word文档合并,书签丢失

问题描述：

当多个word文档进行合并的时候，每个文档都有书签的话，会出现书签丢失的问题？

原因：

通过对word转换成xml进行分析，发现多个文档中的 w:bookmarkStart <w:bookmarkStart w:id="0" w:name="bm__1613808247536"/><w:r><w:rPr><w:rFonts w:hint="eastAsia"/><w:b/><w:color w:val="FF0000"/></w:rPr><w:t>log文件</w:t></w:r><w:bookmarkEnd w:id="0"/> 书签标记中的 w:id的值 会出现重复。

解决思路：

找出每个文档中的书签，然后为每个书签标记w:id 设置唯一值即可解决。

实现代码：

package com.htdd.dmp.common.utils;

import com.google.common.collect.Lists;
import com.google.common.collect.Maps;
import com.htdd.common.utils.StringUtils;
import org.apache.poi.xwpf.usermodel.XWPFDocument;
import org.apache.xmlbeans.XmlException;
import org.apache.xmlbeans.XmlOptions;
import org.openxmlformats.schemas.wordprocessingml.x2006.main.CTBody;

import java.io.*;
import java.util.List;
import java.util.Map;
import java.util.concurrent.atomic.AtomicInteger;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

public class WordUtils {

    private static final Pattern pattern1 = Pattern.compile("<w:bookmarkStart w:id=\"\\d+\" w:name=\"\\w+\"/>");
    private static final Pattern pattern2 = Pattern.compile("w:id=\"\\d+\"");
    private static final int BOOKMARK_NUM = 100;// 每个word文档书签不能超过100


    public static void main(String[] args) throws Exception {
        List<String> list = Lists.newLinkedList();
        list.add("E:\\ts\\tt\\17.docx");
        list.add("E:\\ts\\tt\\18.docx");
        list.add("E:\\ts\\tt\\19.docx");
        list.add("E:\\ts\\tt\\20.docx");
        list.add("E:\\ts\\tt\\21.docx");
        list.add("E:\\ts\\tt\\22.docx");
        list.add("E:\\ts\\tt\\23.docx");
        String p = "E:\\ts\\tt\\ts.docx";
        merge(list,p);

    }

    public static void merge(List<String> filePaths, String destPath) {
        if(filePaths==null||filePaths.isEmpty()|| StringUtils.isEmpty(destPath)) {
           System.out.println(">>>>>>filePaths和destPath都不能为空!!!");
            return;
        }
        StringBuilder sb = new StringBuilder();
        XmlOptions optionOuter = new XmlOptions();
        optionOuter.setSaveOuter();
        AtomicInteger ai = new AtomicInteger(100);
        try(InputStream is = new FileInputStream(filePaths.get(0));XWPFDocument xwpf = new XWPFDocument(is)) {
            CTBody firstBody = xwpf.getDocument().getBody();
            Map<String,String> map = getContentMap(firstBody);
            String header = map.get("head");
            sb.append(header);
            String docStr = map.get("body");
            sb.append(dealBookMark(docStr,ai));
            String tail = map.get("tail");
            CTBody body;
            for (int i = 1; i < filePaths.size(); i++) {
                String path = filePaths.get(i);
                try(InputStream is2 = new FileInputStream(path);XWPFDocument xwpf2 = new XWPFDocument(is2)) {
                    body = xwpf2.getDocument().getBody();
                    docStr = getBody(body,optionOuter);
                    ai.addAndGet(BOOKMARK_NUM*i);
                    sb.append(dealBookMark(docStr,ai));
                }
            }
            try (OutputStream dest = new FileOutputStream(destPath)) {
                CTBody makeBody = CTBody.Factory.parse(sb.append(tail).toString());
                firstBody.set(makeBody);
                xwpf.write(dest);
            }
        } catch (FileNotFoundException e) {
            e.printStackTrace();
        } catch (IOException | XmlException e) {
            e.printStackTrace();
        }
    }

    private static String getBody(CTBody src, XmlOptions optionsOuter) {
        String appendString = src.xmlText(optionsOuter);
        return appendString.substring(appendString.indexOf(">") + 1, appendString.lastIndexOf("<"));
    }

    private static Map<String, String> getContentMap(CTBody body){
        String srcString = body.xmlText();
        Map<String, String> map = Maps.newHashMap();
        String head = srcString.substring(0, srcString.indexOf(">") + 1);
        map.put("head", head);
        String mainPart = srcString.substring(srcString.indexOf(">") + 1, srcString.lastIndexOf("<"));
        map.put("body",mainPart);
        String tail = srcString.substring(srcString.lastIndexOf("<"));
        map.put("tail",tail);
        return map;
    }

    private static String dealBookMark(String docStr, AtomicInteger ai) {
        Matcher matcher = pattern1.matcher(docStr);
        Matcher m;
        while (matcher.find()) {
            String matchStr = matcher.group();
            m = pattern2.matcher(matchStr);
            if (m.find()) {
                String idStr = m.group();
                String idReplaceStr = "w:id=\"" + ai.getAndAdd(1) + "\"";
                docStr = docStr.replaceFirst(idStr,idReplaceStr).replaceFirst(idStr,idReplaceStr);
            }
        }
        return docStr;
    }
}