Update app.py

app.py

@@ -12,12 +12,6 @@ from concurrent.futures import ThreadPoolExecutor
 from functools import partial
 import time
 from datetime import datetime
-import openpyxl
-from openpyxl import Workbook
-from openpyxl.utils import get_column_letter
-from io import BytesIO
-import base64
-import hashlib
 
 # Configure logging
 logging.basicConfig(level=logging.INFO)
@@ -32,26 +26,6 @@ CONFIDENCE_THRESHOLD = 0.65
 BATCH_SIZE = 8  # Reduced batch size for CPU
 MAX_WORKERS = 4  # Number of worker threads for processing
 
-# Get password hash from environment variable (more secure)
-ADMIN_PASSWORD_HASH = os.environ.get('ADMIN_PASSWORD_HASH')
-
-if not ADMIN_PASSWORD_HASH:
-    ADMIN_PASSWORD_HASH = "5e22d1ed71b273b1b2b5331f2d3e0f6cf34595236f201c6924d6bc81de27cdcb"
-
-# Excel file path for logs
-EXCEL_LOG_PATH = "/tmp/prediction_logs.xlsx"
-
-def is_admin_password(input_text: str) -> bool:
-    """
-    Check if the input text matches the admin password using secure hash comparison.
-    This prevents the password from being visible in the source code.
-    """
-    # Hash the input text
-    input_hash = hashlib.sha256(input_text.strip().encode()).hexdigest()
-    
-    # Compare hashes (constant-time comparison to prevent timing attacks)
-    return input_hash == ADMIN_PASSWORD_HASH
-
 class TextWindowProcessor:
     def __init__(self):
         try:
@@ -354,133 +328,8 @@ 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 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:
-        # 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 to Excel: {str(e)}")
-        return False
-
-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 admin password using secure comparison
-    if is_admin_password(text.strip()):
-        # Return logs instead of analysis
-        base64_data = get_logs_as_base64()
-        logs_timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
-        logs_filename = f"prediction_logs_{logs_timestamp}.xlsx"
-        
-        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\nFile: {EXCEL_LOG_PATH}"
-        )
-        
     # Start timing for normal analysis
     start_time = time.time()
     
@@ -508,16 +357,6 @@ def analyze_text(text: str, mode: str, classifier: TextClassifier) -> tuple:
         # Calculate execution time in milliseconds
         execution_time = (time.time() - start_time) * 1000
         
-        # Log the prediction data
-        log_prediction_data(
-            input_text=text, 
-            word_count=word_count, 
-            prediction=result['prediction'], 
-            confidence=result['confidence'],
-            execution_time=execution_time,
-            mode=original_mode
-        )
-        
         return (
             text,  # No highlighting in quick mode
             "Quick scan mode - no sentence-level analysis available",
@@ -544,16 +383,6 @@ def analyze_text(text: str, mode: str, classifier: TextClassifier) -> tuple:
         # Calculate execution time in milliseconds
         execution_time = (time.time() - start_time) * 1000
         
-        # Log the prediction data
-        log_prediction_data(
-            input_text=text, 
-            word_count=word_count, 
-            prediction=final_pred['prediction'],
-            confidence=final_pred['confidence'],
-            execution_time=execution_time,
-            mode=original_mode
-        )
-        
         return (
             analysis['highlighted_text'],
             "\n".join(detailed_analysis),
@@ -609,5 +438,4 @@ if __name__ == "__main__":
         server_name="0.0.0.0",
         server_port=7860,
         share=True
-    )
-
+    )