePathFile = new File(imagePath);
  6.         if(imagePathFile.exists()) {
  7.             FileUtils.deleteDirectory(imagePathFile);
  8.         }
  9.         imagePathFile.mkdirs();
  11.         FileInputStream fis = new FileInputStream(from);
  12.         XWPFDocument doc = new XWPFDocument(fis);
  13.         XHTMLOptions options = XHTMLOptions.create();
  14.         options.setExtractor(new IImageExtractor() {
  16.             @Override
  17.             public void extract(String imagePath1, byte[] imageData) throws IOException {
  18.                 //2.处理文件后缀
  19.                 String suf = "";
  20.                 if(imagePath1.lastIndexOf(".") > 0) {
  21.                     suf = imagePath1.substring(imagePath1.lastIndexOf("."), imagePath1.length());
  22.                 }
  23.                 //3.写文件，并将文件对应关系存入map
  24.                 String tempFile = imagePath+File.separator+UuidUtil.getUUID()+suf;
  25.                 File f = new File(tempFile);
  26.                 FileUtils.writeByteArrayToFile(f, imageData);
  27.                 map.put(imagePath1, tempFile);
  29.             }});
  30.         options.setIgnoreStylesIfUnused(false);
  31.         options.setFragment(true);
  32.         options.URIResolver(new IURIResolver() {
  34.             @Override
  35.             public String resolve(String arg0) {
  36.                 if(map.containsKey(arg0)) {
  37.                     String u = map.get(arg0);
  38.                     if(!XaUtil.isEmpty(u)){
  39.                         try {
  40.                             u = URLEncoder.encode(u,"ISO-8859-1");
  41.                         } catch (UnsupportedEncodingException e) {
  42.                             e.printStackTrace();
  43.                         }
  44.                     }
  45.                     return "/sys/filemanage/getViewImage.do?id="+u;
  46.                 }
  47.                 return arg0;
  48.             }
  49.         });
  50.         ByteArrayOutputStream os = new ByteArrayOutputStream();
  51.         XHTMLConverter.getInstance().convert(doc, os, options);
  52.         byte[] datas = os.toByteArray();
  53.         os.close();
  54.         //处理表格没有边框
  55.         String content = new String(datas,"utf-8");
  56.         content = ORIGIN_HTML.toString().replaceAll("####",content);
  57.         datas = content.getBytes("utf-8");
  58.         out.write(datas, 0, datas.length);
  59.         out.flush();
  60.         out.close();
  61.     }catch(Exception e){
  63.         log.error("",e);
  64.     }
  65. }

word03转为html

  1. public static void doc03ToHtml(String from, OutputStream out, String imagePath)throws Exception{
  2.     try{
  3.         //1.如果图片文件夹存在,删除重新创建之
  4.         File imagePathFile = new File(imagePath);
  5.         if(imagePathFile.exists()) {
  6.             FileUtils.deleteDirectory(imagePathFile);
  7.         }
  8.         imagePathFile.mkdirs();
  9.         FileInputStream fis = new FileInputStream(from);
  10.         HWPFDocument doc = new HWPFDocument(fis);
  11.         WordToHtmlConverter converter = new WordToHtmlConverter(DocumentBuilderFactory.newInstance().newDocumentBuilder().newDocument());
  12.         converter.setPicturesManager(new PicturesManager() {
  14.             @Override
  15.             public String savePicture(byte[] arg0, PictureType arg1, String arg2, float arg3, float arg4) {
  16.                 //2.处理文件后缀
  17.                 String suf = "";
  18.                 if(arg2.lastIndexOf(".") > 0) {
  19.                     suf = arg2.substring(arg2.lastIndexOf("."), arg2.length());
  20.                 }
  21.                 //3.写文件，并将文件对应关系存入map
  22.                 String tempFile = imagePath+File.separator+UuidUtil.getUUID()+suf;
  23.                 File f = new File(tempFile);
  24.                 try {
  25.                     FileUtils.writeByteArrayToFile(f, arg0);
  26.                 } catch (IOException e) {
  27.                     // TODO Auto-generated catch block
  28.                     e.printStackTrace();
  29.                 }
  30.                 if(!XaUtil.isEmpty(tempFile)){
  31.                     try {
  32.                         tempFile = URLEncoder.encode(tempFile,"ISO-8859-1");
  33.                     } catch (UnsupportedEncodingException e) {
  34.                         e.printStackTrace();
  35.                     }
  36.                 }
  37.                 return "/sys/filemanage/getViewImage.do?id="+tempFile;
  38.             }
  39.         });
  41.         converter.processDocument(doc);
  42.         Document htmlDocument = converter.getDocument();
  43.         ByteArrayOutputStream outStream = new ByteArrayOutputStream();
  44.         DOMSource domSource = new DOMSource(htmlDocument);
  45.         StreamResult streamResult = new StreamResult(outStream);
  46.         TransformerFactory tf = TransformerFactory.newInstance();
  47.         Transformer serializer = tf.newTransformer();
  48.         serializer.setOutputProperty(OutputKeys.ENCODING, "utf-8");
  49.         serializer.setOutputProperty(OutputKeys.INDENT, "yes");
  50.         serializer.setOutputProperty(OutputKeys.METHOD, "html");
  51.         serializer.transform(domSource, streamResult);
  52.         outStream.close();
  53.         byte[] datas = outStream.toByteArray();
  54.         //处理表格没有边框
  55.         String content = new String(datas,"utf-8");
  56.         content = ORIGIN_HTML.toString().replaceAll("####",content);
  57.         datas = content.getBytes("utf-8");
  58.         out.write(datas, 0, datas.length);
  59.         out.flush();
  60.         out.close();
  61.     }catch(Exception e){
  63.         log.error("",e);
  64.     }
  65. }

