最近用到了,记一下;
ppt转pdf分为两种情况: 小于2007版本的 .ppt格式(2003) 与大于2007版本的 .pptx格式(2007)
.ppt格式为 二进制文件
.pptx格式为xml格式,在java中有不同的jar包需要使用
引入 jar
<dependency><groupId>org.apache.poi</groupId><artifactId>poi</artifactId><version>4.0.1</version>
</dependency>
<dependency><groupId>org.apache.poi</groupId><artifactId>poi-ooxml</artifactId><version>4.0.1</version>
</dependency>
<dependency><groupId>org.apache.poi</groupId><artifactId>poi-ooxml-schemas</artifactId><version>4.0.1</version>
</dependency>
<dependency><groupId>org.apache.poi</groupId><artifactId>poi-scratchpad</artifactId><version>4.0.1</version>
</dependency>
<dependency><groupId>com.itextpdf</groupId><artifactId>itextpdf</artifactId><version>5.5.6</version>
</dependency>
代码
package cc.vace.cloud.utils;import com.itextpdf.text.Document;
import com.itextpdf.text.DocumentException;
import com.itextpdf.text.pdf.*;
import org.apache.poi.hslf.usermodel.HSLFSlide;
import org.apache.poi.hslf.usermodel.HSLFSlideShow;
import org.apache.poi.hslf.usermodel.HSLFTextShape;
import org.apache.poi.xslf.usermodel.*;import java.awt.*;
import java.awt.image.BufferedImage;
import java.io.*;
import java.util.List;
import java.util.Objects;/*** @author vace cc*/
public class PptUtil {public static void main(String[] args) throws IOException, DocumentException {FileInputStream inputStream0 = new FileInputStream("F:\\file\\text.ppt");FileInputStream inputStream1 = new FileInputStream("F:/file/text.pptx");FileOutputStream outputStream0 = new FileOutputStream("F:\\file\\text0.pdf");FileOutputStream outputStream1 = new FileOutputStream("F:/file/text1.pdf");pptToPdf(inputStream0, outputStream0);pptxToPdf(inputStream1,outputStream1);}/*** ppt二进制文件转pdf** @param pptIs ppt原文件流* @param pdfOs pdf 输出文件流* @return true* @throws IOException io* @throws DocumentException doc*/public static boolean pptToPdf(InputStream pptIs, OutputStream pdfOs) throws IOException, DocumentException {Document doc = new Document();HSLFSlideShow hslfSlideShow = null;PdfWriter pdfWriter = null;try {hslfSlideShow = new HSLFSlideShow(pptIs);Dimension dimension = hslfSlideShow.getPageSize();pdfWriter = PdfWriter.getInstance(doc, pdfOs);doc.open();PdfPTable pdfpTable = new PdfPTable(1);List<HSLFSlide> slides = hslfSlideShow.getSlides();// 设置ppt 为宋体,否则转pdf时会乱码for (HSLFSlide slide : slides) {slide.getShapes().stream().filter(shape -> shape instanceof HSLFTextShape).map(shape -> (HSLFTextShape) shape).forEach(shapeH -> shapeH.getTextParagraphs().forEach(paragraph -> paragraph.getTextRuns().forEach(textRun -> textRun.setFontFamily("宋体"))));BufferedImage bufferedImage = new BufferedImage((int)dimension.getWidth(), (int)dimension.getHeight(), BufferedImage.TYPE_INT_RGB);Graphics2D graphics = bufferedImage.createGraphics();graphics.setPaint(Color.white);graphics.setFont(new java.awt.Font("宋体", java.awt.Font.PLAIN, 12));slide.draw(graphics);graphics.dispose();com.itextpdf.text.Image image = com.itextpdf.text.Image.getInstance(bufferedImage, null);image.scalePercent(50f);// 写入单元格pdfpTable.addCell(new PdfPCell(image, true));doc.add(image);}System.out.println("---------- 转换成功 -------------");return true;} catch (Throwable