from app.services.pdf_processor import PDFProcessor
from app.utils.embeddings import EmbeddingService
from app.utils.schedule_manager import ScheduleManager
import os
import json

def main():
    # Setup services
    embedding_service = EmbeddingService()
    pdf_processor = PDFProcessor(embedding_service)

    # Load books from PDF directory
    pdf_dir = "/app/uploads"
    books = os.listdir(pdf_dir)
    books = [f for f in books if f.endswith('.pdf')]

    print(f"Found {len(books)} books")

    # Schedule manager
    schedule_manager = ScheduleManager("/app/schedules.json")

    # Process each book
    for book_name in books:
        book_path = os.path.join(pdf_dir, book_name)
        book_metadata = {
            "title": book_name.replace(".pdf", "").replace("-", " ").replace("_", " "),
            "author": "Desconhecido",
            "type": "book",
        }

        print(f"Processing: {book_name}")

        # Load and split PDF
        chunks = pdf_processor.load_and_split(book_path, book_metadata)

        # Embed chunks
        chunks_with_embeddings = pdf_processor.embed_chunks(chunks)

        # Save chunks to JSON for reference
        chunks_file = f"/app/index/{book_name}.json"
        os.makedirs("/app/index", exist_ok=True)

        with open(chunks_file, 'w') as f:
            json.dump(chunks_with_embeddings, f, indent=2)

        print(f"Saved {len(chunks)} chunks to {chunks_file}")

    print("Indexing complete!")

if __name__ == "__main__":
    main()