Excel转为html

  1. public static void exceToHtml(String from, OutputStream out){
  2.     InputStream in = null;
  3.     XSSFWorkbook xwb = null;
  4.     HSSFWorkbook hwb= null;
  5.     try{
  6.         in = new FileInputStream(from);
  7.         Workbook wb = WorkbookFactory.create(in);
  8.         if(wb instanceof XSSFWorkbook) {
  9.             xwb = (XSSFWorkbook) wb;
  10.             hwb = new HSSFWorkbook();
  11.             ConvertXSSF2HSSF c = new ConvertXSSF2HSSF();
  12.             c.transformXSSF(xwb, hwb);
  13.         }else{
  14.             hwb = (HSSFWorkbook) wb;
  15.         }
  17.         ExcelToHtmlConverter converter = new ExcelToHtmlConverter(DocumentBuilderFactory.newInstance().newDocumentBuilder().newDocument());
  18.         converter.processWorkbook(hwb);
  20.         wb.close();
  21.         Document htmlDocument = converter.getDocument();
  22.         ByteArrayOutputStream outStream = new ByteArrayOutputStream();
  23.         DOMSource domSource = new DOMSource (htmlDocument);
  24.         StreamResult streamResult = new StreamResult (outStream);
  25.         TransformerFactory tf = TransformerFactory.newInstance();
  26.         Transformer serializer = tf.newTransformer();
  27.         serializer.setOutputProperty (OutputKeys.ENCODING, "utf-8");
  28.         serializer.setOutputProperty (OutputKeys.INDENT, "yes");
  29.         serializer.setOutputProperty (OutputKeys.METHOD, "html");
  30.         serializer.transform (domSource, streamResult);
  31.         outStream.close();
  32.         String content = new String (outStream.toByteArray(),"utf-8" );
  33.         content = ORIGIN_HTML.toString().replaceAll("####",content);
  34.         byte[] datas = content.getBytes("utf-8");
  35.         out.write(datas,0,datas.length);
  36.         out.flush();
  37.         out.close();
  38.     }catch (Exception e){
  39.         log.error("",e);
  40.     }finally {
  41.         try {
  42.             if(null != in){
  43.                 in.close();
  44.             }
  45.             if(null != xwb){
  46.                 xwb.close();
  47.             }
  48.             if(null != hwb){
  49.                 hwb.close();
  50.             }
  51.         } catch (IOException e) {
  53.            log.error("",e);
  54.         }
  55.     }
  56. }

