java ： word,excel,img,ppt各种文档转换pdf格式以流方式
前提：
面对各种文件转换pdf格式，我下面写的都是一些方法，其中每个方法都以流的方式进行参数的传递。
通过猿友的帮忙，修改了部分jar包，解决excel转换pdf导致的水印问题~，通过配置log4j2.xml 解决日志报错问题
源码链接：https://pan.baidu.com/s/1twLNvNE-e0AEa5EVetyOFA
提取码：asdf
jar包 例如com.aspose的包在项目的myjar目录中，需要手动导入。其他的jar包，例如itextpdf可通过依赖直接导入
（上传的项目代码里面ppt/pptx还没有更新代码，主要是修复ppt、pptx转pdf的汉字乱码问题，最新的代码请参考文章，文章内容是最新的）
```java
org.apache.poi
poi
4.1.2
org.apache.poi
poi-ooxml
4.1.2
org.apache.poi
poi-scratchpad
4.1.2
com.itextpdf
itextpdf
5.4.3
com.itextpdf
itext-asian
5.2.0
org.docx4j
docx4j
3.2.2
org.apache.logging.log4j
log4j-api
2.17.1
org.apache.logging.log4j
log4j-core
2.11.1
org.apache.xmlbeans
xmlbeans
5.0.3
org.apache.poi
poi-ooxml-schemas
4.1.2
org.apache.commons
commons-compress
1.19
org.apache.commons
commons-collections4
4.1
com.zaxxer
SparseBitSet
1.2
cn.hutool
hutool-all
5.6.0
# 工具类主体:
```java
import com.aspose.words.*;
import com.itextpdf.text.Document;
import com.itextpdf.text.Image;
import com.itextpdf.text.*;
import com.itextpdf.text.pdf.*;
import org.apache.poi.hslf.usermodel.*;
import org.apache.poi.xslf.usermodel.*;
import java.awt.*;
import java.awt.Color;
import java.awt.image.BufferedImage;
import java.io.*;
import java.util.List;
public final class PdfConverUtil {
// 这里放下面的方法
xxxx...
}
img(png)转换pdf：
关于图片转换pdf的像素问题，可以设置转换pdf的大小来控制
/**
* @param inputStream 源文件输入流
* @param outputStream pdf文件输出流
**/
public static boolean imgToPdf(InputStream inputStream, OutputStream outputStream) {
Document document = null;
try {
// 创建文档,设置PDF页面的大小 A2-A9, 个人觉得A3最合适
document = new Document(PageSize.A3, 20, 20, 20, 20);
// 新建pdf文档,具体逻辑看.getInstance方法
PdfWriter.getInstance(document, outputStream);
document.open();
document.newPage();
// 将文件流转换为字节流，便于格式转换
BufferedInputStream bufferedInputStream = new BufferedInputStream(inputStream);
ByteArrayOutputStream byteArrayOutputStream = new ByteArrayOutputStream();
byte[] bytes = new byte[1024];
int length = 0 ;
while (-1 != (length = bufferedInputStream.read(bytes))) {
byteArrayOutputStream.write(bytes, 0, length);
}
// 处理img图片
Image image = Image.getInstance(byteArrayOutputStream.toByteArray());
float height = image.getHeight();
float width = image.getWidth();
float percent = 0.0f;
// 设置像素或者长宽高,将会影响图片的清晰度，因为只是对图片放大或缩小
if (height > width) {
// A4 - A9
percent = PageSize.A6.getHeight() / height * 100;
} else {
percent = PageSize.A6.getWidth() / width * 100;
}
image.setAlignment(Image.MIDDLE);
image.scalePercent(percent);
// 将图片放入文档中，完成pdf转换
document.add(image);
System.out.println("image转换完毕");
} catch (Exception e) {
e.printStackTrace();
return false;
} finally {
try {
if (document != null) {
document.close();
}
} catch (Exception e) {
e.printStackTrace();
}
}
return true;
}
word(doc/docx)转换pdf：
该方法运行可能出现警告：（可忽略，不影响pdf文件生成！）
WARNING: Could not open/create prefs root node Software\JavaSoft\Prefs at root 0x80000002. Windows RegCreateKeyEx(…) returned error code 5.
