History/scripts/regions.test.ts

/**
 * scripts/regions.test.ts — validation for the committed `public/regions.geo.json`.
 *
 * The dataset is REAL named sub-national administrative regions (Natural
 * Earth admin-1: states, provinces, governorates, oblasts, …) that the
 * coarsening step (`scripts/coarsen-regions.mjs`, v0.14) has merged down to a
 * ~100×100 km (10,000 km²) floor: every small non-island region was dissolved
 * into its nearest same-country neighbor, so the only regions left below the
 * floor are islands (no same-country sibling nearby). One feature per named
 * region, each carrying `properties = { name, parent }` where `parent` is the
 * country's ISO_A3 (the RegionMap key the map resolves ownership through).
 * Tiny or uncovered countries collapse to a single whole-country region
 * (`<ISO_A3>-01`).
 *
 * v0.17 (`scripts/fill-gaps.mjs`) additionally fills the no-one's-land left
 * between merged sub-regions: per country, the uncovered slivers of the
 * country's landmass (≥ 25 km²) were added as extra parts of the nearest
 * region, so the regions now cover the landmass almost completely (the
 * sampling test below measures that per country).
 *
 * This test is self-contained (no import of the generator) and deliberately
 * dependency-free — it re-implements the same planar area model the
 * generator/analysis use, so the area-based assertions measure the same
 * quantity:
 *
 *   x = lon · 111.32 · cos(midLat),  y = lat · 110.574  (km)
 *
 * with a shoelace per OUTER ring, each ring measured at its own mean latitude.
 * Outer rings only — a region's inner rings (holes) are lakes and are ignored
 * by design, the same way the coverage band already absorbed them.
 *
 * No geojson/@turf types are imported: the project keeps `@types/geojson`
 * OUT of the tsc program (see tsconfig `types`) so maplibre-gl's d.ts stays
 * in its loose (skipLibCheck) mode; the one coverage test below uses an
 * inline even-odd ray cast instead of a geometry library.
 *
 * It reads each file exactly once and runs in O(total vertices).
 */
import { readFileSync } from 'node:fs';
import path from 'node:path';
import { fileURLToPath } from 'node:url';
import { describe, expect, it } from 'vitest';

const here = path.dirname(fileURLToPath(import.meta.url));
const root = path.resolve(here, '..');

// --- area model (planar approximation; matches scripts/generate-regions.mjs) --
const KM_LON = 111.32;
const KM_LAT = 110.574;
const rad = (deg: number) => (deg * Math.PI) / 180;

type Ring = [number, number][];
type Geometry =
  | { type: 'Polygon'; coordinates: Ring[] }
  | { type: 'MultiPolygon'; coordinates: Ring[][] };

function ringAreaKm2(ring: Ring, midLat: number): number {
  const kx = KM_LON * Math.cos(rad(midLat));
  let a = 0;
  const n = ring.length;
  for (let i = 0; i < n; i++) {
    const [lon1, lat1] = ring[i];
    const [lon2, lat2] = ring[(i + 1) % n];
    a += lon1 * kx * (lat2 * KM_LAT) - lon2 * kx * (lat1 * KM_LAT);
  }
  return Math.abs(a / 2);
}

function outerRings(geom: Geometry): Ring[] {
  if (geom.type === 'Polygon') return [geom.coordinates[0]];
  if (geom.type === 'MultiPolygon') return geom.coordinates.map((p) => p[0]);
  return [];
}

/** Sum of a feature's outer-ring areas, each ring at its own mean latitude. */
function featureAreaKm2(geom: Geometry): number {
  let total = 0;
  for (const ring of outerRings(geom)) {
    let lat = 0;
    for (const [, la] of ring) lat += la;
    total += ringAreaKm2(ring, ring.length ? lat / ring.length : 0);
  }
  return total;
}

function median(nums: number[]): number {
  if (!nums.length) return 0;
  const s = [...nums].sort((a, b) => a - b);
  const m = Math.floor(s.length / 2);
  return s.length % 2 ? s[m] : (s[m - 1] + s[m]) / 2;
}

