import polars as pl

from pipeline.transform.transform_poi import transform_grocery_retail_points


def test_transform_grocery_retail_points_outputs_chain_categories():
    raw = pl.DataFrame(
        {
            "id": [101, 102, 103],
            "retailer": ["Waitrose", "Sainsburys", "The Co-operative Group"],
            "fascia": ["Waitrose", "Sainsbury's Local", "Co-op Food"],
            "store_name": ["Waitrose Test", "Sainsbury''s Test", "Co-op Test"],
            "long_wgs": [-0.141, -0.142, -0.143],
            "lat_wgs": [51.515, 51.516, 51.517],
        }
    )

    pois = transform_grocery_retail_points(raw, min_chain_locations=1)

    assert pois.select(
        "id", "name", "category", "icon_category", "group", "emoji"
    ).to_dicts() == [
        {
            "id": "glx-101",
            "name": "Waitrose Test",
            "category": "Waitrose",
            "icon_category": "Waitrose",
            "group": "Groceries",
            "emoji": "🛒",
        },
        {
            "id": "glx-102",
            "name": "Sainsbury's Test",
            "category": "Sainsbury's",
            "icon_category": "Sainsbury's Local",
            "group": "Groceries",
            "emoji": "🛒",
        },
        {
            "id": "glx-103",
            "name": "Co-op Test",
            "category": "Co-op",
            "icon_category": "Co-op",
            "group": "Groceries",
            "emoji": "🛒",
        },
    ]


def test_transform_grocery_retail_points_keeps_fascia_icon_category():
    raw = pl.DataFrame(
        {
            "id": [101, 102, 103, 104],
            "retailer": ["Tesco", "Iceland", "Waitrose", "Morrisons"],
            "fascia": [
                "Tesco Express Esso",
                "The Food Warehouse",
                "Little Waitrose Shell",
                "Morrisons Daily",
            ],
            "store_name": [
                "Tesco Test Express",
                "Iceland Test Food Warehouse",
                "Little Waitrose Test",
                "Morrisons Daily Test",
            ],
            "long_wgs": [-0.141, -0.142, -0.143, -0.144],
            "lat_wgs": [51.515, 51.516, 51.517, 51.518],
        }
    )

    pois = transform_grocery_retail_points(raw, min_chain_locations=1)

    assert pois.select("category", "icon_category").to_dicts() == [
        {"category": "Tesco", "icon_category": "Tesco Express"},
        {"category": "Iceland", "icon_category": "The Food Warehouse"},
        {"category": "Waitrose", "icon_category": "Little Waitrose"},
        {"category": "Morrisons", "icon_category": "Morrisons Daily"},
    ]


def test_transform_grocery_retail_points_merges_cooperative_societies():
    raw = pl.DataFrame(
        {
            "id": [101, 102, 103],
            "retailer": [
                "Central England Co-operative",
                "Lincolnshire Co-operative",
                "The Southern Co-operative",
            ],
            "fascia": [
                "Central England Co-operative",
                "The Co-operative Food",
                None,
            ],
            "store_name": [
                "Central Co-op Test",
                "Lincolnshire Co-op Test",
                "Southern Co-op Test",
            ],
            "long_wgs": [-0.141, -0.142, -0.143],
            "lat_wgs": [51.515, 51.516, 51.517],
        }
    )

    pois = transform_grocery_retail_points(raw, min_chain_locations=1)

    assert pois.select("category", "icon_category").to_dicts() == [
        {"category": "Co-op", "icon_category": "Co-op"},
        {"category": "Co-op", "icon_category": "Co-op"},
        {"category": "Co-op", "icon_category": "Co-op"},
    ]


def test_transform_grocery_retail_points_accepts_base_fascias():
    raw = pl.DataFrame(
        {
            "id": [101, 102, 103, 104],
            "retailer": ["Aldi", "Asda", "Booths", "Whole Foods Market"],
            "fascia": ["Aldi", "Asda Superstore", "Booths", "Whole Foods Market"],
            "store_name": [
                "Aldi Test",
                "Asda Test Superstore",
                "Booths Test",
                "Whole Foods Test",
            ],
            "long_wgs": [-0.141, -0.142, -0.143, -0.144],
            "lat_wgs": [51.515, 51.516, 51.517, 51.518],
        }
    )

    pois = transform_grocery_retail_points(raw, min_chain_locations=1)

    assert pois.select("category", "icon_category").to_dicts() == [
        {"category": "Aldi", "icon_category": "Aldi"},
        {"category": "Asda", "icon_category": "Asda Superstore"},
        {"category": "Booths", "icon_category": "Booths"},
        {"category": "Whole Foods Market", "icon_category": "Whole Foods Market"},
    ]


def test_transform_grocery_retail_points_drops_invalid_rows():
    raw = pl.DataFrame(
        {
            "id": [101, 102],
            "retailer": ["Waitrose", ""],
            "fascia": ["Waitrose", "Tesco"],
            "store_name": ["Waitrose Test", "Tesco Test"],
            "long_wgs": [-0.141, -0.142],
            "lat_wgs": [51.515, 51.516],
        }
    )

    pois = transform_grocery_retail_points(raw, min_chain_locations=1)

    assert pois["category"].to_list() == ["Waitrose"]


def test_transform_grocery_retail_points_includes_unmapped_chains_with_five_locations():
    raw = pl.DataFrame(
        {
            "id": list(range(1, 10)),
            "retailer": ["Tian Tian"] * 5 + ["Corner Shop"] * 4,
            "fascia": ["Tian Tian Market"] * 5 + ["Corner Shop"] * 4,
            "store_name": [f"Store {i}" for i in range(1, 10)],
            "long_wgs": [-0.1] * 9,
            "lat_wgs": [51.5] * 9,
        }
    )

    pois = transform_grocery_retail_points(raw)

    assert pois.select("id", "category", "icon_category").to_dicts() == [
        {"id": "glx-1", "category": "Tian Tian", "icon_category": "Tian Tian"},
        {"id": "glx-2", "category": "Tian Tian", "icon_category": "Tian Tian"},
        {"id": "glx-3", "category": "Tian Tian", "icon_category": "Tian Tian"},
        {"id": "glx-4", "category": "Tian Tian", "icon_category": "Tian Tian"},
        {"id": "glx-5", "category": "Tian Tian", "icon_category": "Tian Tian"},
    ]