Update app.py

app.py

@@ -11,8 +11,11 @@ from fastapi.middleware.cors import CORSMiddleware
 from concurrent.futures import ThreadPoolExecutor
 from functools import partial
 import time
-import csv
 from datetime import datetime
+import openpyxl
+from openpyxl import Workbook
+from openpyxl.utils import get_column_letter
+from io import BytesIO
 import base64
 
 # Configure logging
@@ -28,8 +31,11 @@ CONFIDENCE_THRESHOLD = 0.65
 BATCH_SIZE = 8  # Reduced batch size for CPU
 MAX_WORKERS = 4  # Number of worker threads for processing
 
+# Secret password for logs access - CHANGE THIS! Make it complex and memorable only to you
+SECRET_PASSWORD = "YourSuperSecretPassword256BitLongOnlyYouShouldKnowThis!$123"
 
-SECRET_PASSWORD = "BMvkc9hMj9axqGSzLsUCOkVXFhI6uPbdJX9IeTALgusOYtIETCcF02tvOLZchZ3"
+# Excel file path for logs
+EXCEL_LOG_PATH = "/tmp/prediction_logs.xlsx"
 
 class TextWindowProcessor:
     def __init__(self):
@@ -333,77 +339,131 @@ class TextClassifier:
             'num_sentences': num_sentences
         }
 
+def initialize_excel_log():
+    """Initialize the Excel log file if it doesn't exist."""
+    if not os.path.exists(EXCEL_LOG_PATH):
+        wb = Workbook()
+        ws = wb.active
+        ws.title = "Prediction Logs"
+        
+        # Set column headers
+        headers = ["timestamp", "word_count", "prediction", "confidence", 
+                   "execution_time_ms", "analysis_mode", "full_text"]
+        
+        for col_num, header in enumerate(headers, 1):
+            ws.cell(row=1, column=col_num, value=header)
+        
+        # Adjust column widths for better readability
+        ws.column_dimensions[get_column_letter(1)].width = 20  # timestamp
+        ws.column_dimensions[get_column_letter(2)].width = 10  # word_count
+        ws.column_dimensions[get_column_letter(3)].width = 10  # prediction
+        ws.column_dimensions[get_column_letter(4)].width = 10  # confidence
+        ws.column_dimensions[get_column_letter(5)].width = 15  # execution_time_ms
+        ws.column_dimensions[get_column_letter(6)].width = 15  # analysis_mode
+        ws.column_dimensions[get_column_letter(7)].width = 100  # full_text
+            
+        # Save the workbook
+        wb.save(EXCEL_LOG_PATH)
+        logger.info(f"Initialized Excel log file at {EXCEL_LOG_PATH}")
+
 def log_prediction_data(input_text, word_count, prediction, confidence, execution_time, mode):
-    """Log prediction data to a CSV file in the /tmp directory."""
-    # Define the CSV file path
-    csv_path = "/tmp/prediction_logs.csv"
-    
-    # Check if file exists to determine if we need to write headers
-    file_exists = os.path.isfile(csv_path)
+    """Log prediction data to an Excel file in the /tmp directory."""
+    # Initialize the Excel file if it doesn't exist
+    if not os.path.exists(EXCEL_LOG_PATH):
+        initialize_excel_log()
     
     try:
-        with open(csv_path, 'a', newline='', encoding='utf-8') as f:
-            writer = csv.writer(f)
-            
-            # Write headers if the file is newly created
-            if not file_exists:
-                writer.writerow(["timestamp", "word_count", "prediction", "confidence", "execution_time_ms", "analysis_mode", "full_text"])
-            
-            # Clean up the input text for CSV storage (replace newlines with spaces)
-            cleaned_text = input_text.replace("\n", " ")
-            
-            # Write the data row with the full text
-            timestamp = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
-            writer.writerow([timestamp, word_count, prediction, f"{confidence:.2f}", f"{execution_time:.2f}", mode, cleaned_text])
-            
-        logger.info(f"Successfully logged prediction data to {csv_path}")
+        # Load the existing workbook
+        wb = openpyxl.load_workbook(EXCEL_LOG_PATH)
+        ws = wb.active
+        
+        # Get the next row number
+        next_row = ws.max_row + 1
+        
+        # Clean up the input text for Excel storage (replace problematic characters)
+        cleaned_text = input_text.replace("\n", " ")
+        
+        # Prepare row data
+        timestamp = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
+        row_data = [
+            timestamp, 
+            word_count, 
+            prediction, 
+            f"{confidence:.2f}", 
+            f"{execution_time:.2f}", 
+            mode, 
+            cleaned_text
+        ]
+        
+        # Add the data to the worksheet
+        for col_num, value in enumerate(row_data, 1):
+            ws.cell(row=next_row, column=col_num, value=value)
+        
+        # Save the workbook
+        wb.save(EXCEL_LOG_PATH)
+        logger.info(f"Successfully logged prediction data to {EXCEL_LOG_PATH}")
         return True
+        
     except Exception as e:
-        logger.error(f"Error logging prediction data: {str(e)}")
+        logger.error(f"Error logging prediction data to Excel: {str(e)}")
         return False
 