/** Raw min/max bbox [w, s, e, n] of a geometry (all coordinates). */
function rawBBox(geom: Geometry): [number, number, number, number] {
  const polys = geom.type === 'Polygon' ? [geom.coordinates] : geom.coordinates;
  let w = Infinity, s = Infinity, e = -Infinity, n = -Infinity;
  for (const poly of polys)
    for (const ring of poly)
      for (const [lo, la] of ring) {
        if (lo < w) w = lo;
        if (lo > e) e = lo;
        if (la < s) s = la;
        if (la > n) n = la;
      }
  return [w, s, e, n];
}

/**
 * Even-odd ray cast: is `[lon, lat]` inside `ring`? Planar, in raw lon/lat
 * space (no antimeridian handling — the polygons and the sample points live
 * in the same unwrapped space, so containment is mathematically consistent
 * even for countries that cross the date line). Used only as a fast,
 * deterministic coverage proxy (see the sampling test), never for areas.
 */
function pointInRing(pt: [number, number], ring: Ring): boolean {
  const [x, y] = pt;
  let inside = false;
  for (let i = 0, j = ring.length - 1; i < ring.length; j = i++) {
    const [xi, yi] = ring[i];
    const [xj, yj] = ring[j];
    if (yi > y !== yj > y && x < ((xj - xi) * (y - yi)) / (yj - yi) + xi) inside = !inside;
  }
  return inside;
}

/** Is a point inside a (Multi)Polygon: inside the outer ring, outside all holes. */
function pointInGeom(pt: [number, number], geom: Geometry): boolean {
  if (geom.type === 'Polygon') {
    if (!pointInRing(pt, geom.coordinates[0])) return false;
    return geom.coordinates.slice(1).every((h) => !pointInRing(pt, h));
  }
  if (geom.type === 'MultiPolygon')
    return geom.coordinates.some((p) => pointInGeom(pt, { type: 'Polygon', coordinates: p }));
  return false;
}
// ------------------------------------------------------------------------------

interface RegionFeature {
  type: 'Feature';
  id: string;
  properties: { name: string; parent: string };
  geometry: Geometry;
}
interface CountryFeature {
  type: 'Feature';
  id: string;
  properties: { name: string };
  geometry: Geometry;
}

// Read each file exactly once.
const regions = JSON.parse(
  readFileSync(path.join(root, 'public', 'regions.geo.json'), 'utf8'),
) as { type: 'FeatureCollection'; features: RegionFeature[] };
const countries = JSON.parse(
  readFileSync(path.join(root, 'public', 'countries.geo.json'), 'utf8'),
) as { type: 'FeatureCollection'; features: CountryFeature[] };

// Precompute once (O(total vertices)).
const countryIds = new Set(countries.features.map((c) => c.id));
const countryArea = new Map<string, number>();
for (const c of countries.features) countryArea.set(c.id, featureAreaKm2(c.geometry));
const regionArea = new Map<string, number>();
for (const f of regions.features) regionArea.set(f.id, featureAreaKm2(f.geometry));
const sumByParent = new Map<string, number>();
for (const f of regions.features)
  sumByParent.set(f.properties.parent, (sumByParent.get(f.properties.parent) ?? 0) + (regionArea.get(f.id) ?? 0));
const countByParent = new Map<string, number>();
for (const f of regions.features)
  countByParent.set(f.properties.parent, (countByParent.get(f.properties.parent) ?? 0) + 1);
// Raw bboxes for the sampling test's cheap reject (O(total vertices)).
const regionBB = new Map<string, [number, number, number, number]>();
for (const f of regions.features) regionBB.set(f.id, rawBBox(f.geometry));

// --- island/close-neighbor helpers (mirror scripts/coarsen-regions.mjs) ------

interface LonInt {
  a: number;
  b: number;
  full: boolean;
}
interface RegionBBox {
  latMin: number;
  latMax: number;
  lon: LonInt;
}

const COARSE_FLOOR_KM2 = 10_000; // the coarsener's ~100×100 km floor
const CLOSE_DEG = 0.2; // "spatially close" bbox gap (both lat and lon ≤ this)

