import bm25s
from typing import List, Dict
from pathlib import Path
from constants.constants import BM25_INDEX, PRODUCTS_DF

_FILE_PATH = Path(__file__).parents[2]


def search_bm25(query: str, top_k: int = 5) -> List[Dict[str, any]]:
    """
    Search products using BM25 lexical search (keyword matching).

    This is Stage 1: traditional keyword-based ranking without semantic understanding.
    Fast but misses semantic meaning and intent.

    Args:
        query: Search query string
        top_k: Number of top results to return (default: 5)

    Returns:
        List of dictionaries containing product information and scores
    """
    query_tokens = bm25s.tokenize(query, stopwords="en")
    results, scores = BM25_INDEX.retrieve(query_tokens, k=top_k)

    return [
        {
            "product_name": PRODUCTS_DF.iloc[idx]["Product Name"],
            "description": PRODUCTS_DF.iloc[idx]["Description"],
            "main_category": PRODUCTS_DF.iloc[idx]["MainCategory"],
            "secondary_category": PRODUCTS_DF.iloc[idx]["SecondaryCategory"],
            "score": float(score),
        }
        for idx, score in zip(results[0], scores[0])
    ]