投稿
  1. 极客之音首页
  2. 技术随笔

xmlunit比较HTML或者XML文档差异

飞熊 • • 技术随笔 • 阅读 222

如果你不相信努力和时光，那么成果就会是第一个选择辜负你的。不要去否定你自己的过去，也不要用你的过去牵扯你现在的努力和对未来的展望。不是因为拥有希望你才去努力，而是去努力了，你才有可能看到希望的光芒。xmlunit比较HTML或者XML文档差异，希望对大家有帮助，欢迎收藏，转发！站点地址：www.bmabk.com，来源：原文

package com.ruoyi;
import java.io.StringReader;
import java.io.StringWriter;

import javax.xml.parsers.DocumentBuilderFactory;
import javax.xml.transform.OutputKeys;
import javax.xml.transform.Transformer;
import javax.xml.transform.TransformerFactory;
import javax.xml.transform.dom.DOMSource;
import javax.xml.transform.stream.StreamResult;
import javax.xml.xpath.XPath;
import javax.xml.xpath.XPathConstants;
import javax.xml.xpath.XPathFactory;

import org.apache.commons.lang3.ObjectUtils;
import org.w3c.dom.Attr;
import org.w3c.dom.Document;
import org.w3c.dom.Node;
import org.w3c.dom.NodeList;
import org.xml.sax.InputSource;
import org.xmlunit.builder.DiffBuilder;
import org.xmlunit.diff.Comparison;
import org.xmlunit.diff.DefaultNodeMatcher;
import org.xmlunit.diff.Diff;
import org.xmlunit.diff.Difference;
import org.xmlunit.diff.ElementSelectors;

public class HtmlComparator {

    public static void main(String[] args) throws Exception {
        String html1 = "<html><body><b>vv</b><table><tr><td>A</td></tr><tr><td>001</td></tr></table><div>我爱你</div><h1>Q2</h1><h2>Q2</h2></body></html>";//正式文档
        String html2 = "<html><body><div>我爱你</div><b>vv</b><h1>Q2</h1></body></html>";//测试文档

        DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance();
        // 注意：这里需要设置忽略DOCTYPE和实体引用，否则可能因DOCTYPE不匹配导致错误
        factory.setFeature("http://apache.org/xml/features/disallow-doctype-decl", true);
        factory.setFeature("http://xml.org/sax/features/external-general-entities", false);
        factory.setFeature("http://xml.org/sax/features/external-parameter-entities", false);

        Document doc1 = factory.newDocumentBuilder() .parse(new InputSource(new StringReader(html1)));
        Document doc2 = factory.newDocumentBuilder().parse(new InputSource(new StringReader(html2)));

        Diff myDiff = DiffBuilder.compare(doc1)
                                .withTest(doc2)
                                .ignoreWhitespace()
                                .checkForSimilar()//忽略结构顺序
                                .withNodeFilter(n->n.getNodeType()!=Node.PROCESSING_INSTRUCTION_NODE&&
                                n.getNodeType()!=Node.DOCUMENT_NODE)
                                .withNodeMatcher(new DefaultNodeMatcher(ElementSelectors.Default))//byName//Default//byNameAndText
                                .build();

        if (myDiff.hasDifferences()) {
            XPath xpath = XPathFactory.newInstance().newXPath();
            for (Difference difference : myDiff.getDifferences()) {
                Comparison comparison = difference.getComparison();
                switch (comparison.getType()) {
                    case CHILD_NODELIST_LENGTH:
                        String controlParentXPath = difference.getComparison().getControlDetails().getXPath();
                        String testParentXPath = difference.getComparison().getTestDetails().getXPath();

                        // 获取控制文档中父节点及其子节点列表
                        NodeList controlParentNodes = (NodeList) xpath.evaluate(controlParentXPath, doc1, XPathConstants.NODESET);
                        Node controlParentNode = controlParentNodes.item(0);
                        NodeList controlChildNodes = controlParentNode.getChildNodes();

                        // 获取测试文档中父节点及其子节点列表
                        NodeList testParentNodes = (NodeList) xpath.evaluate(testParentXPath, doc2, XPathConstants.NODESET);
                        Node testParentNode = testParentNodes.item(0);
                        NodeList testChildNodes = testParentNode.getChildNodes();

                        int expectedLength = controlChildNodes.getLength();
                        int actualLength = testChildNodes.getLength();

                        if (actualLength < expectedLength) {
                            System.out.println("Missing nodes at path: " + controlParentXPath);