e) {e.printStackTrace();System.out.println("---------- 转换失败 -------------");throw e;} finally {doc.close();if (!Objects.isNull(hslfSlideShow)) {hslfSlideShow.close();}if (null != pdfWriter) {pdfWriter.close();}}}/*** pptx XML文件转pdf* @param pptIs ppt原文件流* @param pdfOs pdf 输出文件流* @return true* @throws IOException io*/public static boolean pptxToPdf(InputStream pptIs, OutputStream pdfOs) throws IOException {Document doc = new Document();XMLSlideShow slideShow = null;PdfWriter pdfWriter = null;try {slideShow = new XMLSlideShow(pptIs);pdfWriter = PdfWriter.getInstance(doc,pdfOs);Dimension dimension = slideShow.getPageSize();doc.open();PdfPTable pdfpTable = new PdfPTable(1);List<XSLFSlide> slides = slideShow.getSlides();for (XSLFSlide slide : slides) {// 设置字体slide.getShapes().stream().filter(shape -> shape instanceof XSLFTextShape).map(shape -> (XSLFTextShape) shape).forEach(shapeH -> shapeH.getTextParagraphs().forEach(paragraph -> paragraph.getTextRuns().forEach(textRun -> textRun.setFontFamily("宋体"))));BufferedImage bufferedImage = new BufferedImage((int) dimension.getWidth(), (int) dimension.getHeight(), BufferedImage.TYPE_INT_RGB);Graphics2D graphics = bufferedImage.createGraphics();graphics.setPaint(Color.white);graphics.setFont(new Font("宋体", Font.PLAIN, 12));slide.draw(graphics);com.itextpdf.text.Image image = com.itextpdf.text.Image.getInstance(bufferedImage, null);image.scalePercent(50f);pdfpTable.addCell(new PdfPCell(image, true));doc.add(image);}if (slides.size() == 0) {BufferedImage bufferedImage = new BufferedImage((int) dimension.getWidth(), (int) dimension.getHeight(), BufferedImage.TYPE_INT_ARGB);com.itextpdf.text.Image image = com.itextpdf.text.Image.getInstance(bufferedImage, null);pdfpTable.addCell(new PdfPCell(image, true));doc.add(image);}System.out.println("---------- 转换成功 -------------");return true;}catch (Throwable e) {e.printStackTrace();
// throw e;return false;}finally {doc.close();if (!Objects.isNull(slideShow)) {slideShow.close();}if (pdfWriter != null) {pdfWriter.close();}}}}
遇到的exception
遇见报错document 是空的
The document has no pages.
遇见这个问题,一般情况下是因为slide.draw报错了,但是catch捕获 不到,最后在执行完成之后报错,但此时的错是finally里异常关闭文件导致的,所以会报document has no pages 无法关闭
这里做几个问题点去切入
一、
首先要注意的是这里catch 的是Throwable 而不是Exception
因为当 slide.draw() 方法报错 是继承的Throwable 的异常,而不是Exception 的,所以使用Exception 去捕获异常的时候会失败
catch (Throwable e) {e.printStackTrace();throw e;return false;
}
二、
针对jdk8以上的版本:如jdk11
报错
javax/xml/bind/JAXBException
需要添加额外的jar包
<dependency><groupId>javax.activation</groupId><artifactId>activation</artifactId><version>1.1.1</version>
</dependency>
<dependency><groupId>javax.xml.bind</groupId><artifactId>jaxb-api</artifactId><version>2.3.0</version>
</dependency>
<dependency><groupId>com.sun.xml.bind</groupId><artifactId>jaxb-core</artifactId><version>2.3.0.1</version>
</dependency>
<dependency><groupId>com.sun.xml.bind</groupId><artifactId>jaxb-impl</artifactId><version>2.3.0.1</version>
</dependency>
三
如果上传的一个空ppt 则pdf文件一定是已损坏,有两种解决办法,一,初始化一个空的pdf
这里选择TYPE_INT_ARGB,这样底色就是空白的啦,如果使用TYPE_INT_RGB那就是一块黑
