From 1e2e8146cc6cece6c1af51b9abc8e06b154b536b Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E5=A7=8B=E4=BA=8E=E5=88=9D=E8=A7=81?= <752204717@qq.com>
Date: Thu, 16 Apr 2026 11:02:01 +0800
Subject: [PATCH] =?UTF-8?q?=E5=AE=A1=E7=A8=BF=E6=A0=A1=E9=AA=8C=E7=A9=BA?=
 =?UTF-8?q?=E6=A0=BC?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 src/common/js/commonJS.js | 31 ++++++++++++-------------------
 1 file changed, 12 insertions(+), 19 deletions(-)

diff --git a/src/common/js/commonJS.js b/src/common/js/commonJS.js
index eae4459..3f15913 100644
--- a/src/common/js/commonJS.js
+++ b/src/common/js/commonJS.js
@@ -1246,35 +1246,28 @@ str = str.replace(regex, function (match, content, offset, fullString) {
 
     getCleanTextForCount(html) {
         if (!html) return "";
-    
-        // 创建临时容器解析 HTML
         const tempDiv = document.createElement('div');
         tempDiv.innerHTML = html;
     
-        // A. 特殊处理 wmath：只拿它里面的公式文本，扔掉里面生成的 mjx-container 等标签
+        // 1. 处理公式 (保留公式文本内容)
         const wmaths = tempDiv.querySelectorAll('wmath');
         wmaths.forEach(wm => {
-            // textContent 会拿到最原始的公式字符，忽略内部所有标签
-            const textNode = document.createTextNode(wm.textContent);
+            const textNode = document.createTextNode(" " + wm.textContent + " ");
             wm.parentNode.replaceChild(textNode, wm);
         });
     
-        // B. 获取现在的 HTML 内容
-        let result = tempDiv.innerHTML;
+        // 2. 移除所有引用标签 [1], [2] (防止用户靠狂刷引用来凑字数)
+        const refs = tempDiv.querySelectorAll('span.reference-link, a.ref'); // 根据你系统的 class 名调整
+        refs.forEach(r => r.remove());
     
-        // C. 去掉特定排版标签的“壳”（保留里面的文字）
-        // 包含 b, strong, br, em, i, sup, sub 等
-        result = result.replace(/<(p|div|b|strong|br|em|i|sup|sub)[^>]*>/gi, "");
-        result = result.replace(/<\/(p|div|b|strong|br|em|i|sup|sub)>/gi, "");
+        // 3. 获取纯文本 (textContent 是浏览器原生方法，能处理所有标签及其属性)
+        let text = tempDiv.textContent || tempDiv.innerText || "";
     
-     
-    
-        // E. 彻底“脱水”：去掉 HTML 实体、换行符、所有空格
-        result = result.replace(/&nbsp;/ig, "");
-        result = result.replace(/[\r\n\t]/g, "");
-        result = result.replace(/\s+/g, "");
-    
-        return result;
+        // 4. 标准化空格：将 HTML 实体、换行、多个空格统一转为一个空格
+        return text.replace(/&nbsp;/ig, " ")
+                   .replace(/[\r\n\t]+/g, " ")
+                   .replace(/\s+/g, " ")
+                   .trim();
     },