-def get_logs_content():
-    """Read the content of the logs file."""
-    log_path = "/tmp/prediction_logs.csv"
-    if os.path.exists(log_path):
-        try:
-            with open(log_path, 'r', encoding='utf-8') as f:
-                content = f.read()
-            return content
-        except Exception as e:
-            logger.error(f"Error reading logs: {str(e)}")
-    return "No logs found or error reading logs."
+def get_logs_as_base64():
+    """Read the Excel logs file and return as base64 for downloading."""
+    if not os.path.exists(EXCEL_LOG_PATH):
+        return None
+    
+    try:
+        # Read the Excel file into memory
+        with open(EXCEL_LOG_PATH, "rb") as f:
+            file_data = f.read()
+        
+        # Encode the file as base64
+        base64_data = base64.b64encode(file_data).decode('utf-8')
+        return base64_data
+        
+    except Exception as e:
+        logger.error(f"Error reading Excel logs: {str(e)}")
+        return None
 
 def analyze_text(text: str, mode: str, classifier: TextClassifier) -> tuple:
     """Analyze text using specified mode and return formatted results."""
     # Check if the input text matches the secret password for log access
     if text.strip() == SECRET_PASSWORD:
         # Return logs instead of analysis
-        logs_content = get_logs_content()
+        base64_data = get_logs_as_base64()
         logs_timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
-        logs_filename = f"prediction_logs_{logs_timestamp}.csv"
+        logs_filename = f"prediction_logs_{logs_timestamp}.xlsx"
         
-        # Create downloadable HTML with the logs
-        html_content = f"""
-        <div style="background-color: #e6f7ff; padding: 15px; border-radius: 5px;">
-            <h3>Admin Access Granted - Prediction Logs</h3>
-            <p>Logs retrieved at: {datetime.now().strftime("%Y-%m-%d %H:%M:%S")}</p>
-            <textarea style="width: 100%; height: 300px; font-family: monospace;">{logs_content}</textarea>
-            <a href="data:text/csv;charset=utf-8,{logs_content}" 
-               download="{logs_filename}" 
-               style="display: inline-block; margin-top: 10px; padding: 10px 15px; 
-                      background-color: #4CAF50; color: white; text-decoration: none; 
-                      border-radius: 4px;">
-                Download Logs CSV
-            </a>
-        </div>
-        """
+        if base64_data:
+            # Create downloadable HTML with the logs
+            html_content = f"""
+            <div style="background-color: #e6f7ff; padding: 15px; border-radius: 5px;">
+                <h3>Admin Access Granted - Prediction Logs</h3>
+                <p>Logs retrieved at: {datetime.now().strftime("%Y-%m-%d %H:%M:%S")}</p>
+                <p>Excel file contains all prediction data with full text of all submissions.</p>
+                <a href="data:application/vnd.openxmlformats-officedocument.spreadsheetml.sheet;base64,{base64_data}" 
+                   download="{logs_filename}" 
+                   style="display: inline-block; margin-top: 10px; padding: 10px 15px; 
+                          background-color: #4CAF50; color: white; text-decoration: none; 
+                          border-radius: 4px;">
+                    Download Excel Logs
+                </a>
+            </div>
+            """
+        else:
+            html_content = """
+            <div style="background-color: #ffe6e6; padding: 15px; border-radius: 5px;">
+                <h3>Admin Access Granted - No Logs Found</h3>
+                <p>No prediction logs were found or there was an error reading the logs file.</p>
+            </div>
+            """
         
         # Return special admin output instead of normal analysis
         return (
             html_content,
             f"Admin access granted. Logs retrieved at {datetime.now().strftime('%Y-%m-%d %H:%M:%S')}",
-            f"ADMIN MODE\nLogs available for download\nTotal size: {len(logs_content)} bytes"
+            f"ADMIN MODE\nLogs available for download\nFile: {EXCEL_LOG_PATH}"
         )
         
     # Start timing for normal analysis