src/services/file_service.py

from fastapi import UploadFile, HTTPException
import os
from typing import Dict
import logging

logger = logging.getLogger(__name__)


class FileService:
    """Service to handle file uploads and text extraction"""
    
    ALLOWED_EXTENSIONS = {'.txt'}
    MAX_FILE_SIZE = 10 * 1024 * 1024  # 10 MB
    
    @staticmethod
    def validate_file(file: UploadFile) -> None:
        """
        Validate uploaded file
        
        Args:
            file: Uploaded file object
            
        Raises:
            HTTPException: If file is invalid
        """
        # Check if file exists
        if not file:
            raise HTTPException(status_code=400, detail="No file provided")
        
        # Check file extension
        file_ext = os.path.splitext(file.filename)[1].lower()
        if file_ext not in FileService.ALLOWED_EXTENSIONS:
            raise HTTPException(
                status_code=400, 
                detail=f"Invalid file type. Only {', '.join(FileService.ALLOWED_EXTENSIONS)} files are allowed"
            )
    
    @staticmethod
    async def extract_text_from_file(file: UploadFile) -> Dict[str, any]:
        """
        Extract text content from uploaded file
        
        Args:
            file: Uploaded file object
            
        Returns:
            Dictionary containing extracted text and metadata
        """
        try:
            # Validate file
            FileService.validate_file(file)
            
            # Read file content
            content = await file.read()
            
            # Check file size
            file_size = len(content)
            if file_size > FileService.MAX_FILE_SIZE:
                raise HTTPException(
                    status_code=400,
                    detail=f"File too large. Maximum size is {FileService.MAX_FILE_SIZE / (1024*1024)} MB"
                )
            
            # Decode text
            try:
                text = content.decode('utf-8')
            except UnicodeDecodeError:
                try:
                    text = content.decode('latin-1')
                except Exception as e:
                    raise HTTPException(
                        status_code=400,
                        detail="Unable to decode file. Please ensure it's a valid text file"
                    )
            
            # Validate extracted text
            if not text.strip():
                raise HTTPException(
                    status_code=400,
                    detail="File is empty or contains no readable text"
                )
            
            if len(text.strip()) < 10:
                raise HTTPException(
                    status_code=400,
                    detail="Extracted text is too short. Please provide more detailed provider notes"
                )
            
            logger.info(f"Successfully extracted {len(text)} characters from {file.filename}")
            
            return {
                "text": text,
                "filename": file.filename,
                "file_size": file_size,
                "text_length": len(text)
            }
            
        except HTTPException:
            raise
        except Exception as e:
            logger.error(f"Error extracting text from file: {str(e)}")
            raise HTTPException(
                status_code=500,
                detail=f"Error processing file: {str(e)}"
            )


# Singleton instance
file_service = FileService()