"""
Utilities for working with PDF files
"""
import PyPDF2
import io
import os
from config import get_settings
import logging

settings = get_settings()
logger = logging.getLogger(__name__)

def extract_text_from_pdf(pdf_path):
    """
    Extracts text from a PDF file.

    Args:
        pdf_path (str): The path to the PDF file.

    Returns:
        str: The extracted text. Returns an empty string if extraction fails.
    """
    text = ""
    try:
        with open(pdf_path, 'rb') as file:
            reader = PyPDF2.PdfReader(file)
            for page_num in range(len(reader.pages)):
                page = reader.pages[page_num]
                text += page.extract_text()
                
        if not text.strip():
            logger.warning(f"Extracted empty text from PDF: {pdf_path}")
        logger.info(f"Extracted text are {text}")
        return text
        
    except Exception as e:
        logger.error(f"Error extracting text from PDF: {e}")
        return ""  # Return empty string on failure

def save_temp_pdf(file_data, filename="temp.pdf"):
    """
    Save uploaded file data to a temporary PDF file
    
    Args:
        file_data: The binary data of the file
        filename: The name to save the file as
        
    Returns:
        Path to the saved file
    """
    # Use the /app/data directory for saving temporary files
    filepath = os.path.join("/app/data", filename)
    try:
        with open(filepath, 'wb') as f:
            f.write(file_data)
        return filepath
    except Exception as e:
        logger.error(f"Error saving temporary PDF: {e}")
        raise