from langchain_community.document_loaders import Docx2txtLoader
from langchain.text_splitter import RecursiveCharacterTextSplitter
from app.core.config import settings
import time
import logging

logging.basicConfig(level=logging.INFO)

def log_latency(func):
    def wrapper(*args, **kwargs):
        start_time = time.time()
        result = func(*args, **kwargs)
        end_time = time.time()
        latency_ms = (end_time - start_time) * 1000
        logging.info(f"Latency for {func.__name__}: {latency_ms:.2f} ms")
        return result
    return wrapper

@log_latency
def docx_to_chunks(file_path: str) -> list[str]:
    """Convert a DOCX file to text chunks."""
    pages = Docx2txtLoader(file_path).load()
    chunks = RecursiveCharacterTextSplitter(
        chunk_size=settings.CHUNK_SIZE,
        chunk_overlap=settings.CHUNK_OVERLAP
    ).split_documents(pages)
    return [c.page_content for c in chunks]