regex微调

epmet-module/gov-voice/gov-voice-server/src/main/java/com/epmet/service/impl/ArticleServiceImpl.java

@@ -1653,18 +1653,34 @@ public class ArticleServiceImpl extends BaseServiceImpl<ArticleDao, ArticleEntit
      * @author zxc
      * @date 2022/7/1 10:32
      */
-    public static String getPreviewContent(String content) {
-    	if (StringUtils.isBlank(content)){
-    		return "";
-		}
-		String regex = "[\\u4e00-\\u9fa5]";
-		Pattern p = Pattern.compile(regex);
-		Matcher m = p.matcher(content);
-		StringBuffer sb = new StringBuffer();
-		while (m.find()) {
-			sb.append(m.group());
-		}
-		return sb.toString();
+	public String getPreviewContent(String content) {
+		// 定义script的正则表达式
+		String regEx_script = "<script[^>]*?>[\\s\\S]*?<\\/script>";
+		// 定义style的正则表达式
+		String regEx_style = "<style[^>]*?>[\\s\\S]*?<\\/style>";
+		// 定义HTML标签的正则表达式
+		String regEx_html = "<[^>]+>";
+		//定义空格回车换行符
+		String regEx_space = "\\s*|\t|\r|\n";
+		Pattern p_script = Pattern.compile(regEx_script, Pattern.CASE_INSENSITIVE);
+		Matcher m_script = p_script.matcher(content);
+		// 过滤script标签
+		content = m_script.replaceAll("");
+		Pattern p_style = Pattern.compile(regEx_style, Pattern.CASE_INSENSITIVE);
+		Matcher m_style = p_style.matcher(content);
+		// 过滤style标签
+		content = m_style.replaceAll("");
+		Pattern p_html = Pattern.compile(regEx_html, Pattern.CASE_INSENSITIVE);
+		Matcher m_html = p_html.matcher(content);
+		// 过滤html标签
+		content = m_html.replaceAll("");
+		Pattern p_space = Pattern.compile(regEx_space, Pattern.CASE_INSENSITIVE);
+		Matcher m_space = p_space.matcher(content);
+		// 过滤空格回车标签
+		content = m_space.replaceAll("");
+		//去空格
+		content = content.replaceAll("&nbsp;", "");
+		return content.trim();
 	}
 
 	@Override