java实现PPT转PDF出现中文乱码问题的解决方法

ppt转成pdf，原理是ppt转成图片，再用图片生产pdf，过程有个问题，不管是ppt还是pptx，都遇到中文乱码，编程方框的问题，其中ppt后缀网上随便找就有解决方案，就是设置字体为统一字体，pptx如果页面是一种中文字体不会有问题，如果一个页面有微软雅黑和宋体，就会导致部分中文方框，怀疑是poi处理的时候，只读取第一种字体，所以导致多个中文字体乱码。
百度和谷歌都找了很久，有看到说apache官网有人说是bug，但他们回复说是字体问题，这个问题其实我觉得poi可能可以自己做，读取原来字体设置成当前字体，不过性能应该会有很多消耗，反正我估计很多人跟我一样花费大量时间找解决方案，网上几乎没有现成的方案。自己也是一步步尝试，最终找到解决办法，ppt格式的就不说了网上找得到，pptx后缀的网上我是没找到。
问题前的pptx转成图片：

解决后的pptx转成图片：

解决方法：
读取每个shape，将文字转成统一的字体，网上找到的那段代码不可行，我自己改的方案如下：

for( XSLFShape shape : slide[i].getShapes() ){
     if ( shape instanceof XSLFTextShape ){
      XSLFTextShape txtshape = (XSLFTextShape)shape ;
      System.out.println("txtshape" + (i+1) + ":" + txtshape.getShapeName());
      System.out.println("text:" +txtshape.getText());

      for ( XSLFTextParagraph textPara : txtshape.getTextParagraphs() ){
       List<XSLFTextRun> textRunList = textPara.getTextRuns();
       for(XSLFTextRun textRun: textRunList) {
        textRun.setFontFamily("宋体");
       }
      }
     }
    }

完整代码如下（除了以上自己的解决方案，大部分是stackoverflow上的代码）：

public static void convertPPTToPDF(String sourcepath, String destinationPath, String fileType) throws Exception {
  FileInputStream inputStream = new FileInputStream(sourcepath);
  double zoom = 2;
  AffineTransform at = new AffineTransform();
  at.setToScale(zoom, zoom);
  Document pdfDocument = new Document();
  PdfWriter pdfWriter = PdfWriter.getInstance(pdfDocument, new FileOutputStream(destinationPath));
  PdfPTable table = new PdfPTable(1);
  pdfWriter.open();
  pdfDocument.open();
  Dimension pgsize = null;
  Image slideImage = null;
  BufferedImage img = null;
  if (fileType.equalsIgnoreCase(".ppt")) {
   SlideShow ppt = new SlideShow(inputStream);
   inputStream.close();
   pgsize = ppt.getPageSize();
   Slide slide[] = ppt.getSlides();
   pdfDocument.setPageSize(new Rectangle((float) pgsize.getWidth(), (float) pgsize.getHeight()));
   pdfWriter.open();
   pdfDocument.open();
   for (int i = 0; i < slide.length; i++) {

    TextRun[] truns = slide[i].getTextRuns();
    for ( int k=0;k<truns.length;k++){
     RichTextRun[] rtruns = truns[k].getRichTextRuns();
     for(int l=0;l<rtruns.length;l++){
//      int index = rtruns[l].getFontIndex();
//      String name = rtruns[l].getFontName();
      rtruns[l].setFontIndex(1);
      rtruns[l].setFontName("宋体");
     }
    }  

    img = new BufferedImage((int) Math.ceil(pgsize.width * zoom), (int) Math.ceil(pgsize.height * zoom), BufferedImage.TYPE_INT_RGB);
    Graphics2D graphics = img.createGraphics();
    graphics.setTransform(at);

    graphics.setPaint(Color.white);
    graphics.fill(new Rectangle2D.Float(0, 0, pgsize.width, pgsize.height));
    slide[i].draw(graphics);
    graphics.getPaint();
    slideImage = Image.getInstance(img, null);
    table.addCell(new PdfPCell(slideImage, true));
   }
  }
  if (fileType.equalsIgnoreCase(".pptx")) {
   XMLSlideShow ppt = new XMLSlideShow(inputStream);
   pgsize = ppt.getPageSize();
   XSLFSlide slide[] = ppt.getSlides();
   pdfDocument.setPageSize(new Rectangle((float) pgsize.getWidth(), (float) pgsize.getHeight()));
   pdfWriter.open();
   pdfDocument.open();

   for (int i = 0; i < slide.length; i++) {
    for( XSLFShape shape : slide[i].getShapes() ){
     if ( shape instanceof XSLFTextShape ){
      XSLFTextShape txtshape = (XSLFTextShape)shape ;
      // System.out.println("txtshape" + (i+1) + ":" + txtshape.getShapeName());
      //System.out.println("text:" +txtshape.getText());

      for ( XSLFTextParagraph textPara : txtshape.getTextParagraphs() ){
       List<XSLFTextRun> textRunList = textPara.getTextRuns();
       for(XSLFTextRun textRun: textRunList) {
        textRun.setFontFamily("宋体");
       }
      }
     }
    }
    img = new BufferedImage((int) Math.ceil(pgsize.width * zoom), (int) Math.ceil(pgsize.height * zoom), BufferedImage.TYPE_INT_RGB);
    Graphics2D graphics = img.createGraphics();
    graphics.setTransform(at);
    graphics.setPaint(Color.white);
    graphics.fill(new Rectangle2D.Float(0, 0, pgsize.width, pgsize.height));
    slide[i].draw(graphics);

//    FileOutputStream out = new FileOutputStream("src/main/resources/test"+i+".jpg");
//    javax.imageio.ImageIO.write(img, "jpg", out);

    graphics.getPaint();
    slideImage = Image.getInstance(img, null);
    table.addCell(new PdfPCell(slideImage, true));
   }
  }
  pdfDocument.add(table);
  pdfDocument.close();
  pdfWriter.close();
  System.out.println("Powerpoint file converted to PDF successfully");
 }

maven配置:

<dependency>
  <groupId>org.apache.poi</groupId>
  <artifactId>poi</artifactId>
 <!-- <version>3.13</version> -->
  <version>3.9</version>
 </dependency>
 <dependency>
  <groupId>org.apache.poi</groupId>
  <artifactId>poi-ooxml</artifactId>
  <!-- <version>3.10-FINAL</version> -->
  <version>3.9</version>
 </dependency>

 <dependency>
   <groupId>com.itextpdf</groupId>
   <artifactId>itextpdf</artifactId>
   <version>5.5.7</version>
 </dependency>

 <dependency>
  <groupId>com.itextpdf.tool</groupId>
  <artifactId>xmlworker</artifactId>
  <version>5.5.7</version>
 </dependency>
 <dependency>
  <groupId>org.apache.poi</groupId>
  <artifactId>poi-scratchpad</artifactId>
  <!-- <version>3.12</version> -->
  <version>3.9</version>
 </dependency>

上面就是为大家分享的java实现PPT转PDF出现中文乱码问题的解决方法，希望对大家的学习有所帮助。