modules/pdf_processor.py

import fitz  # PyMuPDF
from modules.vector_to_text import extract_and_replace_vector_data
import os

def process_pdf(input_pdf_path):
    """
    Processes the PDF to replace vector data with editable text.
    """
    output_pdf_path = os.path.join("static/output", "processed.pdf")

    # Ensure output directory exists
    os.makedirs("static/output", exist_ok=True)

    # Open the PDF
    pdf_document = fitz.open(input_pdf_path)

    # Iterate through each page and process vector data
    for page_number in range(len(pdf_document)):
        page = pdf_document[page_number]
        text_layer = extract_and_replace_vector_data(page)  # Extract and replace vector data
        if text_layer:
            page.insert_text(fitz.Point(72, 72), text_layer, fontsize=12)  # Add editable text

    # Save the modified PDF
    pdf_document.save(output_pdf_path)
    pdf_document.close()

    return output_pdf_path