分别使用dom4j和jdk自带的方法解析xml文件

分别使用dom4j和jdk自带的方法解析xml文件。

---

xml文件

xml文件内容如下(waitReader.xml)：

<!DOCTYPE x172.xml>
<course>
    <courseInfo security="8" new="true" alias="冷笑话精选" courseType="wb-article">
        第一个节点的text内容
        <item id="-1" name="first">第一个节点的第1个子节点</item>
        <item id="-2" name="second">第一个节点的第2个子节点</item>
    </courseInfo>

    <second>
        <item id="0">第二个节点的第1个子节点</item>
        <item id="1">第二个节点的第1个子节点</item>
    </second>
</course>

使用dom4j解析xml

pom.xml引入dom4j

        <!-- dom4j -->
        <dependency>
            <groupId>org.dom4j</groupId>
            <artifactId>dom4j</artifactId>
            <version>2.1.4</version>
        </dependency>

解析xml的代码：

package com.example.study.common;

import org.dom4j.Attribute;
import org.dom4j.Document;
import org.dom4j.DocumentException;
import org.dom4j.Element;
import org.dom4j.io.SAXReader;
import org.xml.sax.SAXException;

import javax.xml.parsers.ParserConfigurationException;
import java.io.IOException;

/**
 * 使用dom4j解析xml文件
 */
public class XmlParse {
    public static void parse(String file) throws DocumentException {
        SAXReader reader = new SAXReader();
        Document document = reader.read(file);
        Element rootElement = document.getRootElement();
        recursionReadElement(rootElement);
    }

    private static void recursionReadElement(Element element) {
        if (element == null) {
            return;
        }
        String path = element.getPath();
        int level = path.length() - path.replace("/", "").length();
        String levelSpace = genlevelSpace(level);
        System.out.println(levelSpace + "标签路径:" + element.getPath());
        System.out.println(levelSpace + "父标签(Element):" + element.getParent());
        System.out.println(levelSpace + "标签名:" + element.getName());
        System.out.println(levelSpace + "标签包裹的内容:" + element.getText().trim()
                .replace("\n", "")
                .replace("\r", ""));
        // System.out.println(levelSpace + "获取指定标签:" + element.element("content"));
        // System.out.println(levelSpace + "获取指定属性:" + element.attribute("id"));
        System.out.print(levelSpace + "标签属性:" + System.getProperty("line.separator") + levelSpace + "attr:");
        for (Attribute attribute : element.attributes()) {
            System.out.print(String.format("%s=%s\t", attribute.getName(), attribute.getValue()));
        }
        System.out.println(System.getProperty("line.separator"));
        for (Element subElement : element.elements()) {
            recursionReadElement(subElement);
        }
    }

    private static String genlevelSpace(int level) {
        StringBuilder sb = new StringBuilder();
        while (--level > 0) {
            sb.append("    ");
        }
        return sb.toString();
    }

    public static void main(String[] args) throws DocumentException, IOException, SAXException, ParserConfigurationException {
        String file = "F:\\tmp\\waitReader.xml";
        parse(file);
    }
}

使用jdk自带方法解析xml

解析xml的代码：

package com.example.study.common;

import org.w3c.dom.Document;
import org.w3c.dom.Element;
import org.w3c.dom.NamedNodeMap;
import org.w3c.dom.Node;
import org.w3c.dom.NodeList;
import org.xml.sax.SAXException;

import javax.xml.parsers.DocumentBuilder;
import javax.xml.parsers.DocumentBuilderFactory;
import javax.xml.parsers.ParserConfigurationException;
import java.io.IOException;

/**
 * 使用jdk自带方法解析xml文件
 */
public class XmlParse {
    public static void parse(String file) throws ParserConfigurationException, IOException, SAXException {
        DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance();
        DocumentBuilder builder = factory.newDocumentBuilder();
        Document document = builder.parse(file);
        Element documentElement = document.getDocumentElement();
        NodeList childNodes = documentElement.getChildNodes();
        for (int i = 0; i < childNodes.getLength(); i++) {
            Node childNode = childNodes.item(i);
            if (childNode.getTextContent().trim().isEmpty()) {
                continue;
            }
            recursionReadElement(childNode);
            System.out.println("--->");
        }
    }

    private static void recursionReadElement(Node node) {
        if (node == null) {
            return;
        }
        int level = getLevel(node, 0);
        String levelSpace = genlevelSpace(level);
        System.out.println(levelSpace + "标签级别:" + level);
        System.out.println(levelSpace + "父标签(Element):" + node.getParentNode());
        System.out.println(levelSpace + "标签名:" + node.getNodeName());
        System.out.println(levelSpace + "标签包裹的内容:" + node.getTextContent()
                .replace("\n", "")
                .replace("\r", ""));
        System.out.print(levelSpace + "标签属性:" + System.getProperty("line.separator") + levelSpace + "attr:");
        NamedNodeMap attributes = node.getAttributes();
        for (int index = 0; attributes != null && index < attributes.getLength(); index++) {
            Node attribute = attributes.item(index);
            if (attribute.getTextContent().trim().isEmpty()) {
                continue;
            }
            System.out.print(String.format("%s=%s\t", attribute.getNodeName(), attribute.getNodeValue()));
        }
        System.out.println(System.getProperty("line.separator"));
        NodeList childNodes = node.getChildNodes();
        for (int index = 0; index < childNodes.getLength(); index++) {
            recursionReadElement(childNodes.item(index));
        }
    }

    private static String genlevelSpace(int level) {
        StringBuilder sb = new StringBuilder();
        while (--level > 0) {
            sb.append("    ");
        }
        return sb.toString();
    }

    private static int getLevel(Node node, int level) {
        return node.getNodeName().equals("#document") ? 0 : 1 + getLevel(node.getParentNode(), level + 1);
    }

    public static void main(String[] args) throws IOException, SAXException, ParserConfigurationException {
        String file = "F:\\tmp\\waitReader.xml";
        parse(file);
    }
}