java - 连接两个 org.w3c.dom.Document

Question

我想连接两个 org.w3c.dom.Document ，我有这样的东西:

Document finalDocument = DocumentBuilderFactory.newInstance().newDocumentBuilder().newDocument()
Document document1 = createDocumentOne();
Document document2 = createDocumentTwo();

// This didn't work
changeFileDocument.appendChild(document1);
changeFileDocument.appendChild(document2);

document1和document2的格式是这样的:

<headerTag>
    <tag1>value</tag1>  
</headerTag>

最后我想要的是这样的文档:

<headerTag>
    <tag1>valueForDocument1</tag1>  
</headerTag>
<headerTag>
    <tag1>valueForDocument2</tag1>  
</headerTag>

我认为你不能这样做，因为他们应该有一个共同的 parent 。如果是这样，我想创建那个“假”父级，连接文件，但然后只恢复元素列表 headerTag

我该怎么做？

Answer 1

创建新文档、解析各个部分并将其节点添加到新文档中，您的方向是正确的。

您的方法失败了，因为您尝试将整个文档附加到另一个文档，这是不可能的。

你可以尝试这样的事情:

public org.w3c.dom.Document concatXmlDocuments(String rootElementName, InputStream... xmlInputStreams) throws ParserConfigurationException, SAXException, IOException {
    DocumentBuilder builder = DocumentBuilderFactory.newInstance().newDocumentBuilder();
    org.w3c.dom.Document result = builder.newDocument();
    org.w3c.dom.Element rootElement = result.createElement(rootElementName);
    result.appendChild(rootElement);
    for(InputStream is : xmlInputStreams) {
        org.w3c.dom.Document document = builder.parse(is);
        org.w3c.dom.Element root = document.getDocumentElement();
        NodeList childNodes = root.getChildNodes();
        for(int i = 0; i < childNodes.getLength(); i++) {
            Node importNode = result.importNode(childNodes.item(i), true);
            rootElement.appendChild(importNode);
        }
    }
    return result;
}

上面的代码复制在每个文档的根元素下找到的所有节点。当然，您可以选择仅选择性地复制您感兴趣的节点。生成的文档将反射(reflect)两个文档中的所有节点。

测试

@Test
public void concatXmlDocuments() throws ParserConfigurationException, SAXException, IOException, TransformerException {
    try (
            InputStream doc1 = new ByteArrayInputStream((
                "<headerTag>\r\n" + 
                "    <tag1>doc1 value</tag1>\r\n" + 
                "</headerTag>").getBytes(StandardCharsets.UTF_8));
            InputStream doc2 = new ByteArrayInputStream((
                "<headerTag>\r\n" + 
                "    <tag1>doc2 value</tag1>\r\n" + 
                "</headerTag>").getBytes(StandardCharsets.UTF_8));
            ByteArrayOutputStream docR = new ByteArrayOutputStream();

        ) {

        org.w3c.dom.Document result = concatXmlDocuments("headerTag", doc1, doc2);
        TransformerFactory trf = TransformerFactory.newInstance();
        Transformer tr = trf.newTransformer();
        tr.setOutputProperty(OutputKeys.INDENT, "yes");
        DOMSource source = new DOMSource(result);
        StreamResult sr = new StreamResult(docR);
        tr.transform(source, sr);
        System.out.print(new String(docR.toByteArray(), StandardCharsets.UTF_8));
    }
}

输出

<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<headerTag>
    <tag1>doc1 value</tag1>
    <tag1>doc2 value</tag1>
</headerTag>

编辑

I would like to create that "fake" parent, concatenate the files, but then only recover the List of elements headerTag

正如您所说，创建一个假父级。以下是您可以如何做到的:

