Update app.py

app.py

@@ -12,29 +12,25 @@ class DataManager:
     def __init__(self, token=None):
         self.repo_id = "CIV3283/Data_Storage"
         self.branch = "data_branch"
+        self.token = token
         
-        # Use provided token first, otherwise get from environment variable
-        self.token = token or os.getenv('CIV3283_access')
-        
-        # Authenticate if token is available
+        # 如果提供了token，进行认证
         if self.token:
             try:
                 login(token=self.token)
-                print("✅ Authentication successful")
+                print("✅ 认证成功")
             except Exception as e:
-                print(f"❌ Authentication failed: {e}")
+                print(f"❌ 认证失败: {e}")
         
         self.api = HfApi(token=self.token)
         
     def get_available_files(self) -> Tuple[List[str], List[str]]:
-        """Get all available feedback and query files"""
+        """获取所有可用的feedback和query文件"""
         try:
-            # Try to get all files from repository
+            # 获取仓库中的所有文件
             repo_files = self.api.list_repo_files(
                 repo_id=self.repo_id,
-                revision=self.branch,
-                token=self.token,
-                repo_type="space"  # Explicitly specify this is a space
+                revision=self.branch
             )
             
             feedback_files = []
@@ -49,67 +45,48 @@ class DataManager:
             return sorted(feedback_files), sorted(query_files)
             
         except Exception as e:
-            print(f"❌ Error getting file list: {e}")
-            # If API call fails, try to generate possible filename list
-            return self._generate_possible_filenames()
-    
-    def _generate_possible_filenames(self) -> Tuple[List[str], List[str]]:
-        """Generate possible filename list as backup"""
-        feedback_files = []
-        query_files = []
-        
-        # Generate all possible filenames from 01 to 95
-        for i in range(1, 96):
-            student_id = f"{i:02d}"  # Format as two digits
-            feedback_file = f"CIV3283_Student_{student_id}_feedback_log.csv"
-            query_file = f"CIV3283_Student_{student_id}_query_log.csv"
-            feedback_files.append(feedback_file)
-            query_files.append(query_file)
-        
-        return feedback_files, query_files
+            print(f"Error getting files: {e}")
+            return [], []
     
     def download_and_read_csv(self, filename: str) -> pd.DataFrame:
-        """Download and read CSV file"""
+        """下载并读取CSV文件"""
         try:
-            # Download file to temporary location
+            # 下载文件到临时位置
             local_file = hf_hub_download(
                 repo_id=self.repo_id,
                 filename=filename,
                 revision=self.branch,
-                repo_type="space",
-                token=self.token,
                 cache_dir=tempfile.gettempdir()
             )
             
-            # Read CSV
+            # 读取CSV
             df = pd.read_csv(local_file)
             
-            # Ensure timestamp column exists and convert to datetime
+            # 确保timestamp列存在并转换为datetime
             if 'timestamp' in df.columns:
                 df['timestamp'] = pd.to_datetime(df['timestamp'])
             
             return df
             
         except Exception as e:
-            print(f"❌ Failed to read file {filename}: {e}")
-            # Return empty DataFrame rather than complete failure
+            print(f"Error reading {filename}: {e}")
             return pd.DataFrame()
     
     def filter_data_by_date(self, df: pd.DataFrame, start_date: str, end_date: str) -> pd.DataFrame:
-        """Filter data by date range"""
+        """根据日期范围筛选数据"""
         if df.empty or 'timestamp' not in df.columns:
             return df
         
         try:
-            # Convert input date strings
+            # 转换输入的日期字符串
             start_dt = pd.to_datetime(start_date)
             
-            if end_date == "now":
+            if end_date == "现在":
                 end_dt = pd.Timestamp.now()
             else:
-                end_dt = pd.to_datetime(end_date) + timedelta(days=1) - timedelta(seconds=1)  # Include full day
+                end_dt = pd.to_datetime(end_date) + timedelta(days=1) - timedelta(seconds=1)  # 包含整天
             
-            # Filter data
+            # 筛选数据
             mask = (df['timestamp'] >= start_dt) & (df['timestamp'] <= end_dt)
             return df[mask]
             
