利用 JDK 自带的 Document + XPath 解析 XML

古城微笑少年丶 2023-02-21 02:26 16阅读 0赞

> 利用 JDK 自带的 Document + XPath 解析 XML，记录一下

## 准备工作 ##

> inventory.dtd 和 inventory.xml 文件  
> dtd 中的 PCDATA 的意思是被解析的字符数据（parsed character data）。可把字符数据想象为 XML 元素的开始标签与结束标签之间的文本。PCDATA 是会被解析器解析的文本。  
> CDATA 的意思是字符数据（character data）。CDATA 是不会被解析器解析的文本。

*  inventory.dtd

<?xml version="1.0" encoding="UTF-8"?>
    <!ELEMENT inventory (book+)>
    <!ELEMENT book (title,author,dynasty,price)>
    <!ATTLIST book year CDATA #REQUIRED>
    <!ELEMENT title (#PCDATA)>
    <!ELEMENT author (#PCDATA)>
    <!ELEMENT dynasty (#PCDATA)>
    <!ELEMENT price (#PCDATA)>

*  inventory.xml

<?xml version="1.0" encoding="UTF-8" ?>
    <!DOCTYPE inventory SYSTEM "D:\\work-space\\springboot\\src\\main\\resources\\inventory.dtd">
    <inventory>
        <book year="2012">
            <title>菜根谭</title>
            <author>洪应明</author>
            <dynasty>明朝</dynasty>
            <price>38</price>
        </book>
        <book year="2013">
            <title>曾国藩家书</title>
            <author>曾国藩</author>
            <dynasty>清朝</dynasty>
            <price>70</price>
        </book>
        <book year="2014">
            <title>高等代数</title>
            <author>丘维声</author>
            <dynasty>中华人民共和国</dynasty>
            <price>86</price>
        </book>
    </inventory>

*  工具类

> 借鉴了博客【[用DOM解析XML ，用xpath快速查询XML节点][DOM_XML _xpath_XML]】的内容

package com.me.util;
    
    import org.w3c.dom.Document;
    import org.w3c.dom.Node;
    import org.w3c.dom.NodeList;
    import org.xml.sax.ErrorHandler;
    import org.xml.sax.SAXException;
    import org.xml.sax.SAXParseException;
    
    import javax.xml.parsers.DocumentBuilder;
    import javax.xml.parsers.DocumentBuilderFactory;
    import javax.xml.xpath.XPath;
    import javax.xml.xpath.XPathConstants;
    import javax.xml.xpath.XPathExpression;
    import javax.xml.xpath.XPathFactory;
    import java.io.File;
    
    /** * @Author yanyg * @Date 2020/6/10 16:37 * @Descripetion admin */
    public class ParseXmlUtil { 
        //查询价格大于80的书的标题的内容
        private static final String XPath_EXPRESSION = "//book[price>80]/title/text()";
    
        public static void main(String[] args) { 
    
            try { 
                DocumentBuilderFactory documentBuilderFactory = DocumentBuilderFactory.newInstance();
                //开启验证：
                documentBuilderFactory.setValidating(true);
                documentBuilderFactory.setNamespaceAware(false);
                documentBuilderFactory.setIgnoringComments(true);
                documentBuilderFactory.setIgnoringElementContentWhitespace(true);
                documentBuilderFactory.setCoalescing(false);
                documentBuilderFactory.setExpandEntityReferences(true);
                DocumentBuilder documentBuilder = documentBuilderFactory.newDocumentBuilder();
                //设置异常处理：
                documentBuilder.setErrorHandler(new ErrorHandler() { 
                    @Override
                    public void warning(SAXParseException exception) throws SAXException { 
                        System.out.println("warn:" + exception.getMessage());
                    }
    
                    @Override
                    public void error(SAXParseException exception) throws SAXException { 
                        System.out.println("error:" + exception.getMessage());
                    }
    
                    @Override
                    public void fatalError(SAXParseException exception) throws SAXException { 
                        System.out.println("fatalError:" + exception.getMessage());
                    }
                });
                //将inventory.xml加载到一个Document的对象中：
                String filePath = "D:\\work-space\\springboot\\src\\main\\resources\\inventory.xml";
                Document document = documentBuilder.parse(new File(filePath));
                //根据表达式查询内容
                processParseXmlWithXpath(document, XPath_EXPRESSION);
            } catch (Exception e) { 
                e.printStackTrace();
            } finally { 
            }
        }
    
    
        private static void processParseXmlWithXpath(Document document, String xPathExpression) throws Exception { 
            // 表达式可以参考：https://blog.csdn.net/zlj_blog/article/details/54092534
            xPathExpression = "/inventory/book/title";
            //创建XPathFactory:
            XPathFactory xPathFactory = XPathFactory.newInstance();
            XPath xPath = xPathFactory.newXPath();
            NodeList nodeList = (NodeList) xPath.evaluate(xPathExpression, document, XPathConstants.NODESET);
            for (int i = 0; i < nodeList.getLength(); i++) { 
                Node item = nodeList.item(i);
                System.out.println(item.getNodeName() + "=" + item.getTextContent());
            }
        }
    
        private static void processParseXmlWithXpathExpress(Document document, String xPathExpression) throws Exception { 
            //创建XPathFactory:
            XPathFactory xPathFactory = XPathFactory.newInstance();
            XPath xPath = xPathFactory.newXPath();
            XPathExpression expression = xPath.compile(xPathExpression);
            Object result = expression.evaluate(document, XPathConstants.NODESET);
            if (result instanceof NodeList) { 
                NodeList nodes = (NodeList) result;
                for (int i = 0; i < nodes.getLength(); i++) { 
                    System.out.println(String.format("%s=%s", nodes.item(i).getNodeName(), nodes.item(i).getNodeValue()));
                }
            }
        }
    }

[DOM_XML _xpath_XML]: https://www.cnblogs.com/1540340840qls/p/9942861.html