fix(文档对比): 相同纯img标签对比不一致问题

laws-modules/src/main/java/com/jero/modules/compare/service/impl/SarFileCompareInfoServiceImpl.java

@@ -21,6 +21,7 @@ import org.springframework.beans.factory.annotation.Autowired;
 import org.springframework.stereotype.Service;
 
 import java.util.*;
+import java.util.regex.Pattern;
 import java.util.stream.Collectors;
 
 /**
@@ -161,7 +162,20 @@ public class SarFileCompareInfoServiceImpl extends ServiceImpl<SarFileCompareInf
                         }
                         String rightTxt = rightItemList.get(j).getItemsText();
                         if (null != rightTxt && !rightTxt.isEmpty()) {
-                            double similarity = CompHanLPUtils.findSimilarity(leftTxt.trim(), rightTxt.trim());
+                            double similarity = 0;
+                                    // 使用正则表达式判断是否是纯<img>标签，不以</p>结尾，也不以</table>结尾
+                            String leftTxtTrim = leftTxt.trim();
+                            String rightTxtTrim = rightTxt.trim();
+                            boolean leftTxtMatches = Pattern.matches("<img[^>]+>(?<!</p>)(?<!</table>)", leftTxtTrim);
+                            boolean rightTxtMatches = Pattern.matches("<img[^>]+>(?<!</p>)(?<!</table>)", rightTxtTrim);
+                            if (leftTxtMatches && rightTxtMatches){
+                                // 如果是纯img标签直接对比内容
+                                if (leftTxtTrim.equals(rightTxtTrim)){
+                                    similarity = 1;
+                                }
+                            }else {
+                                similarity = CompHanLPUtils.findSimilarity(leftTxt.trim(), rightTxt.trim());
+                            }
                             //如果相似度超过0.6 并且该相似度比之前的相似度还高，那么该条款目前相似度最高
                             if (similarity >= 0.6 && compareSimilarity < similarity) {
                                 compareSimilarity = similarity;

laws-modules/src/main/java/com/jero/modules/compare/utils/CompHanLPUtils.java

@@ -15,7 +15,6 @@ import org.wltea.analyzer.core.Lexeme;
 
 import java.io.IOException;
 import java.io.StringReader;
-import java.text.NumberFormat;
 import java.util.*;
 import java.util.stream.Collectors;