@@ -118,21 +95,21 @@ class DataManager:
             return df
     
     def process_files(self, file_type: str, start_date: str, end_date: str) -> Tuple[str, str, str]:
-        """Process files and generate download content"""
+        """处理文件并生成下载内容"""
         feedback_files, query_files = self.get_available_files()
         
         result_data = []
         file_info = []
         total_records = 0
         
-        # Determine files to process based on selected file type
+        # 根据选择的文件类型确定要处理的文件
         files_to_process = []
-        if file_type in ["Feedback Files", "Both"]:
+        if file_type in ["反馈文件", "两者都要"]:
             files_to_process.extend([(f, "feedback") for f in feedback_files])
-        if file_type in ["Query Files", "Both"]:
+        if file_type in ["查询文件", "两者都要"]:
             files_to_process.extend([(f, "query") for f in query_files])
         
-        # Process each file
+        # 处理每个文件
         for filename, ftype in files_to_process:
             df = self.download_and_read_csv(filename)
             if not df.empty:
@@ -144,56 +121,41 @@ class DataManager:
                     result_data.append(filtered_df)
                     total_records += filtered_count
                 
-                file_info.append(f"{filename}: {original_count} records → {filtered_count} matching criteria")
+                file_info.append(f"{filename}: {original_count}条记录 → {filtered_count}条符合条件")
         
-        # Combine all data
+        # 合并所有数据
         if result_data:
             combined_df = pd.concat(result_data, ignore_index=True)
             
-            # Generate CSV content
+            # 生成CSV内容
             csv_buffer = io.StringIO()
             combined_df.to_csv(csv_buffer, index=False, encoding='utf-8')
             csv_content = csv_buffer.getvalue()
             
-            # Generate filename with type and date info
-            end_date_str = "now" if end_date == "now" else end_date
-            type_str = file_type.lower().replace(" ", "_")
-            filename = f"CIV3283_data_export_{type_str}_{start_date}_to_{end_date_str}.csv"
+            # 生成文件名
+            end_date_str = "现在" if end_date == "现在" else end_date
+            filename = f"CIV3283_数据导出_{file_type}_{start_date}_to_{end_date_str}.csv"
             
-            # Generate status info
-            status = f"✅ Successfully processed {len(files_to_process)} files\n"
-            status += f"📊 Total records found: {total_records}\n"
-            status += f"📅 Date range: {start_date} to {end_date_str}\n\n"
-            status += "File details:\n" + "\n".join(file_info)
+            # 生成状态信息
+            status = f"✅ 成功处理 {len(files_to_process)} 个文件\n"
+            status += f"📊 总共找到 {total_records} 条符合条件的记录\n"
+            status += f"📅 时间范围: {start_date} 到 {end_date_str}\n\n"
+            status += "文件详情:\n" + "\n".join(file_info)
             
             return csv_content, filename, status
         else:
-            return "", "", "❌ No matching data found"
-
-# Global variable to store data manager
-data_manager = None
+            return "", "", "❌ 没有找到符合条件的数据"
 
-def initialize_data_manager(hf_token=None):
-    """Initialize data manager"""
-    global data_manager
-    data_manager = DataManager(token=hf_token)
-    return data_manager
+# 初始化数据管理器
+data_manager = DataManager()
 
-def process_and_download(file_type, start_date, end_date, hf_token):
-    """Process request and return download file"""
+def process_and_download(file_type, start_date, end_date):
+    """处理请求并返回下载文件"""
     try:
-        # Ensure data manager is initialized
-        global data_manager
-        env_token = os.getenv('CIV3283_access')
-        current_token = hf_token or env_token
-        
-        if data_manager is None or data_manager.token != current_token:
-            data_manager = initialize_data_manager(current_token)
-        
         csv_content, filename, status = data_manager.process_files(file_type, start_date, end_date)
         
         if csv_content:
-            # Create temporary file
+            # 创建临时文件
             temp_file = tempfile.NamedTemporaryFile(mode='w', suffix='.csv', delete=False, encoding='utf-8')
             temp_file.write(csv_content)
             temp_file.close()
@@ -203,35 +165,19 @@ def process_and_download(file_type, start_date, end_date, hf_token):
             return status, None, None
             
     except Exception as e:
-        return f"❌ Error occurred during processing: {str(e)}", None, None
+        return f"❌ 处理过程中出现错误: {str(e)}", None, None
 
