Update app.py

app.py

@@ -319,19 +319,29 @@ async def process_logs(file_obj, lab_site_filter, equipment_type_filter, date_ra
     start_time = time.time()
     try:
         if not file_obj and not current_file_path:
+            logging.warning("No file provided or cached.")
             return "No file uploaded.", pd.DataFrame(), None, '<p>No device cards available.</p>', None, None, None, None, "No anomalies detected.", "No AMC reminders.", "No insights generated.", None, last_modified_state, cached_df_state, cached_filtered_df_state, current_file_path
 
         file_path = file_obj.name if file_obj else current_file_path
-        current_modified_time = os.path.getmtime(file_path) if os.path.exists(file_path) else 0
+        if not os.path.exists(file_path):
+            logging.error(f"File path does not exist: {file_path}")
+            return "File not found.", pd.DataFrame(), None, '<p>No device cards available.</p>', None, None, None, None, "No anomalies detected.", "No AMC reminders.", "No insights generated.", None, last_modified_state, cached_df_state, cached_filtered_df_state, current_file_path
+
+        current_modified_time = os.path.getmtime(file_path)
+        df = None  # Initialize df to avoid undefined reference
 
         # Check if we can use cached filtered data
         if (last_modified_state == current_modified_time and 
             cached_filtered_df_state is not None and 
             file_path == current_file_path):
+            logging.info("Using cached filtered DataFrame")
             filtered_df = cached_filtered_df_state
         else:
-            if cached_df_state is None or current_modified_time != last_modified_state or file_path != current_file_path:
-                logging.info(f"Processing file: {file_path}")
+            # Load or use cached raw DataFrame
+            if (cached_df_state is None or 
+                current_modified_time != last_modified_state or 
+                file_path != current_file_path):
+                logging.info(f"Reading new CSV file: {file_path}")
                 if not file_path.endswith(".csv"):
                     return "Please upload a CSV file.", pd.DataFrame(), None, '<p>No device cards available.</p>', None, None, None, None, "", "", "", None, last_modified_state, cached_df_state, cached_filtered_df_state, file_path
 
@@ -347,7 +357,7 @@ async def process_logs(file_obj, lab_site_filter, equipment_type_filter, date_ra
                 df = pd.read_csv(file_path, dtype=dtypes)
                 missing_columns = [col for col in required_columns if col not in df.columns]
                 if missing_columns:
-                    return f"Missing columns: {missing_columns}", pd.DataFrame(), None, '<p>No device cards available.</p>', None, None, None, None, None, None, None, None, last_modified_state, cached_df_state, cached_filtered_df_state, file_path
+                    return f"Missing columns: {missing_columns}", pd.DataFrame(), None, '<p>No device cards available.</p>', None, None, None, None, None, None, None, None, last_modified_state, df, cached_filtered_df_state, file_path
 
                 df["timestamp"] = pd.to_datetime(df["timestamp"], errors='coerce')
                 df["amc_date"] = pd.to_datetime(df["amc_date"], errors='coerce')
@@ -356,6 +366,7 @@ async def process_logs(file_obj, lab_site_filter, equipment_type_filter, date_ra
                 if df.empty:
                     return "No data available.", pd.DataFrame(), None, '<p>No device cards available.</p>', None, None, None, None, None, None, None, None, last_modified_state, df, cached_filtered_df_state, file_path
             else:
+                logging.info("Using cached raw DataFrame")
                 df = cached_df_state
 
             # Apply filters
@@ -427,8 +438,9 @@ async def generate_pdf(summary, preview_html, usage_chart, device_cards, daily_l
         return None
 
 # Update filters
-def update_filters(file_path, cached_df_state):
-    if not file_path or not cached_df_state:
+def update_filters(current_file_path, cached_df_state):
+    if not current_file_path or not cached_df_state:
+        logging.warning("No file or cached DataFrame available for filter update")
         return gr.update(choices=['All'], value='All'), gr.update(choices=['All'], value='All')
     try:
         df = cached_df_state
@@ -510,9 +522,9 @@ try:
                         gr.Markdown("### Export Report")
                         pdf_output = gr.File(label="Download Status Report as PDF")
 
-        # Update filters when CSV is uploaded
+        # Update file path and filters when CSV is uploaded
         file_input.change(
-            fn=lambda file_obj, cached_df, file_path: (file_obj.name if file_obj else file_path, cached_df, file_path),
+            fn=lambda file_obj, cached_df, file_path: (file_obj.name if file_obj else file_path, cached_df, file_obj.name if file_obj else file_path),
             inputs=[file_input, cached_df_state, current_file_path],
             outputs=[current_file_path, cached_df_state, current_file_path],
             queue=False
@@ -521,6 +533,10 @@ try:
             inputs=[current_file_path, cached_df_state],
             outputs=[lab_site_filter, equipment_type_filter],
             queue=False
+        ).then(
+            fn=process_logs,
+            inputs=[file_input, lab_site_filter, equipment_type_filter, date_range_filter, last_modified_state, cached_df_state, cached_filtered_df_state, current_file_path],
+            outputs=[summary_output, preview_output, usage_chart_output, device_cards_output, daily_log_trends_output, weekly_uptime_output, anomaly_alerts_output, downtime_chart_output, anomaly_output, amc_output, insights_output, pdf_output, last_modified_state, cached_df_state, cached_filtered_df_state, current_file_path]
         )
 
         # Process logs on submit or filter change