ppt07转为图片

  1. public static String ppt07ToImage(String from, String images) {
  2.     StringBuilder sb = new StringBuilder();
  3.     FileInputStream fis = null;
  4.     XMLSlideShow ppt = null;
  5.     FileOutputStream fos = null;
  6.     try {
  7.         // 1.如果图片文件夹存在,删除重新创建之
  8.         File imagePathFile = new File(images);
  9.         if (imagePathFile.exists()) {
  10.             FileUtils.deleteDirectory(imagePathFile);
  11.         }
  12.         imagePathFile.mkdirs();
  14.         fis = new FileInputStream(from);
  15.         ppt = new XMLSlideShow(fis);
  16.         Dimension pageSize = ppt.getPageSize();
  17.         List<XSLFSlide> slides = ppt.getSlides();
  18.         String xmlFontFormat = "<xml-fragment xmlns:a=\"http://schemas.openxmlformats.org/drawingml/2006/main\" xmlns:r=\"http://schemas.openxmlformats.org/officeDocument/2006/relationships\" xmlns:p=\"http://schemas.openxmlformats.org/presentationml/2006/main\">"
  19.                 + "<a:rPr lang=\"zh-CN\" altLang=\"en-US\" dirty=\"0\" smtClean=\"0\"> "
  20.                 + "<a:latin typeface=\"+mj-ea\"/> " + "</a:rPr>" + "</xml-fragment>";
  21.         int index = 0;
  22.         for (XSLFSlide slide : slides) {
  23.             CTSlide cts = slide.getXmlObject();
  24.             CTGroupShape groupShape = cts.getCSld().getSpTree();
  25.             List<CTShape> shapeList = groupShape.getSpList();
  26.             for (CTShape ctShape : shapeList) {
  27.                 CTTextBody oneCTTextBody = ctShape.getTxBody();
  28.                 if (null == oneCTTextBody) {
  29.                     continue;
  30.                 }
  31.                 CTTextParagraph[] oneCTTextParagraph = oneCTTextBody.getPArray();
  32.                 CTTextFont oneCTTextFont = null;
  33.                 oneCTTextFont = CTTextFont.Factory.parse(xmlFontFormat);
  34.                 for (CTTextParagraph ctTextParagraph : oneCTTextParagraph) {
  35.                     CTRegularTextRun[] onrCTRegularTextRunArray = ctTextParagraph.getRArray();
  36.                     for (CTRegularTextRun ctRegularTextRun : onrCTRegularTextRunArray) {
  37.                         CTTextCharacterProperties oneCTTextCharacterProperties = ctRegularTextRun.getRPr();
  38.                         oneCTTextCharacterProperties.setLatin(oneCTTextFont);
  39.                     }
  41.                 }
  42.             }
  43.             // 创建BufferedImage 对象，图像尺寸为原来的PPT的每页尺寸
  44.             BufferedImage oneBufferedImage = new BufferedImage(pageSize.width, pageSize.height,
  45.                     BufferedImage.TYPE_INT_RGB);
  46.             Graphics2D oneGraphics2D = oneBufferedImage.createGraphics();
  47.             // 将PPT文件中的每个页面中的相关内容画到转换后的图片中
  48.             slides.get(index).draw(oneGraphics2D);
  49.             /**
  50.              * 设置图片的存放路径和图片格式，注意生成的文件路径为绝对路径，最终获得各个图像文件所对应的输出流的对象
  51.              */
  53.             String imgName = images + File.separator + UuidUtil.getUUID() + ".jpg";
  54.             sb.append(imgName + ",");
  56.             fos = new FileOutputStream(imgName);
  57.             ImageIO.write(oneBufferedImage, "jpg", fos);
  58.             index++;
  59.         }
  60.     } catch (Exception e) {
  61.         e.printStackTrace();
  62.     }finally {
  63.         try {
  65.             if(null != fis) {
  67.                 fis.close();
  68.             }
  69.             if(null != ppt) {
  71.                 ppt.close();
  72.             }
  73.             if(null != fos){
  74.                 fos.close();
  75.             }
  76.         } catch (IOException e) {
  77.             e.printStackTrace();
  78.         }
  79.     }
  80.     return sb.toString();
  81. }

