Java实现无损Word转PDF的示例代码

目录

• 前言
• word转pdf实现思路
• 项目远程仓库
• Maven项目pom文件依赖
• 核心代码实现
• 结果分析

前言

本来想写word转pdf和pdf转word的代码呢，没想到word转pdf就写了很多很多行代码才实现，为了方便大家消化理解，先写了word转pdf方法实现作为一篇文章。

word转pdf实现思路

代码实现主要依赖两个第三方jar包，一个是pdfbox，一个是aspose-words。pdfbox包完全开源免费，aspose-words免费版生成有水印，且生成数量有限制。单纯用pdfbox 实现word转pdf的话，实现非常复杂，且样式和原来样式，保持一致的的比例很低。所以，我先用aspose-words生成了带水印的pdf，再用pdfbox去除aspose-words生成的水印的，最终得到了一个无水印的pdf。

项目远程仓库

aspose-words 这个需要配置单独的仓库地址才能下载，不会配置的可以去官网直接下载jar引入项目代码中。

<repositories>
  <repository>
   <id>AsposeJavaAPI</id>
   <name>Aspose Java API</name>
   <url>https://repository.aspose.com/repo/</url>
  </repository>

Maven项目pom文件依赖

<!-- https://mvnrepository.com/artifact/org.apache.pdfbox/pdfbox -->
		<dependency>
			<groupId>org.apache.pdfbox</groupId>
			<artifactId>pdfbox</artifactId>
			<version>3.0.0-RC1</version>
		</dependency>
		<dependency>
			<groupId>com.github.jai-imageio</groupId>
			<artifactId>jai-imageio-jpeg2000</artifactId>
			<version>1.3.0</version>
		</dependency>
		<dependency>
			<groupId>com.aspose</groupId>
			<artifactId>aspose-words</artifactId>
			<version>21.9</version>
			<type>pom</type>
		</dependency>

核心代码实现

import com.aspose.words.Document;
import com.aspose.words.SaveFormat;
import org.apache.pdfbox.Loader;
import org.apache.pdfbox.contentstream.operator.Operator;
import org.apache.pdfbox.cos.COSArray;
import org.apache.pdfbox.cos.COSDictionary;
import org.apache.pdfbox.cos.COSName;
import org.apache.pdfbox.cos.COSString;
import org.apache.pdfbox.pdfparser.PDFStreamParser;
import org.apache.pdfbox.pdfwriter.ContentStreamWriter;
import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.pdmodel.PDPage;
import org.apache.pdfbox.pdmodel.PDPageTree;
import org.apache.pdfbox.pdmodel.PDResources;
import org.apache.pdfbox.pdmodel.common.PDStream;

import java.io.File;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.OutputStream;
import java.util.ArrayList;
import java.util.Iterator;
import java.util.List;

public class PDFHelper3 {

    public static void main(String[] args) throws IOException {

        doc2pdf(\"C:\\\\Users\\\\liuya\\\\Desktop\\\\word\\\\帆软报表帮助文档.docx\");

    }


    //替换pdf文本内容
    public static void replaceText(PDPage page, String searchString, String replacement) throws IOException {
        PDFStreamParser parser = new PDFStreamParser(page);
        List<?> tokens = parser.parse();
        for (int j = 0; j < tokens.size(); j++) {
            Object next = tokens.get(j);
            if (next instanceof Operator) {
                Operator op = (Operator) next;
                String pstring = \"\";
                int prej = 0;
                if (op.getName().equals(\"Tj\")) {
                    COSString previous = (COSString) tokens.get(j - 1);
                    String string = previous.getString();
                    string = string.replaceFirst(searchString, replacement);
                    previous.setValue(string.getBytes());
                } else if (op.getName().equals(\"TJ\")) {
                    COSArray previous = (COSArray) tokens.get(j - 1);
                    for (int k = 0; k < previous.size(); k++) {
                        Object arrElement = previous.getObject(k);
                        if (arrElement instanceof COSString) {
                            COSString cosString = (COSString) arrElement;
                            String string = cosString.getString();