if (slides.size() == 0) {BufferedImage bufferedImage = new BufferedImage((int) dimension.getWidth(), (int) dimension.getHeight(), BufferedImage.TYPE_INT_ARGB);com.itextpdf.text.Image image = com.itextpdf.text.Image.getInstance(bufferedImage, null);pdfpTable.addCell(new PdfPCell(image, true));doc.add(image);}
poi的5.X版本
这里介绍的poi适合4.X的版本,如果使用 5.X版本则需要加入xmlbeans包
<dependency><groupId>org.apache.xmlbeans</groupId><artifactId>xmlbeans</artifactId><version>5.0.3</version>
</dependency>
完整的 5.X包:截止博主写文的时间,最新的poi版本如下
<dependency><groupId>org.apache.poi</groupId><artifactId>poi</artifactId><version>5.2.2</version></dependency><dependency><groupId>org.apache.poi</groupId><artifactId>poi-ooxml</artifactId><version>5.2.2</version></dependency><dependency><groupId>org.apache.poi</groupId><artifactId>poi-ooxml-schemas</artifactId><version>4.1.2</version></dependency><dependency><groupId>org.apache.poi</groupId><artifactId>poi-scratchpad</artifactId><version>5.2.2</version></dependency><dependency><groupId>com.itextpdf</groupId><artifactId>itextpdf</artifactId><version>5.5.13.3</version></dependency><dependency><groupId>org.apache.xmlbeans</groupId><artifactId>xmlbeans</artifactId><version>5.0.3</version></dependency>
设置页面大小
当我们把上边的步骤实现之后,发现两个ppt 合成了一个pdf页面,想要一个pdf页面对应一个ppt页面
实现方式:
Document 在new 的 时候可以直接将页面的尺寸放进去
Document 可以使用 setPageSize来设置大小
setPageSize 有一个问题,setPageSize不会立即生效,导致我们在设置页面的时候,从第二页开始才会生效。 具体是bug还是故意这样设计的不清楚
代码实现:只列出 pptx格式的
ppt 转也是一样的
public static boolean pptxToPdf(InputStream pptIs, OutputStream pdfOs) throws IOException {Document doc = null;XMLSlideShow slideShow = null;PdfWriter pdfWriter = null;try {slideShow = new XMLSlideShow(pptIs);Dimension dimension = slideShow.getPageSize();BufferedImage bufferedImage0 = new BufferedImage((int) dimension.getWidth(), (int) dimension.getHeight(), BufferedImage.TYPE_INT_ARGB);com.itextpdf.text.Image image0 = com.itextpdf.text.Image.getInstance(bufferedImage0, null);com.itextpdf.text.Rectangle pageSize = new com.itextpdf.text.Rectangle(image0);//PageSize.A4.rotate()doc = new Document(pageSize);pdfWriter = PdfWriter.getInstance(doc,pdfOs);doc.open();PdfPTable pdfpTable = new PdfPTable(1);List<XSLFSlide> slides = slideShow.getSlides();// 如果是空ppt, 则生成默认一页if (slides.size() == 0) {doc.add(image0);}for (XSLFSlide slide : slides) {// 设置字体slide.getShapes().stream().filter(shape -> shape instanceof XSLFTextShape).map(shape -> (XSLFTextShape) shape).forEach(shapeH -> shapeH.getTextParagraphs().forEach(paragraph -> paragraph.getTextRuns().forEach(textRun -> textRun.setFontFamily("宋体"))));BufferedImage bufferedImage = new BufferedImage((int) dimension.getWidth(), (int) dimension.getHeight(), BufferedImage.TYPE_INT_RGB);Graphics2D graphics = bufferedImage.createGraphics();graphics.setPaint(Color.white);graphics.setFont(new Font("宋体", Font.PLAIN, 12));slide.draw(graphics);com.itextpdf.text.Image image = com.itextpdf.text.Image.getInstance(bufferedImage, null);image.scalePercent(90f);pdfpTable.addCell(new PdfPCell(image, true));doc.add(image);}System.out.println("---------- 转换成功 -------------");return true;}catch (Throwable e) {e.printStackTrace();
// throw e;return false;}finally {doc.close();if (!Objects.isNull(slideShow)) {slideShow.close();}if (pdfWriter != null) {pdfWriter.close();}}
}