解决方法: http://t.csdn.cn/zQn6C
/**
* @param inputStream 源文件输入流
* @param outputStream pdf文件输出流
**/
public static boolean wordTopdfByAspose(InputStream inputStream, OutputStream outputStream) {
// 验证License 若不验证则转化出的pdf文档会有水印产生
if (!getLicense()) {
return false;
}
try {
// 将源文件保存在com.aspose.words.Document中，具体的转换格式依靠里面的save方法
com.aspose.words.Document doc = new com.aspose.words.Document(inputStream);
// 全面支持DOC, DOCX, OOXML, RTF HTML, OpenDocument, PDF,EPUB, XPS, SWF 相互转换
doc.save(outputStream, SaveFormat.PDF);
System.out.println("word转换完毕");
} catch (Exception e) {
e.printStackTrace();
return false;
}finally {
if (outputStream != null) {
try {
outputStream.flush();
outputStream.close();
} catch (IOException e) {
e.printStackTrace();
}
}
}
return true;
}
// 官方文档的要求 无需理会
public static boolean getLicense() {
boolean result = false;
try {
String s = "Aspose.Total for Java Aspose.Words for Java Enterprise 20991231 20991231 8bfe198c-7f0c-4ef8-8ff0-acc3237bf0d7 sNLLKGMUdF0r8O1kKilWAGdgfs2BvJb/2Xp8p5iuDVfZXmhppo+d0Ran1P9TKdjV4ABwAgKXxJ3jcQTqE/2IRfqwnPf8itN8aFZlV3TJPYeD3yWE7IT55Gz6EijUpC7aKeoohTb4w2fpox58wWoF3SNp6sK6jDfiAUGEHYJ9pjU= excel(xlsx)转换pdf：
excel中的 Workbook 使用的是 com.aspose.cells 包下的。注意！！！
至于sheet相关，分页问题，可以据情况修改方法printSheetPage()和autoDraw()
/**
* @param inputStream 源文件输入流
* @param outputStream pdf文件输出流
**/
public static boolean excelToPdf(InputStream inputStream, OutputStream outputStream) {
// 验证License 若不验证则转化出的pdf文档会有水印产生
if (!getExeclLicense()) {
return false;
}
try {
com.aspose.cells.Workbook wb = new com.aspose.cells.Workbook(inputStream);// 原始excel路径
com.aspose.cells.PdfSaveOptions pdfSaveOptions = new com.aspose.cells.PdfSaveOptions();
pdfSaveOptions.setOnePagePerSheet(false);
int[] autoDrawSheets={3};
//当excel中对应的sheet页宽度太大时，在PDF中会拆断并分页。此处等比缩放。
autoDraw(wb,autoDrawSheets);
int[] showSheets={0};
//隐藏workbook中不需要的sheet页。
printSheetPage(wb,showSheets);
wb.save(outputStream, pdfSaveOptions);
outputStream.flush();
outputStream.close();
System.out.println("excel转换完毕");
} catch (IOException e) {
e.printStackTrace();
} catch (Exception e) {
e.printStackTrace();
}
return true;
}
/**
* 设置打印的sheet 自动拉伸比例
* @param wb
* @param page 自动拉伸的页的sheet数组
*/
public static void autoDraw(com.aspose.cells.Workbook wb,int[] page){
if(null!=page&&page.length>0){
for (int i = 0; i < page.length; i++) {
wb.getWorksheets().get(i).getHorizontalPageBreaks().clear();
wb.getWorksheets().get(i).getVerticalPageBreaks().clear();
}
}
}
/**
* 隐藏workbook中不需要的sheet页。
*
* @param wb
* @param page 显示页的sheet数组
*/
public static void printSheetPage(com.aspose.cells.Workbook wb, int[] page) {
for (int i = 1; i < wb.getWorksheets().getCount(); i++) {
wb.getWorksheets().get(i).setVisible(false);
}
if (null == page || page.length == 0) {
wb.getWorksheets().get(0).setVisible(true);
} else {
for (int i = 0; i < page.length; i++) {
wb.getWorksheets().get(i).setVisible(true);
}
}
}
public static boolean getExeclLicense() {
boolean result = false;
try {
String s = "Aspose.Total for Java Aspose.Words for Java Enterprise 20991231 20991231 8bfe198c-7f0c-4ef8-8ff0-acc3237bf0d7 sNLLKGMUdF0r8O1kKilWAGdgfs2BvJb/2Xp8p5iuDVfZXmhppo+d0Ran1P9TKdjV4ABwAgKXxJ3jcQTqE/2IRfqwnPf8itN8aFZlV3TJPYeD3yWE7IT55Gz6EijUpC7aKeoohTb4w2fpox58wWoF3SNp6sK6jDfiAUGEHYJ9pjU= ppt(ppt/pptx)转换pdf：