                            if (j == prej) {
                                pstring += string;
                            } else {
                                prej = j;
                                pstring = string;
                            }
                        }
                    }
                    if (searchString.equals(pstring.trim())) {
                        COSString cosString2 = (COSString) previous.getObject(0);
                        cosString2.setValue(replacement.getBytes());
                        int total = previous.size() - 1;
                        for (int k = total; k > 0; k--) {
                            previous.remove(k);
                        }
                    }
                }
            }
        }
        List<PDStream> contents = new ArrayList<>();
        Iterator<PDStream> streams = page.getContentStreams();
        while (streams.hasNext()) {
            PDStream updatedStream = streams.next();
            OutputStream out = updatedStream.createOutputStream(COSName.FLATE_DECODE);
            ContentStreamWriter tokenWriter = new ContentStreamWriter(out);
            tokenWriter.writeTokens(tokens);
            contents.add(updatedStream);
            out.close();
        }
        page.setContents(contents);
    }

    //移除图片水印
    public static void removeImage(PDPage page, String cosName) {
        PDResources resources = page.getResources();
        COSDictionary dict1 = resources.getCOSObject();
        resources.getXObjectNames().forEach(e -> {
            if (resources.isImageXObject(e)) {
                COSDictionary dict2 = dict1.getCOSDictionary(COSName.XOBJECT);
                if (e.getName().equals(cosName)) {
                    dict2.removeItem(e);
                }
            }
            page.setResources(new PDResources(dict1));
        });
    }


    //移除文字水印
    public static boolean removeWatermark(File file) {
        try {
            //通过文件名加载文档
            PDDocument document = Loader.loadPDF(file);
            PDPageTree pages = document.getPages();
            Iterator<PDPage> iter = pages.iterator();
            while (iter.hasNext()) {
                PDPage page = iter.next();
                //去除文字水印
                replaceText(page, \"Evaluation Only. Created with Aspose.Words. Copyright 2003-2021 Aspose\", \"\");
                replaceText(page, \"Pty Ltd.\", \"\");
                replaceText(page, \"Created with an evaluation copy of Aspose.Words. To discover the full\", \"\");
                replaceText(page, \"versions of our APIs please visit: https://products.aspose.com/words/\", \"\");
                replaceText(page, \"This document was truncated here because it was created in the Evaluation\", \"\");
                //去除图片水印
                removeImage(page, \"X1\");
            }
            document.removePage(document.getNumberOfPages() - 1);
            file.delete();
            document.save(file);
            document.close();
            return true;
        } catch (IOException ex) {
            ex.printStackTrace();
            return false;
        }

    }


    //doc文件转pdf(目前最大支持21页)
    public static void doc2pdf(String wordPath) {
        long old = System.currentTimeMillis();
        try {
            //新建一个pdf文档
            String pdfPath=wordPath.substring(0,wordPath.lastIndexOf(\".\"))+\".pdf\";
            File file = new File(pdfPath);
            FileOutputStream os = new FileOutputStream(file);
            //Address是将要被转化的word文档
            Document doc = new Document(wordPath);
            //全面支持DOC, DOCX, OOXML, RTF HTML, OpenDocument, PDF, EPUB, XPS, SWF 相互转换
            doc.save(os, SaveFormat.PDF);
            os.close();
            //去除水印
            removeWatermark(new File(pdfPath));
            //转化用时
            long now = System.currentTimeMillis();
            System.out.println(\"Word 转 Pdf 共耗时：\" + ((now - old) / 1000.0) + \"秒\");
        } catch (Exception e) {
            System.out.println(\"Word 转 Pdf 失败...\");
            e.printStackTrace();
        }
    }


}

结果分析

以一个带文字和图片，工21页的doc文件为例，word转pdf花费时长4.398秒

原word样式

转化后pdf效果图

通过对比，word原来的样式和转换pdf文件后的样式基本没有变化。