dynamic history data

app.py

@@ -52,23 +52,33 @@ ACTION_MAP = {
 log_history = []
 initial_df_abn = pd.DataFrame(columns=["timestamp", "ip_address", "cookie_id", "account", "role", "action", "status"])
 
-# --- 1. 載入模型與歷史資料 ---
+# --- 1. 載入模型與歷史資料 (結合 logger_service 雲端同步) ---
 try:
     le_action = joblib.load('le_action.pkl')
     le_ip = joblib.load('le_ip.pkl')
     
-    baseline_df = pd.read_csv('baseline_logs.csv')
+    # 🌟 核心升級：啟動時直接從 Hugging Face 雲端拉取最新動態歷史資料庫
+    print("🔄 正在從 Hugging Face 雲端同步最新動態歷史資料...")
+    baseline_df = logger_service.sync_from_hf()
+    
+    # 防呆機制：如果雲端資料庫為空或下載失敗，退回使用本地端檔案
+    if baseline_df.empty and os.path.exists('baseline_logs.csv'):
+        print("⚠️ 雲端資料庫為空或讀取失敗，改用本地端 baseline_logs.csv")
+        baseline_df = pd.read_csv('baseline_logs.csv')
+        
     baseline_df['timestamp'] = pd.to_datetime(baseline_df['timestamp'])
     
+    # 這裡的統計數據現在會包含雲端的最新總數與異常數
     global_stats["total_count"] = len(baseline_df)
     global_stats["abnormal_count"] = baseline_df[baseline_df['status'].str.contains("異常", na=False)].shape[0]
     print(f"📊 統計初始化：總監測量 {global_stats['total_count']}, 異常數 {global_stats['abnormal_count']}")
 
-    # 🌟 修正點 1：將 Timestamp 強制轉為字串，避免前端 JS 崩潰卡讀取
+    # 確保前端表格吃的是正確的字串格式，並且直接抓取雲端最新的 20 筆作為預設顯示
     display_df = baseline_df.sort_values(by='timestamp', ascending=False).head(20).copy()
     display_df['timestamp'] = display_df['timestamp'].dt.strftime('%Y-%m-%d %H:%M:%S')
     log_history = display_df.to_dict('records')
     
+    # 異常清單也會直接從雲端最新的資料中篩選出來
     initial_abnormal_logs = [log for log in log_history if "異常" in str(log.get("status", ""))]
     if initial_abnormal_logs:
         initial_df_abn = pd.DataFrame(initial_abnormal_logs)
@@ -86,7 +96,7 @@ try:
     ))
     
     AI_READY = True
-    print("✅ AI 模組與歷史基準資料載入成功！")
+    print("✅ AI 模組與動態歷史基準資料載入成功！")
 except Exception as e:
     AI_READY = False
     global_stats["total_count"] = 0
@@ -116,7 +126,7 @@ def get_dashboard_html():
         <div class="stat-card card-total">
             <div class="card-icon">📊</div>
             <div class="card-content">
-                <div class="card-label">總監測量 (預警流量)</div>
+                <div class="card-label">總監測量 (包含雲端資料庫)</div>
                 <div class="card-value">{total:,} <span class="card-unit">筆 Log</span></div>
                 <div class="card-sub-text">自系統啟動起統計 (+今日即時)</div>
             </div>
@@ -456,7 +466,7 @@ custom_css = """
 
 with gr.Blocks(title="模擬校園入口與資安防護系統") as demo:
 
-    # 🌟 修正點 2：建立隱形的 State，作為 Dataframe 的獨立資料載體 (解耦)
+    # 確保 State 初始化時能抓到剛從雲端下載的最新資料
     store_df_all = gr.State(value=pd.DataFrame(log_history))
     store_df_abn = gr.State(value=initial_df_abn)
 
@@ -472,7 +482,6 @@ with gr.Blocks(title="模擬校園入口與資安防護系統") as demo:
             custom_time_input = gr.Textbox(label="輸入自訂時間", placeholder="格式: YYYY-MM-DD HH:MM:SS", value="2026-03-17 03:00:00", visible=False)
             gr.Markdown("---")
             gr.Markdown("### 📊 即時 Log 與 AI 判定區")
-            # 🌟 指定吃 Pandas Dataframe 以維持最穩定的序列化
             log_display = gr.Dataframe(value=pd.DataFrame(log_history), headers=["timestamp", "ip_address", "cookie_id", "account", "role", "action", "status"], datatype=["str", "str", "str", "str", "str", "str", "str"], interactive=False, wrap=True)
 
         with gr.Column(scale=2):
@@ -585,7 +594,6 @@ with gr.Blocks(title="模擬校園入口與資安防護系統") as demo:
                                     with gr.Row():
                                         t_vdesk_norm = gr.Button("✅ 正常: 軟體雲/WebMail (03-22 18:00)", size="sm"); t_vdesk_anom = gr.Button("⚠️ 異常: 軟體雲/WebMail (08-10 00:00)", size="sm")
 
-    # --- 🌟 修正點 3：綁定 State 更新到實體的 Dataframe (確保 DOM 渲染完畢後才餵入資料) ---
     def update_dataframes(df_all, df_abn):
         return gr.update(value=df_all), gr.update(value=df_abn)
         
@@ -600,7 +608,6 @@ with gr.Blocks(title="模擬校園入口與資安防護系統") as demo:
     
     weight_inputs = [overall_weight, time_weight, ip_weight, device_weight]
     
-    # 🎯 把輸出目標從實體 Dataframe 改為背後的 State
     update_outputs = [main_router, role_tabs, login_msg, welcome_text, store_df_all, store_df_abn, abnormal_log_input]
     
     login_btn.click(
@@ -636,7 +643,7 @@ with gr.Blocks(title="模擬校園入口與資安防護系統") as demo:
         btn.click(
             fn=lambda ip, c, acc, t_mode, t_custom, ow, tw, iw, dw, n=action_name: simulate_click(ip, c, acc, n, t_mode, t_custom, ow, tw, iw, dw), 
             inputs=[mock_ip, mock_cookie, acc_input, time_mode, custom_time_input] + weight_inputs, 
-            outputs=[store_df_all, store_df_abn, abnormal_log_input] # 🎯 同步改為輸出給 State
+            outputs=[store_df_all, store_df_abn, abnormal_log_input] 
         )
         
     test_mapping = [
@@ -657,7 +664,7 @@ with gr.Blocks(title="模擬校園入口與資安防護系統") as demo:
         btn.click(
             fn=lambda ip, c, acc, ow, tw, iw, dw, n=action_name, t_str=test_time_str: test_anomaly(ip, c, acc, n, t_str, ow, tw, iw, dw),
             inputs=[mock_ip, mock_cookie, acc_input, overall_weight, time_weight, ip_weight, device_weight],
-            outputs=[store_df_all, store_df_abn, abnormal_log_input] # 🎯 同步改為輸出給 State
+            outputs=[store_df_all, store_df_abn, abnormal_log_input] 
         )
 
 if __name__ == "__main__":