ppt和pptx使用的Document类是 com.itextpdf.text包下面,注意！由于ppt和pptx的编码格式不一样，所以单独写了针对ppt 和 pptx 的转换
/**
* pptToPdf
* @param inputStream
* @param outputStream
* @return
*/
public static boolean pptToPdf(InputStream inputStream, OutputStream outputStream) {
Document document = null;
HSLFSlideShow hslfSlideShow = null;
PdfWriter pdfWriter = null;
try {
hslfSlideShow = new HSLFSlideShow(inputStream);
// 获取ppt文件页面
Dimension dimension = hslfSlideShow.getPageSize();
document = new Document();
// pdfWriter实例
pdfWriter = PdfWriter.getInstance(document, outputStream);
document.open();
PdfPTable pdfPTable = new PdfPTable(1);
List<HSLFSlide> hslfSlideList = hslfSlideShow.getSlides();
for (int i=0; i < hslfSlideList.size(); i++) {
HSLFSlide hslfSlide = hslfSlideList.get(i);
// 设置字体, 解决中文乱码
for (HSLFShape shape : hslfSlide.getShapes()) {
if (shape instanceof HSLFTextShape) {
HSLFTextShape textShape = (HSLFTextShape) shape;
for (HSLFTextParagraph textParagraph : textShape.getTextParagraphs()) {
for (HSLFTextRun textRun : textParagraph.getTextRuns()) {
textRun.setFontFamily("宋体");
}
}
}
}
BufferedImage bufferedImage = new BufferedImage((int)dimension.getWidth(), (int)dimension.getHeight(), BufferedImage.TYPE_INT_RGB);
Graphics2D graphics2d = bufferedImage.createGraphics();
graphics2d.setPaint(Color.white);
graphics2d.setFont(new java.awt.Font("宋体", java.awt.Font.PLAIN, 12));
hslfSlide.draw(graphics2d);
graphics2d.dispose();
Image image = Image.getInstance(bufferedImage, null);
image.scalePercent(50f);
// 写入单元格
pdfPTable.addCell(new PdfPCell(image, true));
document.add(image);
}
} catch (Exception e) {
e.printStackTrace();
return false;
} finally {
if (document != null) {
document.close();
}
if (pdfWriter != null) {
pdfWriter.close();
}
}
System.out.println("ppt转换完毕");
return true;
}
/**
* pptxToPdf
* @param inputStream
* @param outputStream
* @return
*/
public static boolean pptxToPdf(InputStream inputStream, OutputStream outputStream) {
Document document = null;
XMLSlideShow slideShow = null;
PdfWriter pdfWriter = null;
try {
slideShow = new XMLSlideShow(inputStream);
Dimension dimension = slideShow.getPageSize();
document = new Document();
pdfWriter = PdfWriter.getInstance(document, outputStream);
document.open();
PdfPTable pdfPTable = new PdfPTable(1);
List<XSLFSlide> slideList = slideShow.getSlides();
for (int i = 0, row = slideList.size(); i < row; i++) {
XSLFSlide slide = slideList.get(i);
// 设置字体, 解决中文乱码
for (XSLFShape shape : slide.getShapes()) {
if (shape instanceof XSLFTextShape) {
XSLFTextShape textShape = (XSLFTextShape) shape;
for (XSLFTextParagraph textParagraph : textShape.getTextParagraphs()) {
for (XSLFTextRun textRun : textParagraph.getTextRuns()) {
textRun.setFontFamily("宋体");
}
}
}
}
BufferedImage bufferedImage = new BufferedImage((int)dimension.getWidth(), (int)dimension.getHeight(), BufferedImage.TYPE_INT_RGB);
Graphics2D graphics2d = bufferedImage.createGraphics();
graphics2d.setPaint(Color.white);
graphics2d.setFont(new java.awt.Font("宋体", java.awt.Font.PLAIN, 12));
slide.draw(graphics2d);
graphics2d.dispose();
Image image = Image.getInstance(bufferedImage, null);
image.scalePercent(50f);
// 写入单元格
pdfPTable.addCell(new PdfPCell(image, true));
document.add(image);
}
} catch (Exception e) {
e.printStackTrace();
return false;
} finally {
if (document != null) {
document.close();
}
