"""Tests for the place registry (spec 2026-08-21).

The registry is built from the in-memory school DataFrame, so these build a
small frame directly rather than touching a database.
"""

import numpy as np
import pandas as pd
import pytest

from backend.places import MIN_SCHOOLS, build_place_registry


def _df(rows: list[dict]) -> pd.DataFrame:
    base = {
        "year": 202425, "ofsted_grade": 2.0, "ofsted_date": None,
        "rwm_expected_pct": 60.0, "attainment_8_score": np.nan,
        "phase": "Primary", "postcode": "AA1 1AA",
    }
    return pd.DataFrame([{**base, **r} for r in rows])


def _town(n: int, town: str, la: str, start: int = 100000, **kw) -> list[dict]:
    """`start` offsets the URNs so two calls can describe different schools —
    the Bedford case needs two authorities' worth of distinct URNs in one
    town."""
    return [
        {"urn": start + i, "school_name": f"{town} School {i}",
         "town": town, "local_authority": la, **kw}
        for i in range(n)
    ]


def test_town_clearing_the_threshold_is_published():
    reg = build_place_registry(_df(_town(MIN_SCHOOLS, "Brentwood", "Essex")))
    assert "town:brentwood" in reg
    assert reg["town:brentwood"].name == "Brentwood"
    assert len(reg["town:brentwood"].urns) == MIN_SCHOOLS


def test_town_below_the_threshold_is_not_published():
    reg = build_place_registry(_df(_town(MIN_SCHOOLS - 1, "Crosby", "Sefton")))
    assert "town:crosby" not in reg


def test_a_town_below_threshold_still_names_its_authority():
    # The route layer needs somewhere to 301 to.
    reg = build_place_registry(_df(
        _town(MIN_SCHOOLS - 1, "Crosby", "Sefton") + _town(MIN_SCHOOLS, "Bootle", "Sefton")))
    assert "authority:sefton" in reg


def test_town_and_authority_of_the_same_name_are_separate_places():
    # 67 real collisions. Neither set contains the other: Bedford the town has
    # 104 schools, Bedford the authority 86, because postal towns cross
    # authority boundaries.
    rows = (_town(MIN_SCHOOLS, "Bedford", "Bedford")
            + _town(MIN_SCHOOLS, "Bedford", "Central Bedfordshire", start=200000))
    reg = build_place_registry(_df(rows))
    town, authority = reg["town:bedford"], reg["authority:bedford"]
    assert set(town.urns) != set(authority.urns)
    assert len(town.urns) == MIN_SCHOOLS * 2      # both authorities' schools
    assert len(authority.urns) == MIN_SCHOOLS     # only this authority's


def test_schools_without_publishable_data_do_not_count_toward_the_threshold():
    rows = _town(MIN_SCHOOLS, "Ghosttown", "Nowhere")
    for r in rows:
        r["rwm_expected_pct"] = np.nan
        r["ofsted_grade"] = np.nan
    reg = build_place_registry(_df(rows))
    assert "town:ghosttown" not in reg


def test_blank_town_is_ignored():
    rows = _town(MIN_SCHOOLS, "", "Essex")
    reg = build_place_registry(_df(rows))
    assert not any(k.startswith("town:") for k in reg)


def test_a_school_is_counted_once_even_with_several_years_of_rows():
    rows = []
    for year in (202324, 202425):
        rows += [{**r, "year": year} for r in _town(MIN_SCHOOLS, "Beccles", "Suffolk")]
    reg = build_place_registry(_df(rows))
    assert len(reg["town:beccles"].urns) == MIN_SCHOOLS