java 若依框架合并两个word内容

向右看齐 2024-03-16 11:06 50阅读 0赞

package com.ruoyi.survey.test;
    
    import org.apache.poi.openxml4j.opc.OPCPackage;
    import org.apache.poi.openxml4j.util.ZipSecureFile;
    import org.apache.poi.xwpf.usermodel.Document;
    import org.apache.poi.xwpf.usermodel.XWPFDocument;
    import org.apache.poi.xwpf.usermodel.XWPFPictureData;
    import org.apache.xmlbeans.XmlOptions;
    import org.openxmlformats.schemas.wordprocessingml.x2006.main.CTBody;
    
    import java.io.File;
    import java.io.FileInputStream;
    import java.io.FileOutputStream;
    import java.io.OutputStream;
    import java.util.*;
    
    
    public class DocxMerge {
        public static void main(String[] args) {
    //查询出文件夹下所有的需要合并的文件
    //        String basePath="D:\\data\\.work\\0530\\申报书文件";
    //        String[] list=new File(basePath).list();
    //        for (String s:list){
    //            String a=s.substring(0,s.indexOf(".")-1);
    //            String b=s.substring(0,s.indexOf(".")-8);
                System.out.println(a);
    //            System.out.println(b);
    //            File file1 = new File("D:\\data\\.work\\0530\\合并后\\"+b+".docx");
    //        List<File> targetFile1 = new ArrayList<>();
    //        targetFile1.add(new File("D:\\data\\.work\\0530\\申报书文件\\"+a+"4.docx"));
    //        targetFile1.add(new File("D:\\data\\.work\\0530\\申报书文件\\"+a+"5.docx"));
    //
    //        appendDocx(file1, targetFile1);
    //
    //        }
    //        System.out.println("合并成功！！！");
    
    //合并一个
            File file1 = new File("D:\\data\\.work\\0530\\合并后\\3.docx");
            List<File> targetFile1 = new ArrayList<>();
            targetFile1.add(new File("D:\\data\\.work\\0530\\申报书文件\\SQ2022YFC3800142_xm_sqs_zw_part2_4.docx"));
            targetFile1.add(new File("D:\\data\\.work\\0530\\申报书文件\\SQ2022YFC3800142_xm_sqs_zw_part2_5.docx"));
    
            appendDocx(file1, targetFile1);
            System.out.println("合并成功！！！\n");
    
    
        }
    
        /**
         * 把多个docx文件合并成一个
    
         * @param outfile    输出文件
         * @param targetFile 目标文件
         */
        public static void appendDocx(File outfile, List<File> targetFile) {
            try {
    
                OutputStream dest = new FileOutputStream(outfile);
                ArrayList<XWPFDocument> documentList = new ArrayList<>();
                XWPFDocument doc = null;
                for (int i = 0; i < targetFile.size(); i++) {
                    ZipSecureFile.setMinInflateRatio(-1.0d);
                    FileInputStream in = new FileInputStream(targetFile.get(i).getPath());
                    OPCPackage open = OPCPackage.open(in);
                    XWPFDocument document = new XWPFDocument(open);
                    documentList.add(document);
                }
                for (int i = 0; i < documentList.size(); i++) {
                    doc = documentList.get(0);
                    if (i != 0) {
                        //解决word合并完后，所有表格都紧紧挨在一起，没有分页。加上了分页符可解决
                        documentList.get(i).createParagraph().setPageBreak(true);
                        appendBody(doc, documentList.get(i));
                    }
                }
                doc.write(dest);
            } catch (Exception e) {
                e.printStackTrace();
            }
        }
    
        public static void appendBody(XWPFDocument src, XWPFDocument append) throws Exception {
            CTBody src1Body = src.getDocument().getBody();
            CTBody src2Body = append.getDocument().getBody();
    
            List<XWPFPictureData> allPictures = append.getAllPictures();
            // 记录图片合并前及合并后的ID
            Map<String, String> map = new HashMap<>();
            for (XWPFPictureData picture : allPictures) {
                String before = append.getRelationId(picture);
                //将原文档中的图片加入到目标文档中
                String after = src.addPictureData(picture.getData(), Document.PICTURE_TYPE_PNG);
                map.put(before, after);
            }
            //这个代码主要解决合并word报错，解析抛出压缩炸弹
            ZipSecureFile.setMinInflateRatio(-1.0d);
            appendBody(src1Body, src2Body, map);
    
        }
    
        private static void appendBody(CTBody src, CTBody append, Map<String, String> map) throws Exception {
            XmlOptions optionsOuter = new XmlOptions();
            optionsOuter.setSaveOuter();
            String appendString = append.xmlText(optionsOuter);
    
            String srcString = src.xmlText();
            String prefix = srcString.substring(0, srcString.indexOf(">") + 1);
            String mainPart = srcString.substring(srcString.indexOf(">") + 1, srcString.lastIndexOf("<"));
            String sufix = srcString.substring(srcString.lastIndexOf("<"));
            String addPart = appendString.substring(appendString.indexOf(">") + 1, appendString.lastIndexOf("<"));
            //下面这部分可以去掉，我加上的原因是合并的时候，有时候出现打不开的情况，对照document.xml将某些标签去掉就可以正常打开了
            addPart = addPart.replaceAll("w14:paraId=\"[A-Za-z0-9]{1,10}\"", "");
            addPart = addPart.replaceAll("w14:textId=\"[A-Za-z0-9]{1,10}\"", "");
            addPart = addPart.replaceAll("w:rsidP=\"[A-Za-z0-9]{1,10}\"", "");
            addPart = addPart.replaceAll("w:rsidRPr=\"[A-Za-z0-9]{1,10}\"", "");
            addPart = addPart.replace("<w:headerReference r:id=\"rId8\" w:type=\"default\"/>","");
            addPart = addPart.replace("<w:footerReference r:id=\"rId9\" w:type=\"default\"/>","");
            addPart = addPart.replace("xsi:nil=\"true\"","");
    
            if (map != null && !map.isEmpty()) {
                //对xml字符串中图片ID进行替换
                for (Map.Entry<String, String> set : map.entrySet()) {
                    addPart = addPart.replace(set.getKey(), set.getValue());
                }
            }
            //将两个文档的xml内容进行拼接
            CTBody makeBody = CTBody.Factory.parse(prefix + mainPart + addPart + sufix);
    
            src.set(makeBody);
        }
    
    
    }