遍历 DOM 树以获取（名称，值）属性对和叶节点

Question

我想遍历 DOM 中的 XML 文件，以便检索所有（名称，值）对：

1. 属性名称和值；
2. 所有叶子节点名称及其文本内容；

以下面的 XML 文件为例：

<?xml version="1.0" encoding="UTF-8"?>
<title text="title1">
    <comment id="comment1">
        <data> abcd </data>
        <data> efgh </data>
    </comment>
    <comment id="comment2">
        <data> ijkl </data>
        <data> mnop </data>
        <data> qrst </data>
    </comment>
</title>

我想要的名称值对是：

text=title1
id=comment1
data=abcd
data=efgh
id=commment2
data=ijkl
data=mnop
data=qrst

Answer 1

更简单的解决方案可能是使用 XPath 提取所有名称值对，如下例所示。您还可以跳过 DOM 构造并直接在 InputSource 上调用评估。 XPath 表达式

//@* | //*[not(*)]

匹配所有属性和所有没有任何子节点的节点的并集。

import java.io.StringReader;
import javax.xml.parsers.DocumentBuilder;
import javax.xml.parsers.DocumentBuilderFactory;
import javax.xml.xpath.XPath;
import javax.xml.xpath.XPathConstants;
import javax.xml.xpath.XPathFactory;
import org.w3c.dom.Document;
import org.w3c.dom.Node;
import org.w3c.dom.NodeList;
import org.xml.sax.InputSource;

public class Test {

    private static final String xml = "<title text='title1'>\n"
            + "  <comment id='comment1'>\n"
            + "    <data> abcd </data>\n"
            + "    <data> efgh </data>\n"
            + "  </comment>\n"
            + "  <comment id='comment2'>\n"
            + "    <data> ijkl </data>\n"
            + "    <data> mnop </data>\n"
            + "    <data> qrst </data>\n"
            + "  </comment>\n"
            + "</title>\n";

    public static void main(String[] args) throws Exception {
        DocumentBuilder builder = DocumentBuilderFactory.newInstance().newDocumentBuilder();
        Document doc = builder.parse(new InputSource(new StringReader(xml)));

        XPathFactory xpf = XPathFactory.newInstance();
        XPath xp = xpf.newXPath();
        NodeList nodes = (NodeList)xp.evaluate("//@* | //*[not(*)]", doc, XPathConstants.NODESET);

        System.out.println(nodes.getLength());

        for (int i=0, len=nodes.getLength(); i<len; i++) {
            Node item = nodes.item(i);
            System.out.println(item.getNodeName() + " : " + item.getTextContent());
        }
    }
}

Answer 2

怎么样：

    String xml = "<?xml version=\"1.0\" encoding=\"UTF-8\"?>\n" +
        "<title text=\"title1\">\n" +
        "    <comment id=\"comment1\">\n" +
        "        <data> abcd </data>\n" +
        "        <data> efgh </data>\n" +
        "    </comment>\n" +
        "    <comment id=\"comment2\">\n" +
        "        <data> ijkl </data>\n" +
        "        <data> mnop </data>\n" +
        "        <data> qrst </data>\n" +
        "    </comment>\n" +
        "</title>\n";

    try {
        DocumentBuilder builder = DocumentBuilderFactory.newInstance().newDocumentBuilder();
        Document doc = builder.parse(new InputSource(new StringReader(xml)));

        DocumentTraversal traversal = (DocumentTraversal) doc;

        NodeIterator iterator = traversal.createNodeIterator(
          doc.getDocumentElement(), NodeFilter.SHOW_ELEMENT, null, true);

        for (Node n = iterator.nextNode(); n != null; n = iterator.nextNode()) {
            //System.out.println("Element: " + ((Element) n).getTagName());
            String tagname = ((Element) n).getTagName();
            if(tagname.equals("title")) {
                System.out.println("text=" + ((Element)n).getAttribute("text"));
            }
            else if(tagname.equals("comment")) {
                System.out.println("id=" + ((Element)n).getAttribute("id"));
            }
            else if(tagname.equals("data")) {
                System.out.println("data=" + ((Element)n).getTextContent());
            }
            else {
                System.out.println("Unhandled element");
            }
        }

    } catch (Exception e) {
        e.printStackTrace();
    }

好吧，所以你对此不满意，这样怎么样：

 String xml = "<?xml version=\"1.0\" encoding=\"UTF-8\"?>\n" +
        "<title text=\"title1\">\n" +
        "    <comment id=\"comment1\">\n" +
        "        <data> abcd </data>\n" +
        "        <data> efgh </data>\n" +
        "    </comment>\n" +
        "    <comment id=\"comment2\">\n" +
        "        <data> ijkl </data>\n" +
        "        <data> mnop </data>\n" +
        "        <data> qrst </data>\n" +
        "    </comment>\n" +
        "</title>\n";

    try {
        DocumentBuilder builder = DocumentBuilderFactory.newInstance().newDocumentBuilder();
        Document doc = builder.parse(new InputSource(new StringReader(xml)));

        DocumentTraversal traversal = (DocumentTraversal) doc;

        NodeIterator iterator = traversal.createNodeIterator(
          doc.getDocumentElement(), NodeFilter.SHOW_ELEMENT, null, true);

        for (Node n = iterator.nextNode(); n != null; n = iterator.nextNode()) {
            //System.out.println("Element: " + ((Element) n).getTagName());
            String tagname = ((Element) n).getTagName();

            NamedNodeMap map = ((Element)n).getAttributes();
            if(map.getLength() > 0) {

                for(int i=0; i<map.getLength(); i++) {
                    Node node = map.item(i);
                    System.out.println(node.getNodeName() + "=" + node.getNodeValue());
                }
            }
            else {
                System.out.println(tagname + "=" + ((Element)n).getTextContent());
            }
        }

    } catch (Exception e) {
        e.printStackTrace();
    }