if (pdfWriter != null) {
pdfWriter.close();
}
}
System.out.println("pptx转换完毕");
return true;
}
测试
import java.io.FileInputStream;
import java.io.FileNotFoundException;
import java.io.FileOutputStream;
/**
* 功能说明:
* 开发人员: zhouyangyang
* 开发时间: 2022/6/28
* 功能描述: 写明作用，调用方式，使用场景，以及特殊情况
*/
public class Test {
public static void main(String[] args) {
// imgae to pdf
try {
FileInputStream inputStream = new FileInputStream("D:\\testConvert\\银行卡.jpg");
FileOutputStream byteArrayOutputStream = new FileOutputStream("D:\\testConvert\\银行卡.pdf");
PdfConverUtil.imgToPdf(inputStream, byteArrayOutputStream);
} catch (FileNotFoundException e) {
e.printStackTrace();
}
// doc/docx to pdf
try {
FileInputStream inputStream = new FileInputStream("D:\\testConvert\\zyydocx.docx");
FileOutputStream byteArrayOutputStream = new FileOutputStream("D:\\testConvert\\zyydocx.pdf");
PdfConverUtil.wordTopdfByAspose(inputStream, byteArrayOutputStream);
} catch (FileNotFoundException e) {
e.printStackTrace();
}
// execl to pdf
try {
FileInputStream inputStream = new FileInputStream("D:\\testConvert\\zyyexcel.xls");
FileOutputStream byteArrayOutputStream = new FileOutputStream("D:\\testConvert\\zyyexcel.pdf");
PdfConverUtil.excelToPdf(inputStream, byteArrayOutputStream);
} catch (FileNotFoundException e) {
e.printStackTrace();
}
// ppt tp pdf
try {
FileInputStream inputStream = new FileInputStream("D:\\testConvert\\zyy123ppt.ppt");
FileOutputStream byteArrayOutputStream = new FileOutputStream("D:\\testConvert\\zyy123pptnew.pdf");
PdfConverUtil.pptToPdf(inputStream, byteArrayOutputStream);
} catch (FileNotFoundException e) {
e.printStackTrace();
}
// pptx to pdf
try {
FileInputStream inputStream = new FileInputStream("D:\\testConvert\\zyypptx.pptx");
FileOutputStream byteArrayOutputStream = new FileOutputStream("D:\\testConvert\\zyypptxnew.pdf");
PdfConverUtil.pptxToPdf(inputStream, byteArrayOutputStream);
} catch (FileNotFoundException e) {
e.printStackTrace();
}
}
}
如图：
存在的问题
1.中文乱码(已解决),具体可参考
// 设置字体, 解决中文乱码
for (XSLFShape shape : slide.getShapes()) {
if (shape instanceof XSLFTextShape) {
XSLFTextShape textShape = (XSLFTextShape) shape;
- 日志报错(已解决), 错误提示 是要配置引入log4j2
2.1 导入两个依赖
<dependency>
<groupId>org.apache.logging.log4j</groupId>
<artifactId>log4j-api</artifactId>
<version>2.17.1</version>
</dependency>
<dependency>
<groupId>org.apache.logging.log4j</groupId>
<artifactId>log4j-core</artifactId>
<version>2.11.1</version>
</dependency>
2.2 在classpath路径下添加log4j2.xml配置文件
<?xml version="1.0" encoding="UTF-8"?>
<Configuration status="warn">
<Appenders>
<Console name="Console" target="SYSTEM_OUT">
<PatternLayout pattern="[%-5p] %d %c - %m%n" />
</Console>
<File name="File" fileName="dist/my.log">
<PatternLayout pattern="%m%n" />
</File>
</Appenders>
<Loggers>
<Logger name="mh.sample2.Log4jTest2" level="INFO">
<AppenderRef ref="File" />
</Logger>
<Root level="INFO">
<AppenderRef ref="Console" />
</Root>
</Loggers>
</Configuration>
- 目前ppt/pptx若存在图片，则需要注释掉以下代码，否则转换pdf异常，关于如何解决，后续有时间再更新
// 设置字体, 解决中文乱码
for (XSLFShape shape : slide.getShapes()) {
if (shape instanceof XSLFTextShape) {
XSLFTextShape textShape = (XSLFTextShape) shape;
for (XSLFTextParagraph textParagraph : textShape.getTextParagraphs()) {
for (XSLFTextRun textRun : textParagraph.getTextRuns()) {
textRun.setFontFamily("宋体");
}
}
}
}