/**
 * Unwrap a ring's longitudes to a continuous line (np.unwrap shortest-diff
 * scheme, anchored at the first vertex's [0,360) value). `full` when the
 * unwrapped span is ≥ 300° (a full-360° antimeridian band, e.g. Antarctica).
 * Must stay in sync with the coarsening script.
 */
function unwrapRing(ring: Ring) {
  const n = ring.length;
  const norm = (x: number) => ((x % 360) + 360) % 360;
  const u: number[] = new Array(n);
  u[0] = norm(ring[0][0]);
  for (let i = 1; i < n; i++) {
    // the previous UNWRAPPED value may lie outside [0,360); normalize it
    // before measuring the shortest signed difference, or a bogus ~180° jump
    // is inserted and the ring's span balloons.
    const a = norm(u[i - 1]);
    const b = norm(ring[i][0]);
    const d = (((b - a) % 360) + 540) % 360 - 180;
    u[i] = u[i - 1] + d;
  }
  let min = Infinity;
  let max = -Infinity;
  for (const v of u) {
    if (v < min) min = v;
    if (v > max) max = v;
  }
  return { lons: u, full: max - min >= 300 };
}

/**
 * Cyclic 1-D gap (degrees) between two tight longitude intervals in their own
 * unwrapped spaces; a `full` interval is close to everything.
 */
function lonGap(intA: LonInt, intB: LonInt): number {
  if (intA.full || intB.full) return 0;
  let best = Infinity;
  for (const k of [-1, 0, 1]) {
    const a2 = intB.a + 360 * k;
    const b2 = intB.b + 360 * k;
    const gap = intA.b < a2 ? a2 - intA.b : b2 < intA.a ? intA.a - b2 : 0;
    if (gap < best) best = gap;
  }
  return best;
}

// Per-region bbox in antimeridian-safe unwrapped longitude space.
const regionBBox = new Map<string, RegionBBox>();
for (const f of regions.features) {
  const polys = f.geometry.type === 'Polygon' ? [f.geometry.coordinates] : f.geometry.coordinates;
  let latMin = Infinity;
  let latMax = -Infinity;
  let a = Infinity;
  let b = -Infinity;
  let full = false;
  for (const poly of polys) {
    const outer = poly[0];
    for (const [, la] of outer) {
      if (la < latMin) latMin = la;
      if (la > latMax) latMax = la;
    }
    const { lons, full: fl } = unwrapRing(outer);
    if (fl) full = true;
    for (const v of lons) {
      if (v < a) a = v;
      if (v > b) b = v;
    }
  }
  regionBBox.set(f.id, { latMin, latMax, lon: { a, b, full } });
}

/** Bounding-box closeness (same definition the coarsening script uses). */
function bboxesClose(x: RegionBBox, y: RegionBBox): boolean {
  const latGap = x.latMax < y.latMin ? y.latMin - x.latMax : y.latMax < x.latMin ? x.latMin - y.latMax : 0;
  if (latGap > CLOSE_DEG) return false;
  return lonGap(x.lon, y.lon) <= CLOSE_DEG;
}

describe('regions.geo.json', () => {
  it('is a valid GeoJSON FeatureCollection of well-formed features', () => {
    expect(regions.type).toBe('FeatureCollection');
    expect(Array.isArray(regions.features)).toBe(true);
    expect(regions.features.length).toBeGreaterThan(0);
    for (const f of regions.features) {
      expect(f.type, `${f.id ?? '?'}: not a Feature`).toBe('Feature');
      expect(typeof f.id, `${f.id ?? '?'}: id must be a string`).toBe('string');
      expect(f.id.length, `${f.id ?? '?'}: empty id`).toBeGreaterThan(0);
      expect(typeof f.properties?.name, `${f.id}: missing name`).toBe('string');
      expect(f.properties.name.length, `${f.id}: empty name`).toBeGreaterThan(0);
      expect(typeof f.properties.parent, `${f.id}: missing parent`).toBe('string');
      expect(countryIds.has(f.properties.parent), `${f.id}: unknown parent ${f.properties.parent}`).toBe(true);
      const g = f.geometry;
      expect(
        !!g && (g.type === 'Polygon' || g.type === 'MultiPolygon'),
        `${f.id}: bad geometry type ${g?.type}`,
      ).toBe(true);
      if (g) {
        const polys = g.type === 'Polygon' ? [g.coordinates] : g.coordinates;
        for (const poly of polys)
          for (const ring of poly)
            expect(ring.length, `${f.id}: ring with ${ring.length} pts`).toBeGreaterThanOrEqual(3);
      }
    }
  });

