xmlunit比较HTML文档差异

package com.ri;
import java.io.StringWriter;
import java.util.ArrayList;
import java.util.List;

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.io.IOUtils;
import org.springframework.util.ObjectUtils;
import org.w3c.dom.Attr;
import org.w3c.dom.Document;
import org.w3c.dom.Node;
import org.xmlunit.builder.DiffBuilder;
import org.xmlunit.builder.Input;
import org.xmlunit.diff.Comparison;
import org.xmlunit.diff.ComparisonResult;
import org.xmlunit.diff.ComparisonType;
import org.xmlunit.diff.DefaultNodeMatcher;
import org.xmlunit.diff.Diff;
import org.xmlunit.diff.Difference;
import org.xmlunit.diff.DifferenceEvaluator;
import org.xmlunit.diff.ElementSelectors;

public class HtmlDiffExample {

    public static void main(String[] args) {
//    	=====getControlDetails======	CHILD_NODELIST_LENGTH
//		=====getControlDetails======	CHILD_LOOKUP
//		=====getTestDetails======	CHILD_LOOKUP
//		=====getTestDetails======	CHILD_LOOKUP
    	//由此可见xmlunit对差异会生成响应的类型，但是由于结构和长度标签不同差异getControlDetails或者getTestDetails会为空所以分别判断赋值。也有同时它俩都不为空

        String html1 = "
Q
";
        //html1=Jsoup.parse(html1).body().html();
        //html1=Jsoup.parseBodyFragment(html1).html();
        String html2 = "
Q
Q2
Q
";
        //html2=Jsoup.parse(html2).body().html();
        //html2=Jsoup.parseBodyFragment(html2).html();

        // 创建一个记录并标记差异的DifferenceEvaluator
        List<Object> differencesList = new ArrayList<>();
        DifferenceEvaluator evaluator = new DifferenceEvaluator() {
            @Override
            public ComparisonResult evaluate(Comparison comparison, ComparisonResult originalResult) {
                differencesList.add(comparison);
                return originalResult;
            }
        };

        // 使用builders创建DOM对象，并忽略空白字符差异
        Diff myDiff = DiffBuilder.compare(Input.fromString(html1))
                                .withTest(Input.fromString(html2))
                                .ignoreWhitespace()
                                //.withNodeMatcher(new DefaultNodeMatcher(ElementSelectors.byName))// 对于元素匹配，我们只关心名称相同的元素（这将忽略属性顺序等差异）
                                .withNodeMatcher(new DefaultNodeMatcher(ElementSelectors.byNameAndText))
                                .withDifferenceEvaluator(evaluator)
                                .build();

        if (myDiff.hasDifferences()) {
            Document doc1AsDom;
            Document doc2AsDom;
            try {
                DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance();
                factory.setNamespaceAware(false);
                doc1AsDom = factory.newDocumentBuilder().parse(IOUtils.toInputStream(html1));
                doc2AsDom = factory.newDocumentBuilder().parse(IOUtils.toInputStream(html2));
                XPath xpath = XPathFactory.newInstance().newXPath();
                Iterable<Difference> differences = myDiff.getDifferences();  
                for (Difference difference : differences) {
                	ComparisonType comparisonType = difference.getComparison().getType();
                    if (difference.getComparison()!= null&&difference.getComparison().getControlDetails()!= null&&!ObjectUtils.isEmpty(difference.getComparison().getControlDetails().getXPath())) {
                    System.out.println("=====getControlDetails======"+"\t"+comparisonType);
                	Node controlNode = (Node) xpath.evaluate(difference.getComparison().getControlDetails().getXPath(), doc1AsDom, XPathConstants.NODE);
                    // 设置属性以标记差异
                	Attr attr = null;
                    switch (comparisonType) {
                        case CHILD_LOOKUP:
                        	//if (controlNode.getNodeType() != Node.TEXT_NODE) {
                        	//attr=doc1AsDom.createAttribute("data-diff");
                        	attr=controlNode.getOwnerDocument().createAttribute("data-diff");
                            attr.setValue("deleted");
                            controlNode.getAttributes().setNamedItem(attr); 
                            //}
                            break;
                        case CHILD_NODELIST_LENGTH:
                      	  
                        	break;
                        case TEXT_VALUE:
                        	Node parentNode = controlNode.getParentNode();
                        	attr=parentNode.getOwnerDocument().createAttribute("data-diff");
                        	attr.setValue("deleted");
                        	parentNode.getAttributes().setNamedItem(attr); 
                        	break;
                    }
                  
                  }else if(difference.getComparison()!= null&&difference.getComparison().getTestDetails()!= null&&!ObjectUtils.isEmpty(difference.getComparison().getTestDetails().getXPath())) {
                      System.out.println("=====getTestDetails======"+"\t"+comparisonType);
                	  switch (comparisonType) {
                      case CHILD_LOOKUP:
                    	  Node testNode = (Node) xpath.evaluate(difference.getComparison().getTestDetails().getXPath(), doc2AsDom, XPathConstants.NODE);
                    	  //Attr attr = doc2AsDom.createAttribute("data-diff");
                    	  Attr attr = testNode.getOwnerDocument().createAttribute("data-diff");
                          attr.setValue("update");
                          testNode.getAttributes().setNamedItem(attr);
                          break; 
                    }
                  }
                }

                // 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(doc1AsDom), new StreamResult(writer1));
                String modifiedHtml1 = writer1.toString();

                StringWriter writer2 = new StringWriter();
                Transformer transformer2 = TransformerFactory.newInstance().newTransformer();
                transformer2.setOutputProperty(OutputKeys.OMIT_XML_DECLARATION, "yes");
                transformer2.transform(new DOMSource(doc2AsDom), new StreamResult(writer2));
                String modifiedHtml2 = writer2.toString();

                System.out.println("Original HTML with marked differences: " + modifiedHtml1);
                System.out.println("Modified HTML with marked differences: " + modifiedHtml2);

            } catch (Exception e) {
                throw new RuntimeException(e);
            }
        } else {
            System.out.println("Documents are similar.");
        }
    } 
}

=====getControlDetails======	CHILD_NODELIST_LENGTH
=====getTestDetails======	CHILD_LOOKUP
=====getTestDetails======	CHILD_LOOKUP
Original HTML with marked differences: <html>
<body>
<p>Q</p>
</body>
</html>

Modified HTML with marked differences: <html>
<body>
<p>Q</p>
<h1 data-diff="update">Q2</h1>
<h1 data-diff="update">Q</h1>
</body>
</html>