From b8f2919959e1a31979df4476a188517896870e26 Mon Sep 17 00:00:00 2001
From: 03 <1930154319@qq.com>
Date: Mon, 25 Mar 2024 10:15:11 +0800
Subject: [PATCH] Fix bug 553

---
 app/wordfreqCMD.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/app/wordfreqCMD.py b/app/wordfreqCMD.py
index dfdde2e..4cf550e 100644
--- a/app/wordfreqCMD.py
+++ b/app/wordfreqCMD.py
@@ -41,7 +41,7 @@ def file2str(fname):#文件转字符
 
 def remove_punctuation(s): # 这里是s是形参 (parameter)。函数被调用时才给s赋值。
     special_characters = '\_©~<=>+/[]*&$%^@.,?!:;#()"“”—‘’{}|，。？！￥……（）、《》：；·' # 把里面的字符都去掉
-    s = html.unescape(s)
+    s = html.unescape(s) # 将HTML实体转换为对应的字符，比如<会被识别为小于号
     for c in special_characters:
         s = s.replace(c, ' ') # 防止出现把 apple,apple 移掉逗号后变成 appleapple 情况
     s = s.replace('--', ' ')