1) 进行串联

public org.w3c.dom.Document concatXmlDocuments(InputStream... xmlInputStreams) throws ParserConfigurationException, SAXException, IOException {
    DocumentBuilder builder = DocumentBuilderFactory.newInstance().newDocumentBuilder();
    org.w3c.dom.Document result = builder.newDocument();
    org.w3c.dom.Element rootElement = result.createElement("fake");
    result.appendChild(rootElement);
    for(InputStream is : xmlInputStreams) {
        org.w3c.dom.Document document = builder.parse(is);
        org.w3c.dom.Element subRoot = document.getDocumentElement();
        Node importNode = result.importNode(subRoot, true);
        rootElement.appendChild(importNode);
    }
    return result;
}

2)恢复headerTag的节点列表

public NodeList recoverTheListOfElementsHeaderTag(String xml) throws ParserConfigurationException, SAXException, IOException {
    NodeList listOfElementsHeaderTag = null;
    DocumentBuilder builder = DocumentBuilderFactory.newInstance().newDocumentBuilder();
    try (InputStream is = new ByteArrayInputStream(xml.getBytes(StandardCharsets.UTF_8))) {
        listOfElementsHeaderTag = recoverTheListOfElementsHeaderTag(builder.parse(is));
    }
    return listOfElementsHeaderTag;
}

public NodeList recoverTheListOfElementsHeaderTag(org.w3c.dom.Document doc) {
    org.w3c.dom.Element root = doc.getDocumentElement();
    return root.getChildNodes();
}

测试

@Test
public void concatXmlDocuments() throws ParserConfigurationException, SAXException, IOException, TransformerException {
    try (
            InputStream doc1 = new ByteArrayInputStream((
                "<headerTag>" + 
                "<tag1>doc1 value</tag1>" + 
                "</headerTag>").getBytes(StandardCharsets.UTF_8));
            InputStream doc2 = new ByteArrayInputStream((
                "<headerTag>" + 
                "<tag1>doc2 value</tag1>" + 
                "</headerTag>").getBytes(StandardCharsets.UTF_8));

        ) {

        org.w3c.dom.Document result = concatXmlDocuments(doc1, doc2);
        String resultXML = toXML(result);
        System.out.printf("%s%n", resultXML);
        NodeList listOfElementsHeaderTag = null;
        System.out.printf("===================================================%n");
        listOfElementsHeaderTag = recoverTheListOfElementsHeaderTag(resultXML);
        printNodeList(listOfElementsHeaderTag);
        System.out.printf("===================================================%n");
        listOfElementsHeaderTag = recoverTheListOfElementsHeaderTag(result);
        printNodeList(listOfElementsHeaderTag);
    }
}


private String toXML(org.w3c.dom.Document result) throws TransformerFactoryConfigurationError, TransformerConfigurationException, TransformerException, IOException {
    String resultXML = null;
    try (ByteArrayOutputStream docR = new ByteArrayOutputStream()) {
        TransformerFactory trf = TransformerFactory.newInstance();
        Transformer tr = trf.newTransformer();
        DOMSource source = new DOMSource(result);
        StreamResult sr = new StreamResult(docR);
        tr.transform(source, sr);
        resultXML = new String(docR.toByteArray(), StandardCharsets.UTF_8);
    }
    return resultXML;
}

private void printNodeList(NodeList nodeList) {
    for(int i = 0; i < nodeList.getLength(); i++) {
        printNode(nodeList.item(i), "");
    }
}

private void printNode(Node node, String startIndent) {
    if(node != null) {
        System.out.printf("%s%s%n", startIndent, node.toString());
        NodeList childNodes = node.getChildNodes();
        for(int i = 0; i < childNodes.getLength(); i++) {
            printNode(childNodes.item(i), startIndent+ "    ");
        }
    }
}

输出

<?xml version="1.0" encoding="UTF-8" standalone="no"?><fake><headerTag><tag1>doc1 value</tag1></headerTag><headerTag><tag1>doc2 value</tag1></headerTag></fake>
===================================================
[headerTag: null]
    [tag1: null]
        [#text: doc1 value]
[headerTag: null]
    [tag1: null]
        [#text: doc2 value]
===================================================
[headerTag: null]
    [tag1: null]
        [#text: doc1 value]
[headerTag: null]
    [tag1: null]
        [#text: doc2 value]