"""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


def test_school_with_results_is_listed(sitemap):
    assert "/school/100001-alpha-primary" in sitemap


def test_school_with_no_results_and_no_ofsted_is_omitted(sitemap):
    # Nothing for a search result to say about it. Submitting it spends crawl
    # budget and drags the corpus-wide quality signal down.
    assert "/school/100002" not in sitemap


def test_no_invented_priority_or_changefreq(sitemap):
    # Google ignores both. They were noise dressed as signal.
    assert "<priority>" not in sitemap
    assert "<changefreq>" not in sitemap


def test_ofsted_date_becomes_lastmod(monkeypatch):
    from backend import app as app_module
    import datetime

    def _df():
        base = _schools_df()
        base.loc[base["urn"] == 100001, "ofsted_date"] = datetime.date(2024, 3, 14)
        return base

    monkeypatch.setattr(app_module, "load_school_data", _df)
    xml = app_module.build_sitemap()
    assert "<lastmod>2024-03-14</lastmod>" in xml


def test_no_lastmod_invented_when_date_unknown(monkeypatch):
    # An always-now lastmod is a claim Google learns to distrust. Absent
    # honestly means unknown.
    from backend import app as app_module

    def _df():
        df = _schools_df()
        df["ofsted_date"] = None
        return df

    monkeypatch.setattr(app_module, "load_school_data", _df)
    xml = app_module.build_sitemap()
    assert "<lastmod>" not in xml


def test_static_routes_are_listed(sitemap):
    for path in ("/", "/rankings", "/compare", "/admissions"):
        assert f"<loc>https://www.schoolcompare.co.uk{path}</loc>" in sitemap