Update check_ccfa.py

check_ccfa_strict/check_ccfa.py

@@ -33,6 +33,16 @@ def extract_bracket_content(s):
     match = re.search(r'[(（](.*?)[)）]', s)
     return match.group(1).strip() if match else None
 
+def extract_abbr_before_colon(s):
+    """
+    提取冒号前的内容（支持中英文冒号），并只保留英文字母
+    """
+    split_result = re.split(r'[:：]', s, 1)
+    if len(split_result) > 1:
+        abbr = re.sub(r'[^A-Za-z]', '', split_result[0])
+        return abbr if abbr else None
+    return None
+
 def main():
     # 1. 读取CCF-A列表
     abbr_set, fullname_set = read_ccf_a_list(ccf_a_csv)
@@ -60,23 +70,37 @@ def main():
             print(f"错误：{sheetname} 页，标题栏应该在第四行！！第四列标题为【{col4}】，第五列标题为【{col5}】，不符合要求！")
             sys.exit(1)
 
-        # 5. 逐行处理
         for row in ws.iter_rows(min_row=header_row_idx+1):
             name_cell = row[3]  # 第四列
             result_cell = row[4]  # 第五列
             name = name_cell.value
+            if name == 'Proceedings of the 26th ACM International Conference on Architectural Support for Programming Languages and Operating Systems':
+                breakpoint()
             if not name or not str(name).strip():
                 result_cell.value = ""
                 continue
             name_str = str(name).strip()
-            # 6. 先提取括号内内容
+            # 1. 括号简称
             bracket = extract_bracket_content(name_str)
-            is_ccfa = False
-            if bracket and bracket in abbr_set:
-                is_ccfa = True
-            elif name_str in fullname_set:
-                is_ccfa = True
-            result_cell.value = "是" if is_ccfa else "否"
+            bracket_abbr = re.sub(r'[^A-Za-z]', '', bracket) if bracket else None
+            # 2. 冒号前简称
+            colon_abbr = extract_abbr_before_colon(name_str)
+            # 判断是否有简称（括号或冒号前）
+            if bracket_abbr or colon_abbr:
+                match = False
+                if bracket_abbr and bracket_abbr in abbr_set:
+                    match = True
+                elif colon_abbr and colon_abbr in abbr_set:
+                    match = True
+                result_cell.value = "是" if match else "否"
+            else:
+                # 没有简称，判断全称包含
+                is_ccfa = False
+                for fullname in fullname_set:
+                    if fullname and fullname in name_str:
+                        is_ccfa = True
+                        break
+                result_cell.value = "是" if is_ccfa else "否"
 
     # 7. 保存新文件
     base, ext = os.path.splitext(excel_path)