Extract Structured Data from Equipment Warranty and Repair PDFs with Nougat and spaCy

"""
Production implementation for extracting structured data from equipment warranty and repair PDFs using spaCy.
Provides secure, scalable operations.
"""
from typing import Dict, Any, List
import os
import logging
import spacy
from PyPDF2 import PdfReader

# Logger setup for tracking application flow and errors
logging.basicConfig(level=logging.INFO)
logger = logging.getLogger(__name__)

class Config:
    """
    Configuration class to manage environment variables.
    """
    spacy_model: str = os.getenv('SPACY_MODEL', 'en_core_web_sm')
    pdf_directory: str = os.getenv('PDF_DIRECTORY', './pdfs')

# Initialize spaCy model
nlp = spacy.load(Config.spacy_model)

def validate_input(file_path: str) -> None:
    """
    Validate the input PDF file path.
    
    Args:
        file_path: Path to the PDF file
    Raises:
        ValueError: If the file path is invalid
    """
    if not os.path.isfile(file_path):
        raise ValueError(f'Invalid file path: {file_path}')
    logger.info(f'Validated file path: {file_path}')  # Log successful validation

def extract_text_from_pdf(file_path: str) -> str:
    """
    Extract text from the given PDF file.
    
    Args:
        file_path: Path to the PDF file
    Returns:
        Extracted text from the PDF
    Raises:
        Exception: If an error occurs during PDF reading
    """
    try:
        reader = PdfReader(file_path)
        text = ''.join(page.extract_text() for page in reader.pages)
        logger.info('Extracted text from PDF successfully.')
        return text
    except Exception as e:
        logger.error(f'Error reading PDF: {e}')
        raise

def parse_text(text: str) -> Dict[str, Any]:
    """
    Parse the extracted text and return structured data.
    
    Args:
        text: The text extracted from the PDF
    Returns:
        A dictionary containing structured data
    """
    doc = nlp(text)
    data = {}
    for ent in doc.ents:
        data[ent.label_] = ent.text
    logger.info('Parsed text into structured data.')
    return data

def save_to_db(data: Dict[str, Any]) -> None:
    """
    Simulated function to save structured data to a database.
    
    Args:
        data: Structured data to save
    Raises:
        Exception: If saving fails
    """
    try:
        # Simulate database save operation
        logger.info(f'Saving data to database: {data}')
        # Actual database logic would go here
    except Exception as e:
        logger.error(f'Failed to save data: {e}')
        raise

def process_pdf(file_path: str) -> None:
    """
    Main function to process the PDF file and extract structured data.
    
    Args:
        file_path: Path to the PDF file
    """
    try:
        validate_input(file_path)  # Validate the input
        text = extract_text_from_pdf(file_path)  # Extract text from PDF
        data = parse_text(text)  # Parse text into structured data
        save_to_db(data)  # Save data to the database
    except Exception as e:
        logger.error(f'Error processing PDF: {e}')  # Log any errors that occur

if __name__ == '__main__':
    # Example usage of the PDF processing function
    pdf_files = os.listdir(Config.pdf_directory)
    for pdf_file in pdf_files:
        full_path = os.path.join(Config.pdf_directory, pdf_file)
        process_pdf(full_path)  # Process each PDF file