Checking onboardin flow - fix 1

services/data/app/services/data_import_service.py

@@ -10,11 +10,11 @@ import base64
 import openpyxl
 import pandas as pd
 from typing import Dict, Any, List, Optional, Union
-from datetime import datetime, timedelta
 from sqlalchemy.ext.asyncio import AsyncSession
 import structlog
 import re
 from pathlib import Path
+from datetime import datetime, timezone
 
 from app.services.sales_service import SalesService
 from app.schemas.sales import SalesDataCreate
@@ -633,7 +633,7 @@ class DataImportService:
     
     @staticmethod
     def _parse_date(date_str: str) -> Optional[datetime]:
-        """Parse date string with multiple format attempts"""
+        """Parse date string with multiple format attempts - FIXED for timezone"""
         if not date_str or str(date_str).lower() in ['nan', 'null', 'none']:
             return None
         
@@ -642,36 +642,61 @@ class DataImportService:
         
         # Try pandas first (handles most formats automatically)
         try:
-            return pd.to_datetime(date_str, dayfirst=True)
-        except:
+            parsed_dt = pd.to_datetime(date_str, dayfirst=True)
+            
+            # ✅ CRITICAL FIX: Convert pandas Timestamp to timezone-aware datetime
+            if hasattr(parsed_dt, 'to_pydatetime'):
+                # Convert pandas Timestamp to Python datetime
+                parsed_dt = parsed_dt.to_pydatetime()
+            
+            # ✅ CRITICAL FIX: Ensure timezone-aware
+            if parsed_dt.tzinfo is None:
+                # Assume UTC for timezone-naive dates
+                parsed_dt = parsed_dt.replace(tzinfo=timezone.utc)
+            
+            return parsed_dt
+            
+        except Exception:
             pass
         
         # Try specific formats
         for fmt in DataImportService.DATE_FORMATS:
             try:
-                return datetime.strptime(date_str, fmt)
+                parsed_dt = datetime.strptime(date_str, fmt)
+                
+                # ✅ CRITICAL FIX: Ensure timezone-aware
+                if parsed_dt.tzinfo is None:
+                    parsed_dt = parsed_dt.replace(tzinfo=timezone.utc)
+                
+                return parsed_dt
+                
             except ValueError:
                 continue
         
         # Try extracting numbers and common patterns
         try:
             # Look for patterns like dd/mm/yyyy or dd-mm-yyyy
-            date_pattern = re.search(r'(\d{1,2})[/\-.](\d{1,2})[/\-.](\d{2,4})', date_str)
+            date_pattern = re.search(r'(\d{1,2})[/\-.](\d{1,2})[/\-.](\d{4})', date_str)
             if date_pattern:
                 day, month, year = date_pattern.groups()
                 
-                # Convert 2-digit year to 4-digit
-                year = int(year)
-                if year < 50:
-                    year += 2000
-                elif year < 100:
-                    year += 1900
+                # Try dd/mm/yyyy format (European style)
+                try:
+                    parsed_dt = datetime(int(year), int(month), int(day))
+                    return parsed_dt.replace(tzinfo=timezone.utc)
+                except ValueError:
+                    pass
                 
-                return datetime(year, int(month), int(day))
-        except:
+                # Try mm/dd/yyyy format (US style)
+                try:
+                    parsed_dt = datetime(int(year), int(day), int(month))
+                    return parsed_dt.replace(tzinfo=timezone.utc)
+                except ValueError:
+                    pass
+        
+        except Exception:
             pass
         
-        logger.warning(f"Could not parse date: {date_str}")
         return None
     
     @staticmethod