src/data_loader.py

from __future__ import annotations

import json
from functools import lru_cache
from pathlib import Path
from typing import Dict, List, Tuple

import pandas as pd

from .models import Attraction


BASE_DIR = Path(__file__).parent.parent
DATA_DIR = BASE_DIR / "data"


@lru_cache(maxsize=1)
def load_nodes() -> Dict[str, Dict]:
    with (DATA_DIR / "park_nodes.json").open("r", encoding="utf-8") as f:
        return json.load(f)


@lru_cache(maxsize=1)
def load_edges() -> List[Dict]:
    with (DATA_DIR / "park_edges.json").open("r", encoding="utf-8") as f:
        return json.load(f)


@lru_cache(maxsize=1)
def load_attractions() -> Dict[str, Attraction]:
    with (DATA_DIR / "attractions.json").open("r", encoding="utf-8") as f:
        raw = json.load(f)
    return {a["id"]: Attraction.model_validate(a) for a in raw}


@lru_cache(maxsize=1)
def load_wait_history() -> pd.DataFrame:
    return pd.read_csv(DATA_DIR / "wait_time_history.csv")


def get_attraction_by_name(name: str) -> Attraction | None:
    name_lower = name.strip().lower()
    for attr in load_attractions().values():
        if attr.name.lower() == name_lower:
            return attr
    return None


def walking_distance_between(node_from: str, node_to: str) -> int:
    from .routing import shortest_path_distance

    return shortest_path_distance(node_from, node_to)


def summarize_dataset() -> Tuple[int, int, int]:
    nodes = load_nodes()
    edges = load_edges()
    attractions = load_attractions()
    return len(nodes), len(edges), len(attractions)