poi合并多个word成一个新word,原word中横版没了.

Question

用apache poi合并多个word并生成一个新word,现在遇到个问题,原word中有竖版有横版,怎么在合并时按原始word的排版保留原样式.

/**
     * 多个word合并，按照文件顺序合并为一个word
     *
     * @param mergeFileName 指定合并后的目标文件名
     * @param fileNames     指定所有需要合并的word文件名
     */
    public static void mergeMultiWord(String mergeFileName, List<String> fileNames) {
        try {
            OutputStream dest = new FileOutputStream(mergeFileName);
            ArrayList<XWPFDocument> documentList = new ArrayList<>();
            XWPFDocument mergeDoc = null;
            for (int i = 0; i < fileNames.size(); i++) {
                FileInputStream in = new FileInputStream(fileNames.get(i));
                OPCPackage open = OPCPackage.open(in);
                XWPFDocument document = new XWPFDocument(open);
                documentList.add(document);
            }
            for (int i = 0; i < documentList.size(); i++) {
                mergeDoc = documentList.get(0);
                XWPFDocument document = documentList.get(i);

                if (i != documentList.size() - 1) {
                    // 最后一页不再设置分页符
                    document.createParagraph().setPageBreak(true);
                }

                if (i != 0) {
                    appendBody(mergeDoc, document);
                }
            }
            mergeDoc.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();
        Map<String, String> map = new HashMap<>();
        for (XWPFPictureData picture : allPictures) {
            String before = append.getRelationId(picture);
            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()) {
            for (Map.Entry<String, String> set : map.entrySet()) {
                addPart = addPart.replace(set.getKey(), set.getValue());
            }
        }
        CTBody makeBody = CTBody.Factory.parse(prefix + mainPart + addPart + sufix);
        src.set(makeBody);
    }

以上是我现在的代码

Answer 1

引自免费微信小程序：皆我百晓生

为了确保合并后的Word文档能保留原文档的排版样式，你需要使用Apache POI中的XWPFDocument类进行操作。下面是一个详细的步骤和示例代码，展示了如何合并多个Word文档，并保持原有的排版风格。

首先，确保你已经添加了Apache POI的依赖。如果你使用的是Maven，可以在pom.xml文件中添加以下依赖：

<dependencies>
    <dependency>
        <groupId>org.apache.poi</groupId>
        <artifactId>poi-ooxml</artifactId>
        <version>5.0.0</version>
    </dependency>
</dependencies>

接下来是合并Word文档的Java代码示例：

import org.apache.poi.xwpf.usermodel.*;

import java.io.*;
import java.util.ArrayList;
import java.util.List;

public class WordMerger {

    public static void main(String[] args) throws IOException {
        List<File> sourceDocuments = new ArrayList<>();
        // 添加要合并的Word文档路径到列表中
        sourceDocuments.add(new File("path_to_document1.docx"));
        sourceDocuments.add(new File("path_to_document2.docx"));

        mergeDocuments(sourceDocuments, "merged_document.docx");
    }

    private static void mergeDocuments(List<File> sourceDocuments, String outputFilePath) throws IOException {
        XWPFDocument destinationDoc = new XWPFDocument();

        for (File sourceFile : sourceDocuments) {
            XWPFDocument sourceDoc = new XWPFDocument(new FileInputStream(sourceFile));

            int i = 0;
            for (IBodyElement bodyElement : sourceDoc.getBodyElements()) {
                if (i > 0) {
                    // 如果不是第一个文档，插入一个分页符
                    destinationDoc.createParagraph().insertNewRun(0).addBreak(BreakType.PAGE);
                }
                copyBodyElement(bodyElement, destinationDoc);
                i++;
            }

            sourceDoc.close();
        }

        FileOutputStream out = new FileOutputStream(outputFilePath);
        destinationDoc.write(out);
        destinationDoc.close();
        out.close();
    }

    private static void copyBodyElement(IBodyElement element, XWPFDocument destinationDoc) {
        switch (element.getElementType()) {
            case PARAGRAPH:
                XWPFParagraph destPara = destinationDoc.createParagraph();
                destPara.setParagraphStyle(element.getParagraphStyle());
                for (IRunElement runElement : ((XWPFParagraph) element).getRuns()) {
                    IRunElement destRun = destPara.createRun();
                    destRun.setText(runElement.getText(0));
                    destRun.setBold(runElement.isBold());
                    destRun.setFontFamily(runElement.getFontFamily());
                    destRun.setFontSize(runElement.getFontSize());
                    // 处理其他格式属性...
                }
                break;
            case TABLE:
                XWPFTable destTable = destinationDoc.createTable(((XWPFTable) element).getNumRows(), ((XWPFTable) element).getNumColumns());
                for (int row = 0; row < ((XWPFTable) element).getNumRows(); row++) {
                    XWPFTableRow destRow = destTable.getRow(row);
                    for (int cell = 0; cell < ((XWPFTable) element).getRow(row).getCellCount(); cell++) {
                        XWPFTableCell destCell = destRow.getCell(cell);
                        for (IRunElement runElement : ((XWPFTableCell) element.getRow(row).getCell(cell)).getParagraphs().get(0).getRuns()) {
                            IRunElement destRun = destCell.getParagraphs().get(0).createRun();
                            destRun.setText(runElement.getText(0));
                            destRun.setBold(runElement.isBold());
                            destRun.setFontFamily(runElement.getFontFamily());
                            destRun.setFontSize(runElement.getFontSize());
                            // 处理其他格式属性...
                        }
                    }
                }
                break;
            // 处理其他元素类型...
            default:
                break;
        }
    }
}

这段代码首先读取每个源Word文档，然后逐个处理文档中的段落、表格等元素，并将它们复制到目标文档中。注意，这里只处理了段落和表格，你可能需要根据实际需求扩展其他元素类型的处理（例如图片、列表等）。

运行这个程序后，它会创建一个新的Word文档，其中包含了所有源文档的内容，并尽可能地保留了原始的排版样式。如果你发现某些样式没有正确保留，可以检查代码中的样式设置部分，看看是否有遗漏的属性。