Fix issues 3

services/sales/app/services/data_import_service.py

@@ -865,34 +865,65 @@ class DataImportService:
         return mapping
     
     def _parse_date(self, date_str: str) -> Optional[datetime]:
-        """Enhanced date parsing with pandas and multiple format support"""
+        """Enhanced date parsing with explicit format handling for CSV dates"""
         if not date_str or str(date_str).lower() in ['nan', 'null', 'none']:
             return None
         
         date_str = str(date_str).strip()
         
-        # Try pandas first (most robust)
+        # For CSV format like "2024/10/01", try specific formats first to avoid ambiguity
+        # Priority order: YYYY/MM/DD (most likely for machine-generated data)
+        priority_formats = [
+            '%Y/%m/%d',     # 2024/10/01 (October 1, 2024) - most likely for CSV exports
+            '%Y-%m-%d',     # 2024-10-01 
+            '%d/%m/%Y',     # 01/10/2024 (European format)
+            '%m/%d/%Y',     # 10/01/2024 (US format)
+        ]
+        
+        # Try priority formats first
+        for fmt in priority_formats:
+            try:
+                parsed_dt = datetime.strptime(date_str, fmt)
+                if parsed_dt.tzinfo is None:
+                    parsed_dt = parsed_dt.replace(tzinfo=timezone.utc)
+                logger.debug(f"Successfully parsed date '{date_str}' using format '{fmt}' -> {parsed_dt}")
+                return parsed_dt
+            except ValueError:
+                continue
+        
+        # Try pandas as fallback with explicit format inference
         try:
-            parsed_dt = pd.to_datetime(date_str, dayfirst=True)
+            # For YYYY/MM/DD format, disable dayfirst to prevent misinterpretation
+            if '/' in date_str and len(date_str.split('/')[0]) == 4:
+                # Looks like YYYY/MM/DD format, so don't use dayfirst
+                parsed_dt = pd.to_datetime(date_str, dayfirst=False)
+            else:
+                # For other formats, use dayfirst=True for European-style dates
+                parsed_dt = pd.to_datetime(date_str, dayfirst=True)
+                
             if hasattr(parsed_dt, 'to_pydatetime'):
                 parsed_dt = parsed_dt.to_pydatetime()
             
             if parsed_dt.tzinfo is None:
                 parsed_dt = parsed_dt.replace(tzinfo=timezone.utc)
             
+            logger.debug(f"Successfully parsed date '{date_str}' using pandas -> {parsed_dt}")
             return parsed_dt
-        except Exception:
+        except Exception as e:
+            logger.debug(f"Pandas date parsing failed for '{date_str}': {e}")
             pass
         
-        # Try specific formats as fallback
+        # Try remaining formats as last fallback
         for fmt in self.DATE_FORMATS:
-            try:
-                parsed_dt = datetime.strptime(date_str, fmt)
-                if parsed_dt.tzinfo is None:
-                    parsed_dt = parsed_dt.replace(tzinfo=timezone.utc)
-                return parsed_dt
-            except ValueError:
-                continue
+            if fmt not in priority_formats:  # Skip already tried formats
+                try:
+                    parsed_dt = datetime.strptime(date_str, fmt)
+                    if parsed_dt.tzinfo is None:
+                        parsed_dt = parsed_dt.replace(tzinfo=timezone.utc)
+                    logger.debug(f"Successfully parsed date '{date_str}' using fallback format '{fmt}' -> {parsed_dt}")
+                    return parsed_dt
+                except ValueError:
+                    continue
         
         logger.warning(f"Could not parse date: {date_str}")
         return None