word文档操作-doc转docx、合并多个docx

前言：

临时来了一条新的需求：多个doc文档进行合并。

在网上苦苦搜罗了很久才找到可用的文件（原文出处到不到了 所以暂时不能加链接地址了），现在记录下留给有需要的人。

一：doc转docx

所需jar包：链接: https://pan.baidu.com/s/1WQ33HDsON8lpFQKgLu8pCQ 提取码: n1xt

具体代码

public class Doc2Docx {
    public static void main(String[] args) {
        String docFile = "D:/files/dfa3cbb9-a0a0-497a-aa9f-d26cbee9a25b_linux.doc";
        String docxFile = "D:/print/linux.docx";
        doc2docx(docFile, docxFile);
    }

    /**
     * doc转docx
     * @param docFile     源文件
     * @param docxFile    目标文件
     */
    public static void doc2docx(String docFile, String docxFile) {
        Document doc;
        try {
            String tempFile = docxFile.substring(0, docxFile.lastIndexOf(".")) + "_temp"
                    + docxFile.substring(docxFile.lastIndexOf("."), docxFile.length());
            doc = new Document(docFile);
            doc.save(tempFile);
            Map<String, String> map = new HashMap<String, String>();
            map.put("Evaluation Only. Created with Aspose.Words. Copyright 2003-2018 Aspose Pty Ltd.", "");
            DocxReplace.replaceAndGenerateWord(tempFile, docxFile, map);
//            forceDelete(new File(tempFile));
        } catch (Exception e1) {
            log.error("doc 2 docx exception:{}",e1.getMessage());
        }

    }

}

public class DocxReplace {
    // 返回Docx中需要替换的特殊字符，没有重复项
    // 推荐传入正则表达式参数"\\$\\{[^{}]+\\}"
    public ArrayList<String> getReplaceElementsInWord(String filePath,
            String regex) {
        String[] p = filePath.split("\\.");
        if (p.length > 0) {// 判断文件有无扩展名
            // 比较文件扩展名
            if (p[p.length - 1].equalsIgnoreCase("doc")) {
                ArrayList<String> al = new ArrayList<>();
                File file = new File(filePath);
                HWPFDocument document = null;
                try {
                    InputStream is = new FileInputStream(file);
                    document = new HWPFDocument(is);
                } catch (FileNotFoundException e) {
                    e.printStackTrace();
                } catch (IOException e) {
                    e.printStackTrace();
                }
                Range range = document.getRange();
                String rangeText = range.text();
                CharSequence cs = rangeText.subSequence(0, rangeText.length());
                Pattern pattern = Pattern.compile(regex);
                Matcher matcher = pattern.matcher(cs);
                int startPosition = 0;
                while (matcher.find(startPosition)) {
                    if (!al.contains(matcher.group())) {
                        al.add(matcher.group());
                    }
                    startPosition = matcher.end();
                }
                return al;
            } else if (p[p.length - 1].equalsIgnoreCase("docx")) {
                ArrayList<String> al = new ArrayList<>();
                XWPFDocument document = null;
                try {
                    document = new XWPFDocument(
                            POIXMLDocument.openPackage(filePath));
                } catch (IOException e) {
                    e.printStackTrace();
                }
                // 遍历段落
                Iterator<XWPFParagraph> itPara = document
                        .getParagraphsIterator();
                while (itPara.hasNext()) {
                    XWPFParagraph paragraph = (XWPFParagraph) itPara.next();
                    String paragraphString = paragraph.getText();
                    CharSequence cs = paragraphString.subSequence(0,
                            paragraphString.length());
                    Pattern pattern = Pattern.compile(regex);
                    Matcher matcher = pattern.matcher(cs);
                    int startPosition = 0;
                    while (matcher.find(startPosition)) {
                        if (!al.contains(matcher.group())) {
                            al.add(matcher.group());
                        }
                        startPosition = matcher.end();
                    }
                }
                // 遍历表
                Iterator<XWPFTable> itTable = document.getTablesIterator();
                while (itTable.hasNext()) {
                    XWPFTable table = (XWPFTable) itTable.next();
                    int rcount = table.getNumberOfRows();
                    for (int i = 0; i < rcount; i++) {
                        XWPFTableRow row = table.getRow(i);
                        List<XWPFTableCell> cells = row.getTableCells();
                        for (XWPFTableCell cell : cells) {
                            String cellText = "";
                            cellText = cell.getText();
                            CharSequence cs = cellText.subSequence(0,
                                    cellText.length());
                            Pattern pattern = Pattern.compile(regex);
                            Matcher matcher = pattern.matcher(cs);
                            int startPosition = 0;
                            while (matcher.find(startPosition)) {
                                if (!al.contains(matcher.group())) {
                                    al.add(matcher.group());
                                }
                                startPosition = matcher.end();
                            }
                        }
                    }
                }
                return al;
            } else {
                return null;
            }
        } else {
            return null;
        }
    }  