  it('has globally unique feature ids (ISO 3166-2 disambiguated on within-country collision)', () => {
    const seen = new Set<string>();
    const dups = new Set<string>();
    for (const f of regions.features) {
      if (seen.has(f.id)) dups.add(f.id);
      seen.add(f.id);
    }
    expect(
      dups.size,
      `duplicate ids: ${[...dups].slice(0, 10).join(', ')}`,
    ).toBe(0);
    expect(seen.size).toBe(regions.features.length);
  });

  it('covers every one of the 177 countries with at least one region', () => {
    const counts = countries.features.map((c) => countByParent.get(c.id) ?? 0);
    for (const c of countries.features) {
      expect(countByParent.get(c.id) ?? 0, `country ${c.id} has no regions`).toBeGreaterThanOrEqual(1);
    }
    const min = Math.min(...counts);
    const max = Math.max(...counts);
    const med = median(counts);
    const maxCountry = [...countByParent.entries()].sort((a, b) => b[1] - a[1])[0];
    const maxCountryName = countries.features.find((c) => c.id === maxCountry[0])?.properties.name ?? '';
    console.log(
      `\n  per-country region count: min ${min} / median ${med} / max ${max}` +
        ` (max: ${maxCountry[0]} ${maxCountryName} with ${maxCountry[1]})`,
    );
  });

  it('has sane region areas: median >= 100 km2, and no non-Antarctica region >= 5,000,000 km2', () => {
    const areas = regions.features.map((f) => regionArea.get(f.id) ?? 0);
    const med = median(areas);
    const maxRegion = regions.features.reduce((m, f) => ((regionArea.get(f.id) ?? 0) > (regionArea.get(m.id) ?? 0) ? f : m));
    const minRegion = regions.features.reduce((m, f) => ((regionArea.get(f.id) ?? 0) < (regionArea.get(m.id) ?? 0) ? f : m));
    const tiny = areas.filter((a) => a < 1).length;
    // Antarctica (ATA) is a full-360° wrap ring, so the planar model can't
    // measure it (it reports ~21.8M km2 for a ~14M km2 landmass) — exempt it.
    for (const f of regions.features) {
      if (f.properties.parent === 'ATA') continue;
      const a = regionArea.get(f.id) ?? 0;
      expect(a < 5_000_000, `${f.id}: area ${Math.round(a).toLocaleString('en-US')} km2 is absurdly large`).toBe(true);
    }
    expect(med, `median region area ${med.toFixed(1)} km2 is too small`).toBeGreaterThanOrEqual(100);
    console.log(
      `\n  region area: min ${minRegion.id} (${minRegion.properties.name}) ≈ ${(regionArea.get(minRegion.id) ?? 0).toExponential(2)} km2` +
        ` / median ${med.toLocaleString('en-US')} km2` +
        ` / max ${maxRegion.id} (${maxRegion.properties.name}) ≈ ${Math.round(regionArea.get(maxRegion.id) ?? 0).toLocaleString('en-US')} km2` +
        ` — ${tiny} regions < 1 km2 (legit micro-regions: tiny islands, small urban districts, degenerate disputed enclaves)`,
    );
  });

