"""Tests for sitemap generation (spec 2026-08-20, workstream W1).

The sitemap is built from the in-memory school DataFrame, so these inject a
small frame via monkeypatch rather than touching a database.
"""

import numpy as np
import pandas as pd
import pytest


def _schools_df() -> pd.DataFrame:
    """Two schools: one with results, one with neither results nor Ofsted."""
    base = {
        "local_authority": "Testshire",
        "school_type": "Academy",
        "phase": "Primary",
        "year": 202425,
        "ofsted_date": None,
    }
    return pd.DataFrame(
        [
            {**base, "urn": 100001, "school_name": "Alpha Primary",
             "rwm_expected_pct": 62.0, "attainment_8_score": np.nan,
             "ofsted_grade": 2.0},
            {**base, "urn": 100002, "school_name": "Ghost Primary",
             "rwm_expected_pct": np.nan, "attainment_8_score": np.nan,
             "ofsted_grade": np.nan},
        ]
    )


@pytest.fixture()
def sitemap(monkeypatch) -> str:
    from backend import app as app_module

    monkeypatch.setattr(app_module, "load_school_data", _schools_df)
    return app_module.build_sitemap()


def test_every_loc_uses_the_www_host(sitemap):
    # The apex 301s to www. A <loc> that redirects burns a crawl per URL.
    assert "https://www.schoolcompare.co.uk" in sitemap
    assert "https://schoolcompare.co.uk" not in sitemap