ppt03转为图片

  1. public static String ppt03ToImage(String from, String images) {
  2.     StringBuilder sb = new StringBuilder();
  3.     FileInputStream fis = null;
  4.     FileOutputStream fos = null;
  5.     HSLFSlideShow ppt = null;
  6.     try {
  7.         // 1.如果图片文件夹存在,删除重新创建之
  8.         File imagePathFile = new File(images);
  9.         if (imagePathFile.exists()) {
  10.             FileUtils.deleteDirectory(imagePathFile);
  11.         }
  12.         imagePathFile.mkdirs();
  14.         fis = new FileInputStream(from);
  15.         ppt = new HSLFSlideShow(fis);
  16.         // 获取PPT每页的大小（宽和高度）
  17.         Dimension onePPTPageSize = ppt.getPageSize();
  19.         // 获得PPT文件中的所有的PPT页面（获得每一张幻灯片）,并转为一张张的播放片
  20.         List<HSLFSlide> pptPageSlideList = ppt.getSlides();
  21.         // 下面循环的主要功能是实现对PPT文件中的每一张幻灯片进行转换和操作
  22.         for (int i = 0; i < pptPageSlideList.size(); i++) {
  23.             // 这几个循环只要是设置字体为宋体，防止中文乱码，
  24.             List<List<HSLFTextParagraph>> oneTextParagraphs = pptPageSlideList.get(i).getTextParagraphs();
  25.             for (List<HSLFTextParagraph> list : oneTextParagraphs) {
  26.                 for (HSLFTextParagraph hslfTextParagraph : list) {
  27.                     List<HSLFTextRun> HSLFTextRunList = hslfTextParagraph.getTextRuns();
  28.                     for (int j = 0; j < HSLFTextRunList.size(); j++) {
  30.          /*
  31.           * 如果PPT在WPS中保存过，则 HSLFTextRunList.get(j).getFontSize();的值为0或者26040，
  32.           * 因此首先识别当前文本框内的字体尺寸是否为0或者大于26040，则设置默认的字体尺寸。
  33.           *
  34.           */
  35.                         // 设置字体大小
  36.                         Double size = HSLFTextRunList.get(j).getFontSize();
  37.                         if ((size <= 0) || (size >= 26040)) {
  38.                             HSLFTextRunList.get(j).setFontSize(20.0);
  39.                         }
  40.                         // 设置字体样式为宋体
  41.                         // String family=HSLFTextRunList.get(j).getFontFamily();
  42.                         // HSLFTextRunList.get(j).setFontFamily("宋体");
  43.                         int index = HSLFTextRunList.get(j).getFontIndex();
  44.                         String name = HSLFTextRunList.get(j).getFontFamily();
  45.                         HSLFTextRunList.get(j).setFontIndex(1);
  46.                         HSLFTextRunList.get(j).setFontFamily("宋体");
  47.                         log.info("ppt info:"+HSLFTextRunList.get(j).getRawText());
  48.                     }
  49.                 }
  51.             }
  52.             /**
  53.              * 创建BufferedImage对象，图像的尺寸为原来的每页的尺寸
  54.              */
  55.             BufferedImage oneBufferedImage = new BufferedImage(onePPTPageSize.width, onePPTPageSize.height,
  56.                     BufferedImage.TYPE_INT_RGB);
  57.             Graphics2D oneGraphics2D = oneBufferedImage.createGraphics();
  58.             /**
  59.              * 设置转换后的图片背景色为白色
  60.              *
  61.              */
  62.             oneGraphics2D.setPaint(Color.white);
  63.             oneGraphics2D.fill(new Rectangle2D.Float(0, 0, onePPTPageSize.width, onePPTPageSize.height));
  64.             pptPageSlideList.get(i).draw(oneGraphics2D);
  65.             /**
  66.              * 设置图片的存放路径和图片格式
  67.              */
  68.             String imgName = images + File.separator + UuidUtil.getUUID() + ".jpg";
  69.             sb.append(imgName);
  70.             sb.append(",");
  71.             fos = new FileOutputStream(imgName);
  72.             /**
  73.              * 图片文件保存的指定的目录中
  74.              */
  75.             ImageIO.write(oneBufferedImage, "jpg", fos);
  76.         }
  77.     } catch (Exception e) {
  78.         e.printStackTrace();
  79.     } finally {
  80.         try {
  81.             if(null != fis) {
  82.                 fis.close();
  83.             }
  84.             if(null != ppt) {
  85.                 ppt.close();
  86.             }
  87.             if(null != fos){
  88.                 fos.close();
  89.             }
  90.         } catch (IOException e) {
  92.             e.printStackTrace();
  93.         }
  94.     }
  95.     return sb.toString();
  96. }

（完）

发表评论

表情：
评论列表 （有 0 条评论，552人围观）

还没有评论，来说两句吧...

相关阅读

    相关 文件在线预览

    浏览器并不能支持word、excel文件的在线预览，所以都是将word、excel转换为浏览器能直接看的文件格式（html、pdf、txt、png、svg、flash），因此在

    野性酷女野性酷女/ 0 赞/ 914 阅读