  it('leaves only islands below the ~10,000 km2 coarsening floor (non-island small regions merged)', () => {
    // v0.14 coarsening: every region smaller than the floor that has a
    // same-country sibling within CLOSE_DEG of its bbox is dissolved into its
    // nearest such neighbor, so a below-floor region may only survive if it
    // is an island. Count the non-island residuals below the floor and allow
    // a small tolerance band (strictly < 1% of all regions) — the coarsener's
    // fixed point leaves none, and this catches a regression in the merge
    // logic (e.g. a broken neighbor test that exempts land regions) without
    // being brittle to one or two borderline cases.
    const smallNonIslands: string[] = [];
    let smallIslands = 0;
    let smallTotal = 0;
    for (const f of regions.features) {
      const a = regionArea.get(f.id) ?? 0;
      if (a >= COARSE_FLOOR_KM2) continue;
      smallTotal++;
      const bb = regionBBox.get(f.id)!;
      let hasNeighbor = false;
      for (const g of regions.features) {
        if (g.id === f.id || g.properties.parent !== f.properties.parent) continue;
        if (bboxesClose(bb, regionBBox.get(g.id)!)) {
          hasNeighbor = true;
          break;
        }
      }
      if (hasNeighbor) {
        smallNonIslands.push(`${f.id} (${Math.round(a)} km2)`);
      } else smallIslands++;
    }
    const frac = regions.features.length ? smallNonIslands.length / regions.features.length : 0;
    expect(
      frac < 0.01,
      `${smallNonIslands.length} non-island region(s) below the ${COARSE_FLOOR_KM2} km2 floor ` +
        `(${(100 * frac).toFixed(2)}% of all regions): ${smallNonIslands.slice(0, 10).join(', ')}`,
    ).toBe(true);
    console.log(
      `\n  below-floor regions: ${smallTotal} — ${smallIslands} islands (exempt, no same-country neighbor within ${CLOSE_DEG}°)` +
        ` / ${smallNonIslands.length} non-island residuals (must stay < 1% of all regions)`,
    );
  });

  it('leaves exactly one enclosed hole: KZ-KZY (the real Aral Sea), still large', () => {
    // v0.15 filled every small hole; v0.16 smoothing never touches holes; and
    // v0.17's gap-filler explicitly keeps the Aral hole (its centroid matches a
    // pre-existing hole and it lies inside another country's landmass) while
    // dropping phantom holes. So the whole file must contain exactly one hole,
    // on KZ-KZY, at a realistic size (~5,860 km2 planar; the real Aral has
    // shrunk to roughly this by the 2020s) — no new holes of any size.
    let holes = 0;
    let maxHole = 0;
    const holeIds: string[] = [];
    let kzkzyHoleArea = 0;
    for (const f of regions.features) {
      const polys = f.geometry.type === 'Polygon' ? [f.geometry.coordinates] : f.geometry.coordinates;
      for (const poly of polys) {
        for (let i = 1; i < poly.length; i++) {
          holes++;
          let lat = 0;
          for (const [, la] of poly[i]) lat += la;
          const area = ringAreaKm2(poly[i], poly[i].length ? lat / poly[i].length : 0);
          if (area > maxHole) maxHole = area;
          holeIds.push(f.id);
          if (f.id === 'KZ-KZY') kzkzyHoleArea = area;
        }
      }
    }
    expect(holes, `expected exactly 1 hole (KZ-KZY), found ${holes}: ${[...new Set(holeIds)].join(', ')}`).toBe(1);
    expect(holeIds, 'the one remaining hole is KZ-KZY').toEqual(['KZ-KZY']);
    expect(
      kzkzyHoleArea >= 5_000 && kzkzyHoleArea <= 7_000,
      `KZ-KZY hole is ${Math.round(kzkzyHoleArea).toLocaleString('en-US')} km2 — outside the 5,000–7,000 km2 Aral band`,
    ).toBe(true);
    console.log(
      `\n  holes: exactly 1 (KZ-KZY ≈ ${Math.round(kzkzyHoleArea).toLocaleString('en-US')} km2) — the Aral hole survived v0.17's fill`,
    );
  });

