from langchain_community.document_loaders.pdf import PyPDFLoader
from langchain.text_splitter import RecursiveCharacterTextSplitter
import os


# def load_split_docs(file_name: str) -> list:
#     file_path: str = os.path.join("documents", "pdfs", file_name)
#     loader = PyPDFLoader(file_path)
#     docs: list = loader.load()
#     chunk_size: int = 2000
#     chunk_overlap: int = 300
#
#     splitter = RecursiveCharacterTextSplitter(
#         chunk_size=chunk_size, chunk_overlap=chunk_overlap
#     )
#     docs_split: list = splitter.split_documents(docs)
#
#     return docs_split


def load_split_docs(file_name: str) -> list:
    # Obtener el directorio base del proyecto
    base_dir = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))

    # Construir la ruta absoluta al PDF
    file_path = os.path.join(base_dir, "documents", "pdfs", file_name)

    # Verificar si el archivo existe
    if not os.path.exists(file_path):
        print(f"Archivo no encontrado en: {file_path}")
        raise FileNotFoundError(f"No se encontró el archivo en: {file_path}")

    loader = PyPDFLoader(file_path)
    docs: list = loader.load()

    chunk_size: int = 2000
    chunk_overlap: int = 300
    splitter = RecursiveCharacterTextSplitter(
        chunk_size=chunk_size, chunk_overlap=chunk_overlap
    )
    docs_split: list = splitter.split_documents(docs)
    return docs_split