说明

根据业务要求需要将多个pdf合并成一个大的pdf，并且合并后的pdf还需要根据每个小pdf的标题生成目录。 本来使用的是iTextpdf5版本，这个版本不支持书签，所以引入新的依赖，使用pdfbox依赖写一个工具类合并pdf。

依赖

xml
    <dependency>
      <groupId>org.apache.pdfbox</groupId>
      <artifactId>pdfbox</artifactId>
      <version>2.0.30</version>
    </dependency>

工具类

java


package com.lhw.management.utils;

import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.pdmodel.PDPage;
import org.apache.pdfbox.pdmodel.interactive.documentnavigation.destination.PDPageXYZDestination;
import org.apache.pdfbox.pdmodel.interactive.documentnavigation.outline.PDDocumentOutline;
import org.apache.pdfbox.pdmodel.interactive.documentnavigation.outline.PDOutlineItem;

import java.io.ByteArrayInputStream;
import java.io.ByteArrayOutputStream;
import java.io.IOException;
import java.util.List;

public class PdfBoxUtils {

   
    /**
     * 
     * @Description:  合并pdf生成目录
     * @Param: @param null
     * @author lihaowei
     * @since: 2024/5/21 13:46
     * @return 
     */
        public static byte[] MergeByteArrayAddBookMark(List<ByteArrayOutputStream> byteArrayOutputStreamList, List<String> bookMarkNames) throws IOException {
        PDDocument mergedDocument = new PDDocument();
        PDDocumentOutline outline = null;
        int num=0;
        for (int i = 0; i < byteArrayOutputStreamList.size(); i++) {
            ByteArrayInputStream inputStream = new ByteArrayInputStream(byteArrayOutputStreamList.get(i).toByteArray());
            PDDocument document = PDDocument.load(inputStream);

            for (PDPage page : document.getPages()) {
                mergedDocument.addPage(page);
            }

            if (i == 0) {
                outline = mergedDocument.getDocumentCatalog().getDocumentOutline();
                if (outline == null) {
                    outline = new PDDocumentOutline();
                    mergedDocument.getDocumentCatalog().setDocumentOutline(outline);
                }
            }
            PDOutlineItem item = new PDOutlineItem();
            // 设置目标页面索引和目标位置坐标
            PDPageXYZDestination destination = new PDPageXYZDestination();
            destination.setPage(mergedDocument.getPage(num)); // 设置目标页面索引
            destination.setLeft(0); // 设置目标位置坐标（这里设置为页面左上角）
            destination.setTop(0);
            item.setDestination(destination);
            item.setTitle(bookMarkNames.get(i));
            outline.addLast(item);

            //计算索引页数
            num=num+document.getNumberOfPages();
            // 将 document.close(); 移到循环外
        }

}

可能出现的问题

java.io.IOException: Buffer already closed

优化

java

public static byte[] MergeByteArrayAddBookMark(List<ByteArrayOutputStream> byteArrayOutputStreamList, List<String> bookMarkNames) throws IOException {
        PDDocument mergedDocument = new PDDocument();
        PDDocumentOutline outline = null;
        int num=0;
        List<PDDocument> docList = new ArrayList<>();
        for (int i = 0; i < byteArrayOutputStreamList.size(); i++) {
            ByteArrayInputStream inputStream = new ByteArrayInputStream(byteArrayOutputStreamList.get(i).toByteArray());
            PDDocument document= PDDocument.load(inputStream);
            docList.add(document);
            for (PDPage page : document.getPages()) {
                mergedDocument.addPage(page);
            }

            if (i == 0) {
                outline = mergedDocument.getDocumentCatalog().getDocumentOutline();
                if (outline == null) {
                    outline = new PDDocumentOutline();
                    mergedDocument.getDocumentCatalog().setDocumentOutline(outline);
                }
            }
            PDOutlineItem item = new PDOutlineItem();
            // 设置目标页面索引和目标位置坐标
            PDPageXYZDestination destination = new PDPageXYZDestination();
            destination.setPage(mergedDocument.getPage(num)); // 设置目标页面索引
            destination.setLeft(0); // 设置目标位置坐标（这里设置为页面左上角）
            destination.setTop(0);
            item.setDestination(destination);
            item.setTitle(bookMarkNames.get(i));
            outline.addLast(item);

            //计算索引页数
            num=num+document.getNumberOfPages();
        }
        ByteArrayOutputStream outputStream = new ByteArrayOutputStream();
        mergedDocument.save(outputStream);
        for (PDDocument d:docList) {
            d.close();
        }
        mergedDocument.close();

        return outputStream.toByteArray();
    }