用java从odt文件中读取XForm

Question

我正在尝试从odt文件（用LibreOffice创建）读取数据。需求是获取绑定到文档中包含的XForm的xml。我目前正在使用odfdom-java库读取该文件。到目前为止，我已经设法通过使用jdom解析文档来读取表单字段的值，但我实际想要的是使用表单数据获得整个xml。或者，我可以将文件加载为

ODFTextDocument.LoadDocument（“c：//myfile.odt”）；。

    PDDocument pdDoc = PDDocument.loadNonSeq( new File("C://myFile.odt"), null);
    PDDocumentCatalog pdCatalog = pdDoc.getDocumentCatalog();
    PDAcroForm pdAcroForm = pdCatalog.getAcroForm();

Answer 1

我通过jdom（odfdom-java）设法做到了这一点。绑定的xml本身就存在于表示ODT的xml中。您所需要的只是知道表单的id或标记的名称，以便获得适当的节点。然后，构造一个字符串，其中包含带表单数据的xml。我的代码如下：

import org.apache.xerces.dom.DeepNodeListImpl;
import org.apache.xml.serialize.OutputFormat;
import org.apache.xml.serialize.XMLSerializer;
import org.w3c.dom.Document;
import org.w3c.dom.Node;
import org.w3c.dom.NodeList;

import javax.xml.parsers.DocumentBuilder;
import javax.xml.parsers.DocumentBuilderFactory;
import java.io.IOException;
import java.util.Enumeration;
import java.util.zip.ZipEntry;
import java.util.zip.ZipFile;

public class TestXFormData {

    private static StringBuilder nodeContent;

    public static void main(String[] args) throws Exception {
        //Unzip the openOffice Document
        ZipFile zipFile = new ZipFile("C://myFile.odt");
        Enumeration entries = zipFile.entries();
        ZipEntry entry;

        while(entries.hasMoreElements()) {
            entry = (ZipEntry) entries.nextElement();
            if (entry.getName().equals("content.xml")) {
                // construct document
                DocumentBuilderFactory domFactory = DocumentBuilderFactory.newInstance();
                domFactory.setNamespaceAware(true);
                DocumentBuilder docBuilder = domFactory.newDocumentBuilder();
                Document doc = docBuilder.parse(zipFile.getInputStream(entry));
                // print the document
                printDocument(doc);
                // get the node
                NodeList list = doc.getElementsByTagName("myTagName");
                Node node = ((DeepNodeListImpl) list).item(0);
                nodeContent = new StringBuilder();
                // print the xml with the form data
                prettyPrint(node);
                System.out.println(nodeContent.toString());
            }
        }
    }


    private static void prettyPrint(Node node) {
        if (node.getNodeType() == Node.TEXT_NODE) {
            nodeContent.append(node.getNodeValue());
        } else if (node.getNodeType() == Node.ELEMENT_NODE) {
            nodeContent.append("<" + node.getNodeName() + ">");
            NodeList kids = node.getChildNodes();
            for (int i = 0; i < kids.getLength(); i++) {
                prettyPrint(kids.item(i));
            }
            nodeContent.append("</" + node.getNodeName() + ">");
        }
    }


    private static void printDocument(Document doc) throws IOException {
         OutputFormat format = new OutputFormat(doc);
         format.setIndenting(true);
         XMLSerializer serializer = new XMLSerializer(System.out, format);
         serializer.serialize(doc);
    }
}