基于java处理.docx格式的word合并

Posted 2021-03-17 牧野流冰87

如下实例是将 2.docx和3.docx合并，写到empty.docx中，不适用于.doc格式，

public static void main(String[] args) {
    File file1 = new File("D:\empty.docx");
    List<File> targetFile1 = new ArrayList<>();
    targetFile1.add(new File("D:\2.docx"));
    targetFile1.add(new File("D:\3.docx"));
    appendDocx(file1, targetFile1);
}

/**
 * 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++) {
            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) {
               /* if (i != documentList.size() - 1) {
                    documentList.get(i).createParagraph().setPageBreak(true);
                }*/

                appendBody(doc, documentList.get(i));
            }
        }
        //doc.createParagraph().setPageBreak(true);
        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);
    }

    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);
}