""" Utility functions for file processing status determination. """ from typing import Dict, List from sqlalchemy.orm import Session from app.models import FileProcessingStep, ProcessingLog from app.utils.step_manager import get_file_overall_status, get_step_summary def get_file_processing_status(db: Session, file_id: int) -> Dict: """ Get the processing status for a file by checking its processing steps. This function now queries the FileProcessingStep table instead of scanning logs. Args: db: Database session file_id: ID of the file Returns: dict with status, last_step, and has_errors """ # Use the new status table approach overall_status = get_file_overall_status(db, file_id) # Get the most recently updated step to determine last_step latest_step = ( db.query(FileProcessingStep) .filter(FileProcessingStep.file_id == file_id) .order_by(FileProcessingStep.updated_at.desc()) .first() ) return { "status": overall_status["status"], "last_step": latest_step.step_name if latest_step else None, "has_errors": overall_status["has_errors"], "total_steps": overall_status["total_steps"], } def get_files_processing_status(db: Session, file_ids: List[int]) -> Dict[int, Dict]: """ Get processing status for multiple files efficiently. Args: db: Database session file_ids: List of file IDs Returns: dict mapping file_id to status dict """ # Get all steps for these files in one query steps = db.query(FileProcessingStep).filter(FileProcessingStep.file_id.in_(file_ids)).all() # Group steps by file_id steps_by_file = {} for step in steps: if step.file_id not in steps_by_file: steps_by_file[step.file_id] = [] steps_by_file[step.file_id].append(step) # Compute status for each file result = {} for file_id in file_ids: file_steps = steps_by_file.get(file_id, []) if not file_steps: result[file_id] = {"status": "pending", "last_step": None, "has_errors": False, "total_steps": 0} else: # Compute overall status from steps total_steps = len(file_steps) completed_steps = sum(1 for s in file_steps if s.status == "success") failed_steps = sum(1 for s in file_steps if s.status == "failure") in_progress_steps = sum(1 for s in file_steps if s.status == "in_progress") skipped_steps = sum(1 for s in file_steps if s.status == "skipped") has_errors = failed_steps > 0 # Determine overall status if has_errors: status = "failed" elif in_progress_steps > 0: status = "processing" elif completed_steps + skipped_steps == total_steps: status = "completed" else: status = "pending" # Get last updated step latest_step = max(file_steps, key=lambda s: s.updated_at if s.updated_at else s.created_at) result[file_id] = { "status": status, "last_step": latest_step.step_name, "has_errors": has_errors, "total_steps": total_steps, } return result def _compute_status_from_logs(logs: List[ProcessingLog]) -> Dict: """ Compute processing status from a list of processing logs. DEPRECATED: This function is kept for backwards compatibility. New code should use the FileProcessingStep table instead. Args: logs: List of ProcessingLog objects (should be ordered by timestamp desc) Returns: dict with status, last_step, has_errors, and total_steps """ if not logs: return {"status": "pending", "last_step": None, "has_errors": False, "total_steps": 0} # Get the latest status for each unique step # Since logs are ordered by timestamp desc, the first occurrence is the latest latest_by_step = {} for log in logs: if log.step_name not in latest_by_step: latest_by_step[log.step_name] = log # Check for failures in latest statuses has_errors = any(log.status == "failure" for log in latest_by_step.values()) # Check if any step is currently in progress (based on latest status per step) in_progress = any(log.status == "in_progress" for log in latest_by_step.values()) # Get the overall latest log latest_log = logs[0] # Determine overall status if has_errors: status = "failed" elif in_progress: status = "processing" elif latest_log.status == "success": status = "completed" else: status = "pending" return {"status": status, "last_step": latest_log.step_name, "has_errors": has_errors, "total_steps": len(logs)}