                            // 输出控制文档中存在的、但在测试文档中缺失的子节点
                            for (int i = actualLength; i < expectedLength; i++) {
                                Node missingNode = controlChildNodes.item(i);
                                // 复制控制文档中的缺失节点到测试文档，并设置属性data-patch="missing"
                                Node copiedNode = doc2.importNode(missingNode, true);
                                copiedNode.getAttributes().setNamedItem(doc2.createAttribute("data-patch"));
                                copiedNode.getAttributes().getNamedItem("data-patch").setTextContent("missing");
                                testParentNode.appendChild(copiedNode);
                                System.out.println("  Missing node: " + missingNode.getNodeName());
                            }
                        } else if (actualLength > expectedLength) {
                            System.out.println("Extra nodes at path: " + testParentXPath);

                            // 输出测试文档中存在的、但在控制文档中不存在的子节点
                            for (int i = expectedLength; i < actualLength; i++) {
                                Node extraNode = testChildNodes.item(i);
                                System.out.println("  Extra node: " + extraNode.getNodeName());
                            }
                        }

                        break;
                    case CHILD_NODELIST_SEQUENCE:
                        // 根据描述信息判断是哪个节点的子节点顺序不同，并在相应文档中进行标记或操作
                        break;
                    case CHILD_LOOKUP:
                        String tesXPath = difference.getComparison().getTestDetails().getXPath();
                        if(!org.springframework.util.ObjectUtils.isEmpty(tesXPath)) {
                        // 获取测试文档中的新增节点
                        Node newNode = (Node) xpath.evaluate(tesXPath, doc2, XPathConstants.NODE);
                        Node testparentNode = newNode.getParentNode();
                        if (newNode != null) {
                            Attr attrAdded = newNode.getOwnerDocument().createAttribute("data-patch");
                            attrAdded.setValue("added");
                            if(newNode != null && newNode.getNodeType() == Node.TEXT_NODE) {
                                testparentNode.getAttributes().setNamedItem(attrAdded);
                            }else {
                            	newNode.getAttributes().setNamedItem(attrAdded);
                            }
                            
                        }}
                        break;
                    case TEXT_VALUE:
                        String controlXPath = difference.getComparison().getControlDetails().getXPath();
                        Node controlTextNode = (Node) xpath.evaluate(controlXPath, doc1, XPathConstants.NODE);
                        String controlTextValue = controlTextNode.getTextContent();
                        Node conparentNode = controlTextNode.getParentNode();

                        String testXPath = difference.getComparison().getTestDetails().getXPath();
                        Node testTextNode = (Node) xpath.evaluate(testXPath, doc2, XPathConstants.NODE);
                        String testTextValue = testTextNode.getTextContent();
                        Node testparentNode = testTextNode.getParentNode();


                        // 如果内容不同，则在控制文档节点上添加属性标记
                        if (!controlTextValue.equals(testTextValue)) {
                            Attr attrModified = controlTextNode.getOwnerDocument().createAttribute("data-patch");
                            attrModified.setValue("modified");
                            conparentNode.getAttributes().setNamedItem(attrModified);
                            // 如果需要同时在测试文档节点上做标记，请在此处添加类似操作
                            attrModified = testTextNode.getOwnerDocument().createAttribute("data-patch");
                            attrModified.setValue("modified");
                            testparentNode.getAttributes().setNamedItem(attrModified);
                        }
                        break;

                }
            }
            // 输出更新后的doc2内容（假设使用Transformer写出）
            TransformerFactory transformerFactory = TransformerFactory.newInstance();
            Transformer transformer = transformerFactory.newTransformer();
            transformer.setOutputProperty(OutputKeys.INDENT, "yes");
            DOMSource source = new DOMSource(doc2);
            StreamResult result = new StreamResult(System.out);
            transformer.transform(source, result);
            
            
            // 输出整个带有标记的HTML内容
            StringWriter writer1 = new StringWriter();
            Transformer transformer1 = TransformerFactory.newInstance().newTransformer();
            transformer1.setOutputProperty(OutputKeys.OMIT_XML_DECLARATION, "yes");
            transformer1.transform(new DOMSource(doc2), new StreamResult(writer1));
            String modifiedHtml1 = writer1.toString();
            System.out.println(modifiedHtml1);

        }
    }
}

版权声明：本文内容由互联网用户自发贡献，该文观点仅代表作者本人。本站仅提供信息存储空间服务，不拥有所有权，不承担相关法律责任。如发现本站有涉嫌侵权/违法违规的内容， 请发送邮件至 举报，一经查实，本站将立刻删除。

文章由极客之音整理，本文链接：https://www.bmabk.com/index.php/post/200895.html

赞 (0)
飞熊的头像飞熊bm
0 0

相关推荐

发表回复

登录后才能评论
极客之音——专业性很强的中文编程技术网站，欢迎收藏到浏览器，订阅我们！