我想补充的HTML作为altChunk采用Apache POI的DOCX文件。 我知道,doc4jx可以用一个简单的API做到这一点,但由于技术上的原因,我需要使用Apache POI。
使用CT类做低层次的东西与XML是有点棘手。 我可以创建下面的代码的altChunk:
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);
}
}
但我怎么添加HTML内容为“xcci”现在?
在Office Open XML
为Word
( *.docx
)的altChunk
提供了使用纯的方法HTML
描述的文档部分。
约两个重要的备注altChunk
:
首先:它仅用于导入内容。 如果您在使用打开文档Word
和保存,新保存的文件将不包含另一种格式内容的一部分,也不是altChunk标记引用它。 Word保存所有导入的内容为默认Office Open XML
元素。
第二:除了大多数应用程序Word
,其能够读取*.docx
不会太阅读altChunk
含量可言。 例如Libreoffice
或OpenOffice
Writer
不会读altChunk
内容以及apache poi
不会读altChunk
打开时内容*.docx
文件。
如何altChunk
在实施*.docx
ZIP
文件结构?
有/word/*.html
中的文件*.docx
ZIP
文件。 那些被标识在所引用/word/document.xml
如<w:altChunk r:id="htmlDoc1"/>
例如。 的ID和之间的关系/word/*.html
文件中给出/word/_rels/document.xml.rels
如<Relationship Id="htmlDoc1" Target="htmlDoc1.html" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/aFChunk"/>
的例子。
因此,我们需要在第一POIXMLDocumentPart
S为/word/*.html
文件和POIXMLRelation
S为ID和之间的关系/word/*.html
文件。 下面的代码提供,通过使用具有沿POIXMLDocumentPart的包装类/word/htmlDoc#.html
在* .DOCX ZIP压缩文件。 这也提供了操纵HTML方法。 此外,它提供了创建一个方法/word/htmlDoc#.html
在* .DOCX ZIP档案文件,并创建关系到它。
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><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:由于使用的altChunk
此代码需要的所有模式的全罐子ooxml-schemas-*.jar
在提到的Apache POI FAQ-N10025 。
结果:
基于阿克塞尔里希特的回答 ,我更换了调用CTBody.addNewAltChunk()与CTBodyImpl.get_store()。add_element_user(QName的),它消除了加15MB依赖OOXML-模式 。 因为这是一个桌面应用程序中使用,我们正在努力,以保持应用程序的大小尽可能小。 在情况下,它可能是帮助别人:
import java.io.File;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.OutputStream;
import java.io.OutputStreamWriter;
import java.io.Writer;
import javax.xml.namespace.QName;
import org.apache.poi.ooxml.POIXMLDocumentPart;
import org.apache.poi.ooxml.POIXMLRelation;
import org.apache.poi.openxml4j.opc.OPCPackage;
import org.apache.poi.openxml4j.opc.PackagePart;
import org.apache.poi.openxml4j.opc.PackagePartName;
import org.apache.poi.openxml4j.opc.PackagingURIHelper;
import org.apache.poi.xwpf.usermodel.XWPFDocument;
import org.apache.xmlbeans.SimpleValue;
import org.apache.xmlbeans.impl.values.XmlComplexContentImpl;
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:");
addHtml(doc,"chunk1","<!DOCTYPE html><html><head><style></style><title></title></head><body><b>Hello World!</b></body></html>");
FileOutputStream out = new FileOutputStream(new File("test.docx"));
doc.write(out);
}
static void addHtml(XWPFDocument doc, String id,String html) throws Exception {
OPCPackage oPCPackage = doc.getPackage();
PackagePartName partName = PackagingURIHelper.createPartName("/word/" + id + ".html");
PackagePart part = oPCPackage.createPart(partName, "text/html");
class HtmlRelation extends POIXMLRelation {
private HtmlRelation() {
super( "text/html",
"http://schemas.openxmlformats.org/officeDocument/2006/relationships/aFChunk",
"/word/htmlDoc#.html");
}
}
class HtmlDocumentPart extends POIXMLDocumentPart {
private HtmlDocumentPart(PackagePart part) throws Exception {
super(part);
}
@Override
protected void commit() throws IOException {
try (OutputStream out = part.getOutputStream()) {
try (Writer writer = new OutputStreamWriter(out, "UTF-8")) {
writer.write(html);
}
}
}
};
HtmlDocumentPart documentPart = new HtmlDocumentPart(part);
doc.addRelation(id, new HtmlRelation(), documentPart);
CTBodyImpl b = (CTBodyImpl) doc.getDocument().getBody();
QName ALTCHUNK = new QName("http://schemas.openxmlformats.org/wordprocessingml/2006/main", "altChunk");
XmlComplexContentImpl altchunk = (XmlComplexContentImpl) b.get_store().add_element_user(ALTCHUNK);
QName ID = new QName("http://schemas.openxmlformats.org/officeDocument/2006/relationships", "id");
SimpleValue target = (SimpleValue)altchunk.get_store().add_attribute_user(ID);
target.setStringValue(id);
}
}