    // 替换word中需要替换的特殊字符
    public static boolean replaceAndGenerateWord(String srcPath, String destPath, Map<String, String> map) {
        String[] sp = srcPath.split("\\.");
        String[] dp = destPath.split("\\.");
        if ((sp.length > 0) && (dp.length > 0)) {// 判断文件有无扩展名
            // 比较文件扩展名
            if (sp[sp.length - 1].equalsIgnoreCase("docx")) {
                try {
                    XWPFDocument document = new XWPFDocument(POIXMLDocument.openPackage(srcPath));
                    // 替换段落中的指定文字
                    Iterator<XWPFParagraph> itPara = document.getParagraphsIterator();
                    while (itPara.hasNext()) {
                        XWPFParagraph paragraph = (XWPFParagraph) itPara.next();
                        List<XWPFRun> runs = paragraph.getRuns();
                        for (int i = 0; i < runs.size(); i++) {
                            String oneparaString = runs.get(i).getText(runs.get(i).getTextPosition());
                            for (Entry<String, String> entry : map.entrySet()) {
                                if(oneparaString.indexOf(entry.getKey())!=-1){
                                    oneparaString = oneparaString.replace(entry.getKey(), entry.getValue());
                                    runs.get(i).setText(oneparaString, 0);
                                }
                            }
                        }
                    }
                    // 替换表格中的指定文字
                    Iterator<XWPFTable> itTable = document.getTablesIterator();
                    while (itTable.hasNext()) {
                        XWPFTable table = (XWPFTable) itTable.next();
                        int rcount = table.getNumberOfRows();
                        for (int i = 0; i < rcount; i++) {
                            XWPFTableRow row = table.getRow(i);
                            List<XWPFTableCell> cells = row.getTableCells();
                            for (XWPFTableCell cell : cells) {
                                String cellTextString = cell.getText();
                                for (Entry<String, String> e : map.entrySet()) {
                                    if (cellTextString.contains(e.getKey())) {
                                         cellTextString = cellTextString.replace(e.getKey(),e.getValue());
                                         cell.removeParagraph(0);
                                         cell.setText(cellTextString);
                                         cell.setColor(cell.getColor());
                                    }
                                }
                            }
                        }
                    }
                    FileOutputStream outStream = null;
                    outStream = new FileOutputStream(destPath);
                    document.write(outStream);
                    outStream.close();
                    return true;
                } catch (Exception e) {
                    e.printStackTrace();
                    return false;
                }
            } else
            // doc只能生成doc，如果生成docx会出错
            if ((sp[sp.length - 1].equalsIgnoreCase("doc"))
                    && (dp[dp.length - 1].equalsIgnoreCase("doc"))) {
                HWPFDocument document = null;
                try {
                    document = new HWPFDocument(new FileInputStream(srcPath));
                    Range range = document.getRange();
                    for (Entry<String, String> entry : map.entrySet()) {
                        range.replaceText(entry.getKey(), entry.getValue());
                    }
                    FileOutputStream outStream = null;
                    outStream = new FileOutputStream(destPath);
                    document.write(outStream);
                    outStream.close();
                    return true;
                } catch (FileNotFoundException e) {
                    e.printStackTrace();
                    return false;
                } catch (IOException e) {
                    e.printStackTrace();
                    return false;
                }
            } else {
                return false;
            }
        } else {
            return false;
        }
    }  

}

二：合并多个docx

public class WordMergeUtil {
    public static void main (String[] args) throws Exception {

        File newFile = new File("D:\\wdpj\\t.docx");
        List<File> srcfile = new ArrayList<>();
//        File file1 = new File("D:\\wdpj\\函.docx");
//        File file2 = new File("D:\\wdpj\\1.docx");
        File file1 = new File("D:\\wdpj\\2.docx");
        File file2 = new File("D:\\wdpj\\3.docx");
        File file3 = new File("D:\\wdpj\\函.docx");

//        srcfile.add(file2);
//        srcfile.add(file1);
        srcfile.add(file1);
        srcfile.add(file2);
        srcfile.add(file3);

        try {
            OutputStream dest = new FileOutputStream(newFile);
            ArrayList<XWPFDocument> documentList = new ArrayList<>();
            XWPFDocument doc = null;
            for (int i = 0; i < srcfile.size(); i++) {
                FileInputStream in = new FileInputStream(srcfile.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){
                    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 {
        XWPFParagraph p = src.createParagraph();
        //设置分页符
        p.setPageBreak(true);
        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("<"));
        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);

    }