java PPT 轉成PDF,中文亂碼解決

jopen 9年前發布 | 41K 次閱讀 Java PDF工具包

        ppt轉成pdf,原理是ppt轉成圖片,再用圖片生產pdf,過程有個問題,不管是ppt還是pptx,都遇到中文亂碼,編程方框的問題,其中ppt后綴網上隨便找就有解決方案,就是設置字體為統一字體,pptx如果頁面是一種中文字體不會有問題,如果一個頁面有微軟雅黑和宋體,就會導致部分中文方框,懷疑是poi處理的時候,只讀取第一種字體,所以導致多個中文字體亂碼。

        百度和谷歌都找了很久,有看到說apache官網有人說是bug(https://bz.apache.org/bugzilla/show_bug.cgi?id=54880),但他們回復說是字體問題,這個問題其實我覺得poi可能可以自己做,讀取原來字體設置成當前字體,不過性能應該會有很多消耗,反正我估計很多人跟我一樣花費大量時間找解決方案,網上幾乎沒有現成的方案。自己也是一步步嘗試,最終找到解決辦法,ppt格式的就不說了網上找得到,pptx后綴的網上我是沒找到。

    問題前的pptx轉成圖片:

解決后的pptx轉成圖片:

解決方法:

圖取每個shape,將文字轉成統一的字體,網上找到的那段代碼不可行,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("宋體");
                            }
                        }
                    }
                }

完整代碼如下(除了以上自己的解決方案,大部分是網上摘抄):

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("宋體");                          
                   }      
                }      
                
                
                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("宋體");
                            }
                        }
                    }
                }
                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>

參考資料:

http://www.tutorialspoint.com/apache_poi_ppt/apache_poi_ppt_quick_guide.htm

 本文由用戶 jopen 自行上傳分享,僅供網友學習交流。所有權歸原作者,若您的權利被侵害,請聯系管理員。
 轉載本站原創文章,請注明出處,并保留原始鏈接、圖片水印。
 本站是一個以用戶分享為主的開源技術平臺,歡迎各類分享!