优化程序

server/association_detail.py

@@ -458,6 +458,16 @@ def extract_zip_recursive(zip_path: Path, extract_dir: Path, clear_dir: bool = T
     return extracted_files
 
 
+def has_audio_video_files(files_list: List[Dict[str, Union[str, float]]]) -> bool:
+    """检查文件列表中是否包含音视频文件"""
+    audio_video_exts = {'.mp3', '.mp4', '.avi', '.mkv', '.wav', '.flac', '.aac', '.ogg', '.wma', '.mov', '.wmv'}
+    for file_entry in files_list:
+        name = file_entry.get('name', '')
+        if any(name.lower().endswith(ext) for ext in audio_video_exts):
+            return True
+    return False
+
+
 def build_file_associations(
     word_content: List[str],
     twole_folder: Path,
@@ -482,12 +492,16 @@ def build_file_associations(
 
         # 辅助函数：处理文件路径，如果是 zip 则递归解压
         def process_file(file_path: Path) -> List[Dict[str, Union[str, float]]]:
+            def format_datetime(mtime: float) -> str:
+                """将时间戳格式化为可读的日期时间字符串"""
+                return datetime.fromtimestamp(mtime).strftime("%Y-%m-%d %H:%M:%S")
+
             files = []
             # 检查是否是压缩文件
             if file_path.suffix.lower() in ('.zip', '.rar', '.7z'):
                 # 先添加压缩文件本身
                 mtime = file_path.stat().st_mtime
-                files.append({"name": file_path.name, "mtime": mtime})
+                files.append({"name": file_path.name, "mtime": mtime, "datetime": format_datetime(mtime)})
 
                 tmp_dir = Path(__file__).parent / "tmp"
                 tmp_dir.mkdir(exist_ok=True)
@@ -510,10 +524,10 @@ def build_file_associations(
                 for f in extracted:
                     if f.is_file():
                         mtime = f.stat().st_mtime
-                        files.append({"name": f.name, "mtime": mtime})
+                        files.append({"name": f.name, "mtime": mtime, "datetime": format_datetime(mtime)})
             else:
                 mtime = file_path.stat().st_mtime
-                files.append({"name": file_path.name, "mtime": mtime})
+                files.append({"name": file_path.name, "mtime": mtime, "datetime": format_datetime(mtime)})
             return files
 
         def get_latest_extracted_mtime(file_entries: List[Dict[str, Union[str, float]]], archive_name: str) -> Optional[float]:
@@ -522,10 +536,28 @@ def build_file_associations(
                 for entry in file_entries
                 if entry.get("name") != archive_name and "mtime" in entry
             ]
-            return max(extracted_times) if extracted_times else None
+            if not extracted_times:
+                return None
+
+            # 找出压缩文件本身的时间
+            archive_mtime = None
+            for entry in file_entries:
+                if entry.get("name") == archive_name and "mtime" in entry:
+                    archive_mtime = entry["mtime"]
+                    break
+
+            latest_extracted = max(extracted_times)
+
+            # 如果压缩文件时间和解压文件最晚时间差小于 30 秒，返回 None
+            if archive_mtime is not None and abs(latest_extracted - archive_mtime) < 300:
+                return None
+
+            return latest_extracted
 
         # 初始化条目
         entry = {}
+        group1_files = []
+        group2_files = []
         group1_latest = None
         group2_latest = None
 
@@ -593,8 +625,16 @@ def build_file_associations(
                 if file_path.suffix.lower() in ('.zip', '.rar', '.7z'):
                     group2_latest = get_latest_extracted_mtime(group2_files, file_path.name)
 
-        # 如果 group1 和 group2 都是压缩文件，并且 group1 的解压文件最新时间早于 group2，则记录到问题列表
+        # 如果 group1 和 group2 都是压缩文件，并且 group1 的解压文件最新时间早于 group2（时间差超过阈值），则记录到问题列表
-        if group1_latest is not None and group2_latest is not None and group1_latest < group2_latest:
+        # 或者如果解压出来的文件中包含音视频文件，也记录到问题列表
+        TIME_DIFF_THRESHOLD = 30  # 时间差阈值（秒），避免将 zip 文件和解压文件时间相近的误判为问题组
+        time_diff_condition = (
+            group1_latest is not None
+            and group2_latest is not None
+            and group1_latest < group2_latest
+            and (group2_latest - group1_latest) > TIME_DIFF_THRESHOLD
+        )
+        if time_diff_condition:
             problematic_groups.append({
                 "row_index": i,
                 "group1_latest_extracted_mtime": group1_latest,
@@ -750,6 +790,7 @@ def main():
         print(f"\n===== 批量处理完成 =====")
         print(f"成功：{success_count}, 失败：{fail_count}")
         print(f"问题组报告已保存到：{report_file}")
+        print(len(all_problem_groups))
         return
 
 if __name__ == "__main__":