src/dataloader.py

import PyPDF2
import os
from src.logger import setup_logger

logger = setup_logger(__name__)

def dataloader(data_path):
    pdf_path = os.path.join('assets', 'data', data_path)
    
    text = []
    
    try:
        logger.info(f"Attempting to read PDF from: {pdf_path}")
        with open(pdf_path, 'rb') as file:
            pdf_reader = PyPDF2.PdfReader(file)
            total_pages = len(pdf_reader.pages)
            logger.info(f"PDF loaded successfully. Total pages: {total_pages}")
            
            for i, page in enumerate(pdf_reader.pages, 1):
                try:
                    page_text = page.extract_text()
                    text.append(page_text)
                    logger.info(f"Extracted text from page {i}/{total_pages}")
                except Exception as e:
                    logger.error(f"Error extracting text from page {i}: {str(e)}")
        
        logger.info("PDF text extraction completed")
        return text
    except FileNotFoundError:
        logger.error(f"PDF file not found at {pdf_path}")
        return []
    except Exception as e:
        logger.error(f"An error occurred while reading the PDF: {str(e)}")
        return []