  it('sums to within [40%, 190%] of each country area (median in [70%, 130%])', () => {
    // The band is a planar-approximation sanity check. It is wider than a naive
    // [40%, 110%] because Natural Earth's admin-1 polygons are digitized
    // independently of the admin-0 country polygons (they are NOT clipped to
    // them). v0.17's gap fill removed the large UNDER-fills (the old minimum
    // was Brunei at ~52% — its regions now cover the landmass, ≈ 79%), but
    // the OVER-fill tail is a pre-existing admin-1 artifact: a few tiny island
    // nations (Vanuatu 178.9%, Solomon Is. 133%, Bahamas 129%) have admin-1
    // polygons that extend beyond their own country polygon, and the fill
    // only added area *inside* the country, so it can't shrink that tail.
    // The band brackets the measured [78.8%, 178.9%] with margin while still
    // catching a genuinely missing or doubled-up region.
    const ratios: number[] = [];
    let minRatio = Infinity;
    let maxRatio = -Infinity;
    let minId = '';
    let maxId = '';
    for (const c of countries.features) {
      const ca = countryArea.get(c.id) ?? 0;
      if (ca <= 0) continue;
      const ratio = (sumByParent.get(c.id) ?? 0) / ca;
      ratios.push(ratio);
      if (ratio < minRatio) { minRatio = ratio; minId = c.id; }
      if (ratio > maxRatio) { maxRatio = ratio; maxId = c.id; }
      expect(
        ratio >= 0.4 && ratio <= 1.9,
        `${c.id}: coverage ${(100 * ratio).toFixed(1)}% is outside [40%, 190%]`,
      ).toBe(true);
    }
    const medRatio = median(ratios);
    expect(
      medRatio >= 0.7 && medRatio <= 1.3,
      `median coverage ${(100 * medRatio).toFixed(1)}% is outside [70%, 130%]`,
    ).toBe(true);
    console.log(
      `\n  coverage range: min ${minId} ${(100 * minRatio).toFixed(1)}%` +
        ` / median ${(100 * medRatio).toFixed(1)}%` +
        ` / max ${maxId} ${(100 * maxRatio).toFixed(1)}% (band 40–190%)`,
    );
  });

  it('covers each country\'s landmass with no significant no-one\'s-land (v0.17 gap fill, grid-sampled)', () => {
    // The v0.17 fill (scripts/fill-gaps.mjs) assigned every uncovered sliver of
    // each country's landmass (≥ 25 km²) to its nearest region, so the residual
    // no-one's-land per country should be small everywhere. Measuring the
    // exact union is too slow, so this samples a 25×25 grid over each
    // country's raw bbox (skipping points outside the country polygon) and
    // counts the fraction of in-land sample points that fall in NONE of the
    // country's regions — a fast, deterministic proxy (same planar space,
    // inline even-odd ray cast; antimeridian-safe because points and polygons
    // share the raw coordinate space). Sampling over-counts coastline
    // mismatch (admin-0 vs admin-1 edges), so the thresholds are generous:
    // they catch a real regression (a whole sliver left unfilled) without
    // being brittle to digitization fuzz.
    const N = 25;
    const results: { id: string; name: string; frac: number; land: number }[] = [];
    for (const c of countries.features) {
      const [w, s, e, n] = rawBBox(c.geometry);
      if (e - w < 0.01 || n - s < 0.01) continue; // degenerate (point-like) country
      const regs = regions.features.filter((f) => f.properties.parent === c.id);
      let land = 0;
      let uncov = 0;
      for (let i = 0; i < N; i++) {
        const la = s + ((i + 0.5) / N) * (n - s);
        for (let j = 0; j < N; j++) {
          const lo = w + ((j + 0.5) / N) * (e - w);
          const pt: [number, number] = [lo, la];
          if (!pointInGeom(pt, c.geometry)) continue;
          land++;
          // cheap bbox reject first, then the full containment test
          if (!regs.some((f) => {
            const [rw, rs, re, rn] = regionBB.get(f.id)!;
            if (lo < rw || lo > re || la < rs || la > rn) return false;
            return pointInGeom(pt, f.geometry);
          }))
            uncov++;
        }
      }
      if (land >= 4) results.push({ id: c.id, name: c.properties.name, frac: uncov / land, land });
    }
    expect(results.length, `only ${results.length} countries sampled (expected ~176)`).toBeGreaterThanOrEqual(150);
    const fracs = results.map((r) => r.frac).sort((a, b) => a - b);
    const med = median(fracs);
    const p90 = fracs[Math.floor(fracs.length * 0.9)];
    const worst = results.reduce((m, r) => (r.frac > m.frac ? r : m));
    const over20 = results.filter((r) => r.frac > 0.2).sort((a, b) => b.frac - a.frac);
    expect(
      med <= 0.05,
      `median country gap ${(100 * med).toFixed(1)}% > 5% — significant no-one's-land remains`,
    ).toBe(true);
    expect(
      p90 <= 0.15,
      `p90 country gap ${(100 * p90).toFixed(1)}% > 15% — many countries have real gaps`,
    ).toBe(true);
    expect(
      worst.frac <= 0.4,
      `worst country ${worst.id} (${worst.name}) gap ${(100 * worst.frac).toFixed(1)}% > 40%`,
    ).toBe(true);
    expect(
      over20.length <= 3,
      `${over20.length} countries with > 20% gap: ${over20.map((r) => `${r.id} ${(100 * r.frac).toFixed(1)}%`).join(', ')}`,
    ).toBe(true);
    console.log(
      `\n  no-one's-land (grid-sampled, N=${N}): median ${(100 * med).toFixed(1)}% / p90 ${(100 * p90).toFixed(1)}%` +
        ` / max ${worst.id} (${worst.name}) ${(100 * worst.frac).toFixed(1)}%` +
        (over20.length ? ` — >20%: ${over20.map((r) => `${r.id} ${(100 * r.frac).toFixed(1)}%`).join(', ')}` : ' — no country > 20%'),
    );
  });

