process_file.py

"""
Utility function for processing files with OCR in the Historical OCR Workshop app.
"""

import os
import tempfile
from pathlib import Path
from datetime import datetime

def process_file(uploaded_file, use_vision=True, processor=None, custom_prompt=None):
    """Process the uploaded file and return the OCR results
    
    Args:
        uploaded_file: The uploaded file to process
        use_vision: Whether to use vision model
        processor: StructuredOCR processor (if None, it will be imported)
        custom_prompt: Optional additional instructions for the model
        
    Returns:
        dict: The OCR results
    """
    # Import the processor if not provided
    if processor is None:
        from structured_ocr import StructuredOCR
        processor = StructuredOCR()
    
    # Save the uploaded file to a temporary file
    with tempfile.NamedTemporaryFile(delete=False, suffix=Path(uploaded_file.name).suffix) as tmp:
        tmp.write(uploaded_file.getvalue())
        temp_path = tmp.name
    
    try:
        # Determine file type from extension
        file_ext = Path(uploaded_file.name).suffix.lower()
        file_type = "pdf" if file_ext == ".pdf" else "image"
        
        # Get file size in MB
        file_size_mb = os.path.getsize(temp_path) / (1024 * 1024)
        
        # Process the file with file size information for automatic page limiting
        result = processor.process_file(
            temp_path, 
            file_type=file_type, 
            use_vision=use_vision, 
            file_size_mb=file_size_mb,
            custom_prompt=custom_prompt
        )
        
        # Add processing metadata
        result.update({
            "file_name": uploaded_file.name,
            "processed_at": datetime.now().isoformat(),
            "file_size_mb": round(file_size_mb, 2),
            "use_vision": use_vision
        })
        
        # No longer needed - removing confidence score
        
        return result
    except Exception as e:
        return {
            "error": str(e),
            "file_name": uploaded_file.name
        }
    finally:
        # Clean up the temporary file
        if os.path.exists(temp_path):
            os.unlink(temp_path)