java - 如何使用 Apache POI 将 altChunk 元素添加到 XWPFDocument

import java.io.File; import java.io.FileOutputStream; import javax.xml.namespace.QName; import org.apache.poi.xwpf.usermodel.XWPFDocument; import org.apache.poi.xwpf.usermodel.XWPFParagraph; import org.apache.poi.xwpf.usermodel.XWPFRun; import org.apache.xmlbeans.impl.values.XmlComplexContentImpl; import org.openxmlformats.schemas.wordprocessingml.x2006.main.CTDocument1; import org.openxmlformats.schemas.wordprocessingml.x2006.main.impl.CTBodyImpl; public class AltChunkTest { public static void main(String[] args) throws Exception { XWPFDocument doc = new XWPFDocument(); doc.createParagraph().createRun().setText("AltChunk below:"); QName ALTCHUNK = new QName ( "http://schemas.openxmlformats.org/wordprocessingml/2006/main" , "altChunk" ) ; CTDocument1 ctDoc = doc.getDocument() ; CTBodyImpl ctBody = (CTBodyImpl) ctDoc. getBody(); XmlComplexContentImpl xcci = ( XmlComplexContentImpl ) ctBody.get_store().add_element_user(ALTCHUNK); // what's need to now add "<b>Hello World!</b>" FileOutputStream out = new FileOutputStream(new File("test.docx")); doc.write(out); } }

在Office Open XMLfor Word( *.docx) 中altChunk提供了一种使用 pureHTML来描述文档部分的方法。

关于的两个重要说明altChunk：

第一：它仅用于导入内容。如果您使用打开文档Word并保存它，新保存的文档将不包含替代格式内容部分，也不包含引用它的 altChunk 标记。Word 将所有导入的内容保存为默认Office Open XML元素。

第二：除了Word能够阅读的应用程序之外，大多数应用程序*.docx根本不会阅读altChunk内容。例如Libreoffice或OpenOffice Writer不会读取内容以及在打开文件时不会读取内容。altChunkapache poialtChunk*.docx

文件结构中是如何altChunk实现的？*.docx ZIP

/word/*.html文件中有文件*.docx ZIP。/word/document.xml例如，这些由 Id 引用<w:altChunk r:id="htmlDoc1"/>。/word/*.htmlId 和文件之间的关系/word/_rels/document.xml.rels如<Relationship Id="htmlDoc1" Target="htmlDoc1.html" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/aFChunk"/>示例所示。

所以我们首先需要POIXMLDocumentParts 来表示/word/*.html文件，POIXMLRelations 来表示 Id 和文件之间的关系/word/*.html。以下代码提供了一个包装类，该类为 /word/htmlDoc#.html*.docx ZIP 存档中的文件扩展 POIXMLDocumentPart。这也提供了处理 HTML 的方法。它还提供了一种/word/htmlDoc#.html在 *.docx ZIP 存档中创建文件并与之建立关系的方法。

代码：

import java.io.*;

import org.apache.poi.*;
import org.apache.poi.ooxml.*;
import org.apache.poi.openxml4j.opc.*;

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

public class CreateWordWithHTMLaltChunk {

 //a method for creating the htmlDoc /word/htmlDoc#.html in the *.docx ZIP archive  
 //String id will be htmlDoc#.
 private static MyXWPFHtmlDocument createHtmlDoc(XWPFDocument document, String id) throws Exception {
  OPCPackage oPCPackage = document.getPackage();
  PackagePartName partName = PackagingURIHelper.createPartName("/word/" + id + ".html");
  PackagePart part = oPCPackage.createPart(partName, "text/html");
  MyXWPFHtmlDocument myXWPFHtmlDocument = new MyXWPFHtmlDocument(part, id);
  document.addRelation(myXWPFHtmlDocument.getId(), new XWPFHtmlRelation(), myXWPFHtmlDocument);
  return myXWPFHtmlDocument;
 }

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

  XWPFDocument document = new XWPFDocument();
  
  XWPFParagraph paragraph;
  XWPFRun run;
  MyXWPFHtmlDocument myXWPFHtmlDocument;

  paragraph = document.createParagraph();
  run = paragraph.createRun();
  run.setText("Default paragraph followed by first HTML chunk.");

  myXWPFHtmlDocument = createHtmlDoc(document, "htmlDoc1");
  myXWPFHtmlDocument.setHtml(myXWPFHtmlDocument.getHtml().replace("<body></body>",
   "<body><p>Simple <b>HTML</b> <i>formatted</i> <u>text</u></p></body>"));
  document.getDocument().getBody().addNewAltChunk().setId(myXWPFHtmlDocument.getId());  

  paragraph = document.createParagraph();
  run = paragraph.createRun();
  run.setText("Default paragraph followed by second HTML chunk.");

  myXWPFHtmlDocument = createHtmlDoc(document, "htmlDoc2");
  myXWPFHtmlDocument.setHtml(myXWPFHtmlDocument.getHtml().replace("<body></body>",
   "<body>" +
   "<table>"+
   "<caption>A table></caption>" +
   "<tr><th>Name</th><th>Date</th><th>Amount</th></tr>" +
   "<tr><td>John Doe</td><td>2018-12-01</td><td>1,234.56</td></tr>" +
   "</table>" +
   "</body>"
   ));
  document.getDocument().getBody().addNewAltChunk().setId(myXWPFHtmlDocument.getId());  

  FileOutputStream out = new FileOutputStream("CreateWordWithHTMLaltChunk.docx");
  document.write(out);
  out.close();
  document.close();

 }

 //a wrapper class for the  htmlDoc /word/htmlDoc#.html in the *.docx ZIP archive
 //provides methods for manipulating the HTML
 //TODO: We should *not* using String methods for manipulating HTML!
 private static class MyXWPFHtmlDocument extends POIXMLDocumentPart {

  private String html;
  private String id;

  private MyXWPFHtmlDocument(PackagePart part, String id) throws Exception {
   super(part);
   this.html = "<!DOCTYPE html><html><head><meta http-equiv=\"content-type\" content=\"text/html; charset=utf-8\"><style></style><title>HTML import</title></head><body></body>";
   this.id = id;
  }

  private String getId() {
   return id;
  }

  private String getHtml() {
   return html;
  }

  private void setHtml(String html) {
   this.html = html;
  }

  @Override
  protected void commit() throws IOException {
   PackagePart part = getPackagePart();
   OutputStream out = part.getOutputStream();
   Writer writer = new OutputStreamWriter(out, "UTF-8");
   writer.write(html);
   writer.close();
   out.close();
  }

 }

 //the XWPFRelation for /word/htmlDoc#.html
 private final static class XWPFHtmlRelation extends POIXMLRelation {
  private XWPFHtmlRelation() {
   super(
    "text/html", 
    "http://schemas.openxmlformats.org/officeDocument/2006/relationships/aFChunk", 
    "/word/htmlDoc#.html");
  }
 }
}

注意：由于使用altChunk此代码需要apache poi faq-N10025ooxml-schemas-*.jar中提到的所有模式的完整 jar 。

结果：

java - 如何使用 Apache POI 将 altChunk 元素添加到 XWPFDocument

问题描述

解决方案

推荐阅读