  it('is at the v0.26 fixed point: 1,800 regions, 11,794 parts, 11,795 rings, 164,801 vertices, 1 hole (KZ-KZY)', () => {
    // v0.17 (scripts/fill-gaps.mjs) APPENDED cleaned gap pieces to the v0.16
    // fixed point: it never moves an existing border, merges a part, or
    // removes a ring — it only adds new parts (+6,768: 5,026 → 11,794) and
    // keeps the single KZ-KZY hole. The v0.25 Arkhangel'sk split (#31,
    // scripts/split-arkhangel.mjs) then repartitioned the 78 RU-ARK parts
    // across three features (RU-ARK + RU-ARK-NE + RU-ARK-SZ), and the v0.26
    // band split (#41, scripts/split-arkhangel-band.mjs) repartitioned the
    // 33-part mainland again into RU-ARK + RU-PEO + RU-YAM. Both are pure
    // re-groupings: no part/ring/vertex moves, so only the region count
    // changed (1,796 → 1,798 → 1,800); the part/ring/vertex totals, the
    // per-feature ids/names/parents, and the feature order (the new features
    // sit immediately after RU-ARK-SZ) are as pinned below. Pinning the
    // signature guards against a non-idempotent or destructive re-run; both
    // stages are byte-deterministic per input and idempotent (a second run
    // changes nothing).
    const polysOf = (g: Geometry) => (g.type === 'Polygon' ? [g.coordinates] : g.coordinates);
    let verts = 0,
      rings = 0,
      parts = 0,
      holes = 0;
    const holeIds: string[] = [];
    for (const f of regions.features) {
      const polys = polysOf(f.geometry);
      parts += polys.length;
      for (const poly of polys) {
        rings += poly.length;
        holes += Math.max(0, poly.length - 1);
        if (poly.length > 1) holeIds.push(f.id);
        for (const ring of poly) verts += ring.length;
      }
    }
    expect(regions.features.length, 'region count').toBe(1800); // 1,796 + the #31 islands (+2) + the #41 band regions (+2)
    expect(parts, 'parts').toBe(11_794); // v0.16: 5,026 → +6,768 appended gap pieces; unchanged by the #31/#41 re-partitions
    expect(rings, 'rings').toBe(11_795); // every appended part is a single-ring polygon (+1 hole = KZ-KZY, pre-existing)
    expect(holes, 'holes').toBe(1); // the single KZ-KZY hole, unchanged
    expect(holeIds, 'the one remaining hole is KZ-KZY').toEqual(['KZ-KZY']);
    expect(verts, 'total vertices (incl. ring closure)').toBe(164_801); // v0.16: 111,175; unchanged by the #31/#41 re-partitions
    console.log(
      `\n  v0.26 fixed point: ${regions.features.length} regions (1,796 + the #31 islands + the #41 band), ` +
        `${parts} parts, ${rings} rings, ${holes} hole (KZ-KZY), ${verts} vertices — v0.17 topology preserved`,
    );
  });