-def get_file_summary(hf_token=None):
-    """Get file overview"""
+def get_file_summary():
+    """获取文件概览"""
     try:
-        # If not initialized or token changed, reinitialize
-        global data_manager
-        env_token = os.getenv('CIV3283_access')
-        current_token = hf_token or env_token
-        
-        if data_manager is None or data_manager.token != current_token:
-            data_manager = initialize_data_manager(current_token)
-        
         feedback_files, query_files = data_manager.get_available_files()
-        summary = f"📁 Currently available files:\n"
-        summary += f"   Feedback files: {len(feedback_files)}\n"
-        summary += f"   Query files: {len(query_files)}\n"
-        summary += f"   Total: {len(feedback_files) + len(query_files)} files"
-        
-        if env_token:
-            summary += f"\n✅ Authenticated using environment variable CIV3283_access"
-        elif hf_token:
-            summary += f"\n✅ Authenticated using manual token input"
-        else:
-            summary += f"\n⚠️  No authentication token found (may not access private repositories)"
-            
+        summary = f"📁 当前可用文件:\n"
+        summary += f"   反馈文件: {len(feedback_files)} 个\n"
+        summary += f"   查询文件: {len(query_files)} 个\n"
+        summary += f"   总计: {len(feedback_files) + len(query_files)} 个文件"
         return summary
     except Exception as e:
-        return f"❌ Failed to get file list: {str(e)}"
+        return f"❌ 获取文件列表失败: {str(e)}"
 
 # 创建Gradio界面
 def create_interface():
@@ -239,41 +185,18 @@ def create_interface():
         gr.Markdown("# 🗃️ CIV3283 数据存储管理器")
         gr.Markdown("从 Hugging Face Space 的 data_branch 分支整理和下载学生数据")
         
-        # 认证部分
-        with gr.Row():
-            with gr.Column(scale=3):
-                hf_token = gr.Textbox(
-                    label="🔐 Hugging Face Token (可选)",
-                    placeholder="hf_xxxxxxxxxxxx",
-                    type="password",
-                    info="可选：手动输入token，留空将使用环境变量 CIV3283_access"
-                )
-            with gr.Column(scale=1):
-                gr.Markdown(f"""
-                **环境变量状态:**
-                {'✅ CIV3283_access 已设置' if os.getenv('CIV3283_access') else '❌ CIV3283_access 未找到'}
-                """)
-
-        
         # 文件概览
         with gr.Row():
             file_summary = gr.Textbox(
                 label="📊 文件概览",
-                value="点击刷新按钮获取文件列表",
+                value=get_file_summary(),
                 interactive=False,
-                max_lines=6
+                max_lines=5
             )
             refresh_btn = gr.Button("🔄 刷新文件列表", variant="secondary")
         
-        # 自动刷新一次（使用环境变量）
-        demo.load(
-            fn=lambda: get_file_summary(None),
-            outputs=file_summary
-        )
-        
         refresh_btn.click(
             fn=get_file_summary,
-            inputs=[hf_token],
             outputs=file_summary
         )
         
@@ -317,11 +240,6 @@ def create_interface():
         # 使用说明
         with gr.Accordion("📖 使用说明", open=False):
             gr.Markdown("""
-            ### 认证说明
-            - **环境变量优先**: 系统会自动使用环境变量 `CIV3283_access` 中的token
-            - **手动覆盖**: 如果需要使用不同的token，可以在上方手动输入
-            - **获取token**: 如果需要新token，访问 https://huggingface.co/settings/tokens
-            
             ### 功能说明
             1. **文件类型选择**: 选择要导出的数据类型
                - 查询文件: 包含搜索信息和查询响应
@@ -341,19 +259,18 @@ def create_interface():
             - 时间戳格式: 2025-06-16 08:55:33
             - 导出的数据保持原始顺序，不进行时间排序
             - 每次处理会显示详细的文件统计信息
-            - 如果无法访问仓库API，系统会尝试预设的文件名列表
             """)
         
         # 绑定处理函数
         process_btn.click(
             fn=process_and_download,
-            inputs=[file_type, start_date, end_date, hf_token],
+            inputs=[file_type, start_date, end_date],
             outputs=[status_box, download_file, gr.State()]
         )
     
     return demo
 
-# Launch application
+# 启动应用
 if __name__ == "__main__":
     demo = create_interface()
     demo.launch(