  it('has the five Arkhangel\'sk-family features: #31 islands + #41 band (RU-ARK, New Earth, Severnaya Zemlya, Pechora, Yamal)', () => {
    // v0.25 (#31): the ~411,500 km² RU-ARK mega-region (a 78-part MultiPolygon
    // mixing mainland and far-north islands) was repartitioned by part
    // centroid into the mainland (RU-ARK, keeps its id/name/key), the Franz
    // Josef Land islets (RU-ARK-NE "New Earth", centroid lat ≥ 79.5) and the
    // Severnaya Zemlya islets (RU-ARK-SZ, centroid 76–79.5° N, lon ≥ 55°E).
    // v0.26 (#41): the 33-part mainland (post-#31) was repartitioned again —
    // the 5 lat < 68 parts stay RU-ARK (id/name/key unchanged), and the 28
    // lat ≥ 68 "Arctic-coast band" parts split into RU-PEO "Pechora" (the SW
    // Voronoi cell, 13 parts) and RU-YAM "Yamal" (the NE Voronoi cell, 15
    // parts). Pure re-grouping: all five keep parent RUS and all 78 original
    // parts of the pre-#31 feature are accounted for, verbatim.
    const byId = new Map(regions.features.map((f) => [f.id, f]));
    const ark = byId.get('RU-ARK');
    const ne = byId.get('RU-ARK-NE');
    const sz = byId.get('RU-ARK-SZ');
    const peo = byId.get('RU-PEO');
    const yam = byId.get('RU-YAM');
    for (const f of [ark, ne, sz, peo, yam]) {
      expect(f, `${f?.id ?? '?'} exists`).toBeDefined();
      expect(f!.properties.parent, `${f!.id} parent`).toBe('RUS');
      expect(f!.geometry.type, `${f!.id} geometry`).toBe('MultiPolygon');
    }
    expect(ark!.properties.name, 'RU-ARK keeps its name').toBe("Arkhangel'sk");
    expect(ne!.properties.name, 'RU-ARK-NE name').toBe('New Earth');
    expect(sz!.properties.name, 'RU-ARK-SZ name').toBe('Severnaya Zemlya');
    expect(peo!.properties.name, 'RU-PEO name').toBe('Pechora');
    expect(yam!.properties.name, 'RU-YAM name').toBe('Yamal');
    // the 78 parts of the pre-split feature are all accounted for, verbatim
    const countParts = (f: (typeof regions.features)[number]) =>
      f.geometry.type === 'MultiPolygon' ? f.geometry.coordinates.length : 1;
    expect(
      countParts(ark!) + countParts(ne!) + countParts(sz!) + countParts(peo!) + countParts(yam!),
      'total parts across the five features',
    ).toBe(78);
    // the #41 split: the mainland core keeps its 5 lat < 68 parts; the band's
    // 28 parts split 13 (Pechora) / 15 (Yamal)
    expect(countParts(ark!), 'RU-ARK core part count').toBe(5);
    expect(countParts(peo!), 'RU-PEO part count').toBe(13);
    expect(countParts(yam!), 'RU-YAM part count').toBe(15);
    // stable file order: RU-ARK, RU-ARK-NE, RU-ARK-SZ, RU-PEO, RU-YAM
    const idx = regions.features.findIndex((f) => f.id === 'RU-ARK');
    expect(regions.features[idx + 1]?.id).toBe('RU-ARK-NE');
    expect(regions.features[idx + 2]?.id).toBe('RU-ARK-SZ');
    expect(regions.features[idx + 3]?.id).toBe('RU-PEO');
    expect(regions.features[idx + 4]?.id).toBe('RU-YAM');
    console.log(
      `\n  #31 + #41: RU-ARK ${countParts(ark!)} parts (core), RU-ARK-NE ${countParts(ne!)} (New Earth), ` +
        `RU-ARK-SZ ${countParts(sz!)} (Severnaya Zemlya), RU-PEO ${countParts(peo!)} (Pechora), RU-YAM ${countParts(yam!)} (Yamal)`,
    );
  });
});